Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7158041251294407,
+    "train_runtime": 19809.7521,
+    "train_samples": 68459,
+    "train_samples_per_second": 9.171,
+    "train_steps_per_second": 0.082
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56cc04d5319526418c30199238c3019d28b4aeb05dce34e1799ad14d39c5fb7
+size 4986106736

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c7a7a33d9e74903b4bdaa2af9e3a903e9f053c32ef14545b832ef2b856f4dd
+size 4981244328

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485b2f1a6df2017c002dad6e63d4f1fa2b9545b7f7e37cbef01e61cd6da19890
+size 4228306968

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5884a032428e60e8a5fa18cfd16690eef8d63d603cb12d99853b5105585dd8
+size 1242284160

model.safetensors.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 15437897728
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7158041251294407,
+    "train_runtime": 19809.7521,
+    "train_samples": 68459,
+    "train_samples_per_second": 9.171,
+    "train_steps_per_second": 0.082
+}

trainer_state.json

@@ -0,0 +1,2305 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9958391123439667,
+  "eval_steps": 500,
+  "global_step": 1620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.380993430479339,
+      "learning_rate": 1.234567901234568e-07,
+      "loss": 1.2271,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.348501093359578,
+      "learning_rate": 6.17283950617284e-07,
+      "loss": 1.2058,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.168916677113339,
+      "learning_rate": 1.234567901234568e-06,
+      "loss": 1.1892,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.858629179983347,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.1398,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.8628353409602443,
+      "learning_rate": 2.469135802469136e-06,
+      "loss": 1.14,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.3320646229754611,
+      "learning_rate": 3.08641975308642e-06,
+      "loss": 1.1307,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.37142743263814,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 1.1099,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0893052711432178,
+      "learning_rate": 4.3209876543209875e-06,
+      "loss": 1.0872,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.0420541911865238,
+      "learning_rate": 4.938271604938272e-06,
+      "loss": 1.0793,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.9751244819319205,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.0845,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9394712444469778,
+      "learning_rate": 6.17283950617284e-06,
+      "loss": 1.0581,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9446819107089788,
+      "learning_rate": 6.790123456790124e-06,
+      "loss": 1.0711,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.9219248821961198,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.0224,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.9248035052434173,
+      "learning_rate": 8.024691358024692e-06,
+      "loss": 1.0185,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.9767921779181035,
+      "learning_rate": 8.641975308641975e-06,
+      "loss": 1.0403,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.900831325888046,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.9946,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.0329827196383643,
+      "learning_rate": 9.876543209876543e-06,
+      "loss": 0.9826,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.028916413396711,
+      "learning_rate": 1.0493827160493827e-05,
+      "loss": 1.0026,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.9986410221150659,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.0196,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.118007030382272,
+      "learning_rate": 1.1728395061728398e-05,
+      "loss": 1.0301,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0306686260018971,
+      "learning_rate": 1.234567901234568e-05,
+      "loss": 0.991,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.1783877074338627,
+      "learning_rate": 1.2962962962962964e-05,
+      "loss": 0.9863,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.3347304199894814,
+      "learning_rate": 1.3580246913580248e-05,
+      "loss": 1.0055,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.1567825461094403,
+      "learning_rate": 1.4197530864197532e-05,
+      "loss": 0.9907,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.401145384918854,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.0195,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0619364925921315,
+      "learning_rate": 1.54320987654321e-05,
+      "loss": 0.9925,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1224187517180184,
+      "learning_rate": 1.6049382716049385e-05,
+      "loss": 0.9748,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.058015781823731,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.9642,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.0057166388176237,
+      "learning_rate": 1.728395061728395e-05,
+      "loss": 0.9794,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.219336306872448,
+      "learning_rate": 1.7901234567901236e-05,
+      "loss": 0.9848,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.1778812615671694,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.9406,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.4369525808973123,
+      "learning_rate": 1.9135802469135804e-05,
+      "loss": 0.9926,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.267670821149399,
+      "learning_rate": 1.9753086419753087e-05,
+      "loss": 0.9552,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.324502025754122,
+      "learning_rate": 1.9999791072456062e-05,
+      "loss": 0.9594,
+      "step": 165
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.6398800307247399,
+      "learning_rate": 1.9998514324636053e-05,
+      "loss": 0.9742,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.282151405513815,
+      "learning_rate": 1.999607704786645e-05,
+      "loss": 0.9782,
+      "step": 175
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.368937000876658,
+      "learning_rate": 1.9992479525042305e-05,
+      "loss": 0.97,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1429149098857512,
+      "learning_rate": 1.9987722173728587e-05,
+      "loss": 0.9263,
+      "step": 185
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.142494542354463,
+      "learning_rate": 1.9981805546111736e-05,
+      "loss": 0.9612,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.9661133733007405,
+      "learning_rate": 1.9974730328935534e-05,
+      "loss": 0.9564,
+      "step": 195
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.0956422654374287,
+      "learning_rate": 1.996649734342143e-05,
+      "loss": 0.957,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.065395255714296,
+      "learning_rate": 1.995710754517319e-05,
+      "loss": 0.9428,
+      "step": 205
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.0850009958268814,
+      "learning_rate": 1.9946562024066018e-05,
+      "loss": 0.9515,
+      "step": 210
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3698267000140338,
+      "learning_rate": 1.9934862004120003e-05,
+      "loss": 0.9441,
+      "step": 215
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.2180243717222954,
+      "learning_rate": 1.9922008843358097e-05,
+      "loss": 0.9484,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.05421684125154,
+      "learning_rate": 1.9908004033648452e-05,
+      "loss": 0.9672,
+      "step": 225
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.2382950773680732,
+      "learning_rate": 1.9892849200531294e-05,
+      "loss": 0.9375,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.1542981178332155,
+      "learning_rate": 1.9876546103030195e-05,
+      "loss": 0.9401,
+      "step": 235
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0395211592834745,
+      "learning_rate": 1.9859096633447965e-05,
+      "loss": 0.965,
+      "step": 240
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.9620854176466995,
+      "learning_rate": 1.9840502817146965e-05,
+      "loss": 0.9254,
+      "step": 245
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0602273541577587,
+      "learning_rate": 1.9820766812314038e-05,
+      "loss": 0.9307,
+      "step": 250
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.142745002321171,
+      "learning_rate": 1.9799890909710013e-05,
+      "loss": 0.9344,
+      "step": 255
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0822420018459202,
+      "learning_rate": 1.9777877532403816e-05,
+      "loss": 0.9345,
+      "step": 260
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.165254793190554,
+      "learning_rate": 1.9754729235491207e-05,
+      "loss": 0.9148,
+      "step": 265
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9461032408631161,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.9248,
+      "step": 270
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.0161807611793272,
+      "learning_rate": 1.9705038761569372e-05,
+      "loss": 0.9229,
+      "step": 275
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0682171583928652,
+      "learning_rate": 1.967850235214037e-05,
+      "loss": 0.9133,
+      "step": 280
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0674171129419805,
+      "learning_rate": 1.9650842557595968e-05,
+      "loss": 0.9281,
+      "step": 285
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0578949150556498,
+      "learning_rate": 1.9622062588412368e-05,
+      "loss": 0.9192,
+      "step": 290
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.9900599023327956,
+      "learning_rate": 1.9592165785084606e-05,
+      "loss": 0.9312,
+      "step": 295
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0090102752673205,
+      "learning_rate": 1.95611556177388e-05,
+      "loss": 0.9201,
+      "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0481187571731347,
+      "learning_rate": 1.952903568572939e-05,
+      "loss": 0.97,
+      "step": 305
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.0175192665589157,
+      "learning_rate": 1.9495809717221362e-05,
+      "loss": 0.9164,
+      "step": 310
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1537464954378314,
+      "learning_rate": 1.946148156875751e-05,
+      "loss": 0.8919,
+      "step": 315
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0953888335358495,
+      "learning_rate": 1.9426055224810788e-05,
+      "loss": 0.9372,
+      "step": 320
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.109481850979543,
+      "learning_rate": 1.9389534797321886e-05,
+      "loss": 0.9099,
+      "step": 325
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9506715246162528,
+      "learning_rate": 1.93519245252219e-05,
+      "loss": 0.9136,
+      "step": 330
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0986476835482393,
+      "learning_rate": 1.9313228773940346e-05,
+      "loss": 0.9082,
+      "step": 335
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.2893613575243312,
+      "learning_rate": 1.9273452034898472e-05,
+      "loss": 0.9263,
+      "step": 340
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.9810983163054904,
+      "learning_rate": 1.9232598924987904e-05,
+      "loss": 0.9067,
+      "step": 345
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0414864956692913,
+      "learning_rate": 1.9190674186034806e-05,
+      "loss": 0.9325,
+      "step": 350
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0303257386302838,
+      "learning_rate": 1.914768268424946e-05,
+      "loss": 0.9144,
+      "step": 355
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8564282775083322,
+      "learning_rate": 1.9103629409661468e-05,
+      "loss": 0.922,
+      "step": 360
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0162068121952108,
+      "learning_rate": 1.905851947554054e-05,
+      "loss": 0.9117,
+      "step": 365
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9620441168199088,
+      "learning_rate": 1.9012358117803007e-05,
+      "loss": 0.9093,
+      "step": 370
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9267690533225905,
+      "learning_rate": 1.8965150694404094e-05,
+      "loss": 0.8991,
+      "step": 375
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.8836709911598063,
+      "learning_rate": 1.8916902684716004e-05,
+      "loss": 0.875,
+      "step": 380
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9323672084536093,
+      "learning_rate": 1.8867619688891937e-05,
+      "loss": 0.9045,
+      "step": 385
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9390789515929351,
+      "learning_rate": 1.881730742721608e-05,
+      "loss": 0.8889,
+      "step": 390
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.8833432467724566,
+      "learning_rate": 1.876597173943965e-05,
+      "loss": 0.8833,
+      "step": 395
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9323098875612197,
+      "learning_rate": 1.871361858410308e-05,
+      "loss": 0.9008,
+      "step": 400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9297018536651566,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.8825,
+      "step": 405
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8582511160272933,
+      "learning_rate": 1.8605884294693893e-05,
+      "loss": 0.8854,
+      "step": 410
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9765404816133791,
+      "learning_rate": 1.8550515665355248e-05,
+      "loss": 0.8704,
+      "step": 415
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9316200284118313,
+      "learning_rate": 1.8494154576472976e-05,
+      "loss": 0.8944,
+      "step": 420
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.072766513059026,
+      "learning_rate": 1.84368075698865e-05,
+      "loss": 0.8842,
+      "step": 425
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.543811244450574,
+      "learning_rate": 1.8378481301870865e-05,
+      "loss": 0.8928,
+      "step": 430
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.233415241676456,
+      "learning_rate": 1.8319182542364117e-05,
+      "loss": 0.8876,
+      "step": 435
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0407331796481731,
+      "learning_rate": 1.825891817418153e-05,
+      "loss": 0.8898,
+      "step": 440
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9852677786684936,
+      "learning_rate": 1.8197695192216702e-05,
+      "loss": 0.8884,
+      "step": 445
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.9027726854768967,
+      "learning_rate": 1.8135520702629677e-05,
+      "loss": 0.8775,
+      "step": 450
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.0941452436773764,
+      "learning_rate": 1.807240192202212e-05,
+      "loss": 0.884,
+      "step": 455
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.107113850508076,
+      "learning_rate": 1.8008346176599675e-05,
+      "loss": 0.8746,
+      "step": 460
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.060890008040459,
+      "learning_rate": 1.794336090132164e-05,
+      "loss": 0.8952,
+      "step": 465
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.884966732457173,
+      "learning_rate": 1.7877453639037957e-05,
+      "loss": 0.8754,
+      "step": 470
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0704754541130148,
+      "learning_rate": 1.7810632039613735e-05,
+      "loss": 0.8764,
+      "step": 475
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.9919332562506876,
+      "learning_rate": 1.7742903859041324e-05,
+      "loss": 0.9005,
+      "step": 480
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9210227886163259,
+      "learning_rate": 1.7674276958540073e-05,
+      "loss": 0.8959,
+      "step": 485
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.00396374488261,
+      "learning_rate": 1.7604759303643875e-05,
+      "loss": 0.8801,
+      "step": 490
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.9278723416677115,
+      "learning_rate": 1.7534358963276606e-05,
+      "loss": 0.868,
+      "step": 495
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.9760092293453418,
+      "learning_rate": 1.7463084108815587e-05,
+      "loss": 0.8713,
+      "step": 500
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9315652245047339,
+      "learning_rate": 1.7390943013143086e-05,
+      "loss": 0.8864,
+      "step": 505
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9213276756309196,
+      "learning_rate": 1.7317944049686125e-05,
+      "loss": 0.8705,
+      "step": 510
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.873314757040681,
+      "learning_rate": 1.7244095691444548e-05,
+      "loss": 0.8566,
+      "step": 515
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.925108959774349,
+      "learning_rate": 1.7169406510007592e-05,
+      "loss": 0.8742,
+      "step": 520
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9349095138962109,
+      "learning_rate": 1.709388517455893e-05,
+      "loss": 0.8792,
+      "step": 525
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.879571628524229,
+      "learning_rate": 1.7017540450870488e-05,
+      "loss": 0.8503,
+      "step": 530
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9345436064226522,
+      "learning_rate": 1.694038120028497e-05,
+      "loss": 0.8655,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9685720075998935,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.8593,
+      "step": 540
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.3414804136782559,
+      "learning_rate": 1.6783655035465283e-05,
+      "loss": 0.7483,
+      "step": 545
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.9769664465584709,
+      "learning_rate": 1.6704106312458878e-05,
+      "loss": 0.7202,
+      "step": 550
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.9644265725777674,
+      "learning_rate": 1.662377944289948e-05,
+      "loss": 0.6971,
+      "step": 555
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.8362096432716036,
+      "learning_rate": 1.654268375033802e-05,
+      "loss": 0.6859,
+      "step": 560
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.8545500966881254,
+      "learning_rate": 1.646082864756282e-05,
+      "loss": 0.7126,
+      "step": 565
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.010020002670418,
+      "learning_rate": 1.637822363550706e-05,
+      "loss": 0.738,
+      "step": 570
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.9376974945477026,
+      "learning_rate": 1.6294878302145985e-05,
+      "loss": 0.7112,
+      "step": 575
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.980172490577581,
+      "learning_rate": 1.6210802321384046e-05,
+      "loss": 0.7048,
+      "step": 580
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.9692742001606004,
+      "learning_rate": 1.6126005451932028e-05,
+      "loss": 0.715,
+      "step": 585
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.8503062561620759,
+      "learning_rate": 1.6040497536174378e-05,
+      "loss": 0.7068,
+      "step": 590
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.0254807480179138,
+      "learning_rate": 1.5954288499026782e-05,
+      "loss": 0.7268,
+      "step": 595
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.9171158338661931,
+      "learning_rate": 1.586738834678418e-05,
+      "loss": 0.7273,
+      "step": 600
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.9117407742494892,
+      "learning_rate": 1.577980716595934e-05,
+      "loss": 0.7143,
+      "step": 605
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.9418369956367377,
+      "learning_rate": 1.569155512211212e-05,
+      "loss": 0.7151,
+      "step": 610
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.8973669405681762,
+      "learning_rate": 1.5602642458669527e-05,
+      "loss": 0.7096,
+      "step": 615
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.8881508172475038,
+      "learning_rate": 1.5513079495736788e-05,
+      "loss": 0.7104,
+      "step": 620
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.8876361729972202,
+      "learning_rate": 1.5422876628899482e-05,
+      "loss": 0.7195,
+      "step": 625
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9036094377090472,
+      "learning_rate": 1.5332044328016916e-05,
+      "loss": 0.7092,
+      "step": 630
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.8281239604850335,
+      "learning_rate": 1.5240593136006898e-05,
+      "loss": 0.6929,
+      "step": 635
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.8790456122568177,
+      "learning_rate": 1.5148533667622019e-05,
+      "loss": 0.6925,
+      "step": 640
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.8177639630770596,
+      "learning_rate": 1.505587660821759e-05,
+      "loss": 0.6895,
+      "step": 645
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.8927483767429891,
+      "learning_rate": 1.4962632712511395e-05,
+      "loss": 0.7031,
+      "step": 650
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.8254512048587952,
+      "learning_rate": 1.486881280333539e-05,
+      "loss": 0.699,
+      "step": 655
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.8724637574634844,
+      "learning_rate": 1.4774427770379492e-05,
+      "loss": 0.7107,
+      "step": 660
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.8288821089286669,
+      "learning_rate": 1.4679488568927615e-05,
+      "loss": 0.7087,
+      "step": 665
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.8486744655635069,
+      "learning_rate": 1.4584006218586096e-05,
+      "loss": 0.6947,
+      "step": 670
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.957175575662007,
+      "learning_rate": 1.4487991802004625e-05,
+      "loss": 0.708,
+      "step": 675
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.8860372365894343,
+      "learning_rate": 1.43914564635899e-05,
+      "loss": 0.7133,
+      "step": 680
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.8519026179322932,
+      "learning_rate": 1.4294411408212093e-05,
+      "loss": 0.6917,
+      "step": 685
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.8436704959136121,
+      "learning_rate": 1.4196867899904292e-05,
+      "loss": 0.7086,
+      "step": 690
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.9215284562010572,
+      "learning_rate": 1.4098837260555086e-05,
+      "loss": 0.706,
+      "step": 695
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.8726092038996182,
+      "learning_rate": 1.4000330868594428e-05,
+      "loss": 0.715,
+      "step": 700
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.8335655205275098,
+      "learning_rate": 1.390136015767295e-05,
+      "loss": 0.7033,
+      "step": 705
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.8308170289028934,
+      "learning_rate": 1.3801936615334848e-05,
+      "loss": 0.7017,
+      "step": 710
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.8488389190620426,
+      "learning_rate": 1.370207178168452e-05,
+      "loss": 0.7011,
+      "step": 715
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.9139523556398262,
+      "learning_rate": 1.3601777248047105e-05,
+      "loss": 0.7066,
+      "step": 720
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.9381426787661671,
+      "learning_rate": 1.3501064655623095e-05,
+      "loss": 0.7173,
+      "step": 725
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.822817225044632,
+      "learning_rate": 1.3399945694137109e-05,
+      "loss": 0.6979,
+      "step": 730
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.916057907116943,
+      "learning_rate": 1.3298432100481078e-05,
+      "loss": 0.6942,
+      "step": 735
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.9293994240579861,
+      "learning_rate": 1.3196535657351959e-05,
+      "loss": 0.7102,
+      "step": 740
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.8531666161772917,
+      "learning_rate": 1.309426819188409e-05,
+      "loss": 0.6963,
+      "step": 745
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.8969051991163846,
+      "learning_rate": 1.2991641574276419e-05,
+      "loss": 0.7058,
+      "step": 750
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.8758153277433447,
+      "learning_rate": 1.288866771641474e-05,
+      "loss": 0.7033,
+      "step": 755
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.8800800572010911,
+      "learning_rate": 1.2785358570489077e-05,
+      "loss": 0.6951,
+      "step": 760
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.7903117710072121,
+      "learning_rate": 1.2681726127606374e-05,
+      "loss": 0.6992,
+      "step": 765
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.9044773533349648,
+      "learning_rate": 1.2577782416398708e-05,
+      "loss": 0.7204,
+      "step": 770
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.8539428431672353,
+      "learning_rate": 1.2473539501627101e-05,
+      "loss": 0.7212,
+      "step": 775
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.8455375361267863,
+      "learning_rate": 1.2369009482781191e-05,
+      "loss": 0.702,
+      "step": 780
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.8134470805856595,
+      "learning_rate": 1.2264204492674816e-05,
+      "loss": 0.7134,
+      "step": 785
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.9426558956565058,
+      "learning_rate": 1.2159136696037763e-05,
+      "loss": 0.6899,
+      "step": 790
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.0712082472086517,
+      "learning_rate": 1.205381828810382e-05,
+      "loss": 0.6867,
+      "step": 795
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.8650015131089676,
+      "learning_rate": 1.1948261493195256e-05,
+      "loss": 0.6862,
+      "step": 800
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.8092140890169357,
+      "learning_rate": 1.1842478563303953e-05,
+      "loss": 0.692,
+      "step": 805
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.884259378052905,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.6956,
+      "step": 810
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.88390160177522,
+      "learning_rate": 1.1630283436353098e-05,
+      "loss": 0.6867,
+      "step": 815
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.8296289744950246,
+      "learning_rate": 1.1523895868811472e-05,
+      "loss": 0.7104,
+      "step": 820
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.8817584934930776,
+      "learning_rate": 1.1417331422464206e-05,
+      "loss": 0.7035,
+      "step": 825
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.8714688770326949,
+      "learning_rate": 1.1310602466261422e-05,
+      "loss": 0.6852,
+      "step": 830
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.8625649509092821,
+      "learning_rate": 1.1203721388247924e-05,
+      "loss": 0.6965,
+      "step": 835
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.8201921799899131,
+      "learning_rate": 1.1096700594125318e-05,
+      "loss": 0.682,
+      "step": 840
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.8435657261904709,
+      "learning_rate": 1.0989552505812073e-05,
+      "loss": 0.6954,
+      "step": 845
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.7847155172741475,
+      "learning_rate": 1.088228956000172e-05,
+      "loss": 0.6988,
+      "step": 850
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.8407369975482921,
+      "learning_rate": 1.077492420671931e-05,
+      "loss": 0.6852,
+      "step": 855
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.8516693758714967,
+      "learning_rate": 1.0667468907876349e-05,
+      "loss": 0.7018,
+      "step": 860
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.8428393845492996,
+      "learning_rate": 1.0559936135824322e-05,
+      "loss": 0.7013,
+      "step": 865
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.8598951874688993,
+      "learning_rate": 1.0452338371907065e-05,
+      "loss": 0.7056,
+      "step": 870
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.9089941816299408,
+      "learning_rate": 1.0344688105012006e-05,
+      "loss": 0.7008,
+      "step": 875
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.8025939134141212,
+      "learning_rate": 1.0236997830120614e-05,
+      "loss": 0.6995,
+      "step": 880
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.8322635796721002,
+      "learning_rate": 1.0129280046858085e-05,
+      "loss": 0.7119,
+      "step": 885
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.9168431530161661,
+      "learning_rate": 1.0021547258042522e-05,
+      "loss": 0.7166,
+      "step": 890
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.8719580027768455,
+      "learning_rate": 9.913811968233716e-06,
+      "loss": 0.6971,
+      "step": 895
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.8754135160174089,
+      "learning_rate": 9.806086682281759e-06,
+      "loss": 0.6926,
+      "step": 900
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.7545254920889488,
+      "learning_rate": 9.69838390387558e-06,
+      "loss": 0.6881,
+      "step": 905
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.8170094862170797,
+      "learning_rate": 9.59071613409167e-06,
+      "loss": 0.6986,
+      "step": 910
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.8727115323209758,
+      "learning_rate": 9.483095869943056e-06,
+      "loss": 0.701,
+      "step": 915
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.8217893100447828,
+      "learning_rate": 9.375535602928776e-06,
+      "loss": 0.7125,
+      "step": 920
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.7669081950681641,
+      "learning_rate": 9.268047817583997e-06,
+      "loss": 0.6951,
+      "step": 925
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.8691713855735111,
+      "learning_rate": 9.160644990030932e-06,
+      "loss": 0.7053,
+      "step": 930
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.8465735557284857,
+      "learning_rate": 9.053339586530724e-06,
+      "loss": 0.7101,
+      "step": 935
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.8556436244244698,
+      "learning_rate": 8.946144062036496e-06,
+      "loss": 0.6859,
+      "step": 940
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.8013250456726765,
+      "learning_rate": 8.839070858747697e-06,
+      "loss": 0.7001,
+      "step": 945
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.8848341169666858,
+      "learning_rate": 8.732132404665947e-06,
+      "loss": 0.67,
+      "step": 950
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.79454106581273,
+      "learning_rate": 8.625341112152487e-06,
+      "loss": 0.6821,
+      "step": 955
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.8304144336068819,
+      "learning_rate": 8.518709376487515e-06,
+      "loss": 0.6831,
+      "step": 960
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.7913540202550371,
+      "learning_rate": 8.412249574431429e-06,
+      "loss": 0.7086,
+      "step": 965
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.8064141920037301,
+      "learning_rate": 8.305974062788278e-06,
+      "loss": 0.6953,
+      "step": 970
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.7828524157109749,
+      "learning_rate": 8.199895176971489e-06,
+      "loss": 0.6983,
+      "step": 975
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.8098706298944635,
+      "learning_rate": 8.094025229572111e-06,
+      "loss": 0.6966,
+      "step": 980
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.849544093718342,
+      "learning_rate": 7.988376508929676e-06,
+      "loss": 0.6727,
+      "step": 985
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.7975592097506601,
+      "learning_rate": 7.882961277705897e-06,
+      "loss": 0.6856,
+      "step": 990
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.8523673745310055,
+      "learning_rate": 7.777791771461332e-06,
+      "loss": 0.7029,
+      "step": 995
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.8204875573442207,
+      "learning_rate": 7.672880197235223e-06,
+      "loss": 0.6864,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.8248700076350647,
+      "learning_rate": 7.568238732128586e-06,
+      "loss": 0.6835,
+      "step": 1005
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.8191493692115818,
+      "learning_rate": 7.463879521890847e-06,
+      "loss": 0.6943,
+      "step": 1010
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7791309739864153,
+      "learning_rate": 7.359814679510065e-06,
+      "loss": 0.7092,
+      "step": 1015
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.7843289733720519,
+      "learning_rate": 7.256056283806987e-06,
+      "loss": 0.6937,
+      "step": 1020
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.7842615760396254,
+      "learning_rate": 7.152616378033043e-06,
+      "loss": 0.7117,
+      "step": 1025
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.7829943694050134,
+      "learning_rate": 7.049506968472497e-06,
+      "loss": 0.7065,
+      "step": 1030
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.7561205508975692,
+      "learning_rate": 6.94674002304887e-06,
+      "loss": 0.6857,
+      "step": 1035
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7512481608435314,
+      "learning_rate": 6.844327469935826e-06,
+      "loss": 0.6766,
+      "step": 1040
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.7532241014261504,
+      "learning_rate": 6.742281196172663e-06,
+      "loss": 0.6696,
+      "step": 1045
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.723095218170628,
+      "learning_rate": 6.640613046284581e-06,
+      "loss": 0.6695,
+      "step": 1050
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.7252212718824871,
+      "learning_rate": 6.539334820907889e-06,
+      "loss": 0.667,
+      "step": 1055
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7830880287688797,
+      "learning_rate": 6.438458275420309e-06,
+      "loss": 0.683,
+      "step": 1060
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.8130835872824888,
+      "learning_rate": 6.337995118576521e-06,
+      "loss": 0.692,
+      "step": 1065
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.7894458277368371,
+      "learning_rate": 6.23795701114912e-06,
+      "loss": 0.7021,
+      "step": 1070
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.8367949367657657,
+      "learning_rate": 6.138355564575169e-06,
+      "loss": 0.6949,
+      "step": 1075
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7786700756632423,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.6967,
+      "step": 1080
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.9633228870304994,
+      "learning_rate": 5.9405088449775375e-06,
+      "loss": 0.5819,
+      "step": 1085
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.0344070619967278,
+      "learning_rate": 5.842286536050144e-06,
+      "loss": 0.5011,
+      "step": 1090
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.0538641350381497,
+      "learning_rate": 5.744546813503327e-06,
+      "loss": 0.5319,
+      "step": 1095
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.8864489388413449,
+      "learning_rate": 5.647301022000284e-06,
+      "loss": 0.4926,
+      "step": 1100
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.8474505807265904,
+      "learning_rate": 5.550560448873575e-06,
+      "loss": 0.509,
+      "step": 1105
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.8267823766957728,
+      "learning_rate": 5.454336322814995e-06,
+      "loss": 0.5094,
+      "step": 1110
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.8086042498258639,
+      "learning_rate": 5.358639812572244e-06,
+      "loss": 0.4892,
+      "step": 1115
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.7975013388182653,
+      "learning_rate": 5.263482025652591e-06,
+      "loss": 0.501,
+      "step": 1120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8115736728203711,
+      "learning_rate": 5.168874007033615e-06,
+      "loss": 0.4934,
+      "step": 1125
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.7794798018780561,
+      "learning_rate": 5.074826737881202e-06,
+      "loss": 0.5055,
+      "step": 1130
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.795406266403286,
+      "learning_rate": 4.981351134274981e-06,
+      "loss": 0.5062,
+      "step": 1135
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.7805878111888855,
+      "learning_rate": 4.888458045941269e-06,
+      "loss": 0.5016,
+      "step": 1140
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.7875089983056415,
+      "learning_rate": 4.796158254993768e-06,
+      "loss": 0.4976,
+      "step": 1145
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.8049951869389942,
+      "learning_rate": 4.704462474682055e-06,
+      "loss": 0.4987,
+      "step": 1150
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.8009379405913797,
+      "learning_rate": 4.613381348148125e-06,
+      "loss": 0.5092,
+      "step": 1155
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.7841732209811066,
+      "learning_rate": 4.522925447191006e-06,
+      "loss": 0.5061,
+      "step": 1160
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.8055813206538527,
+      "learning_rate": 4.433105271039722e-06,
+      "loss": 0.5303,
+      "step": 1165
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.8150894233057778,
+      "learning_rate": 4.343931245134616e-06,
+      "loss": 0.5078,
+      "step": 1170
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.8052165058822955,
+      "learning_rate": 4.255413719917294e-06,
+      "loss": 0.5124,
+      "step": 1175
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.810378912782989,
+      "learning_rate": 4.167562969629233e-06,
+      "loss": 0.5159,
+      "step": 1180
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.7874419439695609,
+      "learning_rate": 4.080389191119241e-06,
+      "loss": 0.4961,
+      "step": 1185
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.8205952521678742,
+      "learning_rate": 3.9939025026599335e-06,
+      "loss": 0.5109,
+      "step": 1190
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.7961082784450934,
+      "learning_rate": 3.908112942773278e-06,
+      "loss": 0.5106,
+      "step": 1195
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.7902941678889169,
+      "learning_rate": 3.823030469065431e-06,
+      "loss": 0.5087,
+      "step": 1200
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.7993525374229726,
+      "learning_rate": 3.738664957070964e-06,
+      "loss": 0.492,
+      "step": 1205
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.809158748195732,
+      "learning_rate": 3.655026199106595e-06,
+      "loss": 0.4983,
+      "step": 1210
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.7673626425314425,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.4887,
+      "step": 1215
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.7999177297746718,
+      "learning_rate": 3.489967691636038e-06,
+      "loss": 0.5028,
+      "step": 1220
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.7945863024103252,
+      "learning_rate": 3.408567100493787e-06,
+      "loss": 0.4927,
+      "step": 1225
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.786058386688595,
+      "learning_rate": 3.3279315778858034e-06,
+      "loss": 0.4974,
+      "step": 1230
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.7807385510973233,
+      "learning_rate": 3.248070483188426e-06,
+      "loss": 0.4974,
+      "step": 1235
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.7775262685810439,
+      "learning_rate": 3.1689930858900265e-06,
+      "loss": 0.5117,
+      "step": 1240
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.8435777447984063,
+      "learning_rate": 3.090708564515125e-06,
+      "loss": 0.496,
+      "step": 1245
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.7632453857565443,
+      "learning_rate": 3.013226005559009e-06,
+      "loss": 0.4912,
+      "step": 1250
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.7845597758185894,
+      "learning_rate": 2.936554402433087e-06,
+      "loss": 0.4909,
+      "step": 1255
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.7970687413033447,
+      "learning_rate": 2.8607026544210115e-06,
+      "loss": 0.488,
+      "step": 1260
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.7705687660032146,
+      "learning_rate": 2.785679565645726e-06,
+      "loss": 0.492,
+      "step": 1265
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.7871629482025935,
+      "learning_rate": 2.7114938440475926e-06,
+      "loss": 0.4977,
+      "step": 1270
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.7626742896975243,
+      "learning_rate": 2.6381541003736486e-06,
+      "loss": 0.5035,
+      "step": 1275
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.7747493631843794,
+      "learning_rate": 2.5656688471781455e-06,
+      "loss": 0.4865,
+      "step": 1280
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.7768979283390781,
+      "learning_rate": 2.4940464978345182e-06,
+      "loss": 0.4915,
+      "step": 1285
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.770753571366999,
+      "learning_rate": 2.423295365558821e-06,
+      "loss": 0.4877,
+      "step": 1290
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.796821433348244,
+      "learning_rate": 2.3534236624448302e-06,
+      "loss": 0.5015,
+      "step": 1295
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.7686662201911335,
+      "learning_rate": 2.284439498510854e-06,
+      "loss": 0.5033,
+      "step": 1300
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.7995269080777666,
+      "learning_rate": 2.2163508807584e-06,
+      "loss": 0.5032,
+      "step": 1305
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.7798024100681243,
+      "learning_rate": 2.149165712242811e-06,
+      "loss": 0.508,
+      "step": 1310
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.7952549320908302,
+      "learning_rate": 2.0828917911559544e-06,
+      "loss": 0.4991,
+      "step": 1315
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.7562949546743744,
+      "learning_rate": 2.01753680992107e-06,
+      "loss": 0.479,
+      "step": 1320
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.7738313454477512,
+      "learning_rate": 1.953108354299932e-06,
+      "loss": 0.5101,
+      "step": 1325
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.7632280693175711,
+      "learning_rate": 1.8896139025123549e-06,
+      "loss": 0.5029,
+      "step": 1330
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.7782927279263342,
+      "learning_rate": 1.8270608243681953e-06,
+      "loss": 0.4915,
+      "step": 1335
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7721170069306357,
+      "learning_rate": 1.7654563804119395e-06,
+      "loss": 0.4949,
+      "step": 1340
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.7569293553310351,
+      "learning_rate": 1.7048077210799774e-06,
+      "loss": 0.4952,
+      "step": 1345
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.7713352384960788,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.4915,
+      "step": 1350
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.8073489982779348,
+      "learning_rate": 1.5864058025271245e-06,
+      "loss": 0.5019,
+      "step": 1355
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.7532642687412483,
+      "learning_rate": 1.5286662862334035e-06,
+      "loss": 0.4817,
+      "step": 1360
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.7619263721625219,
+      "learning_rate": 1.47191003882317e-06,
+      "loss": 0.4926,
+      "step": 1365
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.7887732532731833,
+      "learning_rate": 1.4161436480019651e-06,
+      "loss": 0.51,
+      "step": 1370
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.756428418923445,
+      "learning_rate": 1.3613735865825305e-06,
+      "loss": 0.5113,
+      "step": 1375
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.7908916608851263,
+      "learning_rate": 1.307606211733522e-06,
+      "loss": 0.4872,
+      "step": 1380
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7849304184738213,
+      "learning_rate": 1.2548477642416258e-06,
+      "loss": 0.4885,
+      "step": 1385
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.7425717403698943,
+      "learning_rate": 1.2031043677871812e-06,
+      "loss": 0.483,
+      "step": 1390
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.7449369354911503,
+      "learning_rate": 1.152382028233422e-06,
+      "loss": 0.4898,
+      "step": 1395
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.7711579503984141,
+      "learning_rate": 1.102686632929363e-06,
+      "loss": 0.5056,
+      "step": 1400
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7859105451086833,
+      "learning_rate": 1.0540239500264516e-06,
+      "loss": 0.4914,
+      "step": 1405
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.7798228268418401,
+      "learning_rate": 1.0063996278090704e-06,
+      "loss": 0.5189,
+      "step": 1410
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.7615368434177107,
+      "learning_rate": 9.598191940389257e-07,
+      "loss": 0.5048,
+      "step": 1415
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.7767400021550324,
+      "learning_rate": 9.142880553134515e-07,
+      "loss": 0.4886,
+      "step": 1420
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7671973600539562,
+      "learning_rate": 8.698114964382598e-07,
+      "loss": 0.4944,
+      "step": 1425
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7912890267916621,
+      "learning_rate": 8.26394679813729e-07,
+      "loss": 0.5031,
+      "step": 1430
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.7411737851307407,
+      "learning_rate": 7.840426448358085e-07,
+      "loss": 0.4921,
+      "step": 1435
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.7523097552132488,
+      "learning_rate": 7.427603073110967e-07,
+      "loss": 0.4976,
+      "step": 1440
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.7706118040011497,
+      "learning_rate": 7.025524588862542e-07,
+      "loss": 0.483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.7825700623120088,
+      "learning_rate": 6.634237664918486e-07,
+      "loss": 0.504,
+      "step": 1450
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.7420108171750802,
+      "learning_rate": 6.253787718006499e-07,
+      "loss": 0.4842,
+      "step": 1455
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.7658665779082047,
+      "learning_rate": 5.884218907004902e-07,
+      "loss": 0.4949,
+      "step": 1460
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.75083219136469,
+      "learning_rate": 5.525574127817046e-07,
+      "loss": 0.4824,
+      "step": 1465
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.7586917678605787,
+      "learning_rate": 5.177895008392353e-07,
+      "loss": 0.4926,
+      "step": 1470
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.7470158525401197,
+      "learning_rate": 4.841221903894633e-07,
+      "loss": 0.4882,
+      "step": 1475
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.7772763452878679,
+      "learning_rate": 4.515593892018e-07,
+      "loss": 0.5021,
+      "step": 1480
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.7477051621945912,
+      "learning_rate": 4.2010487684511105e-07,
+      "loss": 0.5065,
+      "step": 1485
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.7566118062090599,
+      "learning_rate": 3.8976230424902616e-07,
+      "loss": 0.5088,
+      "step": 1490
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.766254582563817,
+      "learning_rate": 3.605351932801693e-07,
+      "loss": 0.4975,
+      "step": 1495
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.7839374958680789,
+      "learning_rate": 3.3242693633337986e-07,
+      "loss": 0.4922,
+      "step": 1500
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.7509582193755757,
+      "learning_rate": 3.054407959379557e-07,
+      "loss": 0.4836,
+      "step": 1505
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.7549781441743341,
+      "learning_rate": 2.795799043789682e-07,
+      "loss": 0.4913,
+      "step": 1510
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.7280618469591504,
+      "learning_rate": 2.548472633337007e-07,
+      "loss": 0.5008,
+      "step": 1515
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.7426209450041604,
+      "learning_rate": 2.3124574352324401e-07,
+      "loss": 0.4859,
+      "step": 1520
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.730840640795566,
+      "learning_rate": 2.0877808437928638e-07,
+      "loss": 0.5015,
+      "step": 1525
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.7454219518836528,
+      "learning_rate": 1.874468937261531e-07,
+      "loss": 0.511,
+      "step": 1530
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.7526874859698496,
+      "learning_rate": 1.6725464747811448e-07,
+      "loss": 0.4833,
+      "step": 1535
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.7749898887857551,
+      "learning_rate": 1.4820368935200003e-07,
+      "loss": 0.5081,
+      "step": 1540
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.7520293477111654,
+      "learning_rate": 1.3029623059517493e-07,
+      "loss": 0.4863,
+      "step": 1545
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.7551486931155532,
+      "learning_rate": 1.1353434972886879e-07,
+      "loss": 0.477,
+      "step": 1550
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.7517623874328504,
+      "learning_rate": 9.791999230692628e-08,
+      "loss": 0.5004,
+      "step": 1555
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.7473196143337467,
+      "learning_rate": 8.345497068998897e-08,
+      "loss": 0.4991,
+      "step": 1560
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.7371970090752852,
+      "learning_rate": 7.014096383512802e-08,
+      "loss": 0.502,
+      "step": 1565
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.7598898724156786,
+      "learning_rate": 5.797951710097449e-08,
+      "loss": 0.4858,
+      "step": 1570
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.7632140847196374,
+      "learning_rate": 4.6972042068341714e-08,
+      "loss": 0.494,
+      "step": 1575
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.7741502455508422,
+      "learning_rate": 3.711981637639084e-08,
+      "loss": 0.4858,
+      "step": 1580
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.7521002538915811,
+      "learning_rate": 2.8423983574328296e-08,
+      "loss": 0.4953,
+      "step": 1585
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.7791912328389965,
+      "learning_rate": 2.088555298867978e-08,
+      "loss": 0.5056,
+      "step": 1590
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.7663549047032114,
+      "learning_rate": 1.4505399606130621e-08,
+      "loss": 0.4958,
+      "step": 1595
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.7692872828036317,
+      "learning_rate": 9.284263971972574e-09,
+      "loss": 0.4986,
+      "step": 1600
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.782988216493056,
+      "learning_rate": 5.222752104147022e-09,
+      "loss": 0.5066,
+      "step": 1605
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.7892002209997082,
+      "learning_rate": 2.3213354229001395e-09,
+      "loss": 0.5093,
+      "step": 1610
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.7748663851832998,
+      "learning_rate": 5.803506960722072e-10,
+      "loss": 0.5038,
+      "step": 1615
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7392896696894132,
+      "learning_rate": 0.0,
+      "loss": 0.4834,
+      "step": 1620
+    },
+    {
+      "epoch": 3.0,
+      "step": 1620,
+      "total_flos": 1470053153243136.0,
+      "train_loss": 0.7158041251294407,
+      "train_runtime": 19809.7521,
+      "train_samples_per_second": 9.171,
+      "train_steps_per_second": 0.082
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1470053153243136.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20abfb3175ace78c7c0c47c4685033299310bc0bf2ca74e7f133da9bab045286
+size 6072