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": 2.9846938775510203,
+    "total_flos": 1.3384682412693258e+18,
+    "train_loss": 0.7546794874545856,
+    "train_runtime": 13624.8324,
+    "train_samples_per_second": 2.76,
+    "train_steps_per_second": 0.029
+}

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 sha256:3753a5363cf80ae90ea7d0f3c968f7dca20935c830512cbd14e60369345e5212
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f3ca23047a9ef9d44d7442edc92b7e8e35f34e31c507c267cb4c6a38667c24
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cb9af7902a3d6736d0fca616c73ba82b6749b735be7aa033adcfe4fd834afa
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d0d38976ff537ed77fd7e8da7f40bcc8a901ac3c2119d69a0ce7ffdb5260ad
+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": 2.9846938775510203,
+    "total_flos": 1.3384682412693258e+18,
+    "train_loss": 0.7546794874545856,
+    "train_runtime": 13624.8324,
+    "train_samples_per_second": 2.76,
+    "train_steps_per_second": 0.029
+}

trainer_log.jsonl

@@ -0,0 +1,391 @@
+{"current_steps": 1, "total_steps": 390, "loss": 1.2547, "lr": 2.564102564102564e-07, "epoch": 0.007653061224489796, "percentage": 0.26, "elapsed_time": "0:00:58", "remaining_time": "6:21:25"}
+{"current_steps": 2, "total_steps": 390, "loss": 1.2846, "lr": 5.128205128205128e-07, "epoch": 0.015306122448979591, "percentage": 0.51, "elapsed_time": "0:01:32", "remaining_time": "5:00:36"}
+{"current_steps": 3, "total_steps": 390, "loss": 1.2358, "lr": 7.692307692307694e-07, "epoch": 0.02295918367346939, "percentage": 0.77, "elapsed_time": "0:02:07", "remaining_time": "4:33:13"}
+{"current_steps": 4, "total_steps": 390, "loss": 1.2664, "lr": 1.0256410256410257e-06, "epoch": 0.030612244897959183, "percentage": 1.03, "elapsed_time": "0:02:41", "remaining_time": "4:19:17"}
+{"current_steps": 5, "total_steps": 390, "loss": 1.2258, "lr": 1.282051282051282e-06, "epoch": 0.03826530612244898, "percentage": 1.28, "elapsed_time": "0:03:15", "remaining_time": "4:10:40"}
+{"current_steps": 6, "total_steps": 390, "loss": 1.2287, "lr": 1.5384615384615387e-06, "epoch": 0.04591836734693878, "percentage": 1.54, "elapsed_time": "0:03:49", "remaining_time": "4:04:39"}
+{"current_steps": 7, "total_steps": 390, "loss": 1.2074, "lr": 1.794871794871795e-06, "epoch": 0.05357142857142857, "percentage": 1.79, "elapsed_time": "0:04:23", "remaining_time": "4:00:13"}
+{"current_steps": 8, "total_steps": 390, "loss": 1.1714, "lr": 2.0512820512820513e-06, "epoch": 0.061224489795918366, "percentage": 2.05, "elapsed_time": "0:04:57", "remaining_time": "3:56:46"}
+{"current_steps": 9, "total_steps": 390, "loss": 1.1896, "lr": 2.307692307692308e-06, "epoch": 0.06887755102040816, "percentage": 2.31, "elapsed_time": "0:05:31", "remaining_time": "3:53:56"}
+{"current_steps": 10, "total_steps": 390, "loss": 1.1187, "lr": 2.564102564102564e-06, "epoch": 0.07653061224489796, "percentage": 2.56, "elapsed_time": "0:06:05", "remaining_time": "3:51:35"}
+{"current_steps": 11, "total_steps": 390, "loss": 1.1054, "lr": 2.8205128205128207e-06, "epoch": 0.08418367346938775, "percentage": 2.82, "elapsed_time": "0:06:39", "remaining_time": "3:49:34"}
+{"current_steps": 12, "total_steps": 390, "loss": 1.1232, "lr": 3.0769230769230774e-06, "epoch": 0.09183673469387756, "percentage": 3.08, "elapsed_time": "0:07:13", "remaining_time": "3:47:47"}
+{"current_steps": 13, "total_steps": 390, "loss": 1.0521, "lr": 3.3333333333333333e-06, "epoch": 0.09948979591836735, "percentage": 3.33, "elapsed_time": "0:07:48", "remaining_time": "3:46:12"}
+{"current_steps": 14, "total_steps": 390, "loss": 1.0695, "lr": 3.58974358974359e-06, "epoch": 0.10714285714285714, "percentage": 3.59, "elapsed_time": "0:08:22", "remaining_time": "3:44:45"}
+{"current_steps": 15, "total_steps": 390, "loss": 1.0492, "lr": 3.846153846153847e-06, "epoch": 0.11479591836734694, "percentage": 3.85, "elapsed_time": "0:08:56", "remaining_time": "3:43:26"}
+{"current_steps": 16, "total_steps": 390, "loss": 1.0507, "lr": 4.102564102564103e-06, "epoch": 0.12244897959183673, "percentage": 4.1, "elapsed_time": "0:09:30", "remaining_time": "3:42:13"}
+{"current_steps": 17, "total_steps": 390, "loss": 1.0352, "lr": 4.358974358974359e-06, "epoch": 0.13010204081632654, "percentage": 4.36, "elapsed_time": "0:10:04", "remaining_time": "3:41:05"}
+{"current_steps": 18, "total_steps": 390, "loss": 0.9931, "lr": 4.615384615384616e-06, "epoch": 0.1377551020408163, "percentage": 4.62, "elapsed_time": "0:10:38", "remaining_time": "3:39:59"}
+{"current_steps": 19, "total_steps": 390, "loss": 0.9909, "lr": 4.871794871794872e-06, "epoch": 0.14540816326530612, "percentage": 4.87, "elapsed_time": "0:11:12", "remaining_time": "3:38:58"}
+{"current_steps": 20, "total_steps": 390, "loss": 0.9585, "lr": 5.128205128205128e-06, "epoch": 0.15306122448979592, "percentage": 5.13, "elapsed_time": "0:11:47", "remaining_time": "3:37:59"}
+{"current_steps": 21, "total_steps": 390, "loss": 0.9512, "lr": 5.384615384615385e-06, "epoch": 0.16071428571428573, "percentage": 5.38, "elapsed_time": "0:12:21", "remaining_time": "3:37:02"}
+{"current_steps": 22, "total_steps": 390, "loss": 0.9211, "lr": 5.641025641025641e-06, "epoch": 0.1683673469387755, "percentage": 5.64, "elapsed_time": "0:12:55", "remaining_time": "3:36:07"}
+{"current_steps": 23, "total_steps": 390, "loss": 0.9276, "lr": 5.897435897435898e-06, "epoch": 0.1760204081632653, "percentage": 5.9, "elapsed_time": "0:13:29", "remaining_time": "3:35:14"}
+{"current_steps": 24, "total_steps": 390, "loss": 0.8952, "lr": 6.153846153846155e-06, "epoch": 0.1836734693877551, "percentage": 6.15, "elapsed_time": "0:14:03", "remaining_time": "3:34:22"}
+{"current_steps": 25, "total_steps": 390, "loss": 0.9, "lr": 6.410256410256412e-06, "epoch": 0.1913265306122449, "percentage": 6.41, "elapsed_time": "0:14:37", "remaining_time": "3:33:32"}
+{"current_steps": 26, "total_steps": 390, "loss": 0.91, "lr": 6.666666666666667e-06, "epoch": 0.1989795918367347, "percentage": 6.67, "elapsed_time": "0:15:11", "remaining_time": "3:32:42"}
+{"current_steps": 27, "total_steps": 390, "loss": 0.8814, "lr": 6.923076923076923e-06, "epoch": 0.2066326530612245, "percentage": 6.92, "elapsed_time": "0:15:45", "remaining_time": "3:31:55"}
+{"current_steps": 28, "total_steps": 390, "loss": 0.8919, "lr": 7.17948717948718e-06, "epoch": 0.21428571428571427, "percentage": 7.18, "elapsed_time": "0:16:19", "remaining_time": "3:31:07"}
+{"current_steps": 29, "total_steps": 390, "loss": 0.8725, "lr": 7.435897435897437e-06, "epoch": 0.22193877551020408, "percentage": 7.44, "elapsed_time": "0:16:53", "remaining_time": "3:30:20"}
+{"current_steps": 30, "total_steps": 390, "loss": 0.8632, "lr": 7.692307692307694e-06, "epoch": 0.22959183673469388, "percentage": 7.69, "elapsed_time": "0:17:27", "remaining_time": "3:29:35"}
+{"current_steps": 31, "total_steps": 390, "loss": 0.8851, "lr": 7.948717948717949e-06, "epoch": 0.2372448979591837, "percentage": 7.95, "elapsed_time": "0:18:02", "remaining_time": "3:28:50"}
+{"current_steps": 32, "total_steps": 390, "loss": 0.8703, "lr": 8.205128205128205e-06, "epoch": 0.24489795918367346, "percentage": 8.21, "elapsed_time": "0:18:36", "remaining_time": "3:28:07"}
+{"current_steps": 33, "total_steps": 390, "loss": 0.8635, "lr": 8.461538461538462e-06, "epoch": 0.25255102040816324, "percentage": 8.46, "elapsed_time": "0:19:10", "remaining_time": "3:27:23"}
+{"current_steps": 34, "total_steps": 390, "loss": 0.857, "lr": 8.717948717948719e-06, "epoch": 0.2602040816326531, "percentage": 8.72, "elapsed_time": "0:19:44", "remaining_time": "3:26:40"}
+{"current_steps": 35, "total_steps": 390, "loss": 0.8674, "lr": 8.974358974358976e-06, "epoch": 0.26785714285714285, "percentage": 8.97, "elapsed_time": "0:20:18", "remaining_time": "3:25:57"}
+{"current_steps": 36, "total_steps": 390, "loss": 0.8643, "lr": 9.230769230769232e-06, "epoch": 0.2755102040816326, "percentage": 9.23, "elapsed_time": "0:20:52", "remaining_time": "3:25:16"}
+{"current_steps": 37, "total_steps": 390, "loss": 0.8524, "lr": 9.487179487179487e-06, "epoch": 0.28316326530612246, "percentage": 9.49, "elapsed_time": "0:21:26", "remaining_time": "3:24:34"}
+{"current_steps": 38, "total_steps": 390, "loss": 0.8345, "lr": 9.743589743589744e-06, "epoch": 0.29081632653061223, "percentage": 9.74, "elapsed_time": "0:22:00", "remaining_time": "3:23:53"}
+{"current_steps": 39, "total_steps": 390, "loss": 0.8383, "lr": 1e-05, "epoch": 0.29846938775510207, "percentage": 10.0, "elapsed_time": "0:22:34", "remaining_time": "3:23:13"}
+{"current_steps": 40, "total_steps": 390, "loss": 0.8445, "lr": 9.999799726899261e-06, "epoch": 0.30612244897959184, "percentage": 10.26, "elapsed_time": "0:23:08", "remaining_time": "3:22:32"}
+{"current_steps": 41, "total_steps": 390, "loss": 0.8339, "lr": 9.999198923640774e-06, "epoch": 0.3137755102040816, "percentage": 10.51, "elapsed_time": "0:23:43", "remaining_time": "3:21:53"}
+{"current_steps": 42, "total_steps": 390, "loss": 0.8395, "lr": 9.998197638354428e-06, "epoch": 0.32142857142857145, "percentage": 10.77, "elapsed_time": "0:24:17", "remaining_time": "3:21:13"}
+{"current_steps": 43, "total_steps": 390, "loss": 0.8447, "lr": 9.996795951252427e-06, "epoch": 0.32908163265306123, "percentage": 11.03, "elapsed_time": "0:24:51", "remaining_time": "3:20:35"}
+{"current_steps": 44, "total_steps": 390, "loss": 0.8388, "lr": 9.994993974622863e-06, "epoch": 0.336734693877551, "percentage": 11.28, "elapsed_time": "0:25:25", "remaining_time": "3:19:55"}
+{"current_steps": 45, "total_steps": 390, "loss": 0.8107, "lr": 9.992791852820709e-06, "epoch": 0.34438775510204084, "percentage": 11.54, "elapsed_time": "0:25:59", "remaining_time": "3:19:17"}
+{"current_steps": 46, "total_steps": 390, "loss": 0.8345, "lr": 9.990189762256275e-06, "epoch": 0.3520408163265306, "percentage": 11.79, "elapsed_time": "0:26:33", "remaining_time": "3:18:38"}
+{"current_steps": 47, "total_steps": 390, "loss": 0.8341, "lr": 9.987187911381059e-06, "epoch": 0.3596938775510204, "percentage": 12.05, "elapsed_time": "0:27:07", "remaining_time": "3:17:59"}
+{"current_steps": 48, "total_steps": 390, "loss": 0.8221, "lr": 9.983786540671052e-06, "epoch": 0.3673469387755102, "percentage": 12.31, "elapsed_time": "0:27:41", "remaining_time": "3:17:21"}
+{"current_steps": 49, "total_steps": 390, "loss": 0.8122, "lr": 9.979985922607476e-06, "epoch": 0.375, "percentage": 12.56, "elapsed_time": "0:28:16", "remaining_time": "3:16:43"}
+{"current_steps": 50, "total_steps": 390, "loss": 0.8266, "lr": 9.975786361654959e-06, "epoch": 0.3826530612244898, "percentage": 12.82, "elapsed_time": "0:28:50", "remaining_time": "3:16:05"}
+{"current_steps": 51, "total_steps": 390, "loss": 0.8088, "lr": 9.971188194237141e-06, "epoch": 0.3903061224489796, "percentage": 13.08, "elapsed_time": "0:29:24", "remaining_time": "3:15:26"}
+{"current_steps": 52, "total_steps": 390, "loss": 0.8104, "lr": 9.966191788709716e-06, "epoch": 0.3979591836734694, "percentage": 13.33, "elapsed_time": "0:29:58", "remaining_time": "3:14:48"}
+{"current_steps": 53, "total_steps": 390, "loss": 0.7912, "lr": 9.960797545330936e-06, "epoch": 0.40561224489795916, "percentage": 13.59, "elapsed_time": "0:30:32", "remaining_time": "3:14:11"}
+{"current_steps": 54, "total_steps": 390, "loss": 0.812, "lr": 9.955005896229543e-06, "epoch": 0.413265306122449, "percentage": 13.85, "elapsed_time": "0:31:06", "remaining_time": "3:13:33"}
+{"current_steps": 55, "total_steps": 390, "loss": 0.817, "lr": 9.948817305370145e-06, "epoch": 0.42091836734693877, "percentage": 14.1, "elapsed_time": "0:31:40", "remaining_time": "3:12:55"}
+{"current_steps": 56, "total_steps": 390, "loss": 0.8101, "lr": 9.942232268516051e-06, "epoch": 0.42857142857142855, "percentage": 14.36, "elapsed_time": "0:32:14", "remaining_time": "3:12:18"}
+{"current_steps": 57, "total_steps": 390, "loss": 0.7987, "lr": 9.935251313189564e-06, "epoch": 0.4362244897959184, "percentage": 14.62, "elapsed_time": "0:32:48", "remaining_time": "3:11:42"}
+{"current_steps": 58, "total_steps": 390, "loss": 0.8122, "lr": 9.927874998629714e-06, "epoch": 0.44387755102040816, "percentage": 14.87, "elapsed_time": "0:33:22", "remaining_time": "3:11:05"}
+{"current_steps": 59, "total_steps": 390, "loss": 0.8113, "lr": 9.920103915747452e-06, "epoch": 0.45153061224489793, "percentage": 15.13, "elapsed_time": "0:33:57", "remaining_time": "3:10:28"}
+{"current_steps": 60, "total_steps": 390, "loss": 0.7859, "lr": 9.911938687078324e-06, "epoch": 0.45918367346938777, "percentage": 15.38, "elapsed_time": "0:34:31", "remaining_time": "3:09:51"}
+{"current_steps": 61, "total_steps": 390, "loss": 0.802, "lr": 9.9033799667326e-06, "epoch": 0.46683673469387754, "percentage": 15.64, "elapsed_time": "0:35:05", "remaining_time": "3:09:15"}
+{"current_steps": 62, "total_steps": 390, "loss": 0.8253, "lr": 9.89442844034286e-06, "epoch": 0.4744897959183674, "percentage": 15.9, "elapsed_time": "0:35:39", "remaining_time": "3:08:38"}
+{"current_steps": 63, "total_steps": 390, "loss": 0.8105, "lr": 9.885084825009085e-06, "epoch": 0.48214285714285715, "percentage": 16.15, "elapsed_time": "0:36:13", "remaining_time": "3:08:01"}
+{"current_steps": 64, "total_steps": 390, "loss": 0.7953, "lr": 9.875349869241202e-06, "epoch": 0.4897959183673469, "percentage": 16.41, "elapsed_time": "0:36:47", "remaining_time": "3:07:25"}
+{"current_steps": 65, "total_steps": 390, "loss": 0.8013, "lr": 9.86522435289912e-06, "epoch": 0.49744897959183676, "percentage": 16.67, "elapsed_time": "0:37:21", "remaining_time": "3:06:48"}
+{"current_steps": 66, "total_steps": 390, "loss": 0.7995, "lr": 9.854709087130261e-06, "epoch": 0.5051020408163265, "percentage": 16.92, "elapsed_time": "0:37:55", "remaining_time": "3:06:12"}
+{"current_steps": 67, "total_steps": 390, "loss": 0.7896, "lr": 9.843804914304578e-06, "epoch": 0.5127551020408163, "percentage": 17.18, "elapsed_time": "0:38:29", "remaining_time": "3:05:36"}
+{"current_steps": 68, "total_steps": 390, "loss": 0.7825, "lr": 9.83251270794707e-06, "epoch": 0.5204081632653061, "percentage": 17.44, "elapsed_time": "0:39:04", "remaining_time": "3:04:59"}
+{"current_steps": 69, "total_steps": 390, "loss": 0.8065, "lr": 9.820833372667813e-06, "epoch": 0.5280612244897959, "percentage": 17.69, "elapsed_time": "0:39:38", "remaining_time": "3:04:23"}
+{"current_steps": 70, "total_steps": 390, "loss": 0.7736, "lr": 9.80876784408948e-06, "epoch": 0.5357142857142857, "percentage": 17.95, "elapsed_time": "0:40:12", "remaining_time": "3:03:47"}
+{"current_steps": 71, "total_steps": 390, "loss": 0.8006, "lr": 9.796317088772402e-06, "epoch": 0.5433673469387755, "percentage": 18.21, "elapsed_time": "0:40:46", "remaining_time": "3:03:11"}
+{"current_steps": 72, "total_steps": 390, "loss": 0.793, "lr": 9.783482104137127e-06, "epoch": 0.5510204081632653, "percentage": 18.46, "elapsed_time": "0:41:20", "remaining_time": "3:02:35"}
+{"current_steps": 73, "total_steps": 390, "loss": 0.7628, "lr": 9.770263918384523e-06, "epoch": 0.5586734693877551, "percentage": 18.72, "elapsed_time": "0:41:54", "remaining_time": "3:02:00"}
+{"current_steps": 74, "total_steps": 390, "loss": 0.7849, "lr": 9.75666359041341e-06, "epoch": 0.5663265306122449, "percentage": 18.97, "elapsed_time": "0:42:28", "remaining_time": "3:01:24"}
+{"current_steps": 75, "total_steps": 390, "loss": 0.7813, "lr": 9.742682209735727e-06, "epoch": 0.5739795918367347, "percentage": 19.23, "elapsed_time": "0:43:02", "remaining_time": "3:00:48"}
+{"current_steps": 76, "total_steps": 390, "loss": 0.7717, "lr": 9.728320896389263e-06, "epoch": 0.5816326530612245, "percentage": 19.49, "elapsed_time": "0:43:37", "remaining_time": "3:00:12"}
+{"current_steps": 77, "total_steps": 390, "loss": 0.7964, "lr": 9.713580800847917e-06, "epoch": 0.5892857142857143, "percentage": 19.74, "elapsed_time": "0:44:11", "remaining_time": "2:59:36"}
+{"current_steps": 78, "total_steps": 390, "loss": 0.783, "lr": 9.698463103929542e-06, "epoch": 0.5969387755102041, "percentage": 20.0, "elapsed_time": "0:44:45", "remaining_time": "2:59:00"}
+{"current_steps": 79, "total_steps": 390, "loss": 0.8124, "lr": 9.682969016701357e-06, "epoch": 0.6045918367346939, "percentage": 20.26, "elapsed_time": "0:45:19", "remaining_time": "2:58:25"}
+{"current_steps": 80, "total_steps": 390, "loss": 0.8027, "lr": 9.66709978038292e-06, "epoch": 0.6122448979591837, "percentage": 20.51, "elapsed_time": "0:45:53", "remaining_time": "2:57:49"}
+{"current_steps": 81, "total_steps": 390, "loss": 0.7884, "lr": 9.650856666246693e-06, "epoch": 0.6198979591836735, "percentage": 20.77, "elapsed_time": "0:46:27", "remaining_time": "2:57:13"}
+{"current_steps": 82, "total_steps": 390, "loss": 0.7914, "lr": 9.63424097551621e-06, "epoch": 0.6275510204081632, "percentage": 21.03, "elapsed_time": "0:47:01", "remaining_time": "2:56:38"}
+{"current_steps": 83, "total_steps": 390, "loss": 0.7698, "lr": 9.617254039261835e-06, "epoch": 0.6352040816326531, "percentage": 21.28, "elapsed_time": "0:47:35", "remaining_time": "2:56:02"}
+{"current_steps": 84, "total_steps": 390, "loss": 0.7958, "lr": 9.599897218294122e-06, "epoch": 0.6428571428571429, "percentage": 21.54, "elapsed_time": "0:48:09", "remaining_time": "2:55:27"}
+{"current_steps": 85, "total_steps": 390, "loss": 0.7677, "lr": 9.582171903054815e-06, "epoch": 0.6505102040816326, "percentage": 21.79, "elapsed_time": "0:48:43", "remaining_time": "2:54:51"}
+{"current_steps": 86, "total_steps": 390, "loss": 0.8015, "lr": 9.564079513505455e-06, "epoch": 0.6581632653061225, "percentage": 22.05, "elapsed_time": "0:49:18", "remaining_time": "2:54:16"}
+{"current_steps": 87, "total_steps": 390, "loss": 0.7638, "lr": 9.54562149901362e-06, "epoch": 0.6658163265306123, "percentage": 22.31, "elapsed_time": "0:49:52", "remaining_time": "2:53:40"}
+{"current_steps": 88, "total_steps": 390, "loss": 0.7843, "lr": 9.526799338236828e-06, "epoch": 0.673469387755102, "percentage": 22.56, "elapsed_time": "0:50:26", "remaining_time": "2:53:05"}
+{"current_steps": 89, "total_steps": 390, "loss": 0.7925, "lr": 9.507614539004082e-06, "epoch": 0.6811224489795918, "percentage": 22.82, "elapsed_time": "0:51:00", "remaining_time": "2:52:29"}
+{"current_steps": 90, "total_steps": 390, "loss": 0.7894, "lr": 9.488068638195072e-06, "epoch": 0.6887755102040817, "percentage": 23.08, "elapsed_time": "0:51:34", "remaining_time": "2:51:54"}
+{"current_steps": 91, "total_steps": 390, "loss": 0.7625, "lr": 9.468163201617063e-06, "epoch": 0.6964285714285714, "percentage": 23.33, "elapsed_time": "0:52:08", "remaining_time": "2:51:19"}
+{"current_steps": 92, "total_steps": 390, "loss": 0.7664, "lr": 9.447899823879456e-06, "epoch": 0.7040816326530612, "percentage": 23.59, "elapsed_time": "0:52:42", "remaining_time": "2:50:44"}
+{"current_steps": 93, "total_steps": 390, "loss": 0.7827, "lr": 9.427280128266049e-06, "epoch": 0.7117346938775511, "percentage": 23.85, "elapsed_time": "0:53:16", "remaining_time": "2:50:08"}
+{"current_steps": 94, "total_steps": 390, "loss": 0.7868, "lr": 9.406305766604996e-06, "epoch": 0.7193877551020408, "percentage": 24.1, "elapsed_time": "0:53:50", "remaining_time": "2:49:33"}
+{"current_steps": 95, "total_steps": 390, "loss": 0.7898, "lr": 9.384978419136469e-06, "epoch": 0.7270408163265306, "percentage": 24.36, "elapsed_time": "0:54:24", "remaining_time": "2:48:58"}
+{"current_steps": 96, "total_steps": 390, "loss": 0.7665, "lr": 9.363299794378072e-06, "epoch": 0.7346938775510204, "percentage": 24.62, "elapsed_time": "0:54:58", "remaining_time": "2:48:22"}
+{"current_steps": 97, "total_steps": 390, "loss": 0.7726, "lr": 9.34127162898797e-06, "epoch": 0.7423469387755102, "percentage": 24.87, "elapsed_time": "0:55:33", "remaining_time": "2:47:47"}
+{"current_steps": 98, "total_steps": 390, "loss": 0.7835, "lr": 9.318895687625752e-06, "epoch": 0.75, "percentage": 25.13, "elapsed_time": "0:56:07", "remaining_time": "2:47:12"}
+{"current_steps": 99, "total_steps": 390, "loss": 0.7777, "lr": 9.296173762811084e-06, "epoch": 0.7576530612244898, "percentage": 25.38, "elapsed_time": "0:56:41", "remaining_time": "2:46:37"}
+{"current_steps": 100, "total_steps": 390, "loss": 0.789, "lr": 9.273107674780102e-06, "epoch": 0.7653061224489796, "percentage": 25.64, "elapsed_time": "0:57:15", "remaining_time": "2:46:02"}
+{"current_steps": 101, "total_steps": 390, "loss": 0.7603, "lr": 9.249699271339594e-06, "epoch": 0.7729591836734694, "percentage": 25.9, "elapsed_time": "0:57:49", "remaining_time": "2:45:27"}
+{"current_steps": 102, "total_steps": 390, "loss": 0.7825, "lr": 9.225950427718974e-06, "epoch": 0.7806122448979592, "percentage": 26.15, "elapsed_time": "0:58:23", "remaining_time": "2:44:52"}
+{"current_steps": 103, "total_steps": 390, "loss": 0.7736, "lr": 9.201863046420065e-06, "epoch": 0.7882653061224489, "percentage": 26.41, "elapsed_time": "0:58:57", "remaining_time": "2:44:17"}
+{"current_steps": 104, "total_steps": 390, "loss": 0.7846, "lr": 9.177439057064684e-06, "epoch": 0.7959183673469388, "percentage": 26.67, "elapsed_time": "0:59:31", "remaining_time": "2:43:42"}
+{"current_steps": 105, "total_steps": 390, "loss": 0.7666, "lr": 9.152680416240059e-06, "epoch": 0.8035714285714286, "percentage": 26.92, "elapsed_time": "1:00:05", "remaining_time": "2:43:07"}
+{"current_steps": 106, "total_steps": 390, "loss": 0.7657, "lr": 9.1275891073421e-06, "epoch": 0.8112244897959183, "percentage": 27.18, "elapsed_time": "1:00:40", "remaining_time": "2:42:32"}
+{"current_steps": 107, "total_steps": 390, "loss": 0.7709, "lr": 9.102167140416503e-06, "epoch": 0.8188775510204082, "percentage": 27.44, "elapsed_time": "1:01:14", "remaining_time": "2:41:57"}
+{"current_steps": 108, "total_steps": 390, "loss": 0.7744, "lr": 9.076416551997721e-06, "epoch": 0.826530612244898, "percentage": 27.69, "elapsed_time": "1:01:48", "remaining_time": "2:41:22"}
+{"current_steps": 109, "total_steps": 390, "loss": 0.7827, "lr": 9.050339404945834e-06, "epoch": 0.8341836734693877, "percentage": 27.95, "elapsed_time": "1:02:22", "remaining_time": "2:40:48"}
+{"current_steps": 110, "total_steps": 390, "loss": 0.7834, "lr": 9.023937788281278e-06, "epoch": 0.8418367346938775, "percentage": 28.21, "elapsed_time": "1:02:56", "remaining_time": "2:40:12"}
+{"current_steps": 111, "total_steps": 390, "loss": 0.7644, "lr": 8.997213817017508e-06, "epoch": 0.8494897959183674, "percentage": 28.46, "elapsed_time": "1:03:30", "remaining_time": "2:39:38"}
+{"current_steps": 112, "total_steps": 390, "loss": 0.779, "lr": 8.970169631991556e-06, "epoch": 0.8571428571428571, "percentage": 28.72, "elapsed_time": "1:04:04", "remaining_time": "2:39:03"}
+{"current_steps": 113, "total_steps": 390, "loss": 0.7688, "lr": 8.942807399692543e-06, "epoch": 0.8647959183673469, "percentage": 28.97, "elapsed_time": "1:04:38", "remaining_time": "2:38:28"}
+{"current_steps": 114, "total_steps": 390, "loss": 0.7757, "lr": 8.915129312088112e-06, "epoch": 0.8724489795918368, "percentage": 29.23, "elapsed_time": "1:05:12", "remaining_time": "2:37:53"}
+{"current_steps": 115, "total_steps": 390, "loss": 0.7674, "lr": 8.88713758644883e-06, "epoch": 0.8801020408163265, "percentage": 29.49, "elapsed_time": "1:05:46", "remaining_time": "2:37:18"}
+{"current_steps": 116, "total_steps": 390, "loss": 0.7677, "lr": 8.858834465170576e-06, "epoch": 0.8877551020408163, "percentage": 29.74, "elapsed_time": "1:06:21", "remaining_time": "2:36:43"}
+{"current_steps": 117, "total_steps": 390, "loss": 0.7568, "lr": 8.83022221559489e-06, "epoch": 0.8954081632653061, "percentage": 30.0, "elapsed_time": "1:06:55", "remaining_time": "2:36:08"}
+{"current_steps": 118, "total_steps": 390, "loss": 0.7822, "lr": 8.801303129827352e-06, "epoch": 0.9030612244897959, "percentage": 30.26, "elapsed_time": "1:07:29", "remaining_time": "2:35:34"}
+{"current_steps": 119, "total_steps": 390, "loss": 0.7534, "lr": 8.772079524553951e-06, "epoch": 0.9107142857142857, "percentage": 30.51, "elapsed_time": "1:08:03", "remaining_time": "2:34:59"}
+{"current_steps": 120, "total_steps": 390, "loss": 0.7739, "lr": 8.742553740855507e-06, "epoch": 0.9183673469387755, "percentage": 30.77, "elapsed_time": "1:08:37", "remaining_time": "2:34:24"}
+{"current_steps": 121, "total_steps": 390, "loss": 0.7603, "lr": 8.712728144020118e-06, "epoch": 0.9260204081632653, "percentage": 31.03, "elapsed_time": "1:09:11", "remaining_time": "2:33:49"}
+{"current_steps": 122, "total_steps": 390, "loss": 0.7629, "lr": 8.682605123353685e-06, "epoch": 0.9336734693877551, "percentage": 31.28, "elapsed_time": "1:09:45", "remaining_time": "2:33:14"}
+{"current_steps": 123, "total_steps": 390, "loss": 0.7751, "lr": 8.652187091988516e-06, "epoch": 0.9413265306122449, "percentage": 31.54, "elapsed_time": "1:10:19", "remaining_time": "2:32:40"}
+{"current_steps": 124, "total_steps": 390, "loss": 0.7617, "lr": 8.621476486689991e-06, "epoch": 0.9489795918367347, "percentage": 31.79, "elapsed_time": "1:10:54", "remaining_time": "2:32:05"}
+{"current_steps": 125, "total_steps": 390, "loss": 0.7715, "lr": 8.590475767661371e-06, "epoch": 0.9566326530612245, "percentage": 32.05, "elapsed_time": "1:11:28", "remaining_time": "2:31:30"}
+{"current_steps": 126, "total_steps": 390, "loss": 0.7702, "lr": 8.559187418346703e-06, "epoch": 0.9642857142857143, "percentage": 32.31, "elapsed_time": "1:12:02", "remaining_time": "2:30:55"}
+{"current_steps": 127, "total_steps": 390, "loss": 0.7486, "lr": 8.527613945231886e-06, "epoch": 0.9719387755102041, "percentage": 32.56, "elapsed_time": "1:12:36", "remaining_time": "2:30:21"}
+{"current_steps": 128, "total_steps": 390, "loss": 0.7539, "lr": 8.495757877643857e-06, "epoch": 0.9795918367346939, "percentage": 32.82, "elapsed_time": "1:13:10", "remaining_time": "2:29:46"}
+{"current_steps": 129, "total_steps": 390, "loss": 0.7823, "lr": 8.463621767547998e-06, "epoch": 0.9872448979591837, "percentage": 33.08, "elapsed_time": "1:13:44", "remaining_time": "2:29:11"}
+{"current_steps": 130, "total_steps": 390, "loss": 0.7676, "lr": 8.43120818934367e-06, "epoch": 0.9948979591836735, "percentage": 33.33, "elapsed_time": "1:14:22", "remaining_time": "2:28:44"}
+{"current_steps": 131, "total_steps": 390, "loss": 0.7447, "lr": 8.398519739657997e-06, "epoch": 1.0025510204081634, "percentage": 33.59, "elapsed_time": "1:15:46", "remaining_time": "2:29:49"}
+{"current_steps": 132, "total_steps": 390, "loss": 0.7192, "lr": 8.36555903713785e-06, "epoch": 1.010204081632653, "percentage": 33.85, "elapsed_time": "1:16:20", "remaining_time": "2:29:13"}
+{"current_steps": 133, "total_steps": 390, "loss": 0.7463, "lr": 8.332328722240072e-06, "epoch": 1.0178571428571428, "percentage": 34.1, "elapsed_time": "1:16:55", "remaining_time": "2:28:37"}
+{"current_steps": 134, "total_steps": 390, "loss": 0.7477, "lr": 8.298831457019943e-06, "epoch": 1.0255102040816326, "percentage": 34.36, "elapsed_time": "1:17:29", "remaining_time": "2:28:02"}
+{"current_steps": 135, "total_steps": 390, "loss": 0.7205, "lr": 8.265069924917925e-06, "epoch": 1.0331632653061225, "percentage": 34.62, "elapsed_time": "1:18:03", "remaining_time": "2:27:26"}
+{"current_steps": 136, "total_steps": 390, "loss": 0.74, "lr": 8.231046830544716e-06, "epoch": 1.0408163265306123, "percentage": 34.87, "elapsed_time": "1:18:37", "remaining_time": "2:26:50"}
+{"current_steps": 137, "total_steps": 390, "loss": 0.7269, "lr": 8.196764899464552e-06, "epoch": 1.0484693877551021, "percentage": 35.13, "elapsed_time": "1:19:11", "remaining_time": "2:26:14"}
+{"current_steps": 138, "total_steps": 390, "loss": 0.7554, "lr": 8.162226877976886e-06, "epoch": 1.0561224489795917, "percentage": 35.38, "elapsed_time": "1:19:45", "remaining_time": "2:25:39"}
+{"current_steps": 139, "total_steps": 390, "loss": 0.7288, "lr": 8.127435532896388e-06, "epoch": 1.0637755102040816, "percentage": 35.64, "elapsed_time": "1:20:19", "remaining_time": "2:25:03"}
+{"current_steps": 140, "total_steps": 390, "loss": 0.7355, "lr": 8.092393651331275e-06, "epoch": 1.0714285714285714, "percentage": 35.9, "elapsed_time": "1:20:54", "remaining_time": "2:24:27"}
+{"current_steps": 141, "total_steps": 390, "loss": 0.7385, "lr": 8.057104040460062e-06, "epoch": 1.0790816326530612, "percentage": 36.15, "elapsed_time": "1:21:28", "remaining_time": "2:23:52"}
+{"current_steps": 142, "total_steps": 390, "loss": 0.728, "lr": 8.021569527306663e-06, "epoch": 1.086734693877551, "percentage": 36.41, "elapsed_time": "1:22:02", "remaining_time": "2:23:16"}
+{"current_steps": 143, "total_steps": 390, "loss": 0.7408, "lr": 7.985792958513932e-06, "epoch": 1.094387755102041, "percentage": 36.67, "elapsed_time": "1:22:36", "remaining_time": "2:22:41"}
+{"current_steps": 144, "total_steps": 390, "loss": 0.7227, "lr": 7.949777200115617e-06, "epoch": 1.1020408163265305, "percentage": 36.92, "elapsed_time": "1:23:10", "remaining_time": "2:22:05"}
+{"current_steps": 145, "total_steps": 390, "loss": 0.7287, "lr": 7.913525137306756e-06, "epoch": 1.1096938775510203, "percentage": 37.18, "elapsed_time": "1:23:44", "remaining_time": "2:21:29"}
+{"current_steps": 146, "total_steps": 390, "loss": 0.7258, "lr": 7.877039674212569e-06, "epoch": 1.1173469387755102, "percentage": 37.44, "elapsed_time": "1:24:18", "remaining_time": "2:20:54"}
+{"current_steps": 147, "total_steps": 390, "loss": 0.7262, "lr": 7.84032373365578e-06, "epoch": 1.125, "percentage": 37.69, "elapsed_time": "1:24:54", "remaining_time": "2:20:21"}
+{"current_steps": 148, "total_steps": 390, "loss": 0.7281, "lr": 7.803380256922495e-06, "epoch": 1.1326530612244898, "percentage": 37.95, "elapsed_time": "1:25:28", "remaining_time": "2:19:45"}
+{"current_steps": 149, "total_steps": 390, "loss": 0.7189, "lr": 7.76621220352657e-06, "epoch": 1.1403061224489797, "percentage": 38.21, "elapsed_time": "1:26:02", "remaining_time": "2:19:10"}
+{"current_steps": 150, "total_steps": 390, "loss": 0.7372, "lr": 7.728822550972523e-06, "epoch": 1.1479591836734695, "percentage": 38.46, "elapsed_time": "1:26:36", "remaining_time": "2:18:34"}
+{"current_steps": 151, "total_steps": 390, "loss": 0.7327, "lr": 7.69121429451702e-06, "epoch": 1.155612244897959, "percentage": 38.72, "elapsed_time": "1:27:10", "remaining_time": "2:17:59"}
+{"current_steps": 152, "total_steps": 390, "loss": 0.7243, "lr": 7.65339044692891e-06, "epoch": 1.163265306122449, "percentage": 38.97, "elapsed_time": "1:27:45", "remaining_time": "2:17:23"}
+{"current_steps": 153, "total_steps": 390, "loss": 0.7132, "lr": 7.615354038247889e-06, "epoch": 1.1709183673469388, "percentage": 39.23, "elapsed_time": "1:28:19", "remaining_time": "2:16:48"}
+{"current_steps": 154, "total_steps": 390, "loss": 0.7136, "lr": 7.577108115541761e-06, "epoch": 1.1785714285714286, "percentage": 39.49, "elapsed_time": "1:28:53", "remaining_time": "2:16:13"}
+{"current_steps": 155, "total_steps": 390, "loss": 0.7423, "lr": 7.53865574266234e-06, "epoch": 1.1862244897959184, "percentage": 39.74, "elapsed_time": "1:29:27", "remaining_time": "2:15:37"}
+{"current_steps": 156, "total_steps": 390, "loss": 0.7194, "lr": 7.500000000000001e-06, "epoch": 1.193877551020408, "percentage": 40.0, "elapsed_time": "1:30:01", "remaining_time": "2:15:02"}
+{"current_steps": 157, "total_steps": 390, "loss": 0.7152, "lr": 7.461143984236925e-06, "epoch": 1.2015306122448979, "percentage": 40.26, "elapsed_time": "1:30:35", "remaining_time": "2:14:26"}
+{"current_steps": 158, "total_steps": 390, "loss": 0.7164, "lr": 7.422090808099014e-06, "epoch": 1.2091836734693877, "percentage": 40.51, "elapsed_time": "1:31:09", "remaining_time": "2:13:51"}
+{"current_steps": 159, "total_steps": 390, "loss": 0.7232, "lr": 7.382843600106539e-06, "epoch": 1.2168367346938775, "percentage": 40.77, "elapsed_time": "1:31:43", "remaining_time": "2:13:16"}
+{"current_steps": 160, "total_steps": 390, "loss": 0.7306, "lr": 7.343405504323519e-06, "epoch": 1.2244897959183674, "percentage": 41.03, "elapsed_time": "1:32:17", "remaining_time": "2:12:40"}
+{"current_steps": 161, "total_steps": 390, "loss": 0.7252, "lr": 7.303779680105844e-06, "epoch": 1.2321428571428572, "percentage": 41.28, "elapsed_time": "1:32:52", "remaining_time": "2:12:05"}
+{"current_steps": 162, "total_steps": 390, "loss": 0.7401, "lr": 7.263969301848188e-06, "epoch": 1.239795918367347, "percentage": 41.54, "elapsed_time": "1:33:26", "remaining_time": "2:11:30"}
+{"current_steps": 163, "total_steps": 390, "loss": 0.7235, "lr": 7.223977558729707e-06, "epoch": 1.2474489795918366, "percentage": 41.79, "elapsed_time": "1:34:00", "remaining_time": "2:10:54"}
+{"current_steps": 164, "total_steps": 390, "loss": 0.7269, "lr": 7.183807654458565e-06, "epoch": 1.2551020408163265, "percentage": 42.05, "elapsed_time": "1:34:34", "remaining_time": "2:10:19"}
+{"current_steps": 165, "total_steps": 390, "loss": 0.7314, "lr": 7.143462807015271e-06, "epoch": 1.2627551020408163, "percentage": 42.31, "elapsed_time": "1:35:08", "remaining_time": "2:09:44"}
+{"current_steps": 166, "total_steps": 390, "loss": 0.7311, "lr": 7.102946248394908e-06, "epoch": 1.2704081632653061, "percentage": 42.56, "elapsed_time": "1:35:42", "remaining_time": "2:09:09"}
+{"current_steps": 167, "total_steps": 390, "loss": 0.7454, "lr": 7.0622612243482035e-06, "epoch": 1.278061224489796, "percentage": 42.82, "elapsed_time": "1:36:16", "remaining_time": "2:08:33"}
+{"current_steps": 168, "total_steps": 390, "loss": 0.716, "lr": 7.021410994121525e-06, "epoch": 1.2857142857142856, "percentage": 43.08, "elapsed_time": "1:38:43", "remaining_time": "2:10:27"}
+{"current_steps": 169, "total_steps": 390, "loss": 0.7227, "lr": 6.980398830195785e-06, "epoch": 1.2933673469387754, "percentage": 43.33, "elapsed_time": "1:39:17", "remaining_time": "2:09:50"}
+{"current_steps": 170, "total_steps": 390, "loss": 0.7334, "lr": 6.939228018024275e-06, "epoch": 1.3010204081632653, "percentage": 43.59, "elapsed_time": "1:39:51", "remaining_time": "2:09:14"}
+{"current_steps": 171, "total_steps": 390, "loss": 0.7138, "lr": 6.897901855769483e-06, "epoch": 1.308673469387755, "percentage": 43.85, "elapsed_time": "1:40:25", "remaining_time": "2:08:37"}
+{"current_steps": 172, "total_steps": 390, "loss": 0.7267, "lr": 6.856423654038868e-06, "epoch": 1.316326530612245, "percentage": 44.1, "elapsed_time": "1:40:59", "remaining_time": "2:08:00"}
+{"current_steps": 173, "total_steps": 390, "loss": 0.7144, "lr": 6.814796735619664e-06, "epoch": 1.3239795918367347, "percentage": 44.36, "elapsed_time": "1:41:34", "remaining_time": "2:07:24"}
+{"current_steps": 174, "total_steps": 390, "loss": 0.7139, "lr": 6.773024435212678e-06, "epoch": 1.3316326530612246, "percentage": 44.62, "elapsed_time": "1:42:08", "remaining_time": "2:06:47"}
+{"current_steps": 175, "total_steps": 390, "loss": 0.7417, "lr": 6.731110099165165e-06, "epoch": 1.3392857142857144, "percentage": 44.87, "elapsed_time": "1:42:42", "remaining_time": "2:06:10"}
+{"current_steps": 176, "total_steps": 390, "loss": 0.7292, "lr": 6.689057085202737e-06, "epoch": 1.346938775510204, "percentage": 45.13, "elapsed_time": "1:43:16", "remaining_time": "2:05:34"}
+{"current_steps": 177, "total_steps": 390, "loss": 0.7169, "lr": 6.646868762160399e-06, "epoch": 1.3545918367346939, "percentage": 45.38, "elapsed_time": "1:43:50", "remaining_time": "2:04:57"}
+{"current_steps": 178, "total_steps": 390, "loss": 0.723, "lr": 6.6045485097126585e-06, "epoch": 1.3622448979591837, "percentage": 45.64, "elapsed_time": "1:44:24", "remaining_time": "2:04:21"}
+{"current_steps": 179, "total_steps": 390, "loss": 0.7111, "lr": 6.562099718102788e-06, "epoch": 1.3698979591836735, "percentage": 45.9, "elapsed_time": "1:44:58", "remaining_time": "2:03:44"}
+{"current_steps": 180, "total_steps": 390, "loss": 0.728, "lr": 6.519525787871235e-06, "epoch": 1.3775510204081631, "percentage": 46.15, "elapsed_time": "1:45:32", "remaining_time": "2:03:08"}
+{"current_steps": 181, "total_steps": 390, "loss": 0.7136, "lr": 6.476830129583207e-06, "epoch": 1.385204081632653, "percentage": 46.41, "elapsed_time": "1:46:06", "remaining_time": "2:02:31"}
+{"current_steps": 182, "total_steps": 390, "loss": 0.7229, "lr": 6.434016163555452e-06, "epoch": 1.3928571428571428, "percentage": 46.67, "elapsed_time": "1:46:40", "remaining_time": "2:01:55"}
+{"current_steps": 183, "total_steps": 390, "loss": 0.7329, "lr": 6.391087319582264e-06, "epoch": 1.4005102040816326, "percentage": 46.92, "elapsed_time": "1:47:14", "remaining_time": "2:01:18"}
+{"current_steps": 184, "total_steps": 390, "loss": 0.6948, "lr": 6.34804703666072e-06, "epoch": 1.4081632653061225, "percentage": 47.18, "elapsed_time": "1:47:49", "remaining_time": "2:00:42"}
+{"current_steps": 185, "total_steps": 390, "loss": 0.7185, "lr": 6.304898762715187e-06, "epoch": 1.4158163265306123, "percentage": 47.44, "elapsed_time": "1:48:23", "remaining_time": "2:00:06"}
+{"current_steps": 186, "total_steps": 390, "loss": 0.7155, "lr": 6.261645954321109e-06, "epoch": 1.4234693877551021, "percentage": 47.69, "elapsed_time": "1:48:57", "remaining_time": "1:59:30"}
+{"current_steps": 187, "total_steps": 390, "loss": 0.72, "lr": 6.21829207642811e-06, "epoch": 1.431122448979592, "percentage": 47.95, "elapsed_time": "1:49:31", "remaining_time": "1:58:53"}
+{"current_steps": 188, "total_steps": 390, "loss": 0.7215, "lr": 6.1748406020824115e-06, "epoch": 1.4387755102040816, "percentage": 48.21, "elapsed_time": "1:50:05", "remaining_time": "1:58:17"}
+{"current_steps": 189, "total_steps": 390, "loss": 0.7161, "lr": 6.131295012148613e-06, "epoch": 1.4464285714285714, "percentage": 48.46, "elapsed_time": "1:50:39", "remaining_time": "1:57:41"}
+{"current_steps": 190, "total_steps": 390, "loss": 0.7212, "lr": 6.087658795030838e-06, "epoch": 1.4540816326530612, "percentage": 48.72, "elapsed_time": "1:51:17", "remaining_time": "1:57:09"}
+{"current_steps": 191, "total_steps": 390, "loss": 0.7138, "lr": 6.043935446393294e-06, "epoch": 1.461734693877551, "percentage": 48.97, "elapsed_time": "1:51:51", "remaining_time": "1:56:32"}
+{"current_steps": 192, "total_steps": 390, "loss": 0.7357, "lr": 6.000128468880223e-06, "epoch": 1.469387755102041, "percentage": 49.23, "elapsed_time": "1:52:25", "remaining_time": "1:55:56"}
+{"current_steps": 193, "total_steps": 390, "loss": 0.7329, "lr": 5.956241371835312e-06, "epoch": 1.4770408163265305, "percentage": 49.49, "elapsed_time": "1:52:59", "remaining_time": "1:55:20"}
+{"current_steps": 194, "total_steps": 390, "loss": 0.7301, "lr": 5.912277671020564e-06, "epoch": 1.4846938775510203, "percentage": 49.74, "elapsed_time": "1:53:34", "remaining_time": "1:54:44"}
+{"current_steps": 195, "total_steps": 390, "loss": 0.6932, "lr": 5.8682408883346535e-06, "epoch": 1.4923469387755102, "percentage": 50.0, "elapsed_time": "1:54:08", "remaining_time": "1:54:08"}
+{"current_steps": 196, "total_steps": 390, "loss": 0.7326, "lr": 5.824134551530783e-06, "epoch": 1.5, "percentage": 50.26, "elapsed_time": "1:54:42", "remaining_time": "1:53:32"}
+{"current_steps": 197, "total_steps": 390, "loss": 0.7195, "lr": 5.77996219393409e-06, "epoch": 1.5076530612244898, "percentage": 50.51, "elapsed_time": "1:55:16", "remaining_time": "1:52:55"}
+{"current_steps": 198, "total_steps": 390, "loss": 0.7353, "lr": 5.735727354158581e-06, "epoch": 1.5153061224489797, "percentage": 50.77, "elapsed_time": "1:55:50", "remaining_time": "1:52:19"}
+{"current_steps": 199, "total_steps": 390, "loss": 0.7262, "lr": 5.6914335758236665e-06, "epoch": 1.5229591836734695, "percentage": 51.03, "elapsed_time": "1:56:24", "remaining_time": "1:51:43"}
+{"current_steps": 200, "total_steps": 390, "loss": 0.725, "lr": 5.647084407270277e-06, "epoch": 1.5306122448979593, "percentage": 51.28, "elapsed_time": "1:56:58", "remaining_time": "1:51:07"}
+{"current_steps": 201, "total_steps": 390, "loss": 0.717, "lr": 5.6026834012766155e-06, "epoch": 1.538265306122449, "percentage": 51.54, "elapsed_time": "1:57:32", "remaining_time": "1:50:31"}
+{"current_steps": 202, "total_steps": 390, "loss": 0.7134, "lr": 5.5582341147735396e-06, "epoch": 1.5459183673469388, "percentage": 51.79, "elapsed_time": "1:58:06", "remaining_time": "1:49:55"}
+{"current_steps": 203, "total_steps": 390, "loss": 0.7334, "lr": 5.5137401085596224e-06, "epoch": 1.5535714285714286, "percentage": 52.05, "elapsed_time": "1:58:41", "remaining_time": "1:49:19"}
+{"current_steps": 204, "total_steps": 390, "loss": 0.7189, "lr": 5.469204947015897e-06, "epoch": 1.5612244897959182, "percentage": 52.31, "elapsed_time": "1:59:15", "remaining_time": "1:48:43"}
+{"current_steps": 205, "total_steps": 390, "loss": 0.6947, "lr": 5.424632197820325e-06, "epoch": 1.568877551020408, "percentage": 52.56, "elapsed_time": "1:59:49", "remaining_time": "1:48:07"}
+{"current_steps": 206, "total_steps": 390, "loss": 0.7146, "lr": 5.380025431661981e-06, "epoch": 1.5765306122448979, "percentage": 52.82, "elapsed_time": "2:00:23", "remaining_time": "1:47:31"}
+{"current_steps": 207, "total_steps": 390, "loss": 0.7131, "lr": 5.335388221955012e-06, "epoch": 1.5841836734693877, "percentage": 53.08, "elapsed_time": "2:00:57", "remaining_time": "1:46:56"}
+{"current_steps": 208, "total_steps": 390, "loss": 0.7221, "lr": 5.290724144552379e-06, "epoch": 1.5918367346938775, "percentage": 53.33, "elapsed_time": "2:01:31", "remaining_time": "1:46:20"}
+{"current_steps": 209, "total_steps": 390, "loss": 0.7141, "lr": 5.246036777459391e-06, "epoch": 1.5994897959183674, "percentage": 53.59, "elapsed_time": "2:02:05", "remaining_time": "1:45:44"}
+{"current_steps": 210, "total_steps": 390, "loss": 0.7154, "lr": 5.201329700547077e-06, "epoch": 1.6071428571428572, "percentage": 53.85, "elapsed_time": "2:02:39", "remaining_time": "1:45:08"}
+{"current_steps": 211, "total_steps": 390, "loss": 0.7185, "lr": 5.156606495265402e-06, "epoch": 1.614795918367347, "percentage": 54.1, "elapsed_time": "2:03:13", "remaining_time": "1:44:32"}
+{"current_steps": 212, "total_steps": 390, "loss": 0.6954, "lr": 5.111870744356366e-06, "epoch": 1.6224489795918369, "percentage": 54.36, "elapsed_time": "2:03:48", "remaining_time": "1:43:56"}
+{"current_steps": 213, "total_steps": 390, "loss": 0.7199, "lr": 5.067126031566988e-06, "epoch": 1.6301020408163265, "percentage": 54.62, "elapsed_time": "2:04:22", "remaining_time": "1:43:20"}
+{"current_steps": 214, "total_steps": 390, "loss": 0.7206, "lr": 5.022375941362218e-06, "epoch": 1.6377551020408163, "percentage": 54.87, "elapsed_time": "2:04:56", "remaining_time": "1:42:45"}
+{"current_steps": 215, "total_steps": 390, "loss": 0.7104, "lr": 4.977624058637783e-06, "epoch": 1.6454081632653061, "percentage": 55.13, "elapsed_time": "2:05:30", "remaining_time": "1:42:09"}
+{"current_steps": 216, "total_steps": 390, "loss": 0.7214, "lr": 4.932873968433014e-06, "epoch": 1.6530612244897958, "percentage": 55.38, "elapsed_time": "2:06:04", "remaining_time": "1:41:33"}
+{"current_steps": 217, "total_steps": 390, "loss": 0.7157, "lr": 4.8881292556436355e-06, "epoch": 1.6607142857142856, "percentage": 55.64, "elapsed_time": "2:06:38", "remaining_time": "1:40:57"}
+{"current_steps": 218, "total_steps": 390, "loss": 0.7129, "lr": 4.8433935047346e-06, "epoch": 1.6683673469387754, "percentage": 55.9, "elapsed_time": "2:07:12", "remaining_time": "1:40:22"}
+{"current_steps": 219, "total_steps": 390, "loss": 0.7228, "lr": 4.798670299452926e-06, "epoch": 1.6760204081632653, "percentage": 56.15, "elapsed_time": "2:07:46", "remaining_time": "1:39:46"}
+{"current_steps": 220, "total_steps": 390, "loss": 0.7329, "lr": 4.75396322254061e-06, "epoch": 1.683673469387755, "percentage": 56.41, "elapsed_time": "2:08:21", "remaining_time": "1:39:10"}
+{"current_steps": 221, "total_steps": 390, "loss": 0.714, "lr": 4.7092758554476215e-06, "epoch": 1.691326530612245, "percentage": 56.67, "elapsed_time": "2:08:55", "remaining_time": "1:38:35"}
+{"current_steps": 222, "total_steps": 390, "loss": 0.7269, "lr": 4.664611778044988e-06, "epoch": 1.6989795918367347, "percentage": 56.92, "elapsed_time": "2:09:29", "remaining_time": "1:37:59"}
+{"current_steps": 223, "total_steps": 390, "loss": 0.7254, "lr": 4.619974568338021e-06, "epoch": 1.7066326530612246, "percentage": 57.18, "elapsed_time": "2:10:03", "remaining_time": "1:37:23"}
+{"current_steps": 224, "total_steps": 390, "loss": 0.7266, "lr": 4.575367802179675e-06, "epoch": 1.7142857142857144, "percentage": 57.44, "elapsed_time": "2:10:37", "remaining_time": "1:36:48"}
+{"current_steps": 225, "total_steps": 390, "loss": 0.7402, "lr": 4.530795052984104e-06, "epoch": 1.7219387755102042, "percentage": 57.69, "elapsed_time": "2:11:11", "remaining_time": "1:36:12"}
+{"current_steps": 226, "total_steps": 390, "loss": 0.7165, "lr": 4.48625989144038e-06, "epoch": 1.7295918367346939, "percentage": 57.95, "elapsed_time": "2:11:45", "remaining_time": "1:35:36"}
+{"current_steps": 227, "total_steps": 390, "loss": 0.7233, "lr": 4.441765885226462e-06, "epoch": 1.7372448979591837, "percentage": 58.21, "elapsed_time": "2:12:19", "remaining_time": "1:35:01"}
+{"current_steps": 228, "total_steps": 390, "loss": 0.729, "lr": 4.397316598723385e-06, "epoch": 1.7448979591836735, "percentage": 58.46, "elapsed_time": "2:12:54", "remaining_time": "1:34:25"}
+{"current_steps": 229, "total_steps": 390, "loss": 0.7242, "lr": 4.352915592729723e-06, "epoch": 1.7525510204081631, "percentage": 58.72, "elapsed_time": "2:13:28", "remaining_time": "1:33:50"}
+{"current_steps": 230, "total_steps": 390, "loss": 0.7154, "lr": 4.308566424176336e-06, "epoch": 1.760204081632653, "percentage": 58.97, "elapsed_time": "2:14:02", "remaining_time": "1:33:14"}
+{"current_steps": 231, "total_steps": 390, "loss": 0.7079, "lr": 4.264272645841419e-06, "epoch": 1.7678571428571428, "percentage": 59.23, "elapsed_time": "2:14:36", "remaining_time": "1:32:39"}
+{"current_steps": 232, "total_steps": 390, "loss": 0.727, "lr": 4.220037806065911e-06, "epoch": 1.7755102040816326, "percentage": 59.49, "elapsed_time": "2:15:10", "remaining_time": "1:32:03"}
+{"current_steps": 233, "total_steps": 390, "loss": 0.7284, "lr": 4.175865448469219e-06, "epoch": 1.7831632653061225, "percentage": 59.74, "elapsed_time": "2:15:44", "remaining_time": "1:31:28"}
+{"current_steps": 234, "total_steps": 390, "loss": 0.7228, "lr": 4.131759111665349e-06, "epoch": 1.7908163265306123, "percentage": 60.0, "elapsed_time": "2:16:22", "remaining_time": "1:30:55"}
+{"current_steps": 235, "total_steps": 390, "loss": 0.7248, "lr": 4.087722328979437e-06, "epoch": 1.7984693877551021, "percentage": 60.26, "elapsed_time": "2:16:56", "remaining_time": "1:30:19"}
+{"current_steps": 236, "total_steps": 390, "loss": 0.7276, "lr": 4.043758628164688e-06, "epoch": 1.806122448979592, "percentage": 60.51, "elapsed_time": "2:17:30", "remaining_time": "1:29:44"}
+{"current_steps": 237, "total_steps": 390, "loss": 0.7172, "lr": 3.999871531119779e-06, "epoch": 1.8137755102040818, "percentage": 60.77, "elapsed_time": "2:18:04", "remaining_time": "1:29:08"}
+{"current_steps": 238, "total_steps": 390, "loss": 0.7096, "lr": 3.956064553606708e-06, "epoch": 1.8214285714285714, "percentage": 61.03, "elapsed_time": "2:18:39", "remaining_time": "1:28:33"}
+{"current_steps": 239, "total_steps": 390, "loss": 0.7085, "lr": 3.912341204969164e-06, "epoch": 1.8290816326530612, "percentage": 61.28, "elapsed_time": "2:19:13", "remaining_time": "1:27:57"}
+{"current_steps": 240, "total_steps": 390, "loss": 0.7079, "lr": 3.86870498785139e-06, "epoch": 1.836734693877551, "percentage": 61.54, "elapsed_time": "2:19:47", "remaining_time": "1:27:22"}
+{"current_steps": 241, "total_steps": 390, "loss": 0.7196, "lr": 3.825159397917589e-06, "epoch": 1.8443877551020407, "percentage": 61.79, "elapsed_time": "2:20:21", "remaining_time": "1:26:46"}
+{"current_steps": 242, "total_steps": 390, "loss": 0.7026, "lr": 3.781707923571891e-06, "epoch": 1.8520408163265305, "percentage": 62.05, "elapsed_time": "2:20:55", "remaining_time": "1:26:11"}
+{"current_steps": 243, "total_steps": 390, "loss": 0.7268, "lr": 3.7383540456788915e-06, "epoch": 1.8596938775510203, "percentage": 62.31, "elapsed_time": "2:21:29", "remaining_time": "1:25:35"}
+{"current_steps": 244, "total_steps": 390, "loss": 0.7248, "lr": 3.695101237284815e-06, "epoch": 1.8673469387755102, "percentage": 62.56, "elapsed_time": "2:22:03", "remaining_time": "1:25:00"}
+{"current_steps": 245, "total_steps": 390, "loss": 0.7084, "lr": 3.6519529633392825e-06, "epoch": 1.875, "percentage": 62.82, "elapsed_time": "2:22:37", "remaining_time": "1:24:24"}
+{"current_steps": 246, "total_steps": 390, "loss": 0.7355, "lr": 3.6089126804177373e-06, "epoch": 1.8826530612244898, "percentage": 63.08, "elapsed_time": "2:23:12", "remaining_time": "1:23:49"}
+{"current_steps": 247, "total_steps": 390, "loss": 0.7243, "lr": 3.5659838364445505e-06, "epoch": 1.8903061224489797, "percentage": 63.33, "elapsed_time": "2:23:46", "remaining_time": "1:23:14"}
+{"current_steps": 248, "total_steps": 390, "loss": 0.7144, "lr": 3.523169870416795e-06, "epoch": 1.8979591836734695, "percentage": 63.59, "elapsed_time": "2:24:20", "remaining_time": "1:22:38"}
+{"current_steps": 249, "total_steps": 390, "loss": 0.7085, "lr": 3.480474212128766e-06, "epoch": 1.9056122448979593, "percentage": 63.85, "elapsed_time": "2:24:54", "remaining_time": "1:22:03"}
+{"current_steps": 250, "total_steps": 390, "loss": 0.6994, "lr": 3.4379002818972122e-06, "epoch": 1.913265306122449, "percentage": 64.1, "elapsed_time": "2:25:28", "remaining_time": "1:21:27"}
+{"current_steps": 251, "total_steps": 390, "loss": 0.7198, "lr": 3.3954514902873427e-06, "epoch": 1.9209183673469388, "percentage": 64.36, "elapsed_time": "2:26:02", "remaining_time": "1:20:52"}
+{"current_steps": 252, "total_steps": 390, "loss": 0.7195, "lr": 3.3531312378396026e-06, "epoch": 1.9285714285714286, "percentage": 64.62, "elapsed_time": "2:26:36", "remaining_time": "1:20:17"}
+{"current_steps": 253, "total_steps": 390, "loss": 0.7221, "lr": 3.310942914797265e-06, "epoch": 1.9362244897959182, "percentage": 64.87, "elapsed_time": "2:27:10", "remaining_time": "1:19:41"}
+{"current_steps": 254, "total_steps": 390, "loss": 0.7098, "lr": 3.2688899008348386e-06, "epoch": 1.943877551020408, "percentage": 65.13, "elapsed_time": "2:27:44", "remaining_time": "1:19:06"}
+{"current_steps": 255, "total_steps": 390, "loss": 0.715, "lr": 3.226975564787322e-06, "epoch": 1.9515306122448979, "percentage": 65.38, "elapsed_time": "2:28:19", "remaining_time": "1:18:31"}
+{"current_steps": 256, "total_steps": 390, "loss": 0.7115, "lr": 3.1852032643803377e-06, "epoch": 1.9591836734693877, "percentage": 65.64, "elapsed_time": "2:28:53", "remaining_time": "1:17:55"}
+{"current_steps": 257, "total_steps": 390, "loss": 0.7108, "lr": 3.143576345961132e-06, "epoch": 1.9668367346938775, "percentage": 65.9, "elapsed_time": "2:29:27", "remaining_time": "1:17:20"}
+{"current_steps": 258, "total_steps": 390, "loss": 0.7177, "lr": 3.1020981442305187e-06, "epoch": 1.9744897959183674, "percentage": 66.15, "elapsed_time": "2:30:01", "remaining_time": "1:16:45"}
+{"current_steps": 259, "total_steps": 390, "loss": 0.714, "lr": 3.0607719819757264e-06, "epoch": 1.9821428571428572, "percentage": 66.41, "elapsed_time": "2:30:35", "remaining_time": "1:16:10"}
+{"current_steps": 260, "total_steps": 390, "loss": 0.6937, "lr": 3.019601169804216e-06, "epoch": 1.989795918367347, "percentage": 66.67, "elapsed_time": "2:31:09", "remaining_time": "1:15:34"}
+{"current_steps": 261, "total_steps": 390, "loss": 0.728, "lr": 2.978589005878476e-06, "epoch": 1.9974489795918369, "percentage": 66.92, "elapsed_time": "2:31:43", "remaining_time": "1:14:59"}
+{"current_steps": 262, "total_steps": 390, "loss": 0.712, "lr": 2.937738775651798e-06, "epoch": 2.0051020408163267, "percentage": 67.18, "elapsed_time": "2:33:01", "remaining_time": "1:14:45"}
+{"current_steps": 263, "total_steps": 390, "loss": 0.6888, "lr": 2.8970537516050935e-06, "epoch": 2.0127551020408165, "percentage": 67.44, "elapsed_time": "2:33:35", "remaining_time": "1:14:10"}
+{"current_steps": 264, "total_steps": 390, "loss": 0.6857, "lr": 2.8565371929847286e-06, "epoch": 2.020408163265306, "percentage": 67.69, "elapsed_time": "2:34:09", "remaining_time": "1:13:34"}
+{"current_steps": 265, "total_steps": 390, "loss": 0.67, "lr": 2.816192345541437e-06, "epoch": 2.0280612244897958, "percentage": 67.95, "elapsed_time": "2:34:43", "remaining_time": "1:12:59"}
+{"current_steps": 266, "total_steps": 390, "loss": 0.677, "lr": 2.776022441270295e-06, "epoch": 2.0357142857142856, "percentage": 68.21, "elapsed_time": "2:35:17", "remaining_time": "1:12:23"}
+{"current_steps": 267, "total_steps": 390, "loss": 0.6901, "lr": 2.736030698151815e-06, "epoch": 2.0433673469387754, "percentage": 68.46, "elapsed_time": "2:35:52", "remaining_time": "1:11:48"}
+{"current_steps": 268, "total_steps": 390, "loss": 0.6799, "lr": 2.6962203198941587e-06, "epoch": 2.0510204081632653, "percentage": 68.72, "elapsed_time": "2:36:26", "remaining_time": "1:11:12"}
+{"current_steps": 269, "total_steps": 390, "loss": 0.6867, "lr": 2.656594495676482e-06, "epoch": 2.058673469387755, "percentage": 68.97, "elapsed_time": "2:37:00", "remaining_time": "1:10:37"}
+{"current_steps": 270, "total_steps": 390, "loss": 0.6798, "lr": 2.6171563998934605e-06, "epoch": 2.066326530612245, "percentage": 69.23, "elapsed_time": "2:37:34", "remaining_time": "1:10:01"}
+{"current_steps": 271, "total_steps": 390, "loss": 0.6775, "lr": 2.577909191900988e-06, "epoch": 2.0739795918367347, "percentage": 69.49, "elapsed_time": "2:38:08", "remaining_time": "1:09:26"}
+{"current_steps": 272, "total_steps": 390, "loss": 0.687, "lr": 2.5388560157630765e-06, "epoch": 2.0816326530612246, "percentage": 69.74, "elapsed_time": "2:38:42", "remaining_time": "1:08:51"}
+{"current_steps": 273, "total_steps": 390, "loss": 0.6933, "lr": 2.5000000000000015e-06, "epoch": 2.0892857142857144, "percentage": 70.0, "elapsed_time": "2:39:20", "remaining_time": "1:08:17"}
+{"current_steps": 274, "total_steps": 390, "loss": 0.6932, "lr": 2.4613442573376625e-06, "epoch": 2.0969387755102042, "percentage": 70.26, "elapsed_time": "2:39:54", "remaining_time": "1:07:42"}
+{"current_steps": 275, "total_steps": 390, "loss": 0.686, "lr": 2.422891884458241e-06, "epoch": 2.104591836734694, "percentage": 70.51, "elapsed_time": "2:40:28", "remaining_time": "1:07:06"}
+{"current_steps": 276, "total_steps": 390, "loss": 0.6794, "lr": 2.384645961752113e-06, "epoch": 2.1122448979591835, "percentage": 70.77, "elapsed_time": "2:41:03", "remaining_time": "1:06:31"}
+{"current_steps": 277, "total_steps": 390, "loss": 0.6757, "lr": 2.346609553071093e-06, "epoch": 2.1198979591836733, "percentage": 71.03, "elapsed_time": "2:41:37", "remaining_time": "1:05:55"}
+{"current_steps": 278, "total_steps": 390, "loss": 0.6904, "lr": 2.308785705482982e-06, "epoch": 2.127551020408163, "percentage": 71.28, "elapsed_time": "2:42:11", "remaining_time": "1:05:20"}
+{"current_steps": 279, "total_steps": 390, "loss": 0.6816, "lr": 2.2711774490274767e-06, "epoch": 2.135204081632653, "percentage": 71.54, "elapsed_time": "2:42:45", "remaining_time": "1:04:45"}
+{"current_steps": 280, "total_steps": 390, "loss": 0.6798, "lr": 2.2337877964734324e-06, "epoch": 2.142857142857143, "percentage": 71.79, "elapsed_time": "2:43:19", "remaining_time": "1:04:09"}
+{"current_steps": 281, "total_steps": 390, "loss": 0.6861, "lr": 2.1966197430775056e-06, "epoch": 2.1505102040816326, "percentage": 72.05, "elapsed_time": "2:43:53", "remaining_time": "1:03:34"}
+{"current_steps": 282, "total_steps": 390, "loss": 0.6929, "lr": 2.159676266344222e-06, "epoch": 2.1581632653061225, "percentage": 72.31, "elapsed_time": "2:44:27", "remaining_time": "1:02:59"}
+{"current_steps": 283, "total_steps": 390, "loss": 0.6828, "lr": 2.122960325787432e-06, "epoch": 2.1658163265306123, "percentage": 72.56, "elapsed_time": "2:45:01", "remaining_time": "1:02:23"}
+{"current_steps": 284, "total_steps": 390, "loss": 0.6871, "lr": 2.086474862693244e-06, "epoch": 2.173469387755102, "percentage": 72.82, "elapsed_time": "2:45:35", "remaining_time": "1:01:48"}
+{"current_steps": 285, "total_steps": 390, "loss": 0.6799, "lr": 2.050222799884387e-06, "epoch": 2.181122448979592, "percentage": 73.08, "elapsed_time": "2:46:10", "remaining_time": "1:01:13"}
+{"current_steps": 286, "total_steps": 390, "loss": 0.6858, "lr": 2.0142070414860704e-06, "epoch": 2.188775510204082, "percentage": 73.33, "elapsed_time": "2:46:44", "remaining_time": "1:00:37"}
+{"current_steps": 287, "total_steps": 390, "loss": 0.6787, "lr": 1.9784304726933384e-06, "epoch": 2.1964285714285716, "percentage": 73.59, "elapsed_time": "2:47:18", "remaining_time": "1:00:02"}
+{"current_steps": 288, "total_steps": 390, "loss": 0.6994, "lr": 1.942895959539939e-06, "epoch": 2.204081632653061, "percentage": 73.85, "elapsed_time": "2:47:52", "remaining_time": "0:59:27"}
+{"current_steps": 289, "total_steps": 390, "loss": 0.6958, "lr": 1.9076063486687256e-06, "epoch": 2.211734693877551, "percentage": 74.1, "elapsed_time": "2:48:26", "remaining_time": "0:58:52"}
+{"current_steps": 290, "total_steps": 390, "loss": 0.6841, "lr": 1.8725644671036125e-06, "epoch": 2.2193877551020407, "percentage": 74.36, "elapsed_time": "2:49:00", "remaining_time": "0:58:16"}
+{"current_steps": 291, "total_steps": 390, "loss": 0.6817, "lr": 1.8377731220231144e-06, "epoch": 2.2270408163265305, "percentage": 74.62, "elapsed_time": "2:49:40", "remaining_time": "0:57:43"}
+{"current_steps": 292, "total_steps": 390, "loss": 0.6928, "lr": 1.803235100535452e-06, "epoch": 2.2346938775510203, "percentage": 74.87, "elapsed_time": "2:50:14", "remaining_time": "0:57:08"}
+{"current_steps": 293, "total_steps": 390, "loss": 0.6924, "lr": 1.7689531694552863e-06, "epoch": 2.24234693877551, "percentage": 75.13, "elapsed_time": "2:50:48", "remaining_time": "0:56:32"}
+{"current_steps": 294, "total_steps": 390, "loss": 0.7014, "lr": 1.7349300750820758e-06, "epoch": 2.25, "percentage": 75.38, "elapsed_time": "2:51:22", "remaining_time": "0:55:57"}
+{"current_steps": 295, "total_steps": 390, "loss": 0.6829, "lr": 1.7011685429800596e-06, "epoch": 2.25765306122449, "percentage": 75.64, "elapsed_time": "2:51:56", "remaining_time": "0:55:22"}
+{"current_steps": 296, "total_steps": 390, "loss": 0.686, "lr": 1.6676712777599275e-06, "epoch": 2.2653061224489797, "percentage": 75.9, "elapsed_time": "2:52:30", "remaining_time": "0:54:47"}
+{"current_steps": 297, "total_steps": 390, "loss": 0.6977, "lr": 1.6344409628621482e-06, "epoch": 2.2729591836734695, "percentage": 76.15, "elapsed_time": "2:53:04", "remaining_time": "0:54:11"}
+{"current_steps": 298, "total_steps": 390, "loss": 0.6929, "lr": 1.6014802603420044e-06, "epoch": 2.2806122448979593, "percentage": 76.41, "elapsed_time": "2:53:38", "remaining_time": "0:53:36"}
+{"current_steps": 299, "total_steps": 390, "loss": 0.6917, "lr": 1.5687918106563326e-06, "epoch": 2.288265306122449, "percentage": 76.67, "elapsed_time": "2:54:12", "remaining_time": "0:53:01"}
+{"current_steps": 300, "total_steps": 390, "loss": 0.6919, "lr": 1.5363782324520033e-06, "epoch": 2.295918367346939, "percentage": 76.92, "elapsed_time": "2:54:46", "remaining_time": "0:52:26"}
+{"current_steps": 301, "total_steps": 390, "loss": 0.7097, "lr": 1.504242122356143e-06, "epoch": 2.3035714285714284, "percentage": 77.18, "elapsed_time": "2:55:21", "remaining_time": "0:51:50"}
+{"current_steps": 302, "total_steps": 390, "loss": 0.6849, "lr": 1.4723860547681163e-06, "epoch": 2.311224489795918, "percentage": 77.44, "elapsed_time": "2:55:55", "remaining_time": "0:51:15"}
+{"current_steps": 303, "total_steps": 390, "loss": 0.6993, "lr": 1.4408125816532981e-06, "epoch": 2.318877551020408, "percentage": 77.69, "elapsed_time": "2:56:29", "remaining_time": "0:50:40"}
+{"current_steps": 304, "total_steps": 390, "loss": 0.6788, "lr": 1.4095242323386305e-06, "epoch": 2.326530612244898, "percentage": 77.95, "elapsed_time": "2:57:03", "remaining_time": "0:50:05"}
+{"current_steps": 305, "total_steps": 390, "loss": 0.6905, "lr": 1.3785235133100088e-06, "epoch": 2.3341836734693877, "percentage": 78.21, "elapsed_time": "2:57:37", "remaining_time": "0:49:30"}
+{"current_steps": 306, "total_steps": 390, "loss": 0.6841, "lr": 1.347812908011485e-06, "epoch": 2.3418367346938775, "percentage": 78.46, "elapsed_time": "2:58:11", "remaining_time": "0:48:54"}
+{"current_steps": 307, "total_steps": 390, "loss": 0.6802, "lr": 1.3173948766463146e-06, "epoch": 2.3494897959183674, "percentage": 78.72, "elapsed_time": "2:58:45", "remaining_time": "0:48:19"}
+{"current_steps": 308, "total_steps": 390, "loss": 0.6886, "lr": 1.2872718559798852e-06, "epoch": 2.357142857142857, "percentage": 78.97, "elapsed_time": "2:59:19", "remaining_time": "0:47:44"}
+{"current_steps": 309, "total_steps": 390, "loss": 0.6868, "lr": 1.257446259144494e-06, "epoch": 2.364795918367347, "percentage": 79.23, "elapsed_time": "2:59:53", "remaining_time": "0:47:09"}
+{"current_steps": 310, "total_steps": 390, "loss": 0.6941, "lr": 1.2279204754460494e-06, "epoch": 2.372448979591837, "percentage": 79.49, "elapsed_time": "3:00:27", "remaining_time": "0:46:34"}
+{"current_steps": 311, "total_steps": 390, "loss": 0.6915, "lr": 1.1986968701726492e-06, "epoch": 2.3801020408163267, "percentage": 79.74, "elapsed_time": "3:01:02", "remaining_time": "0:45:59"}
+{"current_steps": 312, "total_steps": 390, "loss": 0.6921, "lr": 1.1697777844051105e-06, "epoch": 2.387755102040816, "percentage": 80.0, "elapsed_time": "3:01:36", "remaining_time": "0:45:24"}
+{"current_steps": 313, "total_steps": 390, "loss": 0.6893, "lr": 1.141165534829425e-06, "epoch": 2.395408163265306, "percentage": 80.26, "elapsed_time": "3:02:10", "remaining_time": "0:44:48"}
+{"current_steps": 314, "total_steps": 390, "loss": 0.6731, "lr": 1.1128624135511712e-06, "epoch": 2.4030612244897958, "percentage": 80.51, "elapsed_time": "3:02:44", "remaining_time": "0:44:13"}
+{"current_steps": 315, "total_steps": 390, "loss": 0.6969, "lr": 1.0848706879118893e-06, "epoch": 2.4107142857142856, "percentage": 80.77, "elapsed_time": "3:03:18", "remaining_time": "0:43:38"}
+{"current_steps": 316, "total_steps": 390, "loss": 0.6955, "lr": 1.057192600307456e-06, "epoch": 2.4183673469387754, "percentage": 81.03, "elapsed_time": "3:03:52", "remaining_time": "0:43:03"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.6896, "lr": 1.0298303680084448e-06, "epoch": 2.4260204081632653, "percentage": 81.28, "elapsed_time": "3:04:26", "remaining_time": "0:42:28"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.6819, "lr": 1.0027861829824953e-06, "epoch": 2.433673469387755, "percentage": 81.54, "elapsed_time": "3:05:00", "remaining_time": "0:41:53"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.6786, "lr": 9.760622117187234e-07, "epoch": 2.441326530612245, "percentage": 81.79, "elapsed_time": "3:05:36", "remaining_time": "0:41:18"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.7039, "lr": 9.496605950541676e-07, "epoch": 2.4489795918367347, "percentage": 82.05, "elapsed_time": "3:06:10", "remaining_time": "0:40:43"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.688, "lr": 9.235834480022788e-07, "epoch": 2.4566326530612246, "percentage": 82.31, "elapsed_time": "3:06:44", "remaining_time": "0:40:08"}
+{"current_steps": 322, "total_steps": 390, "loss": 0.7044, "lr": 8.978328595834984e-07, "epoch": 2.4642857142857144, "percentage": 82.56, "elapsed_time": "3:07:18", "remaining_time": "0:39:33"}
+{"current_steps": 323, "total_steps": 390, "loss": 0.6872, "lr": 8.724108926579e-07, "epoch": 2.4719387755102042, "percentage": 82.82, "elapsed_time": "3:07:52", "remaining_time": "0:38:58"}
+{"current_steps": 324, "total_steps": 390, "loss": 0.6916, "lr": 8.473195837599419e-07, "epoch": 2.479591836734694, "percentage": 83.08, "elapsed_time": "3:08:26", "remaining_time": "0:38:23"}
+{"current_steps": 325, "total_steps": 390, "loss": 0.684, "lr": 8.225609429353187e-07, "epoch": 2.487244897959184, "percentage": 83.33, "elapsed_time": "3:09:00", "remaining_time": "0:37:48"}
+{"current_steps": 326, "total_steps": 390, "loss": 0.6879, "lr": 7.981369535799354e-07, "epoch": 2.4948979591836733, "percentage": 83.59, "elapsed_time": "3:09:34", "remaining_time": "0:37:13"}
+{"current_steps": 327, "total_steps": 390, "loss": 0.7039, "lr": 7.740495722810271e-07, "epoch": 2.502551020408163, "percentage": 83.85, "elapsed_time": "3:10:09", "remaining_time": "0:36:38"}
+{"current_steps": 328, "total_steps": 390, "loss": 0.6929, "lr": 7.50300728660407e-07, "epoch": 2.510204081632653, "percentage": 84.1, "elapsed_time": "3:10:43", "remaining_time": "0:36:03"}
+{"current_steps": 329, "total_steps": 390, "loss": 0.6959, "lr": 7.26892325219899e-07, "epoch": 2.517857142857143, "percentage": 84.36, "elapsed_time": "3:11:17", "remaining_time": "0:35:27"}
+{"current_steps": 330, "total_steps": 390, "loss": 0.675, "lr": 7.03826237188916e-07, "epoch": 2.5255102040816326, "percentage": 84.62, "elapsed_time": "3:11:51", "remaining_time": "0:34:52"}
+{"current_steps": 331, "total_steps": 390, "loss": 0.6977, "lr": 6.811043123742494e-07, "epoch": 2.5331632653061225, "percentage": 84.87, "elapsed_time": "3:12:25", "remaining_time": "0:34:17"}
+{"current_steps": 332, "total_steps": 390, "loss": 0.6749, "lr": 6.587283710120324e-07, "epoch": 2.5408163265306123, "percentage": 85.13, "elapsed_time": "3:12:59", "remaining_time": "0:33:42"}
+{"current_steps": 333, "total_steps": 390, "loss": 0.6909, "lr": 6.367002056219285e-07, "epoch": 2.548469387755102, "percentage": 85.38, "elapsed_time": "3:13:33", "remaining_time": "0:33:07"}
+{"current_steps": 334, "total_steps": 390, "loss": 0.6832, "lr": 6.150215808635334e-07, "epoch": 2.556122448979592, "percentage": 85.64, "elapsed_time": "3:14:07", "remaining_time": "0:32:32"}
+{"current_steps": 335, "total_steps": 390, "loss": 0.6746, "lr": 5.936942333950063e-07, "epoch": 2.563775510204082, "percentage": 85.9, "elapsed_time": "3:14:41", "remaining_time": "0:31:57"}
+{"current_steps": 336, "total_steps": 390, "loss": 0.6866, "lr": 5.727198717339511e-07, "epoch": 2.571428571428571, "percentage": 86.15, "elapsed_time": "3:15:16", "remaining_time": "0:31:22"}
+{"current_steps": 337, "total_steps": 390, "loss": 0.6995, "lr": 5.521001761205441e-07, "epoch": 2.579081632653061, "percentage": 86.41, "elapsed_time": "3:15:50", "remaining_time": "0:30:47"}
+{"current_steps": 338, "total_steps": 390, "loss": 0.6785, "lr": 5.318367983829393e-07, "epoch": 2.586734693877551, "percentage": 86.67, "elapsed_time": "3:16:24", "remaining_time": "0:30:12"}
+{"current_steps": 339, "total_steps": 390, "loss": 0.6965, "lr": 5.119313618049309e-07, "epoch": 2.5943877551020407, "percentage": 86.92, "elapsed_time": "3:16:58", "remaining_time": "0:29:37"}
+{"current_steps": 340, "total_steps": 390, "loss": 0.6799, "lr": 4.9238546099592e-07, "epoch": 2.6020408163265305, "percentage": 87.18, "elapsed_time": "3:17:32", "remaining_time": "0:29:03"}
+{"current_steps": 341, "total_steps": 390, "loss": 0.6705, "lr": 4.732006617631729e-07, "epoch": 2.6096938775510203, "percentage": 87.44, "elapsed_time": "3:18:06", "remaining_time": "0:28:28"}
+{"current_steps": 342, "total_steps": 390, "loss": 0.6899, "lr": 4.54378500986381e-07, "epoch": 2.61734693877551, "percentage": 87.69, "elapsed_time": "3:18:40", "remaining_time": "0:27:53"}
+{"current_steps": 343, "total_steps": 390, "loss": 0.6735, "lr": 4.35920486494546e-07, "epoch": 2.625, "percentage": 87.95, "elapsed_time": "3:19:14", "remaining_time": "0:27:18"}
+{"current_steps": 344, "total_steps": 390, "loss": 0.691, "lr": 4.1782809694518533e-07, "epoch": 2.63265306122449, "percentage": 88.21, "elapsed_time": "3:19:48", "remaining_time": "0:26:43"}
+{"current_steps": 345, "total_steps": 390, "loss": 0.6862, "lr": 4.001027817058789e-07, "epoch": 2.6403061224489797, "percentage": 88.46, "elapsed_time": "3:20:22", "remaining_time": "0:26:08"}
+{"current_steps": 346, "total_steps": 390, "loss": 0.6863, "lr": 3.8274596073816784e-07, "epoch": 2.6479591836734695, "percentage": 88.72, "elapsed_time": "3:20:57", "remaining_time": "0:25:33"}
+{"current_steps": 347, "total_steps": 390, "loss": 0.6849, "lr": 3.657590244837911e-07, "epoch": 2.6556122448979593, "percentage": 88.97, "elapsed_time": "3:21:31", "remaining_time": "0:24:58"}
+{"current_steps": 348, "total_steps": 390, "loss": 0.6877, "lr": 3.49143333753309e-07, "epoch": 2.663265306122449, "percentage": 89.23, "elapsed_time": "3:22:05", "remaining_time": "0:24:23"}
+{"current_steps": 349, "total_steps": 390, "loss": 0.6802, "lr": 3.3290021961708163e-07, "epoch": 2.670918367346939, "percentage": 89.49, "elapsed_time": "3:22:39", "remaining_time": "0:23:48"}
+{"current_steps": 350, "total_steps": 390, "loss": 0.6824, "lr": 3.1703098329864237e-07, "epoch": 2.678571428571429, "percentage": 89.74, "elapsed_time": "3:23:13", "remaining_time": "0:23:13"}
+{"current_steps": 351, "total_steps": 390, "loss": 0.6928, "lr": 3.015368960704584e-07, "epoch": 2.686224489795918, "percentage": 90.0, "elapsed_time": "3:23:47", "remaining_time": "0:22:38"}
+{"current_steps": 352, "total_steps": 390, "loss": 0.6846, "lr": 2.864191991520848e-07, "epoch": 2.693877551020408, "percentage": 90.26, "elapsed_time": "3:24:21", "remaining_time": "0:22:03"}
+{"current_steps": 353, "total_steps": 390, "loss": 0.6909, "lr": 2.71679103610738e-07, "epoch": 2.701530612244898, "percentage": 90.51, "elapsed_time": "3:24:55", "remaining_time": "0:21:28"}
+{"current_steps": 354, "total_steps": 390, "loss": 0.6788, "lr": 2.573177902642726e-07, "epoch": 2.7091836734693877, "percentage": 90.77, "elapsed_time": "3:25:29", "remaining_time": "0:20:53"}
+{"current_steps": 355, "total_steps": 390, "loss": 0.7087, "lr": 2.4333640958659144e-07, "epoch": 2.7168367346938775, "percentage": 91.03, "elapsed_time": "3:26:04", "remaining_time": "0:20:19"}
+{"current_steps": 356, "total_steps": 390, "loss": 0.695, "lr": 2.2973608161547755e-07, "epoch": 2.7244897959183674, "percentage": 91.28, "elapsed_time": "3:26:38", "remaining_time": "0:19:44"}
+{"current_steps": 357, "total_steps": 390, "loss": 0.6805, "lr": 2.1651789586287442e-07, "epoch": 2.732142857142857, "percentage": 91.54, "elapsed_time": "3:27:12", "remaining_time": "0:19:09"}
+{"current_steps": 358, "total_steps": 390, "loss": 0.6891, "lr": 2.0368291122759898e-07, "epoch": 2.739795918367347, "percentage": 91.79, "elapsed_time": "3:27:46", "remaining_time": "0:18:34"}
+{"current_steps": 359, "total_steps": 390, "loss": 0.6874, "lr": 1.9123215591052014e-07, "epoch": 2.747448979591837, "percentage": 92.05, "elapsed_time": "3:28:20", "remaining_time": "0:17:59"}
+{"current_steps": 360, "total_steps": 390, "loss": 0.6779, "lr": 1.7916662733218848e-07, "epoch": 2.7551020408163263, "percentage": 92.31, "elapsed_time": "3:28:54", "remaining_time": "0:17:24"}
+{"current_steps": 361, "total_steps": 390, "loss": 0.6673, "lr": 1.6748729205293024e-07, "epoch": 2.762755102040816, "percentage": 92.56, "elapsed_time": "3:29:28", "remaining_time": "0:16:49"}
+{"current_steps": 362, "total_steps": 390, "loss": 0.6607, "lr": 1.5619508569542363e-07, "epoch": 2.770408163265306, "percentage": 92.82, "elapsed_time": "3:30:02", "remaining_time": "0:16:14"}
+{"current_steps": 363, "total_steps": 390, "loss": 0.6771, "lr": 1.4529091286973994e-07, "epoch": 2.7780612244897958, "percentage": 93.08, "elapsed_time": "3:30:37", "remaining_time": "0:15:39"}
+{"current_steps": 364, "total_steps": 390, "loss": 0.6853, "lr": 1.3477564710088097e-07, "epoch": 2.7857142857142856, "percentage": 93.33, "elapsed_time": "3:31:11", "remaining_time": "0:15:05"}
+{"current_steps": 365, "total_steps": 390, "loss": 0.6898, "lr": 1.2465013075879884e-07, "epoch": 2.7933673469387754, "percentage": 93.59, "elapsed_time": "3:31:45", "remaining_time": "0:14:30"}
+{"current_steps": 366, "total_steps": 390, "loss": 0.6936, "lr": 1.1491517499091498e-07, "epoch": 2.8010204081632653, "percentage": 93.85, "elapsed_time": "3:32:19", "remaining_time": "0:13:55"}
+{"current_steps": 367, "total_steps": 390, "loss": 0.6814, "lr": 1.055715596571405e-07, "epoch": 2.808673469387755, "percentage": 94.1, "elapsed_time": "3:32:53", "remaining_time": "0:13:20"}
+{"current_steps": 368, "total_steps": 390, "loss": 0.6808, "lr": 9.662003326740166e-08, "epoch": 2.816326530612245, "percentage": 94.36, "elapsed_time": "3:33:27", "remaining_time": "0:12:45"}
+{"current_steps": 369, "total_steps": 390, "loss": 0.6754, "lr": 8.80613129216762e-08, "epoch": 2.8239795918367347, "percentage": 94.62, "elapsed_time": "3:34:01", "remaining_time": "0:12:10"}
+{"current_steps": 370, "total_steps": 390, "loss": 0.6787, "lr": 7.989608425254924e-08, "epoch": 2.8316326530612246, "percentage": 94.87, "elapsed_time": "3:34:35", "remaining_time": "0:11:35"}
+{"current_steps": 371, "total_steps": 390, "loss": 0.6894, "lr": 7.212500137028789e-08, "epoch": 2.8392857142857144, "percentage": 95.13, "elapsed_time": "3:35:09", "remaining_time": "0:11:01"}
+{"current_steps": 372, "total_steps": 390, "loss": 0.6698, "lr": 6.474868681043578e-08, "epoch": 2.8469387755102042, "percentage": 95.38, "elapsed_time": "3:35:43", "remaining_time": "0:10:26"}
+{"current_steps": 373, "total_steps": 390, "loss": 0.6952, "lr": 5.776773148394976e-08, "epoch": 2.854591836734694, "percentage": 95.64, "elapsed_time": "3:36:18", "remaining_time": "0:09:51"}
+{"current_steps": 374, "total_steps": 390, "loss": 0.6957, "lr": 5.1182694629857145e-08, "epoch": 2.862244897959184, "percentage": 95.9, "elapsed_time": "3:36:52", "remaining_time": "0:09:16"}
+{"current_steps": 375, "total_steps": 390, "loss": 0.6886, "lr": 4.499410377045765e-08, "epoch": 2.8698979591836737, "percentage": 96.15, "elapsed_time": "3:37:26", "remaining_time": "0:08:41"}
+{"current_steps": 376, "total_steps": 390, "loss": 0.6977, "lr": 3.9202454669063915e-08, "epoch": 2.877551020408163, "percentage": 96.41, "elapsed_time": "3:38:00", "remaining_time": "0:08:07"}
+{"current_steps": 377, "total_steps": 390, "loss": 0.698, "lr": 3.3808211290284886e-08, "epoch": 2.885204081632653, "percentage": 96.67, "elapsed_time": "3:38:34", "remaining_time": "0:07:32"}
+{"current_steps": 378, "total_steps": 390, "loss": 0.6915, "lr": 2.8811805762860578e-08, "epoch": 2.892857142857143, "percentage": 96.92, "elapsed_time": "3:39:08", "remaining_time": "0:06:57"}
+{"current_steps": 379, "total_steps": 390, "loss": 0.6814, "lr": 2.4213638345040868e-08, "epoch": 2.9005102040816326, "percentage": 97.18, "elapsed_time": "3:39:42", "remaining_time": "0:06:22"}
+{"current_steps": 380, "total_steps": 390, "loss": 0.6795, "lr": 2.0014077392525035e-08, "epoch": 2.9081632653061225, "percentage": 97.44, "elapsed_time": "3:40:16", "remaining_time": "0:05:47"}
+{"current_steps": 381, "total_steps": 390, "loss": 0.6788, "lr": 1.6213459328950355e-08, "epoch": 2.9158163265306123, "percentage": 97.69, "elapsed_time": "3:40:51", "remaining_time": "0:05:13"}
+{"current_steps": 382, "total_steps": 390, "loss": 0.6957, "lr": 1.2812088618942009e-08, "epoch": 2.923469387755102, "percentage": 97.95, "elapsed_time": "3:41:25", "remaining_time": "0:04:38"}
+{"current_steps": 383, "total_steps": 390, "loss": 0.6813, "lr": 9.810237743724805e-09, "epoch": 2.931122448979592, "percentage": 98.21, "elapsed_time": "3:41:59", "remaining_time": "0:04:03"}
+{"current_steps": 384, "total_steps": 390, "loss": 0.685, "lr": 7.2081471792911914e-09, "epoch": 2.938775510204082, "percentage": 98.46, "elapsed_time": "3:42:33", "remaining_time": "0:03:28"}
+{"current_steps": 385, "total_steps": 390, "loss": 0.6748, "lr": 5.006025377138901e-09, "epoch": 2.946428571428571, "percentage": 98.72, "elapsed_time": "3:43:07", "remaining_time": "0:02:53"}
+{"current_steps": 386, "total_steps": 390, "loss": 0.6824, "lr": 3.204048747573185e-09, "epoch": 2.954081632653061, "percentage": 98.97, "elapsed_time": "3:43:41", "remaining_time": "0:02:19"}
+{"current_steps": 387, "total_steps": 390, "loss": 0.6791, "lr": 1.8023616455731253e-09, "epoch": 2.961734693877551, "percentage": 99.23, "elapsed_time": "3:44:15", "remaining_time": "0:01:44"}
+{"current_steps": 388, "total_steps": 390, "loss": 0.6825, "lr": 8.010763592264381e-10, "epoch": 2.9693877551020407, "percentage": 99.49, "elapsed_time": "3:44:49", "remaining_time": "0:01:09"}
+{"current_steps": 389, "total_steps": 390, "loss": 0.6797, "lr": 2.0027310073833516e-10, "epoch": 2.9770408163265305, "percentage": 99.74, "elapsed_time": "3:45:23", "remaining_time": "0:00:34"}
+{"current_steps": 390, "total_steps": 390, "loss": 0.6847, "lr": 0.0, "epoch": 2.9846938775510203, "percentage": 100.0, "elapsed_time": "3:45:57", "remaining_time": "0:00:00"}
+{"current_steps": 390, "total_steps": 390, "epoch": 2.9846938775510203, "percentage": 100.0, "elapsed_time": "3:46:59", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2772 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9846938775510203,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007653061224489796,
+      "grad_norm": 7.900599139656812,
+      "learning_rate": 2.564102564102564e-07,
+      "loss": 1.2547,
+      "step": 1
+    },
+    {
+      "epoch": 0.015306122448979591,
+      "grad_norm": 8.119600107369656,
+      "learning_rate": 5.128205128205128e-07,
+      "loss": 1.2846,
+      "step": 2
+    },
+    {
+      "epoch": 0.02295918367346939,
+      "grad_norm": 7.716599625963762,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.2358,
+      "step": 3
+    },
+    {
+      "epoch": 0.030612244897959183,
+      "grad_norm": 8.053428990837991,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 1.2664,
+      "step": 4
+    },
+    {
+      "epoch": 0.03826530612244898,
+      "grad_norm": 7.669927836204581,
+      "learning_rate": 1.282051282051282e-06,
+      "loss": 1.2258,
+      "step": 5
+    },
+    {
+      "epoch": 0.04591836734693878,
+      "grad_norm": 7.202844535122422,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.2287,
+      "step": 6
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 6.242569470438793,
+      "learning_rate": 1.794871794871795e-06,
+      "loss": 1.2074,
+      "step": 7
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 5.60650986860704,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 1.1714,
+      "step": 8
+    },
+    {
+      "epoch": 0.06887755102040816,
+      "grad_norm": 5.288779120719776,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.1896,
+      "step": 9
+    },
+    {
+      "epoch": 0.07653061224489796,
+      "grad_norm": 2.9734467693838242,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.1187,
+      "step": 10
+    },
+    {
+      "epoch": 0.08418367346938775,
+      "grad_norm": 2.6447321687920935,
+      "learning_rate": 2.8205128205128207e-06,
+      "loss": 1.1054,
+      "step": 11
+    },
+    {
+      "epoch": 0.09183673469387756,
+      "grad_norm": 2.500691487000675,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.1232,
+      "step": 12
+    },
+    {
+      "epoch": 0.09948979591836735,
+      "grad_norm": 3.7896412560526667,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0521,
+      "step": 13
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 4.330435607713412,
+      "learning_rate": 3.58974358974359e-06,
+      "loss": 1.0695,
+      "step": 14
+    },
+    {
+      "epoch": 0.11479591836734694,
+      "grad_norm": 4.065967025129537,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.0492,
+      "step": 15
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 3.8218626260606254,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 1.0507,
+      "step": 16
+    },
+    {
+      "epoch": 0.13010204081632654,
+      "grad_norm": 2.913408611179218,
+      "learning_rate": 4.358974358974359e-06,
+      "loss": 1.0352,
+      "step": 17
+    },
+    {
+      "epoch": 0.1377551020408163,
+      "grad_norm": 2.181426061973388,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.9931,
+      "step": 18
+    },
+    {
+      "epoch": 0.14540816326530612,
+      "grad_norm": 2.231160799643045,
+      "learning_rate": 4.871794871794872e-06,
+      "loss": 0.9909,
+      "step": 19
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": 1.8886705253423084,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 0.9585,
+      "step": 20
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 1.4487020320934674,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.9512,
+      "step": 21
+    },
+    {
+      "epoch": 0.1683673469387755,
+      "grad_norm": 1.1474113193070334,
+      "learning_rate": 5.641025641025641e-06,
+      "loss": 0.9211,
+      "step": 22
+    },
+    {
+      "epoch": 0.1760204081632653,
+      "grad_norm": 1.1082161392111283,
+      "learning_rate": 5.897435897435898e-06,
+      "loss": 0.9276,
+      "step": 23
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 1.0650174913457753,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.8952,
+      "step": 24
+    },
+    {
+      "epoch": 0.1913265306122449,
+      "grad_norm": 1.0639688813292578,
+      "learning_rate": 6.410256410256412e-06,
+      "loss": 0.9,
+      "step": 25
+    },
+    {
+      "epoch": 0.1989795918367347,
+      "grad_norm": 1.026817161303438,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.91,
+      "step": 26
+    },
+    {
+      "epoch": 0.2066326530612245,
+      "grad_norm": 0.8417599731227993,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.8814,
+      "step": 27
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.6981856946789826,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.8919,
+      "step": 28
+    },
+    {
+      "epoch": 0.22193877551020408,
+      "grad_norm": 0.8305699974027309,
+      "learning_rate": 7.435897435897437e-06,
+      "loss": 0.8725,
+      "step": 29
+    },
+    {
+      "epoch": 0.22959183673469388,
+      "grad_norm": 0.8347298264686718,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.8632,
+      "step": 30
+    },
+    {
+      "epoch": 0.2372448979591837,
+      "grad_norm": 0.7073808513621134,
+      "learning_rate": 7.948717948717949e-06,
+      "loss": 0.8851,
+      "step": 31
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.696082003876517,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 0.8703,
+      "step": 32
+    },
+    {
+      "epoch": 0.25255102040816324,
+      "grad_norm": 0.6487862374432037,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.8635,
+      "step": 33
+    },
+    {
+      "epoch": 0.2602040816326531,
+      "grad_norm": 0.6887600459571754,
+      "learning_rate": 8.717948717948719e-06,
+      "loss": 0.857,
+      "step": 34
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.6265375198163766,
+      "learning_rate": 8.974358974358976e-06,
+      "loss": 0.8674,
+      "step": 35
+    },
+    {
+      "epoch": 0.2755102040816326,
+      "grad_norm": 0.5853042860058177,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.8643,
+      "step": 36
+    },
+    {
+      "epoch": 0.28316326530612246,
+      "grad_norm": 0.5778280304486835,
+      "learning_rate": 9.487179487179487e-06,
+      "loss": 0.8524,
+      "step": 37
+    },
+    {
+      "epoch": 0.29081632653061223,
+      "grad_norm": 0.47109648165463025,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 0.8345,
+      "step": 38
+    },
+    {
+      "epoch": 0.29846938775510207,
+      "grad_norm": 0.6185653217679288,
+      "learning_rate": 1e-05,
+      "loss": 0.8383,
+      "step": 39
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.47985971027522895,
+      "learning_rate": 9.999799726899261e-06,
+      "loss": 0.8445,
+      "step": 40
+    },
+    {
+      "epoch": 0.3137755102040816,
+      "grad_norm": 0.5168786180126856,
+      "learning_rate": 9.999198923640774e-06,
+      "loss": 0.8339,
+      "step": 41
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.4697815414710563,
+      "learning_rate": 9.998197638354428e-06,
+      "loss": 0.8395,
+      "step": 42
+    },
+    {
+      "epoch": 0.32908163265306123,
+      "grad_norm": 0.43778336023032777,
+      "learning_rate": 9.996795951252427e-06,
+      "loss": 0.8447,
+      "step": 43
+    },
+    {
+      "epoch": 0.336734693877551,
+      "grad_norm": 0.4556959273145522,
+      "learning_rate": 9.994993974622863e-06,
+      "loss": 0.8388,
+      "step": 44
+    },
+    {
+      "epoch": 0.34438775510204084,
+      "grad_norm": 0.4348649136417768,
+      "learning_rate": 9.992791852820709e-06,
+      "loss": 0.8107,
+      "step": 45
+    },
+    {
+      "epoch": 0.3520408163265306,
+      "grad_norm": 0.3789542620181641,
+      "learning_rate": 9.990189762256275e-06,
+      "loss": 0.8345,
+      "step": 46
+    },
+    {
+      "epoch": 0.3596938775510204,
+      "grad_norm": 0.38275331303639004,
+      "learning_rate": 9.987187911381059e-06,
+      "loss": 0.8341,
+      "step": 47
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 0.4117058990117418,
+      "learning_rate": 9.983786540671052e-06,
+      "loss": 0.8221,
+      "step": 48
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.4382241759510747,
+      "learning_rate": 9.979985922607476e-06,
+      "loss": 0.8122,
+      "step": 49
+    },
+    {
+      "epoch": 0.3826530612244898,
+      "grad_norm": 0.3762436724149032,
+      "learning_rate": 9.975786361654959e-06,
+      "loss": 0.8266,
+      "step": 50
+    },
+    {
+      "epoch": 0.3903061224489796,
+      "grad_norm": 0.41057346443737175,
+      "learning_rate": 9.971188194237141e-06,
+      "loss": 0.8088,
+      "step": 51
+    },
+    {
+      "epoch": 0.3979591836734694,
+      "grad_norm": 0.4047860097370241,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.8104,
+      "step": 52
+    },
+    {
+      "epoch": 0.40561224489795916,
+      "grad_norm": 0.33943575533118764,
+      "learning_rate": 9.960797545330936e-06,
+      "loss": 0.7912,
+      "step": 53
+    },
+    {
+      "epoch": 0.413265306122449,
+      "grad_norm": 0.4320896078070966,
+      "learning_rate": 9.955005896229543e-06,
+      "loss": 0.812,
+      "step": 54
+    },
+    {
+      "epoch": 0.42091836734693877,
+      "grad_norm": 0.36490629588097284,
+      "learning_rate": 9.948817305370145e-06,
+      "loss": 0.817,
+      "step": 55
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.3811135120016499,
+      "learning_rate": 9.942232268516051e-06,
+      "loss": 0.8101,
+      "step": 56
+    },
+    {
+      "epoch": 0.4362244897959184,
+      "grad_norm": 0.3406018259398481,
+      "learning_rate": 9.935251313189564e-06,
+      "loss": 0.7987,
+      "step": 57
+    },
+    {
+      "epoch": 0.44387755102040816,
+      "grad_norm": 0.41568382541199506,
+      "learning_rate": 9.927874998629714e-06,
+      "loss": 0.8122,
+      "step": 58
+    },
+    {
+      "epoch": 0.45153061224489793,
+      "grad_norm": 0.37378450752963704,
+      "learning_rate": 9.920103915747452e-06,
+      "loss": 0.8113,
+      "step": 59
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 0.38855892151900484,
+      "learning_rate": 9.911938687078324e-06,
+      "loss": 0.7859,
+      "step": 60
+    },
+    {
+      "epoch": 0.46683673469387754,
+      "grad_norm": 0.4427608830523002,
+      "learning_rate": 9.9033799667326e-06,
+      "loss": 0.802,
+      "step": 61
+    },
+    {
+      "epoch": 0.4744897959183674,
+      "grad_norm": 0.35381982973714704,
+      "learning_rate": 9.89442844034286e-06,
+      "loss": 0.8253,
+      "step": 62
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 0.39211658446728886,
+      "learning_rate": 9.885084825009085e-06,
+      "loss": 0.8105,
+      "step": 63
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.40435166675919726,
+      "learning_rate": 9.875349869241202e-06,
+      "loss": 0.7953,
+      "step": 64
+    },
+    {
+      "epoch": 0.49744897959183676,
+      "grad_norm": 0.3549380749010608,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.8013,
+      "step": 65
+    },
+    {
+      "epoch": 0.5051020408163265,
+      "grad_norm": 0.30865050646134456,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.7995,
+      "step": 66
+    },
+    {
+      "epoch": 0.5127551020408163,
+      "grad_norm": 0.37493039088229285,
+      "learning_rate": 9.843804914304578e-06,
+      "loss": 0.7896,
+      "step": 67
+    },
+    {
+      "epoch": 0.5204081632653061,
+      "grad_norm": 0.35445041874178557,
+      "learning_rate": 9.83251270794707e-06,
+      "loss": 0.7825,
+      "step": 68
+    },
+    {
+      "epoch": 0.5280612244897959,
+      "grad_norm": 0.37028381618760225,
+      "learning_rate": 9.820833372667813e-06,
+      "loss": 0.8065,
+      "step": 69
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.3401014836367619,
+      "learning_rate": 9.80876784408948e-06,
+      "loss": 0.7736,
+      "step": 70
+    },
+    {
+      "epoch": 0.5433673469387755,
+      "grad_norm": 0.38135639736053345,
+      "learning_rate": 9.796317088772402e-06,
+      "loss": 0.8006,
+      "step": 71
+    },
+    {
+      "epoch": 0.5510204081632653,
+      "grad_norm": 0.3449580873725305,
+      "learning_rate": 9.783482104137127e-06,
+      "loss": 0.793,
+      "step": 72
+    },
+    {
+      "epoch": 0.5586734693877551,
+      "grad_norm": 0.39773824101732064,
+      "learning_rate": 9.770263918384523e-06,
+      "loss": 0.7628,
+      "step": 73
+    },
+    {
+      "epoch": 0.5663265306122449,
+      "grad_norm": 0.36658929825409153,
+      "learning_rate": 9.75666359041341e-06,
+      "loss": 0.7849,
+      "step": 74
+    },
+    {
+      "epoch": 0.5739795918367347,
+      "grad_norm": 0.40174916793470977,
+      "learning_rate": 9.742682209735727e-06,
+      "loss": 0.7813,
+      "step": 75
+    },
+    {
+      "epoch": 0.5816326530612245,
+      "grad_norm": 0.3675910724991157,
+      "learning_rate": 9.728320896389263e-06,
+      "loss": 0.7717,
+      "step": 76
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 0.35241618551974574,
+      "learning_rate": 9.713580800847917e-06,
+      "loss": 0.7964,
+      "step": 77
+    },
+    {
+      "epoch": 0.5969387755102041,
+      "grad_norm": 0.42227511752715124,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.783,
+      "step": 78
+    },
+    {
+      "epoch": 0.6045918367346939,
+      "grad_norm": 0.41099008300592765,
+      "learning_rate": 9.682969016701357e-06,
+      "loss": 0.8124,
+      "step": 79
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.3588362815681614,
+      "learning_rate": 9.66709978038292e-06,
+      "loss": 0.8027,
+      "step": 80
+    },
+    {
+      "epoch": 0.6198979591836735,
+      "grad_norm": 0.44603372884723097,
+      "learning_rate": 9.650856666246693e-06,
+      "loss": 0.7884,
+      "step": 81
+    },
+    {
+      "epoch": 0.6275510204081632,
+      "grad_norm": 0.36738127885232164,
+      "learning_rate": 9.63424097551621e-06,
+      "loss": 0.7914,
+      "step": 82
+    },
+    {
+      "epoch": 0.6352040816326531,
+      "grad_norm": 0.3461400435266106,
+      "learning_rate": 9.617254039261835e-06,
+      "loss": 0.7698,
+      "step": 83
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.3746146031615924,
+      "learning_rate": 9.599897218294122e-06,
+      "loss": 0.7958,
+      "step": 84
+    },
+    {
+      "epoch": 0.6505102040816326,
+      "grad_norm": 0.37460698420532035,
+      "learning_rate": 9.582171903054815e-06,
+      "loss": 0.7677,
+      "step": 85
+    },
+    {
+      "epoch": 0.6581632653061225,
+      "grad_norm": 0.3433298671011665,
+      "learning_rate": 9.564079513505455e-06,
+      "loss": 0.8015,
+      "step": 86
+    },
+    {
+      "epoch": 0.6658163265306123,
+      "grad_norm": 0.3482571197001568,
+      "learning_rate": 9.54562149901362e-06,
+      "loss": 0.7638,
+      "step": 87
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": 0.40316278701128183,
+      "learning_rate": 9.526799338236828e-06,
+      "loss": 0.7843,
+      "step": 88
+    },
+    {
+      "epoch": 0.6811224489795918,
+      "grad_norm": 0.3555197534077026,
+      "learning_rate": 9.507614539004082e-06,
+      "loss": 0.7925,
+      "step": 89
+    },
+    {
+      "epoch": 0.6887755102040817,
+      "grad_norm": 0.38348347862843785,
+      "learning_rate": 9.488068638195072e-06,
+      "loss": 0.7894,
+      "step": 90
+    },
+    {
+      "epoch": 0.6964285714285714,
+      "grad_norm": 0.3578221543396146,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.7625,
+      "step": 91
+    },
+    {
+      "epoch": 0.7040816326530612,
+      "grad_norm": 0.3512021435202505,
+      "learning_rate": 9.447899823879456e-06,
+      "loss": 0.7664,
+      "step": 92
+    },
+    {
+      "epoch": 0.7117346938775511,
+      "grad_norm": 0.359766111570709,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.7827,
+      "step": 93
+    },
+    {
+      "epoch": 0.7193877551020408,
+      "grad_norm": 0.3342360288463418,
+      "learning_rate": 9.406305766604996e-06,
+      "loss": 0.7868,
+      "step": 94
+    },
+    {
+      "epoch": 0.7270408163265306,
+      "grad_norm": 0.32321038061189955,
+      "learning_rate": 9.384978419136469e-06,
+      "loss": 0.7898,
+      "step": 95
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.34171882937229003,
+      "learning_rate": 9.363299794378072e-06,
+      "loss": 0.7665,
+      "step": 96
+    },
+    {
+      "epoch": 0.7423469387755102,
+      "grad_norm": 0.35118533636970833,
+      "learning_rate": 9.34127162898797e-06,
+      "loss": 0.7726,
+      "step": 97
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3370944528784506,
+      "learning_rate": 9.318895687625752e-06,
+      "loss": 0.7835,
+      "step": 98
+    },
+    {
+      "epoch": 0.7576530612244898,
+      "grad_norm": 0.29470217608260335,
+      "learning_rate": 9.296173762811084e-06,
+      "loss": 0.7777,
+      "step": 99
+    },
+    {
+      "epoch": 0.7653061224489796,
+      "grad_norm": 0.3454016966220543,
+      "learning_rate": 9.273107674780102e-06,
+      "loss": 0.789,
+      "step": 100
+    },
+    {
+      "epoch": 0.7729591836734694,
+      "grad_norm": 0.39511779117121837,
+      "learning_rate": 9.249699271339594e-06,
+      "loss": 0.7603,
+      "step": 101
+    },
+    {
+      "epoch": 0.7806122448979592,
+      "grad_norm": 0.38047057845879517,
+      "learning_rate": 9.225950427718974e-06,
+      "loss": 0.7825,
+      "step": 102
+    },
+    {
+      "epoch": 0.7882653061224489,
+      "grad_norm": 0.4086929427189167,
+      "learning_rate": 9.201863046420065e-06,
+      "loss": 0.7736,
+      "step": 103
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 0.40106266010702624,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.7846,
+      "step": 104
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 0.4228915644292435,
+      "learning_rate": 9.152680416240059e-06,
+      "loss": 0.7666,
+      "step": 105
+    },
+    {
+      "epoch": 0.8112244897959183,
+      "grad_norm": 0.3146448558809326,
+      "learning_rate": 9.1275891073421e-06,
+      "loss": 0.7657,
+      "step": 106
+    },
+    {
+      "epoch": 0.8188775510204082,
+      "grad_norm": 0.43451140759881535,
+      "learning_rate": 9.102167140416503e-06,
+      "loss": 0.7709,
+      "step": 107
+    },
+    {
+      "epoch": 0.826530612244898,
+      "grad_norm": 0.33837608510390754,
+      "learning_rate": 9.076416551997721e-06,
+      "loss": 0.7744,
+      "step": 108
+    },
+    {
+      "epoch": 0.8341836734693877,
+      "grad_norm": 0.37565083198791915,
+      "learning_rate": 9.050339404945834e-06,
+      "loss": 0.7827,
+      "step": 109
+    },
+    {
+      "epoch": 0.8418367346938775,
+      "grad_norm": 0.365977104631186,
+      "learning_rate": 9.023937788281278e-06,
+      "loss": 0.7834,
+      "step": 110
+    },
+    {
+      "epoch": 0.8494897959183674,
+      "grad_norm": 0.4486855497610728,
+      "learning_rate": 8.997213817017508e-06,
+      "loss": 0.7644,
+      "step": 111
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.3817323486497425,
+      "learning_rate": 8.970169631991556e-06,
+      "loss": 0.779,
+      "step": 112
+    },
+    {
+      "epoch": 0.8647959183673469,
+      "grad_norm": 0.38664365638910025,
+      "learning_rate": 8.942807399692543e-06,
+      "loss": 0.7688,
+      "step": 113
+    },
+    {
+      "epoch": 0.8724489795918368,
+      "grad_norm": 0.37215420738034083,
+      "learning_rate": 8.915129312088112e-06,
+      "loss": 0.7757,
+      "step": 114
+    },
+    {
+      "epoch": 0.8801020408163265,
+      "grad_norm": 0.35426054376993094,
+      "learning_rate": 8.88713758644883e-06,
+      "loss": 0.7674,
+      "step": 115
+    },
+    {
+      "epoch": 0.8877551020408163,
+      "grad_norm": 0.4195483369441139,
+      "learning_rate": 8.858834465170576e-06,
+      "loss": 0.7677,
+      "step": 116
+    },
+    {
+      "epoch": 0.8954081632653061,
+      "grad_norm": 0.41930027175437984,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7568,
+      "step": 117
+    },
+    {
+      "epoch": 0.9030612244897959,
+      "grad_norm": 0.3279073397597126,
+      "learning_rate": 8.801303129827352e-06,
+      "loss": 0.7822,
+      "step": 118
+    },
+    {
+      "epoch": 0.9107142857142857,
+      "grad_norm": 0.357892031294145,
+      "learning_rate": 8.772079524553951e-06,
+      "loss": 0.7534,
+      "step": 119
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 0.3165448329232979,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.7739,
+      "step": 120
+    },
+    {
+      "epoch": 0.9260204081632653,
+      "grad_norm": 0.3383676190282577,
+      "learning_rate": 8.712728144020118e-06,
+      "loss": 0.7603,
+      "step": 121
+    },
+    {
+      "epoch": 0.9336734693877551,
+      "grad_norm": 0.3208003771597576,
+      "learning_rate": 8.682605123353685e-06,
+      "loss": 0.7629,
+      "step": 122
+    },
+    {
+      "epoch": 0.9413265306122449,
+      "grad_norm": 0.32756065557104463,
+      "learning_rate": 8.652187091988516e-06,
+      "loss": 0.7751,
+      "step": 123
+    },
+    {
+      "epoch": 0.9489795918367347,
+      "grad_norm": 0.3144217008561782,
+      "learning_rate": 8.621476486689991e-06,
+      "loss": 0.7617,
+      "step": 124
+    },
+    {
+      "epoch": 0.9566326530612245,
+      "grad_norm": 0.34740205977487404,
+      "learning_rate": 8.590475767661371e-06,
+      "loss": 0.7715,
+      "step": 125
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.36365085803217173,
+      "learning_rate": 8.559187418346703e-06,
+      "loss": 0.7702,
+      "step": 126
+    },
+    {
+      "epoch": 0.9719387755102041,
+      "grad_norm": 0.3242477226265553,
+      "learning_rate": 8.527613945231886e-06,
+      "loss": 0.7486,
+      "step": 127
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.33767240411889204,
+      "learning_rate": 8.495757877643857e-06,
+      "loss": 0.7539,
+      "step": 128
+    },
+    {
+      "epoch": 0.9872448979591837,
+      "grad_norm": 0.3728149497460986,
+      "learning_rate": 8.463621767547998e-06,
+      "loss": 0.7823,
+      "step": 129
+    },
+    {
+      "epoch": 0.9948979591836735,
+      "grad_norm": 0.3037904703658018,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.7676,
+      "step": 130
+    },
+    {
+      "epoch": 1.0025510204081634,
+      "grad_norm": 0.3657607958037338,
+      "learning_rate": 8.398519739657997e-06,
+      "loss": 0.7447,
+      "step": 131
+    },
+    {
+      "epoch": 1.010204081632653,
+      "grad_norm": 0.32702463131138215,
+      "learning_rate": 8.36555903713785e-06,
+      "loss": 0.7192,
+      "step": 132
+    },
+    {
+      "epoch": 1.0178571428571428,
+      "grad_norm": 0.3241261143033043,
+      "learning_rate": 8.332328722240072e-06,
+      "loss": 0.7463,
+      "step": 133
+    },
+    {
+      "epoch": 1.0255102040816326,
+      "grad_norm": 0.34857830092581826,
+      "learning_rate": 8.298831457019943e-06,
+      "loss": 0.7477,
+      "step": 134
+    },
+    {
+      "epoch": 1.0331632653061225,
+      "grad_norm": 0.34054768296119625,
+      "learning_rate": 8.265069924917925e-06,
+      "loss": 0.7205,
+      "step": 135
+    },
+    {
+      "epoch": 1.0408163265306123,
+      "grad_norm": 0.3456929422423653,
+      "learning_rate": 8.231046830544716e-06,
+      "loss": 0.74,
+      "step": 136
+    },
+    {
+      "epoch": 1.0484693877551021,
+      "grad_norm": 0.3535133441712295,
+      "learning_rate": 8.196764899464552e-06,
+      "loss": 0.7269,
+      "step": 137
+    },
+    {
+      "epoch": 1.0561224489795917,
+      "grad_norm": 0.3547241666178161,
+      "learning_rate": 8.162226877976886e-06,
+      "loss": 0.7554,
+      "step": 138
+    },
+    {
+      "epoch": 1.0637755102040816,
+      "grad_norm": 0.3107043446143115,
+      "learning_rate": 8.127435532896388e-06,
+      "loss": 0.7288,
+      "step": 139
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.3373069931944795,
+      "learning_rate": 8.092393651331275e-06,
+      "loss": 0.7355,
+      "step": 140
+    },
+    {
+      "epoch": 1.0790816326530612,
+      "grad_norm": 0.3279896770891133,
+      "learning_rate": 8.057104040460062e-06,
+      "loss": 0.7385,
+      "step": 141
+    },
+    {
+      "epoch": 1.086734693877551,
+      "grad_norm": 0.3261929334088148,
+      "learning_rate": 8.021569527306663e-06,
+      "loss": 0.728,
+      "step": 142
+    },
+    {
+      "epoch": 1.094387755102041,
+      "grad_norm": 0.3174495615043381,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.7408,
+      "step": 143
+    },
+    {
+      "epoch": 1.1020408163265305,
+      "grad_norm": 0.3067789820058703,
+      "learning_rate": 7.949777200115617e-06,
+      "loss": 0.7227,
+      "step": 144
+    },
+    {
+      "epoch": 1.1096938775510203,
+      "grad_norm": 0.35433845526552205,
+      "learning_rate": 7.913525137306756e-06,
+      "loss": 0.7287,
+      "step": 145
+    },
+    {
+      "epoch": 1.1173469387755102,
+      "grad_norm": 0.34741723337985486,
+      "learning_rate": 7.877039674212569e-06,
+      "loss": 0.7258,
+      "step": 146
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.3280286780388698,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.7262,
+      "step": 147
+    },
+    {
+      "epoch": 1.1326530612244898,
+      "grad_norm": 0.30769648626514395,
+      "learning_rate": 7.803380256922495e-06,
+      "loss": 0.7281,
+      "step": 148
+    },
+    {
+      "epoch": 1.1403061224489797,
+      "grad_norm": 0.3815259137143696,
+      "learning_rate": 7.76621220352657e-06,
+      "loss": 0.7189,
+      "step": 149
+    },
+    {
+      "epoch": 1.1479591836734695,
+      "grad_norm": 0.3003966668112163,
+      "learning_rate": 7.728822550972523e-06,
+      "loss": 0.7372,
+      "step": 150
+    },
+    {
+      "epoch": 1.155612244897959,
+      "grad_norm": 0.3730853217142341,
+      "learning_rate": 7.69121429451702e-06,
+      "loss": 0.7327,
+      "step": 151
+    },
+    {
+      "epoch": 1.163265306122449,
+      "grad_norm": 0.3077673668382533,
+      "learning_rate": 7.65339044692891e-06,
+      "loss": 0.7243,
+      "step": 152
+    },
+    {
+      "epoch": 1.1709183673469388,
+      "grad_norm": 0.3419341487539606,
+      "learning_rate": 7.615354038247889e-06,
+      "loss": 0.7132,
+      "step": 153
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.4263455028715549,
+      "learning_rate": 7.577108115541761e-06,
+      "loss": 0.7136,
+      "step": 154
+    },
+    {
+      "epoch": 1.1862244897959184,
+      "grad_norm": 0.3659660917830282,
+      "learning_rate": 7.53865574266234e-06,
+      "loss": 0.7423,
+      "step": 155
+    },
+    {
+      "epoch": 1.193877551020408,
+      "grad_norm": 0.38942680340360186,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7194,
+      "step": 156
+    },
+    {
+      "epoch": 1.2015306122448979,
+      "grad_norm": 0.4077561265291119,
+      "learning_rate": 7.461143984236925e-06,
+      "loss": 0.7152,
+      "step": 157
+    },
+    {
+      "epoch": 1.2091836734693877,
+      "grad_norm": 0.31673843482064173,
+      "learning_rate": 7.422090808099014e-06,
+      "loss": 0.7164,
+      "step": 158
+    },
+    {
+      "epoch": 1.2168367346938775,
+      "grad_norm": 0.3411891380728348,
+      "learning_rate": 7.382843600106539e-06,
+      "loss": 0.7232,
+      "step": 159
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.35077489655944777,
+      "learning_rate": 7.343405504323519e-06,
+      "loss": 0.7306,
+      "step": 160
+    },
+    {
+      "epoch": 1.2321428571428572,
+      "grad_norm": 0.35048005407769184,
+      "learning_rate": 7.303779680105844e-06,
+      "loss": 0.7252,
+      "step": 161
+    },
+    {
+      "epoch": 1.239795918367347,
+      "grad_norm": 0.3074506613629546,
+      "learning_rate": 7.263969301848188e-06,
+      "loss": 0.7401,
+      "step": 162
+    },
+    {
+      "epoch": 1.2474489795918366,
+      "grad_norm": 0.3522836731747551,
+      "learning_rate": 7.223977558729707e-06,
+      "loss": 0.7235,
+      "step": 163
+    },
+    {
+      "epoch": 1.2551020408163265,
+      "grad_norm": 0.320879835567969,
+      "learning_rate": 7.183807654458565e-06,
+      "loss": 0.7269,
+      "step": 164
+    },
+    {
+      "epoch": 1.2627551020408163,
+      "grad_norm": 0.3369884807808652,
+      "learning_rate": 7.143462807015271e-06,
+      "loss": 0.7314,
+      "step": 165
+    },
+    {
+      "epoch": 1.2704081632653061,
+      "grad_norm": 0.3106327480512219,
+      "learning_rate": 7.102946248394908e-06,
+      "loss": 0.7311,
+      "step": 166
+    },
+    {
+      "epoch": 1.278061224489796,
+      "grad_norm": 0.3350969859669365,
+      "learning_rate": 7.0622612243482035e-06,
+      "loss": 0.7454,
+      "step": 167
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.32981543690241394,
+      "learning_rate": 7.021410994121525e-06,
+      "loss": 0.716,
+      "step": 168
+    },
+    {
+      "epoch": 1.2933673469387754,
+      "grad_norm": 0.3124947696287792,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.7227,
+      "step": 169
+    },
+    {
+      "epoch": 1.3010204081632653,
+      "grad_norm": 0.29800502106565513,
+      "learning_rate": 6.939228018024275e-06,
+      "loss": 0.7334,
+      "step": 170
+    },
+    {
+      "epoch": 1.308673469387755,
+      "grad_norm": 0.33815713937721337,
+      "learning_rate": 6.897901855769483e-06,
+      "loss": 0.7138,
+      "step": 171
+    },
+    {
+      "epoch": 1.316326530612245,
+      "grad_norm": 0.307107701344449,
+      "learning_rate": 6.856423654038868e-06,
+      "loss": 0.7267,
+      "step": 172
+    },
+    {
+      "epoch": 1.3239795918367347,
+      "grad_norm": 0.3373642844242084,
+      "learning_rate": 6.814796735619664e-06,
+      "loss": 0.7144,
+      "step": 173
+    },
+    {
+      "epoch": 1.3316326530612246,
+      "grad_norm": 0.2967492516461531,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.7139,
+      "step": 174
+    },
+    {
+      "epoch": 1.3392857142857144,
+      "grad_norm": 0.2944971616996988,
+      "learning_rate": 6.731110099165165e-06,
+      "loss": 0.7417,
+      "step": 175
+    },
+    {
+      "epoch": 1.346938775510204,
+      "grad_norm": 0.293601269092346,
+      "learning_rate": 6.689057085202737e-06,
+      "loss": 0.7292,
+      "step": 176
+    },
+    {
+      "epoch": 1.3545918367346939,
+      "grad_norm": 0.2857412083314722,
+      "learning_rate": 6.646868762160399e-06,
+      "loss": 0.7169,
+      "step": 177
+    },
+    {
+      "epoch": 1.3622448979591837,
+      "grad_norm": 0.2793697266770511,
+      "learning_rate": 6.6045485097126585e-06,
+      "loss": 0.723,
+      "step": 178
+    },
+    {
+      "epoch": 1.3698979591836735,
+      "grad_norm": 0.28168414558063304,
+      "learning_rate": 6.562099718102788e-06,
+      "loss": 0.7111,
+      "step": 179
+    },
+    {
+      "epoch": 1.3775510204081631,
+      "grad_norm": 0.31727867501147977,
+      "learning_rate": 6.519525787871235e-06,
+      "loss": 0.728,
+      "step": 180
+    },
+    {
+      "epoch": 1.385204081632653,
+      "grad_norm": 0.298603631519449,
+      "learning_rate": 6.476830129583207e-06,
+      "loss": 0.7136,
+      "step": 181
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.29156749391023734,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.7229,
+      "step": 182
+    },
+    {
+      "epoch": 1.4005102040816326,
+      "grad_norm": 0.3216966381557731,
+      "learning_rate": 6.391087319582264e-06,
+      "loss": 0.7329,
+      "step": 183
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": 0.3100392635441308,
+      "learning_rate": 6.34804703666072e-06,
+      "loss": 0.6948,
+      "step": 184
+    },
+    {
+      "epoch": 1.4158163265306123,
+      "grad_norm": 0.3205090950935673,
+      "learning_rate": 6.304898762715187e-06,
+      "loss": 0.7185,
+      "step": 185
+    },
+    {
+      "epoch": 1.4234693877551021,
+      "grad_norm": 0.31408394255073874,
+      "learning_rate": 6.261645954321109e-06,
+      "loss": 0.7155,
+      "step": 186
+    },
+    {
+      "epoch": 1.431122448979592,
+      "grad_norm": 0.3615372791973604,
+      "learning_rate": 6.21829207642811e-06,
+      "loss": 0.72,
+      "step": 187
+    },
+    {
+      "epoch": 1.4387755102040816,
+      "grad_norm": 0.3179800138909638,
+      "learning_rate": 6.1748406020824115e-06,
+      "loss": 0.7215,
+      "step": 188
+    },
+    {
+      "epoch": 1.4464285714285714,
+      "grad_norm": 0.39197778035917613,
+      "learning_rate": 6.131295012148613e-06,
+      "loss": 0.7161,
+      "step": 189
+    },
+    {
+      "epoch": 1.4540816326530612,
+      "grad_norm": 0.3475079137600484,
+      "learning_rate": 6.087658795030838e-06,
+      "loss": 0.7212,
+      "step": 190
+    },
+    {
+      "epoch": 1.461734693877551,
+      "grad_norm": 0.3303825779966534,
+      "learning_rate": 6.043935446393294e-06,
+      "loss": 0.7138,
+      "step": 191
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": 0.3397781093231611,
+      "learning_rate": 6.000128468880223e-06,
+      "loss": 0.7357,
+      "step": 192
+    },
+    {
+      "epoch": 1.4770408163265305,
+      "grad_norm": 0.28796995234216377,
+      "learning_rate": 5.956241371835312e-06,
+      "loss": 0.7329,
+      "step": 193
+    },
+    {
+      "epoch": 1.4846938775510203,
+      "grad_norm": 0.33155770096938897,
+      "learning_rate": 5.912277671020564e-06,
+      "loss": 0.7301,
+      "step": 194
+    },
+    {
+      "epoch": 1.4923469387755102,
+      "grad_norm": 0.3094759577498115,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.6932,
+      "step": 195
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.3318537172693951,
+      "learning_rate": 5.824134551530783e-06,
+      "loss": 0.7326,
+      "step": 196
+    },
+    {
+      "epoch": 1.5076530612244898,
+      "grad_norm": 0.30879561481901263,
+      "learning_rate": 5.77996219393409e-06,
+      "loss": 0.7195,
+      "step": 197
+    },
+    {
+      "epoch": 1.5153061224489797,
+      "grad_norm": 0.3303797600701955,
+      "learning_rate": 5.735727354158581e-06,
+      "loss": 0.7353,
+      "step": 198
+    },
+    {
+      "epoch": 1.5229591836734695,
+      "grad_norm": 0.29685163959288646,
+      "learning_rate": 5.6914335758236665e-06,
+      "loss": 0.7262,
+      "step": 199
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 0.3006334315846896,
+      "learning_rate": 5.647084407270277e-06,
+      "loss": 0.725,
+      "step": 200
+    },
+    {
+      "epoch": 1.538265306122449,
+      "grad_norm": 0.3181086382843995,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.717,
+      "step": 201
+    },
+    {
+      "epoch": 1.5459183673469388,
+      "grad_norm": 0.2828538681954745,
+      "learning_rate": 5.5582341147735396e-06,
+      "loss": 0.7134,
+      "step": 202
+    },
+    {
+      "epoch": 1.5535714285714286,
+      "grad_norm": 0.2949909914868706,
+      "learning_rate": 5.5137401085596224e-06,
+      "loss": 0.7334,
+      "step": 203
+    },
+    {
+      "epoch": 1.5612244897959182,
+      "grad_norm": 0.3090417583811012,
+      "learning_rate": 5.469204947015897e-06,
+      "loss": 0.7189,
+      "step": 204
+    },
+    {
+      "epoch": 1.568877551020408,
+      "grad_norm": 0.28811678419113473,
+      "learning_rate": 5.424632197820325e-06,
+      "loss": 0.6947,
+      "step": 205
+    },
+    {
+      "epoch": 1.5765306122448979,
+      "grad_norm": 0.29198617120064,
+      "learning_rate": 5.380025431661981e-06,
+      "loss": 0.7146,
+      "step": 206
+    },
+    {
+      "epoch": 1.5841836734693877,
+      "grad_norm": 0.30576199585440467,
+      "learning_rate": 5.335388221955012e-06,
+      "loss": 0.7131,
+      "step": 207
+    },
+    {
+      "epoch": 1.5918367346938775,
+      "grad_norm": 0.2812362549753351,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.7221,
+      "step": 208
+    },
+    {
+      "epoch": 1.5994897959183674,
+      "grad_norm": 0.2760501677497026,
+      "learning_rate": 5.246036777459391e-06,
+      "loss": 0.7141,
+      "step": 209
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.2688411176432346,
+      "learning_rate": 5.201329700547077e-06,
+      "loss": 0.7154,
+      "step": 210
+    },
+    {
+      "epoch": 1.614795918367347,
+      "grad_norm": 0.30444010616896106,
+      "learning_rate": 5.156606495265402e-06,
+      "loss": 0.7185,
+      "step": 211
+    },
+    {
+      "epoch": 1.6224489795918369,
+      "grad_norm": 0.2834241043348135,
+      "learning_rate": 5.111870744356366e-06,
+      "loss": 0.6954,
+      "step": 212
+    },
+    {
+      "epoch": 1.6301020408163265,
+      "grad_norm": 0.2839078787011765,
+      "learning_rate": 5.067126031566988e-06,
+      "loss": 0.7199,
+      "step": 213
+    },
+    {
+      "epoch": 1.6377551020408163,
+      "grad_norm": 0.2894314952948115,
+      "learning_rate": 5.022375941362218e-06,
+      "loss": 0.7206,
+      "step": 214
+    },
+    {
+      "epoch": 1.6454081632653061,
+      "grad_norm": 0.30105116531481235,
+      "learning_rate": 4.977624058637783e-06,
+      "loss": 0.7104,
+      "step": 215
+    },
+    {
+      "epoch": 1.6530612244897958,
+      "grad_norm": 0.30603121168713104,
+      "learning_rate": 4.932873968433014e-06,
+      "loss": 0.7214,
+      "step": 216
+    },
+    {
+      "epoch": 1.6607142857142856,
+      "grad_norm": 0.2897952522073487,
+      "learning_rate": 4.8881292556436355e-06,
+      "loss": 0.7157,
+      "step": 217
+    },
+    {
+      "epoch": 1.6683673469387754,
+      "grad_norm": 0.3064132815038337,
+      "learning_rate": 4.8433935047346e-06,
+      "loss": 0.7129,
+      "step": 218
+    },
+    {
+      "epoch": 1.6760204081632653,
+      "grad_norm": 0.2729773805617788,
+      "learning_rate": 4.798670299452926e-06,
+      "loss": 0.7228,
+      "step": 219
+    },
+    {
+      "epoch": 1.683673469387755,
+      "grad_norm": 0.2860890205936976,
+      "learning_rate": 4.75396322254061e-06,
+      "loss": 0.7329,
+      "step": 220
+    },
+    {
+      "epoch": 1.691326530612245,
+      "grad_norm": 0.28789253491280553,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.714,
+      "step": 221
+    },
+    {
+      "epoch": 1.6989795918367347,
+      "grad_norm": 0.28710361826225933,
+      "learning_rate": 4.664611778044988e-06,
+      "loss": 0.7269,
+      "step": 222
+    },
+    {
+      "epoch": 1.7066326530612246,
+      "grad_norm": 0.2607466160182967,
+      "learning_rate": 4.619974568338021e-06,
+      "loss": 0.7254,
+      "step": 223
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.3109562373122327,
+      "learning_rate": 4.575367802179675e-06,
+      "loss": 0.7266,
+      "step": 224
+    },
+    {
+      "epoch": 1.7219387755102042,
+      "grad_norm": 0.2671326490442337,
+      "learning_rate": 4.530795052984104e-06,
+      "loss": 0.7402,
+      "step": 225
+    },
+    {
+      "epoch": 1.7295918367346939,
+      "grad_norm": 0.3024449623652671,
+      "learning_rate": 4.48625989144038e-06,
+      "loss": 0.7165,
+      "step": 226
+    },
+    {
+      "epoch": 1.7372448979591837,
+      "grad_norm": 0.29297628220674093,
+      "learning_rate": 4.441765885226462e-06,
+      "loss": 0.7233,
+      "step": 227
+    },
+    {
+      "epoch": 1.7448979591836735,
+      "grad_norm": 0.2703897681423039,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.729,
+      "step": 228
+    },
+    {
+      "epoch": 1.7525510204081631,
+      "grad_norm": 0.30928488016271816,
+      "learning_rate": 4.352915592729723e-06,
+      "loss": 0.7242,
+      "step": 229
+    },
+    {
+      "epoch": 1.760204081632653,
+      "grad_norm": 0.2706286337944358,
+      "learning_rate": 4.308566424176336e-06,
+      "loss": 0.7154,
+      "step": 230
+    },
+    {
+      "epoch": 1.7678571428571428,
+      "grad_norm": 0.260276440616788,
+      "learning_rate": 4.264272645841419e-06,
+      "loss": 0.7079,
+      "step": 231
+    },
+    {
+      "epoch": 1.7755102040816326,
+      "grad_norm": 0.27550251553605226,
+      "learning_rate": 4.220037806065911e-06,
+      "loss": 0.727,
+      "step": 232
+    },
+    {
+      "epoch": 1.7831632653061225,
+      "grad_norm": 0.27167673630299904,
+      "learning_rate": 4.175865448469219e-06,
+      "loss": 0.7284,
+      "step": 233
+    },
+    {
+      "epoch": 1.7908163265306123,
+      "grad_norm": 0.27870909240366326,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7228,
+      "step": 234
+    },
+    {
+      "epoch": 1.7984693877551021,
+      "grad_norm": 0.25737644360984807,
+      "learning_rate": 4.087722328979437e-06,
+      "loss": 0.7248,
+      "step": 235
+    },
+    {
+      "epoch": 1.806122448979592,
+      "grad_norm": 0.2678752125292958,
+      "learning_rate": 4.043758628164688e-06,
+      "loss": 0.7276,
+      "step": 236
+    },
+    {
+      "epoch": 1.8137755102040818,
+      "grad_norm": 0.2937753087166277,
+      "learning_rate": 3.999871531119779e-06,
+      "loss": 0.7172,
+      "step": 237
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.2935500143060239,
+      "learning_rate": 3.956064553606708e-06,
+      "loss": 0.7096,
+      "step": 238
+    },
+    {
+      "epoch": 1.8290816326530612,
+      "grad_norm": 0.2872174760470752,
+      "learning_rate": 3.912341204969164e-06,
+      "loss": 0.7085,
+      "step": 239
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.27257890683898406,
+      "learning_rate": 3.86870498785139e-06,
+      "loss": 0.7079,
+      "step": 240
+    },
+    {
+      "epoch": 1.8443877551020407,
+      "grad_norm": 0.2569539726278704,
+      "learning_rate": 3.825159397917589e-06,
+      "loss": 0.7196,
+      "step": 241
+    },
+    {
+      "epoch": 1.8520408163265305,
+      "grad_norm": 0.27151411294136946,
+      "learning_rate": 3.781707923571891e-06,
+      "loss": 0.7026,
+      "step": 242
+    },
+    {
+      "epoch": 1.8596938775510203,
+      "grad_norm": 0.27930041542818224,
+      "learning_rate": 3.7383540456788915e-06,
+      "loss": 0.7268,
+      "step": 243
+    },
+    {
+      "epoch": 1.8673469387755102,
+      "grad_norm": 0.26864299220619914,
+      "learning_rate": 3.695101237284815e-06,
+      "loss": 0.7248,
+      "step": 244
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.27555317317712996,
+      "learning_rate": 3.6519529633392825e-06,
+      "loss": 0.7084,
+      "step": 245
+    },
+    {
+      "epoch": 1.8826530612244898,
+      "grad_norm": 0.2804770635369131,
+      "learning_rate": 3.6089126804177373e-06,
+      "loss": 0.7355,
+      "step": 246
+    },
+    {
+      "epoch": 1.8903061224489797,
+      "grad_norm": 0.273320036360711,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.7243,
+      "step": 247
+    },
+    {
+      "epoch": 1.8979591836734695,
+      "grad_norm": 0.28634409896833934,
+      "learning_rate": 3.523169870416795e-06,
+      "loss": 0.7144,
+      "step": 248
+    },
+    {
+      "epoch": 1.9056122448979593,
+      "grad_norm": 0.2731707658644953,
+      "learning_rate": 3.480474212128766e-06,
+      "loss": 0.7085,
+      "step": 249
+    },
+    {
+      "epoch": 1.913265306122449,
+      "grad_norm": 0.2856724418711564,
+      "learning_rate": 3.4379002818972122e-06,
+      "loss": 0.6994,
+      "step": 250
+    },
+    {
+      "epoch": 1.9209183673469388,
+      "grad_norm": 0.25169725455713693,
+      "learning_rate": 3.3954514902873427e-06,
+      "loss": 0.7198,
+      "step": 251
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.2707259735033453,
+      "learning_rate": 3.3531312378396026e-06,
+      "loss": 0.7195,
+      "step": 252
+    },
+    {
+      "epoch": 1.9362244897959182,
+      "grad_norm": 0.2575058815163588,
+      "learning_rate": 3.310942914797265e-06,
+      "loss": 0.7221,
+      "step": 253
+    },
+    {
+      "epoch": 1.943877551020408,
+      "grad_norm": 0.2624601348833616,
+      "learning_rate": 3.2688899008348386e-06,
+      "loss": 0.7098,
+      "step": 254
+    },
+    {
+      "epoch": 1.9515306122448979,
+      "grad_norm": 0.26759811934604133,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.715,
+      "step": 255
+    },
+    {
+      "epoch": 1.9591836734693877,
+      "grad_norm": 0.26105450865585245,
+      "learning_rate": 3.1852032643803377e-06,
+      "loss": 0.7115,
+      "step": 256
+    },
+    {
+      "epoch": 1.9668367346938775,
+      "grad_norm": 0.2679020391433801,
+      "learning_rate": 3.143576345961132e-06,
+      "loss": 0.7108,
+      "step": 257
+    },
+    {
+      "epoch": 1.9744897959183674,
+      "grad_norm": 0.2619436598503336,
+      "learning_rate": 3.1020981442305187e-06,
+      "loss": 0.7177,
+      "step": 258
+    },
+    {
+      "epoch": 1.9821428571428572,
+      "grad_norm": 0.28254050960476124,
+      "learning_rate": 3.0607719819757264e-06,
+      "loss": 0.714,
+      "step": 259
+    },
+    {
+      "epoch": 1.989795918367347,
+      "grad_norm": 0.25168812703672494,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.6937,
+      "step": 260
+    },
+    {
+      "epoch": 1.9974489795918369,
+      "grad_norm": 0.25916481234256045,
+      "learning_rate": 2.978589005878476e-06,
+      "loss": 0.728,
+      "step": 261
+    },
+    {
+      "epoch": 2.0051020408163267,
+      "grad_norm": 0.29079133938515395,
+      "learning_rate": 2.937738775651798e-06,
+      "loss": 0.712,
+      "step": 262
+    },
+    {
+      "epoch": 2.0127551020408165,
+      "grad_norm": 0.30679942022688345,
+      "learning_rate": 2.8970537516050935e-06,
+      "loss": 0.6888,
+      "step": 263
+    },
+    {
+      "epoch": 2.020408163265306,
+      "grad_norm": 0.26247554064017004,
+      "learning_rate": 2.8565371929847286e-06,
+      "loss": 0.6857,
+      "step": 264
+    },
+    {
+      "epoch": 2.0280612244897958,
+      "grad_norm": 0.25777996123866176,
+      "learning_rate": 2.816192345541437e-06,
+      "loss": 0.67,
+      "step": 265
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 0.27157311348157104,
+      "learning_rate": 2.776022441270295e-06,
+      "loss": 0.677,
+      "step": 266
+    },
+    {
+      "epoch": 2.0433673469387754,
+      "grad_norm": 0.2906167681301434,
+      "learning_rate": 2.736030698151815e-06,
+      "loss": 0.6901,
+      "step": 267
+    },
+    {
+      "epoch": 2.0510204081632653,
+      "grad_norm": 0.2682203092623702,
+      "learning_rate": 2.6962203198941587e-06,
+      "loss": 0.6799,
+      "step": 268
+    },
+    {
+      "epoch": 2.058673469387755,
+      "grad_norm": 0.26952637185558564,
+      "learning_rate": 2.656594495676482e-06,
+      "loss": 0.6867,
+      "step": 269
+    },
+    {
+      "epoch": 2.066326530612245,
+      "grad_norm": 0.2976523762247378,
+      "learning_rate": 2.6171563998934605e-06,
+      "loss": 0.6798,
+      "step": 270
+    },
+    {
+      "epoch": 2.0739795918367347,
+      "grad_norm": 0.2952839578045796,
+      "learning_rate": 2.577909191900988e-06,
+      "loss": 0.6775,
+      "step": 271
+    },
+    {
+      "epoch": 2.0816326530612246,
+      "grad_norm": 0.26694864359766846,
+      "learning_rate": 2.5388560157630765e-06,
+      "loss": 0.687,
+      "step": 272
+    },
+    {
+      "epoch": 2.0892857142857144,
+      "grad_norm": 0.2846824142546979,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.6933,
+      "step": 273
+    },
+    {
+      "epoch": 2.0969387755102042,
+      "grad_norm": 0.2603852023863315,
+      "learning_rate": 2.4613442573376625e-06,
+      "loss": 0.6932,
+      "step": 274
+    },
+    {
+      "epoch": 2.104591836734694,
+      "grad_norm": 0.25484664824654074,
+      "learning_rate": 2.422891884458241e-06,
+      "loss": 0.686,
+      "step": 275
+    },
+    {
+      "epoch": 2.1122448979591835,
+      "grad_norm": 0.26504213354211553,
+      "learning_rate": 2.384645961752113e-06,
+      "loss": 0.6794,
+      "step": 276
+    },
+    {
+      "epoch": 2.1198979591836733,
+      "grad_norm": 0.25708180544743425,
+      "learning_rate": 2.346609553071093e-06,
+      "loss": 0.6757,
+      "step": 277
+    },
+    {
+      "epoch": 2.127551020408163,
+      "grad_norm": 0.2495286574798052,
+      "learning_rate": 2.308785705482982e-06,
+      "loss": 0.6904,
+      "step": 278
+    },
+    {
+      "epoch": 2.135204081632653,
+      "grad_norm": 0.258995496102722,
+      "learning_rate": 2.2711774490274767e-06,
+      "loss": 0.6816,
+      "step": 279
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.26920967816385,
+      "learning_rate": 2.2337877964734324e-06,
+      "loss": 0.6798,
+      "step": 280
+    },
+    {
+      "epoch": 2.1505102040816326,
+      "grad_norm": 0.25763183428685615,
+      "learning_rate": 2.1966197430775056e-06,
+      "loss": 0.6861,
+      "step": 281
+    },
+    {
+      "epoch": 2.1581632653061225,
+      "grad_norm": 0.2476928851183991,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.6929,
+      "step": 282
+    },
+    {
+      "epoch": 2.1658163265306123,
+      "grad_norm": 0.2509285445340273,
+      "learning_rate": 2.122960325787432e-06,
+      "loss": 0.6828,
+      "step": 283
+    },
+    {
+      "epoch": 2.173469387755102,
+      "grad_norm": 0.2507947715753146,
+      "learning_rate": 2.086474862693244e-06,
+      "loss": 0.6871,
+      "step": 284
+    },
+    {
+      "epoch": 2.181122448979592,
+      "grad_norm": 0.2630733156124699,
+      "learning_rate": 2.050222799884387e-06,
+      "loss": 0.6799,
+      "step": 285
+    },
+    {
+      "epoch": 2.188775510204082,
+      "grad_norm": 0.26301976727268556,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.6858,
+      "step": 286
+    },
+    {
+      "epoch": 2.1964285714285716,
+      "grad_norm": 0.24578041007237145,
+      "learning_rate": 1.9784304726933384e-06,
+      "loss": 0.6787,
+      "step": 287
+    },
+    {
+      "epoch": 2.204081632653061,
+      "grad_norm": 0.2461786949708224,
+      "learning_rate": 1.942895959539939e-06,
+      "loss": 0.6994,
+      "step": 288
+    },
+    {
+      "epoch": 2.211734693877551,
+      "grad_norm": 0.24930437639531394,
+      "learning_rate": 1.9076063486687256e-06,
+      "loss": 0.6958,
+      "step": 289
+    },
+    {
+      "epoch": 2.2193877551020407,
+      "grad_norm": 0.24702757253020044,
+      "learning_rate": 1.8725644671036125e-06,
+      "loss": 0.6841,
+      "step": 290
+    },
+    {
+      "epoch": 2.2270408163265305,
+      "grad_norm": 0.24810798041544824,
+      "learning_rate": 1.8377731220231144e-06,
+      "loss": 0.6817,
+      "step": 291
+    },
+    {
+      "epoch": 2.2346938775510203,
+      "grad_norm": 0.2398463945344876,
+      "learning_rate": 1.803235100535452e-06,
+      "loss": 0.6928,
+      "step": 292
+    },
+    {
+      "epoch": 2.24234693877551,
+      "grad_norm": 0.25536410312526053,
+      "learning_rate": 1.7689531694552863e-06,
+      "loss": 0.6924,
+      "step": 293
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.24193948267148485,
+      "learning_rate": 1.7349300750820758e-06,
+      "loss": 0.7014,
+      "step": 294
+    },
+    {
+      "epoch": 2.25765306122449,
+      "grad_norm": 0.25314351545479186,
+      "learning_rate": 1.7011685429800596e-06,
+      "loss": 0.6829,
+      "step": 295
+    },
+    {
+      "epoch": 2.2653061224489797,
+      "grad_norm": 0.2557447381261113,
+      "learning_rate": 1.6676712777599275e-06,
+      "loss": 0.686,
+      "step": 296
+    },
+    {
+      "epoch": 2.2729591836734695,
+      "grad_norm": 0.24015367436036683,
+      "learning_rate": 1.6344409628621482e-06,
+      "loss": 0.6977,
+      "step": 297
+    },
+    {
+      "epoch": 2.2806122448979593,
+      "grad_norm": 0.24549848915323214,
+      "learning_rate": 1.6014802603420044e-06,
+      "loss": 0.6929,
+      "step": 298
+    },
+    {
+      "epoch": 2.288265306122449,
+      "grad_norm": 0.2554793618240299,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.6917,
+      "step": 299
+    },
+    {
+      "epoch": 2.295918367346939,
+      "grad_norm": 0.23893288637534513,
+      "learning_rate": 1.5363782324520033e-06,
+      "loss": 0.6919,
+      "step": 300
+    },
+    {
+      "epoch": 2.3035714285714284,
+      "grad_norm": 0.2564714188554446,
+      "learning_rate": 1.504242122356143e-06,
+      "loss": 0.7097,
+      "step": 301
+    },
+    {
+      "epoch": 2.311224489795918,
+      "grad_norm": 0.24283921622086807,
+      "learning_rate": 1.4723860547681163e-06,
+      "loss": 0.6849,
+      "step": 302
+    },
+    {
+      "epoch": 2.318877551020408,
+      "grad_norm": 0.26173546523391394,
+      "learning_rate": 1.4408125816532981e-06,
+      "loss": 0.6993,
+      "step": 303
+    },
+    {
+      "epoch": 2.326530612244898,
+      "grad_norm": 0.25486241688912814,
+      "learning_rate": 1.4095242323386305e-06,
+      "loss": 0.6788,
+      "step": 304
+    },
+    {
+      "epoch": 2.3341836734693877,
+      "grad_norm": 0.2361817323877386,
+      "learning_rate": 1.3785235133100088e-06,
+      "loss": 0.6905,
+      "step": 305
+    },
+    {
+      "epoch": 2.3418367346938775,
+      "grad_norm": 0.24162144820607892,
+      "learning_rate": 1.347812908011485e-06,
+      "loss": 0.6841,
+      "step": 306
+    },
+    {
+      "epoch": 2.3494897959183674,
+      "grad_norm": 0.2490597468001364,
+      "learning_rate": 1.3173948766463146e-06,
+      "loss": 0.6802,
+      "step": 307
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.25398677763039623,
+      "learning_rate": 1.2872718559798852e-06,
+      "loss": 0.6886,
+      "step": 308
+    },
+    {
+      "epoch": 2.364795918367347,
+      "grad_norm": 0.23490252476576118,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 0.6868,
+      "step": 309
+    },
+    {
+      "epoch": 2.372448979591837,
+      "grad_norm": 0.23763836546961506,
+      "learning_rate": 1.2279204754460494e-06,
+      "loss": 0.6941,
+      "step": 310
+    },
+    {
+      "epoch": 2.3801020408163267,
+      "grad_norm": 0.2355524230958337,
+      "learning_rate": 1.1986968701726492e-06,
+      "loss": 0.6915,
+      "step": 311
+    },
+    {
+      "epoch": 2.387755102040816,
+      "grad_norm": 0.24752535017353638,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.6921,
+      "step": 312
+    },
+    {
+      "epoch": 2.395408163265306,
+      "grad_norm": 0.2471974082020202,
+      "learning_rate": 1.141165534829425e-06,
+      "loss": 0.6893,
+      "step": 313
+    },
+    {
+      "epoch": 2.4030612244897958,
+      "grad_norm": 0.23381448120221882,
+      "learning_rate": 1.1128624135511712e-06,
+      "loss": 0.6731,
+      "step": 314
+    },
+    {
+      "epoch": 2.4107142857142856,
+      "grad_norm": 0.2389896648493918,
+      "learning_rate": 1.0848706879118893e-06,
+      "loss": 0.6969,
+      "step": 315
+    },
+    {
+      "epoch": 2.4183673469387754,
+      "grad_norm": 0.24224169159980133,
+      "learning_rate": 1.057192600307456e-06,
+      "loss": 0.6955,
+      "step": 316
+    },
+    {
+      "epoch": 2.4260204081632653,
+      "grad_norm": 0.24100521101649902,
+      "learning_rate": 1.0298303680084448e-06,
+      "loss": 0.6896,
+      "step": 317
+    },
+    {
+      "epoch": 2.433673469387755,
+      "grad_norm": 0.2344749626752725,
+      "learning_rate": 1.0027861829824953e-06,
+      "loss": 0.6819,
+      "step": 318
+    },
+    {
+      "epoch": 2.441326530612245,
+      "grad_norm": 0.2319344660343658,
+      "learning_rate": 9.760622117187234e-07,
+      "loss": 0.6786,
+      "step": 319
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.23391479387830102,
+      "learning_rate": 9.496605950541676e-07,
+      "loss": 0.7039,
+      "step": 320
+    },
+    {
+      "epoch": 2.4566326530612246,
+      "grad_norm": 0.23186779062668114,
+      "learning_rate": 9.235834480022788e-07,
+      "loss": 0.688,
+      "step": 321
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 0.23669253409024169,
+      "learning_rate": 8.978328595834984e-07,
+      "loss": 0.7044,
+      "step": 322
+    },
+    {
+      "epoch": 2.4719387755102042,
+      "grad_norm": 0.24077368080825076,
+      "learning_rate": 8.724108926579e-07,
+      "loss": 0.6872,
+      "step": 323
+    },
+    {
+      "epoch": 2.479591836734694,
+      "grad_norm": 0.2388246013777763,
+      "learning_rate": 8.473195837599419e-07,
+      "loss": 0.6916,
+      "step": 324
+    },
+    {
+      "epoch": 2.487244897959184,
+      "grad_norm": 0.24710155251980784,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.684,
+      "step": 325
+    },
+    {
+      "epoch": 2.4948979591836733,
+      "grad_norm": 0.24220633252180443,
+      "learning_rate": 7.981369535799354e-07,
+      "loss": 0.6879,
+      "step": 326
+    },
+    {
+      "epoch": 2.502551020408163,
+      "grad_norm": 0.2302557057062771,
+      "learning_rate": 7.740495722810271e-07,
+      "loss": 0.7039,
+      "step": 327
+    },
+    {
+      "epoch": 2.510204081632653,
+      "grad_norm": 0.24237334538109565,
+      "learning_rate": 7.50300728660407e-07,
+      "loss": 0.6929,
+      "step": 328
+    },
+    {
+      "epoch": 2.517857142857143,
+      "grad_norm": 0.23815797746653947,
+      "learning_rate": 7.26892325219899e-07,
+      "loss": 0.6959,
+      "step": 329
+    },
+    {
+      "epoch": 2.5255102040816326,
+      "grad_norm": 0.23135128489800952,
+      "learning_rate": 7.03826237188916e-07,
+      "loss": 0.675,
+      "step": 330
+    },
+    {
+      "epoch": 2.5331632653061225,
+      "grad_norm": 0.22784611175554673,
+      "learning_rate": 6.811043123742494e-07,
+      "loss": 0.6977,
+      "step": 331
+    },
+    {
+      "epoch": 2.5408163265306123,
+      "grad_norm": 0.2405465208719118,
+      "learning_rate": 6.587283710120324e-07,
+      "loss": 0.6749,
+      "step": 332
+    },
+    {
+      "epoch": 2.548469387755102,
+      "grad_norm": 0.2309843149804867,
+      "learning_rate": 6.367002056219285e-07,
+      "loss": 0.6909,
+      "step": 333
+    },
+    {
+      "epoch": 2.556122448979592,
+      "grad_norm": 0.22895030021484628,
+      "learning_rate": 6.150215808635334e-07,
+      "loss": 0.6832,
+      "step": 334
+    },
+    {
+      "epoch": 2.563775510204082,
+      "grad_norm": 0.22696479172732587,
+      "learning_rate": 5.936942333950063e-07,
+      "loss": 0.6746,
+      "step": 335
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.22839398316256343,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.6866,
+      "step": 336
+    },
+    {
+      "epoch": 2.579081632653061,
+      "grad_norm": 0.22787946605540033,
+      "learning_rate": 5.521001761205441e-07,
+      "loss": 0.6995,
+      "step": 337
+    },
+    {
+      "epoch": 2.586734693877551,
+      "grad_norm": 0.22190853543659503,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.6785,
+      "step": 338
+    },
+    {
+      "epoch": 2.5943877551020407,
+      "grad_norm": 0.23020833242127728,
+      "learning_rate": 5.119313618049309e-07,
+      "loss": 0.6965,
+      "step": 339
+    },
+    {
+      "epoch": 2.6020408163265305,
+      "grad_norm": 0.24859089494546147,
+      "learning_rate": 4.9238546099592e-07,
+      "loss": 0.6799,
+      "step": 340
+    },
+    {
+      "epoch": 2.6096938775510203,
+      "grad_norm": 0.24590659281484603,
+      "learning_rate": 4.732006617631729e-07,
+      "loss": 0.6705,
+      "step": 341
+    },
+    {
+      "epoch": 2.61734693877551,
+      "grad_norm": 0.23193659731275013,
+      "learning_rate": 4.54378500986381e-07,
+      "loss": 0.6899,
+      "step": 342
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.22818730097649043,
+      "learning_rate": 4.35920486494546e-07,
+      "loss": 0.6735,
+      "step": 343
+    },
+    {
+      "epoch": 2.63265306122449,
+      "grad_norm": 0.23430936758279247,
+      "learning_rate": 4.1782809694518533e-07,
+      "loss": 0.691,
+      "step": 344
+    },
+    {
+      "epoch": 2.6403061224489797,
+      "grad_norm": 0.22808387025349178,
+      "learning_rate": 4.001027817058789e-07,
+      "loss": 0.6862,
+      "step": 345
+    },
+    {
+      "epoch": 2.6479591836734695,
+      "grad_norm": 0.22146676723869588,
+      "learning_rate": 3.8274596073816784e-07,
+      "loss": 0.6863,
+      "step": 346
+    },
+    {
+      "epoch": 2.6556122448979593,
+      "grad_norm": 0.22664786178462878,
+      "learning_rate": 3.657590244837911e-07,
+      "loss": 0.6849,
+      "step": 347
+    },
+    {
+      "epoch": 2.663265306122449,
+      "grad_norm": 0.23451188263459435,
+      "learning_rate": 3.49143333753309e-07,
+      "loss": 0.6877,
+      "step": 348
+    },
+    {
+      "epoch": 2.670918367346939,
+      "grad_norm": 0.24867897398782676,
+      "learning_rate": 3.3290021961708163e-07,
+      "loss": 0.6802,
+      "step": 349
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.22314324400743446,
+      "learning_rate": 3.1703098329864237e-07,
+      "loss": 0.6824,
+      "step": 350
+    },
+    {
+      "epoch": 2.686224489795918,
+      "grad_norm": 0.2236801602770835,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.6928,
+      "step": 351
+    },
+    {
+      "epoch": 2.693877551020408,
+      "grad_norm": 0.2385665875720026,
+      "learning_rate": 2.864191991520848e-07,
+      "loss": 0.6846,
+      "step": 352
+    },
+    {
+      "epoch": 2.701530612244898,
+      "grad_norm": 0.23375450743740805,
+      "learning_rate": 2.71679103610738e-07,
+      "loss": 0.6909,
+      "step": 353
+    },
+    {
+      "epoch": 2.7091836734693877,
+      "grad_norm": 0.22520474139439234,
+      "learning_rate": 2.573177902642726e-07,
+      "loss": 0.6788,
+      "step": 354
+    },
+    {
+      "epoch": 2.7168367346938775,
+      "grad_norm": 0.22804273783537157,
+      "learning_rate": 2.4333640958659144e-07,
+      "loss": 0.7087,
+      "step": 355
+    },
+    {
+      "epoch": 2.7244897959183674,
+      "grad_norm": 0.22739247348429448,
+      "learning_rate": 2.2973608161547755e-07,
+      "loss": 0.695,
+      "step": 356
+    },
+    {
+      "epoch": 2.732142857142857,
+      "grad_norm": 0.23455037703234047,
+      "learning_rate": 2.1651789586287442e-07,
+      "loss": 0.6805,
+      "step": 357
+    },
+    {
+      "epoch": 2.739795918367347,
+      "grad_norm": 0.23159720573508338,
+      "learning_rate": 2.0368291122759898e-07,
+      "loss": 0.6891,
+      "step": 358
+    },
+    {
+      "epoch": 2.747448979591837,
+      "grad_norm": 0.22563711327867858,
+      "learning_rate": 1.9123215591052014e-07,
+      "loss": 0.6874,
+      "step": 359
+    },
+    {
+      "epoch": 2.7551020408163263,
+      "grad_norm": 0.2244203065125607,
+      "learning_rate": 1.7916662733218848e-07,
+      "loss": 0.6779,
+      "step": 360
+    },
+    {
+      "epoch": 2.762755102040816,
+      "grad_norm": 0.22559981924958145,
+      "learning_rate": 1.6748729205293024e-07,
+      "loss": 0.6673,
+      "step": 361
+    },
+    {
+      "epoch": 2.770408163265306,
+      "grad_norm": 0.23162805532792882,
+      "learning_rate": 1.5619508569542363e-07,
+      "loss": 0.6607,
+      "step": 362
+    },
+    {
+      "epoch": 2.7780612244897958,
+      "grad_norm": 0.23717254901729207,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 0.6771,
+      "step": 363
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.22534766714917717,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.6853,
+      "step": 364
+    },
+    {
+      "epoch": 2.7933673469387754,
+      "grad_norm": 0.23074216180625626,
+      "learning_rate": 1.2465013075879884e-07,
+      "loss": 0.6898,
+      "step": 365
+    },
+    {
+      "epoch": 2.8010204081632653,
+      "grad_norm": 0.23196388562982978,
+      "learning_rate": 1.1491517499091498e-07,
+      "loss": 0.6936,
+      "step": 366
+    },
+    {
+      "epoch": 2.808673469387755,
+      "grad_norm": 0.2358477783756292,
+      "learning_rate": 1.055715596571405e-07,
+      "loss": 0.6814,
+      "step": 367
+    },
+    {
+      "epoch": 2.816326530612245,
+      "grad_norm": 0.22714752868258517,
+      "learning_rate": 9.662003326740166e-08,
+      "loss": 0.6808,
+      "step": 368
+    },
+    {
+      "epoch": 2.8239795918367347,
+      "grad_norm": 0.21518858671804875,
+      "learning_rate": 8.80613129216762e-08,
+      "loss": 0.6754,
+      "step": 369
+    },
+    {
+      "epoch": 2.8316326530612246,
+      "grad_norm": 0.23291929200714853,
+      "learning_rate": 7.989608425254924e-08,
+      "loss": 0.6787,
+      "step": 370
+    },
+    {
+      "epoch": 2.8392857142857144,
+      "grad_norm": 0.22181996825718708,
+      "learning_rate": 7.212500137028789e-08,
+      "loss": 0.6894,
+      "step": 371
+    },
+    {
+      "epoch": 2.8469387755102042,
+      "grad_norm": 0.22193037565442786,
+      "learning_rate": 6.474868681043578e-08,
+      "loss": 0.6698,
+      "step": 372
+    },
+    {
+      "epoch": 2.854591836734694,
+      "grad_norm": 0.22934416722405232,
+      "learning_rate": 5.776773148394976e-08,
+      "loss": 0.6952,
+      "step": 373
+    },
+    {
+      "epoch": 2.862244897959184,
+      "grad_norm": 0.22584203654514134,
+      "learning_rate": 5.1182694629857145e-08,
+      "loss": 0.6957,
+      "step": 374
+    },
+    {
+      "epoch": 2.8698979591836737,
+      "grad_norm": 0.22461460701111055,
+      "learning_rate": 4.499410377045765e-08,
+      "loss": 0.6886,
+      "step": 375
+    },
+    {
+      "epoch": 2.877551020408163,
+      "grad_norm": 0.22733876386433874,
+      "learning_rate": 3.9202454669063915e-08,
+      "loss": 0.6977,
+      "step": 376
+    },
+    {
+      "epoch": 2.885204081632653,
+      "grad_norm": 0.22962431221391724,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.698,
+      "step": 377
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 0.23151231532840025,
+      "learning_rate": 2.8811805762860578e-08,
+      "loss": 0.6915,
+      "step": 378
+    },
+    {
+      "epoch": 2.9005102040816326,
+      "grad_norm": 0.22229087776784215,
+      "learning_rate": 2.4213638345040868e-08,
+      "loss": 0.6814,
+      "step": 379
+    },
+    {
+      "epoch": 2.9081632653061225,
+      "grad_norm": 0.2266877035262688,
+      "learning_rate": 2.0014077392525035e-08,
+      "loss": 0.6795,
+      "step": 380
+    },
+    {
+      "epoch": 2.9158163265306123,
+      "grad_norm": 0.2250462204085745,
+      "learning_rate": 1.6213459328950355e-08,
+      "loss": 0.6788,
+      "step": 381
+    },
+    {
+      "epoch": 2.923469387755102,
+      "grad_norm": 0.23211476979219928,
+      "learning_rate": 1.2812088618942009e-08,
+      "loss": 0.6957,
+      "step": 382
+    },
+    {
+      "epoch": 2.931122448979592,
+      "grad_norm": 0.22076310527156465,
+      "learning_rate": 9.810237743724805e-09,
+      "loss": 0.6813,
+      "step": 383
+    },
+    {
+      "epoch": 2.938775510204082,
+      "grad_norm": 0.2275087137841747,
+      "learning_rate": 7.2081471792911914e-09,
+      "loss": 0.685,
+      "step": 384
+    },
+    {
+      "epoch": 2.946428571428571,
+      "grad_norm": 0.22791650362368526,
+      "learning_rate": 5.006025377138901e-09,
+      "loss": 0.6748,
+      "step": 385
+    },
+    {
+      "epoch": 2.954081632653061,
+      "grad_norm": 0.22210915099031533,
+      "learning_rate": 3.204048747573185e-09,
+      "loss": 0.6824,
+      "step": 386
+    },
+    {
+      "epoch": 2.961734693877551,
+      "grad_norm": 0.22179326719231918,
+      "learning_rate": 1.8023616455731253e-09,
+      "loss": 0.6791,
+      "step": 387
+    },
+    {
+      "epoch": 2.9693877551020407,
+      "grad_norm": 0.21982432832999604,
+      "learning_rate": 8.010763592264381e-10,
+      "loss": 0.6825,
+      "step": 388
+    },
+    {
+      "epoch": 2.9770408163265305,
+      "grad_norm": 0.23354611683548948,
+      "learning_rate": 2.0027310073833516e-10,
+      "loss": 0.6797,
+      "step": 389
+    },
+    {
+      "epoch": 2.9846938775510203,
+      "grad_norm": 0.22225271783019312,
+      "learning_rate": 0.0,
+      "loss": 0.6847,
+      "step": 390
+    },
+    {
+      "epoch": 2.9846938775510203,
+      "step": 390,
+      "total_flos": 1.3384682412693258e+18,
+      "train_loss": 0.7546794874545856,
+      "train_runtime": 13624.8324,
+      "train_samples_per_second": 2.76,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 390,
+  "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": 1.3384682412693258e+18,
+  "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 sha256:9a635bebe28a3e0b4726979bdaca0c4799dbb244e9dd74c76b4d453d721cc19b
+size 7416