Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1130/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-565/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1130/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128257
+}

checkpoint-1130/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

checkpoint-1130/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7303917d4e6e7c98254f48aa3ed8b6f73400ff008994d07946b2af4aab69cc
+size 4965805240

checkpoint-1130/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f0b5356894518d74f4947e14c78a9de62f6184fed07ee781c5cb4283afea75
+size 1459729952

checkpoint-1130/model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 6425505792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-1130/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26da79ce73e7359a80fccd496cc8e3521d895292f3129df1d9be9f0452552f41
+size 12851233054

checkpoint-1130/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d2daf201a5b2104ee0131a3cf19da2d195737616b18a3687442fa1c0d89844
+size 14244

checkpoint-1130/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652d7f31ed264debd818483debd72af34145424c130e723edd11ff1166dce1fc
+size 1064

checkpoint-1130/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]"
+}

checkpoint-1130/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
+size 17210102

checkpoint-1130/tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-1130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01c1f42af75afc36183509ddfc5eead46b5093e9cd4d9131f2cf31d96c1e836
+size 5432

checkpoint-565/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128257
+}

checkpoint-565/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

checkpoint-565/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e15aa8f8d0747952d4c13ad9bf8357ab07ba1c220b544ae14827b650bb12777
+size 4965805240

checkpoint-565/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4f15361c0803373a3b9998a735702b69a2fcfe3b6ed3766198e702dda9dfd9
+size 1459729952

checkpoint-565/model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 6425505792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-565/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93f02dfa4d63b41a021ba24d542d229502962ba5a6fbec4d5f3926c74c791a9
+size 12851233054

checkpoint-565/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de18027da110c6ae62420237f66a1e6ead2ecdeb694e63dede48b45681d09529
+size 14244

checkpoint-565/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e3a047d3c7a3799d528857c049b58da83330bbc420362c7dd0186b274982fd
+size 1064

checkpoint-565/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]"
+}

checkpoint-565/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
+size 17210102

checkpoint-565/tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-565/trainer_state.json

@@ -0,0 +1,3988 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49972360420121614,
+  "eval_steps": 1130,
+  "global_step": 565,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008844665561083472,
+      "grad_norm": 19.125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.7264,
+      "step": 1
+    },
+    {
+      "epoch": 0.0017689331122166944,
+      "grad_norm": 21.25,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.7435,
+      "step": 2
+    },
+    {
+      "epoch": 0.0026533996683250414,
+      "grad_norm": 17.625,
+      "learning_rate": 1.5e-06,
+      "loss": 2.6087,
+      "step": 3
+    },
+    {
+      "epoch": 0.0035378662244333887,
+      "grad_norm": 20.25,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.7812,
+      "step": 4
+    },
+    {
+      "epoch": 0.004422332780541736,
+      "grad_norm": 19.375,
+      "learning_rate": 2.5e-06,
+      "loss": 2.766,
+      "step": 5
+    },
+    {
+      "epoch": 0.005306799336650083,
+      "grad_norm": 16.875,
+      "learning_rate": 3e-06,
+      "loss": 2.6936,
+      "step": 6
+    },
+    {
+      "epoch": 0.00619126589275843,
+      "grad_norm": 16.75,
+      "learning_rate": 3.5e-06,
+      "loss": 2.5778,
+      "step": 7
+    },
+    {
+      "epoch": 0.0070757324488667775,
+      "grad_norm": 15.625,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.648,
+      "step": 8
+    },
+    {
+      "epoch": 0.007960199004975124,
+      "grad_norm": 16.0,
+      "learning_rate": 4.5e-06,
+      "loss": 2.546,
+      "step": 9
+    },
+    {
+      "epoch": 0.008844665561083471,
+      "grad_norm": 14.9375,
+      "learning_rate": 5e-06,
+      "loss": 2.4363,
+      "step": 10
+    },
+    {
+      "epoch": 0.009729132117191818,
+      "grad_norm": 12.875,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 2.3512,
+      "step": 11
+    },
+    {
+      "epoch": 0.010613598673300166,
+      "grad_norm": 12.5625,
+      "learning_rate": 6e-06,
+      "loss": 2.2891,
+      "step": 12
+    },
+    {
+      "epoch": 0.011498065229408513,
+      "grad_norm": 12.5,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 2.2531,
+      "step": 13
+    },
+    {
+      "epoch": 0.01238253178551686,
+      "grad_norm": 11.875,
+      "learning_rate": 7e-06,
+      "loss": 2.1287,
+      "step": 14
+    },
+    {
+      "epoch": 0.013266998341625208,
+      "grad_norm": 12.3125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.9634,
+      "step": 15
+    },
+    {
+      "epoch": 0.014151464897733555,
+      "grad_norm": 10.9375,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.932,
+      "step": 16
+    },
+    {
+      "epoch": 0.015035931453841902,
+      "grad_norm": 8.625,
+      "learning_rate": 8.5e-06,
+      "loss": 1.8733,
+      "step": 17
+    },
+    {
+      "epoch": 0.015920398009950248,
+      "grad_norm": 8.25,
+      "learning_rate": 9e-06,
+      "loss": 1.7971,
+      "step": 18
+    },
+    {
+      "epoch": 0.016804864566058595,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.5e-06,
+      "loss": 1.7309,
+      "step": 19
+    },
+    {
+      "epoch": 0.017689331122166942,
+      "grad_norm": 6.8125,
+      "learning_rate": 1e-05,
+      "loss": 1.5786,
+      "step": 20
+    },
+    {
+      "epoch": 0.01857379767827529,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.99997997403252e-06,
+      "loss": 1.6661,
+      "step": 21
+    },
+    {
+      "epoch": 0.019458264234383637,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.999919896290497e-06,
+      "loss": 1.5721,
+      "step": 22
+    },
+    {
+      "epoch": 0.020342730790491984,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.999819767255175e-06,
+      "loss": 1.5429,
+      "step": 23
+    },
+    {
+      "epoch": 0.02122719734660033,
+      "grad_norm": 3.5,
+      "learning_rate": 9.999679587728626e-06,
+      "loss": 1.6435,
+      "step": 24
+    },
+    {
+      "epoch": 0.02211166390270868,
+      "grad_norm": 4.25,
+      "learning_rate": 9.999499358833745e-06,
+      "loss": 1.5422,
+      "step": 25
+    },
+    {
+      "epoch": 0.022996130458817026,
+      "grad_norm": 3.59375,
+      "learning_rate": 9.999279082014233e-06,
+      "loss": 1.5343,
+      "step": 26
+    },
+    {
+      "epoch": 0.023880597014925373,
+      "grad_norm": 3.109375,
+      "learning_rate": 9.999018759034594e-06,
+      "loss": 1.5568,
+      "step": 27
+    },
+    {
+      "epoch": 0.02476506357103372,
+      "grad_norm": 3.328125,
+      "learning_rate": 9.998718391980113e-06,
+      "loss": 1.5014,
+      "step": 28
+    },
+    {
+      "epoch": 0.025649530127142068,
+      "grad_norm": 3.25,
+      "learning_rate": 9.998377983256851e-06,
+      "loss": 1.5582,
+      "step": 29
+    },
+    {
+      "epoch": 0.026533996683250415,
+      "grad_norm": 2.640625,
+      "learning_rate": 9.99799753559161e-06,
+      "loss": 1.5808,
+      "step": 30
+    },
+    {
+      "epoch": 0.027418463239358763,
+      "grad_norm": 2.796875,
+      "learning_rate": 9.997577052031922e-06,
+      "loss": 1.5662,
+      "step": 31
+    },
+    {
+      "epoch": 0.02830292979546711,
+      "grad_norm": 3.171875,
+      "learning_rate": 9.997116535946028e-06,
+      "loss": 1.3981,
+      "step": 32
+    },
+    {
+      "epoch": 0.029187396351575457,
+      "grad_norm": 2.59375,
+      "learning_rate": 9.996615991022835e-06,
+      "loss": 1.6638,
+      "step": 33
+    },
+    {
+      "epoch": 0.030071862907683804,
+      "grad_norm": 2.75,
+      "learning_rate": 9.996075421271905e-06,
+      "loss": 1.504,
+      "step": 34
+    },
+    {
+      "epoch": 0.03095632946379215,
+      "grad_norm": 2.84375,
+      "learning_rate": 9.99549483102341e-06,
+      "loss": 1.5365,
+      "step": 35
+    },
+    {
+      "epoch": 0.031840796019900496,
+      "grad_norm": 2.796875,
+      "learning_rate": 9.9948742249281e-06,
+      "loss": 1.5635,
+      "step": 36
+    },
+    {
+      "epoch": 0.03272526257600884,
+      "grad_norm": 2.734375,
+      "learning_rate": 9.994213607957273e-06,
+      "loss": 1.4878,
+      "step": 37
+    },
+    {
+      "epoch": 0.03360972913211719,
+      "grad_norm": 2.921875,
+      "learning_rate": 9.993512985402724e-06,
+      "loss": 1.4711,
+      "step": 38
+    },
+    {
+      "epoch": 0.03449419568822554,
+      "grad_norm": 2.75,
+      "learning_rate": 9.992772362876714e-06,
+      "loss": 1.5323,
+      "step": 39
+    },
+    {
+      "epoch": 0.035378662244333885,
+      "grad_norm": 2.890625,
+      "learning_rate": 9.991991746311916e-06,
+      "loss": 1.4929,
+      "step": 40
+    },
+    {
+      "epoch": 0.03626312880044223,
+      "grad_norm": 3.0,
+      "learning_rate": 9.99117114196137e-06,
+      "loss": 1.5633,
+      "step": 41
+    },
+    {
+      "epoch": 0.03714759535655058,
+      "grad_norm": 3.03125,
+      "learning_rate": 9.99031055639843e-06,
+      "loss": 1.4699,
+      "step": 42
+    },
+    {
+      "epoch": 0.03803206191265893,
+      "grad_norm": 3.015625,
+      "learning_rate": 9.989409996516726e-06,
+      "loss": 1.5251,
+      "step": 43
+    },
+    {
+      "epoch": 0.038916528468767274,
+      "grad_norm": 3.171875,
+      "learning_rate": 9.988469469530086e-06,
+      "loss": 1.5411,
+      "step": 44
+    },
+    {
+      "epoch": 0.03980099502487562,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.9874889829725e-06,
+      "loss": 1.5814,
+      "step": 45
+    },
+    {
+      "epoch": 0.04068546158098397,
+      "grad_norm": 3.328125,
+      "learning_rate": 9.986468544698041e-06,
+      "loss": 1.4796,
+      "step": 46
+    },
+    {
+      "epoch": 0.041569928137092316,
+      "grad_norm": 3.40625,
+      "learning_rate": 9.985408162880813e-06,
+      "loss": 1.4821,
+      "step": 47
+    },
+    {
+      "epoch": 0.04245439469320066,
+      "grad_norm": 3.859375,
+      "learning_rate": 9.984307846014891e-06,
+      "loss": 1.3797,
+      "step": 48
+    },
+    {
+      "epoch": 0.04333886124930901,
+      "grad_norm": 3.734375,
+      "learning_rate": 9.983167602914236e-06,
+      "loss": 1.457,
+      "step": 49
+    },
+    {
+      "epoch": 0.04422332780541736,
+      "grad_norm": 3.75,
+      "learning_rate": 9.981987442712634e-06,
+      "loss": 1.5753,
+      "step": 50
+    },
+    {
+      "epoch": 0.045107794361525705,
+      "grad_norm": 4.09375,
+      "learning_rate": 9.980767374863627e-06,
+      "loss": 1.4693,
+      "step": 51
+    },
+    {
+      "epoch": 0.04599226091763405,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.97950740914043e-06,
+      "loss": 1.3406,
+      "step": 52
+    },
+    {
+      "epoch": 0.0468767274737424,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.978207555635856e-06,
+      "loss": 1.5236,
+      "step": 53
+    },
+    {
+      "epoch": 0.04776119402985075,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.976867824762236e-06,
+      "loss": 1.4044,
+      "step": 54
+    },
+    {
+      "epoch": 0.048645660585959094,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.97548822725133e-06,
+      "loss": 1.516,
+      "step": 55
+    },
+    {
+      "epoch": 0.04953012714206744,
+      "grad_norm": 4.9375,
+      "learning_rate": 9.974068774154252e-06,
+      "loss": 1.5449,
+      "step": 56
+    },
+    {
+      "epoch": 0.05041459369817579,
+      "grad_norm": 5.75,
+      "learning_rate": 9.972609476841368e-06,
+      "loss": 1.4127,
+      "step": 57
+    },
+    {
+      "epoch": 0.051299060254284136,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.971110347002213e-06,
+      "loss": 1.4381,
+      "step": 58
+    },
+    {
+      "epoch": 0.05218352681039248,
+      "grad_norm": 6.34375,
+      "learning_rate": 9.9695713966454e-06,
+      "loss": 1.4088,
+      "step": 59
+    },
+    {
+      "epoch": 0.05306799336650083,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.967992638098517e-06,
+      "loss": 1.4954,
+      "step": 60
+    },
+    {
+      "epoch": 0.05395245992260918,
+      "grad_norm": 6.59375,
+      "learning_rate": 9.966374084008025e-06,
+      "loss": 1.4407,
+      "step": 61
+    },
+    {
+      "epoch": 0.054836926478717525,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.964715747339178e-06,
+      "loss": 1.4941,
+      "step": 62
+    },
+    {
+      "epoch": 0.05572139303482587,
+      "grad_norm": 5.40625,
+      "learning_rate": 9.963017641375888e-06,
+      "loss": 1.4971,
+      "step": 63
+    },
+    {
+      "epoch": 0.05660585959093422,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.961279779720641e-06,
+      "loss": 1.4614,
+      "step": 64
+    },
+    {
+      "epoch": 0.05749032614704257,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.959502176294384e-06,
+      "loss": 1.373,
+      "step": 65
+    },
+    {
+      "epoch": 0.058374792703150914,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.957684845336409e-06,
+      "loss": 1.378,
+      "step": 66
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.955827801404237e-06,
+      "loss": 1.4324,
+      "step": 67
+    },
+    {
+      "epoch": 0.06014372581536761,
+      "grad_norm": 4.65625,
+      "learning_rate": 9.95393105937351e-06,
+      "loss": 1.3723,
+      "step": 68
+    },
+    {
+      "epoch": 0.061028192371475956,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.951994634437866e-06,
+      "loss": 1.3495,
+      "step": 69
+    },
+    {
+      "epoch": 0.0619126589275843,
+      "grad_norm": 4.75,
+      "learning_rate": 9.950018542108818e-06,
+      "loss": 1.3664,
+      "step": 70
+    },
+    {
+      "epoch": 0.06279712548369265,
+      "grad_norm": 4.875,
+      "learning_rate": 9.948002798215632e-06,
+      "loss": 1.4035,
+      "step": 71
+    },
+    {
+      "epoch": 0.06368159203980099,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.945947418905193e-06,
+      "loss": 1.4816,
+      "step": 72
+    },
+    {
+      "epoch": 0.06456605859590935,
+      "grad_norm": 4.5,
+      "learning_rate": 9.943852420641888e-06,
+      "loss": 1.2219,
+      "step": 73
+    },
+    {
+      "epoch": 0.06545052515201769,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.941717820207461e-06,
+      "loss": 1.3755,
+      "step": 74
+    },
+    {
+      "epoch": 0.06633499170812604,
+      "grad_norm": 3.625,
+      "learning_rate": 9.939543634700891e-06,
+      "loss": 1.3874,
+      "step": 75
+    },
+    {
+      "epoch": 0.06721945826423438,
+      "grad_norm": 2.953125,
+      "learning_rate": 9.937329881538242e-06,
+      "loss": 1.4869,
+      "step": 76
+    },
+    {
+      "epoch": 0.06810392482034273,
+      "grad_norm": 3.0,
+      "learning_rate": 9.935076578452535e-06,
+      "loss": 1.2983,
+      "step": 77
+    },
+    {
+      "epoch": 0.06898839137645107,
+      "grad_norm": 2.234375,
+      "learning_rate": 9.932783743493599e-06,
+      "loss": 1.4231,
+      "step": 78
+    },
+    {
+      "epoch": 0.06987285793255943,
+      "grad_norm": 2.03125,
+      "learning_rate": 9.930451395027932e-06,
+      "loss": 1.4256,
+      "step": 79
+    },
+    {
+      "epoch": 0.07075732448866777,
+      "grad_norm": 2.109375,
+      "learning_rate": 9.928079551738542e-06,
+      "loss": 1.3877,
+      "step": 80
+    },
+    {
+      "epoch": 0.07164179104477612,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.925668232624819e-06,
+      "loss": 1.4216,
+      "step": 81
+    },
+    {
+      "epoch": 0.07252625760088446,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.923217457002356e-06,
+      "loss": 1.3535,
+      "step": 82
+    },
+    {
+      "epoch": 0.07341072415699282,
+      "grad_norm": 2.0,
+      "learning_rate": 9.92072724450282e-06,
+      "loss": 1.3751,
+      "step": 83
+    },
+    {
+      "epoch": 0.07429519071310116,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.91819761507377e-06,
+      "loss": 1.4323,
+      "step": 84
+    },
+    {
+      "epoch": 0.07517965726920951,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.915628588978522e-06,
+      "loss": 1.3007,
+      "step": 85
+    },
+    {
+      "epoch": 0.07606412382531785,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.913020186795967e-06,
+      "loss": 1.3573,
+      "step": 86
+    },
+    {
+      "epoch": 0.07694859038142621,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.910372429420416e-06,
+      "loss": 1.3889,
+      "step": 87
+    },
+    {
+      "epoch": 0.07783305693753455,
+      "grad_norm": 1.90625,
+      "learning_rate": 9.907685338061433e-06,
+      "loss": 1.3792,
+      "step": 88
+    },
+    {
+      "epoch": 0.0787175234936429,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.904958934243655e-06,
+      "loss": 1.3878,
+      "step": 89
+    },
+    {
+      "epoch": 0.07960199004975124,
+      "grad_norm": 1.9765625,
+      "learning_rate": 9.902193239806634e-06,
+      "loss": 1.4644,
+      "step": 90
+    },
+    {
+      "epoch": 0.0804864566058596,
+      "grad_norm": 2.390625,
+      "learning_rate": 9.899388276904653e-06,
+      "loss": 1.2637,
+      "step": 91
+    },
+    {
+      "epoch": 0.08137092316196794,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.89654406800655e-06,
+      "loss": 1.3179,
+      "step": 92
+    },
+    {
+      "epoch": 0.08225538971807629,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.893660635895542e-06,
+      "loss": 1.4912,
+      "step": 93
+    },
+    {
+      "epoch": 0.08313985627418463,
+      "grad_norm": 2.40625,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 1.3619,
+      "step": 94
+    },
+    {
+      "epoch": 0.08402432283029299,
+      "grad_norm": 2.0,
+      "learning_rate": 9.887776194738433e-06,
+      "loss": 1.4251,
+      "step": 95
+    },
+    {
+      "epoch": 0.08490878938640133,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.884775232828985e-06,
+      "loss": 1.4095,
+      "step": 96
+    },
+    {
+      "epoch": 0.08579325594250968,
+      "grad_norm": 1.96875,
+      "learning_rate": 9.881735141979554e-06,
+      "loss": 1.3442,
+      "step": 97
+    },
+    {
+      "epoch": 0.08667772249861802,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.878655946542443e-06,
+      "loss": 1.2661,
+      "step": 98
+    },
+    {
+      "epoch": 0.08756218905472637,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.8755376711832e-06,
+      "loss": 1.3718,
+      "step": 99
+    },
+    {
+      "epoch": 0.08844665561083472,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.872380340880416e-06,
+      "loss": 1.3015,
+      "step": 100
+    },
+    {
+      "epoch": 0.08933112216694307,
+      "grad_norm": 1.8671875,
+      "learning_rate": 9.869183980925531e-06,
+      "loss": 1.3145,
+      "step": 101
+    },
+    {
+      "epoch": 0.09021558872305141,
+      "grad_norm": 1.96875,
+      "learning_rate": 9.865948616922623e-06,
+      "loss": 1.3347,
+      "step": 102
+    },
+    {
+      "epoch": 0.09110005527915975,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.862674274788212e-06,
+      "loss": 1.3284,
+      "step": 103
+    },
+    {
+      "epoch": 0.0919845218352681,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.85936098075104e-06,
+      "loss": 1.3199,
+      "step": 104
+    },
+    {
+      "epoch": 0.09286898839137644,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.856008761351882e-06,
+      "loss": 1.1935,
+      "step": 105
+    },
+    {
+      "epoch": 0.0937534549474848,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.85261764344331e-06,
+      "loss": 1.3422,
+      "step": 106
+    },
+    {
+      "epoch": 0.09463792150359314,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.849187654189486e-06,
+      "loss": 1.411,
+      "step": 107
+    },
+    {
+      "epoch": 0.0955223880597015,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.845718821065957e-06,
+      "loss": 1.4758,
+      "step": 108
+    },
+    {
+      "epoch": 0.09640685461580983,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.842211171859418e-06,
+      "loss": 1.3477,
+      "step": 109
+    },
+    {
+      "epoch": 0.09729132117191819,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.838664734667496e-06,
+      "loss": 1.4211,
+      "step": 110
+    },
+    {
+      "epoch": 0.09817578772802653,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.835079537898523e-06,
+      "loss": 1.2801,
+      "step": 111
+    },
+    {
+      "epoch": 0.09906025428413488,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.831455610271315e-06,
+      "loss": 1.4228,
+      "step": 112
+    },
+    {
+      "epoch": 0.09994472084024322,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.827792980814934e-06,
+      "loss": 1.3096,
+      "step": 113
+    },
+    {
+      "epoch": 0.10082918739635158,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.82409167886846e-06,
+      "loss": 1.4389,
+      "step": 114
+    },
+    {
+      "epoch": 0.10171365395245992,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.820351734080754e-06,
+      "loss": 1.2514,
+      "step": 115
+    },
+    {
+      "epoch": 0.10259812050856827,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.81657317641022e-06,
+      "loss": 1.341,
+      "step": 116
+    },
+    {
+      "epoch": 0.10348258706467661,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.81275603612457e-06,
+      "loss": 1.3341,
+      "step": 117
+    },
+    {
+      "epoch": 0.10436705362078497,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.808900343800568e-06,
+      "loss": 1.3598,
+      "step": 118
+    },
+    {
+      "epoch": 0.1052515201768933,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.80500613032381e-06,
+      "loss": 1.2291,
+      "step": 119
+    },
+    {
+      "epoch": 0.10613598673300166,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.801073426888447e-06,
+      "loss": 1.3055,
+      "step": 120
+    },
+    {
+      "epoch": 0.10702045328911,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.79710226499696e-06,
+      "loss": 1.3064,
+      "step": 121
+    },
+    {
+      "epoch": 0.10790491984521836,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.79309267645989e-06,
+      "loss": 1.5078,
+      "step": 122
+    },
+    {
+      "epoch": 0.1087893864013267,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.789044693395593e-06,
+      "loss": 1.3984,
+      "step": 123
+    },
+    {
+      "epoch": 0.10967385295743505,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.784958348229978e-06,
+      "loss": 1.3424,
+      "step": 124
+    },
+    {
+      "epoch": 0.11055831951354339,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.780833673696255e-06,
+      "loss": 1.3416,
+      "step": 125
+    },
+    {
+      "epoch": 0.11144278606965174,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.776670702834662e-06,
+      "loss": 1.2557,
+      "step": 126
+    },
+    {
+      "epoch": 0.11232725262576009,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.772469468992206e-06,
+      "loss": 1.3391,
+      "step": 127
+    },
+    {
+      "epoch": 0.11321171918186844,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.768230005822394e-06,
+      "loss": 1.2914,
+      "step": 128
+    },
+    {
+      "epoch": 0.11409618573797678,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.76395234728497e-06,
+      "loss": 1.3263,
+      "step": 129
+    },
+    {
+      "epoch": 0.11498065229408513,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.759636527645633e-06,
+      "loss": 1.374,
+      "step": 130
+    },
+    {
+      "epoch": 0.11586511885019347,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 1.4286,
+      "step": 131
+    },
+    {
+      "epoch": 0.11674958540630183,
+      "grad_norm": 1.5,
+      "learning_rate": 9.750890543652169e-06,
+      "loss": 1.4717,
+      "step": 132
+    },
+    {
+      "epoch": 0.11763405196241017,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.74646044935676e-06,
+      "loss": 1.343,
+      "step": 133
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.741992334076309e-06,
+      "loss": 1.3997,
+      "step": 134
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.737486233602149e-06,
+      "loss": 1.3006,
+      "step": 135
+    },
+    {
+      "epoch": 0.12028745163073522,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.73294218402989e-06,
+      "loss": 1.319,
+      "step": 136
+    },
+    {
+      "epoch": 0.12117191818684356,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.728360221759125e-06,
+      "loss": 1.4336,
+      "step": 137
+    },
+    {
+      "epoch": 0.12205638474295191,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.723740383493146e-06,
+      "loss": 1.3181,
+      "step": 138
+    },
+    {
+      "epoch": 0.12294085129906025,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.719082706238645e-06,
+      "loss": 1.2935,
+      "step": 139
+    },
+    {
+      "epoch": 0.1238253178551686,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.714387227305422e-06,
+      "loss": 1.2438,
+      "step": 140
+    },
+    {
+      "epoch": 0.12470978441127695,
+      "grad_norm": 1.625,
+      "learning_rate": 9.709653984306077e-06,
+      "loss": 1.3358,
+      "step": 141
+    },
+    {
+      "epoch": 0.1255942509673853,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.70488301515572e-06,
+      "loss": 1.3511,
+      "step": 142
+    },
+    {
+      "epoch": 0.12647871752349366,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.700074358071658e-06,
+      "loss": 1.3239,
+      "step": 143
+    },
+    {
+      "epoch": 0.12736318407960198,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.695228051573098e-06,
+      "loss": 1.4606,
+      "step": 144
+    },
+    {
+      "epoch": 0.12824765063571034,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.69034413448083e-06,
+      "loss": 1.3747,
+      "step": 145
+    },
+    {
+      "epoch": 0.1291321171918187,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.68542264591692e-06,
+      "loss": 1.4193,
+      "step": 146
+    },
+    {
+      "epoch": 0.13001658374792704,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.680463625304393e-06,
+      "loss": 1.4057,
+      "step": 147
+    },
+    {
+      "epoch": 0.13090105030403537,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.675467112366925e-06,
+      "loss": 1.281,
+      "step": 148
+    },
+    {
+      "epoch": 0.13178551686014373,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.670433147128522e-06,
+      "loss": 1.325,
+      "step": 149
+    },
+    {
+      "epoch": 0.13266998341625208,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.665361769913187e-06,
+      "loss": 1.3501,
+      "step": 150
+    },
+    {
+      "epoch": 0.13355444997236043,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.660253021344618e-06,
+      "loss": 1.3012,
+      "step": 151
+    },
+    {
+      "epoch": 0.13443891652846876,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.65510694234587e-06,
+      "loss": 1.4016,
+      "step": 152
+    },
+    {
+      "epoch": 0.13532338308457711,
+      "grad_norm": 1.625,
+      "learning_rate": 9.649923574139023e-06,
+      "loss": 1.4438,
+      "step": 153
+    },
+    {
+      "epoch": 0.13620784964068547,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.644702958244865e-06,
+      "loss": 1.1223,
+      "step": 154
+    },
+    {
+      "epoch": 0.1370923161967938,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.639445136482549e-06,
+      "loss": 1.3927,
+      "step": 155
+    },
+    {
+      "epoch": 0.13797678275290215,
+      "grad_norm": 1.75,
+      "learning_rate": 9.634150150969259e-06,
+      "loss": 1.2505,
+      "step": 156
+    },
+    {
+      "epoch": 0.1388612493090105,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.628818044119884e-06,
+      "loss": 1.4761,
+      "step": 157
+    },
+    {
+      "epoch": 0.13974571586511886,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.623448858646658e-06,
+      "loss": 1.3678,
+      "step": 158
+    },
+    {
+      "epoch": 0.14063018242122718,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.618042637558838e-06,
+      "loss": 1.2537,
+      "step": 159
+    },
+    {
+      "epoch": 0.14151464897733554,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.612599424162344e-06,
+      "loss": 1.3916,
+      "step": 160
+    },
+    {
+      "epoch": 0.1423991155334439,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.607119262059426e-06,
+      "loss": 1.384,
+      "step": 161
+    },
+    {
+      "epoch": 0.14328358208955225,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.601602195148299e-06,
+      "loss": 1.2958,
+      "step": 162
+    },
+    {
+      "epoch": 0.14416804864566057,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.596048267622806e-06,
+      "loss": 1.2946,
+      "step": 163
+    },
+    {
+      "epoch": 0.14505251520176893,
+      "grad_norm": 1.5,
+      "learning_rate": 9.590457523972055e-06,
+      "loss": 1.3237,
+      "step": 164
+    },
+    {
+      "epoch": 0.14593698175787728,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.584830008980068e-06,
+      "loss": 1.3629,
+      "step": 165
+    },
+    {
+      "epoch": 0.14682144831398564,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.579165767725416e-06,
+      "loss": 1.401,
+      "step": 166
+    },
+    {
+      "epoch": 0.14770591487009396,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.573464845580864e-06,
+      "loss": 1.3616,
+      "step": 167
+    },
+    {
+      "epoch": 0.14859038142620232,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 1.3525,
+      "step": 168
+    },
+    {
+      "epoch": 0.14947484798231067,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.561953141581895e-06,
+      "loss": 1.2719,
+      "step": 169
+    },
+    {
+      "epoch": 0.15035931453841903,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.55614245194068e-06,
+      "loss": 1.4089,
+      "step": 170
+    },
+    {
+      "epoch": 0.15124378109452735,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.550295265835235e-06,
+      "loss": 1.2775,
+      "step": 171
+    },
+    {
+      "epoch": 0.1521282476506357,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.544411630103782e-06,
+      "loss": 1.4217,
+      "step": 172
+    },
+    {
+      "epoch": 0.15301271420674406,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.538491591876522e-06,
+      "loss": 1.3348,
+      "step": 173
+    },
+    {
+      "epoch": 0.15389718076285241,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.53253519857525e-06,
+      "loss": 1.2124,
+      "step": 174
+    },
+    {
+      "epoch": 0.15478164731896074,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.526542497912984e-06,
+      "loss": 1.3922,
+      "step": 175
+    },
+    {
+      "epoch": 0.1556661138750691,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.520513537893574e-06,
+      "loss": 1.1851,
+      "step": 176
+    },
+    {
+      "epoch": 0.15655058043117745,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.514448366811322e-06,
+      "loss": 1.2694,
+      "step": 177
+    },
+    {
+      "epoch": 0.1574350469872858,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.508347033250597e-06,
+      "loss": 1.3177,
+      "step": 178
+    },
+    {
+      "epoch": 0.15831951354339413,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.502209586085444e-06,
+      "loss": 1.3924,
+      "step": 179
+    },
+    {
+      "epoch": 0.15920398009950248,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.496036074479184e-06,
+      "loss": 1.4299,
+      "step": 180
+    },
+    {
+      "epoch": 0.16008844665561084,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.48982654788404e-06,
+      "loss": 1.3324,
+      "step": 181
+    },
+    {
+      "epoch": 0.1609729132117192,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.48358105604072e-06,
+      "loss": 1.3089,
+      "step": 182
+    },
+    {
+      "epoch": 0.16185737976782752,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.47729964897803e-06,
+      "loss": 1.2949,
+      "step": 183
+    },
+    {
+      "epoch": 0.16274184632393587,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.470982377012475e-06,
+      "loss": 1.3925,
+      "step": 184
+    },
+    {
+      "epoch": 0.16362631288004423,
+      "grad_norm": 1.5,
+      "learning_rate": 9.464629290747844e-06,
+      "loss": 1.334,
+      "step": 185
+    },
+    {
+      "epoch": 0.16451077943615258,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.458240441074818e-06,
+      "loss": 1.3127,
+      "step": 186
+    },
+    {
+      "epoch": 0.1653952459922609,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.451815879170556e-06,
+      "loss": 1.3017,
+      "step": 187
+    },
+    {
+      "epoch": 0.16627971254836926,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.445355656498284e-06,
+      "loss": 1.2663,
+      "step": 188
+    },
+    {
+      "epoch": 0.16716417910447762,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.438859824806889e-06,
+      "loss": 1.3447,
+      "step": 189
+    },
+    {
+      "epoch": 0.16804864566058597,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.432328436130493e-06,
+      "loss": 1.2753,
+      "step": 190
+    },
+    {
+      "epoch": 0.1689331122166943,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.425761542788049e-06,
+      "loss": 1.2451,
+      "step": 191
+    },
+    {
+      "epoch": 0.16981757877280265,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.419159197382913e-06,
+      "loss": 1.2753,
+      "step": 192
+    },
+    {
+      "epoch": 0.170702045328911,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.412521452802425e-06,
+      "loss": 1.2273,
+      "step": 193
+    },
+    {
+      "epoch": 0.17158651188501936,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.40584836221749e-06,
+      "loss": 1.1869,
+      "step": 194
+    },
+    {
+      "epoch": 0.1724709784411277,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.399139979082148e-06,
+      "loss": 1.3873,
+      "step": 195
+    },
+    {
+      "epoch": 0.17335544499723604,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.39239635713314e-06,
+      "loss": 1.3526,
+      "step": 196
+    },
+    {
+      "epoch": 0.1742399115533444,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.38561755038949e-06,
+      "loss": 1.2479,
+      "step": 197
+    },
+    {
+      "epoch": 0.17512437810945275,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.37880361315206e-06,
+      "loss": 1.3395,
+      "step": 198
+    },
+    {
+      "epoch": 0.17600884466556108,
+      "grad_norm": 1.5,
+      "learning_rate": 9.37195460000313e-06,
+      "loss": 1.3771,
+      "step": 199
+    },
+    {
+      "epoch": 0.17689331122166943,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.365070565805941e-06,
+      "loss": 1.3621,
+      "step": 200
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.358151565704275e-06,
+      "loss": 1.2497,
+      "step": 201
+    },
+    {
+      "epoch": 0.17866224433388614,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.351197655121995e-06,
+      "loss": 1.3137,
+      "step": 202
+    },
+    {
+      "epoch": 0.17954671088999447,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.34420888976262e-06,
+      "loss": 1.2582,
+      "step": 203
+    },
+    {
+      "epoch": 0.18043117744610282,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.337185325608864e-06,
+      "loss": 1.3406,
+      "step": 204
+    },
+    {
+      "epoch": 0.18131564400221117,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.3131,
+      "step": 205
+    },
+    {
+      "epoch": 0.1822001105583195,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.323034026242378e-06,
+      "loss": 1.2423,
+      "step": 206
+    },
+    {
+      "epoch": 0.18308457711442785,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.315906404387032e-06,
+      "loss": 1.4379,
+      "step": 207
+    },
+    {
+      "epoch": 0.1839690436705362,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.308744210451167e-06,
+      "loss": 1.3036,
+      "step": 208
+    },
+    {
+      "epoch": 0.18485351022664456,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.301547501806725e-06,
+      "loss": 1.2342,
+      "step": 209
+    },
+    {
+      "epoch": 0.1857379767827529,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.294316336102132e-06,
+      "loss": 1.3907,
+      "step": 210
+    },
+    {
+      "epoch": 0.18662244333886124,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.287050771261818e-06,
+      "loss": 1.3667,
+      "step": 211
+    },
+    {
+      "epoch": 0.1875069098949696,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.279750865485772e-06,
+      "loss": 1.413,
+      "step": 212
+    },
+    {
+      "epoch": 0.18839137645107795,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.272416677249067e-06,
+      "loss": 1.4096,
+      "step": 213
+    },
+    {
+      "epoch": 0.18927584300718628,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.265048265301385e-06,
+      "loss": 1.4081,
+      "step": 214
+    },
+    {
+      "epoch": 0.19016030956329463,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.257645688666557e-06,
+      "loss": 1.2725,
+      "step": 215
+    },
+    {
+      "epoch": 0.191044776119403,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.25020900664209e-06,
+      "loss": 1.3413,
+      "step": 216
+    },
+    {
+      "epoch": 0.19192924267551134,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.242738278798682e-06,
+      "loss": 1.2653,
+      "step": 217
+    },
+    {
+      "epoch": 0.19281370923161967,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.235233564979756e-06,
+      "loss": 1.291,
+      "step": 218
+    },
+    {
+      "epoch": 0.19369817578772802,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.227694925300972e-06,
+      "loss": 1.2319,
+      "step": 219
+    },
+    {
+      "epoch": 0.19458264234383638,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.220122420149753e-06,
+      "loss": 1.4077,
+      "step": 220
+    },
+    {
+      "epoch": 0.19546710889994473,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.212516110184794e-06,
+      "loss": 1.3852,
+      "step": 221
+    },
+    {
+      "epoch": 0.19635157545605306,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.204876056335584e-06,
+      "loss": 1.3,
+      "step": 222
+    },
+    {
+      "epoch": 0.1972360420121614,
+      "grad_norm": 1.5,
+      "learning_rate": 9.197202319801908e-06,
+      "loss": 1.2786,
+      "step": 223
+    },
+    {
+      "epoch": 0.19812050856826977,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.18949496205337e-06,
+      "loss": 1.3455,
+      "step": 224
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.181754044828882e-06,
+      "loss": 1.3383,
+      "step": 225
+    },
+    {
+      "epoch": 0.19988944168048645,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.17397963013619e-06,
+      "loss": 1.3784,
+      "step": 226
+    },
+    {
+      "epoch": 0.2007739082365948,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.166171780251365e-06,
+      "loss": 1.3286,
+      "step": 227
+    },
+    {
+      "epoch": 0.20165837479270315,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.158330557718304e-06,
+      "loss": 1.2621,
+      "step": 228
+    },
+    {
+      "epoch": 0.2025428413488115,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.150456025348236e-06,
+      "loss": 1.2498,
+      "step": 229
+    },
+    {
+      "epoch": 0.20342730790491984,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.142548246219212e-06,
+      "loss": 1.3013,
+      "step": 230
+    },
+    {
+      "epoch": 0.2043117744610282,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.134607283675601e-06,
+      "loss": 1.406,
+      "step": 231
+    },
+    {
+      "epoch": 0.20519624101713654,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.12663320132759e-06,
+      "loss": 1.3578,
+      "step": 232
+    },
+    {
+      "epoch": 0.2060807075732449,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.118626063050661e-06,
+      "loss": 1.282,
+      "step": 233
+    },
+    {
+      "epoch": 0.20696517412935322,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.110585932985095e-06,
+      "loss": 1.2806,
+      "step": 234
+    },
+    {
+      "epoch": 0.20784964068546158,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.102512875535439e-06,
+      "loss": 1.3169,
+      "step": 235
+    },
+    {
+      "epoch": 0.20873410724156993,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.09440695537001e-06,
+      "loss": 1.2739,
+      "step": 236
+    },
+    {
+      "epoch": 0.2096185737976783,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.086268237420368e-06,
+      "loss": 1.3251,
+      "step": 237
+    },
+    {
+      "epoch": 0.2105030403537866,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.07809678688079e-06,
+      "loss": 1.4005,
+      "step": 238
+    },
+    {
+      "epoch": 0.21138750690989497,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.069892669207757e-06,
+      "loss": 1.291,
+      "step": 239
+    },
+    {
+      "epoch": 0.21227197346600332,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.06165595011943e-06,
+      "loss": 1.3164,
+      "step": 240
+    },
+    {
+      "epoch": 0.21315644002211168,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.053386695595114e-06,
+      "loss": 1.244,
+      "step": 241
+    },
+    {
+      "epoch": 0.21404090657822,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 1.3773,
+      "step": 242
+    },
+    {
+      "epoch": 0.21492537313432836,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.036750845458323e-06,
+      "loss": 1.5006,
+      "step": 243
+    },
+    {
+      "epoch": 0.2158098396904367,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.028384383105444e-06,
+      "loss": 1.1597,
+      "step": 244
+    },
+    {
+      "epoch": 0.21669430624654507,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.019985651834703e-06,
+      "loss": 1.352,
+      "step": 245
+    },
+    {
+      "epoch": 0.2175787728026534,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.01155471892319e-06,
+      "loss": 1.3903,
+      "step": 246
+    },
+    {
+      "epoch": 0.21846323935876175,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.00309165190594e-06,
+      "loss": 1.2875,
+      "step": 247
+    },
+    {
+      "epoch": 0.2193477059148701,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.994596518575393e-06,
+      "loss": 1.3835,
+      "step": 248
+    },
+    {
+      "epoch": 0.22023217247097845,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.986069386980855e-06,
+      "loss": 1.1993,
+      "step": 249
+    },
+    {
+      "epoch": 0.22111663902708678,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.97751032542795e-06,
+      "loss": 1.2783,
+      "step": 250
+    },
+    {
+      "epoch": 0.22200110558319514,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.968919402478076e-06,
+      "loss": 1.2083,
+      "step": 251
+    },
+    {
+      "epoch": 0.2228855721393035,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.960296686947846e-06,
+      "loss": 1.3347,
+      "step": 252
+    },
+    {
+      "epoch": 0.22377003869541182,
+      "grad_norm": 1.5,
+      "learning_rate": 8.95164224790855e-06,
+      "loss": 1.3392,
+      "step": 253
+    },
+    {
+      "epoch": 0.22465450525152017,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.942956154685596e-06,
+      "loss": 1.2584,
+      "step": 254
+    },
+    {
+      "epoch": 0.22553897180762852,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.93423847685795e-06,
+      "loss": 1.3409,
+      "step": 255
+    },
+    {
+      "epoch": 0.22642343836373688,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.925489284257587e-06,
+      "loss": 1.15,
+      "step": 256
+    },
+    {
+      "epoch": 0.2273079049198452,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.916708646968924e-06,
+      "loss": 1.3322,
+      "step": 257
+    },
+    {
+      "epoch": 0.22819237147595356,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.907896635328262e-06,
+      "loss": 1.2895,
+      "step": 258
+    },
+    {
+      "epoch": 0.2290768380320619,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.899053319923228e-06,
+      "loss": 1.3535,
+      "step": 259
+    },
+    {
+      "epoch": 0.22996130458817027,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.890178771592198e-06,
+      "loss": 1.2847,
+      "step": 260
+    },
+    {
+      "epoch": 0.2308457711442786,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.881273061423741e-06,
+      "loss": 1.1571,
+      "step": 261
+    },
+    {
+      "epoch": 0.23173023770038695,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.87233626075604e-06,
+      "loss": 1.3256,
+      "step": 262
+    },
+    {
+      "epoch": 0.2326147042564953,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.863368441176326e-06,
+      "loss": 1.2712,
+      "step": 263
+    },
+    {
+      "epoch": 0.23349917081260366,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.854369674520306e-06,
+      "loss": 1.1101,
+      "step": 264
+    },
+    {
+      "epoch": 0.23438363736871198,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.845340032871584e-06,
+      "loss": 1.3047,
+      "step": 265
+    },
+    {
+      "epoch": 0.23526810392482034,
+      "grad_norm": 1.5,
+      "learning_rate": 8.836279588561084e-06,
+      "loss": 1.4033,
+      "step": 266
+    },
+    {
+      "epoch": 0.2361525704809287,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.827188414166468e-06,
+      "loss": 1.1166,
+      "step": 267
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 1.625,
+      "learning_rate": 8.818066582511564e-06,
+      "loss": 1.4317,
+      "step": 268
+    },
+    {
+      "epoch": 0.23792150359314537,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.808914166665773e-06,
+      "loss": 1.2804,
+      "step": 269
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.799731239943488e-06,
+      "loss": 1.2792,
+      "step": 270
+    },
+    {
+      "epoch": 0.23969043670536208,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.790517875903506e-06,
+      "loss": 1.24,
+      "step": 271
+    },
+    {
+      "epoch": 0.24057490326147044,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.781274148348438e-06,
+      "loss": 1.4203,
+      "step": 272
+    },
+    {
+      "epoch": 0.24145936981757876,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.772000131324117e-06,
+      "loss": 1.277,
+      "step": 273
+    },
+    {
+      "epoch": 0.24234383637368712,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.762695899119012e-06,
+      "loss": 1.3946,
+      "step": 274
+    },
+    {
+      "epoch": 0.24322830292979547,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.753361526263622e-06,
+      "loss": 1.2966,
+      "step": 275
+    },
+    {
+      "epoch": 0.24411276948590382,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.743997087529886e-06,
+      "loss": 1.2638,
+      "step": 276
+    },
+    {
+      "epoch": 0.24499723604201215,
+      "grad_norm": 1.765625,
+      "learning_rate": 8.734602657930582e-06,
+      "loss": 1.2616,
+      "step": 277
+    },
+    {
+      "epoch": 0.2458817025981205,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.725178312718727e-06,
+      "loss": 1.2486,
+      "step": 278
+    },
+    {
+      "epoch": 0.24676616915422886,
+      "grad_norm": 1.640625,
+      "learning_rate": 8.715724127386971e-06,
+      "loss": 1.2472,
+      "step": 279
+    },
+    {
+      "epoch": 0.2476506357103372,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.706240177667003e-06,
+      "loss": 1.351,
+      "step": 280
+    },
+    {
+      "epoch": 0.24853510226644554,
+      "grad_norm": 1.6015625,
+      "learning_rate": 8.696726539528924e-06,
+      "loss": 1.4451,
+      "step": 281
+    },
+    {
+      "epoch": 0.2494195688225539,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.687183289180659e-06,
+      "loss": 1.309,
+      "step": 282
+    },
+    {
+      "epoch": 0.25030403537866225,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.67761050306734e-06,
+      "loss": 1.4025,
+      "step": 283
+    },
+    {
+      "epoch": 0.2511885019347706,
+      "grad_norm": 1.5,
+      "learning_rate": 8.668008257870684e-06,
+      "loss": 1.2973,
+      "step": 284
+    },
+    {
+      "epoch": 0.25207296849087896,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.658376630508391e-06,
+      "loss": 1.3479,
+      "step": 285
+    },
+    {
+      "epoch": 0.2529574350469873,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.648715698133529e-06,
+      "loss": 1.279,
+      "step": 286
+    },
+    {
+      "epoch": 0.2538419016030956,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.639025538133899e-06,
+      "loss": 1.3607,
+      "step": 287
+    },
+    {
+      "epoch": 0.25472636815920396,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.629306228131435e-06,
+      "loss": 1.3523,
+      "step": 288
+    },
+    {
+      "epoch": 0.2556108347153123,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.619557845981571e-06,
+      "loss": 1.3212,
+      "step": 289
+    },
+    {
+      "epoch": 0.2564953012714207,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.609780469772623e-06,
+      "loss": 1.3868,
+      "step": 290
+    },
+    {
+      "epoch": 0.257379767827529,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.599974177825155e-06,
+      "loss": 1.3542,
+      "step": 291
+    },
+    {
+      "epoch": 0.2582642343836374,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.590139048691361e-06,
+      "loss": 1.3966,
+      "step": 292
+    },
+    {
+      "epoch": 0.25914870093974574,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.580275161154432e-06,
+      "loss": 1.3338,
+      "step": 293
+    },
+    {
+      "epoch": 0.2600331674958541,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.570382594227923e-06,
+      "loss": 1.2503,
+      "step": 294
+    },
+    {
+      "epoch": 0.2609176340519624,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.56046142715513e-06,
+      "loss": 1.2396,
+      "step": 295
+    },
+    {
+      "epoch": 0.26180210060807074,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.550511739408428e-06,
+      "loss": 1.3188,
+      "step": 296
+    },
+    {
+      "epoch": 0.2626865671641791,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.540533610688679e-06,
+      "loss": 1.4024,
+      "step": 297
+    },
+    {
+      "epoch": 0.26357103372028745,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.53052712092455e-06,
+      "loss": 1.2181,
+      "step": 298
+    },
+    {
+      "epoch": 0.2644555002763958,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.520492350271895e-06,
+      "loss": 1.2585,
+      "step": 299
+    },
+    {
+      "epoch": 0.26533996683250416,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.510429379113114e-06,
+      "loss": 1.2949,
+      "step": 300
+    },
+    {
+      "epoch": 0.2662244333886125,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.500338288056496e-06,
+      "loss": 1.3983,
+      "step": 301
+    },
+    {
+      "epoch": 0.26710889994472087,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.490219157935589e-06,
+      "loss": 1.3058,
+      "step": 302
+    },
+    {
+      "epoch": 0.26799336650082917,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.480072069808541e-06,
+      "loss": 1.2306,
+      "step": 303
+    },
+    {
+      "epoch": 0.2688778330569375,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.469897104957454e-06,
+      "loss": 1.3757,
+      "step": 304
+    },
+    {
+      "epoch": 0.2697622996130459,
+      "grad_norm": 1.7734375,
+      "learning_rate": 8.459694344887732e-06,
+      "loss": 1.2108,
+      "step": 305
+    },
+    {
+      "epoch": 0.27064676616915423,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.449463871327434e-06,
+      "loss": 1.3828,
+      "step": 306
+    },
+    {
+      "epoch": 0.2715312327252626,
+      "grad_norm": 1.6875,
+      "learning_rate": 8.439205766226613e-06,
+      "loss": 1.1469,
+      "step": 307
+    },
+    {
+      "epoch": 0.27241569928137094,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.428920111756658e-06,
+      "loss": 1.3126,
+      "step": 308
+    },
+    {
+      "epoch": 0.2733001658374793,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.418606990309645e-06,
+      "loss": 1.2627,
+      "step": 309
+    },
+    {
+      "epoch": 0.2741846323935876,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.408266484497664e-06,
+      "loss": 1.3172,
+      "step": 310
+    },
+    {
+      "epoch": 0.27506909894969594,
+      "grad_norm": 1.671875,
+      "learning_rate": 8.397898677152173e-06,
+      "loss": 1.3972,
+      "step": 311
+    },
+    {
+      "epoch": 0.2759535655058043,
+      "grad_norm": 1.703125,
+      "learning_rate": 8.387503651323317e-06,
+      "loss": 1.4311,
+      "step": 312
+    },
+    {
+      "epoch": 0.27683803206191265,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.377081490279278e-06,
+      "loss": 1.4227,
+      "step": 313
+    },
+    {
+      "epoch": 0.277722498618021,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.366632277505598e-06,
+      "loss": 1.246,
+      "step": 314
+    },
+    {
+      "epoch": 0.27860696517412936,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.356156096704516e-06,
+      "loss": 1.3163,
+      "step": 315
+    },
+    {
+      "epoch": 0.2794914317302377,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 1.3999,
+      "step": 316
+    },
+    {
+      "epoch": 0.28037589828634607,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.335123166908544e-06,
+      "loss": 1.3587,
+      "step": 317
+    },
+    {
+      "epoch": 0.28126036484245437,
+      "grad_norm": 1.6796875,
+      "learning_rate": 8.324566586395563e-06,
+      "loss": 1.2732,
+      "step": 318
+    },
+    {
+      "epoch": 0.2821448313985627,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.313983374817643e-06,
+      "loss": 1.3928,
+      "step": 319
+    },
+    {
+      "epoch": 0.2830292979546711,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.303373616950408e-06,
+      "loss": 1.4351,
+      "step": 320
+    },
+    {
+      "epoch": 0.28391376451077943,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.29273739778212e-06,
+      "loss": 1.3724,
+      "step": 321
+    },
+    {
+      "epoch": 0.2847982310668878,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.282074802513016e-06,
+      "loss": 1.2856,
+      "step": 322
+    },
+    {
+      "epoch": 0.28568269762299614,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.271385916554605e-06,
+      "loss": 1.261,
+      "step": 323
+    },
+    {
+      "epoch": 0.2865671641791045,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.260670825529002e-06,
+      "loss": 1.3472,
+      "step": 324
+    },
+    {
+      "epoch": 0.28745163073521285,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.249929615268234e-06,
+      "loss": 1.3534,
+      "step": 325
+    },
+    {
+      "epoch": 0.28833609729132115,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.239162371813552e-06,
+      "loss": 1.1108,
+      "step": 326
+    },
+    {
+      "epoch": 0.2892205638474295,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.22836918141474e-06,
+      "loss": 1.3162,
+      "step": 327
+    },
+    {
+      "epoch": 0.29010503040353786,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.217550130529433e-06,
+      "loss": 1.2907,
+      "step": 328
+    },
+    {
+      "epoch": 0.2909894969596462,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.206705305822414e-06,
+      "loss": 1.2548,
+      "step": 329
+    },
+    {
+      "epoch": 0.29187396351575456,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.195834794164925e-06,
+      "loss": 1.298,
+      "step": 330
+    },
+    {
+      "epoch": 0.2927584300718629,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.184938682633973e-06,
+      "loss": 1.332,
+      "step": 331
+    },
+    {
+      "epoch": 0.2936428966279713,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.17401705851163e-06,
+      "loss": 1.3759,
+      "step": 332
+    },
+    {
+      "epoch": 0.2945273631840796,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.163070009284326e-06,
+      "loss": 1.3423,
+      "step": 333
+    },
+    {
+      "epoch": 0.2954118297401879,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.152097622642167e-06,
+      "loss": 1.3557,
+      "step": 334
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.141099986478212e-06,
+      "loss": 1.2991,
+      "step": 335
+    },
+    {
+      "epoch": 0.29718076285240463,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.130077188887786e-06,
+      "loss": 1.4552,
+      "step": 336
+    },
+    {
+      "epoch": 0.298065229408513,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.119029318167763e-06,
+      "loss": 1.291,
+      "step": 337
+    },
+    {
+      "epoch": 0.29894969596462134,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.107956462815862e-06,
+      "loss": 1.3673,
+      "step": 338
+    },
+    {
+      "epoch": 0.2998341625207297,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.096858711529938e-06,
+      "loss": 1.1633,
+      "step": 339
+    },
+    {
+      "epoch": 0.30071862907683805,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.085736153207277e-06,
+      "loss": 1.3215,
+      "step": 340
+    },
+    {
+      "epoch": 0.3016030956329464,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.074588876943872e-06,
+      "loss": 1.2753,
+      "step": 341
+    },
+    {
+      "epoch": 0.3024875621890547,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.063416972033725e-06,
+      "loss": 1.2715,
+      "step": 342
+    },
+    {
+      "epoch": 0.30337202874516306,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.05222052796811e-06,
+      "loss": 1.2994,
+      "step": 343
+    },
+    {
+      "epoch": 0.3042564953012714,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.040999634434883e-06,
+      "loss": 1.3947,
+      "step": 344
+    },
+    {
+      "epoch": 0.30514096185737977,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.029754381317741e-06,
+      "loss": 1.2093,
+      "step": 345
+    },
+    {
+      "epoch": 0.3060254284134881,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.018484858695514e-06,
+      "loss": 1.2984,
+      "step": 346
+    },
+    {
+      "epoch": 0.3069098949695965,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.00719115684144e-06,
+      "loss": 1.1755,
+      "step": 347
+    },
+    {
+      "epoch": 0.30779436152570483,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.995873366222442e-06,
+      "loss": 1.4613,
+      "step": 348
+    },
+    {
+      "epoch": 0.3086788280818132,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.9845315774984e-06,
+      "loss": 1.3404,
+      "step": 349
+    },
+    {
+      "epoch": 0.3095632946379215,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.973165881521435e-06,
+      "loss": 1.3636,
+      "step": 350
+    },
+    {
+      "epoch": 0.31044776119402984,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.961776369335164e-06,
+      "loss": 1.327,
+      "step": 351
+    },
+    {
+      "epoch": 0.3113322277501382,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.950363132173992e-06,
+      "loss": 1.3362,
+      "step": 352
+    },
+    {
+      "epoch": 0.31221669430624654,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 1.3349,
+      "step": 353
+    },
+    {
+      "epoch": 0.3131011608623549,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.927465848814045e-06,
+      "loss": 1.249,
+      "step": 354
+    },
+    {
+      "epoch": 0.31398562741846325,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.915981986031367e-06,
+      "loss": 1.343,
+      "step": 355
+    },
+    {
+      "epoch": 0.3148700939745716,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.90447476510452e-06,
+      "loss": 1.2293,
+      "step": 356
+    },
+    {
+      "epoch": 0.3157545605306799,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.892944278210796e-06,
+      "loss": 1.3836,
+      "step": 357
+    },
+    {
+      "epoch": 0.31663902708678826,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.88139061771386e-06,
+      "loss": 1.3617,
+      "step": 358
+    },
+    {
+      "epoch": 0.3175234936428966,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.869813876162997e-06,
+      "loss": 1.2932,
+      "step": 359
+    },
+    {
+      "epoch": 0.31840796019900497,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.858214146292394e-06,
+      "loss": 1.2999,
+      "step": 360
+    },
+    {
+      "epoch": 0.3192924267551133,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.846591521020373e-06,
+      "loss": 1.123,
+      "step": 361
+    },
+    {
+      "epoch": 0.3201768933112217,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.834946093448658e-06,
+      "loss": 1.2873,
+      "step": 362
+    },
+    {
+      "epoch": 0.32106135986733003,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.823277956861635e-06,
+      "loss": 1.247,
+      "step": 363
+    },
+    {
+      "epoch": 0.3219458264234384,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.811587204725593e-06,
+      "loss": 1.4118,
+      "step": 364
+    },
+    {
+      "epoch": 0.3228302929795467,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.799873930687979e-06,
+      "loss": 1.3047,
+      "step": 365
+    },
+    {
+      "epoch": 0.32371475953565504,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.78813822857665e-06,
+      "loss": 1.4277,
+      "step": 366
+    },
+    {
+      "epoch": 0.3245992260917634,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.776380192399122e-06,
+      "loss": 1.3883,
+      "step": 367
+    },
+    {
+      "epoch": 0.32548369264787175,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.764599916341817e-06,
+      "loss": 1.226,
+      "step": 368
+    },
+    {
+      "epoch": 0.3263681592039801,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.752797494769307e-06,
+      "loss": 1.3181,
+      "step": 369
+    },
+    {
+      "epoch": 0.32725262576008846,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.74097302222355e-06,
+      "loss": 1.3447,
+      "step": 370
+    },
+    {
+      "epoch": 0.3281370923161968,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.729126593423151e-06,
+      "loss": 1.3561,
+      "step": 371
+    },
+    {
+      "epoch": 0.32902155887230516,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.71725830326259e-06,
+      "loss": 1.2279,
+      "step": 372
+    },
+    {
+      "epoch": 0.32990602542841346,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.70536824681146e-06,
+      "loss": 1.3024,
+      "step": 373
+    },
+    {
+      "epoch": 0.3307904919845218,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.69345651931372e-06,
+      "loss": 1.337,
+      "step": 374
+    },
+    {
+      "epoch": 0.33167495854063017,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.681523216186912e-06,
+      "loss": 1.4033,
+      "step": 375
+    },
+    {
+      "epoch": 0.3325594250967385,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.669568433021418e-06,
+      "loss": 1.1647,
+      "step": 376
+    },
+    {
+      "epoch": 0.3334438916528469,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.65759226557967e-06,
+      "loss": 1.1414,
+      "step": 377
+    },
+    {
+      "epoch": 0.33432835820895523,
+      "grad_norm": 1.6015625,
+      "learning_rate": 7.64559480979541e-06,
+      "loss": 1.3938,
+      "step": 378
+    },
+    {
+      "epoch": 0.3352128247650636,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.633576161772898e-06,
+      "loss": 1.2994,
+      "step": 379
+    },
+    {
+      "epoch": 0.33609729132117194,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.621536417786159e-06,
+      "loss": 1.3032,
+      "step": 380
+    },
+    {
+      "epoch": 0.33698175787728024,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.6094756742782e-06,
+      "loss": 1.3452,
+      "step": 381
+    },
+    {
+      "epoch": 0.3378662244333886,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.597394027860243e-06,
+      "loss": 1.3581,
+      "step": 382
+    },
+    {
+      "epoch": 0.33875069098949695,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.585291575310952e-06,
+      "loss": 1.3481,
+      "step": 383
+    },
+    {
+      "epoch": 0.3396351575456053,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.5731684135756566e-06,
+      "loss": 1.3737,
+      "step": 384
+    },
+    {
+      "epoch": 0.34051962410171366,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.5610246397655715e-06,
+      "loss": 1.2722,
+      "step": 385
+    },
+    {
+      "epoch": 0.341404090657822,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.548860351157028e-06,
+      "loss": 1.379,
+      "step": 386
+    },
+    {
+      "epoch": 0.34228855721393037,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.536675645190682e-06,
+      "loss": 1.4649,
+      "step": 387
+    },
+    {
+      "epoch": 0.3431730237700387,
+      "grad_norm": 1.5,
+      "learning_rate": 7.524470619470745e-06,
+      "loss": 1.3405,
+      "step": 388
+    },
+    {
+      "epoch": 0.344057490326147,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.512245371764197e-06,
+      "loss": 1.4036,
+      "step": 389
+    },
+    {
+      "epoch": 0.3449419568822554,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.2561,
+      "step": 390
+    },
+    {
+      "epoch": 0.34582642343836373,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.487734602268326e-06,
+      "loss": 1.2204,
+      "step": 391
+    },
+    {
+      "epoch": 0.3467108899944721,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.475449276819753e-06,
+      "loss": 1.2697,
+      "step": 392
+    },
+    {
+      "epoch": 0.34759535655058044,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.463144122064494e-06,
+      "loss": 1.3556,
+      "step": 393
+    },
+    {
+      "epoch": 0.3484798231066888,
+      "grad_norm": 1.5,
+      "learning_rate": 7.4508192365716005e-06,
+      "loss": 1.2972,
+      "step": 394
+    },
+    {
+      "epoch": 0.34936428966279715,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.438474719068174e-06,
+      "loss": 1.2835,
+      "step": 395
+    },
+    {
+      "epoch": 0.3502487562189055,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.426110668438578e-06,
+      "loss": 1.3313,
+      "step": 396
+    },
+    {
+      "epoch": 0.3511332227750138,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.413727183723642e-06,
+      "loss": 1.3757,
+      "step": 397
+    },
+    {
+      "epoch": 0.35201768933112215,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.401324364119872e-06,
+      "loss": 1.292,
+      "step": 398
+    },
+    {
+      "epoch": 0.3529021558872305,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.388902308978652e-06,
+      "loss": 1.2737,
+      "step": 399
+    },
+    {
+      "epoch": 0.35378662244333886,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.37646111780545e-06,
+      "loss": 1.28,
+      "step": 400
+    },
+    {
+      "epoch": 0.3546710889994472,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.364000890259024e-06,
+      "loss": 1.3259,
+      "step": 401
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.351521726150619e-06,
+      "loss": 1.2384,
+      "step": 402
+    },
+    {
+      "epoch": 0.3564400221116639,
+      "grad_norm": 1.625,
+      "learning_rate": 7.339023725443166e-06,
+      "loss": 1.2752,
+      "step": 403
+    },
+    {
+      "epoch": 0.3573244886677723,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.326506988250488e-06,
+      "loss": 1.1803,
+      "step": 404
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.313971614836496e-06,
+      "loss": 1.2475,
+      "step": 405
+    },
+    {
+      "epoch": 0.35909342177998893,
+      "grad_norm": 1.5625,
+      "learning_rate": 7.3014177056143795e-06,
+      "loss": 1.357,
+      "step": 406
+    },
+    {
+      "epoch": 0.3599778883360973,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.288845361145812e-06,
+      "loss": 1.3584,
+      "step": 407
+    },
+    {
+      "epoch": 0.36086235489220564,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.276254682140137e-06,
+      "loss": 1.2694,
+      "step": 408
+    },
+    {
+      "epoch": 0.361746821448314,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.2636457694535655e-06,
+      "loss": 1.2661,
+      "step": 409
+    },
+    {
+      "epoch": 0.36263128800442235,
+      "grad_norm": 1.6796875,
+      "learning_rate": 7.251018724088367e-06,
+      "loss": 1.3589,
+      "step": 410
+    },
+    {
+      "epoch": 0.3635157545605307,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.238373647192063e-06,
+      "loss": 1.3182,
+      "step": 411
+    },
+    {
+      "epoch": 0.364400221116639,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.225710640056614e-06,
+      "loss": 1.1271,
+      "step": 412
+    },
+    {
+      "epoch": 0.36528468767274735,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.213029804117604e-06,
+      "loss": 1.3374,
+      "step": 413
+    },
+    {
+      "epoch": 0.3661691542288557,
+      "grad_norm": 1.4921875,
+      "learning_rate": 7.200331240953439e-06,
+      "loss": 1.3872,
+      "step": 414
+    },
+    {
+      "epoch": 0.36705362078496406,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.187615052284522e-06,
+      "loss": 1.3109,
+      "step": 415
+    },
+    {
+      "epoch": 0.3679380873410724,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.174881339972448e-06,
+      "loss": 1.2522,
+      "step": 416
+    },
+    {
+      "epoch": 0.36882255389718077,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.16213020601918e-06,
+      "loss": 1.1243,
+      "step": 417
+    },
+    {
+      "epoch": 0.3697070204532891,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.149361752566233e-06,
+      "loss": 1.1873,
+      "step": 418
+    },
+    {
+      "epoch": 0.3705914870093975,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.136576081893863e-06,
+      "loss": 1.2798,
+      "step": 419
+    },
+    {
+      "epoch": 0.3714759535655058,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.12377329642024e-06,
+      "loss": 1.2831,
+      "step": 420
+    },
+    {
+      "epoch": 0.37236042012161413,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.110953498700629e-06,
+      "loss": 1.2508,
+      "step": 421
+    },
+    {
+      "epoch": 0.3732448866777225,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.09811679142657e-06,
+      "loss": 1.3639,
+      "step": 422
+    },
+    {
+      "epoch": 0.37412935323383084,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.085263277425058e-06,
+      "loss": 1.4001,
+      "step": 423
+    },
+    {
+      "epoch": 0.3750138197899392,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.072393059657716e-06,
+      "loss": 1.2889,
+      "step": 424
+    },
+    {
+      "epoch": 0.37589828634604755,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.059506241219964e-06,
+      "loss": 1.2256,
+      "step": 425
+    },
+    {
+      "epoch": 0.3767827529021559,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.046602925340209e-06,
+      "loss": 1.3299,
+      "step": 426
+    },
+    {
+      "epoch": 0.37766721945826426,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.033683215379002e-06,
+      "loss": 1.352,
+      "step": 427
+    },
+    {
+      "epoch": 0.37855168601437256,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.020747214828221e-06,
+      "loss": 1.2948,
+      "step": 428
+    },
+    {
+      "epoch": 0.3794361525704809,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.007795027310236e-06,
+      "loss": 1.3365,
+      "step": 429
+    },
+    {
+      "epoch": 0.38032061912658927,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.994826756577082e-06,
+      "loss": 1.3109,
+      "step": 430
+    },
+    {
+      "epoch": 0.3812050856826976,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.981842506509626e-06,
+      "loss": 1.3172,
+      "step": 431
+    },
+    {
+      "epoch": 0.382089552238806,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.968842381116736e-06,
+      "loss": 1.1969,
+      "step": 432
+    },
+    {
+      "epoch": 0.38297401879491433,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.955826484534447e-06,
+      "loss": 1.3244,
+      "step": 433
+    },
+    {
+      "epoch": 0.3838584853510227,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.942794921025127e-06,
+      "loss": 1.195,
+      "step": 434
+    },
+    {
+      "epoch": 0.38474295190713104,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.9297477949766445e-06,
+      "loss": 1.3408,
+      "step": 435
+    },
+    {
+      "epoch": 0.38562741846323934,
+      "grad_norm": 1.6171875,
+      "learning_rate": 6.916685210901527e-06,
+      "loss": 1.3806,
+      "step": 436
+    },
+    {
+      "epoch": 0.3865118850193477,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.903607273436128e-06,
+      "loss": 1.4428,
+      "step": 437
+    },
+    {
+      "epoch": 0.38739635157545604,
+      "grad_norm": 1.5703125,
+      "learning_rate": 6.890514087339789e-06,
+      "loss": 1.3007,
+      "step": 438
+    },
+    {
+      "epoch": 0.3882808181315644,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.8774057574939956e-06,
+      "loss": 1.271,
+      "step": 439
+    },
+    {
+      "epoch": 0.38916528468767275,
+      "grad_norm": 1.6171875,
+      "learning_rate": 6.864282388901544e-06,
+      "loss": 1.3061,
+      "step": 440
+    },
+    {
+      "epoch": 0.3900497512437811,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.851144086685695e-06,
+      "loss": 1.2362,
+      "step": 441
+    },
+    {
+      "epoch": 0.39093421779988946,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.837990956089334e-06,
+      "loss": 1.2555,
+      "step": 442
+    },
+    {
+      "epoch": 0.3918186843559978,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.824823102474127e-06,
+      "loss": 1.3481,
+      "step": 443
+    },
+    {
+      "epoch": 0.3927031509121061,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.811640631319677e-06,
+      "loss": 1.3096,
+      "step": 444
+    },
+    {
+      "epoch": 0.39358761746821447,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.79844364822268e-06,
+      "loss": 1.2762,
+      "step": 445
+    },
+    {
+      "epoch": 0.3944720840243228,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.785232258896078e-06,
+      "loss": 1.2889,
+      "step": 446
+    },
+    {
+      "epoch": 0.3953565505804312,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.77200656916821e-06,
+      "loss": 1.2047,
+      "step": 447
+    },
+    {
+      "epoch": 0.39624101713653953,
+      "grad_norm": 1.5,
+      "learning_rate": 6.758766684981972e-06,
+      "loss": 1.3131,
+      "step": 448
+    },
+    {
+      "epoch": 0.3971254836926479,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.745512712393958e-06,
+      "loss": 1.4186,
+      "step": 449
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.732244757573619e-06,
+      "loss": 1.3782,
+      "step": 450
+    },
+    {
+      "epoch": 0.3988944168048646,
+      "grad_norm": 1.5,
+      "learning_rate": 6.718962926802407e-06,
+      "loss": 1.3168,
+      "step": 451
+    },
+    {
+      "epoch": 0.3997788833609729,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.705667326472926e-06,
+      "loss": 1.4082,
+      "step": 452
+    },
+    {
+      "epoch": 0.40066334991708125,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.69235806308808e-06,
+      "loss": 1.3062,
+      "step": 453
+    },
+    {
+      "epoch": 0.4015478164731896,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.67903524326022e-06,
+      "loss": 1.2223,
+      "step": 454
+    },
+    {
+      "epoch": 0.40243228302929795,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.665698973710289e-06,
+      "loss": 1.267,
+      "step": 455
+    },
+    {
+      "epoch": 0.4033167495854063,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.652349361266967e-06,
+      "loss": 1.2493,
+      "step": 456
+    },
+    {
+      "epoch": 0.40420121614151466,
+      "grad_norm": 1.5625,
+      "learning_rate": 6.638986512865814e-06,
+      "loss": 1.398,
+      "step": 457
+    },
+    {
+      "epoch": 0.405085682697623,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.625610535548418e-06,
+      "loss": 1.2029,
+      "step": 458
+    },
+    {
+      "epoch": 0.4059701492537313,
+      "grad_norm": 1.375,
+      "learning_rate": 6.612221536461534e-06,
+      "loss": 1.2681,
+      "step": 459
+    },
+    {
+      "epoch": 0.40685461580983967,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.598819622856227e-06,
+      "loss": 1.4175,
+      "step": 460
+    },
+    {
+      "epoch": 0.407739082365948,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.585404902087011e-06,
+      "loss": 1.2896,
+      "step": 461
+    },
+    {
+      "epoch": 0.4086235489220564,
+      "grad_norm": 1.6171875,
+      "learning_rate": 6.571977481610989e-06,
+      "loss": 1.357,
+      "step": 462
+    },
+    {
+      "epoch": 0.40950801547816473,
+      "grad_norm": 1.4375,
+      "learning_rate": 6.558537468986998e-06,
+      "loss": 1.3894,
+      "step": 463
+    },
+    {
+      "epoch": 0.4103924820342731,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 1.2183,
+      "step": 464
+    },
+    {
+      "epoch": 0.41127694859038144,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.531620098033919e-06,
+      "loss": 1.3502,
+      "step": 465
+    },
+    {
+      "epoch": 0.4121614151464898,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.518142955323389e-06,
+      "loss": 1.3692,
+      "step": 466
+    },
+    {
+      "epoch": 0.4130458817025981,
+      "grad_norm": 1.5,
+      "learning_rate": 6.504653651700278e-06,
+      "loss": 1.3098,
+      "step": 467
+    },
+    {
+      "epoch": 0.41393034825870645,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.4911522952191275e-06,
+      "loss": 1.295,
+      "step": 468
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.477638994031028e-06,
+      "loss": 1.2863,
+      "step": 469
+    },
+    {
+      "epoch": 0.41569928137092316,
+      "grad_norm": 1.4375,
+      "learning_rate": 6.464113856382752e-06,
+      "loss": 1.3384,
+      "step": 470
+    },
+    {
+      "epoch": 0.4165837479270315,
+      "grad_norm": 1.5,
+      "learning_rate": 6.450576990615888e-06,
+      "loss": 1.2623,
+      "step": 471
+    },
+    {
+      "epoch": 0.41746821448313987,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.437028505165965e-06,
+      "loss": 1.2254,
+      "step": 472
+    },
+    {
+      "epoch": 0.4183526810392482,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.423468508561599e-06,
+      "loss": 1.3022,
+      "step": 473
+    },
+    {
+      "epoch": 0.4192371475953566,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.409897109423607e-06,
+      "loss": 1.3489,
+      "step": 474
+    },
+    {
+      "epoch": 0.4201216141514649,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.396314416464151e-06,
+      "loss": 1.2661,
+      "step": 475
+    },
+    {
+      "epoch": 0.4210060807075732,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.382720538485856e-06,
+      "loss": 1.374,
+      "step": 476
+    },
+    {
+      "epoch": 0.4218905472636816,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.3691155843809475e-06,
+      "loss": 1.3028,
+      "step": 477
+    },
+    {
+      "epoch": 0.42277501381978994,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.355499663130369e-06,
+      "loss": 1.3189,
+      "step": 478
+    },
+    {
+      "epoch": 0.4236594803758983,
+      "grad_norm": 1.703125,
+      "learning_rate": 6.341872883802923e-06,
+      "loss": 1.3246,
+      "step": 479
+    },
+    {
+      "epoch": 0.42454394693200664,
+      "grad_norm": 1.5,
+      "learning_rate": 6.328235355554382e-06,
+      "loss": 1.3169,
+      "step": 480
+    },
+    {
+      "epoch": 0.425428413488115,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.314587187626628e-06,
+      "loss": 1.2175,
+      "step": 481
+    },
+    {
+      "epoch": 0.42631288004422335,
+      "grad_norm": 1.390625,
+      "learning_rate": 6.3009284893467655e-06,
+      "loss": 1.2877,
+      "step": 482
+    },
+    {
+      "epoch": 0.42719734660033165,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.287259370126255e-06,
+      "loss": 1.2718,
+      "step": 483
+    },
+    {
+      "epoch": 0.42808181315644,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.273579939460032e-06,
+      "loss": 1.2376,
+      "step": 484
+    },
+    {
+      "epoch": 0.42896627971254836,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.259890306925627e-06,
+      "loss": 1.3573,
+      "step": 485
+    },
+    {
+      "epoch": 0.4298507462686567,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.246190582182296e-06,
+      "loss": 1.3166,
+      "step": 486
+    },
+    {
+      "epoch": 0.43073521282476507,
+      "grad_norm": 1.5546875,
+      "learning_rate": 6.232480874970137e-06,
+      "loss": 1.2718,
+      "step": 487
+    },
+    {
+      "epoch": 0.4316196793808734,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.218761295109209e-06,
+      "loss": 1.3318,
+      "step": 488
+    },
+    {
+      "epoch": 0.4325041459369818,
+      "grad_norm": 1.5,
+      "learning_rate": 6.205031952498656e-06,
+      "loss": 1.2443,
+      "step": 489
+    },
+    {
+      "epoch": 0.43338861249309013,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.191292957115825e-06,
+      "loss": 1.3425,
+      "step": 490
+    },
+    {
+      "epoch": 0.43427307904919843,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.177544419015388e-06,
+      "loss": 1.2717,
+      "step": 491
+    },
+    {
+      "epoch": 0.4351575456053068,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.163786448328455e-06,
+      "loss": 1.2011,
+      "step": 492
+    },
+    {
+      "epoch": 0.43604201216141514,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.150019155261694e-06,
+      "loss": 1.3354,
+      "step": 493
+    },
+    {
+      "epoch": 0.4369264787175235,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.136242650096451e-06,
+      "loss": 1.2146,
+      "step": 494
+    },
+    {
+      "epoch": 0.43781094527363185,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.122457043187863e-06,
+      "loss": 1.2419,
+      "step": 495
+    },
+    {
+      "epoch": 0.4386954118297402,
+      "grad_norm": 1.5546875,
+      "learning_rate": 6.108662444963979e-06,
+      "loss": 1.2667,
+      "step": 496
+    },
+    {
+      "epoch": 0.43957987838584855,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.094858965924866e-06,
+      "loss": 1.2808,
+      "step": 497
+    },
+    {
+      "epoch": 0.4404643449419569,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.081046716641735e-06,
+      "loss": 1.3747,
+      "step": 498
+    },
+    {
+      "epoch": 0.4413488114980652,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.0672258077560475e-06,
+      "loss": 1.2254,
+      "step": 499
+    },
+    {
+      "epoch": 0.44223327805417356,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.053396349978632e-06,
+      "loss": 1.3895,
+      "step": 500
+    },
+    {
+      "epoch": 0.4431177446102819,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.039558454088796e-06,
+      "loss": 1.3571,
+      "step": 501
+    },
+    {
+      "epoch": 0.44400221116639027,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.025712230933443e-06,
+      "loss": 1.3348,
+      "step": 502
+    },
+    {
+      "epoch": 0.4448866777224986,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.0118577914261786e-06,
+      "loss": 1.2218,
+      "step": 503
+    },
+    {
+      "epoch": 0.445771144278607,
+      "grad_norm": 1.5234375,
+      "learning_rate": 5.997995246546424e-06,
+      "loss": 1.4473,
+      "step": 504
+    },
+    {
+      "epoch": 0.44665561083471533,
+      "grad_norm": 1.4296875,
+      "learning_rate": 5.984124707338528e-06,
+      "loss": 1.4345,
+      "step": 505
+    },
+    {
+      "epoch": 0.44754007739082363,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.970246284910877e-06,
+      "loss": 1.2563,
+      "step": 506
+    },
+    {
+      "epoch": 0.448424543946932,
+      "grad_norm": 1.4453125,
+      "learning_rate": 5.9563600904350074e-06,
+      "loss": 1.3348,
+      "step": 507
+    },
+    {
+      "epoch": 0.44930901050304034,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.942466235144708e-06,
+      "loss": 1.4264,
+      "step": 508
+    },
+    {
+      "epoch": 0.4501934770591487,
+      "grad_norm": 1.53125,
+      "learning_rate": 5.9285648303351404e-06,
+      "loss": 1.3125,
+      "step": 509
+    },
+    {
+      "epoch": 0.45107794361525705,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.914655987361934e-06,
+      "loss": 1.2483,
+      "step": 510
+    },
+    {
+      "epoch": 0.4519624101713654,
+      "grad_norm": 1.5234375,
+      "learning_rate": 5.900739817640304e-06,
+      "loss": 1.2831,
+      "step": 511
+    },
+    {
+      "epoch": 0.45284687672747376,
+      "grad_norm": 1.625,
+      "learning_rate": 5.886816432644155e-06,
+      "loss": 1.1095,
+      "step": 512
+    },
+    {
+      "epoch": 0.4537313432835821,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.872885943905191e-06,
+      "loss": 1.3684,
+      "step": 513
+    },
+    {
+      "epoch": 0.4546158098396904,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.858948463012015e-06,
+      "loss": 1.2872,
+      "step": 514
+    },
+    {
+      "epoch": 0.45550027639579876,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.8450041016092465e-06,
+      "loss": 1.3367,
+      "step": 515
+    },
+    {
+      "epoch": 0.4563847429519071,
+      "grad_norm": 1.5859375,
+      "learning_rate": 5.831052971396613e-06,
+      "loss": 1.3533,
+      "step": 516
+    },
+    {
+      "epoch": 0.4572692095080155,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.817095184128067e-06,
+      "loss": 1.2871,
+      "step": 517
+    },
+    {
+      "epoch": 0.4581536760641238,
+      "grad_norm": 1.546875,
+      "learning_rate": 5.803130851610887e-06,
+      "loss": 1.2318,
+      "step": 518
+    },
+    {
+      "epoch": 0.4590381426202322,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.78916008570478e-06,
+      "loss": 1.2482,
+      "step": 519
+    },
+    {
+      "epoch": 0.45992260917634054,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.77518299832099e-06,
+      "loss": 1.2048,
+      "step": 520
+    },
+    {
+      "epoch": 0.4608070757324489,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.761199701421392e-06,
+      "loss": 1.328,
+      "step": 521
+    },
+    {
+      "epoch": 0.4616915422885572,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.747210307017609e-06,
+      "loss": 1.2961,
+      "step": 522
+    },
+    {
+      "epoch": 0.46257600884466554,
+      "grad_norm": 1.5078125,
+      "learning_rate": 5.733214927170101e-06,
+      "loss": 1.2443,
+      "step": 523
+    },
+    {
+      "epoch": 0.4634604754007739,
+      "grad_norm": 1.484375,
+      "learning_rate": 5.719213673987277e-06,
+      "loss": 1.4573,
+      "step": 524
+    },
+    {
+      "epoch": 0.46434494195688225,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.705206659624597e-06,
+      "loss": 1.3384,
+      "step": 525
+    },
+    {
+      "epoch": 0.4652294085129906,
+      "grad_norm": 1.5546875,
+      "learning_rate": 5.6911939962836625e-06,
+      "loss": 1.1806,
+      "step": 526
+    },
+    {
+      "epoch": 0.46611387506909896,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.6771757962113325e-06,
+      "loss": 1.381,
+      "step": 527
+    },
+    {
+      "epoch": 0.4669983416252073,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.663152171698813e-06,
+      "loss": 1.4115,
+      "step": 528
+    },
+    {
+      "epoch": 0.46788280818131567,
+      "grad_norm": 1.4453125,
+      "learning_rate": 5.649123235080762e-06,
+      "loss": 1.3213,
+      "step": 529
+    },
+    {
+      "epoch": 0.46876727473742397,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.635089098734394e-06,
+      "loss": 1.2742,
+      "step": 530
+    },
+    {
+      "epoch": 0.4696517412935323,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.621049875078571e-06,
+      "loss": 1.2376,
+      "step": 531
+    },
+    {
+      "epoch": 0.4705362078496407,
+      "grad_norm": 1.59375,
+      "learning_rate": 5.6070056765729065e-06,
+      "loss": 1.375,
+      "step": 532
+    },
+    {
+      "epoch": 0.47142067440574903,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.592956615716867e-06,
+      "loss": 1.2276,
+      "step": 533
+    },
+    {
+      "epoch": 0.4723051409618574,
+      "grad_norm": 1.546875,
+      "learning_rate": 5.578902805048866e-06,
+      "loss": 1.2616,
+      "step": 534
+    },
+    {
+      "epoch": 0.47318960751796574,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.564844357145365e-06,
+      "loss": 1.2783,
+      "step": 535
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.5,
+      "learning_rate": 5.550781384619974e-06,
+      "loss": 1.3205,
+      "step": 536
+    },
+    {
+      "epoch": 0.47495854063018245,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.536714000122543e-06,
+      "loss": 1.2756,
+      "step": 537
+    },
+    {
+      "epoch": 0.47584300718629075,
+      "grad_norm": 1.5390625,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 1.4603,
+      "step": 538
+    },
+    {
+      "epoch": 0.4767274737423991,
+      "grad_norm": 1.5546875,
+      "learning_rate": 5.50856644598678e-06,
+      "loss": 1.1787,
+      "step": 539
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.49448650182125e-06,
+      "loss": 1.3597,
+      "step": 540
+    },
+    {
+      "epoch": 0.4784964068546158,
+      "grad_norm": 1.9375,
+      "learning_rate": 5.480402596627477e-06,
+      "loss": 1.3682,
+      "step": 541
+    },
+    {
+      "epoch": 0.47938087341072416,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.466314843222993e-06,
+      "loss": 1.3036,
+      "step": 542
+    },
+    {
+      "epoch": 0.4802653399668325,
+      "grad_norm": 1.5546875,
+      "learning_rate": 5.452223354456154e-06,
+      "loss": 1.4319,
+      "step": 543
+    },
+    {
+      "epoch": 0.48114980652294087,
+      "grad_norm": 1.6015625,
+      "learning_rate": 5.438128243205241e-06,
+      "loss": 1.2868,
+      "step": 544
+    },
+    {
+      "epoch": 0.4820342730790492,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.4240296223775465e-06,
+      "loss": 1.281,
+      "step": 545
+    },
+    {
+      "epoch": 0.4829187396351575,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.409927604908481e-06,
+      "loss": 1.3847,
+      "step": 546
+    },
+    {
+      "epoch": 0.4838032061912659,
+      "grad_norm": 1.6796875,
+      "learning_rate": 5.395822303760662e-06,
+      "loss": 1.2893,
+      "step": 547
+    },
+    {
+      "epoch": 0.48468767274737423,
+      "grad_norm": 1.625,
+      "learning_rate": 5.381713831923008e-06,
+      "loss": 1.2149,
+      "step": 548
+    },
+    {
+      "epoch": 0.4855721393034826,
+      "grad_norm": 1.53125,
+      "learning_rate": 5.367602302409841e-06,
+      "loss": 1.3257,
+      "step": 549
+    },
+    {
+      "epoch": 0.48645660585959094,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.353487828259973e-06,
+      "loss": 1.247,
+      "step": 550
+    },
+    {
+      "epoch": 0.4873410724156993,
+      "grad_norm": 1.421875,
+      "learning_rate": 5.339370522535805e-06,
+      "loss": 1.2801,
+      "step": 551
+    },
+    {
+      "epoch": 0.48822553897180765,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.325250498322417e-06,
+      "loss": 1.2999,
+      "step": 552
+    },
+    {
+      "epoch": 0.489110005527916,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.311127868726667e-06,
+      "loss": 1.2862,
+      "step": 553
+    },
+    {
+      "epoch": 0.4899944720840243,
+      "grad_norm": 1.5859375,
+      "learning_rate": 5.297002746876284e-06,
+      "loss": 1.3081,
+      "step": 554
+    },
+    {
+      "epoch": 0.49087893864013266,
+      "grad_norm": 1.7265625,
+      "learning_rate": 5.282875245918963e-06,
+      "loss": 1.2368,
+      "step": 555
+    },
+    {
+      "epoch": 0.491763405196241,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.26874547902145e-06,
+      "loss": 1.3329,
+      "step": 556
+    },
+    {
+      "epoch": 0.49264787175234936,
+      "grad_norm": 1.5859375,
+      "learning_rate": 5.2546135593686484e-06,
+      "loss": 1.2371,
+      "step": 557
+    },
+    {
+      "epoch": 0.4935323383084577,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.240479600162704e-06,
+      "loss": 1.1912,
+      "step": 558
+    },
+    {
+      "epoch": 0.4944168048645661,
+      "grad_norm": 1.546875,
+      "learning_rate": 5.226343714622096e-06,
+      "loss": 1.3819,
+      "step": 559
+    },
+    {
+      "epoch": 0.4953012714206744,
+      "grad_norm": 1.5078125,
+      "learning_rate": 5.212206015980742e-06,
+      "loss": 1.2515,
+      "step": 560
+    },
+    {
+      "epoch": 0.4961857379767827,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.198066617487078e-06,
+      "loss": 1.1991,
+      "step": 561
+    },
+    {
+      "epoch": 0.4970702045328911,
+      "grad_norm": 1.5859375,
+      "learning_rate": 5.1839256324031575e-06,
+      "loss": 1.3371,
+      "step": 562
+    },
+    {
+      "epoch": 0.49795467108899943,
+      "grad_norm": 1.4296875,
+      "learning_rate": 5.169783174003744e-06,
+      "loss": 1.3991,
+      "step": 563
+    },
+    {
+      "epoch": 0.4988391376451078,
+      "grad_norm": 1.5,
+      "learning_rate": 5.155639355575402e-06,
+      "loss": 1.2768,
+      "step": 564
+    },
+    {
+      "epoch": 0.49972360420121614,
+      "grad_norm": 1.46875,
+      "learning_rate": 5.141494290415592e-06,
+      "loss": 1.2707,
+      "step": 565
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 565,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.262327645883597e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-565/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01c1f42af75afc36183509ddfc5eead46b5093e9cd4d9131f2cf31d96c1e836
+size 5432

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128257
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7303917d4e6e7c98254f48aa3ed8b6f73400ff008994d07946b2af4aab69cc
+size 4965805240

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f0b5356894518d74f4947e14c78a9de62f6184fed07ee781c5cb4283afea75
+size 1459729952

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 6425505792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
+size 17210102

tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}