Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "mlfoundations-dev/evol_tt_5s",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717a00f534f888cf9a2111d09c515479909d535a70a211279d3721a18eab9fd3
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90465700b1d7fd8ddc0948ba18f3f6a6938cc7a2e63d7198556a4c9d7e3d308
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98e364988c6d8bf83886550b2158404caba03cf6166c28cbf94e1d2089a20d9
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84cb0ce976c3f243a061b4e5ccf6b1ad13049d6fd279d46fb1d23035d238fe4
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-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.weight": "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-00003-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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-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-00004-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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_log.jsonl

@@ -0,0 +1,444 @@
+{"current_steps": 1, "total_steps": 442, "loss": 5.7103, "accuracy": 0.59375, "lr": 1.7777777777777777e-08, "epoch": 0.0022618037885213456, "percentage": 0.23, "elapsed_time": "0:00:20", "remaining_time": "2:31:09"}
+{"current_steps": 2, "total_steps": 442, "loss": 6.1559, "accuracy": 0.5390625, "lr": 3.5555555555555554e-08, "epoch": 0.004523607577042691, "percentage": 0.45, "elapsed_time": "0:00:37", "remaining_time": "2:16:37"}
+{"current_steps": 3, "total_steps": 442, "loss": 6.4107, "accuracy": 0.5546875, "lr": 5.333333333333333e-08, "epoch": 0.006785411365564037, "percentage": 0.68, "elapsed_time": "0:00:54", "remaining_time": "2:13:37"}
+{"current_steps": 4, "total_steps": 442, "loss": 6.2871, "accuracy": 0.578125, "lr": 7.111111111111111e-08, "epoch": 0.009047215154085382, "percentage": 0.9, "elapsed_time": "0:01:10", "remaining_time": "2:08:57"}
+{"current_steps": 5, "total_steps": 442, "loss": 5.7732, "accuracy": 0.5625, "lr": 8.888888888888888e-08, "epoch": 0.01130901894260673, "percentage": 1.13, "elapsed_time": "0:01:30", "remaining_time": "2:11:54"}
+{"current_steps": 6, "total_steps": 442, "loss": 6.2788, "accuracy": 0.5078125, "lr": 1.0666666666666666e-07, "epoch": 0.013570822731128074, "percentage": 1.36, "elapsed_time": "0:01:45", "remaining_time": "2:08:16"}
+{"current_steps": 7, "total_steps": 442, "loss": 4.1206, "accuracy": 0.6328125, "lr": 1.2444444444444443e-07, "epoch": 0.01583262651964942, "percentage": 1.58, "elapsed_time": "0:01:59", "remaining_time": "2:03:57"}
+{"current_steps": 8, "total_steps": 442, "loss": 5.9544, "accuracy": 0.5390625, "lr": 1.4222222222222222e-07, "epoch": 0.018094430308170765, "percentage": 1.81, "elapsed_time": "0:02:16", "remaining_time": "2:03:38"}
+{"current_steps": 9, "total_steps": 442, "loss": 5.3604, "accuracy": 0.5546875, "lr": 1.6e-07, "epoch": 0.020356234096692113, "percentage": 2.04, "elapsed_time": "0:02:34", "remaining_time": "2:03:36"}
+{"current_steps": 10, "total_steps": 442, "loss": 6.0802, "accuracy": 0.5625, "lr": 1.7777777777777776e-07, "epoch": 0.02261803788521346, "percentage": 2.26, "elapsed_time": "0:02:49", "remaining_time": "2:02:10"}
+{"current_steps": 11, "total_steps": 442, "loss": 5.3828, "accuracy": 0.5625, "lr": 1.9555555555555555e-07, "epoch": 0.024879841673734804, "percentage": 2.49, "elapsed_time": "0:03:07", "remaining_time": "2:02:24"}
+{"current_steps": 12, "total_steps": 442, "loss": 6.3133, "accuracy": 0.625, "lr": 2.133333333333333e-07, "epoch": 0.02714164546225615, "percentage": 2.71, "elapsed_time": "0:03:25", "remaining_time": "2:02:27"}
+{"current_steps": 13, "total_steps": 442, "loss": 6.1689, "accuracy": 0.5546875, "lr": 2.3111111111111107e-07, "epoch": 0.029403449250777494, "percentage": 2.94, "elapsed_time": "0:03:40", "remaining_time": "2:01:31"}
+{"current_steps": 14, "total_steps": 442, "loss": 4.5476, "accuracy": 0.6171875, "lr": 2.4888888888888886e-07, "epoch": 0.03166525303929884, "percentage": 3.17, "elapsed_time": "0:03:58", "remaining_time": "2:01:22"}
+{"current_steps": 15, "total_steps": 442, "loss": 5.1372, "accuracy": 0.6171875, "lr": 2.666666666666666e-07, "epoch": 0.033927056827820185, "percentage": 3.39, "elapsed_time": "0:04:14", "remaining_time": "2:00:39"}
+{"current_steps": 16, "total_steps": 442, "loss": 6.4049, "accuracy": 0.53125, "lr": 2.8444444444444443e-07, "epoch": 0.03618886061634153, "percentage": 3.62, "elapsed_time": "0:04:31", "remaining_time": "2:00:30"}
+{"current_steps": 17, "total_steps": 442, "loss": 6.2812, "accuracy": 0.5390625, "lr": 3.022222222222222e-07, "epoch": 0.038450664404862875, "percentage": 3.85, "elapsed_time": "0:04:47", "remaining_time": "1:59:45"}
+{"current_steps": 18, "total_steps": 442, "loss": 6.0793, "accuracy": 0.5234375, "lr": 3.2e-07, "epoch": 0.04071246819338423, "percentage": 4.07, "elapsed_time": "0:05:04", "remaining_time": "1:59:36"}
+{"current_steps": 19, "total_steps": 442, "loss": 5.2537, "accuracy": 0.625, "lr": 3.3777777777777777e-07, "epoch": 0.04297427198190557, "percentage": 4.3, "elapsed_time": "0:05:20", "remaining_time": "1:59:03"}
+{"current_steps": 20, "total_steps": 442, "loss": 4.3313, "accuracy": 0.6875, "lr": 3.5555555555555553e-07, "epoch": 0.04523607577042692, "percentage": 4.52, "elapsed_time": "0:05:35", "remaining_time": "1:58:08"}
+{"current_steps": 21, "total_steps": 442, "loss": 5.4623, "accuracy": 0.6015625, "lr": 3.7333333333333334e-07, "epoch": 0.04749787955894826, "percentage": 4.75, "elapsed_time": "0:05:54", "remaining_time": "1:58:28"}
+{"current_steps": 22, "total_steps": 442, "loss": 4.7122, "accuracy": 0.609375, "lr": 3.911111111111111e-07, "epoch": 0.04975968334746961, "percentage": 4.98, "elapsed_time": "0:06:10", "remaining_time": "1:57:54"}
+{"current_steps": 23, "total_steps": 442, "loss": 5.8867, "accuracy": 0.5390625, "lr": 4.0888888888888886e-07, "epoch": 0.05202148713599095, "percentage": 5.2, "elapsed_time": "0:06:28", "remaining_time": "1:57:51"}
+{"current_steps": 24, "total_steps": 442, "loss": 5.1217, "accuracy": 0.5859375, "lr": 4.266666666666666e-07, "epoch": 0.0542832909245123, "percentage": 5.43, "elapsed_time": "0:06:46", "remaining_time": "1:58:04"}
+{"current_steps": 25, "total_steps": 442, "loss": 5.5417, "accuracy": 0.5703125, "lr": 4.4444444444444444e-07, "epoch": 0.05654509471303364, "percentage": 5.66, "elapsed_time": "0:07:02", "remaining_time": "1:57:24"}
+{"current_steps": 26, "total_steps": 442, "loss": 5.4918, "accuracy": 0.5625, "lr": 4.6222222222222214e-07, "epoch": 0.05880689850155499, "percentage": 5.88, "elapsed_time": "0:07:19", "remaining_time": "1:57:06"}
+{"current_steps": 27, "total_steps": 442, "loss": 6.2062, "accuracy": 0.5390625, "lr": 4.8e-07, "epoch": 0.061068702290076333, "percentage": 6.11, "elapsed_time": "0:07:34", "remaining_time": "1:56:25"}
+{"current_steps": 28, "total_steps": 442, "loss": 5.6067, "accuracy": 0.5234375, "lr": 4.977777777777777e-07, "epoch": 0.06333050607859768, "percentage": 6.33, "elapsed_time": "0:07:48", "remaining_time": "1:55:27"}
+{"current_steps": 29, "total_steps": 442, "loss": 5.307, "accuracy": 0.515625, "lr": 5.155555555555556e-07, "epoch": 0.06559230986711903, "percentage": 6.56, "elapsed_time": "0:08:06", "remaining_time": "1:55:29"}
+{"current_steps": 30, "total_steps": 442, "loss": 6.1408, "accuracy": 0.5078125, "lr": 5.333333333333332e-07, "epoch": 0.06785411365564037, "percentage": 6.79, "elapsed_time": "0:08:22", "remaining_time": "1:54:55"}
+{"current_steps": 31, "total_steps": 442, "loss": 5.7537, "accuracy": 0.5625, "lr": 5.511111111111111e-07, "epoch": 0.07011591744416172, "percentage": 7.01, "elapsed_time": "0:08:40", "remaining_time": "1:55:05"}
+{"current_steps": 32, "total_steps": 442, "loss": 5.6448, "accuracy": 0.546875, "lr": 5.688888888888889e-07, "epoch": 0.07237772123268306, "percentage": 7.24, "elapsed_time": "0:08:58", "remaining_time": "1:55:02"}
+{"current_steps": 33, "total_steps": 442, "loss": 4.6798, "accuracy": 0.5859375, "lr": 5.866666666666666e-07, "epoch": 0.07463952502120441, "percentage": 7.47, "elapsed_time": "0:09:16", "remaining_time": "1:54:53"}
+{"current_steps": 34, "total_steps": 442, "loss": 4.4742, "accuracy": 0.5703125, "lr": 6.044444444444444e-07, "epoch": 0.07690132880972575, "percentage": 7.69, "elapsed_time": "0:09:31", "remaining_time": "1:54:18"}
+{"current_steps": 35, "total_steps": 442, "loss": 5.0488, "accuracy": 0.5546875, "lr": 6.222222222222223e-07, "epoch": 0.0791631325982471, "percentage": 7.92, "elapsed_time": "0:09:47", "remaining_time": "1:53:55"}
+{"current_steps": 36, "total_steps": 442, "loss": 4.7704, "accuracy": 0.578125, "lr": 6.4e-07, "epoch": 0.08142493638676845, "percentage": 8.14, "elapsed_time": "0:10:06", "remaining_time": "1:53:58"}
+{"current_steps": 37, "total_steps": 442, "loss": 5.1667, "accuracy": 0.6015625, "lr": 6.577777777777777e-07, "epoch": 0.08368674017528979, "percentage": 8.37, "elapsed_time": "0:10:24", "remaining_time": "1:53:59"}
+{"current_steps": 38, "total_steps": 442, "loss": 5.278, "accuracy": 0.5703125, "lr": 6.755555555555555e-07, "epoch": 0.08594854396381114, "percentage": 8.6, "elapsed_time": "0:10:40", "remaining_time": "1:53:28"}
+{"current_steps": 39, "total_steps": 442, "loss": 5.0061, "accuracy": 0.5546875, "lr": 6.933333333333333e-07, "epoch": 0.08821034775233248, "percentage": 8.82, "elapsed_time": "0:10:59", "remaining_time": "1:53:30"}
+{"current_steps": 40, "total_steps": 442, "loss": 3.922, "accuracy": 0.671875, "lr": 7.111111111111111e-07, "epoch": 0.09047215154085383, "percentage": 9.05, "elapsed_time": "0:11:16", "remaining_time": "1:53:23"}
+{"current_steps": 41, "total_steps": 442, "loss": 4.4318, "accuracy": 0.609375, "lr": 7.288888888888888e-07, "epoch": 0.09273395532937517, "percentage": 9.28, "elapsed_time": "0:11:31", "remaining_time": "1:52:41"}
+{"current_steps": 42, "total_steps": 442, "loss": 5.0405, "accuracy": 0.546875, "lr": 7.466666666666667e-07, "epoch": 0.09499575911789652, "percentage": 9.5, "elapsed_time": "0:11:46", "remaining_time": "1:52:11"}
+{"current_steps": 43, "total_steps": 442, "loss": 5.0187, "accuracy": 0.5625, "lr": 7.644444444444444e-07, "epoch": 0.09725756290641786, "percentage": 9.73, "elapsed_time": "0:12:01", "remaining_time": "1:51:31"}
+{"current_steps": 44, "total_steps": 442, "loss": 4.1227, "accuracy": 0.671875, "lr": 7.822222222222222e-07, "epoch": 0.09951936669493922, "percentage": 9.95, "elapsed_time": "0:12:19", "remaining_time": "1:51:28"}
+{"current_steps": 45, "total_steps": 442, "loss": 4.5268, "accuracy": 0.6015625, "lr": 8e-07, "epoch": 0.10178117048346055, "percentage": 10.18, "elapsed_time": "0:12:35", "remaining_time": "1:51:03"}
+{"current_steps": 46, "total_steps": 442, "loss": 4.5489, "accuracy": 0.640625, "lr": 7.999874759018868e-07, "epoch": 0.1040429742719819, "percentage": 10.41, "elapsed_time": "0:12:53", "remaining_time": "1:50:56"}
+{"current_steps": 47, "total_steps": 442, "loss": 4.9532, "accuracy": 0.53125, "lr": 7.999499043918123e-07, "epoch": 0.10630477806050326, "percentage": 10.63, "elapsed_time": "0:13:07", "remaining_time": "1:50:22"}
+{"current_steps": 48, "total_steps": 442, "loss": 4.35, "accuracy": 0.6015625, "lr": 7.998872878225228e-07, "epoch": 0.1085665818490246, "percentage": 10.86, "elapsed_time": "0:13:24", "remaining_time": "1:50:06"}
+{"current_steps": 49, "total_steps": 442, "loss": 4.6801, "accuracy": 0.5859375, "lr": 7.997996301150987e-07, "epoch": 0.11082838563754595, "percentage": 11.09, "elapsed_time": "0:13:41", "remaining_time": "1:49:51"}
+{"current_steps": 50, "total_steps": 442, "loss": 4.7132, "accuracy": 0.578125, "lr": 7.996869367587088e-07, "epoch": 0.11309018942606729, "percentage": 11.31, "elapsed_time": "0:13:59", "remaining_time": "1:49:40"}
+{"current_steps": 51, "total_steps": 442, "loss": 4.624, "accuracy": 0.6015625, "lr": 7.99549214810266e-07, "epoch": 0.11535199321458864, "percentage": 11.54, "elapsed_time": "0:14:15", "remaining_time": "1:49:16"}
+{"current_steps": 52, "total_steps": 442, "loss": 4.8234, "accuracy": 0.59375, "lr": 7.993864728939867e-07, "epoch": 0.11761379700310998, "percentage": 11.76, "elapsed_time": "0:14:28", "remaining_time": "1:48:32"}
+{"current_steps": 53, "total_steps": 442, "loss": 4.2403, "accuracy": 0.625, "lr": 7.991987212008491e-07, "epoch": 0.11987560079163133, "percentage": 11.99, "elapsed_time": "0:14:45", "remaining_time": "1:48:20"}
+{"current_steps": 54, "total_steps": 442, "loss": 4.7775, "accuracy": 0.546875, "lr": 7.989859714879565e-07, "epoch": 0.12213740458015267, "percentage": 12.22, "elapsed_time": "0:15:01", "remaining_time": "1:47:56"}
+{"current_steps": 55, "total_steps": 442, "loss": 4.6785, "accuracy": 0.5703125, "lr": 7.987482370778005e-07, "epoch": 0.12439920836867402, "percentage": 12.44, "elapsed_time": "0:15:17", "remaining_time": "1:47:34"}
+{"current_steps": 56, "total_steps": 442, "loss": 4.4245, "accuracy": 0.6171875, "lr": 7.984855328574262e-07, "epoch": 0.12666101215719536, "percentage": 12.67, "elapsed_time": "0:15:36", "remaining_time": "1:47:33"}
+{"current_steps": 57, "total_steps": 442, "loss": 4.6952, "accuracy": 0.59375, "lr": 7.981978752775009e-07, "epoch": 0.1289228159457167, "percentage": 12.9, "elapsed_time": "0:15:53", "remaining_time": "1:47:17"}
+{"current_steps": 58, "total_steps": 442, "loss": 5.0523, "accuracy": 0.578125, "lr": 7.978852823512833e-07, "epoch": 0.13118461973423806, "percentage": 13.12, "elapsed_time": "0:16:13", "remaining_time": "1:47:22"}
+{"current_steps": 59, "total_steps": 442, "loss": 4.4589, "accuracy": 0.5859375, "lr": 7.975477736534957e-07, "epoch": 0.1334464235227594, "percentage": 13.35, "elapsed_time": "0:16:31", "remaining_time": "1:47:15"}
+{"current_steps": 60, "total_steps": 442, "loss": 4.2887, "accuracy": 0.6796875, "lr": 7.971853703190986e-07, "epoch": 0.13570822731128074, "percentage": 13.57, "elapsed_time": "0:16:45", "remaining_time": "1:46:44"}
+{"current_steps": 61, "total_steps": 442, "loss": 4.4567, "accuracy": 0.6640625, "lr": 7.967980950419664e-07, "epoch": 0.1379700310998021, "percentage": 13.8, "elapsed_time": "0:17:03", "remaining_time": "1:46:34"}
+{"current_steps": 62, "total_steps": 442, "loss": 4.2358, "accuracy": 0.6328125, "lr": 7.963859720734669e-07, "epoch": 0.14023183488832344, "percentage": 14.03, "elapsed_time": "0:17:21", "remaining_time": "1:46:21"}
+{"current_steps": 63, "total_steps": 442, "loss": 3.7751, "accuracy": 0.6953125, "lr": 7.959490272209427e-07, "epoch": 0.14249363867684478, "percentage": 14.25, "elapsed_time": "0:17:36", "remaining_time": "1:45:56"}
+{"current_steps": 64, "total_steps": 442, "loss": 3.9722, "accuracy": 0.640625, "lr": 7.954872878460946e-07, "epoch": 0.14475544246536612, "percentage": 14.48, "elapsed_time": "0:17:53", "remaining_time": "1:45:42"}
+{"current_steps": 65, "total_steps": 442, "loss": 4.0631, "accuracy": 0.640625, "lr": 7.950007828632691e-07, "epoch": 0.14701724625388748, "percentage": 14.71, "elapsed_time": "0:18:10", "remaining_time": "1:45:23"}
+{"current_steps": 66, "total_steps": 442, "loss": 4.1606, "accuracy": 0.59375, "lr": 7.944895427376465e-07, "epoch": 0.14927905004240882, "percentage": 14.93, "elapsed_time": "0:18:27", "remaining_time": "1:45:10"}
+{"current_steps": 67, "total_steps": 442, "loss": 3.9425, "accuracy": 0.65625, "lr": 7.939535994833345e-07, "epoch": 0.15154085383093016, "percentage": 15.16, "elapsed_time": "0:18:43", "remaining_time": "1:44:49"}
+{"current_steps": 68, "total_steps": 442, "loss": 4.5149, "accuracy": 0.640625, "lr": 7.933929866613628e-07, "epoch": 0.1538026576194515, "percentage": 15.38, "elapsed_time": "0:19:01", "remaining_time": "1:44:37"}
+{"current_steps": 69, "total_steps": 442, "loss": 3.5203, "accuracy": 0.65625, "lr": 7.928077393775808e-07, "epoch": 0.15606446140797287, "percentage": 15.61, "elapsed_time": "0:19:16", "remaining_time": "1:44:13"}
+{"current_steps": 70, "total_steps": 442, "loss": 3.8556, "accuracy": 0.6640625, "lr": 7.921978942804609e-07, "epoch": 0.1583262651964942, "percentage": 15.84, "elapsed_time": "0:19:34", "remaining_time": "1:44:03"}
+{"current_steps": 71, "total_steps": 442, "loss": 4.513, "accuracy": 0.65625, "lr": 7.915634895588021e-07, "epoch": 0.16058806898501554, "percentage": 16.06, "elapsed_time": "0:19:49", "remaining_time": "1:43:37"}
+{"current_steps": 72, "total_steps": 442, "loss": 4.5088, "accuracy": 0.625, "lr": 7.909045649393394e-07, "epoch": 0.1628498727735369, "percentage": 16.29, "elapsed_time": "0:20:05", "remaining_time": "1:43:12"}
+{"current_steps": 73, "total_steps": 442, "loss": 4.078, "accuracy": 0.640625, "lr": 7.902211616842556e-07, "epoch": 0.16511167656205825, "percentage": 16.52, "elapsed_time": "0:20:24", "remaining_time": "1:43:11"}
+{"current_steps": 74, "total_steps": 442, "loss": 3.8547, "accuracy": 0.6875, "lr": 7.89513322588598e-07, "epoch": 0.16737348035057958, "percentage": 16.74, "elapsed_time": "0:20:41", "remaining_time": "1:42:54"}
+{"current_steps": 75, "total_steps": 442, "loss": 4.0357, "accuracy": 0.65625, "lr": 7.887810919775976e-07, "epoch": 0.16963528413910092, "percentage": 16.97, "elapsed_time": "0:20:59", "remaining_time": "1:42:41"}
+{"current_steps": 76, "total_steps": 442, "loss": 4.1242, "accuracy": 0.640625, "lr": 7.880245157038949e-07, "epoch": 0.1718970879276223, "percentage": 17.19, "elapsed_time": "0:21:16", "remaining_time": "1:42:27"}
+{"current_steps": 77, "total_steps": 442, "loss": 4.4641, "accuracy": 0.6015625, "lr": 7.872436411446671e-07, "epoch": 0.17415889171614363, "percentage": 17.42, "elapsed_time": "0:21:30", "remaining_time": "1:41:57"}
+{"current_steps": 78, "total_steps": 442, "loss": 4.3324, "accuracy": 0.6484375, "lr": 7.86438517198662e-07, "epoch": 0.17642069550466496, "percentage": 17.65, "elapsed_time": "0:21:46", "remaining_time": "1:41:35"}
+{"current_steps": 79, "total_steps": 442, "loss": 4.3785, "accuracy": 0.6640625, "lr": 7.856091942831366e-07, "epoch": 0.1786824992931863, "percentage": 17.87, "elapsed_time": "0:22:02", "remaining_time": "1:41:15"}
+{"current_steps": 80, "total_steps": 442, "loss": 3.9842, "accuracy": 0.6875, "lr": 7.847557243306982e-07, "epoch": 0.18094430308170767, "percentage": 18.1, "elapsed_time": "0:22:18", "remaining_time": "1:40:57"}
+{"current_steps": 81, "total_steps": 442, "loss": 3.7454, "accuracy": 0.671875, "lr": 7.838781607860541e-07, "epoch": 0.183206106870229, "percentage": 18.33, "elapsed_time": "0:22:34", "remaining_time": "1:40:36"}
+{"current_steps": 82, "total_steps": 442, "loss": 4.1062, "accuracy": 0.6640625, "lr": 7.82976558602664e-07, "epoch": 0.18546791065875035, "percentage": 18.55, "elapsed_time": "0:22:53", "remaining_time": "1:40:28"}
+{"current_steps": 83, "total_steps": 442, "loss": 4.1924, "accuracy": 0.6796875, "lr": 7.820509742392988e-07, "epoch": 0.1877297144472717, "percentage": 18.78, "elapsed_time": "0:23:08", "remaining_time": "1:40:07"}
+{"current_steps": 84, "total_steps": 442, "loss": 3.5515, "accuracy": 0.7265625, "lr": 7.811014656565054e-07, "epoch": 0.18999151823579305, "percentage": 19.0, "elapsed_time": "0:23:24", "remaining_time": "1:39:46"}
+{"current_steps": 85, "total_steps": 442, "loss": 4.4942, "accuracy": 0.6328125, "lr": 7.801280923129773e-07, "epoch": 0.1922533220243144, "percentage": 19.23, "elapsed_time": "0:23:39", "remaining_time": "1:39:22"}
+{"current_steps": 86, "total_steps": 442, "loss": 4.2346, "accuracy": 0.6015625, "lr": 7.791309151618305e-07, "epoch": 0.19451512581283573, "percentage": 19.46, "elapsed_time": "0:23:56", "remaining_time": "1:39:04"}
+{"current_steps": 87, "total_steps": 442, "loss": 3.7192, "accuracy": 0.6953125, "lr": 7.781099966467874e-07, "epoch": 0.1967769296013571, "percentage": 19.68, "elapsed_time": "0:24:12", "remaining_time": "1:38:46"}
+{"current_steps": 88, "total_steps": 442, "loss": 4.4877, "accuracy": 0.6875, "lr": 7.770654006982664e-07, "epoch": 0.19903873338987843, "percentage": 19.91, "elapsed_time": "0:24:29", "remaining_time": "1:38:32"}
+{"current_steps": 89, "total_steps": 442, "loss": 3.9806, "accuracy": 0.671875, "lr": 7.759971927293781e-07, "epoch": 0.20130053717839977, "percentage": 20.14, "elapsed_time": "0:24:44", "remaining_time": "1:38:09"}
+{"current_steps": 90, "total_steps": 442, "loss": 4.0478, "accuracy": 0.6796875, "lr": 7.749054396318297e-07, "epoch": 0.2035623409669211, "percentage": 20.36, "elapsed_time": "0:25:00", "remaining_time": "1:37:49"}
+{"current_steps": 91, "total_steps": 442, "loss": 4.1678, "accuracy": 0.6171875, "lr": 7.737902097717356e-07, "epoch": 0.20582414475544247, "percentage": 20.59, "elapsed_time": "0:25:18", "remaining_time": "1:37:37"}
+{"current_steps": 92, "total_steps": 442, "loss": 4.3746, "accuracy": 0.65625, "lr": 7.726515729853367e-07, "epoch": 0.2080859485439638, "percentage": 20.81, "elapsed_time": "0:25:36", "remaining_time": "1:37:27"}
+{"current_steps": 93, "total_steps": 442, "loss": 3.6005, "accuracy": 0.6796875, "lr": 7.714896005746272e-07, "epoch": 0.21034775233248515, "percentage": 21.04, "elapsed_time": "0:25:53", "remaining_time": "1:37:09"}
+{"current_steps": 94, "total_steps": 442, "loss": 4.1693, "accuracy": 0.7109375, "lr": 7.703043653028896e-07, "epoch": 0.21260955612100652, "percentage": 21.27, "elapsed_time": "0:26:08", "remaining_time": "1:36:47"}
+{"current_steps": 95, "total_steps": 442, "loss": 4.1, "accuracy": 0.671875, "lr": 7.690959413901379e-07, "epoch": 0.21487135990952785, "percentage": 21.49, "elapsed_time": "0:26:25", "remaining_time": "1:36:30"}
+{"current_steps": 96, "total_steps": 442, "loss": 4.2664, "accuracy": 0.59375, "lr": 7.678644045084704e-07, "epoch": 0.2171331636980492, "percentage": 21.72, "elapsed_time": "0:26:39", "remaining_time": "1:36:05"}
+{"current_steps": 97, "total_steps": 442, "loss": 3.6566, "accuracy": 0.703125, "lr": 7.666098317773308e-07, "epoch": 0.21939496748657053, "percentage": 21.95, "elapsed_time": "0:26:54", "remaining_time": "1:35:40"}
+{"current_steps": 98, "total_steps": 442, "loss": 3.7794, "accuracy": 0.7265625, "lr": 7.653323017586789e-07, "epoch": 0.2216567712750919, "percentage": 22.17, "elapsed_time": "0:27:11", "remaining_time": "1:35:25"}
+{"current_steps": 99, "total_steps": 442, "loss": 3.5253, "accuracy": 0.7734375, "lr": 7.640318944520711e-07, "epoch": 0.22391857506361323, "percentage": 22.4, "elapsed_time": "0:27:28", "remaining_time": "1:35:10"}
+{"current_steps": 100, "total_steps": 442, "loss": 3.5183, "accuracy": 0.7109375, "lr": 7.627086912896511e-07, "epoch": 0.22618037885213457, "percentage": 22.62, "elapsed_time": "0:27:46", "remaining_time": "1:34:58"}
+{"current_steps": 101, "total_steps": 442, "loss": 3.5656, "accuracy": 0.6953125, "lr": 7.613627751310499e-07, "epoch": 0.2284421826406559, "percentage": 22.85, "elapsed_time": "0:28:02", "remaining_time": "1:34:40"}
+{"current_steps": 102, "total_steps": 442, "loss": 3.4855, "accuracy": 0.6875, "lr": 7.599942302581977e-07, "epoch": 0.23070398642917728, "percentage": 23.08, "elapsed_time": "0:28:18", "remaining_time": "1:34:21"}
+{"current_steps": 103, "total_steps": 442, "loss": 3.9243, "accuracy": 0.6875, "lr": 7.586031423700457e-07, "epoch": 0.23296579021769862, "percentage": 23.3, "elapsed_time": "0:28:38", "remaining_time": "1:34:15"}
+{"current_steps": 104, "total_steps": 442, "loss": 3.1857, "accuracy": 0.703125, "lr": 7.571895985772e-07, "epoch": 0.23522759400621995, "percentage": 23.53, "elapsed_time": "0:28:52", "remaining_time": "1:33:51"}
+{"current_steps": 105, "total_steps": 442, "loss": 4.0931, "accuracy": 0.7109375, "lr": 7.557536873964661e-07, "epoch": 0.23748939779474132, "percentage": 23.76, "elapsed_time": "0:29:07", "remaining_time": "1:33:29"}
+{"current_steps": 106, "total_steps": 442, "loss": 3.7142, "accuracy": 0.7109375, "lr": 7.542954987453069e-07, "epoch": 0.23975120158326266, "percentage": 23.98, "elapsed_time": "0:29:24", "remaining_time": "1:33:14"}
+{"current_steps": 107, "total_steps": 442, "loss": 3.6407, "accuracy": 0.671875, "lr": 7.528151239362108e-07, "epoch": 0.242013005371784, "percentage": 24.21, "elapsed_time": "0:29:41", "remaining_time": "1:32:56"}
+{"current_steps": 108, "total_steps": 442, "loss": 3.287, "accuracy": 0.6953125, "lr": 7.513126556709748e-07, "epoch": 0.24427480916030533, "percentage": 24.43, "elapsed_time": "0:29:56", "remaining_time": "1:32:37"}
+{"current_steps": 109, "total_steps": 442, "loss": 3.72, "accuracy": 0.6875, "lr": 7.497881880348984e-07, "epoch": 0.2465366129488267, "percentage": 24.66, "elapsed_time": "0:30:13", "remaining_time": "1:32:20"}
+{"current_steps": 110, "total_steps": 442, "loss": 3.7899, "accuracy": 0.7109375, "lr": 7.482418164908931e-07, "epoch": 0.24879841673734804, "percentage": 24.89, "elapsed_time": "0:30:30", "remaining_time": "1:32:05"}
+{"current_steps": 111, "total_steps": 442, "loss": 3.5651, "accuracy": 0.7265625, "lr": 7.466736378735035e-07, "epoch": 0.2510602205258694, "percentage": 25.11, "elapsed_time": "0:30:47", "remaining_time": "1:31:49"}
+{"current_steps": 112, "total_steps": 442, "loss": 3.3517, "accuracy": 0.7265625, "lr": 7.450837503828439e-07, "epoch": 0.2533220243143907, "percentage": 25.34, "elapsed_time": "0:31:01", "remaining_time": "1:31:24"}
+{"current_steps": 113, "total_steps": 442, "loss": 3.435, "accuracy": 0.7421875, "lr": 7.43472253578449e-07, "epoch": 0.2555838281029121, "percentage": 25.57, "elapsed_time": "0:31:19", "remaining_time": "1:31:11"}
+{"current_steps": 114, "total_steps": 442, "loss": 3.3585, "accuracy": 0.734375, "lr": 7.418392483730389e-07, "epoch": 0.2578456318914334, "percentage": 25.79, "elapsed_time": "0:31:35", "remaining_time": "1:30:52"}
+{"current_steps": 115, "total_steps": 442, "loss": 3.7008, "accuracy": 0.71875, "lr": 7.401848370262012e-07, "epoch": 0.26010743567995476, "percentage": 26.02, "elapsed_time": "0:31:50", "remaining_time": "1:30:33"}
+{"current_steps": 116, "total_steps": 442, "loss": 3.7519, "accuracy": 0.734375, "lr": 7.385091231379856e-07, "epoch": 0.2623692394684761, "percentage": 26.24, "elapsed_time": "0:32:10", "remaining_time": "1:30:24"}
+{"current_steps": 117, "total_steps": 442, "loss": 3.4941, "accuracy": 0.703125, "lr": 7.368122116424182e-07, "epoch": 0.26463104325699743, "percentage": 26.47, "elapsed_time": "0:32:28", "remaining_time": "1:30:11"}
+{"current_steps": 118, "total_steps": 442, "loss": 3.2773, "accuracy": 0.7734375, "lr": 7.350942088009289e-07, "epoch": 0.2668928470455188, "percentage": 26.7, "elapsed_time": "0:32:44", "remaining_time": "1:29:54"}
+{"current_steps": 119, "total_steps": 442, "loss": 3.7568, "accuracy": 0.6875, "lr": 7.333552221956986e-07, "epoch": 0.26915465083404017, "percentage": 26.92, "elapsed_time": "0:32:59", "remaining_time": "1:29:34"}
+{"current_steps": 120, "total_steps": 442, "loss": 3.3962, "accuracy": 0.6953125, "lr": 7.315953607229217e-07, "epoch": 0.2714164546225615, "percentage": 27.15, "elapsed_time": "0:33:17", "remaining_time": "1:29:19"}
+{"current_steps": 121, "total_steps": 442, "loss": 3.541, "accuracy": 0.75, "lr": 7.298147345859869e-07, "epoch": 0.27367825841108284, "percentage": 27.38, "elapsed_time": "0:33:34", "remaining_time": "1:29:03"}
+{"current_steps": 122, "total_steps": 442, "loss": 3.2942, "accuracy": 0.7421875, "lr": 7.280134552885762e-07, "epoch": 0.2759400621996042, "percentage": 27.6, "elapsed_time": "0:33:52", "remaining_time": "1:28:52"}
+{"current_steps": 123, "total_steps": 442, "loss": 2.8993, "accuracy": 0.8203125, "lr": 7.261916356276831e-07, "epoch": 0.2782018659881255, "percentage": 27.83, "elapsed_time": "0:34:07", "remaining_time": "1:28:29"}
+{"current_steps": 124, "total_steps": 442, "loss": 3.6222, "accuracy": 0.71875, "lr": 7.243493896865486e-07, "epoch": 0.2804636697766469, "percentage": 28.05, "elapsed_time": "0:34:26", "remaining_time": "1:28:19"}
+{"current_steps": 125, "total_steps": 442, "loss": 3.5839, "accuracy": 0.6875, "lr": 7.224868328275169e-07, "epoch": 0.2827254735651682, "percentage": 28.28, "elapsed_time": "0:34:41", "remaining_time": "1:27:59"}
+{"current_steps": 126, "total_steps": 442, "loss": 4.5346, "accuracy": 0.6953125, "lr": 7.206040816848126e-07, "epoch": 0.28498727735368956, "percentage": 28.51, "elapsed_time": "0:34:57", "remaining_time": "1:27:40"}
+{"current_steps": 127, "total_steps": 442, "loss": 3.4458, "accuracy": 0.6875, "lr": 7.187012541572356e-07, "epoch": 0.2872490811422109, "percentage": 28.73, "elapsed_time": "0:35:13", "remaining_time": "1:27:21"}
+{"current_steps": 128, "total_steps": 442, "loss": 3.2917, "accuracy": 0.7265625, "lr": 7.167784694007791e-07, "epoch": 0.28951088493073224, "percentage": 28.96, "elapsed_time": "0:35:28", "remaining_time": "1:27:01"}
+{"current_steps": 129, "total_steps": 442, "loss": 2.8207, "accuracy": 0.75, "lr": 7.148358478211682e-07, "epoch": 0.2917726887192536, "percentage": 29.19, "elapsed_time": "0:35:45", "remaining_time": "1:26:45"}
+{"current_steps": 130, "total_steps": 442, "loss": 3.3385, "accuracy": 0.6796875, "lr": 7.128735110663187e-07, "epoch": 0.29403449250777497, "percentage": 29.41, "elapsed_time": "0:36:02", "remaining_time": "1:26:28"}
+{"current_steps": 131, "total_steps": 442, "loss": 3.7675, "accuracy": 0.7421875, "lr": 7.108915820187211e-07, "epoch": 0.2962962962962963, "percentage": 29.64, "elapsed_time": "0:36:17", "remaining_time": "1:26:10"}
+{"current_steps": 132, "total_steps": 442, "loss": 4.558, "accuracy": 0.71875, "lr": 7.088901847877447e-07, "epoch": 0.29855810008481765, "percentage": 29.86, "elapsed_time": "0:36:33", "remaining_time": "1:25:50"}
+{"current_steps": 133, "total_steps": 442, "loss": 3.4103, "accuracy": 0.734375, "lr": 7.068694447018658e-07, "epoch": 0.300819903873339, "percentage": 30.09, "elapsed_time": "0:36:50", "remaining_time": "1:25:36"}
+{"current_steps": 134, "total_steps": 442, "loss": 3.4383, "accuracy": 0.7734375, "lr": 7.048294883008199e-07, "epoch": 0.3030817076618603, "percentage": 30.32, "elapsed_time": "0:37:07", "remaining_time": "1:25:19"}
+{"current_steps": 135, "total_steps": 442, "loss": 3.0593, "accuracy": 0.734375, "lr": 7.027704433276776e-07, "epoch": 0.3053435114503817, "percentage": 30.54, "elapsed_time": "0:37:23", "remaining_time": "1:25:01"}
+{"current_steps": 136, "total_steps": 442, "loss": 3.5074, "accuracy": 0.78125, "lr": 7.006924387208452e-07, "epoch": 0.307605315238903, "percentage": 30.77, "elapsed_time": "0:37:41", "remaining_time": "1:24:47"}
+{"current_steps": 137, "total_steps": 442, "loss": 3.691, "accuracy": 0.6875, "lr": 6.985956046059904e-07, "epoch": 0.30986711902742436, "percentage": 31.0, "elapsed_time": "0:37:59", "remaining_time": "1:24:35"}
+{"current_steps": 138, "total_steps": 442, "loss": 3.0089, "accuracy": 0.7734375, "lr": 6.964800722878945e-07, "epoch": 0.31212892281594573, "percentage": 31.22, "elapsed_time": "0:38:16", "remaining_time": "1:24:19"}
+{"current_steps": 139, "total_steps": 442, "loss": 3.5096, "accuracy": 0.6796875, "lr": 6.943459742422287e-07, "epoch": 0.31439072660446704, "percentage": 31.45, "elapsed_time": "0:38:37", "remaining_time": "1:24:12"}
+{"current_steps": 140, "total_steps": 442, "loss": 3.6164, "accuracy": 0.7578125, "lr": 6.921934441072597e-07, "epoch": 0.3166525303929884, "percentage": 31.67, "elapsed_time": "0:38:51", "remaining_time": "1:23:49"}
+{"current_steps": 141, "total_steps": 442, "loss": 3.953, "accuracy": 0.7265625, "lr": 6.900226166754807e-07, "epoch": 0.3189143341815098, "percentage": 31.9, "elapsed_time": "0:39:07", "remaining_time": "1:23:30"}
+{"current_steps": 142, "total_steps": 442, "loss": 4.0009, "accuracy": 0.6875, "lr": 6.8783362788517e-07, "epoch": 0.3211761379700311, "percentage": 32.13, "elapsed_time": "0:39:21", "remaining_time": "1:23:09"}
+{"current_steps": 143, "total_steps": 442, "loss": 3.265, "accuracy": 0.734375, "lr": 6.856266148118796e-07, "epoch": 0.32343794175855245, "percentage": 32.35, "elapsed_time": "0:39:37", "remaining_time": "1:22:51"}
+{"current_steps": 144, "total_steps": 442, "loss": 3.5015, "accuracy": 0.7421875, "lr": 6.834017156598512e-07, "epoch": 0.3256997455470738, "percentage": 32.58, "elapsed_time": "0:39:54", "remaining_time": "1:22:34"}
+{"current_steps": 145, "total_steps": 442, "loss": 3.3848, "accuracy": 0.765625, "lr": 6.811590697533607e-07, "epoch": 0.3279615493355951, "percentage": 32.81, "elapsed_time": "0:40:15", "remaining_time": "1:22:26"}
+{"current_steps": 146, "total_steps": 442, "loss": 3.8778, "accuracy": 0.65625, "lr": 6.788988175279951e-07, "epoch": 0.3302233531241165, "percentage": 33.03, "elapsed_time": "0:40:32", "remaining_time": "1:22:10"}
+{"current_steps": 147, "total_steps": 442, "loss": 2.9708, "accuracy": 0.7890625, "lr": 6.766211005218577e-07, "epoch": 0.3324851569126378, "percentage": 33.26, "elapsed_time": "0:40:49", "remaining_time": "1:21:55"}
+{"current_steps": 148, "total_steps": 442, "loss": 3.2708, "accuracy": 0.796875, "lr": 6.743260613667047e-07, "epoch": 0.33474696070115917, "percentage": 33.48, "elapsed_time": "0:41:05", "remaining_time": "1:21:36"}
+{"current_steps": 149, "total_steps": 442, "loss": 3.1961, "accuracy": 0.75, "lr": 6.720138437790139e-07, "epoch": 0.33700876448968053, "percentage": 33.71, "elapsed_time": "0:41:23", "remaining_time": "1:21:23"}
+{"current_steps": 150, "total_steps": 442, "loss": 3.6883, "accuracy": 0.703125, "lr": 6.696845925509848e-07, "epoch": 0.33927056827820185, "percentage": 33.94, "elapsed_time": "0:41:41", "remaining_time": "1:21:09"}
+{"current_steps": 151, "total_steps": 442, "loss": 3.9923, "accuracy": 0.6796875, "lr": 6.673384535414718e-07, "epoch": 0.3415323720667232, "percentage": 34.16, "elapsed_time": "0:41:58", "remaining_time": "1:20:53"}
+{"current_steps": 152, "total_steps": 442, "loss": 2.7389, "accuracy": 0.828125, "lr": 6.649755736668511e-07, "epoch": 0.3437941758552446, "percentage": 34.39, "elapsed_time": "0:42:13", "remaining_time": "1:20:33"}
+{"current_steps": 153, "total_steps": 442, "loss": 2.8879, "accuracy": 0.7578125, "lr": 6.625961008918192e-07, "epoch": 0.3460559796437659, "percentage": 34.62, "elapsed_time": "0:42:31", "remaining_time": "1:20:18"}
+{"current_steps": 154, "total_steps": 442, "loss": 3.8502, "accuracy": 0.734375, "lr": 6.602001842201289e-07, "epoch": 0.34831778343228725, "percentage": 34.84, "elapsed_time": "0:42:46", "remaining_time": "1:20:00"}
+{"current_steps": 155, "total_steps": 442, "loss": 3.789, "accuracy": 0.671875, "lr": 6.577879736852571e-07, "epoch": 0.3505795872208086, "percentage": 35.07, "elapsed_time": "0:43:05", "remaining_time": "1:19:46"}
+{"current_steps": 156, "total_steps": 442, "loss": 2.5342, "accuracy": 0.7890625, "lr": 6.553596203410112e-07, "epoch": 0.35284139100932993, "percentage": 35.29, "elapsed_time": "0:43:20", "remaining_time": "1:19:27"}
+{"current_steps": 157, "total_steps": 442, "loss": 3.3879, "accuracy": 0.734375, "lr": 6.529152762520688e-07, "epoch": 0.3551031947978513, "percentage": 35.52, "elapsed_time": "0:43:38", "remaining_time": "1:19:12"}
+{"current_steps": 158, "total_steps": 442, "loss": 3.4617, "accuracy": 0.7265625, "lr": 6.504550944844558e-07, "epoch": 0.3573649985863726, "percentage": 35.75, "elapsed_time": "0:43:53", "remaining_time": "1:18:54"}
+{"current_steps": 159, "total_steps": 442, "loss": 3.03, "accuracy": 0.78125, "lr": 6.479792290959613e-07, "epoch": 0.359626802374894, "percentage": 35.97, "elapsed_time": "0:44:11", "remaining_time": "1:18:38"}
+{"current_steps": 160, "total_steps": 442, "loss": 3.5175, "accuracy": 0.6796875, "lr": 6.454878351264906e-07, "epoch": 0.36188860616341534, "percentage": 36.2, "elapsed_time": "0:44:24", "remaining_time": "1:18:16"}
+{"current_steps": 161, "total_steps": 442, "loss": 3.1092, "accuracy": 0.796875, "lr": 6.429810685883565e-07, "epoch": 0.36415040995193665, "percentage": 36.43, "elapsed_time": "0:44:43", "remaining_time": "1:18:03"}
+{"current_steps": 162, "total_steps": 442, "loss": 3.8613, "accuracy": 0.734375, "lr": 6.404590864565088e-07, "epoch": 0.366412213740458, "percentage": 36.65, "elapsed_time": "0:45:02", "remaining_time": "1:17:50"}
+{"current_steps": 163, "total_steps": 442, "loss": 3.0171, "accuracy": 0.8359375, "lr": 6.379220466587063e-07, "epoch": 0.3686740175289794, "percentage": 36.88, "elapsed_time": "0:45:18", "remaining_time": "1:17:32"}
+{"current_steps": 164, "total_steps": 442, "loss": 3.4067, "accuracy": 0.7734375, "lr": 6.353701080656254e-07, "epoch": 0.3709358213175007, "percentage": 37.1, "elapsed_time": "0:45:32", "remaining_time": "1:17:12"}
+{"current_steps": 165, "total_steps": 442, "loss": 3.3279, "accuracy": 0.7578125, "lr": 6.32803430480913e-07, "epoch": 0.37319762510602206, "percentage": 37.33, "elapsed_time": "0:45:53", "remaining_time": "1:17:02"}
+{"current_steps": 166, "total_steps": 442, "loss": 3.3934, "accuracy": 0.734375, "lr": 6.302221746311782e-07, "epoch": 0.3754594288945434, "percentage": 37.56, "elapsed_time": "0:46:08", "remaining_time": "1:16:42"}
+{"current_steps": 167, "total_steps": 442, "loss": 3.7992, "accuracy": 0.703125, "lr": 6.276265021559288e-07, "epoch": 0.37772123268306473, "percentage": 37.78, "elapsed_time": "0:46:25", "remaining_time": "1:16:26"}
+{"current_steps": 168, "total_steps": 442, "loss": 3.0053, "accuracy": 0.7265625, "lr": 6.250165755974487e-07, "epoch": 0.3799830364715861, "percentage": 38.01, "elapsed_time": "0:46:44", "remaining_time": "1:16:13"}
+{"current_steps": 169, "total_steps": 442, "loss": 3.0164, "accuracy": 0.7421875, "lr": 6.223925583906192e-07, "epoch": 0.3822448402601074, "percentage": 38.24, "elapsed_time": "0:47:02", "remaining_time": "1:15:58"}
+{"current_steps": 170, "total_steps": 442, "loss": 2.992, "accuracy": 0.8046875, "lr": 6.19754614852685e-07, "epoch": 0.3845066440486288, "percentage": 38.46, "elapsed_time": "0:47:19", "remaining_time": "1:15:43"}
+{"current_steps": 171, "total_steps": 442, "loss": 3.0985, "accuracy": 0.78125, "lr": 6.171029101729644e-07, "epoch": 0.38676844783715014, "percentage": 38.69, "elapsed_time": "0:47:37", "remaining_time": "1:15:28"}
+{"current_steps": 172, "total_steps": 442, "loss": 2.8953, "accuracy": 0.796875, "lr": 6.144376104025055e-07, "epoch": 0.38903025162567145, "percentage": 38.91, "elapsed_time": "0:47:54", "remaining_time": "1:15:12"}
+{"current_steps": 173, "total_steps": 442, "loss": 3.5203, "accuracy": 0.703125, "lr": 6.117588824436873e-07, "epoch": 0.3912920554141928, "percentage": 39.14, "elapsed_time": "0:48:10", "remaining_time": "1:14:53"}
+{"current_steps": 174, "total_steps": 442, "loss": 2.8987, "accuracy": 0.7734375, "lr": 6.090668940397688e-07, "epoch": 0.3935538592027142, "percentage": 39.37, "elapsed_time": "0:48:26", "remaining_time": "1:14:36"}
+{"current_steps": 175, "total_steps": 442, "loss": 2.9943, "accuracy": 0.78125, "lr": 6.063618137643844e-07, "epoch": 0.3958156629912355, "percentage": 39.59, "elapsed_time": "0:48:40", "remaining_time": "1:14:16"}
+{"current_steps": 176, "total_steps": 442, "loss": 2.9707, "accuracy": 0.765625, "lr": 6.03643811010988e-07, "epoch": 0.39807746677975686, "percentage": 39.82, "elapsed_time": "0:48:57", "remaining_time": "1:13:59"}
+{"current_steps": 177, "total_steps": 442, "loss": 4.0276, "accuracy": 0.6640625, "lr": 6.009130559822453e-07, "epoch": 0.4003392705682782, "percentage": 40.05, "elapsed_time": "0:49:13", "remaining_time": "1:13:41"}
+{"current_steps": 178, "total_steps": 442, "loss": 2.6604, "accuracy": 0.796875, "lr": 5.981697196793758e-07, "epoch": 0.40260107435679954, "percentage": 40.27, "elapsed_time": "0:49:30", "remaining_time": "1:13:25"}
+{"current_steps": 179, "total_steps": 442, "loss": 3.0403, "accuracy": 0.734375, "lr": 5.954139738914446e-07, "epoch": 0.4048628781453209, "percentage": 40.5, "elapsed_time": "0:49:44", "remaining_time": "1:13:05"}
+{"current_steps": 180, "total_steps": 442, "loss": 2.8079, "accuracy": 0.7734375, "lr": 5.92645991184605e-07, "epoch": 0.4071246819338422, "percentage": 40.72, "elapsed_time": "0:50:01", "remaining_time": "1:12:49"}
+{"current_steps": 181, "total_steps": 442, "loss": 3.2278, "accuracy": 0.734375, "lr": 5.898659448912917e-07, "epoch": 0.4093864857223636, "percentage": 40.95, "elapsed_time": "0:50:18", "remaining_time": "1:12:33"}
+{"current_steps": 182, "total_steps": 442, "loss": 2.726, "accuracy": 0.8125, "lr": 5.870740090993676e-07, "epoch": 0.41164828951088495, "percentage": 41.18, "elapsed_time": "0:50:35", "remaining_time": "1:12:16"}
+{"current_steps": 183, "total_steps": 442, "loss": 3.7509, "accuracy": 0.7109375, "lr": 5.842703586412214e-07, "epoch": 0.41391009329940626, "percentage": 41.4, "elapsed_time": "0:50:53", "remaining_time": "1:12:01"}
+{"current_steps": 184, "total_steps": 442, "loss": 2.9234, "accuracy": 0.796875, "lr": 5.814551690828203e-07, "epoch": 0.4161718970879276, "percentage": 41.63, "elapsed_time": "0:51:08", "remaining_time": "1:11:42"}
+{"current_steps": 185, "total_steps": 442, "loss": 3.094, "accuracy": 0.7578125, "lr": 5.786286167127155e-07, "epoch": 0.418433700876449, "percentage": 41.86, "elapsed_time": "0:51:25", "remaining_time": "1:11:25"}
+{"current_steps": 186, "total_steps": 442, "loss": 3.2427, "accuracy": 0.765625, "lr": 5.757908785310031e-07, "epoch": 0.4206955046649703, "percentage": 42.08, "elapsed_time": "0:51:40", "remaining_time": "1:11:07"}
+{"current_steps": 187, "total_steps": 442, "loss": 2.862, "accuracy": 0.75, "lr": 5.729421322382399e-07, "epoch": 0.42295730845349166, "percentage": 42.31, "elapsed_time": "0:51:57", "remaining_time": "1:10:51"}
+{"current_steps": 188, "total_steps": 442, "loss": 2.8991, "accuracy": 0.7578125, "lr": 5.700825562243163e-07, "epoch": 0.42521911224201303, "percentage": 42.53, "elapsed_time": "0:52:16", "remaining_time": "1:10:37"}
+{"current_steps": 189, "total_steps": 442, "loss": 2.8708, "accuracy": 0.734375, "lr": 5.672123295572854e-07, "epoch": 0.42748091603053434, "percentage": 42.76, "elapsed_time": "0:52:34", "remaining_time": "1:10:22"}
+{"current_steps": 190, "total_steps": 442, "loss": 3.5312, "accuracy": 0.6953125, "lr": 5.643316319721487e-07, "epoch": 0.4297427198190557, "percentage": 42.99, "elapsed_time": "0:52:51", "remaining_time": "1:10:06"}
+{"current_steps": 191, "total_steps": 442, "loss": 3.3801, "accuracy": 0.7109375, "lr": 5.614406438596026e-07, "epoch": 0.432004523607577, "percentage": 43.21, "elapsed_time": "0:53:08", "remaining_time": "1:09:49"}
+{"current_steps": 192, "total_steps": 442, "loss": 3.4023, "accuracy": 0.703125, "lr": 5.585395462547406e-07, "epoch": 0.4342663273960984, "percentage": 43.44, "elapsed_time": "0:53:26", "remaining_time": "1:09:34"}
+{"current_steps": 193, "total_steps": 442, "loss": 3.3482, "accuracy": 0.7109375, "lr": 5.55628520825718e-07, "epoch": 0.43652813118461975, "percentage": 43.67, "elapsed_time": "0:53:42", "remaining_time": "1:09:17"}
+{"current_steps": 194, "total_steps": 442, "loss": 2.9719, "accuracy": 0.796875, "lr": 5.527077498623752e-07, "epoch": 0.43878993497314106, "percentage": 43.89, "elapsed_time": "0:54:00", "remaining_time": "1:09:03"}
+{"current_steps": 195, "total_steps": 442, "loss": 2.7626, "accuracy": 0.78125, "lr": 5.497774162648228e-07, "epoch": 0.4410517387616624, "percentage": 44.12, "elapsed_time": "0:54:18", "remaining_time": "1:08:47"}
+{"current_steps": 196, "total_steps": 442, "loss": 3.0469, "accuracy": 0.7109375, "lr": 5.468377035319882e-07, "epoch": 0.4433135425501838, "percentage": 44.34, "elapsed_time": "0:54:33", "remaining_time": "1:08:29"}
+{"current_steps": 197, "total_steps": 442, "loss": 3.1804, "accuracy": 0.7265625, "lr": 5.438887957501248e-07, "epoch": 0.4455753463387051, "percentage": 44.57, "elapsed_time": "0:54:49", "remaining_time": "1:08:10"}
+{"current_steps": 198, "total_steps": 442, "loss": 3.3267, "accuracy": 0.71875, "lr": 5.409308775812844e-07, "epoch": 0.44783715012722647, "percentage": 44.8, "elapsed_time": "0:55:05", "remaining_time": "1:07:53"}
+{"current_steps": 199, "total_steps": 442, "loss": 2.9717, "accuracy": 0.75, "lr": 5.379641342517541e-07, "epoch": 0.45009895391574783, "percentage": 45.02, "elapsed_time": "0:55:22", "remaining_time": "1:07:36"}
+{"current_steps": 200, "total_steps": 442, "loss": 2.6106, "accuracy": 0.7734375, "lr": 5.349887515404564e-07, "epoch": 0.45236075770426915, "percentage": 45.25, "elapsed_time": "0:55:38", "remaining_time": "1:07:19"}
+{"current_steps": 201, "total_steps": 442, "loss": 2.8006, "accuracy": 0.7734375, "lr": 5.320049157673163e-07, "epoch": 0.4546225614927905, "percentage": 45.48, "elapsed_time": "0:55:55", "remaining_time": "1:07:03"}
+{"current_steps": 202, "total_steps": 442, "loss": 2.6128, "accuracy": 0.7890625, "lr": 5.290128137815938e-07, "epoch": 0.4568843652813118, "percentage": 45.7, "elapsed_time": "0:56:14", "remaining_time": "1:06:49"}
+{"current_steps": 203, "total_steps": 442, "loss": 2.4693, "accuracy": 0.7890625, "lr": 5.260126329501828e-07, "epoch": 0.4591461690698332, "percentage": 45.93, "elapsed_time": "0:56:28", "remaining_time": "1:06:28"}
+{"current_steps": 204, "total_steps": 442, "loss": 2.9617, "accuracy": 0.78125, "lr": 5.230045611458789e-07, "epoch": 0.46140797285835455, "percentage": 46.15, "elapsed_time": "0:56:44", "remaining_time": "1:06:11"}
+{"current_steps": 205, "total_steps": 442, "loss": 2.5375, "accuracy": 0.7734375, "lr": 5.199887867356143e-07, "epoch": 0.46366977664687586, "percentage": 46.38, "elapsed_time": "0:57:01", "remaining_time": "1:05:55"}
+{"current_steps": 206, "total_steps": 442, "loss": 2.7563, "accuracy": 0.796875, "lr": 5.16965498568662e-07, "epoch": 0.46593158043539723, "percentage": 46.61, "elapsed_time": "0:57:18", "remaining_time": "1:05:38"}
+{"current_steps": 207, "total_steps": 442, "loss": 2.9053, "accuracy": 0.765625, "lr": 5.139348859648098e-07, "epoch": 0.4681933842239186, "percentage": 46.83, "elapsed_time": "0:57:33", "remaining_time": "1:05:20"}
+{"current_steps": 208, "total_steps": 442, "loss": 3.3148, "accuracy": 0.7421875, "lr": 5.10897138702506e-07, "epoch": 0.4704551880124399, "percentage": 47.06, "elapsed_time": "0:57:47", "remaining_time": "1:05:01"}
+{"current_steps": 209, "total_steps": 442, "loss": 2.3755, "accuracy": 0.828125, "lr": 5.078524470069743e-07, "epoch": 0.4727169918009613, "percentage": 47.29, "elapsed_time": "0:58:04", "remaining_time": "1:04:44"}
+{"current_steps": 210, "total_steps": 442, "loss": 2.3901, "accuracy": 0.765625, "lr": 5.048010015383021e-07, "epoch": 0.47497879558948264, "percentage": 47.51, "elapsed_time": "0:58:23", "remaining_time": "1:04:31"}
+{"current_steps": 211, "total_steps": 442, "loss": 2.4793, "accuracy": 0.8125, "lr": 5.01742993379502e-07, "epoch": 0.47724059937800395, "percentage": 47.74, "elapsed_time": "0:58:40", "remaining_time": "1:04:14"}
+{"current_steps": 212, "total_steps": 442, "loss": 3.0145, "accuracy": 0.7265625, "lr": 4.986786140245446e-07, "epoch": 0.4795024031665253, "percentage": 47.96, "elapsed_time": "0:58:58", "remaining_time": "1:03:58"}
+{"current_steps": 213, "total_steps": 442, "loss": 2.8036, "accuracy": 0.7890625, "lr": 4.956080553663687e-07, "epoch": 0.4817642069550466, "percentage": 48.19, "elapsed_time": "0:59:16", "remaining_time": "1:03:44"}
+{"current_steps": 214, "total_steps": 442, "loss": 2.5133, "accuracy": 0.8125, "lr": 4.925315096848636e-07, "epoch": 0.484026010743568, "percentage": 48.42, "elapsed_time": "0:59:33", "remaining_time": "1:03:27"}
+{"current_steps": 215, "total_steps": 442, "loss": 3.0521, "accuracy": 0.78125, "lr": 4.894491696348293e-07, "epoch": 0.48628781453208936, "percentage": 48.64, "elapsed_time": "0:59:47", "remaining_time": "1:03:07"}
+{"current_steps": 216, "total_steps": 442, "loss": 3.0894, "accuracy": 0.703125, "lr": 4.863612282339116e-07, "epoch": 0.48854961832061067, "percentage": 48.87, "elapsed_time": "1:00:05", "remaining_time": "1:02:52"}
+{"current_steps": 217, "total_steps": 442, "loss": 3.2773, "accuracy": 0.71875, "lr": 4.832678788505161e-07, "epoch": 0.49081142210913203, "percentage": 49.1, "elapsed_time": "1:00:22", "remaining_time": "1:02:35"}
+{"current_steps": 218, "total_steps": 442, "loss": 2.7277, "accuracy": 0.7890625, "lr": 4.801693151916985e-07, "epoch": 0.4930732258976534, "percentage": 49.32, "elapsed_time": "1:00:36", "remaining_time": "1:02:16"}
+{"current_steps": 219, "total_steps": 442, "loss": 3.2197, "accuracy": 0.7109375, "lr": 4.770657312910354e-07, "epoch": 0.4953350296861747, "percentage": 49.55, "elapsed_time": "1:00:52", "remaining_time": "1:01:59"}
+{"current_steps": 220, "total_steps": 442, "loss": 2.939, "accuracy": 0.7421875, "lr": 4.739573214964729e-07, "epoch": 0.4975968334746961, "percentage": 49.77, "elapsed_time": "1:01:11", "remaining_time": "1:01:44"}
+{"current_steps": 221, "total_steps": 442, "loss": 3.0027, "accuracy": 0.78125, "lr": 4.7084428045815733e-07, "epoch": 0.49985863726321744, "percentage": 50.0, "elapsed_time": "1:01:27", "remaining_time": "1:01:27"}
+{"current_steps": 222, "total_steps": 442, "loss": 2.9436, "accuracy": 0.75, "lr": 4.677268031162457e-07, "epoch": 0.5021204410517388, "percentage": 50.23, "elapsed_time": "1:01:45", "remaining_time": "1:01:11"}
+{"current_steps": 223, "total_steps": 442, "loss": 2.4596, "accuracy": 0.8046875, "lr": 4.646050846886985e-07, "epoch": 0.5043822448402601, "percentage": 50.45, "elapsed_time": "1:02:00", "remaining_time": "1:00:53"}
+{"current_steps": 224, "total_steps": 442, "loss": 3.3481, "accuracy": 0.765625, "lr": 4.6147932065905494e-07, "epoch": 0.5066440486287814, "percentage": 50.68, "elapsed_time": "1:02:16", "remaining_time": "1:00:36"}
+{"current_steps": 225, "total_steps": 442, "loss": 2.8019, "accuracy": 0.7421875, "lr": 4.5834970676419214e-07, "epoch": 0.5089058524173028, "percentage": 50.9, "elapsed_time": "1:02:32", "remaining_time": "1:00:18"}
+{"current_steps": 226, "total_steps": 442, "loss": 2.539, "accuracy": 0.859375, "lr": 4.552164389820673e-07, "epoch": 0.5111676562058242, "percentage": 51.13, "elapsed_time": "1:02:51", "remaining_time": "1:00:04"}
+{"current_steps": 227, "total_steps": 442, "loss": 3.3887, "accuracy": 0.734375, "lr": 4.5207971351944605e-07, "epoch": 0.5134294599943455, "percentage": 51.36, "elapsed_time": "1:03:05", "remaining_time": "0:59:45"}
+{"current_steps": 228, "total_steps": 442, "loss": 2.96, "accuracy": 0.7734375, "lr": 4.489397267996157e-07, "epoch": 0.5156912637828668, "percentage": 51.58, "elapsed_time": "1:03:24", "remaining_time": "0:59:30"}
+{"current_steps": 229, "total_steps": 442, "loss": 2.6745, "accuracy": 0.765625, "lr": 4.45796675450085e-07, "epoch": 0.5179530675713881, "percentage": 51.81, "elapsed_time": "1:03:40", "remaining_time": "0:59:13"}
+{"current_steps": 230, "total_steps": 442, "loss": 2.7029, "accuracy": 0.828125, "lr": 4.4265075629027126e-07, "epoch": 0.5202148713599095, "percentage": 52.04, "elapsed_time": "1:03:55", "remaining_time": "0:58:55"}
+{"current_steps": 231, "total_steps": 442, "loss": 2.6628, "accuracy": 0.78125, "lr": 4.3950216631917563e-07, "epoch": 0.5224766751484309, "percentage": 52.26, "elapsed_time": "1:04:13", "remaining_time": "0:58:39"}
+{"current_steps": 232, "total_steps": 442, "loss": 2.148, "accuracy": 0.8359375, "lr": 4.3635110270304676e-07, "epoch": 0.5247384789369522, "percentage": 52.49, "elapsed_time": "1:04:30", "remaining_time": "0:58:23"}
+{"current_steps": 233, "total_steps": 442, "loss": 2.7551, "accuracy": 0.8046875, "lr": 4.331977627630339e-07, "epoch": 0.5270002827254736, "percentage": 52.71, "elapsed_time": "1:04:46", "remaining_time": "0:58:06"}
+{"current_steps": 234, "total_steps": 442, "loss": 2.5606, "accuracy": 0.7890625, "lr": 4.300423439628313e-07, "epoch": 0.5292620865139949, "percentage": 52.94, "elapsed_time": "1:05:01", "remaining_time": "0:57:48"}
+{"current_steps": 235, "total_steps": 442, "loss": 2.584, "accuracy": 0.765625, "lr": 4.268850438963118e-07, "epoch": 0.5315238903025162, "percentage": 53.17, "elapsed_time": "1:05:18", "remaining_time": "0:57:31"}
+{"current_steps": 236, "total_steps": 442, "loss": 2.9659, "accuracy": 0.7421875, "lr": 4.2372606027515463e-07, "epoch": 0.5337856940910376, "percentage": 53.39, "elapsed_time": "1:05:33", "remaining_time": "0:57:13"}
+{"current_steps": 237, "total_steps": 442, "loss": 2.9693, "accuracy": 0.75, "lr": 4.2056559091646387e-07, "epoch": 0.536047497879559, "percentage": 53.62, "elapsed_time": "1:05:51", "remaining_time": "0:56:57"}
+{"current_steps": 238, "total_steps": 442, "loss": 2.8123, "accuracy": 0.796875, "lr": 4.1740383373038116e-07, "epoch": 0.5383093016680803, "percentage": 53.85, "elapsed_time": "1:06:06", "remaining_time": "0:56:40"}
+{"current_steps": 239, "total_steps": 442, "loss": 3.2117, "accuracy": 0.734375, "lr": 4.1424098670769255e-07, "epoch": 0.5405711054566016, "percentage": 54.07, "elapsed_time": "1:06:24", "remaining_time": "0:56:24"}
+{"current_steps": 240, "total_steps": 442, "loss": 2.8325, "accuracy": 0.8046875, "lr": 4.1107724790743007e-07, "epoch": 0.542832909245123, "percentage": 54.3, "elapsed_time": "1:06:40", "remaining_time": "0:56:07"}
+{"current_steps": 241, "total_steps": 442, "loss": 2.3828, "accuracy": 0.8125, "lr": 4.0791281544446947e-07, "epoch": 0.5450947130336443, "percentage": 54.52, "elapsed_time": "1:06:55", "remaining_time": "0:55:48"}
+{"current_steps": 242, "total_steps": 442, "loss": 3.3288, "accuracy": 0.7109375, "lr": 4.0474788747712416e-07, "epoch": 0.5473565168221657, "percentage": 54.75, "elapsed_time": "1:07:10", "remaining_time": "0:55:31"}
+{"current_steps": 243, "total_steps": 442, "loss": 2.4764, "accuracy": 0.8359375, "lr": 4.0158266219473573e-07, "epoch": 0.549618320610687, "percentage": 54.98, "elapsed_time": "1:07:29", "remaining_time": "0:55:16"}
+{"current_steps": 244, "total_steps": 442, "loss": 2.6619, "accuracy": 0.7734375, "lr": 3.984173378052643e-07, "epoch": 0.5518801243992084, "percentage": 55.2, "elapsed_time": "1:07:46", "remaining_time": "0:54:59"}
+{"current_steps": 245, "total_steps": 442, "loss": 2.5828, "accuracy": 0.8046875, "lr": 3.9525211252287585e-07, "epoch": 0.5541419281877297, "percentage": 55.43, "elapsed_time": "1:07:59", "remaining_time": "0:54:40"}
+{"current_steps": 246, "total_steps": 442, "loss": 2.385, "accuracy": 0.796875, "lr": 3.920871845555305e-07, "epoch": 0.556403731976251, "percentage": 55.66, "elapsed_time": "1:08:14", "remaining_time": "0:54:22"}
+{"current_steps": 247, "total_steps": 442, "loss": 2.7693, "accuracy": 0.78125, "lr": 3.8892275209256984e-07, "epoch": 0.5586655357647724, "percentage": 55.88, "elapsed_time": "1:08:30", "remaining_time": "0:54:05"}
+{"current_steps": 248, "total_steps": 442, "loss": 2.9864, "accuracy": 0.7578125, "lr": 3.8575901329230747e-07, "epoch": 0.5609273395532938, "percentage": 56.11, "elapsed_time": "1:08:49", "remaining_time": "0:53:50"}
+{"current_steps": 249, "total_steps": 442, "loss": 2.4375, "accuracy": 0.8203125, "lr": 3.8259616626961886e-07, "epoch": 0.5631891433418151, "percentage": 56.33, "elapsed_time": "1:09:06", "remaining_time": "0:53:34"}
+{"current_steps": 250, "total_steps": 442, "loss": 2.8436, "accuracy": 0.734375, "lr": 3.794344090835362e-07, "epoch": 0.5654509471303364, "percentage": 56.56, "elapsed_time": "1:09:21", "remaining_time": "0:53:16"}
+{"current_steps": 251, "total_steps": 442, "loss": 3.303, "accuracy": 0.6796875, "lr": 3.7627393972484534e-07, "epoch": 0.5677127509188578, "percentage": 56.79, "elapsed_time": "1:09:35", "remaining_time": "0:52:57"}
+{"current_steps": 252, "total_steps": 442, "loss": 2.7301, "accuracy": 0.8046875, "lr": 3.7311495610368823e-07, "epoch": 0.5699745547073791, "percentage": 57.01, "elapsed_time": "1:09:52", "remaining_time": "0:52:40"}
+{"current_steps": 253, "total_steps": 442, "loss": 2.1306, "accuracy": 0.8125, "lr": 3.699576560371689e-07, "epoch": 0.5722363584959005, "percentage": 57.24, "elapsed_time": "1:10:08", "remaining_time": "0:52:23"}
+{"current_steps": 254, "total_steps": 442, "loss": 2.4779, "accuracy": 0.7890625, "lr": 3.66802237236966e-07, "epoch": 0.5744981622844219, "percentage": 57.47, "elapsed_time": "1:10:25", "remaining_time": "0:52:07"}
+{"current_steps": 255, "total_steps": 442, "loss": 2.7067, "accuracy": 0.7890625, "lr": 3.636488972969532e-07, "epoch": 0.5767599660729432, "percentage": 57.69, "elapsed_time": "1:10:41", "remaining_time": "0:51:50"}
+{"current_steps": 256, "total_steps": 442, "loss": 2.7346, "accuracy": 0.7890625, "lr": 3.604978336808244e-07, "epoch": 0.5790217698614645, "percentage": 57.92, "elapsed_time": "1:10:57", "remaining_time": "0:51:33"}
+{"current_steps": 257, "total_steps": 442, "loss": 3.0486, "accuracy": 0.7734375, "lr": 3.5734924370972876e-07, "epoch": 0.5812835736499858, "percentage": 58.14, "elapsed_time": "1:11:13", "remaining_time": "0:51:16"}
+{"current_steps": 258, "total_steps": 442, "loss": 3.0441, "accuracy": 0.7421875, "lr": 3.5420332454991504e-07, "epoch": 0.5835453774385072, "percentage": 58.37, "elapsed_time": "1:11:27", "remaining_time": "0:50:57"}
+{"current_steps": 259, "total_steps": 442, "loss": 2.6279, "accuracy": 0.7734375, "lr": 3.510602732003843e-07, "epoch": 0.5858071812270286, "percentage": 58.6, "elapsed_time": "1:11:45", "remaining_time": "0:50:41"}
+{"current_steps": 260, "total_steps": 442, "loss": 2.8402, "accuracy": 0.78125, "lr": 3.4792028648055396e-07, "epoch": 0.5880689850155499, "percentage": 58.82, "elapsed_time": "1:12:00", "remaining_time": "0:50:24"}
+{"current_steps": 261, "total_steps": 442, "loss": 2.5099, "accuracy": 0.8125, "lr": 3.447835610179327e-07, "epoch": 0.5903307888040712, "percentage": 59.05, "elapsed_time": "1:12:17", "remaining_time": "0:50:07"}
+{"current_steps": 262, "total_steps": 442, "loss": 3.191, "accuracy": 0.7421875, "lr": 3.416502932358079e-07, "epoch": 0.5925925925925926, "percentage": 59.28, "elapsed_time": "1:12:34", "remaining_time": "0:49:51"}
+{"current_steps": 263, "total_steps": 442, "loss": 2.657, "accuracy": 0.8125, "lr": 3.385206793409451e-07, "epoch": 0.5948543963811139, "percentage": 59.5, "elapsed_time": "1:12:51", "remaining_time": "0:49:35"}
+{"current_steps": 264, "total_steps": 442, "loss": 2.4892, "accuracy": 0.8125, "lr": 3.3539491531130163e-07, "epoch": 0.5971162001696353, "percentage": 59.73, "elapsed_time": "1:13:10", "remaining_time": "0:49:20"}
+{"current_steps": 265, "total_steps": 442, "loss": 2.6008, "accuracy": 0.796875, "lr": 3.3227319688375426e-07, "epoch": 0.5993780039581567, "percentage": 59.95, "elapsed_time": "1:13:25", "remaining_time": "0:49:02"}
+{"current_steps": 266, "total_steps": 442, "loss": 3.1704, "accuracy": 0.75, "lr": 3.291557195418427e-07, "epoch": 0.601639807746678, "percentage": 60.18, "elapsed_time": "1:13:42", "remaining_time": "0:48:45"}
+{"current_steps": 267, "total_steps": 442, "loss": 3.3689, "accuracy": 0.703125, "lr": 3.260426785035272e-07, "epoch": 0.6039016115351993, "percentage": 60.41, "elapsed_time": "1:13:57", "remaining_time": "0:48:28"}
+{"current_steps": 268, "total_steps": 442, "loss": 2.6359, "accuracy": 0.796875, "lr": 3.229342687089646e-07, "epoch": 0.6061634153237206, "percentage": 60.63, "elapsed_time": "1:14:14", "remaining_time": "0:48:11"}
+{"current_steps": 269, "total_steps": 442, "loss": 2.6094, "accuracy": 0.765625, "lr": 3.1983068480830143e-07, "epoch": 0.608425219112242, "percentage": 60.86, "elapsed_time": "1:14:29", "remaining_time": "0:47:54"}
+{"current_steps": 270, "total_steps": 442, "loss": 2.5696, "accuracy": 0.84375, "lr": 3.1673212114948387e-07, "epoch": 0.6106870229007634, "percentage": 61.09, "elapsed_time": "1:14:46", "remaining_time": "0:47:38"}
+{"current_steps": 271, "total_steps": 442, "loss": 2.721, "accuracy": 0.78125, "lr": 3.1363877176608845e-07, "epoch": 0.6129488266892847, "percentage": 61.31, "elapsed_time": "1:15:05", "remaining_time": "0:47:23"}
+{"current_steps": 272, "total_steps": 442, "loss": 2.5416, "accuracy": 0.8203125, "lr": 3.1055083036517076e-07, "epoch": 0.615210630477806, "percentage": 61.54, "elapsed_time": "1:15:24", "remaining_time": "0:47:07"}
+{"current_steps": 273, "total_steps": 442, "loss": 2.4568, "accuracy": 0.7734375, "lr": 3.074684903151364e-07, "epoch": 0.6174724342663274, "percentage": 61.76, "elapsed_time": "1:15:40", "remaining_time": "0:46:50"}
+{"current_steps": 274, "total_steps": 442, "loss": 3.0769, "accuracy": 0.75, "lr": 3.0439194463363136e-07, "epoch": 0.6197342380548487, "percentage": 61.99, "elapsed_time": "1:15:57", "remaining_time": "0:46:34"}
+{"current_steps": 275, "total_steps": 442, "loss": 2.5638, "accuracy": 0.796875, "lr": 3.0132138597545537e-07, "epoch": 0.6219960418433701, "percentage": 62.22, "elapsed_time": "1:16:13", "remaining_time": "0:46:17"}
+{"current_steps": 276, "total_steps": 442, "loss": 2.8045, "accuracy": 0.7890625, "lr": 2.982570066204981e-07, "epoch": 0.6242578456318915, "percentage": 62.44, "elapsed_time": "1:16:30", "remaining_time": "0:46:01"}
+{"current_steps": 277, "total_steps": 442, "loss": 3.2425, "accuracy": 0.765625, "lr": 2.951989984616979e-07, "epoch": 0.6265196494204128, "percentage": 62.67, "elapsed_time": "1:16:48", "remaining_time": "0:45:45"}
+{"current_steps": 278, "total_steps": 442, "loss": 2.1795, "accuracy": 0.7890625, "lr": 2.9214755299302584e-07, "epoch": 0.6287814532089341, "percentage": 62.9, "elapsed_time": "1:17:03", "remaining_time": "0:45:27"}
+{"current_steps": 279, "total_steps": 442, "loss": 3.1683, "accuracy": 0.7421875, "lr": 2.89102861297494e-07, "epoch": 0.6310432569974554, "percentage": 63.12, "elapsed_time": "1:17:21", "remaining_time": "0:45:11"}
+{"current_steps": 280, "total_steps": 442, "loss": 2.8367, "accuracy": 0.8046875, "lr": 2.860651140351902e-07, "epoch": 0.6333050607859768, "percentage": 63.35, "elapsed_time": "1:17:41", "remaining_time": "0:44:56"}
+{"current_steps": 281, "total_steps": 442, "loss": 2.0959, "accuracy": 0.8359375, "lr": 2.830345014313381e-07, "epoch": 0.6355668645744982, "percentage": 63.57, "elapsed_time": "1:17:56", "remaining_time": "0:44:39"}
+{"current_steps": 282, "total_steps": 442, "loss": 2.6367, "accuracy": 0.7578125, "lr": 2.800112132643856e-07, "epoch": 0.6378286683630195, "percentage": 63.8, "elapsed_time": "1:18:12", "remaining_time": "0:44:22"}
+{"current_steps": 283, "total_steps": 442, "loss": 2.2448, "accuracy": 0.8203125, "lr": 2.7699543885412105e-07, "epoch": 0.6400904721515408, "percentage": 64.03, "elapsed_time": "1:18:32", "remaining_time": "0:44:07"}
+{"current_steps": 284, "total_steps": 442, "loss": 2.4145, "accuracy": 0.796875, "lr": 2.7398736704981725e-07, "epoch": 0.6423522759400622, "percentage": 64.25, "elapsed_time": "1:18:47", "remaining_time": "0:43:50"}
+{"current_steps": 285, "total_steps": 442, "loss": 2.8569, "accuracy": 0.8125, "lr": 2.709871862184063e-07, "epoch": 0.6446140797285835, "percentage": 64.48, "elapsed_time": "1:19:03", "remaining_time": "0:43:33"}
+{"current_steps": 286, "total_steps": 442, "loss": 2.3291, "accuracy": 0.78125, "lr": 2.679950842326837e-07, "epoch": 0.6468758835171049, "percentage": 64.71, "elapsed_time": "1:19:19", "remaining_time": "0:43:16"}
+{"current_steps": 287, "total_steps": 442, "loss": 2.0703, "accuracy": 0.859375, "lr": 2.6501124845954363e-07, "epoch": 0.6491376873056263, "percentage": 64.93, "elapsed_time": "1:19:36", "remaining_time": "0:42:59"}
+{"current_steps": 288, "total_steps": 442, "loss": 2.3861, "accuracy": 0.828125, "lr": 2.62035865748246e-07, "epoch": 0.6513994910941476, "percentage": 65.16, "elapsed_time": "1:19:55", "remaining_time": "0:42:44"}
+{"current_steps": 289, "total_steps": 442, "loss": 2.4851, "accuracy": 0.8125, "lr": 2.5906912241871554e-07, "epoch": 0.6536612948826689, "percentage": 65.38, "elapsed_time": "1:20:12", "remaining_time": "0:42:27"}
+{"current_steps": 290, "total_steps": 442, "loss": 3.2414, "accuracy": 0.7421875, "lr": 2.561112042498753e-07, "epoch": 0.6559230986711903, "percentage": 65.61, "elapsed_time": "1:20:31", "remaining_time": "0:42:12"}
+{"current_steps": 291, "total_steps": 442, "loss": 2.6496, "accuracy": 0.796875, "lr": 2.5316229646801195e-07, "epoch": 0.6581849024597116, "percentage": 65.84, "elapsed_time": "1:20:48", "remaining_time": "0:41:55"}
+{"current_steps": 292, "total_steps": 442, "loss": 2.3251, "accuracy": 0.8203125, "lr": 2.5022258373517714e-07, "epoch": 0.660446706248233, "percentage": 66.06, "elapsed_time": "1:21:02", "remaining_time": "0:41:37"}
+{"current_steps": 293, "total_steps": 442, "loss": 3.3606, "accuracy": 0.7578125, "lr": 2.4729225013762474e-07, "epoch": 0.6627085100367544, "percentage": 66.29, "elapsed_time": "1:21:18", "remaining_time": "0:41:20"}
+{"current_steps": 294, "total_steps": 442, "loss": 2.5064, "accuracy": 0.8125, "lr": 2.4437147917428203e-07, "epoch": 0.6649703138252756, "percentage": 66.52, "elapsed_time": "1:21:35", "remaining_time": "0:41:04"}
+{"current_steps": 295, "total_steps": 442, "loss": 2.7098, "accuracy": 0.765625, "lr": 2.414604537452595e-07, "epoch": 0.667232117613797, "percentage": 66.74, "elapsed_time": "1:21:51", "remaining_time": "0:40:47"}
+{"current_steps": 296, "total_steps": 442, "loss": 2.1979, "accuracy": 0.8125, "lr": 2.385593561403974e-07, "epoch": 0.6694939214023183, "percentage": 66.97, "elapsed_time": "1:22:10", "remaining_time": "0:40:31"}
+{"current_steps": 297, "total_steps": 442, "loss": 2.467, "accuracy": 0.765625, "lr": 2.3566836802785119e-07, "epoch": 0.6717557251908397, "percentage": 67.19, "elapsed_time": "1:22:25", "remaining_time": "0:40:14"}
+{"current_steps": 298, "total_steps": 442, "loss": 2.8868, "accuracy": 0.7578125, "lr": 2.327876704427146e-07, "epoch": 0.6740175289793611, "percentage": 67.42, "elapsed_time": "1:22:41", "remaining_time": "0:39:57"}
+{"current_steps": 299, "total_steps": 442, "loss": 2.9575, "accuracy": 0.78125, "lr": 2.2991744377568358e-07, "epoch": 0.6762793327678824, "percentage": 67.65, "elapsed_time": "1:22:57", "remaining_time": "0:39:40"}
+{"current_steps": 300, "total_steps": 442, "loss": 3.3764, "accuracy": 0.71875, "lr": 2.270578677617601e-07, "epoch": 0.6785411365564037, "percentage": 67.87, "elapsed_time": "1:23:14", "remaining_time": "0:39:24"}
+{"current_steps": 301, "total_steps": 442, "loss": 2.2267, "accuracy": 0.84375, "lr": 2.242091214689971e-07, "epoch": 0.6808029403449251, "percentage": 68.1, "elapsed_time": "1:23:29", "remaining_time": "0:39:06"}
+{"current_steps": 302, "total_steps": 442, "loss": 2.6692, "accuracy": 0.796875, "lr": 2.2137138328728456e-07, "epoch": 0.6830647441334464, "percentage": 68.33, "elapsed_time": "1:23:48", "remaining_time": "0:38:50"}
+{"current_steps": 303, "total_steps": 442, "loss": 2.3552, "accuracy": 0.78125, "lr": 2.1854483091717974e-07, "epoch": 0.6853265479219678, "percentage": 68.55, "elapsed_time": "1:24:04", "remaining_time": "0:38:34"}
+{"current_steps": 304, "total_steps": 442, "loss": 2.8414, "accuracy": 0.7734375, "lr": 2.1572964135877863e-07, "epoch": 0.6875883517104892, "percentage": 68.78, "elapsed_time": "1:24:19", "remaining_time": "0:38:16"}
+{"current_steps": 305, "total_steps": 442, "loss": 2.0894, "accuracy": 0.828125, "lr": 2.1292599090063245e-07, "epoch": 0.6898501554990104, "percentage": 69.0, "elapsed_time": "1:24:33", "remaining_time": "0:37:59"}
+{"current_steps": 306, "total_steps": 442, "loss": 2.0643, "accuracy": 0.828125, "lr": 2.1013405510870824e-07, "epoch": 0.6921119592875318, "percentage": 69.23, "elapsed_time": "1:24:50", "remaining_time": "0:37:42"}
+{"current_steps": 307, "total_steps": 442, "loss": 2.4669, "accuracy": 0.8125, "lr": 2.0735400881539494e-07, "epoch": 0.6943737630760531, "percentage": 69.46, "elapsed_time": "1:25:08", "remaining_time": "0:37:26"}
+{"current_steps": 308, "total_steps": 442, "loss": 2.1998, "accuracy": 0.796875, "lr": 2.0458602610855536e-07, "epoch": 0.6966355668645745, "percentage": 69.68, "elapsed_time": "1:25:23", "remaining_time": "0:37:08"}
+{"current_steps": 309, "total_steps": 442, "loss": 2.7826, "accuracy": 0.765625, "lr": 2.0183028032062422e-07, "epoch": 0.6988973706530959, "percentage": 69.91, "elapsed_time": "1:25:38", "remaining_time": "0:36:51"}
+{"current_steps": 310, "total_steps": 442, "loss": 2.4588, "accuracy": 0.7734375, "lr": 1.9908694401775473e-07, "epoch": 0.7011591744416172, "percentage": 70.14, "elapsed_time": "1:25:55", "remaining_time": "0:36:35"}
+{"current_steps": 311, "total_steps": 442, "loss": 2.7131, "accuracy": 0.7578125, "lr": 1.9635618898901196e-07, "epoch": 0.7034209782301385, "percentage": 70.36, "elapsed_time": "1:26:12", "remaining_time": "0:36:18"}
+{"current_steps": 312, "total_steps": 442, "loss": 2.3183, "accuracy": 0.8125, "lr": 1.9363818623561565e-07, "epoch": 0.7056827820186599, "percentage": 70.59, "elapsed_time": "1:26:28", "remaining_time": "0:36:01"}
+{"current_steps": 313, "total_steps": 442, "loss": 2.1502, "accuracy": 0.8203125, "lr": 1.9093310596023108e-07, "epoch": 0.7079445858071812, "percentage": 70.81, "elapsed_time": "1:26:41", "remaining_time": "0:35:43"}
+{"current_steps": 314, "total_steps": 442, "loss": 2.9757, "accuracy": 0.765625, "lr": 1.8824111755631274e-07, "epoch": 0.7102063895957026, "percentage": 71.04, "elapsed_time": "1:26:57", "remaining_time": "0:35:27"}
+{"current_steps": 315, "total_steps": 442, "loss": 3.4906, "accuracy": 0.7421875, "lr": 1.8556238959749457e-07, "epoch": 0.712468193384224, "percentage": 71.27, "elapsed_time": "1:27:15", "remaining_time": "0:35:10"}
+{"current_steps": 316, "total_steps": 442, "loss": 3.2191, "accuracy": 0.78125, "lr": 1.8289708982703562e-07, "epoch": 0.7147299971727452, "percentage": 71.49, "elapsed_time": "1:27:32", "remaining_time": "0:34:54"}
+{"current_steps": 317, "total_steps": 442, "loss": 2.2796, "accuracy": 0.8359375, "lr": 1.802453851473151e-07, "epoch": 0.7169918009612666, "percentage": 71.72, "elapsed_time": "1:27:50", "remaining_time": "0:34:38"}
+{"current_steps": 318, "total_steps": 442, "loss": 2.351, "accuracy": 0.8359375, "lr": 1.7760744160938093e-07, "epoch": 0.719253604749788, "percentage": 71.95, "elapsed_time": "1:28:07", "remaining_time": "0:34:21"}
+{"current_steps": 319, "total_steps": 442, "loss": 2.5509, "accuracy": 0.7890625, "lr": 1.7498342440255135e-07, "epoch": 0.7215154085383093, "percentage": 72.17, "elapsed_time": "1:28:24", "remaining_time": "0:34:05"}
+{"current_steps": 320, "total_steps": 442, "loss": 2.2834, "accuracy": 0.84375, "lr": 1.7237349784407115e-07, "epoch": 0.7237772123268307, "percentage": 72.4, "elapsed_time": "1:28:40", "remaining_time": "0:33:48"}
+{"current_steps": 321, "total_steps": 442, "loss": 2.3171, "accuracy": 0.8125, "lr": 1.6977782536882178e-07, "epoch": 0.726039016115352, "percentage": 72.62, "elapsed_time": "1:29:00", "remaining_time": "0:33:32"}
+{"current_steps": 322, "total_steps": 442, "loss": 2.2743, "accuracy": 0.8203125, "lr": 1.6719656951908708e-07, "epoch": 0.7283008199038733, "percentage": 72.85, "elapsed_time": "1:29:17", "remaining_time": "0:33:16"}
+{"current_steps": 323, "total_steps": 442, "loss": 2.7438, "accuracy": 0.7734375, "lr": 1.6462989193437453e-07, "epoch": 0.7305626236923947, "percentage": 73.08, "elapsed_time": "1:29:34", "remaining_time": "0:33:00"}
+{"current_steps": 324, "total_steps": 442, "loss": 2.7085, "accuracy": 0.7734375, "lr": 1.6207795334129365e-07, "epoch": 0.732824427480916, "percentage": 73.3, "elapsed_time": "1:29:49", "remaining_time": "0:32:42"}
+{"current_steps": 325, "total_steps": 442, "loss": 3.1544, "accuracy": 0.75, "lr": 1.5954091354349121e-07, "epoch": 0.7350862312694374, "percentage": 73.53, "elapsed_time": "1:30:06", "remaining_time": "0:32:26"}
+{"current_steps": 326, "total_steps": 442, "loss": 2.9428, "accuracy": 0.78125, "lr": 1.5701893141164364e-07, "epoch": 0.7373480350579588, "percentage": 73.76, "elapsed_time": "1:30:24", "remaining_time": "0:32:10"}
+{"current_steps": 327, "total_steps": 442, "loss": 2.9854, "accuracy": 0.765625, "lr": 1.545121648735093e-07, "epoch": 0.73960983884648, "percentage": 73.98, "elapsed_time": "1:30:41", "remaining_time": "0:31:53"}
+{"current_steps": 328, "total_steps": 442, "loss": 2.4082, "accuracy": 0.8125, "lr": 1.5202077090403863e-07, "epoch": 0.7418716426350014, "percentage": 74.21, "elapsed_time": "1:30:58", "remaining_time": "0:31:37"}
+{"current_steps": 329, "total_steps": 442, "loss": 2.1108, "accuracy": 0.828125, "lr": 1.495449055155443e-07, "epoch": 0.7441334464235227, "percentage": 74.43, "elapsed_time": "1:31:13", "remaining_time": "0:31:19"}
+{"current_steps": 330, "total_steps": 442, "loss": 3.6505, "accuracy": 0.671875, "lr": 1.4708472374793112e-07, "epoch": 0.7463952502120441, "percentage": 74.66, "elapsed_time": "1:31:28", "remaining_time": "0:31:02"}
+{"current_steps": 331, "total_steps": 442, "loss": 2.7636, "accuracy": 0.7890625, "lr": 1.4464037965898878e-07, "epoch": 0.7486570540005655, "percentage": 74.89, "elapsed_time": "1:31:47", "remaining_time": "0:30:47"}
+{"current_steps": 332, "total_steps": 442, "loss": 2.6764, "accuracy": 0.796875, "lr": 1.4221202631474282e-07, "epoch": 0.7509188577890868, "percentage": 75.11, "elapsed_time": "1:32:02", "remaining_time": "0:30:29"}
+{"current_steps": 333, "total_steps": 442, "loss": 2.4723, "accuracy": 0.78125, "lr": 1.3979981577987113e-07, "epoch": 0.7531806615776081, "percentage": 75.34, "elapsed_time": "1:32:17", "remaining_time": "0:30:12"}
+{"current_steps": 334, "total_steps": 442, "loss": 2.8695, "accuracy": 0.7578125, "lr": 1.374038991081807e-07, "epoch": 0.7554424653661295, "percentage": 75.57, "elapsed_time": "1:32:37", "remaining_time": "0:29:56"}
+{"current_steps": 335, "total_steps": 442, "loss": 2.568, "accuracy": 0.7890625, "lr": 1.3502442633314882e-07, "epoch": 0.7577042691546508, "percentage": 75.79, "elapsed_time": "1:32:52", "remaining_time": "0:29:39"}
+{"current_steps": 336, "total_steps": 442, "loss": 2.4884, "accuracy": 0.8203125, "lr": 1.3266154645852815e-07, "epoch": 0.7599660729431722, "percentage": 76.02, "elapsed_time": "1:33:10", "remaining_time": "0:29:23"}
+{"current_steps": 337, "total_steps": 442, "loss": 2.8335, "accuracy": 0.7421875, "lr": 1.303154074490152e-07, "epoch": 0.7622278767316936, "percentage": 76.24, "elapsed_time": "1:33:27", "remaining_time": "0:29:07"}
+{"current_steps": 338, "total_steps": 442, "loss": 2.743, "accuracy": 0.7578125, "lr": 1.2798615622098616e-07, "epoch": 0.7644896805202148, "percentage": 76.47, "elapsed_time": "1:33:45", "remaining_time": "0:28:50"}
+{"current_steps": 339, "total_steps": 442, "loss": 2.3621, "accuracy": 0.828125, "lr": 1.2567393863329523e-07, "epoch": 0.7667514843087362, "percentage": 76.7, "elapsed_time": "1:34:01", "remaining_time": "0:28:34"}
+{"current_steps": 340, "total_steps": 442, "loss": 2.2977, "accuracy": 0.8125, "lr": 1.233788994781423e-07, "epoch": 0.7690132880972576, "percentage": 76.92, "elapsed_time": "1:34:17", "remaining_time": "0:28:17"}
+{"current_steps": 341, "total_steps": 442, "loss": 2.0917, "accuracy": 0.84375, "lr": 1.2110118247200468e-07, "epoch": 0.7712750918857789, "percentage": 77.15, "elapsed_time": "1:34:35", "remaining_time": "0:28:00"}
+{"current_steps": 342, "total_steps": 442, "loss": 2.5956, "accuracy": 0.765625, "lr": 1.1884093024663933e-07, "epoch": 0.7735368956743003, "percentage": 77.38, "elapsed_time": "1:34:52", "remaining_time": "0:27:44"}
+{"current_steps": 343, "total_steps": 442, "loss": 2.3451, "accuracy": 0.8359375, "lr": 1.1659828434014886e-07, "epoch": 0.7757986994628217, "percentage": 77.6, "elapsed_time": "1:35:09", "remaining_time": "0:27:27"}
+{"current_steps": 344, "total_steps": 442, "loss": 2.3046, "accuracy": 0.8046875, "lr": 1.143733851881203e-07, "epoch": 0.7780605032513429, "percentage": 77.83, "elapsed_time": "1:35:25", "remaining_time": "0:27:11"}
+{"current_steps": 345, "total_steps": 442, "loss": 2.8093, "accuracy": 0.7734375, "lr": 1.1216637211483005e-07, "epoch": 0.7803223070398643, "percentage": 78.05, "elapsed_time": "1:35:42", "remaining_time": "0:26:54"}
+{"current_steps": 346, "total_steps": 442, "loss": 2.555, "accuracy": 0.7890625, "lr": 1.0997738332451936e-07, "epoch": 0.7825841108283856, "percentage": 78.28, "elapsed_time": "1:35:59", "remaining_time": "0:26:38"}
+{"current_steps": 347, "total_steps": 442, "loss": 2.2597, "accuracy": 0.8359375, "lr": 1.0780655589274031e-07, "epoch": 0.784845914616907, "percentage": 78.51, "elapsed_time": "1:36:17", "remaining_time": "0:26:21"}
+{"current_steps": 348, "total_steps": 442, "loss": 1.8934, "accuracy": 0.84375, "lr": 1.056540257577712e-07, "epoch": 0.7871077184054284, "percentage": 78.73, "elapsed_time": "1:36:34", "remaining_time": "0:26:05"}
+{"current_steps": 349, "total_steps": 442, "loss": 2.5149, "accuracy": 0.8515625, "lr": 1.0351992771210554e-07, "epoch": 0.7893695221939496, "percentage": 78.96, "elapsed_time": "1:36:52", "remaining_time": "0:25:48"}
+{"current_steps": 350, "total_steps": 442, "loss": 3.156, "accuracy": 0.7265625, "lr": 1.0140439539400953e-07, "epoch": 0.791631325982471, "percentage": 79.19, "elapsed_time": "1:37:09", "remaining_time": "0:25:32"}
+{"current_steps": 351, "total_steps": 442, "loss": 2.4118, "accuracy": 0.796875, "lr": 9.930756127915488e-08, "epoch": 0.7938931297709924, "percentage": 79.41, "elapsed_time": "1:37:25", "remaining_time": "0:25:15"}
+{"current_steps": 352, "total_steps": 442, "loss": 3.0279, "accuracy": 0.7421875, "lr": 9.722955667232242e-08, "epoch": 0.7961549335595137, "percentage": 79.64, "elapsed_time": "1:37:43", "remaining_time": "0:24:59"}
+{"current_steps": 353, "total_steps": 442, "loss": 3.1398, "accuracy": 0.7421875, "lr": 9.517051169918016e-08, "epoch": 0.7984167373480351, "percentage": 79.86, "elapsed_time": "1:37:57", "remaining_time": "0:24:41"}
+{"current_steps": 354, "total_steps": 442, "loss": 2.3245, "accuracy": 0.8203125, "lr": 9.313055529813412e-08, "epoch": 0.8006785411365565, "percentage": 80.09, "elapsed_time": "1:38:13", "remaining_time": "0:24:25"}
+{"current_steps": 355, "total_steps": 442, "loss": 2.7619, "accuracy": 0.78125, "lr": 9.110981521225532e-08, "epoch": 0.8029403449250777, "percentage": 80.32, "elapsed_time": "1:38:30", "remaining_time": "0:24:08"}
+{"current_steps": 356, "total_steps": 442, "loss": 2.4937, "accuracy": 0.8359375, "lr": 8.910841798127884e-08, "epoch": 0.8052021487135991, "percentage": 80.54, "elapsed_time": "1:38:45", "remaining_time": "0:23:51"}
+{"current_steps": 357, "total_steps": 442, "loss": 2.4164, "accuracy": 0.7734375, "lr": 8.712648893368139e-08, "epoch": 0.8074639525021204, "percentage": 80.77, "elapsed_time": "1:39:02", "remaining_time": "0:23:34"}
+{"current_steps": 358, "total_steps": 442, "loss": 2.1505, "accuracy": 0.8515625, "lr": 8.516415217883186e-08, "epoch": 0.8097257562906418, "percentage": 81.0, "elapsed_time": "1:39:19", "remaining_time": "0:23:18"}
+{"current_steps": 359, "total_steps": 442, "loss": 2.9886, "accuracy": 0.7734375, "lr": 8.32215305992209e-08, "epoch": 0.8119875600791632, "percentage": 81.22, "elapsed_time": "1:39:35", "remaining_time": "0:23:01"}
+{"current_steps": 360, "total_steps": 442, "loss": 1.8634, "accuracy": 0.84375, "lr": 8.129874584276448e-08, "epoch": 0.8142493638676844, "percentage": 81.45, "elapsed_time": "1:39:51", "remaining_time": "0:22:44"}
+{"current_steps": 361, "total_steps": 442, "loss": 2.4179, "accuracy": 0.828125, "lr": 7.939591831518746e-08, "epoch": 0.8165111676562058, "percentage": 81.67, "elapsed_time": "1:40:07", "remaining_time": "0:22:28"}
+{"current_steps": 362, "total_steps": 442, "loss": 2.4426, "accuracy": 0.8046875, "lr": 7.751316717248304e-08, "epoch": 0.8187729714447272, "percentage": 81.9, "elapsed_time": "1:40:21", "remaining_time": "0:22:10"}
+{"current_steps": 363, "total_steps": 442, "loss": 2.4316, "accuracy": 0.8359375, "lr": 7.565061031345142e-08, "epoch": 0.8210347752332485, "percentage": 82.13, "elapsed_time": "1:40:40", "remaining_time": "0:21:54"}
+{"current_steps": 364, "total_steps": 442, "loss": 2.5825, "accuracy": 0.78125, "lr": 7.380836437231686e-08, "epoch": 0.8232965790217699, "percentage": 82.35, "elapsed_time": "1:40:55", "remaining_time": "0:21:37"}
+{"current_steps": 365, "total_steps": 442, "loss": 2.3187, "accuracy": 0.796875, "lr": 7.198654471142371e-08, "epoch": 0.8255583828102913, "percentage": 82.58, "elapsed_time": "1:41:11", "remaining_time": "0:21:20"}
+{"current_steps": 366, "total_steps": 442, "loss": 2.5367, "accuracy": 0.796875, "lr": 7.01852654140132e-08, "epoch": 0.8278201865988125, "percentage": 82.81, "elapsed_time": "1:41:28", "remaining_time": "0:21:04"}
+{"current_steps": 367, "total_steps": 442, "loss": 2.5045, "accuracy": 0.796875, "lr": 6.840463927707833e-08, "epoch": 0.8300819903873339, "percentage": 83.03, "elapsed_time": "1:41:42", "remaining_time": "0:20:47"}
+{"current_steps": 368, "total_steps": 442, "loss": 2.717, "accuracy": 0.78125, "lr": 6.664477780430138e-08, "epoch": 0.8323437941758552, "percentage": 83.26, "elapsed_time": "1:41:59", "remaining_time": "0:20:30"}
+{"current_steps": 369, "total_steps": 442, "loss": 2.8896, "accuracy": 0.7421875, "lr": 6.49057911990711e-08, "epoch": 0.8346055979643766, "percentage": 83.48, "elapsed_time": "1:42:14", "remaining_time": "0:20:13"}
+{"current_steps": 370, "total_steps": 442, "loss": 2.0356, "accuracy": 0.84375, "lr": 6.318778835758189e-08, "epoch": 0.836867401752898, "percentage": 83.71, "elapsed_time": "1:42:32", "remaining_time": "0:19:57"}
+{"current_steps": 371, "total_steps": 442, "loss": 3.3273, "accuracy": 0.765625, "lr": 6.149087686201433e-08, "epoch": 0.8391292055414192, "percentage": 83.94, "elapsed_time": "1:42:48", "remaining_time": "0:19:40"}
+{"current_steps": 372, "total_steps": 442, "loss": 2.1937, "accuracy": 0.8203125, "lr": 5.98151629737988e-08, "epoch": 0.8413910093299406, "percentage": 84.16, "elapsed_time": "1:43:04", "remaining_time": "0:19:23"}
+{"current_steps": 373, "total_steps": 442, "loss": 2.3016, "accuracy": 0.8125, "lr": 5.816075162696097e-08, "epoch": 0.843652813118462, "percentage": 84.39, "elapsed_time": "1:43:18", "remaining_time": "0:19:06"}
+{"current_steps": 374, "total_steps": 442, "loss": 2.4519, "accuracy": 0.8046875, "lr": 5.6527746421551046e-08, "epoch": 0.8459146169069833, "percentage": 84.62, "elapsed_time": "1:43:37", "remaining_time": "0:18:50"}
+{"current_steps": 375, "total_steps": 442, "loss": 2.6259, "accuracy": 0.75, "lr": 5.4916249617156064e-08, "epoch": 0.8481764206955047, "percentage": 84.84, "elapsed_time": "1:43:52", "remaining_time": "0:18:33"}
+{"current_steps": 376, "total_steps": 442, "loss": 2.0549, "accuracy": 0.859375, "lr": 5.332636212649646e-08, "epoch": 0.8504382244840261, "percentage": 85.07, "elapsed_time": "1:44:11", "remaining_time": "0:18:17"}
+{"current_steps": 377, "total_steps": 442, "loss": 2.734, "accuracy": 0.7890625, "lr": 5.17581835091069e-08, "epoch": 0.8527000282725473, "percentage": 85.29, "elapsed_time": "1:44:26", "remaining_time": "0:18:00"}
+{"current_steps": 378, "total_steps": 442, "loss": 2.3562, "accuracy": 0.84375, "lr": 5.02118119651016e-08, "epoch": 0.8549618320610687, "percentage": 85.52, "elapsed_time": "1:44:41", "remaining_time": "0:17:43"}
+{"current_steps": 379, "total_steps": 442, "loss": 2.9397, "accuracy": 0.765625, "lr": 4.868734432902526e-08, "epoch": 0.85722363584959, "percentage": 85.75, "elapsed_time": "1:44:59", "remaining_time": "0:17:27"}
+{"current_steps": 380, "total_steps": 442, "loss": 2.5866, "accuracy": 0.828125, "lr": 4.7184876063789134e-08, "epoch": 0.8594854396381114, "percentage": 85.97, "elapsed_time": "1:45:18", "remaining_time": "0:17:10"}
+{"current_steps": 381, "total_steps": 442, "loss": 2.0476, "accuracy": 0.859375, "lr": 4.570450125469314e-08, "epoch": 0.8617472434266328, "percentage": 86.2, "elapsed_time": "1:45:33", "remaining_time": "0:16:53"}
+{"current_steps": 382, "total_steps": 442, "loss": 2.568, "accuracy": 0.8203125, "lr": 4.424631260353378e-08, "epoch": 0.864009047215154, "percentage": 86.43, "elapsed_time": "1:45:49", "remaining_time": "0:16:37"}
+{"current_steps": 383, "total_steps": 442, "loss": 1.7937, "accuracy": 0.8359375, "lr": 4.281040142280008e-08, "epoch": 0.8662708510036754, "percentage": 86.65, "elapsed_time": "1:46:05", "remaining_time": "0:16:20"}
+{"current_steps": 384, "total_steps": 442, "loss": 2.6449, "accuracy": 0.7734375, "lr": 4.1396857629954286e-08, "epoch": 0.8685326547921968, "percentage": 86.88, "elapsed_time": "1:46:19", "remaining_time": "0:16:03"}
+{"current_steps": 385, "total_steps": 442, "loss": 2.5334, "accuracy": 0.84375, "lr": 4.000576974180232e-08, "epoch": 0.8707944585807181, "percentage": 87.1, "elapsed_time": "1:46:35", "remaining_time": "0:15:46"}
+{"current_steps": 386, "total_steps": 442, "loss": 2.7981, "accuracy": 0.796875, "lr": 3.8637224868950066e-08, "epoch": 0.8730562623692395, "percentage": 87.33, "elapsed_time": "1:46:51", "remaining_time": "0:15:30"}
+{"current_steps": 387, "total_steps": 442, "loss": 2.5976, "accuracy": 0.765625, "lr": 3.729130871034885e-08, "epoch": 0.8753180661577609, "percentage": 87.56, "elapsed_time": "1:47:08", "remaining_time": "0:15:13"}
+{"current_steps": 388, "total_steps": 442, "loss": 2.6181, "accuracy": 0.7890625, "lr": 3.596810554792888e-08, "epoch": 0.8775798699462821, "percentage": 87.78, "elapsed_time": "1:47:25", "remaining_time": "0:14:57"}
+{"current_steps": 389, "total_steps": 442, "loss": 2.2404, "accuracy": 0.828125, "lr": 3.466769824132116e-08, "epoch": 0.8798416737348035, "percentage": 88.01, "elapsed_time": "1:47:42", "remaining_time": "0:14:40"}
+{"current_steps": 390, "total_steps": 442, "loss": 1.7452, "accuracy": 0.8671875, "lr": 3.339016822266925e-08, "epoch": 0.8821034775233249, "percentage": 88.24, "elapsed_time": "1:48:01", "remaining_time": "0:14:24"}
+{"current_steps": 391, "total_steps": 442, "loss": 2.5852, "accuracy": 0.796875, "lr": 3.213559549152958e-08, "epoch": 0.8843652813118462, "percentage": 88.46, "elapsed_time": "1:48:19", "remaining_time": "0:14:07"}
+{"current_steps": 392, "total_steps": 442, "loss": 2.4299, "accuracy": 0.8125, "lr": 3.090405860986203e-08, "epoch": 0.8866270851003676, "percentage": 88.69, "elapsed_time": "1:48:35", "remaining_time": "0:13:51"}
+{"current_steps": 393, "total_steps": 442, "loss": 2.6235, "accuracy": 0.796875, "lr": 2.9695634697110315e-08, "epoch": 0.8888888888888888, "percentage": 88.91, "elapsed_time": "1:48:53", "remaining_time": "0:13:34"}
+{"current_steps": 394, "total_steps": 442, "loss": 2.6714, "accuracy": 0.7734375, "lr": 2.8510399425372766e-08, "epoch": 0.8911506926774102, "percentage": 89.14, "elapsed_time": "1:49:09", "remaining_time": "0:13:17"}
+{"current_steps": 395, "total_steps": 442, "loss": 2.2655, "accuracy": 0.828125, "lr": 2.734842701466329e-08, "epoch": 0.8934124964659316, "percentage": 89.37, "elapsed_time": "1:49:23", "remaining_time": "0:13:00"}
+{"current_steps": 396, "total_steps": 442, "loss": 2.2384, "accuracy": 0.8515625, "lr": 2.6209790228264438e-08, "epoch": 0.8956743002544529, "percentage": 89.59, "elapsed_time": "1:49:39", "remaining_time": "0:12:44"}
+{"current_steps": 397, "total_steps": 442, "loss": 2.3075, "accuracy": 0.84375, "lr": 2.5094560368170305e-08, "epoch": 0.8979361040429743, "percentage": 89.82, "elapsed_time": "1:49:55", "remaining_time": "0:12:27"}
+{"current_steps": 398, "total_steps": 442, "loss": 2.4449, "accuracy": 0.8359375, "lr": 2.4002807270621893e-08, "epoch": 0.9001979078314957, "percentage": 90.05, "elapsed_time": "1:50:10", "remaining_time": "0:12:10"}
+{"current_steps": 399, "total_steps": 442, "loss": 2.3729, "accuracy": 0.8125, "lr": 2.293459930173354e-08, "epoch": 0.9024597116200169, "percentage": 90.27, "elapsed_time": "1:50:26", "remaining_time": "0:11:54"}
+{"current_steps": 400, "total_steps": 442, "loss": 2.9326, "accuracy": 0.7734375, "lr": 2.189000335321256e-08, "epoch": 0.9047215154085383, "percentage": 90.5, "elapsed_time": "1:50:44", "remaining_time": "0:11:37"}
+{"current_steps": 401, "total_steps": 442, "loss": 2.5806, "accuracy": 0.7890625, "lr": 2.086908483816954e-08, "epoch": 0.9069833191970597, "percentage": 90.72, "elapsed_time": "1:51:01", "remaining_time": "0:11:21"}
+{"current_steps": 402, "total_steps": 442, "loss": 2.4165, "accuracy": 0.7890625, "lr": 1.9871907687022717e-08, "epoch": 0.909245122985581, "percentage": 90.95, "elapsed_time": "1:51:17", "remaining_time": "0:11:04"}
+{"current_steps": 403, "total_steps": 442, "loss": 2.441, "accuracy": 0.765625, "lr": 1.889853434349451e-08, "epoch": 0.9115069267741024, "percentage": 91.18, "elapsed_time": "1:51:33", "remaining_time": "0:10:47"}
+{"current_steps": 404, "total_steps": 442, "loss": 2.4213, "accuracy": 0.8203125, "lr": 1.7949025760701164e-08, "epoch": 0.9137687305626236, "percentage": 91.4, "elapsed_time": "1:51:49", "remaining_time": "0:10:31"}
+{"current_steps": 405, "total_steps": 442, "loss": 2.1802, "accuracy": 0.8125, "lr": 1.7023441397336023e-08, "epoch": 0.916030534351145, "percentage": 91.63, "elapsed_time": "1:52:06", "remaining_time": "0:10:14"}
+{"current_steps": 406, "total_steps": 442, "loss": 2.6478, "accuracy": 0.8125, "lr": 1.6121839213945854e-08, "epoch": 0.9182923381396664, "percentage": 91.86, "elapsed_time": "1:52:23", "remaining_time": "0:09:57"}
+{"current_steps": 407, "total_steps": 442, "loss": 2.6662, "accuracy": 0.78125, "lr": 1.5244275669301777e-08, "epoch": 0.9205541419281877, "percentage": 92.08, "elapsed_time": "1:52:40", "remaining_time": "0:09:41"}
+{"current_steps": 408, "total_steps": 442, "loss": 3.0725, "accuracy": 0.7578125, "lr": 1.4390805716863398e-08, "epoch": 0.9228159457167091, "percentage": 92.31, "elapsed_time": "1:52:58", "remaining_time": "0:09:24"}
+{"current_steps": 409, "total_steps": 442, "loss": 2.8243, "accuracy": 0.7734375, "lr": 1.3561482801337908e-08, "epoch": 0.9250777495052305, "percentage": 92.53, "elapsed_time": "1:53:16", "remaining_time": "0:09:08"}
+{"current_steps": 410, "total_steps": 442, "loss": 3.201, "accuracy": 0.71875, "lr": 1.2756358855332904e-08, "epoch": 0.9273395532937517, "percentage": 92.76, "elapsed_time": "1:53:32", "remaining_time": "0:08:51"}
+{"current_steps": 411, "total_steps": 442, "loss": 2.8047, "accuracy": 0.7734375, "lr": 1.1975484296105154e-08, "epoch": 0.9296013570822731, "percentage": 92.99, "elapsed_time": "1:53:51", "remaining_time": "0:08:35"}
+{"current_steps": 412, "total_steps": 442, "loss": 2.3413, "accuracy": 0.859375, "lr": 1.1218908022402374e-08, "epoch": 0.9318631608707945, "percentage": 93.21, "elapsed_time": "1:54:08", "remaining_time": "0:08:18"}
+{"current_steps": 413, "total_steps": 442, "loss": 2.7482, "accuracy": 0.8046875, "lr": 1.0486677411402079e-08, "epoch": 0.9341249646593158, "percentage": 93.44, "elapsed_time": "1:54:24", "remaining_time": "0:08:02"}
+{"current_steps": 414, "total_steps": 442, "loss": 2.2191, "accuracy": 0.84375, "lr": 9.778838315744353e-09, "epoch": 0.9363867684478372, "percentage": 93.67, "elapsed_time": "1:54:40", "remaining_time": "0:07:45"}
+{"current_steps": 415, "total_steps": 442, "loss": 2.663, "accuracy": 0.78125, "lr": 9.095435060660595e-09, "epoch": 0.9386485722363584, "percentage": 93.89, "elapsed_time": "1:54:59", "remaining_time": "0:07:28"}
+{"current_steps": 416, "total_steps": 442, "loss": 2.9006, "accuracy": 0.765625, "lr": 8.436510441197864e-09, "epoch": 0.9409103760248798, "percentage": 94.12, "elapsed_time": "1:55:17", "remaining_time": "0:07:12"}
+{"current_steps": 417, "total_steps": 442, "loss": 3.2472, "accuracy": 0.71875, "lr": 7.802105719539076e-09, "epoch": 0.9431721798134012, "percentage": 94.34, "elapsed_time": "1:55:33", "remaining_time": "0:06:55"}
+{"current_steps": 418, "total_steps": 442, "loss": 2.396, "accuracy": 0.8046875, "lr": 7.1922606224192e-09, "epoch": 0.9454339836019225, "percentage": 94.57, "elapsed_time": "1:55:48", "remaining_time": "0:06:38"}
+{"current_steps": 419, "total_steps": 442, "loss": 2.7637, "accuracy": 0.765625, "lr": 6.6070133386372906e-09, "epoch": 0.9476957873904439, "percentage": 94.8, "elapsed_time": "1:56:02", "remaining_time": "0:06:22"}
+{"current_steps": 420, "total_steps": 442, "loss": 2.9147, "accuracy": 0.734375, "lr": 6.046400516665384e-09, "epoch": 0.9499575911789653, "percentage": 95.02, "elapsed_time": "1:56:20", "remaining_time": "0:06:05"}
+{"current_steps": 421, "total_steps": 442, "loss": 2.3305, "accuracy": 0.8203125, "lr": 5.510457262353396e-09, "epoch": 0.9522193949674865, "percentage": 95.25, "elapsed_time": "1:56:37", "remaining_time": "0:05:49"}
+{"current_steps": 422, "total_steps": 442, "loss": 2.2812, "accuracy": 0.859375, "lr": 4.9992171367309265e-09, "epoch": 0.9544811987560079, "percentage": 95.48, "elapsed_time": "1:56:55", "remaining_time": "0:05:32"}
+{"current_steps": 423, "total_steps": 442, "loss": 2.4137, "accuracy": 0.8125, "lr": 4.5127121539052955e-09, "epoch": 0.9567430025445293, "percentage": 95.7, "elapsed_time": "1:57:15", "remaining_time": "0:05:15"}
+{"current_steps": 424, "total_steps": 442, "loss": 2.7246, "accuracy": 0.78125, "lr": 4.050972779057327e-09, "epoch": 0.9590048063330506, "percentage": 95.93, "elapsed_time": "1:57:30", "remaining_time": "0:04:59"}
+{"current_steps": 425, "total_steps": 442, "loss": 2.6723, "accuracy": 0.75, "lr": 3.6140279265330477e-09, "epoch": 0.961266610121572, "percentage": 96.15, "elapsed_time": "1:57:44", "remaining_time": "0:04:42"}
+{"current_steps": 426, "total_steps": 442, "loss": 3.2617, "accuracy": 0.7265625, "lr": 3.2019049580335853e-09, "epoch": 0.9635284139100933, "percentage": 96.38, "elapsed_time": "1:58:03", "remaining_time": "0:04:26"}
+{"current_steps": 427, "total_steps": 442, "loss": 2.4462, "accuracy": 0.8046875, "lr": 2.814629680901337e-09, "epoch": 0.9657902176986146, "percentage": 96.61, "elapsed_time": "1:58:21", "remaining_time": "0:04:09"}
+{"current_steps": 428, "total_steps": 442, "loss": 2.1732, "accuracy": 0.8359375, "lr": 2.4522263465041937e-09, "epoch": 0.968052021487136, "percentage": 96.83, "elapsed_time": "1:58:39", "remaining_time": "0:03:52"}
+{"current_steps": 429, "total_steps": 442, "loss": 2.2091, "accuracy": 0.8359375, "lr": 2.114717648716713e-09, "epoch": 0.9703138252756573, "percentage": 97.06, "elapsed_time": "1:58:54", "remaining_time": "0:03:36"}
+{"current_steps": 430, "total_steps": 442, "loss": 2.5129, "accuracy": 0.8125, "lr": 1.802124722499121e-09, "epoch": 0.9725756290641787, "percentage": 97.29, "elapsed_time": "1:59:11", "remaining_time": "0:03:19"}
+{"current_steps": 431, "total_steps": 442, "loss": 2.8765, "accuracy": 0.765625, "lr": 1.5144671425737499e-09, "epoch": 0.9748374328527001, "percentage": 97.51, "elapsed_time": "1:59:27", "remaining_time": "0:03:02"}
+{"current_steps": 432, "total_steps": 442, "loss": 1.9835, "accuracy": 0.859375, "lr": 1.251762922199484e-09, "epoch": 0.9770992366412213, "percentage": 97.74, "elapsed_time": "1:59:44", "remaining_time": "0:02:46"}
+{"current_steps": 433, "total_steps": 442, "loss": 2.527, "accuracy": 0.7578125, "lr": 1.0140285120433744e-09, "epoch": 0.9793610404297427, "percentage": 97.96, "elapsed_time": "2:00:01", "remaining_time": "0:02:29"}
+{"current_steps": 434, "total_steps": 442, "loss": 2.8152, "accuracy": 0.7734375, "lr": 8.012787991508396e-10, "epoch": 0.9816228442182641, "percentage": 98.19, "elapsed_time": "2:00:16", "remaining_time": "0:02:13"}
+{"current_steps": 435, "total_steps": 442, "loss": 2.9644, "accuracy": 0.7734375, "lr": 6.135271060133007e-10, "epoch": 0.9838846480067854, "percentage": 98.42, "elapsed_time": "2:00:30", "remaining_time": "0:01:56"}
+{"current_steps": 436, "total_steps": 442, "loss": 2.1384, "accuracy": 0.8125, "lr": 4.50785189733871e-10, "epoch": 0.9861464517953068, "percentage": 98.64, "elapsed_time": "2:00:48", "remaining_time": "0:01:39"}
+{"current_steps": 437, "total_steps": 442, "loss": 2.6014, "accuracy": 0.8203125, "lr": 3.1306324129118935e-10, "epoch": 0.988408255583828, "percentage": 98.87, "elapsed_time": "2:01:04", "remaining_time": "0:01:23"}
+{"current_steps": 438, "total_steps": 442, "loss": 2.7518, "accuracy": 0.8046875, "lr": 2.003698849011748e-10, "epoch": 0.9906700593723494, "percentage": 99.1, "elapsed_time": "2:01:20", "remaining_time": "0:01:06"}
+{"current_steps": 439, "total_steps": 442, "loss": 2.7764, "accuracy": 0.765625, "lr": 1.1271217747714779e-10, "epoch": 0.9929318631608708, "percentage": 99.32, "elapsed_time": "2:01:39", "remaining_time": "0:00:49"}
+{"current_steps": 440, "total_steps": 442, "loss": 2.7284, "accuracy": 0.78125, "lr": 5.0095608187739055e-11, "epoch": 0.9951936669493922, "percentage": 99.55, "elapsed_time": "2:01:55", "remaining_time": "0:00:33"}
+{"current_steps": 441, "total_steps": 442, "loss": 2.9133, "accuracy": 0.8125, "lr": 1.2524098113209092e-11, "epoch": 0.9974554707379135, "percentage": 99.77, "elapsed_time": "2:02:11", "remaining_time": "0:00:16"}
+{"current_steps": 442, "total_steps": 442, "loss": 2.838, "accuracy": 0.7734375, "lr": 0.0, "epoch": 0.9997172745264349, "percentage": 100.0, "elapsed_time": "2:02:25", "remaining_time": "0:00:00"}
+{"current_steps": 442, "total_steps": 442, "eval_loss": 2.455941915512085, "epoch": 0.9997172745264349, "percentage": 100.0, "elapsed_time": "2:05:14", "remaining_time": "0:00:00"}
+{"current_steps": 442, "total_steps": 442, "epoch": 0.9997172745264349, "percentage": 100.0, "elapsed_time": "2:06:28", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a3309fdfbfb551ce03a463f643e8532d21c52595d7ea03923bd5c588b899e9
+size 7160