Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9894736842105263,
+    "total_flos": 3.713025592344904e+17,
+    "train_loss": 0.0,
+    "train_runtime": 12.3976,
+    "train_samples_per_second": 2940.336,
+    "train_steps_per_second": 30.49
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/eguha/models_cache/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c32f5e20237fffb87633bf489c6ca61fa81c37aba03f0406658e679fde6331
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ae768c9b904caafe3b91b7341456c10dedadaaa45edc4384f5d306ba2920a9
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fa130e0960cbcb32af4129331b6ee3e0091f746f38b41a03d733d1ad5e719a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d062c3551d68566807d5fd9706b56c28a2dfa88137739e6f80be993e47380e69
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9894736842105263,
+    "total_flos": 3.713025592344904e+17,
+    "train_loss": 0.0,
+    "train_runtime": 12.3976,
+    "train_samples_per_second": 2940.336,
+    "train_steps_per_second": 30.49
+}

trainer_log.jsonl

@@ -0,0 +1,384 @@
+{"current_steps": 1, "total_steps": 378, "loss": 1.1186, "lr": 2.6315789473684213e-07, "epoch": 0.007894736842105263, "percentage": 0.26, "elapsed_time": "0:00:40", "remaining_time": "4:16:09"}
+{"current_steps": 2, "total_steps": 378, "loss": 1.1281, "lr": 5.263157894736843e-07, "epoch": 0.015789473684210527, "percentage": 0.53, "elapsed_time": "0:01:02", "remaining_time": "3:16:57"}
+{"current_steps": 3, "total_steps": 378, "loss": 1.1185, "lr": 7.894736842105263e-07, "epoch": 0.02368421052631579, "percentage": 0.79, "elapsed_time": "0:01:28", "remaining_time": "3:05:05"}
+{"current_steps": 4, "total_steps": 378, "loss": 1.129, "lr": 1.0526315789473685e-06, "epoch": 0.031578947368421054, "percentage": 1.06, "elapsed_time": "0:01:51", "remaining_time": "2:53:54"}
+{"current_steps": 5, "total_steps": 378, "loss": 1.103, "lr": 1.3157894736842106e-06, "epoch": 0.039473684210526314, "percentage": 1.32, "elapsed_time": "0:02:14", "remaining_time": "2:47:48"}
+{"current_steps": 6, "total_steps": 378, "loss": 1.129, "lr": 1.5789473684210526e-06, "epoch": 0.04736842105263158, "percentage": 1.59, "elapsed_time": "0:02:35", "remaining_time": "2:40:51"}
+{"current_steps": 7, "total_steps": 378, "loss": 1.0762, "lr": 1.8421052631578948e-06, "epoch": 0.05526315789473684, "percentage": 1.85, "elapsed_time": "0:02:59", "remaining_time": "2:38:53"}
+{"current_steps": 8, "total_steps": 378, "loss": 1.0529, "lr": 2.105263157894737e-06, "epoch": 0.06315789473684211, "percentage": 2.12, "elapsed_time": "0:03:21", "remaining_time": "2:34:58"}
+{"current_steps": 9, "total_steps": 378, "loss": 1.0531, "lr": 2.368421052631579e-06, "epoch": 0.07105263157894737, "percentage": 2.38, "elapsed_time": "0:03:49", "remaining_time": "2:36:54"}
+{"current_steps": 10, "total_steps": 378, "loss": 0.9795, "lr": 2.631578947368421e-06, "epoch": 0.07894736842105263, "percentage": 2.65, "elapsed_time": "0:04:12", "remaining_time": "2:34:50"}
+{"current_steps": 11, "total_steps": 378, "loss": 1.0095, "lr": 2.8947368421052634e-06, "epoch": 0.0868421052631579, "percentage": 2.91, "elapsed_time": "0:04:35", "remaining_time": "2:33:22"}
+{"current_steps": 12, "total_steps": 378, "loss": 0.9728, "lr": 3.157894736842105e-06, "epoch": 0.09473684210526316, "percentage": 3.17, "elapsed_time": "0:04:59", "remaining_time": "2:32:22"}
+{"current_steps": 13, "total_steps": 378, "loss": 0.9307, "lr": 3.421052631578948e-06, "epoch": 0.10263157894736842, "percentage": 3.44, "elapsed_time": "0:05:23", "remaining_time": "2:31:14"}
+{"current_steps": 14, "total_steps": 378, "loss": 0.9612, "lr": 3.6842105263157896e-06, "epoch": 0.11052631578947368, "percentage": 3.7, "elapsed_time": "0:05:46", "remaining_time": "2:30:19"}
+{"current_steps": 15, "total_steps": 378, "loss": 0.9617, "lr": 3.947368421052632e-06, "epoch": 0.11842105263157894, "percentage": 3.97, "elapsed_time": "0:06:12", "remaining_time": "2:30:07"}
+{"current_steps": 16, "total_steps": 378, "loss": 0.9333, "lr": 4.210526315789474e-06, "epoch": 0.12631578947368421, "percentage": 4.23, "elapsed_time": "0:06:32", "remaining_time": "2:27:50"}
+{"current_steps": 17, "total_steps": 378, "loss": 0.9159, "lr": 4.473684210526316e-06, "epoch": 0.13421052631578947, "percentage": 4.5, "elapsed_time": "0:06:59", "remaining_time": "2:28:31"}
+{"current_steps": 18, "total_steps": 378, "loss": 0.8997, "lr": 4.736842105263158e-06, "epoch": 0.14210526315789473, "percentage": 4.76, "elapsed_time": "0:07:24", "remaining_time": "2:28:14"}
+{"current_steps": 19, "total_steps": 378, "loss": 0.9104, "lr": 5e-06, "epoch": 0.15, "percentage": 5.03, "elapsed_time": "0:07:53", "remaining_time": "2:29:14"}
+{"current_steps": 20, "total_steps": 378, "loss": 0.8804, "lr": 5.263157894736842e-06, "epoch": 0.15789473684210525, "percentage": 5.29, "elapsed_time": "0:08:17", "remaining_time": "2:28:26"}
+{"current_steps": 21, "total_steps": 378, "loss": 0.8454, "lr": 5.526315789473685e-06, "epoch": 0.16578947368421051, "percentage": 5.56, "elapsed_time": "0:08:47", "remaining_time": "2:29:34"}
+{"current_steps": 22, "total_steps": 378, "loss": 0.8531, "lr": 5.789473684210527e-06, "epoch": 0.1736842105263158, "percentage": 5.82, "elapsed_time": "0:09:13", "remaining_time": "2:29:18"}
+{"current_steps": 23, "total_steps": 378, "loss": 0.8296, "lr": 6.0526315789473685e-06, "epoch": 0.18157894736842106, "percentage": 6.08, "elapsed_time": "0:09:39", "remaining_time": "2:29:10"}
+{"current_steps": 24, "total_steps": 378, "loss": 0.828, "lr": 6.31578947368421e-06, "epoch": 0.18947368421052632, "percentage": 6.35, "elapsed_time": "0:10:03", "remaining_time": "2:28:20"}
+{"current_steps": 25, "total_steps": 378, "loss": 0.8286, "lr": 6.578947368421054e-06, "epoch": 0.19736842105263158, "percentage": 6.61, "elapsed_time": "0:10:25", "remaining_time": "2:27:16"}
+{"current_steps": 26, "total_steps": 378, "loss": 0.8069, "lr": 6.842105263157896e-06, "epoch": 0.20526315789473684, "percentage": 6.88, "elapsed_time": "0:10:51", "remaining_time": "2:26:56"}
+{"current_steps": 27, "total_steps": 378, "loss": 0.8102, "lr": 7.1052631578947375e-06, "epoch": 0.2131578947368421, "percentage": 7.14, "elapsed_time": "0:11:12", "remaining_time": "2:25:47"}
+{"current_steps": 28, "total_steps": 378, "loss": 0.7892, "lr": 7.368421052631579e-06, "epoch": 0.22105263157894736, "percentage": 7.41, "elapsed_time": "0:11:37", "remaining_time": "2:25:24"}
+{"current_steps": 29, "total_steps": 378, "loss": 0.7961, "lr": 7.631578947368423e-06, "epoch": 0.22894736842105262, "percentage": 7.67, "elapsed_time": "0:12:00", "remaining_time": "2:24:34"}
+{"current_steps": 30, "total_steps": 378, "loss": 0.8092, "lr": 7.894736842105265e-06, "epoch": 0.23684210526315788, "percentage": 7.94, "elapsed_time": "0:12:25", "remaining_time": "2:24:09"}
+{"current_steps": 31, "total_steps": 378, "loss": 0.7846, "lr": 8.157894736842106e-06, "epoch": 0.24473684210526317, "percentage": 8.2, "elapsed_time": "0:12:50", "remaining_time": "2:23:45"}
+{"current_steps": 32, "total_steps": 378, "loss": 0.7538, "lr": 8.421052631578948e-06, "epoch": 0.25263157894736843, "percentage": 8.47, "elapsed_time": "0:13:17", "remaining_time": "2:23:38"}
+{"current_steps": 33, "total_steps": 378, "loss": 0.7802, "lr": 8.68421052631579e-06, "epoch": 0.26052631578947366, "percentage": 8.73, "elapsed_time": "0:13:38", "remaining_time": "2:22:39"}
+{"current_steps": 34, "total_steps": 378, "loss": 0.7718, "lr": 8.947368421052632e-06, "epoch": 0.26842105263157895, "percentage": 8.99, "elapsed_time": "0:13:55", "remaining_time": "2:20:53"}
+{"current_steps": 35, "total_steps": 378, "loss": 0.7826, "lr": 9.210526315789474e-06, "epoch": 0.27631578947368424, "percentage": 9.26, "elapsed_time": "0:14:18", "remaining_time": "2:20:11"}
+{"current_steps": 36, "total_steps": 378, "loss": 0.7763, "lr": 9.473684210526315e-06, "epoch": 0.28421052631578947, "percentage": 9.52, "elapsed_time": "0:14:42", "remaining_time": "2:19:41"}
+{"current_steps": 37, "total_steps": 378, "loss": 0.7564, "lr": 9.736842105263159e-06, "epoch": 0.29210526315789476, "percentage": 9.79, "elapsed_time": "0:15:04", "remaining_time": "2:18:58"}
+{"current_steps": 38, "total_steps": 378, "loss": 0.7508, "lr": 1e-05, "epoch": 0.3, "percentage": 10.05, "elapsed_time": "0:15:31", "remaining_time": "2:18:50"}
+{"current_steps": 39, "total_steps": 378, "loss": 0.7492, "lr": 9.99978655851684e-06, "epoch": 0.3078947368421053, "percentage": 10.32, "elapsed_time": "0:15:54", "remaining_time": "2:18:12"}
+{"current_steps": 40, "total_steps": 378, "loss": 0.7627, "lr": 9.999146252290264e-06, "epoch": 0.3157894736842105, "percentage": 10.58, "elapsed_time": "0:16:21", "remaining_time": "2:18:11"}
+{"current_steps": 41, "total_steps": 378, "loss": 0.739, "lr": 9.998079135987437e-06, "epoch": 0.3236842105263158, "percentage": 10.85, "elapsed_time": "0:16:42", "remaining_time": "2:17:24"}
+{"current_steps": 42, "total_steps": 378, "loss": 0.7372, "lr": 9.996585300715117e-06, "epoch": 0.33157894736842103, "percentage": 11.11, "elapsed_time": "0:17:06", "remaining_time": "2:16:55"}
+{"current_steps": 43, "total_steps": 378, "loss": 0.7537, "lr": 9.994664874011864e-06, "epoch": 0.3394736842105263, "percentage": 11.38, "elapsed_time": "0:17:30", "remaining_time": "2:16:24"}
+{"current_steps": 44, "total_steps": 378, "loss": 0.7485, "lr": 9.992318019837171e-06, "epoch": 0.3473684210526316, "percentage": 11.64, "elapsed_time": "0:17:54", "remaining_time": "2:15:55"}
+{"current_steps": 45, "total_steps": 378, "loss": 0.7487, "lr": 9.989544938557453e-06, "epoch": 0.35526315789473684, "percentage": 11.9, "elapsed_time": "0:18:13", "remaining_time": "2:14:50"}
+{"current_steps": 46, "total_steps": 378, "loss": 0.7465, "lr": 9.98634586692894e-06, "epoch": 0.3631578947368421, "percentage": 12.17, "elapsed_time": "0:18:39", "remaining_time": "2:14:36"}
+{"current_steps": 47, "total_steps": 378, "loss": 0.7471, "lr": 9.982721078077474e-06, "epoch": 0.37105263157894736, "percentage": 12.43, "elapsed_time": "0:19:01", "remaining_time": "2:13:59"}
+{"current_steps": 48, "total_steps": 378, "loss": 0.7643, "lr": 9.978670881475173e-06, "epoch": 0.37894736842105264, "percentage": 12.7, "elapsed_time": "0:19:21", "remaining_time": "2:13:03"}
+{"current_steps": 49, "total_steps": 378, "loss": 0.7386, "lr": 9.97419562291403e-06, "epoch": 0.3868421052631579, "percentage": 12.96, "elapsed_time": "0:19:46", "remaining_time": "2:12:43"}
+{"current_steps": 50, "total_steps": 378, "loss": 0.754, "lr": 9.96929568447637e-06, "epoch": 0.39473684210526316, "percentage": 13.23, "elapsed_time": "0:20:12", "remaining_time": "2:12:31"}
+{"current_steps": 51, "total_steps": 378, "loss": 0.731, "lr": 9.963971484502247e-06, "epoch": 0.4026315789473684, "percentage": 13.49, "elapsed_time": "0:20:37", "remaining_time": "2:12:16"}
+{"current_steps": 52, "total_steps": 378, "loss": 0.7542, "lr": 9.958223477553715e-06, "epoch": 0.4105263157894737, "percentage": 13.76, "elapsed_time": "0:21:06", "remaining_time": "2:12:16"}
+{"current_steps": 53, "total_steps": 378, "loss": 0.7626, "lr": 9.952052154376027e-06, "epoch": 0.41842105263157897, "percentage": 14.02, "elapsed_time": "0:21:34", "remaining_time": "2:12:15"}
+{"current_steps": 54, "total_steps": 378, "loss": 0.7303, "lr": 9.945458041855732e-06, "epoch": 0.4263157894736842, "percentage": 14.29, "elapsed_time": "0:22:00", "remaining_time": "2:12:04"}
+{"current_steps": 55, "total_steps": 378, "loss": 0.7143, "lr": 9.938441702975689e-06, "epoch": 0.4342105263157895, "percentage": 14.55, "elapsed_time": "0:22:27", "remaining_time": "2:11:50"}
+{"current_steps": 56, "total_steps": 378, "loss": 0.7097, "lr": 9.931003736767013e-06, "epoch": 0.4421052631578947, "percentage": 14.81, "elapsed_time": "0:22:53", "remaining_time": "2:11:38"}
+{"current_steps": 57, "total_steps": 378, "loss": 0.7253, "lr": 9.923144778257918e-06, "epoch": 0.45, "percentage": 15.08, "elapsed_time": "0:23:18", "remaining_time": "2:11:14"}
+{"current_steps": 58, "total_steps": 378, "loss": 0.7212, "lr": 9.91486549841951e-06, "epoch": 0.45789473684210524, "percentage": 15.34, "elapsed_time": "0:23:44", "remaining_time": "2:11:01"}
+{"current_steps": 59, "total_steps": 378, "loss": 0.7254, "lr": 9.906166604108494e-06, "epoch": 0.46578947368421053, "percentage": 15.61, "elapsed_time": "0:24:08", "remaining_time": "2:10:33"}
+{"current_steps": 60, "total_steps": 378, "loss": 0.7306, "lr": 9.89704883800683e-06, "epoch": 0.47368421052631576, "percentage": 15.87, "elapsed_time": "0:24:33", "remaining_time": "2:10:12"}
+{"current_steps": 61, "total_steps": 378, "loss": 0.7245, "lr": 9.887512978558329e-06, "epoch": 0.48157894736842105, "percentage": 16.14, "elapsed_time": "0:24:59", "remaining_time": "2:09:54"}
+{"current_steps": 62, "total_steps": 378, "loss": 0.7239, "lr": 9.877559839902185e-06, "epoch": 0.48947368421052634, "percentage": 16.4, "elapsed_time": "0:25:27", "remaining_time": "2:09:46"}
+{"current_steps": 63, "total_steps": 378, "loss": 0.6966, "lr": 9.867190271803466e-06, "epoch": 0.49736842105263157, "percentage": 16.67, "elapsed_time": "0:25:52", "remaining_time": "2:09:23"}
+{"current_steps": 64, "total_steps": 378, "loss": 0.7246, "lr": 9.85640515958057e-06, "epoch": 0.5052631578947369, "percentage": 16.93, "elapsed_time": "0:26:20", "remaining_time": "2:09:14"}
+{"current_steps": 65, "total_steps": 378, "loss": 0.7121, "lr": 9.845205424029639e-06, "epoch": 0.5131578947368421, "percentage": 17.2, "elapsed_time": "0:26:47", "remaining_time": "2:08:58"}
+{"current_steps": 66, "total_steps": 378, "loss": 0.7341, "lr": 9.833592021345938e-06, "epoch": 0.5210526315789473, "percentage": 17.46, "elapsed_time": "0:27:11", "remaining_time": "2:08:32"}
+{"current_steps": 67, "total_steps": 378, "loss": 0.707, "lr": 9.821565943042225e-06, "epoch": 0.5289473684210526, "percentage": 17.72, "elapsed_time": "0:27:34", "remaining_time": "2:07:57"}
+{"current_steps": 68, "total_steps": 378, "loss": 0.7118, "lr": 9.809128215864096e-06, "epoch": 0.5368421052631579, "percentage": 17.99, "elapsed_time": "0:27:57", "remaining_time": "2:07:26"}
+{"current_steps": 69, "total_steps": 378, "loss": 0.6977, "lr": 9.796279901702326e-06, "epoch": 0.5447368421052632, "percentage": 18.25, "elapsed_time": "0:28:21", "remaining_time": "2:07:00"}
+{"current_steps": 70, "total_steps": 378, "loss": 0.7213, "lr": 9.783022097502204e-06, "epoch": 0.5526315789473685, "percentage": 18.52, "elapsed_time": "0:28:46", "remaining_time": "2:06:37"}
+{"current_steps": 71, "total_steps": 378, "loss": 0.7079, "lr": 9.76935593516989e-06, "epoch": 0.5605263157894737, "percentage": 18.78, "elapsed_time": "0:29:08", "remaining_time": "2:05:58"}
+{"current_steps": 72, "total_steps": 378, "loss": 0.7304, "lr": 9.755282581475769e-06, "epoch": 0.5684210526315789, "percentage": 19.05, "elapsed_time": "0:29:29", "remaining_time": "2:05:22"}
+{"current_steps": 73, "total_steps": 378, "loss": 0.714, "lr": 9.74080323795483e-06, "epoch": 0.5763157894736842, "percentage": 19.31, "elapsed_time": "0:29:58", "remaining_time": "2:05:15"}
+{"current_steps": 74, "total_steps": 378, "loss": 0.7155, "lr": 9.7259191408041e-06, "epoch": 0.5842105263157895, "percentage": 19.58, "elapsed_time": "0:30:21", "remaining_time": "2:04:44"}
+{"current_steps": 75, "total_steps": 378, "loss": 0.7088, "lr": 9.710631560777082e-06, "epoch": 0.5921052631578947, "percentage": 19.84, "elapsed_time": "0:30:47", "remaining_time": "2:04:23"}
+{"current_steps": 76, "total_steps": 378, "loss": 0.7058, "lr": 9.694941803075285e-06, "epoch": 0.6, "percentage": 20.11, "elapsed_time": "0:31:05", "remaining_time": "2:03:32"}
+{"current_steps": 77, "total_steps": 378, "loss": 0.738, "lr": 9.678851207236764e-06, "epoch": 0.6078947368421053, "percentage": 20.37, "elapsed_time": "0:31:28", "remaining_time": "2:03:01"}
+{"current_steps": 78, "total_steps": 378, "loss": 0.7116, "lr": 9.66236114702178e-06, "epoch": 0.6157894736842106, "percentage": 20.63, "elapsed_time": "0:31:50", "remaining_time": "2:02:29"}
+{"current_steps": 79, "total_steps": 378, "loss": 0.7207, "lr": 9.645473030295496e-06, "epoch": 0.6236842105263158, "percentage": 20.9, "elapsed_time": "0:32:15", "remaining_time": "2:02:04"}
+{"current_steps": 80, "total_steps": 378, "loss": 0.7015, "lr": 9.628188298907782e-06, "epoch": 0.631578947368421, "percentage": 21.16, "elapsed_time": "0:32:40", "remaining_time": "2:01:42"}
+{"current_steps": 81, "total_steps": 378, "loss": 0.7204, "lr": 9.610508428570122e-06, "epoch": 0.6394736842105263, "percentage": 21.43, "elapsed_time": "0:33:07", "remaining_time": "2:01:25"}
+{"current_steps": 82, "total_steps": 378, "loss": 0.7215, "lr": 9.592434928729617e-06, "epoch": 0.6473684210526316, "percentage": 21.69, "elapsed_time": "0:33:30", "remaining_time": "2:00:55"}
+{"current_steps": 83, "total_steps": 378, "loss": 0.7187, "lr": 9.573969342440107e-06, "epoch": 0.6552631578947369, "percentage": 21.96, "elapsed_time": "0:33:56", "remaining_time": "2:00:37"}
+{"current_steps": 84, "total_steps": 378, "loss": 0.7383, "lr": 9.555113246230443e-06, "epoch": 0.6631578947368421, "percentage": 22.22, "elapsed_time": "0:34:22", "remaining_time": "2:00:17"}
+{"current_steps": 85, "total_steps": 378, "loss": 0.7006, "lr": 9.535868249969882e-06, "epoch": 0.6710526315789473, "percentage": 22.49, "elapsed_time": "0:34:45", "remaining_time": "1:59:47"}
+{"current_steps": 86, "total_steps": 378, "loss": 0.7098, "lr": 9.516235996730645e-06, "epoch": 0.6789473684210526, "percentage": 22.75, "elapsed_time": "0:35:07", "remaining_time": "1:59:16"}
+{"current_steps": 87, "total_steps": 378, "loss": 0.7095, "lr": 9.496218162647629e-06, "epoch": 0.6868421052631579, "percentage": 23.02, "elapsed_time": "0:35:33", "remaining_time": "1:58:56"}
+{"current_steps": 88, "total_steps": 378, "loss": 0.7209, "lr": 9.475816456775313e-06, "epoch": 0.6947368421052632, "percentage": 23.28, "elapsed_time": "0:35:59", "remaining_time": "1:58:35"}
+{"current_steps": 89, "total_steps": 378, "loss": 0.7133, "lr": 9.45503262094184e-06, "epoch": 0.7026315789473684, "percentage": 23.54, "elapsed_time": "0:36:26", "remaining_time": "1:58:19"}
+{"current_steps": 90, "total_steps": 378, "loss": 0.7017, "lr": 9.43386842960031e-06, "epoch": 0.7105263157894737, "percentage": 23.81, "elapsed_time": "0:36:52", "remaining_time": "1:57:58"}
+{"current_steps": 91, "total_steps": 378, "loss": 0.7039, "lr": 9.41232568967728e-06, "epoch": 0.718421052631579, "percentage": 24.07, "elapsed_time": "0:37:14", "remaining_time": "1:57:27"}
+{"current_steps": 92, "total_steps": 378, "loss": 0.6955, "lr": 9.39040624041849e-06, "epoch": 0.7263157894736842, "percentage": 24.34, "elapsed_time": "0:37:41", "remaining_time": "1:57:09"}
+{"current_steps": 93, "total_steps": 378, "loss": 0.6895, "lr": 9.368111953231849e-06, "epoch": 0.7342105263157894, "percentage": 24.6, "elapsed_time": "0:38:05", "remaining_time": "1:56:44"}
+{"current_steps": 94, "total_steps": 378, "loss": 0.6935, "lr": 9.345444731527642e-06, "epoch": 0.7421052631578947, "percentage": 24.87, "elapsed_time": "0:38:34", "remaining_time": "1:56:31"}
+{"current_steps": 95, "total_steps": 378, "loss": 0.6787, "lr": 9.32240651055604e-06, "epoch": 0.75, "percentage": 25.13, "elapsed_time": "0:39:02", "remaining_time": "1:56:19"}
+{"current_steps": 96, "total_steps": 378, "loss": 0.7282, "lr": 9.298999257241862e-06, "epoch": 0.7578947368421053, "percentage": 25.4, "elapsed_time": "0:39:27", "remaining_time": "1:55:55"}
+{"current_steps": 97, "total_steps": 378, "loss": 0.7166, "lr": 9.275224970016656e-06, "epoch": 0.7657894736842106, "percentage": 25.66, "elapsed_time": "0:39:52", "remaining_time": "1:55:30"}
+{"current_steps": 98, "total_steps": 378, "loss": 0.6881, "lr": 9.251085678648072e-06, "epoch": 0.7736842105263158, "percentage": 25.93, "elapsed_time": "0:40:21", "remaining_time": "1:55:17"}
+{"current_steps": 99, "total_steps": 378, "loss": 0.7071, "lr": 9.22658344406657e-06, "epoch": 0.781578947368421, "percentage": 26.19, "elapsed_time": "0:40:42", "remaining_time": "1:54:43"}
+{"current_steps": 100, "total_steps": 378, "loss": 0.708, "lr": 9.201720358189464e-06, "epoch": 0.7894736842105263, "percentage": 26.46, "elapsed_time": "0:41:06", "remaining_time": "1:54:17"}
+{"current_steps": 101, "total_steps": 378, "loss": 0.696, "lr": 9.176498543742328e-06, "epoch": 0.7973684210526316, "percentage": 26.72, "elapsed_time": "0:41:32", "remaining_time": "1:53:56"}
+{"current_steps": 102, "total_steps": 378, "loss": 0.7138, "lr": 9.150920154077753e-06, "epoch": 0.8052631578947368, "percentage": 26.98, "elapsed_time": "0:41:58", "remaining_time": "1:53:34"}
+{"current_steps": 103, "total_steps": 378, "loss": 0.6937, "lr": 9.124987372991512e-06, "epoch": 0.8131578947368421, "percentage": 27.25, "elapsed_time": "0:42:25", "remaining_time": "1:53:17"}
+{"current_steps": 104, "total_steps": 378, "loss": 0.7022, "lr": 9.098702414536107e-06, "epoch": 0.8210526315789474, "percentage": 27.51, "elapsed_time": "0:42:50", "remaining_time": "1:52:52"}
+{"current_steps": 105, "total_steps": 378, "loss": 0.6789, "lr": 9.072067522831743e-06, "epoch": 0.8289473684210527, "percentage": 27.78, "elapsed_time": "0:43:16", "remaining_time": "1:52:30"}
+{"current_steps": 106, "total_steps": 378, "loss": 0.7057, "lr": 9.045084971874738e-06, "epoch": 0.8368421052631579, "percentage": 28.04, "elapsed_time": "0:43:41", "remaining_time": "1:52:07"}
+{"current_steps": 107, "total_steps": 378, "loss": 0.7262, "lr": 9.017757065343368e-06, "epoch": 0.8447368421052631, "percentage": 28.31, "elapsed_time": "0:44:10", "remaining_time": "1:51:52"}
+{"current_steps": 108, "total_steps": 378, "loss": 0.6853, "lr": 8.990086136401199e-06, "epoch": 0.8526315789473684, "percentage": 28.57, "elapsed_time": "0:44:33", "remaining_time": "1:51:23"}
+{"current_steps": 109, "total_steps": 378, "loss": 0.7164, "lr": 8.96207454749787e-06, "epoch": 0.8605263157894737, "percentage": 28.84, "elapsed_time": "0:44:57", "remaining_time": "1:50:56"}
+{"current_steps": 110, "total_steps": 378, "loss": 0.7058, "lr": 8.933724690167417e-06, "epoch": 0.868421052631579, "percentage": 29.1, "elapsed_time": "0:45:24", "remaining_time": "1:50:38"}
+{"current_steps": 111, "total_steps": 378, "loss": 0.698, "lr": 8.905038984824079e-06, "epoch": 0.8763157894736842, "percentage": 29.37, "elapsed_time": "0:45:54", "remaining_time": "1:50:25"}
+{"current_steps": 112, "total_steps": 378, "loss": 0.6961, "lr": 8.87601988055565e-06, "epoch": 0.8842105263157894, "percentage": 29.63, "elapsed_time": "0:46:16", "remaining_time": "1:49:55"}
+{"current_steps": 113, "total_steps": 378, "loss": 0.7129, "lr": 8.846669854914395e-06, "epoch": 0.8921052631578947, "percentage": 29.89, "elapsed_time": "0:46:45", "remaining_time": "1:49:39"}
+{"current_steps": 114, "total_steps": 378, "loss": 0.716, "lr": 8.816991413705515e-06, "epoch": 0.9, "percentage": 30.16, "elapsed_time": "0:47:09", "remaining_time": "1:49:12"}
+{"current_steps": 115, "total_steps": 378, "loss": 0.7034, "lr": 8.786987090773214e-06, "epoch": 0.9078947368421053, "percentage": 30.42, "elapsed_time": "0:47:25", "remaining_time": "1:48:28"}
+{"current_steps": 116, "total_steps": 378, "loss": 0.6933, "lr": 8.756659447784367e-06, "epoch": 0.9157894736842105, "percentage": 30.69, "elapsed_time": "0:47:51", "remaining_time": "1:48:05"}
+{"current_steps": 117, "total_steps": 378, "loss": 0.7154, "lr": 8.726011074009813e-06, "epoch": 0.9236842105263158, "percentage": 30.95, "elapsed_time": "0:48:13", "remaining_time": "1:47:34"}
+{"current_steps": 118, "total_steps": 378, "loss": 0.6916, "lr": 8.695044586103297e-06, "epoch": 0.9315789473684211, "percentage": 31.22, "elapsed_time": "0:48:41", "remaining_time": "1:47:16"}
+{"current_steps": 119, "total_steps": 378, "loss": 0.7074, "lr": 8.663762627878059e-06, "epoch": 0.9394736842105263, "percentage": 31.48, "elapsed_time": "0:49:05", "remaining_time": "1:46:51"}
+{"current_steps": 120, "total_steps": 378, "loss": 0.7028, "lr": 8.632167870081122e-06, "epoch": 0.9473684210526315, "percentage": 31.75, "elapsed_time": "0:49:23", "remaining_time": "1:46:11"}
+{"current_steps": 121, "total_steps": 378, "loss": 0.6997, "lr": 8.600263010165275e-06, "epoch": 0.9552631578947368, "percentage": 32.01, "elapsed_time": "0:49:48", "remaining_time": "1:45:48"}
+{"current_steps": 122, "total_steps": 378, "loss": 0.7066, "lr": 8.568050772058763e-06, "epoch": 0.9631578947368421, "percentage": 32.28, "elapsed_time": "0:50:15", "remaining_time": "1:45:27"}
+{"current_steps": 123, "total_steps": 378, "loss": 0.7001, "lr": 8.535533905932739e-06, "epoch": 0.9710526315789474, "percentage": 32.54, "elapsed_time": "0:50:36", "remaining_time": "1:44:55"}
+{"current_steps": 124, "total_steps": 378, "loss": 0.702, "lr": 8.502715187966455e-06, "epoch": 0.9789473684210527, "percentage": 32.8, "elapsed_time": "0:51:04", "remaining_time": "1:44:36"}
+{"current_steps": 125, "total_steps": 378, "loss": 0.6927, "lr": 8.469597420110249e-06, "epoch": 0.9868421052631579, "percentage": 33.07, "elapsed_time": "0:51:25", "remaining_time": "1:44:05"}
+{"current_steps": 126, "total_steps": 378, "loss": 0.6743, "lr": 8.436183429846314e-06, "epoch": 0.9947368421052631, "percentage": 33.33, "elapsed_time": "0:51:54", "remaining_time": "1:43:48"}
+{"current_steps": 127, "total_steps": 378, "loss": 0.6556, "lr": 8.402476069947309e-06, "epoch": 1.0052631578947369, "percentage": 33.6, "elapsed_time": "0:52:49", "remaining_time": "1:44:23"}
+{"current_steps": 128, "total_steps": 378, "loss": 0.6348, "lr": 8.368478218232787e-06, "epoch": 1.013157894736842, "percentage": 33.86, "elapsed_time": "0:53:13", "remaining_time": "1:43:57"}
+{"current_steps": 129, "total_steps": 378, "loss": 0.63, "lr": 8.334192777323508e-06, "epoch": 1.0210526315789474, "percentage": 34.13, "elapsed_time": "0:53:41", "remaining_time": "1:43:37"}
+{"current_steps": 130, "total_steps": 378, "loss": 0.621, "lr": 8.299622674393615e-06, "epoch": 1.0289473684210526, "percentage": 34.39, "elapsed_time": "0:54:06", "remaining_time": "1:43:13"}
+{"current_steps": 131, "total_steps": 378, "loss": 0.6294, "lr": 8.264770860920722e-06, "epoch": 1.0368421052631578, "percentage": 34.66, "elapsed_time": "0:54:27", "remaining_time": "1:42:41"}
+{"current_steps": 132, "total_steps": 378, "loss": 0.6003, "lr": 8.229640312433938e-06, "epoch": 1.0447368421052632, "percentage": 34.92, "elapsed_time": "0:54:49", "remaining_time": "1:42:10"}
+{"current_steps": 133, "total_steps": 378, "loss": 0.6044, "lr": 8.194234028259806e-06, "epoch": 1.0526315789473684, "percentage": 35.19, "elapsed_time": "0:55:10", "remaining_time": "1:41:37"}
+{"current_steps": 134, "total_steps": 378, "loss": 0.6059, "lr": 8.158555031266255e-06, "epoch": 1.0605263157894738, "percentage": 35.45, "elapsed_time": "0:55:37", "remaining_time": "1:41:16"}
+{"current_steps": 135, "total_steps": 378, "loss": 0.5948, "lr": 8.122606367604497e-06, "epoch": 1.068421052631579, "percentage": 35.71, "elapsed_time": "0:55:59", "remaining_time": "1:40:46"}
+{"current_steps": 136, "total_steps": 378, "loss": 0.617, "lr": 8.086391106448965e-06, "epoch": 1.0763157894736841, "percentage": 35.98, "elapsed_time": "0:56:24", "remaining_time": "1:40:22"}
+{"current_steps": 137, "total_steps": 378, "loss": 0.6205, "lr": 8.049912339735284e-06, "epoch": 1.0842105263157895, "percentage": 36.24, "elapsed_time": "0:56:48", "remaining_time": "1:39:56"}
+{"current_steps": 138, "total_steps": 378, "loss": 0.5898, "lr": 8.013173181896283e-06, "epoch": 1.0921052631578947, "percentage": 36.51, "elapsed_time": "0:57:17", "remaining_time": "1:39:38"}
+{"current_steps": 139, "total_steps": 378, "loss": 0.6283, "lr": 7.976176769596095e-06, "epoch": 1.1, "percentage": 36.77, "elapsed_time": "0:57:44", "remaining_time": "1:39:17"}
+{"current_steps": 140, "total_steps": 378, "loss": 0.5947, "lr": 7.938926261462366e-06, "epoch": 1.1078947368421053, "percentage": 37.04, "elapsed_time": "0:58:09", "remaining_time": "1:38:52"}
+{"current_steps": 141, "total_steps": 378, "loss": 0.6338, "lr": 7.90142483781658e-06, "epoch": 1.1157894736842104, "percentage": 37.3, "elapsed_time": "0:58:35", "remaining_time": "1:38:29"}
+{"current_steps": 142, "total_steps": 378, "loss": 0.6113, "lr": 7.863675700402527e-06, "epoch": 1.1236842105263158, "percentage": 37.57, "elapsed_time": "0:58:57", "remaining_time": "1:37:58"}
+{"current_steps": 143, "total_steps": 378, "loss": 0.6254, "lr": 7.82568207211296e-06, "epoch": 1.131578947368421, "percentage": 37.83, "elapsed_time": "0:59:23", "remaining_time": "1:37:36"}
+{"current_steps": 144, "total_steps": 378, "loss": 0.6213, "lr": 7.787447196714428e-06, "epoch": 1.1394736842105262, "percentage": 38.1, "elapsed_time": "0:59:41", "remaining_time": "1:36:59"}
+{"current_steps": 145, "total_steps": 378, "loss": 0.6221, "lr": 7.748974338570337e-06, "epoch": 1.1473684210526316, "percentage": 38.36, "elapsed_time": "1:00:03", "remaining_time": "1:36:31"}
+{"current_steps": 146, "total_steps": 378, "loss": 0.5909, "lr": 7.710266782362248e-06, "epoch": 1.1552631578947368, "percentage": 38.62, "elapsed_time": "1:00:20", "remaining_time": "1:35:52"}
+{"current_steps": 147, "total_steps": 378, "loss": 0.6373, "lr": 7.671327832809442e-06, "epoch": 1.1631578947368422, "percentage": 38.89, "elapsed_time": "1:00:43", "remaining_time": "1:35:25"}
+{"current_steps": 148, "total_steps": 378, "loss": 0.5908, "lr": 7.63216081438678e-06, "epoch": 1.1710526315789473, "percentage": 39.15, "elapsed_time": "1:01:07", "remaining_time": "1:34:59"}
+{"current_steps": 149, "total_steps": 378, "loss": 0.6138, "lr": 7.5927690710408606e-06, "epoch": 1.1789473684210527, "percentage": 39.42, "elapsed_time": "1:01:33", "remaining_time": "1:34:36"}
+{"current_steps": 150, "total_steps": 378, "loss": 0.6165, "lr": 7.553155965904535e-06, "epoch": 1.186842105263158, "percentage": 39.68, "elapsed_time": "1:01:59", "remaining_time": "1:34:13"}
+{"current_steps": 151, "total_steps": 378, "loss": 0.6308, "lr": 7.513324881009769e-06, "epoch": 1.194736842105263, "percentage": 39.95, "elapsed_time": "1:02:17", "remaining_time": "1:33:38"}
+{"current_steps": 152, "total_steps": 378, "loss": 0.6227, "lr": 7.473279216998896e-06, "epoch": 1.2026315789473685, "percentage": 40.21, "elapsed_time": "1:02:36", "remaining_time": "1:33:05"}
+{"current_steps": 153, "total_steps": 378, "loss": 0.6248, "lr": 7.4330223928342814e-06, "epoch": 1.2105263157894737, "percentage": 40.48, "elapsed_time": "1:03:02", "remaining_time": "1:32:42"}
+{"current_steps": 154, "total_steps": 378, "loss": 0.6043, "lr": 7.392557845506433e-06, "epoch": 1.2184210526315788, "percentage": 40.74, "elapsed_time": "1:03:24", "remaining_time": "1:32:13"}
+{"current_steps": 155, "total_steps": 378, "loss": 0.6122, "lr": 7.351889029740548e-06, "epoch": 1.2263157894736842, "percentage": 41.01, "elapsed_time": "1:03:46", "remaining_time": "1:31:44"}
+{"current_steps": 156, "total_steps": 378, "loss": 0.6091, "lr": 7.311019417701567e-06, "epoch": 1.2342105263157894, "percentage": 41.27, "elapsed_time": "1:04:11", "remaining_time": "1:31:21"}
+{"current_steps": 157, "total_steps": 378, "loss": 0.6092, "lr": 7.269952498697734e-06, "epoch": 1.2421052631578948, "percentage": 41.53, "elapsed_time": "1:04:37", "remaining_time": "1:30:57"}
+{"current_steps": 158, "total_steps": 378, "loss": 0.6164, "lr": 7.2286917788826926e-06, "epoch": 1.25, "percentage": 41.8, "elapsed_time": "1:05:03", "remaining_time": "1:30:35"}
+{"current_steps": 159, "total_steps": 378, "loss": 0.6028, "lr": 7.187240780956133e-06, "epoch": 1.2578947368421054, "percentage": 42.06, "elapsed_time": "1:05:23", "remaining_time": "1:30:04"}
+{"current_steps": 160, "total_steps": 378, "loss": 0.6052, "lr": 7.145603043863045e-06, "epoch": 1.2657894736842106, "percentage": 42.33, "elapsed_time": "1:05:46", "remaining_time": "1:29:36"}
+{"current_steps": 161, "total_steps": 378, "loss": 0.6188, "lr": 7.103782122491577e-06, "epoch": 1.2736842105263158, "percentage": 42.59, "elapsed_time": "1:06:13", "remaining_time": "1:29:15"}
+{"current_steps": 162, "total_steps": 378, "loss": 0.6288, "lr": 7.061781587369518e-06, "epoch": 1.2815789473684212, "percentage": 42.86, "elapsed_time": "1:06:42", "remaining_time": "1:28:57"}
+{"current_steps": 163, "total_steps": 378, "loss": 0.6037, "lr": 7.019605024359475e-06, "epoch": 1.2894736842105263, "percentage": 43.12, "elapsed_time": "1:07:07", "remaining_time": "1:28:32"}
+{"current_steps": 164, "total_steps": 378, "loss": 0.6268, "lr": 6.977256034352713e-06, "epoch": 1.2973684210526315, "percentage": 43.39, "elapsed_time": "1:07:29", "remaining_time": "1:28:04"}
+{"current_steps": 165, "total_steps": 378, "loss": 0.6283, "lr": 6.934738232961728e-06, "epoch": 1.305263157894737, "percentage": 43.65, "elapsed_time": "1:07:55", "remaining_time": "1:27:40"}
+{"current_steps": 166, "total_steps": 378, "loss": 0.6157, "lr": 6.892055250211552e-06, "epoch": 1.313157894736842, "percentage": 43.92, "elapsed_time": "1:08:18", "remaining_time": "1:27:14"}
+{"current_steps": 167, "total_steps": 378, "loss": 0.6187, "lr": 6.849210730229846e-06, "epoch": 1.3210526315789473, "percentage": 44.18, "elapsed_time": "1:08:36", "remaining_time": "1:26:40"}
+{"current_steps": 168, "total_steps": 378, "loss": 0.6162, "lr": 6.806208330935766e-06, "epoch": 1.3289473684210527, "percentage": 44.44, "elapsed_time": "1:08:56", "remaining_time": "1:26:10"}
+{"current_steps": 169, "total_steps": 378, "loss": 0.605, "lr": 6.763051723727663e-06, "epoch": 1.3368421052631578, "percentage": 44.71, "elapsed_time": "1:09:20", "remaining_time": "1:25:44"}
+{"current_steps": 170, "total_steps": 378, "loss": 0.5954, "lr": 6.719744593169642e-06, "epoch": 1.3447368421052632, "percentage": 44.97, "elapsed_time": "1:09:40", "remaining_time": "1:25:15"}
+{"current_steps": 171, "total_steps": 378, "loss": 0.6233, "lr": 6.67629063667697e-06, "epoch": 1.3526315789473684, "percentage": 45.24, "elapsed_time": "1:10:06", "remaining_time": "1:24:52"}
+{"current_steps": 172, "total_steps": 378, "loss": 0.6186, "lr": 6.6326935642004165e-06, "epoch": 1.3605263157894738, "percentage": 45.5, "elapsed_time": "1:10:32", "remaining_time": "1:24:28"}
+{"current_steps": 173, "total_steps": 378, "loss": 0.6171, "lr": 6.588957097909509e-06, "epoch": 1.368421052631579, "percentage": 45.77, "elapsed_time": "1:10:56", "remaining_time": "1:24:04"}
+{"current_steps": 174, "total_steps": 378, "loss": 0.5943, "lr": 6.545084971874738e-06, "epoch": 1.3763157894736842, "percentage": 46.03, "elapsed_time": "1:11:27", "remaining_time": "1:23:47"}
+{"current_steps": 175, "total_steps": 378, "loss": 0.6191, "lr": 6.501080931748764e-06, "epoch": 1.3842105263157896, "percentage": 46.3, "elapsed_time": "1:11:47", "remaining_time": "1:23:16"}
+{"current_steps": 176, "total_steps": 378, "loss": 0.6134, "lr": 6.456948734446624e-06, "epoch": 1.3921052631578947, "percentage": 46.56, "elapsed_time": "1:12:13", "remaining_time": "1:22:54"}
+{"current_steps": 177, "total_steps": 378, "loss": 0.6005, "lr": 6.412692147824976e-06, "epoch": 1.4, "percentage": 46.83, "elapsed_time": "1:12:44", "remaining_time": "1:22:36"}
+{"current_steps": 178, "total_steps": 378, "loss": 0.6082, "lr": 6.368314950360416e-06, "epoch": 1.4078947368421053, "percentage": 47.09, "elapsed_time": "1:13:06", "remaining_time": "1:22:08"}
+{"current_steps": 179, "total_steps": 378, "loss": 0.6306, "lr": 6.323820930826879e-06, "epoch": 1.4157894736842105, "percentage": 47.35, "elapsed_time": "1:13:37", "remaining_time": "1:21:51"}
+{"current_steps": 180, "total_steps": 378, "loss": 0.6188, "lr": 6.279213887972179e-06, "epoch": 1.4236842105263157, "percentage": 47.62, "elapsed_time": "1:13:59", "remaining_time": "1:21:23"}
+{"current_steps": 181, "total_steps": 378, "loss": 0.6154, "lr": 6.234497630193666e-06, "epoch": 1.431578947368421, "percentage": 47.88, "elapsed_time": "1:14:21", "remaining_time": "1:20:56"}
+{"current_steps": 182, "total_steps": 378, "loss": 0.6105, "lr": 6.189675975213094e-06, "epoch": 1.4394736842105262, "percentage": 48.15, "elapsed_time": "1:14:43", "remaining_time": "1:20:28"}
+{"current_steps": 183, "total_steps": 378, "loss": 0.6023, "lr": 6.144752749750671e-06, "epoch": 1.4473684210526316, "percentage": 48.41, "elapsed_time": "1:15:09", "remaining_time": "1:20:05"}
+{"current_steps": 184, "total_steps": 378, "loss": 0.6081, "lr": 6.099731789198344e-06, "epoch": 1.4552631578947368, "percentage": 48.68, "elapsed_time": "1:15:36", "remaining_time": "1:19:42"}
+{"current_steps": 185, "total_steps": 378, "loss": 0.6115, "lr": 6.05461693729235e-06, "epoch": 1.4631578947368422, "percentage": 48.94, "elapsed_time": "1:15:55", "remaining_time": "1:19:12"}
+{"current_steps": 186, "total_steps": 378, "loss": 0.6044, "lr": 6.009412045785051e-06, "epoch": 1.4710526315789474, "percentage": 49.21, "elapsed_time": "1:16:20", "remaining_time": "1:18:48"}
+{"current_steps": 187, "total_steps": 378, "loss": 0.6253, "lr": 5.964120974116085e-06, "epoch": 1.4789473684210526, "percentage": 49.47, "elapsed_time": "1:16:44", "remaining_time": "1:18:23"}
+{"current_steps": 188, "total_steps": 378, "loss": 0.614, "lr": 5.918747589082853e-06, "epoch": 1.486842105263158, "percentage": 49.74, "elapsed_time": "1:17:09", "remaining_time": "1:17:58"}
+{"current_steps": 189, "total_steps": 378, "loss": 0.5987, "lr": 5.8732957645103946e-06, "epoch": 1.4947368421052631, "percentage": 50.0, "elapsed_time": "1:17:36", "remaining_time": "1:17:36"}
+{"current_steps": 190, "total_steps": 378, "loss": 0.6099, "lr": 5.82776938092065e-06, "epoch": 1.5026315789473683, "percentage": 50.26, "elapsed_time": "1:17:58", "remaining_time": "1:17:08"}
+{"current_steps": 191, "total_steps": 378, "loss": 0.6272, "lr": 5.782172325201155e-06, "epoch": 1.5105263157894737, "percentage": 50.53, "elapsed_time": "1:18:30", "remaining_time": "1:16:51"}
+{"current_steps": 192, "total_steps": 378, "loss": 0.6132, "lr": 5.736508490273189e-06, "epoch": 1.518421052631579, "percentage": 50.79, "elapsed_time": "1:18:57", "remaining_time": "1:16:29"}
+{"current_steps": 193, "total_steps": 378, "loss": 0.6022, "lr": 5.690781774759412e-06, "epoch": 1.526315789473684, "percentage": 51.06, "elapsed_time": "1:19:17", "remaining_time": "1:16:00"}
+{"current_steps": 194, "total_steps": 378, "loss": 0.6144, "lr": 5.644996082651018e-06, "epoch": 1.5342105263157895, "percentage": 51.32, "elapsed_time": "1:19:42", "remaining_time": "1:15:35"}
+{"current_steps": 195, "total_steps": 378, "loss": 0.6343, "lr": 5.5991553229744166e-06, "epoch": 1.5421052631578949, "percentage": 51.59, "elapsed_time": "1:20:04", "remaining_time": "1:15:09"}
+{"current_steps": 196, "total_steps": 378, "loss": 0.6165, "lr": 5.553263409457504e-06, "epoch": 1.55, "percentage": 51.85, "elapsed_time": "1:20:27", "remaining_time": "1:14:42"}
+{"current_steps": 197, "total_steps": 378, "loss": 0.611, "lr": 5.507324260195516e-06, "epoch": 1.5578947368421052, "percentage": 52.12, "elapsed_time": "1:20:51", "remaining_time": "1:14:17"}
+{"current_steps": 198, "total_steps": 378, "loss": 0.6079, "lr": 5.46134179731651e-06, "epoch": 1.5657894736842106, "percentage": 52.38, "elapsed_time": "1:21:16", "remaining_time": "1:13:53"}
+{"current_steps": 199, "total_steps": 378, "loss": 0.5994, "lr": 5.41531994664652e-06, "epoch": 1.5736842105263158, "percentage": 52.65, "elapsed_time": "1:21:35", "remaining_time": "1:13:23"}
+{"current_steps": 200, "total_steps": 378, "loss": 0.597, "lr": 5.36926263737437e-06, "epoch": 1.581578947368421, "percentage": 52.91, "elapsed_time": "1:22:01", "remaining_time": "1:13:00"}
+{"current_steps": 201, "total_steps": 378, "loss": 0.596, "lr": 5.323173801716222e-06, "epoch": 1.5894736842105264, "percentage": 53.17, "elapsed_time": "1:22:28", "remaining_time": "1:12:37"}
+{"current_steps": 202, "total_steps": 378, "loss": 0.6261, "lr": 5.27705737457985e-06, "epoch": 1.5973684210526315, "percentage": 53.44, "elapsed_time": "1:22:49", "remaining_time": "1:12:09"}
+{"current_steps": 203, "total_steps": 378, "loss": 0.6079, "lr": 5.230917293228699e-06, "epoch": 1.6052631578947367, "percentage": 53.7, "elapsed_time": "1:23:09", "remaining_time": "1:11:41"}
+{"current_steps": 204, "total_steps": 378, "loss": 0.5942, "lr": 5.184757496945726e-06, "epoch": 1.6131578947368421, "percentage": 53.97, "elapsed_time": "1:23:31", "remaining_time": "1:11:14"}
+{"current_steps": 205, "total_steps": 378, "loss": 0.6135, "lr": 5.138581926697083e-06, "epoch": 1.6210526315789475, "percentage": 54.23, "elapsed_time": "1:23:57", "remaining_time": "1:10:51"}
+{"current_steps": 206, "total_steps": 378, "loss": 0.587, "lr": 5.09239452479565e-06, "epoch": 1.6289473684210525, "percentage": 54.5, "elapsed_time": "1:24:21", "remaining_time": "1:10:26"}
+{"current_steps": 207, "total_steps": 378, "loss": 0.5961, "lr": 5.046199234564455e-06, "epoch": 1.6368421052631579, "percentage": 54.76, "elapsed_time": "1:24:53", "remaining_time": "1:10:07"}
+{"current_steps": 208, "total_steps": 378, "loss": 0.6022, "lr": 5e-06, "epoch": 1.6447368421052633, "percentage": 55.03, "elapsed_time": "1:25:21", "remaining_time": "1:09:45"}
+{"current_steps": 209, "total_steps": 378, "loss": 0.5966, "lr": 4.953800765435547e-06, "epoch": 1.6526315789473685, "percentage": 55.29, "elapsed_time": "1:25:43", "remaining_time": "1:09:19"}
+{"current_steps": 210, "total_steps": 378, "loss": 0.6069, "lr": 4.907605475204352e-06, "epoch": 1.6605263157894736, "percentage": 55.56, "elapsed_time": "1:26:10", "remaining_time": "1:08:56"}
+{"current_steps": 211, "total_steps": 378, "loss": 0.6009, "lr": 4.861418073302919e-06, "epoch": 1.668421052631579, "percentage": 55.82, "elapsed_time": "1:26:33", "remaining_time": "1:08:30"}
+{"current_steps": 212, "total_steps": 378, "loss": 0.6183, "lr": 4.815242503054277e-06, "epoch": 1.6763157894736842, "percentage": 56.08, "elapsed_time": "1:27:02", "remaining_time": "1:08:09"}
+{"current_steps": 213, "total_steps": 378, "loss": 0.6109, "lr": 4.7690827067713035e-06, "epoch": 1.6842105263157894, "percentage": 56.35, "elapsed_time": "1:27:29", "remaining_time": "1:07:46"}
+{"current_steps": 214, "total_steps": 378, "loss": 0.615, "lr": 4.7229426254201504e-06, "epoch": 1.6921052631578948, "percentage": 56.61, "elapsed_time": "1:27:54", "remaining_time": "1:07:22"}
+{"current_steps": 215, "total_steps": 378, "loss": 0.6114, "lr": 4.676826198283779e-06, "epoch": 1.7, "percentage": 56.88, "elapsed_time": "1:28:18", "remaining_time": "1:06:57"}
+{"current_steps": 216, "total_steps": 378, "loss": 0.6039, "lr": 4.630737362625631e-06, "epoch": 1.7078947368421051, "percentage": 57.14, "elapsed_time": "1:28:41", "remaining_time": "1:06:31"}
+{"current_steps": 217, "total_steps": 378, "loss": 0.6154, "lr": 4.584680053353481e-06, "epoch": 1.7157894736842105, "percentage": 57.41, "elapsed_time": "1:29:07", "remaining_time": "1:06:07"}
+{"current_steps": 218, "total_steps": 378, "loss": 0.6133, "lr": 4.53865820268349e-06, "epoch": 1.723684210526316, "percentage": 57.67, "elapsed_time": "1:29:31", "remaining_time": "1:05:42"}
+{"current_steps": 219, "total_steps": 378, "loss": 0.6018, "lr": 4.492675739804486e-06, "epoch": 1.731578947368421, "percentage": 57.94, "elapsed_time": "1:29:57", "remaining_time": "1:05:18"}
+{"current_steps": 220, "total_steps": 378, "loss": 0.6083, "lr": 4.446736590542497e-06, "epoch": 1.7394736842105263, "percentage": 58.2, "elapsed_time": "1:30:21", "remaining_time": "1:04:53"}
+{"current_steps": 221, "total_steps": 378, "loss": 0.6015, "lr": 4.400844677025585e-06, "epoch": 1.7473684210526317, "percentage": 58.47, "elapsed_time": "1:30:47", "remaining_time": "1:04:30"}
+{"current_steps": 222, "total_steps": 378, "loss": 0.5983, "lr": 4.355003917348985e-06, "epoch": 1.7552631578947369, "percentage": 58.73, "elapsed_time": "1:31:16", "remaining_time": "1:04:08"}
+{"current_steps": 223, "total_steps": 378, "loss": 0.5891, "lr": 4.309218225240591e-06, "epoch": 1.763157894736842, "percentage": 58.99, "elapsed_time": "1:31:42", "remaining_time": "1:03:44"}
+{"current_steps": 224, "total_steps": 378, "loss": 0.5864, "lr": 4.263491509726812e-06, "epoch": 1.7710526315789474, "percentage": 59.26, "elapsed_time": "1:32:03", "remaining_time": "1:03:17"}
+{"current_steps": 225, "total_steps": 378, "loss": 0.6084, "lr": 4.217827674798845e-06, "epoch": 1.7789473684210526, "percentage": 59.52, "elapsed_time": "1:32:25", "remaining_time": "1:02:51"}
+{"current_steps": 226, "total_steps": 378, "loss": 0.6055, "lr": 4.17223061907935e-06, "epoch": 1.7868421052631578, "percentage": 59.79, "elapsed_time": "1:32:50", "remaining_time": "1:02:26"}
+{"current_steps": 227, "total_steps": 378, "loss": 0.616, "lr": 4.126704235489606e-06, "epoch": 1.7947368421052632, "percentage": 60.05, "elapsed_time": "1:33:15", "remaining_time": "1:02:02"}
+{"current_steps": 228, "total_steps": 378, "loss": 0.6088, "lr": 4.081252410917148e-06, "epoch": 1.8026315789473686, "percentage": 60.32, "elapsed_time": "1:33:39", "remaining_time": "1:01:36"}
+{"current_steps": 229, "total_steps": 378, "loss": 0.6146, "lr": 4.035879025883916e-06, "epoch": 1.8105263157894735, "percentage": 60.58, "elapsed_time": "1:34:05", "remaining_time": "1:01:13"}
+{"current_steps": 230, "total_steps": 378, "loss": 0.5895, "lr": 3.99058795421495e-06, "epoch": 1.818421052631579, "percentage": 60.85, "elapsed_time": "1:34:33", "remaining_time": "1:00:51"}
+{"current_steps": 231, "total_steps": 378, "loss": 0.5979, "lr": 3.945383062707652e-06, "epoch": 1.8263157894736843, "percentage": 61.11, "elapsed_time": "1:34:57", "remaining_time": "1:00:25"}
+{"current_steps": 232, "total_steps": 378, "loss": 0.6119, "lr": 3.9002682108016585e-06, "epoch": 1.8342105263157895, "percentage": 61.38, "elapsed_time": "1:35:21", "remaining_time": "1:00:00"}
+{"current_steps": 233, "total_steps": 378, "loss": 0.6104, "lr": 3.855247250249331e-06, "epoch": 1.8421052631578947, "percentage": 61.64, "elapsed_time": "1:35:47", "remaining_time": "0:59:37"}
+{"current_steps": 234, "total_steps": 378, "loss": 0.606, "lr": 3.8103240247869077e-06, "epoch": 1.85, "percentage": 61.9, "elapsed_time": "1:36:13", "remaining_time": "0:59:12"}
+{"current_steps": 235, "total_steps": 378, "loss": 0.6147, "lr": 3.765502369806334e-06, "epoch": 1.8578947368421053, "percentage": 62.17, "elapsed_time": "1:36:35", "remaining_time": "0:58:46"}
+{"current_steps": 236, "total_steps": 378, "loss": 0.5947, "lr": 3.720786112027822e-06, "epoch": 1.8657894736842104, "percentage": 62.43, "elapsed_time": "1:36:56", "remaining_time": "0:58:20"}
+{"current_steps": 237, "total_steps": 378, "loss": 0.5975, "lr": 3.6761790691731207e-06, "epoch": 1.8736842105263158, "percentage": 62.7, "elapsed_time": "1:37:22", "remaining_time": "0:57:55"}
+{"current_steps": 238, "total_steps": 378, "loss": 0.5898, "lr": 3.6316850496395863e-06, "epoch": 1.881578947368421, "percentage": 62.96, "elapsed_time": "1:37:46", "remaining_time": "0:57:30"}
+{"current_steps": 239, "total_steps": 378, "loss": 0.5953, "lr": 3.587307852175025e-06, "epoch": 1.8894736842105262, "percentage": 63.23, "elapsed_time": "1:38:10", "remaining_time": "0:57:05"}
+{"current_steps": 240, "total_steps": 378, "loss": 0.6185, "lr": 3.5430512655533774e-06, "epoch": 1.8973684210526316, "percentage": 63.49, "elapsed_time": "1:38:31", "remaining_time": "0:56:38"}
+{"current_steps": 241, "total_steps": 378, "loss": 0.5985, "lr": 3.498919068251237e-06, "epoch": 1.905263157894737, "percentage": 63.76, "elapsed_time": "1:38:55", "remaining_time": "0:56:13"}
+{"current_steps": 242, "total_steps": 378, "loss": 0.6052, "lr": 3.4549150281252635e-06, "epoch": 1.913157894736842, "percentage": 64.02, "elapsed_time": "1:39:14", "remaining_time": "0:55:46"}
+{"current_steps": 243, "total_steps": 378, "loss": 0.6158, "lr": 3.4110429020904924e-06, "epoch": 1.9210526315789473, "percentage": 64.29, "elapsed_time": "1:39:40", "remaining_time": "0:55:22"}
+{"current_steps": 244, "total_steps": 378, "loss": 0.6079, "lr": 3.3673064357995844e-06, "epoch": 1.9289473684210527, "percentage": 64.55, "elapsed_time": "1:40:02", "remaining_time": "0:54:56"}
+{"current_steps": 245, "total_steps": 378, "loss": 0.6023, "lr": 3.3237093633230323e-06, "epoch": 1.936842105263158, "percentage": 64.81, "elapsed_time": "1:40:30", "remaining_time": "0:54:33"}
+{"current_steps": 246, "total_steps": 378, "loss": 0.5972, "lr": 3.2802554068303595e-06, "epoch": 1.944736842105263, "percentage": 65.08, "elapsed_time": "1:40:50", "remaining_time": "0:54:06"}
+{"current_steps": 247, "total_steps": 378, "loss": 0.6012, "lr": 3.236948276272337e-06, "epoch": 1.9526315789473685, "percentage": 65.34, "elapsed_time": "1:41:17", "remaining_time": "0:53:43"}
+{"current_steps": 248, "total_steps": 378, "loss": 0.6186, "lr": 3.1937916690642356e-06, "epoch": 1.9605263157894737, "percentage": 65.61, "elapsed_time": "1:41:42", "remaining_time": "0:53:19"}
+{"current_steps": 249, "total_steps": 378, "loss": 0.6218, "lr": 3.150789269770155e-06, "epoch": 1.9684210526315788, "percentage": 65.87, "elapsed_time": "1:42:10", "remaining_time": "0:52:56"}
+{"current_steps": 250, "total_steps": 378, "loss": 0.6088, "lr": 3.107944749788449e-06, "epoch": 1.9763157894736842, "percentage": 66.14, "elapsed_time": "1:42:33", "remaining_time": "0:52:30"}
+{"current_steps": 251, "total_steps": 378, "loss": 0.5958, "lr": 3.0652617670382745e-06, "epoch": 1.9842105263157894, "percentage": 66.4, "elapsed_time": "1:43:02", "remaining_time": "0:52:08"}
+{"current_steps": 252, "total_steps": 378, "loss": 0.6141, "lr": 3.0227439656472878e-06, "epoch": 1.9921052631578946, "percentage": 66.67, "elapsed_time": "1:43:31", "remaining_time": "0:51:45"}
+{"current_steps": 253, "total_steps": 378, "loss": 0.5795, "lr": 2.980394975640526e-06, "epoch": 2.0026315789473683, "percentage": 66.93, "elapsed_time": "1:44:27", "remaining_time": "0:51:36"}
+{"current_steps": 254, "total_steps": 378, "loss": 0.5615, "lr": 2.9382184126304834e-06, "epoch": 2.0105263157894737, "percentage": 67.2, "elapsed_time": "1:44:46", "remaining_time": "0:51:09"}
+{"current_steps": 255, "total_steps": 378, "loss": 0.517, "lr": 2.8962178775084267e-06, "epoch": 2.018421052631579, "percentage": 67.46, "elapsed_time": "1:45:09", "remaining_time": "0:50:43"}
+{"current_steps": 256, "total_steps": 378, "loss": 0.5421, "lr": 2.8543969561369556e-06, "epoch": 2.026315789473684, "percentage": 67.72, "elapsed_time": "1:45:29", "remaining_time": "0:50:16"}
+{"current_steps": 257, "total_steps": 378, "loss": 0.5397, "lr": 2.812759219043869e-06, "epoch": 2.0342105263157895, "percentage": 67.99, "elapsed_time": "1:45:57", "remaining_time": "0:49:53"}
+{"current_steps": 258, "total_steps": 378, "loss": 0.5523, "lr": 2.771308221117309e-06, "epoch": 2.042105263157895, "percentage": 68.25, "elapsed_time": "1:46:26", "remaining_time": "0:49:30"}
+{"current_steps": 259, "total_steps": 378, "loss": 0.518, "lr": 2.7300475013022666e-06, "epoch": 2.05, "percentage": 68.52, "elapsed_time": "1:46:58", "remaining_time": "0:49:09"}
+{"current_steps": 260, "total_steps": 378, "loss": 0.5343, "lr": 2.6889805822984348e-06, "epoch": 2.057894736842105, "percentage": 68.78, "elapsed_time": "1:47:26", "remaining_time": "0:48:45"}
+{"current_steps": 261, "total_steps": 378, "loss": 0.5421, "lr": 2.648110970259454e-06, "epoch": 2.0657894736842106, "percentage": 69.05, "elapsed_time": "1:47:50", "remaining_time": "0:48:20"}
+{"current_steps": 262, "total_steps": 378, "loss": 0.5382, "lr": 2.607442154493568e-06, "epoch": 2.0736842105263156, "percentage": 69.31, "elapsed_time": "1:48:12", "remaining_time": "0:47:54"}
+{"current_steps": 263, "total_steps": 378, "loss": 0.5367, "lr": 2.5669776071657194e-06, "epoch": 2.081578947368421, "percentage": 69.58, "elapsed_time": "1:48:38", "remaining_time": "0:47:30"}
+{"current_steps": 264, "total_steps": 378, "loss": 0.5371, "lr": 2.526720783001107e-06, "epoch": 2.0894736842105264, "percentage": 69.84, "elapsed_time": "1:49:03", "remaining_time": "0:47:05"}
+{"current_steps": 265, "total_steps": 378, "loss": 0.5304, "lr": 2.486675118990233e-06, "epoch": 2.0973684210526318, "percentage": 70.11, "elapsed_time": "1:49:28", "remaining_time": "0:46:41"}
+{"current_steps": 266, "total_steps": 378, "loss": 0.5286, "lr": 2.4468440340954664e-06, "epoch": 2.1052631578947367, "percentage": 70.37, "elapsed_time": "1:49:55", "remaining_time": "0:46:17"}
+{"current_steps": 267, "total_steps": 378, "loss": 0.5733, "lr": 2.4072309289591394e-06, "epoch": 2.113157894736842, "percentage": 70.63, "elapsed_time": "1:50:17", "remaining_time": "0:45:50"}
+{"current_steps": 268, "total_steps": 378, "loss": 0.5464, "lr": 2.3678391856132203e-06, "epoch": 2.1210526315789475, "percentage": 70.9, "elapsed_time": "1:50:41", "remaining_time": "0:45:26"}
+{"current_steps": 269, "total_steps": 378, "loss": 0.5326, "lr": 2.328672167190558e-06, "epoch": 2.1289473684210525, "percentage": 71.16, "elapsed_time": "1:51:06", "remaining_time": "0:45:01"}
+{"current_steps": 270, "total_steps": 378, "loss": 0.5045, "lr": 2.289733217637753e-06, "epoch": 2.136842105263158, "percentage": 71.43, "elapsed_time": "1:51:32", "remaining_time": "0:44:36"}
+{"current_steps": 271, "total_steps": 378, "loss": 0.5214, "lr": 2.2510256614296638e-06, "epoch": 2.1447368421052633, "percentage": 71.69, "elapsed_time": "1:51:53", "remaining_time": "0:44:10"}
+{"current_steps": 272, "total_steps": 378, "loss": 0.5436, "lr": 2.2125528032855727e-06, "epoch": 2.1526315789473682, "percentage": 71.96, "elapsed_time": "1:52:22", "remaining_time": "0:43:47"}
+{"current_steps": 273, "total_steps": 378, "loss": 0.5268, "lr": 2.174317927887041e-06, "epoch": 2.1605263157894736, "percentage": 72.22, "elapsed_time": "1:52:49", "remaining_time": "0:43:23"}
+{"current_steps": 274, "total_steps": 378, "loss": 0.5281, "lr": 2.136324299597474e-06, "epoch": 2.168421052631579, "percentage": 72.49, "elapsed_time": "1:53:13", "remaining_time": "0:42:58"}
+{"current_steps": 275, "total_steps": 378, "loss": 0.5177, "lr": 2.098575162183422e-06, "epoch": 2.1763157894736844, "percentage": 72.75, "elapsed_time": "1:53:36", "remaining_time": "0:42:32"}
+{"current_steps": 276, "total_steps": 378, "loss": 0.533, "lr": 2.061073738537635e-06, "epoch": 2.1842105263157894, "percentage": 73.02, "elapsed_time": "1:54:02", "remaining_time": "0:42:08"}
+{"current_steps": 277, "total_steps": 378, "loss": 0.5286, "lr": 2.023823230403907e-06, "epoch": 2.192105263157895, "percentage": 73.28, "elapsed_time": "1:54:27", "remaining_time": "0:41:43"}
+{"current_steps": 278, "total_steps": 378, "loss": 0.5249, "lr": 1.9868268181037186e-06, "epoch": 2.2, "percentage": 73.54, "elapsed_time": "1:54:53", "remaining_time": "0:41:19"}
+{"current_steps": 279, "total_steps": 378, "loss": 0.5307, "lr": 1.9500876602647167e-06, "epoch": 2.207894736842105, "percentage": 73.81, "elapsed_time": "1:55:19", "remaining_time": "0:40:55"}
+{"current_steps": 280, "total_steps": 378, "loss": 0.5511, "lr": 1.913608893551036e-06, "epoch": 2.2157894736842105, "percentage": 74.07, "elapsed_time": "1:55:40", "remaining_time": "0:40:29"}
+{"current_steps": 281, "total_steps": 378, "loss": 0.5424, "lr": 1.8773936323955055e-06, "epoch": 2.223684210526316, "percentage": 74.34, "elapsed_time": "1:56:07", "remaining_time": "0:40:05"}
+{"current_steps": 282, "total_steps": 378, "loss": 0.5365, "lr": 1.8414449687337467e-06, "epoch": 2.231578947368421, "percentage": 74.6, "elapsed_time": "1:56:34", "remaining_time": "0:39:41"}
+{"current_steps": 283, "total_steps": 378, "loss": 0.5303, "lr": 1.8057659717401948e-06, "epoch": 2.2394736842105263, "percentage": 74.87, "elapsed_time": "1:57:02", "remaining_time": "0:39:17"}
+{"current_steps": 284, "total_steps": 378, "loss": 0.5386, "lr": 1.7703596875660645e-06, "epoch": 2.2473684210526317, "percentage": 75.13, "elapsed_time": "1:57:23", "remaining_time": "0:38:51"}
+{"current_steps": 285, "total_steps": 378, "loss": 0.5349, "lr": 1.7352291390792798e-06, "epoch": 2.2552631578947366, "percentage": 75.4, "elapsed_time": "1:57:45", "remaining_time": "0:38:25"}
+{"current_steps": 286, "total_steps": 378, "loss": 0.5159, "lr": 1.7003773256063882e-06, "epoch": 2.263157894736842, "percentage": 75.66, "elapsed_time": "1:58:10", "remaining_time": "0:38:00"}
+{"current_steps": 287, "total_steps": 378, "loss": 0.5432, "lr": 1.6658072226764949e-06, "epoch": 2.2710526315789474, "percentage": 75.93, "elapsed_time": "1:58:35", "remaining_time": "0:37:36"}
+{"current_steps": 288, "total_steps": 378, "loss": 0.5133, "lr": 1.6315217817672142e-06, "epoch": 2.2789473684210524, "percentage": 76.19, "elapsed_time": "1:58:52", "remaining_time": "0:37:09"}
+{"current_steps": 289, "total_steps": 378, "loss": 0.5364, "lr": 1.5975239300526924e-06, "epoch": 2.286842105263158, "percentage": 76.46, "elapsed_time": "1:59:12", "remaining_time": "0:36:42"}
+{"current_steps": 290, "total_steps": 378, "loss": 0.5325, "lr": 1.5638165701536866e-06, "epoch": 2.294736842105263, "percentage": 76.72, "elapsed_time": "1:59:34", "remaining_time": "0:36:17"}
+{"current_steps": 291, "total_steps": 378, "loss": 0.5429, "lr": 1.5304025798897521e-06, "epoch": 2.3026315789473686, "percentage": 76.98, "elapsed_time": "2:00:02", "remaining_time": "0:35:53"}
+{"current_steps": 292, "total_steps": 378, "loss": 0.5384, "lr": 1.4972848120335453e-06, "epoch": 2.3105263157894735, "percentage": 77.25, "elapsed_time": "2:00:27", "remaining_time": "0:35:28"}
+{"current_steps": 293, "total_steps": 378, "loss": 0.5449, "lr": 1.4644660940672628e-06, "epoch": 2.318421052631579, "percentage": 77.51, "elapsed_time": "2:00:53", "remaining_time": "0:35:04"}
+{"current_steps": 294, "total_steps": 378, "loss": 0.5404, "lr": 1.4319492279412388e-06, "epoch": 2.3263157894736843, "percentage": 77.78, "elapsed_time": "2:01:20", "remaining_time": "0:34:40"}
+{"current_steps": 295, "total_steps": 378, "loss": 0.5431, "lr": 1.399736989834728e-06, "epoch": 2.3342105263157893, "percentage": 78.04, "elapsed_time": "2:01:43", "remaining_time": "0:34:14"}
+{"current_steps": 296, "total_steps": 378, "loss": 0.5221, "lr": 1.3678321299188802e-06, "epoch": 2.3421052631578947, "percentage": 78.31, "elapsed_time": "2:02:06", "remaining_time": "0:33:49"}
+{"current_steps": 297, "total_steps": 378, "loss": 0.5229, "lr": 1.336237372121944e-06, "epoch": 2.35, "percentage": 78.57, "elapsed_time": "2:02:29", "remaining_time": "0:33:24"}
+{"current_steps": 298, "total_steps": 378, "loss": 0.5344, "lr": 1.3049554138967052e-06, "epoch": 2.3578947368421055, "percentage": 78.84, "elapsed_time": "2:02:59", "remaining_time": "0:33:01"}
+{"current_steps": 299, "total_steps": 378, "loss": 0.5432, "lr": 1.2739889259901866e-06, "epoch": 2.3657894736842104, "percentage": 79.1, "elapsed_time": "2:03:22", "remaining_time": "0:32:35"}
+{"current_steps": 300, "total_steps": 378, "loss": 0.5374, "lr": 1.2433405522156334e-06, "epoch": 2.373684210526316, "percentage": 79.37, "elapsed_time": "2:03:47", "remaining_time": "0:32:11"}
+{"current_steps": 301, "total_steps": 378, "loss": 0.5286, "lr": 1.213012909226786e-06, "epoch": 2.3815789473684212, "percentage": 79.63, "elapsed_time": "2:04:08", "remaining_time": "0:31:45"}
+{"current_steps": 302, "total_steps": 378, "loss": 0.5527, "lr": 1.1830085862944851e-06, "epoch": 2.389473684210526, "percentage": 79.89, "elapsed_time": "2:04:35", "remaining_time": "0:31:21"}
+{"current_steps": 303, "total_steps": 378, "loss": 0.567, "lr": 1.1533301450856054e-06, "epoch": 2.3973684210526316, "percentage": 80.16, "elapsed_time": "2:05:05", "remaining_time": "0:30:57"}
+{"current_steps": 304, "total_steps": 378, "loss": 0.5406, "lr": 1.1239801194443507e-06, "epoch": 2.405263157894737, "percentage": 80.42, "elapsed_time": "2:05:27", "remaining_time": "0:30:32"}
+{"current_steps": 305, "total_steps": 378, "loss": 0.5395, "lr": 1.0949610151759233e-06, "epoch": 2.413157894736842, "percentage": 80.69, "elapsed_time": "2:05:51", "remaining_time": "0:30:07"}
+{"current_steps": 306, "total_steps": 378, "loss": 0.5485, "lr": 1.066275309832584e-06, "epoch": 2.4210526315789473, "percentage": 80.95, "elapsed_time": "2:06:15", "remaining_time": "0:29:42"}
+{"current_steps": 307, "total_steps": 378, "loss": 0.5344, "lr": 1.037925452502131e-06, "epoch": 2.4289473684210527, "percentage": 81.22, "elapsed_time": "2:06:38", "remaining_time": "0:29:17"}
+{"current_steps": 308, "total_steps": 378, "loss": 0.5647, "lr": 1.0099138635988026e-06, "epoch": 2.4368421052631577, "percentage": 81.48, "elapsed_time": "2:07:05", "remaining_time": "0:28:53"}
+{"current_steps": 309, "total_steps": 378, "loss": 0.5219, "lr": 9.822429346566314e-07, "epoch": 2.444736842105263, "percentage": 81.75, "elapsed_time": "2:07:30", "remaining_time": "0:28:28"}
+{"current_steps": 310, "total_steps": 378, "loss": 0.5413, "lr": 9.549150281252633e-07, "epoch": 2.4526315789473685, "percentage": 82.01, "elapsed_time": "2:07:47", "remaining_time": "0:28:01"}
+{"current_steps": 311, "total_steps": 378, "loss": 0.5288, "lr": 9.279324771682586e-07, "epoch": 2.4605263157894735, "percentage": 82.28, "elapsed_time": "2:08:15", "remaining_time": "0:27:37"}
+{"current_steps": 312, "total_steps": 378, "loss": 0.5194, "lr": 9.01297585463895e-07, "epoch": 2.468421052631579, "percentage": 82.54, "elapsed_time": "2:08:39", "remaining_time": "0:27:13"}
+{"current_steps": 313, "total_steps": 378, "loss": 0.5446, "lr": 8.750126270084891e-07, "epoch": 2.4763157894736842, "percentage": 82.8, "elapsed_time": "2:09:04", "remaining_time": "0:26:48"}
+{"current_steps": 314, "total_steps": 378, "loss": 0.5544, "lr": 8.490798459222477e-07, "epoch": 2.4842105263157896, "percentage": 83.07, "elapsed_time": "2:09:28", "remaining_time": "0:26:23"}
+{"current_steps": 315, "total_steps": 378, "loss": 0.5344, "lr": 8.235014562576732e-07, "epoch": 2.4921052631578946, "percentage": 83.33, "elapsed_time": "2:09:54", "remaining_time": "0:25:58"}
+{"current_steps": 316, "total_steps": 378, "loss": 0.5304, "lr": 7.98279641810537e-07, "epoch": 2.5, "percentage": 83.6, "elapsed_time": "2:10:16", "remaining_time": "0:25:33"}
+{"current_steps": 317, "total_steps": 378, "loss": 0.5423, "lr": 7.734165559334327e-07, "epoch": 2.5078947368421054, "percentage": 83.86, "elapsed_time": "2:10:43", "remaining_time": "0:25:09"}
+{"current_steps": 318, "total_steps": 378, "loss": 0.5383, "lr": 7.489143213519301e-07, "epoch": 2.515789473684211, "percentage": 84.13, "elapsed_time": "2:11:04", "remaining_time": "0:24:43"}
+{"current_steps": 319, "total_steps": 378, "loss": 0.5626, "lr": 7.24775029983345e-07, "epoch": 2.5236842105263158, "percentage": 84.39, "elapsed_time": "2:11:32", "remaining_time": "0:24:19"}
+{"current_steps": 320, "total_steps": 378, "loss": 0.5321, "lr": 7.010007427581378e-07, "epoch": 2.531578947368421, "percentage": 84.66, "elapsed_time": "2:11:55", "remaining_time": "0:23:54"}
+{"current_steps": 321, "total_steps": 378, "loss": 0.5305, "lr": 6.775934894439606e-07, "epoch": 2.5394736842105265, "percentage": 84.92, "elapsed_time": "2:12:19", "remaining_time": "0:23:29"}
+{"current_steps": 322, "total_steps": 378, "loss": 0.5698, "lr": 6.545552684723583e-07, "epoch": 2.5473684210526315, "percentage": 85.19, "elapsed_time": "2:12:45", "remaining_time": "0:23:05"}
+{"current_steps": 323, "total_steps": 378, "loss": 0.5368, "lr": 6.318880467681527e-07, "epoch": 2.555263157894737, "percentage": 85.45, "elapsed_time": "2:13:10", "remaining_time": "0:22:40"}
+{"current_steps": 324, "total_steps": 378, "loss": 0.5099, "lr": 6.095937595815104e-07, "epoch": 2.5631578947368423, "percentage": 85.71, "elapsed_time": "2:13:35", "remaining_time": "0:22:15"}
+{"current_steps": 325, "total_steps": 378, "loss": 0.5048, "lr": 5.876743103227217e-07, "epoch": 2.5710526315789473, "percentage": 85.98, "elapsed_time": "2:14:00", "remaining_time": "0:21:51"}
+{"current_steps": 326, "total_steps": 378, "loss": 0.5433, "lr": 5.661315703996905e-07, "epoch": 2.5789473684210527, "percentage": 86.24, "elapsed_time": "2:14:24", "remaining_time": "0:21:26"}
+{"current_steps": 327, "total_steps": 378, "loss": 0.5684, "lr": 5.449673790581611e-07, "epoch": 2.586842105263158, "percentage": 86.51, "elapsed_time": "2:14:48", "remaining_time": "0:21:01"}
+{"current_steps": 328, "total_steps": 378, "loss": 0.5395, "lr": 5.241835432246888e-07, "epoch": 2.594736842105263, "percentage": 86.77, "elapsed_time": "2:15:11", "remaining_time": "0:20:36"}
+{"current_steps": 329, "total_steps": 378, "loss": 0.5369, "lr": 5.037818373523723e-07, "epoch": 2.6026315789473684, "percentage": 87.04, "elapsed_time": "2:15:39", "remaining_time": "0:20:12"}
+{"current_steps": 330, "total_steps": 378, "loss": 0.5295, "lr": 4.837640032693558e-07, "epoch": 2.610526315789474, "percentage": 87.3, "elapsed_time": "2:16:09", "remaining_time": "0:19:48"}
+{"current_steps": 331, "total_steps": 378, "loss": 0.5354, "lr": 4.641317500301173e-07, "epoch": 2.6184210526315788, "percentage": 87.57, "elapsed_time": "2:16:34", "remaining_time": "0:19:23"}
+{"current_steps": 332, "total_steps": 378, "loss": 0.563, "lr": 4.448867537695578e-07, "epoch": 2.626315789473684, "percentage": 87.83, "elapsed_time": "2:16:55", "remaining_time": "0:18:58"}
+{"current_steps": 333, "total_steps": 378, "loss": 0.5453, "lr": 4.2603065755989493e-07, "epoch": 2.6342105263157896, "percentage": 88.1, "elapsed_time": "2:17:20", "remaining_time": "0:18:33"}
+{"current_steps": 334, "total_steps": 378, "loss": 0.5348, "lr": 4.0756507127038494e-07, "epoch": 2.6421052631578945, "percentage": 88.36, "elapsed_time": "2:17:41", "remaining_time": "0:18:08"}
+{"current_steps": 335, "total_steps": 378, "loss": 0.5247, "lr": 3.894915714298775e-07, "epoch": 2.65, "percentage": 88.62, "elapsed_time": "2:18:05", "remaining_time": "0:17:43"}
+{"current_steps": 336, "total_steps": 378, "loss": 0.5541, "lr": 3.71811701092219e-07, "epoch": 2.6578947368421053, "percentage": 88.89, "elapsed_time": "2:18:30", "remaining_time": "0:17:18"}
+{"current_steps": 337, "total_steps": 378, "loss": 0.5609, "lr": 3.5452696970450674e-07, "epoch": 2.6657894736842103, "percentage": 89.15, "elapsed_time": "2:18:56", "remaining_time": "0:16:54"}
+{"current_steps": 338, "total_steps": 378, "loss": 0.5143, "lr": 3.3763885297822153e-07, "epoch": 2.6736842105263157, "percentage": 89.42, "elapsed_time": "2:19:17", "remaining_time": "0:16:29"}
+{"current_steps": 339, "total_steps": 378, "loss": 0.5422, "lr": 3.2114879276323783e-07, "epoch": 2.681578947368421, "percentage": 89.68, "elapsed_time": "2:19:42", "remaining_time": "0:16:04"}
+{"current_steps": 340, "total_steps": 378, "loss": 0.5403, "lr": 3.0505819692471797e-07, "epoch": 2.6894736842105265, "percentage": 89.95, "elapsed_time": "2:20:08", "remaining_time": "0:15:39"}
+{"current_steps": 341, "total_steps": 378, "loss": 0.5299, "lr": 2.893684392229185e-07, "epoch": 2.6973684210526314, "percentage": 90.21, "elapsed_time": "2:20:35", "remaining_time": "0:15:15"}
+{"current_steps": 342, "total_steps": 378, "loss": 0.5385, "lr": 2.7408085919590265e-07, "epoch": 2.705263157894737, "percentage": 90.48, "elapsed_time": "2:21:05", "remaining_time": "0:14:51"}
+{"current_steps": 343, "total_steps": 378, "loss": 0.5522, "lr": 2.5919676204517073e-07, "epoch": 2.713157894736842, "percentage": 90.74, "elapsed_time": "2:21:28", "remaining_time": "0:14:26"}
+{"current_steps": 344, "total_steps": 378, "loss": 0.5499, "lr": 2.447174185242324e-07, "epoch": 2.7210526315789476, "percentage": 91.01, "elapsed_time": "2:21:49", "remaining_time": "0:14:01"}
+{"current_steps": 345, "total_steps": 378, "loss": 0.539, "lr": 2.3064406483010947e-07, "epoch": 2.7289473684210526, "percentage": 91.27, "elapsed_time": "2:22:12", "remaining_time": "0:13:36"}
+{"current_steps": 346, "total_steps": 378, "loss": 0.5388, "lr": 2.1697790249779638e-07, "epoch": 2.736842105263158, "percentage": 91.53, "elapsed_time": "2:22:39", "remaining_time": "0:13:11"}
+{"current_steps": 347, "total_steps": 378, "loss": 0.5378, "lr": 2.0372009829767558e-07, "epoch": 2.7447368421052634, "percentage": 91.8, "elapsed_time": "2:23:05", "remaining_time": "0:12:47"}
+{"current_steps": 348, "total_steps": 378, "loss": 0.5362, "lr": 1.908717841359048e-07, "epoch": 2.7526315789473683, "percentage": 92.06, "elapsed_time": "2:23:27", "remaining_time": "0:12:22"}
+{"current_steps": 349, "total_steps": 378, "loss": 0.54, "lr": 1.7843405695777582e-07, "epoch": 2.7605263157894737, "percentage": 92.33, "elapsed_time": "2:23:52", "remaining_time": "0:11:57"}
+{"current_steps": 350, "total_steps": 378, "loss": 0.5466, "lr": 1.664079786540629e-07, "epoch": 2.768421052631579, "percentage": 92.59, "elapsed_time": "2:24:14", "remaining_time": "0:11:32"}
+{"current_steps": 351, "total_steps": 378, "loss": 0.5468, "lr": 1.547945759703623e-07, "epoch": 2.776315789473684, "percentage": 92.86, "elapsed_time": "2:24:40", "remaining_time": "0:11:07"}
+{"current_steps": 352, "total_steps": 378, "loss": 0.5359, "lr": 1.435948404194304e-07, "epoch": 2.7842105263157895, "percentage": 93.12, "elapsed_time": "2:24:59", "remaining_time": "0:10:42"}
+{"current_steps": 353, "total_steps": 378, "loss": 0.5218, "lr": 1.328097281965357e-07, "epoch": 2.792105263157895, "percentage": 93.39, "elapsed_time": "2:25:21", "remaining_time": "0:10:17"}
+{"current_steps": 354, "total_steps": 378, "loss": 0.5318, "lr": 1.22440160097817e-07, "epoch": 2.8, "percentage": 93.65, "elapsed_time": "2:25:43", "remaining_time": "0:09:52"}
+{"current_steps": 355, "total_steps": 378, "loss": 0.5175, "lr": 1.1248702144167123e-07, "epoch": 2.807894736842105, "percentage": 93.92, "elapsed_time": "2:26:11", "remaining_time": "0:09:28"}
+{"current_steps": 356, "total_steps": 378, "loss": 0.5459, "lr": 1.0295116199317057e-07, "epoch": 2.8157894736842106, "percentage": 94.18, "elapsed_time": "2:26:38", "remaining_time": "0:09:03"}
+{"current_steps": 357, "total_steps": 378, "loss": 0.5221, "lr": 9.383339589150776e-08, "epoch": 2.8236842105263156, "percentage": 94.44, "elapsed_time": "2:26:59", "remaining_time": "0:08:38"}
+{"current_steps": 358, "total_steps": 378, "loss": 0.5192, "lr": 8.513450158049109e-08, "epoch": 2.831578947368421, "percentage": 94.71, "elapsed_time": "2:27:32", "remaining_time": "0:08:14"}
+{"current_steps": 359, "total_steps": 378, "loss": 0.5347, "lr": 7.685522174208205e-08, "epoch": 2.8394736842105264, "percentage": 94.97, "elapsed_time": "2:27:53", "remaining_time": "0:07:49"}
+{"current_steps": 360, "total_steps": 378, "loss": 0.5286, "lr": 6.899626323298714e-08, "epoch": 2.8473684210526313, "percentage": 95.24, "elapsed_time": "2:28:14", "remaining_time": "0:07:24"}
+{"current_steps": 361, "total_steps": 378, "loss": 0.5202, "lr": 6.15582970243117e-08, "epoch": 2.8552631578947367, "percentage": 95.5, "elapsed_time": "2:28:41", "remaining_time": "0:07:00"}
+{"current_steps": 362, "total_steps": 378, "loss": 0.5044, "lr": 5.454195814427021e-08, "epoch": 2.863157894736842, "percentage": 95.77, "elapsed_time": "2:29:04", "remaining_time": "0:06:35"}
+{"current_steps": 363, "total_steps": 378, "loss": 0.535, "lr": 4.794784562397459e-08, "epoch": 2.8710526315789475, "percentage": 96.03, "elapsed_time": "2:29:28", "remaining_time": "0:06:10"}
+{"current_steps": 364, "total_steps": 378, "loss": 0.5383, "lr": 4.177652244628627e-08, "epoch": 2.8789473684210525, "percentage": 96.3, "elapsed_time": "2:29:52", "remaining_time": "0:05:45"}
+{"current_steps": 365, "total_steps": 378, "loss": 0.5396, "lr": 3.602851549775521e-08, "epoch": 2.886842105263158, "percentage": 96.56, "elapsed_time": "2:30:16", "remaining_time": "0:05:21"}
+{"current_steps": 366, "total_steps": 378, "loss": 0.5389, "lr": 3.0704315523631956e-08, "epoch": 2.8947368421052633, "percentage": 96.83, "elapsed_time": "2:30:45", "remaining_time": "0:04:56"}
+{"current_steps": 367, "total_steps": 378, "loss": 0.5565, "lr": 2.5804377085972278e-08, "epoch": 2.9026315789473687, "percentage": 97.09, "elapsed_time": "2:31:10", "remaining_time": "0:04:31"}
+{"current_steps": 368, "total_steps": 378, "loss": 0.522, "lr": 2.1329118524827662e-08, "epoch": 2.9105263157894736, "percentage": 97.35, "elapsed_time": "2:31:34", "remaining_time": "0:04:07"}
+{"current_steps": 369, "total_steps": 378, "loss": 0.5146, "lr": 1.7278921922527224e-08, "epoch": 2.918421052631579, "percentage": 97.62, "elapsed_time": "2:31:55", "remaining_time": "0:03:42"}
+{"current_steps": 370, "total_steps": 378, "loss": 0.5414, "lr": 1.3654133071059894e-08, "epoch": 2.9263157894736844, "percentage": 97.88, "elapsed_time": "2:32:23", "remaining_time": "0:03:17"}
+{"current_steps": 371, "total_steps": 378, "loss": 0.5294, "lr": 1.0455061442548597e-08, "epoch": 2.9342105263157894, "percentage": 98.15, "elapsed_time": "2:32:48", "remaining_time": "0:02:52"}
+{"current_steps": 372, "total_steps": 378, "loss": 0.5533, "lr": 7.681980162830283e-09, "epoch": 2.942105263157895, "percentage": 98.41, "elapsed_time": "2:33:06", "remaining_time": "0:02:28"}
+{"current_steps": 373, "total_steps": 378, "loss": 0.5315, "lr": 5.3351259881379016e-09, "epoch": 2.95, "percentage": 98.68, "elapsed_time": "2:33:33", "remaining_time": "0:02:03"}
+{"current_steps": 374, "total_steps": 378, "loss": 0.5376, "lr": 3.41469928488547e-09, "epoch": 2.957894736842105, "percentage": 98.94, "elapsed_time": "2:34:00", "remaining_time": "0:01:38"}
+{"current_steps": 375, "total_steps": 378, "loss": 0.5484, "lr": 1.9208640125628618e-09, "epoch": 2.9657894736842105, "percentage": 99.21, "elapsed_time": "2:34:28", "remaining_time": "0:01:14"}
+{"current_steps": 376, "total_steps": 378, "loss": 0.5329, "lr": 8.537477097364522e-10, "epoch": 2.973684210526316, "percentage": 99.47, "elapsed_time": "2:34:54", "remaining_time": "0:00:49"}
+{"current_steps": 377, "total_steps": 378, "loss": 0.5301, "lr": 2.1344148316060352e-10, "epoch": 2.981578947368421, "percentage": 99.74, "elapsed_time": "2:35:24", "remaining_time": "0:00:24"}
+{"current_steps": 378, "total_steps": 378, "loss": 0.5492, "lr": 0.0, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "2:35:52", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "2:36:50", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "0:00:01", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 378, "total_steps": 378, "epoch": 2.9894736842105263, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2688 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9894736842105263,
+  "eval_steps": 500,
+  "global_step": 378,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007894736842105263,
+      "grad_norm": 7.0740203857421875,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 1.1186,
+      "step": 1
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 7.031124114990234,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 1.1281,
+      "step": 2
+    },
+    {
+      "epoch": 0.02368421052631579,
+      "grad_norm": 6.89492654800415,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 1.1185,
+      "step": 3
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": 7.015303134918213,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 1.129,
+      "step": 4
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 6.810600757598877,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 1.103,
+      "step": 5
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 6.700727462768555,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 1.129,
+      "step": 6
+    },
+    {
+      "epoch": 0.05526315789473684,
+      "grad_norm": 5.1340131759643555,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 1.0762,
+      "step": 7
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 4.850973606109619,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.0529,
+      "step": 8
+    },
+    {
+      "epoch": 0.07105263157894737,
+      "grad_norm": 4.519778728485107,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 1.0531,
+      "step": 9
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 2.700388193130493,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.9795,
+      "step": 10
+    },
+    {
+      "epoch": 0.0868421052631579,
+      "grad_norm": 2.6331188678741455,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 1.0095,
+      "step": 11
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "grad_norm": 2.4724442958831787,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.9728,
+      "step": 12
+    },
+    {
+      "epoch": 0.10263157894736842,
+      "grad_norm": 3.1326963901519775,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.9307,
+      "step": 13
+    },
+    {
+      "epoch": 0.11052631578947368,
+      "grad_norm": 3.435920476913452,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.9612,
+      "step": 14
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 3.3896520137786865,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.9617,
+      "step": 15
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 2.802786111831665,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.9333,
+      "step": 16
+    },
+    {
+      "epoch": 0.13421052631578947,
+      "grad_norm": 1.9803308248519897,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.9159,
+      "step": 17
+    },
+    {
+      "epoch": 0.14210526315789473,
+      "grad_norm": 2.1656057834625244,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.8997,
+      "step": 18
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.4422030448913574,
+      "learning_rate": 5e-06,
+      "loss": 0.9104,
+      "step": 19
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 2.1623854637145996,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.8804,
+      "step": 20
+    },
+    {
+      "epoch": 0.16578947368421051,
+      "grad_norm": 1.7336848974227905,
+      "learning_rate": 5.526315789473685e-06,
+      "loss": 0.8454,
+      "step": 21
+    },
+    {
+      "epoch": 0.1736842105263158,
+      "grad_norm": 1.314452886581421,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 0.8531,
+      "step": 22
+    },
+    {
+      "epoch": 0.18157894736842106,
+      "grad_norm": 1.3969931602478027,
+      "learning_rate": 6.0526315789473685e-06,
+      "loss": 0.8296,
+      "step": 23
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 1.5788418054580688,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 0.828,
+      "step": 24
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 1.5884418487548828,
+      "learning_rate": 6.578947368421054e-06,
+      "loss": 0.8286,
+      "step": 25
+    },
+    {
+      "epoch": 0.20526315789473684,
+      "grad_norm": 1.1489850282669067,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.8069,
+      "step": 26
+    },
+    {
+      "epoch": 0.2131578947368421,
+      "grad_norm": 1.0133432149887085,
+      "learning_rate": 7.1052631578947375e-06,
+      "loss": 0.8102,
+      "step": 27
+    },
+    {
+      "epoch": 0.22105263157894736,
+      "grad_norm": 0.9435691237449646,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 0.7892,
+      "step": 28
+    },
+    {
+      "epoch": 0.22894736842105262,
+      "grad_norm": 1.0618520975112915,
+      "learning_rate": 7.631578947368423e-06,
+      "loss": 0.7961,
+      "step": 29
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.953088641166687,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 0.8092,
+      "step": 30
+    },
+    {
+      "epoch": 0.24473684210526317,
+      "grad_norm": 0.843917727470398,
+      "learning_rate": 8.157894736842106e-06,
+      "loss": 0.7846,
+      "step": 31
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.8666284680366516,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.7538,
+      "step": 32
+    },
+    {
+      "epoch": 0.26052631578947366,
+      "grad_norm": 0.8682100176811218,
+      "learning_rate": 8.68421052631579e-06,
+      "loss": 0.7802,
+      "step": 33
+    },
+    {
+      "epoch": 0.26842105263157895,
+      "grad_norm": 0.7664394974708557,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 0.7718,
+      "step": 34
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 0.7890555262565613,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.7826,
+      "step": 35
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "grad_norm": 0.8435359001159668,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 0.7763,
+      "step": 36
+    },
+    {
+      "epoch": 0.29210526315789476,
+      "grad_norm": 0.8021636605262756,
+      "learning_rate": 9.736842105263159e-06,
+      "loss": 0.7564,
+      "step": 37
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8132019639015198,
+      "learning_rate": 1e-05,
+      "loss": 0.7508,
+      "step": 38
+    },
+    {
+      "epoch": 0.3078947368421053,
+      "grad_norm": 0.7610636949539185,
+      "learning_rate": 9.99978655851684e-06,
+      "loss": 0.7492,
+      "step": 39
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.8269503712654114,
+      "learning_rate": 9.999146252290264e-06,
+      "loss": 0.7627,
+      "step": 40
+    },
+    {
+      "epoch": 0.3236842105263158,
+      "grad_norm": 0.7848504781723022,
+      "learning_rate": 9.998079135987437e-06,
+      "loss": 0.739,
+      "step": 41
+    },
+    {
+      "epoch": 0.33157894736842103,
+      "grad_norm": 0.7971328496932983,
+      "learning_rate": 9.996585300715117e-06,
+      "loss": 0.7372,
+      "step": 42
+    },
+    {
+      "epoch": 0.3394736842105263,
+      "grad_norm": 0.7159483432769775,
+      "learning_rate": 9.994664874011864e-06,
+      "loss": 0.7537,
+      "step": 43
+    },
+    {
+      "epoch": 0.3473684210526316,
+      "grad_norm": 0.7174955606460571,
+      "learning_rate": 9.992318019837171e-06,
+      "loss": 0.7485,
+      "step": 44
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 0.8257307410240173,
+      "learning_rate": 9.989544938557453e-06,
+      "loss": 0.7487,
+      "step": 45
+    },
+    {
+      "epoch": 0.3631578947368421,
+      "grad_norm": 0.7395874857902527,
+      "learning_rate": 9.98634586692894e-06,
+      "loss": 0.7465,
+      "step": 46
+    },
+    {
+      "epoch": 0.37105263157894736,
+      "grad_norm": 0.8656660914421082,
+      "learning_rate": 9.982721078077474e-06,
+      "loss": 0.7471,
+      "step": 47
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.6341963410377502,
+      "learning_rate": 9.978670881475173e-06,
+      "loss": 0.7643,
+      "step": 48
+    },
+    {
+      "epoch": 0.3868421052631579,
+      "grad_norm": 0.8313978910446167,
+      "learning_rate": 9.97419562291403e-06,
+      "loss": 0.7386,
+      "step": 49
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.93310546875,
+      "learning_rate": 9.96929568447637e-06,
+      "loss": 0.754,
+      "step": 50
+    },
+    {
+      "epoch": 0.4026315789473684,
+      "grad_norm": 0.7993932962417603,
+      "learning_rate": 9.963971484502247e-06,
+      "loss": 0.731,
+      "step": 51
+    },
+    {
+      "epoch": 0.4105263157894737,
+      "grad_norm": 0.7355050444602966,
+      "learning_rate": 9.958223477553715e-06,
+      "loss": 0.7542,
+      "step": 52
+    },
+    {
+      "epoch": 0.41842105263157897,
+      "grad_norm": 0.7957926392555237,
+      "learning_rate": 9.952052154376027e-06,
+      "loss": 0.7626,
+      "step": 53
+    },
+    {
+      "epoch": 0.4263157894736842,
+      "grad_norm": 0.9310785531997681,
+      "learning_rate": 9.945458041855732e-06,
+      "loss": 0.7303,
+      "step": 54
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 0.8477827906608582,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.7143,
+      "step": 55
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 0.654358446598053,
+      "learning_rate": 9.931003736767013e-06,
+      "loss": 0.7097,
+      "step": 56
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8673765063285828,
+      "learning_rate": 9.923144778257918e-06,
+      "loss": 0.7253,
+      "step": 57
+    },
+    {
+      "epoch": 0.45789473684210524,
+      "grad_norm": 0.7678876519203186,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.7212,
+      "step": 58
+    },
+    {
+      "epoch": 0.46578947368421053,
+      "grad_norm": 0.7339031100273132,
+      "learning_rate": 9.906166604108494e-06,
+      "loss": 0.7254,
+      "step": 59
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.7133976221084595,
+      "learning_rate": 9.89704883800683e-06,
+      "loss": 0.7306,
+      "step": 60
+    },
+    {
+      "epoch": 0.48157894736842105,
+      "grad_norm": 0.8026192784309387,
+      "learning_rate": 9.887512978558329e-06,
+      "loss": 0.7245,
+      "step": 61
+    },
+    {
+      "epoch": 0.48947368421052634,
+      "grad_norm": 0.659774899482727,
+      "learning_rate": 9.877559839902185e-06,
+      "loss": 0.7239,
+      "step": 62
+    },
+    {
+      "epoch": 0.49736842105263157,
+      "grad_norm": 0.6718412637710571,
+      "learning_rate": 9.867190271803466e-06,
+      "loss": 0.6966,
+      "step": 63
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.782952070236206,
+      "learning_rate": 9.85640515958057e-06,
+      "loss": 0.7246,
+      "step": 64
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.749127984046936,
+      "learning_rate": 9.845205424029639e-06,
+      "loss": 0.7121,
+      "step": 65
+    },
+    {
+      "epoch": 0.5210526315789473,
+      "grad_norm": 0.773841917514801,
+      "learning_rate": 9.833592021345938e-06,
+      "loss": 0.7341,
+      "step": 66
+    },
+    {
+      "epoch": 0.5289473684210526,
+      "grad_norm": 0.7773014903068542,
+      "learning_rate": 9.821565943042225e-06,
+      "loss": 0.707,
+      "step": 67
+    },
+    {
+      "epoch": 0.5368421052631579,
+      "grad_norm": 0.748015820980072,
+      "learning_rate": 9.809128215864096e-06,
+      "loss": 0.7118,
+      "step": 68
+    },
+    {
+      "epoch": 0.5447368421052632,
+      "grad_norm": 0.6848940849304199,
+      "learning_rate": 9.796279901702326e-06,
+      "loss": 0.6977,
+      "step": 69
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.8350101709365845,
+      "learning_rate": 9.783022097502204e-06,
+      "loss": 0.7213,
+      "step": 70
+    },
+    {
+      "epoch": 0.5605263157894737,
+      "grad_norm": 0.7320327758789062,
+      "learning_rate": 9.76935593516989e-06,
+      "loss": 0.7079,
+      "step": 71
+    },
+    {
+      "epoch": 0.5684210526315789,
+      "grad_norm": 0.7068721055984497,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.7304,
+      "step": 72
+    },
+    {
+      "epoch": 0.5763157894736842,
+      "grad_norm": 0.7000291347503662,
+      "learning_rate": 9.74080323795483e-06,
+      "loss": 0.714,
+      "step": 73
+    },
+    {
+      "epoch": 0.5842105263157895,
+      "grad_norm": 0.8786887526512146,
+      "learning_rate": 9.7259191408041e-06,
+      "loss": 0.7155,
+      "step": 74
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.7386007905006409,
+      "learning_rate": 9.710631560777082e-06,
+      "loss": 0.7088,
+      "step": 75
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6937209367752075,
+      "learning_rate": 9.694941803075285e-06,
+      "loss": 0.7058,
+      "step": 76
+    },
+    {
+      "epoch": 0.6078947368421053,
+      "grad_norm": 0.9193783402442932,
+      "learning_rate": 9.678851207236764e-06,
+      "loss": 0.738,
+      "step": 77
+    },
+    {
+      "epoch": 0.6157894736842106,
+      "grad_norm": 0.9059263467788696,
+      "learning_rate": 9.66236114702178e-06,
+      "loss": 0.7116,
+      "step": 78
+    },
+    {
+      "epoch": 0.6236842105263158,
+      "grad_norm": 0.6896800994873047,
+      "learning_rate": 9.645473030295496e-06,
+      "loss": 0.7207,
+      "step": 79
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.8141930103302002,
+      "learning_rate": 9.628188298907782e-06,
+      "loss": 0.7015,
+      "step": 80
+    },
+    {
+      "epoch": 0.6394736842105263,
+      "grad_norm": 0.6706604361534119,
+      "learning_rate": 9.610508428570122e-06,
+      "loss": 0.7204,
+      "step": 81
+    },
+    {
+      "epoch": 0.6473684210526316,
+      "grad_norm": 0.7771408557891846,
+      "learning_rate": 9.592434928729617e-06,
+      "loss": 0.7215,
+      "step": 82
+    },
+    {
+      "epoch": 0.6552631578947369,
+      "grad_norm": 0.6452600955963135,
+      "learning_rate": 9.573969342440107e-06,
+      "loss": 0.7187,
+      "step": 83
+    },
+    {
+      "epoch": 0.6631578947368421,
+      "grad_norm": 0.704627275466919,
+      "learning_rate": 9.555113246230443e-06,
+      "loss": 0.7383,
+      "step": 84
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.675726056098938,
+      "learning_rate": 9.535868249969882e-06,
+      "loss": 0.7006,
+      "step": 85
+    },
+    {
+      "epoch": 0.6789473684210526,
+      "grad_norm": 0.807037353515625,
+      "learning_rate": 9.516235996730645e-06,
+      "loss": 0.7098,
+      "step": 86
+    },
+    {
+      "epoch": 0.6868421052631579,
+      "grad_norm": 0.6850730776786804,
+      "learning_rate": 9.496218162647629e-06,
+      "loss": 0.7095,
+      "step": 87
+    },
+    {
+      "epoch": 0.6947368421052632,
+      "grad_norm": 0.7169205546379089,
+      "learning_rate": 9.475816456775313e-06,
+      "loss": 0.7209,
+      "step": 88
+    },
+    {
+      "epoch": 0.7026315789473684,
+      "grad_norm": 0.8442161083221436,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.7133,
+      "step": 89
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.67853182554245,
+      "learning_rate": 9.43386842960031e-06,
+      "loss": 0.7017,
+      "step": 90
+    },
+    {
+      "epoch": 0.718421052631579,
+      "grad_norm": 0.6674996018409729,
+      "learning_rate": 9.41232568967728e-06,
+      "loss": 0.7039,
+      "step": 91
+    },
+    {
+      "epoch": 0.7263157894736842,
+      "grad_norm": 0.6516873240470886,
+      "learning_rate": 9.39040624041849e-06,
+      "loss": 0.6955,
+      "step": 92
+    },
+    {
+      "epoch": 0.7342105263157894,
+      "grad_norm": 0.6596349477767944,
+      "learning_rate": 9.368111953231849e-06,
+      "loss": 0.6895,
+      "step": 93
+    },
+    {
+      "epoch": 0.7421052631578947,
+      "grad_norm": 0.6478255987167358,
+      "learning_rate": 9.345444731527642e-06,
+      "loss": 0.6935,
+      "step": 94
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6235653758049011,
+      "learning_rate": 9.32240651055604e-06,
+      "loss": 0.6787,
+      "step": 95
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.638984739780426,
+      "learning_rate": 9.298999257241862e-06,
+      "loss": 0.7282,
+      "step": 96
+    },
+    {
+      "epoch": 0.7657894736842106,
+      "grad_norm": 0.710728108882904,
+      "learning_rate": 9.275224970016656e-06,
+      "loss": 0.7166,
+      "step": 97
+    },
+    {
+      "epoch": 0.7736842105263158,
+      "grad_norm": 0.6417115926742554,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 0.6881,
+      "step": 98
+    },
+    {
+      "epoch": 0.781578947368421,
+      "grad_norm": 0.7576119303703308,
+      "learning_rate": 9.22658344406657e-06,
+      "loss": 0.7071,
+      "step": 99
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.8099032640457153,
+      "learning_rate": 9.201720358189464e-06,
+      "loss": 0.708,
+      "step": 100
+    },
+    {
+      "epoch": 0.7973684210526316,
+      "grad_norm": 0.649307131767273,
+      "learning_rate": 9.176498543742328e-06,
+      "loss": 0.696,
+      "step": 101
+    },
+    {
+      "epoch": 0.8052631578947368,
+      "grad_norm": 0.7050330638885498,
+      "learning_rate": 9.150920154077753e-06,
+      "loss": 0.7138,
+      "step": 102
+    },
+    {
+      "epoch": 0.8131578947368421,
+      "grad_norm": 0.6682823896408081,
+      "learning_rate": 9.124987372991512e-06,
+      "loss": 0.6937,
+      "step": 103
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 0.718499481678009,
+      "learning_rate": 9.098702414536107e-06,
+      "loss": 0.7022,
+      "step": 104
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.7294292449951172,
+      "learning_rate": 9.072067522831743e-06,
+      "loss": 0.6789,
+      "step": 105
+    },
+    {
+      "epoch": 0.8368421052631579,
+      "grad_norm": 0.6921276450157166,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7057,
+      "step": 106
+    },
+    {
+      "epoch": 0.8447368421052631,
+      "grad_norm": 0.8754315376281738,
+      "learning_rate": 9.017757065343368e-06,
+      "loss": 0.7262,
+      "step": 107
+    },
+    {
+      "epoch": 0.8526315789473684,
+      "grad_norm": 0.6188150644302368,
+      "learning_rate": 8.990086136401199e-06,
+      "loss": 0.6853,
+      "step": 108
+    },
+    {
+      "epoch": 0.8605263157894737,
+      "grad_norm": 0.7342610955238342,
+      "learning_rate": 8.96207454749787e-06,
+      "loss": 0.7164,
+      "step": 109
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.7715557217597961,
+      "learning_rate": 8.933724690167417e-06,
+      "loss": 0.7058,
+      "step": 110
+    },
+    {
+      "epoch": 0.8763157894736842,
+      "grad_norm": 0.7064869403839111,
+      "learning_rate": 8.905038984824079e-06,
+      "loss": 0.698,
+      "step": 111
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.7494336366653442,
+      "learning_rate": 8.87601988055565e-06,
+      "loss": 0.6961,
+      "step": 112
+    },
+    {
+      "epoch": 0.8921052631578947,
+      "grad_norm": 0.664580762386322,
+      "learning_rate": 8.846669854914395e-06,
+      "loss": 0.7129,
+      "step": 113
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7173993587493896,
+      "learning_rate": 8.816991413705515e-06,
+      "loss": 0.716,
+      "step": 114
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.6451180577278137,
+      "learning_rate": 8.786987090773214e-06,
+      "loss": 0.7034,
+      "step": 115
+    },
+    {
+      "epoch": 0.9157894736842105,
+      "grad_norm": 0.6762385368347168,
+      "learning_rate": 8.756659447784367e-06,
+      "loss": 0.6933,
+      "step": 116
+    },
+    {
+      "epoch": 0.9236842105263158,
+      "grad_norm": 0.688220739364624,
+      "learning_rate": 8.726011074009813e-06,
+      "loss": 0.7154,
+      "step": 117
+    },
+    {
+      "epoch": 0.9315789473684211,
+      "grad_norm": 0.6731222867965698,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 0.6916,
+      "step": 118
+    },
+    {
+      "epoch": 0.9394736842105263,
+      "grad_norm": 0.6552385687828064,
+      "learning_rate": 8.663762627878059e-06,
+      "loss": 0.7074,
+      "step": 119
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.6504393815994263,
+      "learning_rate": 8.632167870081122e-06,
+      "loss": 0.7028,
+      "step": 120
+    },
+    {
+      "epoch": 0.9552631578947368,
+      "grad_norm": 0.7418521046638489,
+      "learning_rate": 8.600263010165275e-06,
+      "loss": 0.6997,
+      "step": 121
+    },
+    {
+      "epoch": 0.9631578947368421,
+      "grad_norm": 0.6728154420852661,
+      "learning_rate": 8.568050772058763e-06,
+      "loss": 0.7066,
+      "step": 122
+    },
+    {
+      "epoch": 0.9710526315789474,
+      "grad_norm": 0.6942195892333984,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.7001,
+      "step": 123
+    },
+    {
+      "epoch": 0.9789473684210527,
+      "grad_norm": 0.6641739010810852,
+      "learning_rate": 8.502715187966455e-06,
+      "loss": 0.702,
+      "step": 124
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.7299260497093201,
+      "learning_rate": 8.469597420110249e-06,
+      "loss": 0.6927,
+      "step": 125
+    },
+    {
+      "epoch": 0.9947368421052631,
+      "grad_norm": 0.6769669055938721,
+      "learning_rate": 8.436183429846314e-06,
+      "loss": 0.6743,
+      "step": 126
+    },
+    {
+      "epoch": 1.0052631578947369,
+      "grad_norm": 0.7567976713180542,
+      "learning_rate": 8.402476069947309e-06,
+      "loss": 0.6556,
+      "step": 127
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.7088767290115356,
+      "learning_rate": 8.368478218232787e-06,
+      "loss": 0.6348,
+      "step": 128
+    },
+    {
+      "epoch": 1.0210526315789474,
+      "grad_norm": 0.6701803207397461,
+      "learning_rate": 8.334192777323508e-06,
+      "loss": 0.63,
+      "step": 129
+    },
+    {
+      "epoch": 1.0289473684210526,
+      "grad_norm": 0.7436509132385254,
+      "learning_rate": 8.299622674393615e-06,
+      "loss": 0.621,
+      "step": 130
+    },
+    {
+      "epoch": 1.0368421052631578,
+      "grad_norm": 0.6837674379348755,
+      "learning_rate": 8.264770860920722e-06,
+      "loss": 0.6294,
+      "step": 131
+    },
+    {
+      "epoch": 1.0447368421052632,
+      "grad_norm": 0.6941933035850525,
+      "learning_rate": 8.229640312433938e-06,
+      "loss": 0.6003,
+      "step": 132
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.6441699266433716,
+      "learning_rate": 8.194234028259806e-06,
+      "loss": 0.6044,
+      "step": 133
+    },
+    {
+      "epoch": 1.0605263157894738,
+      "grad_norm": 0.6503862142562866,
+      "learning_rate": 8.158555031266255e-06,
+      "loss": 0.6059,
+      "step": 134
+    },
+    {
+      "epoch": 1.068421052631579,
+      "grad_norm": 0.6873996257781982,
+      "learning_rate": 8.122606367604497e-06,
+      "loss": 0.5948,
+      "step": 135
+    },
+    {
+      "epoch": 1.0763157894736841,
+      "grad_norm": 0.6901219487190247,
+      "learning_rate": 8.086391106448965e-06,
+      "loss": 0.617,
+      "step": 136
+    },
+    {
+      "epoch": 1.0842105263157895,
+      "grad_norm": 0.5913821458816528,
+      "learning_rate": 8.049912339735284e-06,
+      "loss": 0.6205,
+      "step": 137
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.6473250389099121,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.5898,
+      "step": 138
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.6466673016548157,
+      "learning_rate": 7.976176769596095e-06,
+      "loss": 0.6283,
+      "step": 139
+    },
+    {
+      "epoch": 1.1078947368421053,
+      "grad_norm": 0.562574565410614,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.5947,
+      "step": 140
+    },
+    {
+      "epoch": 1.1157894736842104,
+      "grad_norm": 0.6042968034744263,
+      "learning_rate": 7.90142483781658e-06,
+      "loss": 0.6338,
+      "step": 141
+    },
+    {
+      "epoch": 1.1236842105263158,
+      "grad_norm": 0.6527702808380127,
+      "learning_rate": 7.863675700402527e-06,
+      "loss": 0.6113,
+      "step": 142
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.5683473944664001,
+      "learning_rate": 7.82568207211296e-06,
+      "loss": 0.6254,
+      "step": 143
+    },
+    {
+      "epoch": 1.1394736842105262,
+      "grad_norm": 0.6214303374290466,
+      "learning_rate": 7.787447196714428e-06,
+      "loss": 0.6213,
+      "step": 144
+    },
+    {
+      "epoch": 1.1473684210526316,
+      "grad_norm": 0.5913365483283997,
+      "learning_rate": 7.748974338570337e-06,
+      "loss": 0.6221,
+      "step": 145
+    },
+    {
+      "epoch": 1.1552631578947368,
+      "grad_norm": 0.6266749501228333,
+      "learning_rate": 7.710266782362248e-06,
+      "loss": 0.5909,
+      "step": 146
+    },
+    {
+      "epoch": 1.1631578947368422,
+      "grad_norm": 0.6693281531333923,
+      "learning_rate": 7.671327832809442e-06,
+      "loss": 0.6373,
+      "step": 147
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.6370000839233398,
+      "learning_rate": 7.63216081438678e-06,
+      "loss": 0.5908,
+      "step": 148
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 0.6319229602813721,
+      "learning_rate": 7.5927690710408606e-06,
+      "loss": 0.6138,
+      "step": 149
+    },
+    {
+      "epoch": 1.186842105263158,
+      "grad_norm": 0.6503207683563232,
+      "learning_rate": 7.553155965904535e-06,
+      "loss": 0.6165,
+      "step": 150
+    },
+    {
+      "epoch": 1.194736842105263,
+      "grad_norm": 0.6979773640632629,
+      "learning_rate": 7.513324881009769e-06,
+      "loss": 0.6308,
+      "step": 151
+    },
+    {
+      "epoch": 1.2026315789473685,
+      "grad_norm": 0.591997504234314,
+      "learning_rate": 7.473279216998896e-06,
+      "loss": 0.6227,
+      "step": 152
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.6470649242401123,
+      "learning_rate": 7.4330223928342814e-06,
+      "loss": 0.6248,
+      "step": 153
+    },
+    {
+      "epoch": 1.2184210526315788,
+      "grad_norm": 0.6023352742195129,
+      "learning_rate": 7.392557845506433e-06,
+      "loss": 0.6043,
+      "step": 154
+    },
+    {
+      "epoch": 1.2263157894736842,
+      "grad_norm": 0.6112087368965149,
+      "learning_rate": 7.351889029740548e-06,
+      "loss": 0.6122,
+      "step": 155
+    },
+    {
+      "epoch": 1.2342105263157894,
+      "grad_norm": 0.737591028213501,
+      "learning_rate": 7.311019417701567e-06,
+      "loss": 0.6091,
+      "step": 156
+    },
+    {
+      "epoch": 1.2421052631578948,
+      "grad_norm": 0.6064261198043823,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.6092,
+      "step": 157
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6505361199378967,
+      "learning_rate": 7.2286917788826926e-06,
+      "loss": 0.6164,
+      "step": 158
+    },
+    {
+      "epoch": 1.2578947368421054,
+      "grad_norm": 0.6192215085029602,
+      "learning_rate": 7.187240780956133e-06,
+      "loss": 0.6028,
+      "step": 159
+    },
+    {
+      "epoch": 1.2657894736842106,
+      "grad_norm": 0.6353914141654968,
+      "learning_rate": 7.145603043863045e-06,
+      "loss": 0.6052,
+      "step": 160
+    },
+    {
+      "epoch": 1.2736842105263158,
+      "grad_norm": 0.634981632232666,
+      "learning_rate": 7.103782122491577e-06,
+      "loss": 0.6188,
+      "step": 161
+    },
+    {
+      "epoch": 1.2815789473684212,
+      "grad_norm": 0.6064332127571106,
+      "learning_rate": 7.061781587369518e-06,
+      "loss": 0.6288,
+      "step": 162
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.5805593729019165,
+      "learning_rate": 7.019605024359475e-06,
+      "loss": 0.6037,
+      "step": 163
+    },
+    {
+      "epoch": 1.2973684210526315,
+      "grad_norm": 0.7273927927017212,
+      "learning_rate": 6.977256034352713e-06,
+      "loss": 0.6268,
+      "step": 164
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 0.6278533339500427,
+      "learning_rate": 6.934738232961728e-06,
+      "loss": 0.6283,
+      "step": 165
+    },
+    {
+      "epoch": 1.313157894736842,
+      "grad_norm": 0.6402047872543335,
+      "learning_rate": 6.892055250211552e-06,
+      "loss": 0.6157,
+      "step": 166
+    },
+    {
+      "epoch": 1.3210526315789473,
+      "grad_norm": 0.6458708047866821,
+      "learning_rate": 6.849210730229846e-06,
+      "loss": 0.6187,
+      "step": 167
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.5871455073356628,
+      "learning_rate": 6.806208330935766e-06,
+      "loss": 0.6162,
+      "step": 168
+    },
+    {
+      "epoch": 1.3368421052631578,
+      "grad_norm": 0.5851725935935974,
+      "learning_rate": 6.763051723727663e-06,
+      "loss": 0.605,
+      "step": 169
+    },
+    {
+      "epoch": 1.3447368421052632,
+      "grad_norm": 0.607880175113678,
+      "learning_rate": 6.719744593169642e-06,
+      "loss": 0.5954,
+      "step": 170
+    },
+    {
+      "epoch": 1.3526315789473684,
+      "grad_norm": 0.6497223973274231,
+      "learning_rate": 6.67629063667697e-06,
+      "loss": 0.6233,
+      "step": 171
+    },
+    {
+      "epoch": 1.3605263157894738,
+      "grad_norm": 0.6154512166976929,
+      "learning_rate": 6.6326935642004165e-06,
+      "loss": 0.6186,
+      "step": 172
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.6759777665138245,
+      "learning_rate": 6.588957097909509e-06,
+      "loss": 0.6171,
+      "step": 173
+    },
+    {
+      "epoch": 1.3763157894736842,
+      "grad_norm": 0.6606743931770325,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5943,
+      "step": 174
+    },
+    {
+      "epoch": 1.3842105263157896,
+      "grad_norm": 0.6321778297424316,
+      "learning_rate": 6.501080931748764e-06,
+      "loss": 0.6191,
+      "step": 175
+    },
+    {
+      "epoch": 1.3921052631578947,
+      "grad_norm": 0.622314453125,
+      "learning_rate": 6.456948734446624e-06,
+      "loss": 0.6134,
+      "step": 176
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.6384446620941162,
+      "learning_rate": 6.412692147824976e-06,
+      "loss": 0.6005,
+      "step": 177
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.6004672646522522,
+      "learning_rate": 6.368314950360416e-06,
+      "loss": 0.6082,
+      "step": 178
+    },
+    {
+      "epoch": 1.4157894736842105,
+      "grad_norm": 0.6092491745948792,
+      "learning_rate": 6.323820930826879e-06,
+      "loss": 0.6306,
+      "step": 179
+    },
+    {
+      "epoch": 1.4236842105263157,
+      "grad_norm": 0.6291044354438782,
+      "learning_rate": 6.279213887972179e-06,
+      "loss": 0.6188,
+      "step": 180
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 0.5878775119781494,
+      "learning_rate": 6.234497630193666e-06,
+      "loss": 0.6154,
+      "step": 181
+    },
+    {
+      "epoch": 1.4394736842105262,
+      "grad_norm": 0.5391842126846313,
+      "learning_rate": 6.189675975213094e-06,
+      "loss": 0.6105,
+      "step": 182
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.5454199314117432,
+      "learning_rate": 6.144752749750671e-06,
+      "loss": 0.6023,
+      "step": 183
+    },
+    {
+      "epoch": 1.4552631578947368,
+      "grad_norm": 0.6040089130401611,
+      "learning_rate": 6.099731789198344e-06,
+      "loss": 0.6081,
+      "step": 184
+    },
+    {
+      "epoch": 1.4631578947368422,
+      "grad_norm": 0.6564128398895264,
+      "learning_rate": 6.05461693729235e-06,
+      "loss": 0.6115,
+      "step": 185
+    },
+    {
+      "epoch": 1.4710526315789474,
+      "grad_norm": 0.5978277325630188,
+      "learning_rate": 6.009412045785051e-06,
+      "loss": 0.6044,
+      "step": 186
+    },
+    {
+      "epoch": 1.4789473684210526,
+      "grad_norm": 0.6195292472839355,
+      "learning_rate": 5.964120974116085e-06,
+      "loss": 0.6253,
+      "step": 187
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.5672737956047058,
+      "learning_rate": 5.918747589082853e-06,
+      "loss": 0.614,
+      "step": 188
+    },
+    {
+      "epoch": 1.4947368421052631,
+      "grad_norm": 0.5825613737106323,
+      "learning_rate": 5.8732957645103946e-06,
+      "loss": 0.5987,
+      "step": 189
+    },
+    {
+      "epoch": 1.5026315789473683,
+      "grad_norm": 0.5839316844940186,
+      "learning_rate": 5.82776938092065e-06,
+      "loss": 0.6099,
+      "step": 190
+    },
+    {
+      "epoch": 1.5105263157894737,
+      "grad_norm": 0.592494010925293,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.6272,
+      "step": 191
+    },
+    {
+      "epoch": 1.518421052631579,
+      "grad_norm": 0.6230676174163818,
+      "learning_rate": 5.736508490273189e-06,
+      "loss": 0.6132,
+      "step": 192
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.5931450724601746,
+      "learning_rate": 5.690781774759412e-06,
+      "loss": 0.6022,
+      "step": 193
+    },
+    {
+      "epoch": 1.5342105263157895,
+      "grad_norm": 0.6010186076164246,
+      "learning_rate": 5.644996082651018e-06,
+      "loss": 0.6144,
+      "step": 194
+    },
+    {
+      "epoch": 1.5421052631578949,
+      "grad_norm": 0.6734380722045898,
+      "learning_rate": 5.5991553229744166e-06,
+      "loss": 0.6343,
+      "step": 195
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.5894003510475159,
+      "learning_rate": 5.553263409457504e-06,
+      "loss": 0.6165,
+      "step": 196
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 0.5955084562301636,
+      "learning_rate": 5.507324260195516e-06,
+      "loss": 0.611,
+      "step": 197
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.5771483778953552,
+      "learning_rate": 5.46134179731651e-06,
+      "loss": 0.6079,
+      "step": 198
+    },
+    {
+      "epoch": 1.5736842105263158,
+      "grad_norm": 0.6015431880950928,
+      "learning_rate": 5.41531994664652e-06,
+      "loss": 0.5994,
+      "step": 199
+    },
+    {
+      "epoch": 1.581578947368421,
+      "grad_norm": 0.5537875890731812,
+      "learning_rate": 5.36926263737437e-06,
+      "loss": 0.597,
+      "step": 200
+    },
+    {
+      "epoch": 1.5894736842105264,
+      "grad_norm": 0.5928704142570496,
+      "learning_rate": 5.323173801716222e-06,
+      "loss": 0.596,
+      "step": 201
+    },
+    {
+      "epoch": 1.5973684210526315,
+      "grad_norm": 0.6157421469688416,
+      "learning_rate": 5.27705737457985e-06,
+      "loss": 0.6261,
+      "step": 202
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.612349271774292,
+      "learning_rate": 5.230917293228699e-06,
+      "loss": 0.6079,
+      "step": 203
+    },
+    {
+      "epoch": 1.6131578947368421,
+      "grad_norm": 0.54092937707901,
+      "learning_rate": 5.184757496945726e-06,
+      "loss": 0.5942,
+      "step": 204
+    },
+    {
+      "epoch": 1.6210526315789475,
+      "grad_norm": 0.5439791083335876,
+      "learning_rate": 5.138581926697083e-06,
+      "loss": 0.6135,
+      "step": 205
+    },
+    {
+      "epoch": 1.6289473684210525,
+      "grad_norm": 0.5337532758712769,
+      "learning_rate": 5.09239452479565e-06,
+      "loss": 0.587,
+      "step": 206
+    },
+    {
+      "epoch": 1.6368421052631579,
+      "grad_norm": 0.5457773208618164,
+      "learning_rate": 5.046199234564455e-06,
+      "loss": 0.5961,
+      "step": 207
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.5572032332420349,
+      "learning_rate": 5e-06,
+      "loss": 0.6022,
+      "step": 208
+    },
+    {
+      "epoch": 1.6526315789473685,
+      "grad_norm": 0.5409188270568848,
+      "learning_rate": 4.953800765435547e-06,
+      "loss": 0.5966,
+      "step": 209
+    },
+    {
+      "epoch": 1.6605263157894736,
+      "grad_norm": 0.5420222878456116,
+      "learning_rate": 4.907605475204352e-06,
+      "loss": 0.6069,
+      "step": 210
+    },
+    {
+      "epoch": 1.668421052631579,
+      "grad_norm": 0.5424708724021912,
+      "learning_rate": 4.861418073302919e-06,
+      "loss": 0.6009,
+      "step": 211
+    },
+    {
+      "epoch": 1.6763157894736842,
+      "grad_norm": 0.5323647856712341,
+      "learning_rate": 4.815242503054277e-06,
+      "loss": 0.6183,
+      "step": 212
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.5776340961456299,
+      "learning_rate": 4.7690827067713035e-06,
+      "loss": 0.6109,
+      "step": 213
+    },
+    {
+      "epoch": 1.6921052631578948,
+      "grad_norm": 0.5825272798538208,
+      "learning_rate": 4.7229426254201504e-06,
+      "loss": 0.615,
+      "step": 214
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.5867627859115601,
+      "learning_rate": 4.676826198283779e-06,
+      "loss": 0.6114,
+      "step": 215
+    },
+    {
+      "epoch": 1.7078947368421051,
+      "grad_norm": 0.5459916591644287,
+      "learning_rate": 4.630737362625631e-06,
+      "loss": 0.6039,
+      "step": 216
+    },
+    {
+      "epoch": 1.7157894736842105,
+      "grad_norm": 0.5879709124565125,
+      "learning_rate": 4.584680053353481e-06,
+      "loss": 0.6154,
+      "step": 217
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.5895808339118958,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 0.6133,
+      "step": 218
+    },
+    {
+      "epoch": 1.731578947368421,
+      "grad_norm": 0.6173647046089172,
+      "learning_rate": 4.492675739804486e-06,
+      "loss": 0.6018,
+      "step": 219
+    },
+    {
+      "epoch": 1.7394736842105263,
+      "grad_norm": 0.5456452965736389,
+      "learning_rate": 4.446736590542497e-06,
+      "loss": 0.6083,
+      "step": 220
+    },
+    {
+      "epoch": 1.7473684210526317,
+      "grad_norm": 0.5733683705329895,
+      "learning_rate": 4.400844677025585e-06,
+      "loss": 0.6015,
+      "step": 221
+    },
+    {
+      "epoch": 1.7552631578947369,
+      "grad_norm": 0.5852586627006531,
+      "learning_rate": 4.355003917348985e-06,
+      "loss": 0.5983,
+      "step": 222
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.5621438026428223,
+      "learning_rate": 4.309218225240591e-06,
+      "loss": 0.5891,
+      "step": 223
+    },
+    {
+      "epoch": 1.7710526315789474,
+      "grad_norm": 0.582830011844635,
+      "learning_rate": 4.263491509726812e-06,
+      "loss": 0.5864,
+      "step": 224
+    },
+    {
+      "epoch": 1.7789473684210526,
+      "grad_norm": 0.5376387238502502,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.6084,
+      "step": 225
+    },
+    {
+      "epoch": 1.7868421052631578,
+      "grad_norm": 0.6110755801200867,
+      "learning_rate": 4.17223061907935e-06,
+      "loss": 0.6055,
+      "step": 226
+    },
+    {
+      "epoch": 1.7947368421052632,
+      "grad_norm": 0.5580980777740479,
+      "learning_rate": 4.126704235489606e-06,
+      "loss": 0.616,
+      "step": 227
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.6138029098510742,
+      "learning_rate": 4.081252410917148e-06,
+      "loss": 0.6088,
+      "step": 228
+    },
+    {
+      "epoch": 1.8105263157894735,
+      "grad_norm": 0.5521398186683655,
+      "learning_rate": 4.035879025883916e-06,
+      "loss": 0.6146,
+      "step": 229
+    },
+    {
+      "epoch": 1.818421052631579,
+      "grad_norm": 0.5325535535812378,
+      "learning_rate": 3.99058795421495e-06,
+      "loss": 0.5895,
+      "step": 230
+    },
+    {
+      "epoch": 1.8263157894736843,
+      "grad_norm": 0.6027734875679016,
+      "learning_rate": 3.945383062707652e-06,
+      "loss": 0.5979,
+      "step": 231
+    },
+    {
+      "epoch": 1.8342105263157895,
+      "grad_norm": 0.5285260677337646,
+      "learning_rate": 3.9002682108016585e-06,
+      "loss": 0.6119,
+      "step": 232
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.5392246246337891,
+      "learning_rate": 3.855247250249331e-06,
+      "loss": 0.6104,
+      "step": 233
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.5578750967979431,
+      "learning_rate": 3.8103240247869077e-06,
+      "loss": 0.606,
+      "step": 234
+    },
+    {
+      "epoch": 1.8578947368421053,
+      "grad_norm": 0.5479610562324524,
+      "learning_rate": 3.765502369806334e-06,
+      "loss": 0.6147,
+      "step": 235
+    },
+    {
+      "epoch": 1.8657894736842104,
+      "grad_norm": 0.5477908253669739,
+      "learning_rate": 3.720786112027822e-06,
+      "loss": 0.5947,
+      "step": 236
+    },
+    {
+      "epoch": 1.8736842105263158,
+      "grad_norm": 0.5339275598526001,
+      "learning_rate": 3.6761790691731207e-06,
+      "loss": 0.5975,
+      "step": 237
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.5823328495025635,
+      "learning_rate": 3.6316850496395863e-06,
+      "loss": 0.5898,
+      "step": 238
+    },
+    {
+      "epoch": 1.8894736842105262,
+      "grad_norm": 0.5550434589385986,
+      "learning_rate": 3.587307852175025e-06,
+      "loss": 0.5953,
+      "step": 239
+    },
+    {
+      "epoch": 1.8973684210526316,
+      "grad_norm": 0.5742660164833069,
+      "learning_rate": 3.5430512655533774e-06,
+      "loss": 0.6185,
+      "step": 240
+    },
+    {
+      "epoch": 1.905263157894737,
+      "grad_norm": 0.5972154140472412,
+      "learning_rate": 3.498919068251237e-06,
+      "loss": 0.5985,
+      "step": 241
+    },
+    {
+      "epoch": 1.913157894736842,
+      "grad_norm": 0.5590418577194214,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6052,
+      "step": 242
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.58773273229599,
+      "learning_rate": 3.4110429020904924e-06,
+      "loss": 0.6158,
+      "step": 243
+    },
+    {
+      "epoch": 1.9289473684210527,
+      "grad_norm": 0.5843963027000427,
+      "learning_rate": 3.3673064357995844e-06,
+      "loss": 0.6079,
+      "step": 244
+    },
+    {
+      "epoch": 1.936842105263158,
+      "grad_norm": 0.5518509745597839,
+      "learning_rate": 3.3237093633230323e-06,
+      "loss": 0.6023,
+      "step": 245
+    },
+    {
+      "epoch": 1.944736842105263,
+      "grad_norm": 0.5634933114051819,
+      "learning_rate": 3.2802554068303595e-06,
+      "loss": 0.5972,
+      "step": 246
+    },
+    {
+      "epoch": 1.9526315789473685,
+      "grad_norm": 0.5546795129776001,
+      "learning_rate": 3.236948276272337e-06,
+      "loss": 0.6012,
+      "step": 247
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.55860435962677,
+      "learning_rate": 3.1937916690642356e-06,
+      "loss": 0.6186,
+      "step": 248
+    },
+    {
+      "epoch": 1.9684210526315788,
+      "grad_norm": 0.5482208728790283,
+      "learning_rate": 3.150789269770155e-06,
+      "loss": 0.6218,
+      "step": 249
+    },
+    {
+      "epoch": 1.9763157894736842,
+      "grad_norm": 0.6123985648155212,
+      "learning_rate": 3.107944749788449e-06,
+      "loss": 0.6088,
+      "step": 250
+    },
+    {
+      "epoch": 1.9842105263157894,
+      "grad_norm": 0.5692940354347229,
+      "learning_rate": 3.0652617670382745e-06,
+      "loss": 0.5958,
+      "step": 251
+    },
+    {
+      "epoch": 1.9921052631578946,
+      "grad_norm": 0.5609405040740967,
+      "learning_rate": 3.0227439656472878e-06,
+      "loss": 0.6141,
+      "step": 252
+    },
+    {
+      "epoch": 2.0026315789473683,
+      "grad_norm": 0.5651322603225708,
+      "learning_rate": 2.980394975640526e-06,
+      "loss": 0.5795,
+      "step": 253
+    },
+    {
+      "epoch": 2.0105263157894737,
+      "grad_norm": 0.6917658448219299,
+      "learning_rate": 2.9382184126304834e-06,
+      "loss": 0.5615,
+      "step": 254
+    },
+    {
+      "epoch": 2.018421052631579,
+      "grad_norm": 0.6464757323265076,
+      "learning_rate": 2.8962178775084267e-06,
+      "loss": 0.517,
+      "step": 255
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.5215118527412415,
+      "learning_rate": 2.8543969561369556e-06,
+      "loss": 0.5421,
+      "step": 256
+    },
+    {
+      "epoch": 2.0342105263157895,
+      "grad_norm": 0.5354113578796387,
+      "learning_rate": 2.812759219043869e-06,
+      "loss": 0.5397,
+      "step": 257
+    },
+    {
+      "epoch": 2.042105263157895,
+      "grad_norm": 0.6157158613204956,
+      "learning_rate": 2.771308221117309e-06,
+      "loss": 0.5523,
+      "step": 258
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.646392822265625,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.518,
+      "step": 259
+    },
+    {
+      "epoch": 2.057894736842105,
+      "grad_norm": 0.5618102550506592,
+      "learning_rate": 2.6889805822984348e-06,
+      "loss": 0.5343,
+      "step": 260
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.5714638233184814,
+      "learning_rate": 2.648110970259454e-06,
+      "loss": 0.5421,
+      "step": 261
+    },
+    {
+      "epoch": 2.0736842105263156,
+      "grad_norm": 0.55697101354599,
+      "learning_rate": 2.607442154493568e-06,
+      "loss": 0.5382,
+      "step": 262
+    },
+    {
+      "epoch": 2.081578947368421,
+      "grad_norm": 0.6028394103050232,
+      "learning_rate": 2.5669776071657194e-06,
+      "loss": 0.5367,
+      "step": 263
+    },
+    {
+      "epoch": 2.0894736842105264,
+      "grad_norm": 0.580823540687561,
+      "learning_rate": 2.526720783001107e-06,
+      "loss": 0.5371,
+      "step": 264
+    },
+    {
+      "epoch": 2.0973684210526318,
+      "grad_norm": 0.558423638343811,
+      "learning_rate": 2.486675118990233e-06,
+      "loss": 0.5304,
+      "step": 265
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.5470890998840332,
+      "learning_rate": 2.4468440340954664e-06,
+      "loss": 0.5286,
+      "step": 266
+    },
+    {
+      "epoch": 2.113157894736842,
+      "grad_norm": 0.5406467914581299,
+      "learning_rate": 2.4072309289591394e-06,
+      "loss": 0.5733,
+      "step": 267
+    },
+    {
+      "epoch": 2.1210526315789475,
+      "grad_norm": 0.5414575934410095,
+      "learning_rate": 2.3678391856132203e-06,
+      "loss": 0.5464,
+      "step": 268
+    },
+    {
+      "epoch": 2.1289473684210525,
+      "grad_norm": 0.5568278431892395,
+      "learning_rate": 2.328672167190558e-06,
+      "loss": 0.5326,
+      "step": 269
+    },
+    {
+      "epoch": 2.136842105263158,
+      "grad_norm": 0.5567864775657654,
+      "learning_rate": 2.289733217637753e-06,
+      "loss": 0.5045,
+      "step": 270
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.5617071986198425,
+      "learning_rate": 2.2510256614296638e-06,
+      "loss": 0.5214,
+      "step": 271
+    },
+    {
+      "epoch": 2.1526315789473682,
+      "grad_norm": 0.5503396391868591,
+      "learning_rate": 2.2125528032855727e-06,
+      "loss": 0.5436,
+      "step": 272
+    },
+    {
+      "epoch": 2.1605263157894736,
+      "grad_norm": 0.5096573829650879,
+      "learning_rate": 2.174317927887041e-06,
+      "loss": 0.5268,
+      "step": 273
+    },
+    {
+      "epoch": 2.168421052631579,
+      "grad_norm": 0.5499228239059448,
+      "learning_rate": 2.136324299597474e-06,
+      "loss": 0.5281,
+      "step": 274
+    },
+    {
+      "epoch": 2.1763157894736844,
+      "grad_norm": 0.4998083710670471,
+      "learning_rate": 2.098575162183422e-06,
+      "loss": 0.5177,
+      "step": 275
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.4903915524482727,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.533,
+      "step": 276
+    },
+    {
+      "epoch": 2.192105263157895,
+      "grad_norm": 0.5267230868339539,
+      "learning_rate": 2.023823230403907e-06,
+      "loss": 0.5286,
+      "step": 277
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.5258969664573669,
+      "learning_rate": 1.9868268181037186e-06,
+      "loss": 0.5249,
+      "step": 278
+    },
+    {
+      "epoch": 2.207894736842105,
+      "grad_norm": 0.5024856925010681,
+      "learning_rate": 1.9500876602647167e-06,
+      "loss": 0.5307,
+      "step": 279
+    },
+    {
+      "epoch": 2.2157894736842105,
+      "grad_norm": 0.5637997984886169,
+      "learning_rate": 1.913608893551036e-06,
+      "loss": 0.5511,
+      "step": 280
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.5119351744651794,
+      "learning_rate": 1.8773936323955055e-06,
+      "loss": 0.5424,
+      "step": 281
+    },
+    {
+      "epoch": 2.231578947368421,
+      "grad_norm": 0.5853419303894043,
+      "learning_rate": 1.8414449687337467e-06,
+      "loss": 0.5365,
+      "step": 282
+    },
+    {
+      "epoch": 2.2394736842105263,
+      "grad_norm": 0.496768593788147,
+      "learning_rate": 1.8057659717401948e-06,
+      "loss": 0.5303,
+      "step": 283
+    },
+    {
+      "epoch": 2.2473684210526317,
+      "grad_norm": 0.5818266272544861,
+      "learning_rate": 1.7703596875660645e-06,
+      "loss": 0.5386,
+      "step": 284
+    },
+    {
+      "epoch": 2.2552631578947366,
+      "grad_norm": 0.5075578689575195,
+      "learning_rate": 1.7352291390792798e-06,
+      "loss": 0.5349,
+      "step": 285
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.4751499593257904,
+      "learning_rate": 1.7003773256063882e-06,
+      "loss": 0.5159,
+      "step": 286
+    },
+    {
+      "epoch": 2.2710526315789474,
+      "grad_norm": 0.4846212565898895,
+      "learning_rate": 1.6658072226764949e-06,
+      "loss": 0.5432,
+      "step": 287
+    },
+    {
+      "epoch": 2.2789473684210524,
+      "grad_norm": 0.5411502122879028,
+      "learning_rate": 1.6315217817672142e-06,
+      "loss": 0.5133,
+      "step": 288
+    },
+    {
+      "epoch": 2.286842105263158,
+      "grad_norm": 0.5099013447761536,
+      "learning_rate": 1.5975239300526924e-06,
+      "loss": 0.5364,
+      "step": 289
+    },
+    {
+      "epoch": 2.294736842105263,
+      "grad_norm": 0.5247920155525208,
+      "learning_rate": 1.5638165701536866e-06,
+      "loss": 0.5325,
+      "step": 290
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.5047224760055542,
+      "learning_rate": 1.5304025798897521e-06,
+      "loss": 0.5429,
+      "step": 291
+    },
+    {
+      "epoch": 2.3105263157894735,
+      "grad_norm": 0.4913298487663269,
+      "learning_rate": 1.4972848120335453e-06,
+      "loss": 0.5384,
+      "step": 292
+    },
+    {
+      "epoch": 2.318421052631579,
+      "grad_norm": 0.4855342507362366,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5449,
+      "step": 293
+    },
+    {
+      "epoch": 2.3263157894736843,
+      "grad_norm": 0.5031416416168213,
+      "learning_rate": 1.4319492279412388e-06,
+      "loss": 0.5404,
+      "step": 294
+    },
+    {
+      "epoch": 2.3342105263157893,
+      "grad_norm": 0.4946608245372772,
+      "learning_rate": 1.399736989834728e-06,
+      "loss": 0.5431,
+      "step": 295
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.5071939826011658,
+      "learning_rate": 1.3678321299188802e-06,
+      "loss": 0.5221,
+      "step": 296
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.48161017894744873,
+      "learning_rate": 1.336237372121944e-06,
+      "loss": 0.5229,
+      "step": 297
+    },
+    {
+      "epoch": 2.3578947368421055,
+      "grad_norm": 0.5062857270240784,
+      "learning_rate": 1.3049554138967052e-06,
+      "loss": 0.5344,
+      "step": 298
+    },
+    {
+      "epoch": 2.3657894736842104,
+      "grad_norm": 0.5024528503417969,
+      "learning_rate": 1.2739889259901866e-06,
+      "loss": 0.5432,
+      "step": 299
+    },
+    {
+      "epoch": 2.373684210526316,
+      "grad_norm": 0.5160316824913025,
+      "learning_rate": 1.2433405522156334e-06,
+      "loss": 0.5374,
+      "step": 300
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.527028501033783,
+      "learning_rate": 1.213012909226786e-06,
+      "loss": 0.5286,
+      "step": 301
+    },
+    {
+      "epoch": 2.389473684210526,
+      "grad_norm": 0.5148992538452148,
+      "learning_rate": 1.1830085862944851e-06,
+      "loss": 0.5527,
+      "step": 302
+    },
+    {
+      "epoch": 2.3973684210526316,
+      "grad_norm": 0.47975584864616394,
+      "learning_rate": 1.1533301450856054e-06,
+      "loss": 0.567,
+      "step": 303
+    },
+    {
+      "epoch": 2.405263157894737,
+      "grad_norm": 0.4557743966579437,
+      "learning_rate": 1.1239801194443507e-06,
+      "loss": 0.5406,
+      "step": 304
+    },
+    {
+      "epoch": 2.413157894736842,
+      "grad_norm": 0.5039398074150085,
+      "learning_rate": 1.0949610151759233e-06,
+      "loss": 0.5395,
+      "step": 305
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.5025436282157898,
+      "learning_rate": 1.066275309832584e-06,
+      "loss": 0.5485,
+      "step": 306
+    },
+    {
+      "epoch": 2.4289473684210527,
+      "grad_norm": 0.48488861322402954,
+      "learning_rate": 1.037925452502131e-06,
+      "loss": 0.5344,
+      "step": 307
+    },
+    {
+      "epoch": 2.4368421052631577,
+      "grad_norm": 0.47348925471305847,
+      "learning_rate": 1.0099138635988026e-06,
+      "loss": 0.5647,
+      "step": 308
+    },
+    {
+      "epoch": 2.444736842105263,
+      "grad_norm": 0.5118060111999512,
+      "learning_rate": 9.822429346566314e-07,
+      "loss": 0.5219,
+      "step": 309
+    },
+    {
+      "epoch": 2.4526315789473685,
+      "grad_norm": 0.48763391375541687,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5413,
+      "step": 310
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.4737011194229126,
+      "learning_rate": 9.279324771682586e-07,
+      "loss": 0.5288,
+      "step": 311
+    },
+    {
+      "epoch": 2.468421052631579,
+      "grad_norm": 0.501611590385437,
+      "learning_rate": 9.01297585463895e-07,
+      "loss": 0.5194,
+      "step": 312
+    },
+    {
+      "epoch": 2.4763157894736842,
+      "grad_norm": 0.4514743983745575,
+      "learning_rate": 8.750126270084891e-07,
+      "loss": 0.5446,
+      "step": 313
+    },
+    {
+      "epoch": 2.4842105263157896,
+      "grad_norm": 0.4870568811893463,
+      "learning_rate": 8.490798459222477e-07,
+      "loss": 0.5544,
+      "step": 314
+    },
+    {
+      "epoch": 2.4921052631578946,
+      "grad_norm": 0.4649040102958679,
+      "learning_rate": 8.235014562576732e-07,
+      "loss": 0.5344,
+      "step": 315
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.49083462357521057,
+      "learning_rate": 7.98279641810537e-07,
+      "loss": 0.5304,
+      "step": 316
+    },
+    {
+      "epoch": 2.5078947368421054,
+      "grad_norm": 0.49484091997146606,
+      "learning_rate": 7.734165559334327e-07,
+      "loss": 0.5423,
+      "step": 317
+    },
+    {
+      "epoch": 2.515789473684211,
+      "grad_norm": 0.5281040072441101,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 0.5383,
+      "step": 318
+    },
+    {
+      "epoch": 2.5236842105263158,
+      "grad_norm": 0.44312354922294617,
+      "learning_rate": 7.24775029983345e-07,
+      "loss": 0.5626,
+      "step": 319
+    },
+    {
+      "epoch": 2.531578947368421,
+      "grad_norm": 0.47553321719169617,
+      "learning_rate": 7.010007427581378e-07,
+      "loss": 0.5321,
+      "step": 320
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.4963271915912628,
+      "learning_rate": 6.775934894439606e-07,
+      "loss": 0.5305,
+      "step": 321
+    },
+    {
+      "epoch": 2.5473684210526315,
+      "grad_norm": 0.4486421048641205,
+      "learning_rate": 6.545552684723583e-07,
+      "loss": 0.5698,
+      "step": 322
+    },
+    {
+      "epoch": 2.555263157894737,
+      "grad_norm": 0.49345487356185913,
+      "learning_rate": 6.318880467681527e-07,
+      "loss": 0.5368,
+      "step": 323
+    },
+    {
+      "epoch": 2.5631578947368423,
+      "grad_norm": 0.4889611601829529,
+      "learning_rate": 6.095937595815104e-07,
+      "loss": 0.5099,
+      "step": 324
+    },
+    {
+      "epoch": 2.5710526315789473,
+      "grad_norm": 0.4943506419658661,
+      "learning_rate": 5.876743103227217e-07,
+      "loss": 0.5048,
+      "step": 325
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.48465171456336975,
+      "learning_rate": 5.661315703996905e-07,
+      "loss": 0.5433,
+      "step": 326
+    },
+    {
+      "epoch": 2.586842105263158,
+      "grad_norm": 0.49014216661453247,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.5684,
+      "step": 327
+    },
+    {
+      "epoch": 2.594736842105263,
+      "grad_norm": 0.47829702496528625,
+      "learning_rate": 5.241835432246888e-07,
+      "loss": 0.5395,
+      "step": 328
+    },
+    {
+      "epoch": 2.6026315789473684,
+      "grad_norm": 0.507520854473114,
+      "learning_rate": 5.037818373523723e-07,
+      "loss": 0.5369,
+      "step": 329
+    },
+    {
+      "epoch": 2.610526315789474,
+      "grad_norm": 0.4816722869873047,
+      "learning_rate": 4.837640032693558e-07,
+      "loss": 0.5295,
+      "step": 330
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.484370619058609,
+      "learning_rate": 4.641317500301173e-07,
+      "loss": 0.5354,
+      "step": 331
+    },
+    {
+      "epoch": 2.626315789473684,
+      "grad_norm": 0.45856356620788574,
+      "learning_rate": 4.448867537695578e-07,
+      "loss": 0.563,
+      "step": 332
+    },
+    {
+      "epoch": 2.6342105263157896,
+      "grad_norm": 0.47436991333961487,
+      "learning_rate": 4.2603065755989493e-07,
+      "loss": 0.5453,
+      "step": 333
+    },
+    {
+      "epoch": 2.6421052631578945,
+      "grad_norm": 0.48465612530708313,
+      "learning_rate": 4.0756507127038494e-07,
+      "loss": 0.5348,
+      "step": 334
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.4726357161998749,
+      "learning_rate": 3.894915714298775e-07,
+      "loss": 0.5247,
+      "step": 335
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.4793488681316376,
+      "learning_rate": 3.71811701092219e-07,
+      "loss": 0.5541,
+      "step": 336
+    },
+    {
+      "epoch": 2.6657894736842103,
+      "grad_norm": 0.5060055255889893,
+      "learning_rate": 3.5452696970450674e-07,
+      "loss": 0.5609,
+      "step": 337
+    },
+    {
+      "epoch": 2.6736842105263157,
+      "grad_norm": 0.5144080519676208,
+      "learning_rate": 3.3763885297822153e-07,
+      "loss": 0.5143,
+      "step": 338
+    },
+    {
+      "epoch": 2.681578947368421,
+      "grad_norm": 0.461753249168396,
+      "learning_rate": 3.2114879276323783e-07,
+      "loss": 0.5422,
+      "step": 339
+    },
+    {
+      "epoch": 2.6894736842105265,
+      "grad_norm": 0.48919305205345154,
+      "learning_rate": 3.0505819692471797e-07,
+      "loss": 0.5403,
+      "step": 340
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.4654390811920166,
+      "learning_rate": 2.893684392229185e-07,
+      "loss": 0.5299,
+      "step": 341
+    },
+    {
+      "epoch": 2.705263157894737,
+      "grad_norm": 0.45241108536720276,
+      "learning_rate": 2.7408085919590265e-07,
+      "loss": 0.5385,
+      "step": 342
+    },
+    {
+      "epoch": 2.713157894736842,
+      "grad_norm": 0.4543478190898895,
+      "learning_rate": 2.5919676204517073e-07,
+      "loss": 0.5522,
+      "step": 343
+    },
+    {
+      "epoch": 2.7210526315789476,
+      "grad_norm": 0.4557345509529114,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5499,
+      "step": 344
+    },
+    {
+      "epoch": 2.7289473684210526,
+      "grad_norm": 0.47247329354286194,
+      "learning_rate": 2.3064406483010947e-07,
+      "loss": 0.539,
+      "step": 345
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.5086033344268799,
+      "learning_rate": 2.1697790249779638e-07,
+      "loss": 0.5388,
+      "step": 346
+    },
+    {
+      "epoch": 2.7447368421052634,
+      "grad_norm": 0.45670172572135925,
+      "learning_rate": 2.0372009829767558e-07,
+      "loss": 0.5378,
+      "step": 347
+    },
+    {
+      "epoch": 2.7526315789473683,
+      "grad_norm": 0.47339746356010437,
+      "learning_rate": 1.908717841359048e-07,
+      "loss": 0.5362,
+      "step": 348
+    },
+    {
+      "epoch": 2.7605263157894737,
+      "grad_norm": 0.47306424379348755,
+      "learning_rate": 1.7843405695777582e-07,
+      "loss": 0.54,
+      "step": 349
+    },
+    {
+      "epoch": 2.768421052631579,
+      "grad_norm": 0.49057334661483765,
+      "learning_rate": 1.664079786540629e-07,
+      "loss": 0.5466,
+      "step": 350
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.4364169239997864,
+      "learning_rate": 1.547945759703623e-07,
+      "loss": 0.5468,
+      "step": 351
+    },
+    {
+      "epoch": 2.7842105263157895,
+      "grad_norm": 0.45972496271133423,
+      "learning_rate": 1.435948404194304e-07,
+      "loss": 0.5359,
+      "step": 352
+    },
+    {
+      "epoch": 2.792105263157895,
+      "grad_norm": 0.4681927561759949,
+      "learning_rate": 1.328097281965357e-07,
+      "loss": 0.5218,
+      "step": 353
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.48078453540802,
+      "learning_rate": 1.22440160097817e-07,
+      "loss": 0.5318,
+      "step": 354
+    },
+    {
+      "epoch": 2.807894736842105,
+      "grad_norm": 0.5014187097549438,
+      "learning_rate": 1.1248702144167123e-07,
+      "loss": 0.5175,
+      "step": 355
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.4723798632621765,
+      "learning_rate": 1.0295116199317057e-07,
+      "loss": 0.5459,
+      "step": 356
+    },
+    {
+      "epoch": 2.8236842105263156,
+      "grad_norm": 0.485458105802536,
+      "learning_rate": 9.383339589150776e-08,
+      "loss": 0.5221,
+      "step": 357
+    },
+    {
+      "epoch": 2.831578947368421,
+      "grad_norm": 0.4910981059074402,
+      "learning_rate": 8.513450158049109e-08,
+      "loss": 0.5192,
+      "step": 358
+    },
+    {
+      "epoch": 2.8394736842105264,
+      "grad_norm": 0.49855437874794006,
+      "learning_rate": 7.685522174208205e-08,
+      "loss": 0.5347,
+      "step": 359
+    },
+    {
+      "epoch": 2.8473684210526313,
+      "grad_norm": 0.46188458800315857,
+      "learning_rate": 6.899626323298714e-08,
+      "loss": 0.5286,
+      "step": 360
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.488492876291275,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.5202,
+      "step": 361
+    },
+    {
+      "epoch": 2.863157894736842,
+      "grad_norm": 0.516136109828949,
+      "learning_rate": 5.454195814427021e-08,
+      "loss": 0.5044,
+      "step": 362
+    },
+    {
+      "epoch": 2.8710526315789475,
+      "grad_norm": 0.4855652451515198,
+      "learning_rate": 4.794784562397459e-08,
+      "loss": 0.535,
+      "step": 363
+    },
+    {
+      "epoch": 2.8789473684210525,
+      "grad_norm": 0.49933773279190063,
+      "learning_rate": 4.177652244628627e-08,
+      "loss": 0.5383,
+      "step": 364
+    },
+    {
+      "epoch": 2.886842105263158,
+      "grad_norm": 0.48090240359306335,
+      "learning_rate": 3.602851549775521e-08,
+      "loss": 0.5396,
+      "step": 365
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.4793301820755005,
+      "learning_rate": 3.0704315523631956e-08,
+      "loss": 0.5389,
+      "step": 366
+    },
+    {
+      "epoch": 2.9026315789473687,
+      "grad_norm": 0.5019791722297668,
+      "learning_rate": 2.5804377085972278e-08,
+      "loss": 0.5565,
+      "step": 367
+    },
+    {
+      "epoch": 2.9105263157894736,
+      "grad_norm": 0.4860020577907562,
+      "learning_rate": 2.1329118524827662e-08,
+      "loss": 0.522,
+      "step": 368
+    },
+    {
+      "epoch": 2.918421052631579,
+      "grad_norm": 0.49818456172943115,
+      "learning_rate": 1.7278921922527224e-08,
+      "loss": 0.5146,
+      "step": 369
+    },
+    {
+      "epoch": 2.9263157894736844,
+      "grad_norm": 0.46853312849998474,
+      "learning_rate": 1.3654133071059894e-08,
+      "loss": 0.5414,
+      "step": 370
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.47929537296295166,
+      "learning_rate": 1.0455061442548597e-08,
+      "loss": 0.5294,
+      "step": 371
+    },
+    {
+      "epoch": 2.942105263157895,
+      "grad_norm": 0.4867682158946991,
+      "learning_rate": 7.681980162830283e-09,
+      "loss": 0.5533,
+      "step": 372
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.47420981526374817,
+      "learning_rate": 5.3351259881379016e-09,
+      "loss": 0.5315,
+      "step": 373
+    },
+    {
+      "epoch": 2.957894736842105,
+      "grad_norm": 0.5050917863845825,
+      "learning_rate": 3.41469928488547e-09,
+      "loss": 0.5376,
+      "step": 374
+    },
+    {
+      "epoch": 2.9657894736842105,
+      "grad_norm": 0.4844934940338135,
+      "learning_rate": 1.9208640125628618e-09,
+      "loss": 0.5484,
+      "step": 375
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.478400319814682,
+      "learning_rate": 8.537477097364522e-10,
+      "loss": 0.5329,
+      "step": 376
+    },
+    {
+      "epoch": 2.981578947368421,
+      "grad_norm": 0.47381076216697693,
+      "learning_rate": 2.1344148316060352e-10,
+      "loss": 0.5301,
+      "step": 377
+    },
+    {
+      "epoch": 2.9894736842105263,
+      "grad_norm": 0.5020145177841187,
+      "learning_rate": 0.0,
+      "loss": 0.5492,
+      "step": 378
+    },
+    {
+      "epoch": 2.9894736842105263,
+      "step": 378,
+      "total_flos": 3.713025592344904e+17,
+      "train_loss": 0.0,
+      "train_runtime": 12.3976,
+      "train_samples_per_second": 2940.336,
+      "train_steps_per_second": 30.49
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 378,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.713025592344904e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78925a876e986143bb67aab94f58cde5ef66463cd109324e5b7505867f42e2a
+size 7672