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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-Coder-7B-Instruct-num07
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen2.5-Coder-7B-Instruct-num07
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the fim_midtrain_v1, the fim_midtrain_v2, the fim_midtrain_v3_pairs and the fim_midtrain_v3_triples datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

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": 1.0,
+    "total_flos": 1.1092292323919266e+19,
+    "train_loss": 0.46906891030845593,
+    "train_runtime": 81648.0087,
+    "train_samples_per_second": 7.765,
+    "train_steps_per_second": 0.061
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9de7cf9935efba400feb2caf964cd1767fc7e139ced1775a6aee3ae94341365
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1446f57e4c40c3e983f040fd9624f527d73330856ec311379490e770ec4d84ba
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f76ba4ac2b7bb4f0db108eb2a0bb8d906409cc249582a65a4c8c09960a11b3
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f6a8dac714001399197b46646a91ee4b665bf15aaa28aeb8f83012d51fcc70
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "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": "<|im_end|>",
+    "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1092292323919266e+19,
+    "train_loss": 0.46906891030845593,
+    "train_runtime": 81648.0087,
+    "train_samples_per_second": 7.765,
+    "train_steps_per_second": 0.061
+}

trainer_log.jsonl

@@ -0,0 +1,496 @@
+{"current_steps": 10, "total_steps": 4954, "loss": 0.7881, "lr": 1.8145161290322583e-07, "epoch": 0.002018927444794953, "percentage": 0.2, "elapsed_time": "0:03:08", "remaining_time": "1 day, 1:50:39"}
+{"current_steps": 20, "total_steps": 4954, "loss": 0.8121, "lr": 3.830645161290323e-07, "epoch": 0.004037854889589906, "percentage": 0.4, "elapsed_time": "0:05:57", "remaining_time": "1 day, 0:29:13"}
+{"current_steps": 30, "total_steps": 4954, "loss": 0.7797, "lr": 5.846774193548388e-07, "epoch": 0.006056782334384858, "percentage": 0.61, "elapsed_time": "0:08:29", "remaining_time": "23:13:13"}
+{"current_steps": 40, "total_steps": 4954, "loss": 0.7318, "lr": 7.862903225806453e-07, "epoch": 0.008075709779179811, "percentage": 0.81, "elapsed_time": "0:11:30", "remaining_time": "23:33:48"}
+{"current_steps": 50, "total_steps": 4954, "loss": 0.7018, "lr": 9.879032258064516e-07, "epoch": 0.010094637223974764, "percentage": 1.01, "elapsed_time": "0:13:58", "remaining_time": "22:51:13"}
+{"current_steps": 60, "total_steps": 4954, "loss": 0.6708, "lr": 1.1895161290322582e-06, "epoch": 0.012113564668769715, "percentage": 1.21, "elapsed_time": "0:17:01", "remaining_time": "23:09:11"}
+{"current_steps": 70, "total_steps": 4954, "loss": 0.6417, "lr": 1.3911290322580644e-06, "epoch": 0.014132492113564668, "percentage": 1.41, "elapsed_time": "0:19:48", "remaining_time": "23:02:22"}
+{"current_steps": 80, "total_steps": 4954, "loss": 0.6227, "lr": 1.5927419354838712e-06, "epoch": 0.016151419558359623, "percentage": 1.61, "elapsed_time": "0:22:23", "remaining_time": "22:44:22"}
+{"current_steps": 90, "total_steps": 4954, "loss": 0.615, "lr": 1.7943548387096777e-06, "epoch": 0.018170347003154574, "percentage": 1.82, "elapsed_time": "0:25:25", "remaining_time": "22:53:48"}
+{"current_steps": 100, "total_steps": 4954, "loss": 0.6105, "lr": 1.9959677419354837e-06, "epoch": 0.02018927444794953, "percentage": 2.02, "elapsed_time": "0:27:53", "remaining_time": "22:34:06"}
+{"current_steps": 110, "total_steps": 4954, "loss": 0.5911, "lr": 2.1975806451612907e-06, "epoch": 0.02220820189274448, "percentage": 2.22, "elapsed_time": "0:30:55", "remaining_time": "22:42:06"}
+{"current_steps": 120, "total_steps": 4954, "loss": 0.5921, "lr": 2.399193548387097e-06, "epoch": 0.02422712933753943, "percentage": 2.42, "elapsed_time": "0:33:40", "remaining_time": "22:36:38"}
+{"current_steps": 130, "total_steps": 4954, "loss": 0.5818, "lr": 2.6008064516129032e-06, "epoch": 0.026246056782334385, "percentage": 2.62, "elapsed_time": "0:36:15", "remaining_time": "22:25:43"}
+{"current_steps": 140, "total_steps": 4954, "loss": 0.5876, "lr": 2.8024193548387097e-06, "epoch": 0.028264984227129336, "percentage": 2.83, "elapsed_time": "0:39:09", "remaining_time": "22:26:35"}
+{"current_steps": 150, "total_steps": 4954, "loss": 0.5728, "lr": 3.0040322580645167e-06, "epoch": 0.03028391167192429, "percentage": 3.03, "elapsed_time": "0:41:31", "remaining_time": "22:09:44"}
+{"current_steps": 160, "total_steps": 4954, "loss": 0.5643, "lr": 3.2056451612903228e-06, "epoch": 0.032302839116719245, "percentage": 3.23, "elapsed_time": "0:44:31", "remaining_time": "22:14:14"}
+{"current_steps": 170, "total_steps": 4954, "loss": 0.5617, "lr": 3.4072580645161293e-06, "epoch": 0.03432176656151419, "percentage": 3.43, "elapsed_time": "0:47:19", "remaining_time": "22:11:44"}
+{"current_steps": 180, "total_steps": 4954, "loss": 0.5501, "lr": 3.6088709677419358e-06, "epoch": 0.03634069400630915, "percentage": 3.63, "elapsed_time": "0:49:52", "remaining_time": "22:02:43"}
+{"current_steps": 190, "total_steps": 4954, "loss": 0.559, "lr": 3.8104838709677423e-06, "epoch": 0.0383596214511041, "percentage": 3.84, "elapsed_time": "0:52:49", "remaining_time": "22:04:39"}
+{"current_steps": 200, "total_steps": 4954, "loss": 0.5601, "lr": 4.012096774193548e-06, "epoch": 0.04037854889589906, "percentage": 4.04, "elapsed_time": "0:55:13", "remaining_time": "21:52:44"}
+{"current_steps": 210, "total_steps": 4954, "loss": 0.546, "lr": 4.213709677419355e-06, "epoch": 0.042397476340694004, "percentage": 4.24, "elapsed_time": "0:58:14", "remaining_time": "21:55:43"}
+{"current_steps": 220, "total_steps": 4954, "loss": 0.5527, "lr": 4.415322580645161e-06, "epoch": 0.04441640378548896, "percentage": 4.44, "elapsed_time": "1:01:04", "remaining_time": "21:54:13"}
+{"current_steps": 230, "total_steps": 4954, "loss": 0.5428, "lr": 4.616935483870968e-06, "epoch": 0.04643533123028391, "percentage": 4.64, "elapsed_time": "1:03:38", "remaining_time": "21:47:17"}
+{"current_steps": 240, "total_steps": 4954, "loss": 0.5338, "lr": 4.818548387096774e-06, "epoch": 0.04845425867507886, "percentage": 4.84, "elapsed_time": "1:06:34", "remaining_time": "21:47:48"}
+{"current_steps": 250, "total_steps": 4954, "loss": 0.5546, "lr": 5.020161290322581e-06, "epoch": 0.050473186119873815, "percentage": 5.05, "elapsed_time": "1:08:59", "remaining_time": "21:38:14"}
+{"current_steps": 260, "total_steps": 4954, "loss": 0.5408, "lr": 5.221774193548388e-06, "epoch": 0.05249211356466877, "percentage": 5.25, "elapsed_time": "1:12:02", "remaining_time": "21:40:34"}
+{"current_steps": 270, "total_steps": 4954, "loss": 0.5427, "lr": 5.423387096774194e-06, "epoch": 0.054511041009463725, "percentage": 5.45, "elapsed_time": "1:14:48", "remaining_time": "21:37:51"}
+{"current_steps": 280, "total_steps": 4954, "loss": 0.5357, "lr": 5.625e-06, "epoch": 0.05652996845425867, "percentage": 5.65, "elapsed_time": "1:17:19", "remaining_time": "21:30:51"}
+{"current_steps": 290, "total_steps": 4954, "loss": 0.5316, "lr": 5.8266129032258064e-06, "epoch": 0.05854889589905363, "percentage": 5.85, "elapsed_time": "1:20:11", "remaining_time": "21:29:40"}
+{"current_steps": 300, "total_steps": 4954, "loss": 0.5444, "lr": 6.028225806451613e-06, "epoch": 0.06056782334384858, "percentage": 6.06, "elapsed_time": "1:22:34", "remaining_time": "21:20:55"}
+{"current_steps": 310, "total_steps": 4954, "loss": 0.5256, "lr": 6.2298387096774194e-06, "epoch": 0.06258675078864354, "percentage": 6.26, "elapsed_time": "1:25:33", "remaining_time": "21:21:35"}
+{"current_steps": 320, "total_steps": 4954, "loss": 0.535, "lr": 6.431451612903226e-06, "epoch": 0.06460567823343849, "percentage": 6.46, "elapsed_time": "1:28:20", "remaining_time": "21:19:16"}
+{"current_steps": 330, "total_steps": 4954, "loss": 0.5281, "lr": 6.633064516129033e-06, "epoch": 0.06662460567823345, "percentage": 6.66, "elapsed_time": "1:30:50", "remaining_time": "21:12:51"}
+{"current_steps": 340, "total_steps": 4954, "loss": 0.5324, "lr": 6.834677419354839e-06, "epoch": 0.06864353312302839, "percentage": 6.86, "elapsed_time": "1:33:51", "remaining_time": "21:13:43"}
+{"current_steps": 350, "total_steps": 4954, "loss": 0.5321, "lr": 7.0362903225806454e-06, "epoch": 0.07066246056782334, "percentage": 7.06, "elapsed_time": "1:36:17", "remaining_time": "21:06:37"}
+{"current_steps": 360, "total_steps": 4954, "loss": 0.5235, "lr": 7.2379032258064515e-06, "epoch": 0.0726813880126183, "percentage": 7.27, "elapsed_time": "1:39:15", "remaining_time": "21:06:35"}
+{"current_steps": 370, "total_steps": 4954, "loss": 0.5203, "lr": 7.4395161290322585e-06, "epoch": 0.07470031545741325, "percentage": 7.47, "elapsed_time": "1:42:01", "remaining_time": "21:03:59"}
+{"current_steps": 380, "total_steps": 4954, "loss": 0.5289, "lr": 7.641129032258065e-06, "epoch": 0.0767192429022082, "percentage": 7.67, "elapsed_time": "1:44:33", "remaining_time": "20:58:30"}
+{"current_steps": 390, "total_steps": 4954, "loss": 0.5199, "lr": 7.842741935483872e-06, "epoch": 0.07873817034700316, "percentage": 7.87, "elapsed_time": "1:47:31", "remaining_time": "20:58:16"}
+{"current_steps": 400, "total_steps": 4954, "loss": 0.5239, "lr": 8.044354838709678e-06, "epoch": 0.08075709779179811, "percentage": 8.07, "elapsed_time": "1:49:55", "remaining_time": "20:51:34"}
+{"current_steps": 410, "total_steps": 4954, "loss": 0.5217, "lr": 8.245967741935484e-06, "epoch": 0.08277602523659305, "percentage": 8.28, "elapsed_time": "1:52:52", "remaining_time": "20:51:01"}
+{"current_steps": 420, "total_steps": 4954, "loss": 0.5187, "lr": 8.447580645161291e-06, "epoch": 0.08479495268138801, "percentage": 8.48, "elapsed_time": "1:55:39", "remaining_time": "20:48:29"}
+{"current_steps": 430, "total_steps": 4954, "loss": 0.5194, "lr": 8.649193548387097e-06, "epoch": 0.08681388012618296, "percentage": 8.68, "elapsed_time": "1:58:17", "remaining_time": "20:44:33"}
+{"current_steps": 440, "total_steps": 4954, "loss": 0.513, "lr": 8.850806451612905e-06, "epoch": 0.08883280757097792, "percentage": 8.88, "elapsed_time": "2:01:12", "remaining_time": "20:43:30"}
+{"current_steps": 450, "total_steps": 4954, "loss": 0.5161, "lr": 9.05241935483871e-06, "epoch": 0.09085173501577287, "percentage": 9.08, "elapsed_time": "2:03:40", "remaining_time": "20:37:50"}
+{"current_steps": 460, "total_steps": 4954, "loss": 0.5033, "lr": 9.254032258064517e-06, "epoch": 0.09287066246056783, "percentage": 9.29, "elapsed_time": "2:06:42", "remaining_time": "20:37:48"}
+{"current_steps": 470, "total_steps": 4954, "loss": 0.5145, "lr": 9.455645161290323e-06, "epoch": 0.09488958990536278, "percentage": 9.49, "elapsed_time": "2:09:30", "remaining_time": "20:35:31"}
+{"current_steps": 480, "total_steps": 4954, "loss": 0.5178, "lr": 9.65725806451613e-06, "epoch": 0.09690851735015772, "percentage": 9.69, "elapsed_time": "2:12:01", "remaining_time": "20:30:37"}
+{"current_steps": 490, "total_steps": 4954, "loss": 0.5069, "lr": 9.858870967741936e-06, "epoch": 0.09892744479495268, "percentage": 9.89, "elapsed_time": "2:15:02", "remaining_time": "20:30:14"}
+{"current_steps": 500, "total_steps": 4954, "loss": 0.5169, "lr": 9.99998882617222e-06, "epoch": 0.10094637223974763, "percentage": 10.09, "elapsed_time": "2:17:31", "remaining_time": "20:25:05"}
+{"current_steps": 510, "total_steps": 4954, "loss": 0.5067, "lr": 9.999790181734308e-06, "epoch": 0.10296529968454259, "percentage": 10.29, "elapsed_time": "2:20:32", "remaining_time": "20:24:37"}
+{"current_steps": 520, "total_steps": 4954, "loss": 0.5152, "lr": 9.999343241367322e-06, "epoch": 0.10498422712933754, "percentage": 10.5, "elapsed_time": "2:23:16", "remaining_time": "20:21:43"}
+{"current_steps": 530, "total_steps": 4954, "loss": 0.5131, "lr": 9.998648027266884e-06, "epoch": 0.1070031545741325, "percentage": 10.7, "elapsed_time": "2:25:47", "remaining_time": "20:17:00"}
+{"current_steps": 540, "total_steps": 4954, "loss": 0.5053, "lr": 9.997704573958209e-06, "epoch": 0.10902208201892745, "percentage": 10.9, "elapsed_time": "2:28:45", "remaining_time": "20:15:58"}
+{"current_steps": 550, "total_steps": 4954, "loss": 0.5083, "lr": 9.996512928294389e-06, "epoch": 0.1110410094637224, "percentage": 11.1, "elapsed_time": "2:31:07", "remaining_time": "20:10:08"}
+{"current_steps": 560, "total_steps": 4954, "loss": 0.4997, "lr": 9.995073149454057e-06, "epoch": 0.11305993690851734, "percentage": 11.3, "elapsed_time": "2:34:10", "remaining_time": "20:09:45"}
+{"current_steps": 570, "total_steps": 4954, "loss": 0.516, "lr": 9.99338530893846e-06, "epoch": 0.1150788643533123, "percentage": 11.51, "elapsed_time": "2:37:02", "remaining_time": "20:07:52"}
+{"current_steps": 580, "total_steps": 4954, "loss": 0.5073, "lr": 9.991449490567901e-06, "epoch": 0.11709779179810725, "percentage": 11.71, "elapsed_time": "2:39:36", "remaining_time": "20:03:43"}
+{"current_steps": 590, "total_steps": 4954, "loss": 0.5014, "lr": 9.989265790477581e-06, "epoch": 0.11911671924290221, "percentage": 11.91, "elapsed_time": "2:42:29", "remaining_time": "20:01:51"}
+{"current_steps": 600, "total_steps": 4954, "loss": 0.5177, "lr": 9.986834317112817e-06, "epoch": 0.12113564668769716, "percentage": 12.11, "elapsed_time": "2:44:52", "remaining_time": "19:56:29"}
+{"current_steps": 610, "total_steps": 4954, "loss": 0.5054, "lr": 9.984155191223663e-06, "epoch": 0.12315457413249212, "percentage": 12.31, "elapsed_time": "2:47:51", "remaining_time": "19:55:24"}
+{"current_steps": 620, "total_steps": 4954, "loss": 0.5086, "lr": 9.981228545858913e-06, "epoch": 0.12517350157728707, "percentage": 12.52, "elapsed_time": "2:50:40", "remaining_time": "19:53:02"}
+{"current_steps": 630, "total_steps": 4954, "loss": 0.5029, "lr": 9.978054526359493e-06, "epoch": 0.12719242902208203, "percentage": 12.72, "elapsed_time": "2:53:14", "remaining_time": "19:49:01"}
+{"current_steps": 640, "total_steps": 4954, "loss": 0.5021, "lr": 9.97463329035124e-06, "epoch": 0.12921135646687698, "percentage": 12.92, "elapsed_time": "2:56:08", "remaining_time": "19:47:20"}
+{"current_steps": 650, "total_steps": 4954, "loss": 0.5077, "lr": 9.970965007737081e-06, "epoch": 0.13123028391167194, "percentage": 13.12, "elapsed_time": "2:58:36", "remaining_time": "19:42:37"}
+{"current_steps": 660, "total_steps": 4954, "loss": 0.4961, "lr": 9.967049860688587e-06, "epoch": 0.1332492113564669, "percentage": 13.32, "elapsed_time": "3:01:35", "remaining_time": "19:41:25"}
+{"current_steps": 670, "total_steps": 4954, "loss": 0.5036, "lr": 9.962888043636931e-06, "epoch": 0.13526813880126182, "percentage": 13.52, "elapsed_time": "3:04:24", "remaining_time": "19:39:07"}
+{"current_steps": 680, "total_steps": 4954, "loss": 0.4972, "lr": 9.958479763263234e-06, "epoch": 0.13728706624605677, "percentage": 13.73, "elapsed_time": "3:06:58", "remaining_time": "19:35:12"}
+{"current_steps": 690, "total_steps": 4954, "loss": 0.4955, "lr": 9.953825238488296e-06, "epoch": 0.13930599369085173, "percentage": 13.93, "elapsed_time": "3:09:54", "remaining_time": "19:33:33"}
+{"current_steps": 700, "total_steps": 4954, "loss": 0.5013, "lr": 9.948924700461727e-06, "epoch": 0.14132492113564668, "percentage": 14.13, "elapsed_time": "3:12:18", "remaining_time": "19:28:42"}
+{"current_steps": 710, "total_steps": 4954, "loss": 0.4945, "lr": 9.94377839255047e-06, "epoch": 0.14334384858044164, "percentage": 14.33, "elapsed_time": "3:15:21", "remaining_time": "19:27:42"}
+{"current_steps": 720, "total_steps": 4954, "loss": 0.5033, "lr": 9.938386570326707e-06, "epoch": 0.1453627760252366, "percentage": 14.53, "elapsed_time": "3:18:06", "remaining_time": "19:25:01"}
+{"current_steps": 730, "total_steps": 4954, "loss": 0.5013, "lr": 9.93274950155518e-06, "epoch": 0.14738170347003154, "percentage": 14.74, "elapsed_time": "3:20:40", "remaining_time": "19:21:09"}
+{"current_steps": 740, "total_steps": 4954, "loss": 0.4923, "lr": 9.926867466179883e-06, "epoch": 0.1494006309148265, "percentage": 14.94, "elapsed_time": "3:23:37", "remaining_time": "19:19:34"}
+{"current_steps": 750, "total_steps": 4954, "loss": 0.5038, "lr": 9.920740756310156e-06, "epoch": 0.15141955835962145, "percentage": 15.14, "elapsed_time": "3:26:00", "remaining_time": "19:14:43"}
+{"current_steps": 760, "total_steps": 4954, "loss": 0.4875, "lr": 9.914369676206195e-06, "epoch": 0.1534384858044164, "percentage": 15.34, "elapsed_time": "3:29:04", "remaining_time": "19:13:47"}
+{"current_steps": 770, "total_steps": 4954, "loss": 0.4939, "lr": 9.907754542263926e-06, "epoch": 0.15545741324921136, "percentage": 15.54, "elapsed_time": "3:31:56", "remaining_time": "19:11:41"}
+{"current_steps": 780, "total_steps": 4954, "loss": 0.501, "lr": 9.900895682999301e-06, "epoch": 0.15747634069400632, "percentage": 15.74, "elapsed_time": "3:34:35", "remaining_time": "19:08:18"}
+{"current_steps": 790, "total_steps": 4954, "loss": 0.4927, "lr": 9.893793439031982e-06, "epoch": 0.15949526813880127, "percentage": 15.95, "elapsed_time": "3:37:33", "remaining_time": "19:06:41"}
+{"current_steps": 800, "total_steps": 4954, "loss": 0.4971, "lr": 9.88644816306842e-06, "epoch": 0.16151419558359623, "percentage": 16.15, "elapsed_time": "3:39:58", "remaining_time": "19:02:15"}
+{"current_steps": 810, "total_steps": 4954, "loss": 0.4981, "lr": 9.878860219884347e-06, "epoch": 0.16353312302839118, "percentage": 16.35, "elapsed_time": "3:42:59", "remaining_time": "19:00:49"}
+{"current_steps": 820, "total_steps": 4954, "loss": 0.4964, "lr": 9.871029986306658e-06, "epoch": 0.1655520504731861, "percentage": 16.55, "elapsed_time": "3:45:49", "remaining_time": "18:58:26"}
+{"current_steps": 830, "total_steps": 4954, "loss": 0.4891, "lr": 9.862957851194694e-06, "epoch": 0.16757097791798106, "percentage": 16.75, "elapsed_time": "3:48:22", "remaining_time": "18:54:45"}
+{"current_steps": 840, "total_steps": 4954, "loss": 0.501, "lr": 9.854644215420933e-06, "epoch": 0.16958990536277602, "percentage": 16.96, "elapsed_time": "3:51:16", "remaining_time": "18:52:43"}
+{"current_steps": 850, "total_steps": 4954, "loss": 0.5012, "lr": 9.846089491851089e-06, "epoch": 0.17160883280757097, "percentage": 17.16, "elapsed_time": "3:53:43", "remaining_time": "18:48:28"}
+{"current_steps": 860, "total_steps": 4954, "loss": 0.501, "lr": 9.837294105323592e-06, "epoch": 0.17362776025236593, "percentage": 17.36, "elapsed_time": "3:56:41", "remaining_time": "18:46:47"}
+{"current_steps": 870, "total_steps": 4954, "loss": 0.5019, "lr": 9.828258492628506e-06, "epoch": 0.17564668769716088, "percentage": 17.56, "elapsed_time": "3:59:25", "remaining_time": "18:43:57"}
+{"current_steps": 880, "total_steps": 4954, "loss": 0.4914, "lr": 9.818983102485832e-06, "epoch": 0.17766561514195583, "percentage": 17.76, "elapsed_time": "4:01:59", "remaining_time": "18:40:18"}
+{"current_steps": 890, "total_steps": 4954, "loss": 0.4874, "lr": 9.809468395523225e-06, "epoch": 0.1796845425867508, "percentage": 17.97, "elapsed_time": "4:04:51", "remaining_time": "18:38:05"}
+{"current_steps": 900, "total_steps": 4954, "loss": 0.4995, "lr": 9.799714844253109e-06, "epoch": 0.18170347003154574, "percentage": 18.17, "elapsed_time": "4:07:17", "remaining_time": "18:33:55"}
+{"current_steps": 910, "total_steps": 4954, "loss": 0.4892, "lr": 9.789722933049227e-06, "epoch": 0.1837223974763407, "percentage": 18.37, "elapsed_time": "4:10:20", "remaining_time": "18:32:28"}
+{"current_steps": 920, "total_steps": 4954, "loss": 0.4909, "lr": 9.779493158122578e-06, "epoch": 0.18574132492113565, "percentage": 18.57, "elapsed_time": "4:13:06", "remaining_time": "18:29:49"}
+{"current_steps": 930, "total_steps": 4954, "loss": 0.4881, "lr": 9.769026027496773e-06, "epoch": 0.1877602523659306, "percentage": 18.77, "elapsed_time": "4:15:43", "remaining_time": "18:26:29"}
+{"current_steps": 940, "total_steps": 4954, "loss": 0.4923, "lr": 9.758322060982813e-06, "epoch": 0.18977917981072556, "percentage": 18.97, "elapsed_time": "4:18:38", "remaining_time": "18:24:27"}
+{"current_steps": 950, "total_steps": 4954, "loss": 0.4912, "lr": 9.747381790153262e-06, "epoch": 0.19179810725552052, "percentage": 19.18, "elapsed_time": "4:21:01", "remaining_time": "18:20:09"}
+{"current_steps": 960, "total_steps": 4954, "loss": 0.4744, "lr": 9.736205758315864e-06, "epoch": 0.19381703470031544, "percentage": 19.38, "elapsed_time": "4:23:57", "remaining_time": "18:18:10"}
+{"current_steps": 970, "total_steps": 4954, "loss": 0.485, "lr": 9.724794520486551e-06, "epoch": 0.1958359621451104, "percentage": 19.58, "elapsed_time": "4:26:47", "remaining_time": "18:15:45"}
+{"current_steps": 980, "total_steps": 4954, "loss": 0.488, "lr": 9.713148643361884e-06, "epoch": 0.19785488958990535, "percentage": 19.78, "elapsed_time": "4:29:18", "remaining_time": "18:12:03"}
+{"current_steps": 990, "total_steps": 4954, "loss": 0.4886, "lr": 9.701268705290907e-06, "epoch": 0.1998738170347003, "percentage": 19.98, "elapsed_time": "4:32:15", "remaining_time": "18:10:07"}
+{"current_steps": 1000, "total_steps": 4954, "loss": 0.4897, "lr": 9.689155296246431e-06, "epoch": 0.20189274447949526, "percentage": 20.19, "elapsed_time": "4:34:42", "remaining_time": "18:06:11"}
+{"current_steps": 1010, "total_steps": 4954, "loss": 0.4809, "lr": 9.67680901779573e-06, "epoch": 0.20391167192429022, "percentage": 20.39, "elapsed_time": "4:37:42", "remaining_time": "18:04:26"}
+{"current_steps": 1020, "total_steps": 4954, "loss": 0.4848, "lr": 9.664230483070669e-06, "epoch": 0.20593059936908517, "percentage": 20.59, "elapsed_time": "4:40:33", "remaining_time": "18:02:05"}
+{"current_steps": 1030, "total_steps": 4954, "loss": 0.4817, "lr": 9.651420316737254e-06, "epoch": 0.20794952681388013, "percentage": 20.79, "elapsed_time": "4:43:08", "remaining_time": "17:58:39"}
+{"current_steps": 1040, "total_steps": 4954, "loss": 0.4927, "lr": 9.638379154964615e-06, "epoch": 0.20996845425867508, "percentage": 20.99, "elapsed_time": "4:46:01", "remaining_time": "17:56:26"}
+{"current_steps": 1050, "total_steps": 4954, "loss": 0.4906, "lr": 9.625107645393398e-06, "epoch": 0.21198738170347003, "percentage": 21.19, "elapsed_time": "4:48:28", "remaining_time": "17:52:33"}
+{"current_steps": 1060, "total_steps": 4954, "loss": 0.4701, "lr": 9.611606447103625e-06, "epoch": 0.214006309148265, "percentage": 21.4, "elapsed_time": "4:51:26", "remaining_time": "17:50:39"}
+{"current_steps": 1070, "total_steps": 4954, "loss": 0.4844, "lr": 9.597876230581946e-06, "epoch": 0.21602523659305994, "percentage": 21.6, "elapsed_time": "4:54:19", "remaining_time": "17:48:21"}
+{"current_steps": 1080, "total_steps": 4954, "loss": 0.4802, "lr": 9.583917677688348e-06, "epoch": 0.2180441640378549, "percentage": 21.8, "elapsed_time": "4:56:54", "remaining_time": "17:45:00"}
+{"current_steps": 1090, "total_steps": 4954, "loss": 0.4822, "lr": 9.56973148162229e-06, "epoch": 0.22006309148264985, "percentage": 22.0, "elapsed_time": "4:59:54", "remaining_time": "17:43:09"}
+{"current_steps": 1100, "total_steps": 4954, "loss": 0.4887, "lr": 9.555318346888287e-06, "epoch": 0.2220820189274448, "percentage": 22.2, "elapsed_time": "5:02:18", "remaining_time": "17:39:12"}
+{"current_steps": 1110, "total_steps": 4954, "loss": 0.4804, "lr": 9.540678989260907e-06, "epoch": 0.22410094637223973, "percentage": 22.41, "elapsed_time": "5:05:10", "remaining_time": "17:36:51"}
+{"current_steps": 1120, "total_steps": 4954, "loss": 0.4776, "lr": 9.525814135749238e-06, "epoch": 0.2261198738170347, "percentage": 22.61, "elapsed_time": "5:08:00", "remaining_time": "17:34:21"}
+{"current_steps": 1130, "total_steps": 4954, "loss": 0.4753, "lr": 9.510724524560783e-06, "epoch": 0.22813880126182964, "percentage": 22.81, "elapsed_time": "5:10:33", "remaining_time": "17:30:58"}
+{"current_steps": 1140, "total_steps": 4954, "loss": 0.4802, "lr": 9.495410905064795e-06, "epoch": 0.2301577287066246, "percentage": 23.01, "elapsed_time": "5:13:26", "remaining_time": "17:28:38"}
+{"current_steps": 1150, "total_steps": 4954, "loss": 0.4826, "lr": 9.479874037755061e-06, "epoch": 0.23217665615141955, "percentage": 23.21, "elapsed_time": "5:15:53", "remaining_time": "17:24:55"}
+{"current_steps": 1160, "total_steps": 4954, "loss": 0.4802, "lr": 9.46411469421214e-06, "epoch": 0.2341955835962145, "percentage": 23.42, "elapsed_time": "5:18:49", "remaining_time": "17:22:45"}
+{"current_steps": 1170, "total_steps": 4954, "loss": 0.4863, "lr": 9.448133657065045e-06, "epoch": 0.23621451104100946, "percentage": 23.62, "elapsed_time": "5:21:39", "remaining_time": "17:20:17"}
+{"current_steps": 1180, "total_steps": 4954, "loss": 0.4785, "lr": 9.431931719952372e-06, "epoch": 0.23823343848580442, "percentage": 23.82, "elapsed_time": "5:24:14", "remaining_time": "17:17:00"}
+{"current_steps": 1190, "total_steps": 4954, "loss": 0.4719, "lr": 9.415509687482892e-06, "epoch": 0.24025236593059937, "percentage": 24.02, "elapsed_time": "5:27:16", "remaining_time": "17:15:09"}
+{"current_steps": 1200, "total_steps": 4954, "loss": 0.4926, "lr": 9.398868375195587e-06, "epoch": 0.24227129337539433, "percentage": 24.22, "elapsed_time": "5:29:47", "remaining_time": "17:11:41"}
+{"current_steps": 1210, "total_steps": 4954, "loss": 0.4741, "lr": 9.382008609519159e-06, "epoch": 0.24429022082018928, "percentage": 24.42, "elapsed_time": "5:32:46", "remaining_time": "17:09:41"}
+{"current_steps": 1220, "total_steps": 4954, "loss": 0.4826, "lr": 9.364931227730978e-06, "epoch": 0.24630914826498423, "percentage": 24.63, "elapsed_time": "5:35:34", "remaining_time": "17:07:04"}
+{"current_steps": 1230, "total_steps": 4954, "loss": 0.4837, "lr": 9.34763707791551e-06, "epoch": 0.2483280757097792, "percentage": 24.83, "elapsed_time": "5:38:08", "remaining_time": "17:03:47"}
+{"current_steps": 1240, "total_steps": 4954, "loss": 0.4834, "lr": 9.330127018922195e-06, "epoch": 0.25034700315457414, "percentage": 25.03, "elapsed_time": "5:41:02", "remaining_time": "17:01:28"}
+{"current_steps": 1250, "total_steps": 4954, "loss": 0.4858, "lr": 9.312401920322793e-06, "epoch": 0.25236593059936907, "percentage": 25.23, "elapsed_time": "5:43:25", "remaining_time": "16:57:39"}
+{"current_steps": 1260, "total_steps": 4954, "loss": 0.4757, "lr": 9.294462662368211e-06, "epoch": 0.25438485804416405, "percentage": 25.43, "elapsed_time": "5:46:26", "remaining_time": "16:55:42"}
+{"current_steps": 1270, "total_steps": 4954, "loss": 0.4783, "lr": 9.276310135944777e-06, "epoch": 0.256403785488959, "percentage": 25.64, "elapsed_time": "5:49:15", "remaining_time": "16:53:08"}
+{"current_steps": 1280, "total_steps": 4954, "loss": 0.4785, "lr": 9.257945242530002e-06, "epoch": 0.25842271293375396, "percentage": 25.84, "elapsed_time": "5:51:51", "remaining_time": "16:49:55"}
+{"current_steps": 1290, "total_steps": 4954, "loss": 0.4786, "lr": 9.239368894147812e-06, "epoch": 0.2604416403785489, "percentage": 26.04, "elapsed_time": "5:54:50", "remaining_time": "16:47:51"}
+{"current_steps": 1300, "total_steps": 4954, "loss": 0.4807, "lr": 9.220582013323258e-06, "epoch": 0.26246056782334387, "percentage": 26.24, "elapsed_time": "5:57:13", "remaining_time": "16:44:03"}
+{"current_steps": 1310, "total_steps": 4954, "loss": 0.4706, "lr": 9.201585533036696e-06, "epoch": 0.2644794952681388, "percentage": 26.44, "elapsed_time": "6:00:11", "remaining_time": "16:41:56"}
+{"current_steps": 1320, "total_steps": 4954, "loss": 0.4879, "lr": 9.18238039667746e-06, "epoch": 0.2664984227129338, "percentage": 26.65, "elapsed_time": "6:02:59", "remaining_time": "16:39:18"}
+{"current_steps": 1330, "total_steps": 4954, "loss": 0.4799, "lr": 9.162967557997003e-06, "epoch": 0.2685173501577287, "percentage": 26.85, "elapsed_time": "6:05:31", "remaining_time": "16:36:00"}
+{"current_steps": 1340, "total_steps": 4954, "loss": 0.4757, "lr": 9.14334798106155e-06, "epoch": 0.27053627760252363, "percentage": 27.05, "elapsed_time": "6:08:29", "remaining_time": "16:33:49"}
+{"current_steps": 1350, "total_steps": 4954, "loss": 0.4805, "lr": 9.123522640204198e-06, "epoch": 0.2725552050473186, "percentage": 27.25, "elapsed_time": "6:10:51", "remaining_time": "16:30:02"}
+{"current_steps": 1360, "total_steps": 4954, "loss": 0.4769, "lr": 9.103492519976555e-06, "epoch": 0.27457413249211354, "percentage": 27.45, "elapsed_time": "6:13:47", "remaining_time": "16:27:47"}
+{"current_steps": 1370, "total_steps": 4954, "loss": 0.4777, "lr": 9.083258615099819e-06, "epoch": 0.2765930599369085, "percentage": 27.65, "elapsed_time": "6:16:40", "remaining_time": "16:25:24"}
+{"current_steps": 1380, "total_steps": 4954, "loss": 0.4728, "lr": 9.062821930415404e-06, "epoch": 0.27861198738170345, "percentage": 27.86, "elapsed_time": "6:19:12", "remaining_time": "16:22:05"}
+{"current_steps": 1390, "total_steps": 4954, "loss": 0.4705, "lr": 9.042183480835018e-06, "epoch": 0.28063091482649843, "percentage": 28.06, "elapsed_time": "6:22:09", "remaining_time": "16:19:52"}
+{"current_steps": 1400, "total_steps": 4954, "loss": 0.4782, "lr": 9.021344291290275e-06, "epoch": 0.28264984227129336, "percentage": 28.26, "elapsed_time": "6:24:33", "remaining_time": "16:16:14"}
+{"current_steps": 1410, "total_steps": 4954, "loss": 0.4705, "lr": 9.000305396681788e-06, "epoch": 0.28466876971608834, "percentage": 28.46, "elapsed_time": "6:27:30", "remaining_time": "16:14:00"}
+{"current_steps": 1420, "total_steps": 4954, "loss": 0.4694, "lr": 8.97906784182778e-06, "epoch": 0.28668769716088327, "percentage": 28.66, "elapsed_time": "6:30:21", "remaining_time": "16:11:30"}
+{"current_steps": 1430, "total_steps": 4954, "loss": 0.4698, "lr": 8.95763268141219e-06, "epoch": 0.28870662460567825, "percentage": 28.87, "elapsed_time": "6:32:55", "remaining_time": "16:08:18"}
+{"current_steps": 1440, "total_steps": 4954, "loss": 0.4766, "lr": 8.936000979932304e-06, "epoch": 0.2907255520504732, "percentage": 29.07, "elapsed_time": "6:35:54", "remaining_time": "16:06:08"}
+{"current_steps": 1450, "total_steps": 4954, "loss": 0.4773, "lr": 8.914173811645884e-06, "epoch": 0.29274447949526816, "percentage": 29.27, "elapsed_time": "6:38:23", "remaining_time": "16:02:45"}
+{"current_steps": 1460, "total_steps": 4954, "loss": 0.4652, "lr": 8.892152260517824e-06, "epoch": 0.2947634069400631, "percentage": 29.47, "elapsed_time": "6:41:21", "remaining_time": "16:00:30"}
+{"current_steps": 1470, "total_steps": 4954, "loss": 0.475, "lr": 8.869937420166312e-06, "epoch": 0.29678233438485807, "percentage": 29.67, "elapsed_time": "6:44:11", "remaining_time": "15:57:57"}
+{"current_steps": 1480, "total_steps": 4954, "loss": 0.4811, "lr": 8.847530393808534e-06, "epoch": 0.298801261829653, "percentage": 29.87, "elapsed_time": "6:46:45", "remaining_time": "15:54:46"}
+{"current_steps": 1490, "total_steps": 4954, "loss": 0.4723, "lr": 8.824932294205868e-06, "epoch": 0.3008201892744479, "percentage": 30.08, "elapsed_time": "6:49:49", "remaining_time": "15:52:46"}
+{"current_steps": 1500, "total_steps": 4954, "loss": 0.4728, "lr": 8.802144243608633e-06, "epoch": 0.3028391167192429, "percentage": 30.28, "elapsed_time": "6:52:14", "remaining_time": "15:49:14"}
+{"current_steps": 1510, "total_steps": 4954, "loss": 0.4687, "lr": 8.779167373700359e-06, "epoch": 0.30485804416403783, "percentage": 30.48, "elapsed_time": "6:55:11", "remaining_time": "15:46:58"}
+{"current_steps": 1520, "total_steps": 4954, "loss": 0.4795, "lr": 8.756002825541583e-06, "epoch": 0.3068769716088328, "percentage": 30.68, "elapsed_time": "6:58:05", "remaining_time": "15:44:33"}
+{"current_steps": 1530, "total_steps": 4954, "loss": 0.4782, "lr": 8.73265174951318e-06, "epoch": 0.30889589905362774, "percentage": 30.88, "elapsed_time": "7:00:39", "remaining_time": "15:41:24"}
+{"current_steps": 1540, "total_steps": 4954, "loss": 0.4722, "lr": 8.709115305259233e-06, "epoch": 0.3109148264984227, "percentage": 31.09, "elapsed_time": "7:03:40", "remaining_time": "15:39:14"}
+{"current_steps": 1550, "total_steps": 4954, "loss": 0.4764, "lr": 8.685394661629453e-06, "epoch": 0.31293375394321765, "percentage": 31.29, "elapsed_time": "7:06:03", "remaining_time": "15:35:41"}
+{"current_steps": 1560, "total_steps": 4954, "loss": 0.4749, "lr": 8.661490996621125e-06, "epoch": 0.31495268138801263, "percentage": 31.49, "elapsed_time": "7:08:55", "remaining_time": "15:33:12"}
+{"current_steps": 1570, "total_steps": 4954, "loss": 0.4685, "lr": 8.637405497320599e-06, "epoch": 0.31697160883280756, "percentage": 31.69, "elapsed_time": "7:11:44", "remaining_time": "15:30:35"}
+{"current_steps": 1580, "total_steps": 4954, "loss": 0.473, "lr": 8.61313935984436e-06, "epoch": 0.31899053627760254, "percentage": 31.89, "elapsed_time": "7:14:18", "remaining_time": "15:27:25"}
+{"current_steps": 1590, "total_steps": 4954, "loss": 0.467, "lr": 8.588693789279605e-06, "epoch": 0.32100946372239747, "percentage": 32.1, "elapsed_time": "7:17:14", "remaining_time": "15:25:05"}
+{"current_steps": 1600, "total_steps": 4954, "loss": 0.4715, "lr": 8.56406999962441e-06, "epoch": 0.32302839116719245, "percentage": 32.3, "elapsed_time": "7:19:39", "remaining_time": "15:21:37"}
+{"current_steps": 1610, "total_steps": 4954, "loss": 0.4643, "lr": 8.539269213727434e-06, "epoch": 0.3250473186119874, "percentage": 32.5, "elapsed_time": "7:22:41", "remaining_time": "15:19:29"}
+{"current_steps": 1620, "total_steps": 4954, "loss": 0.4753, "lr": 8.514292663227196e-06, "epoch": 0.32706624605678236, "percentage": 32.7, "elapsed_time": "7:25:31", "remaining_time": "15:16:53"}
+{"current_steps": 1630, "total_steps": 4954, "loss": 0.4692, "lr": 8.489141588490914e-06, "epoch": 0.3290851735015773, "percentage": 32.9, "elapsed_time": "7:28:04", "remaining_time": "15:13:43"}
+{"current_steps": 1640, "total_steps": 4954, "loss": 0.4626, "lr": 8.46381723855289e-06, "epoch": 0.3311041009463722, "percentage": 33.1, "elapsed_time": "7:31:01", "remaining_time": "15:11:23"}
+{"current_steps": 1650, "total_steps": 4954, "loss": 0.4722, "lr": 8.438320871052501e-06, "epoch": 0.3331230283911672, "percentage": 33.31, "elapsed_time": "7:33:29", "remaining_time": "15:08:03"}
+{"current_steps": 1660, "total_steps": 4954, "loss": 0.4591, "lr": 8.412653752171732e-06, "epoch": 0.3351419558359621, "percentage": 33.51, "elapsed_time": "7:36:29", "remaining_time": "15:05:50"}
+{"current_steps": 1670, "total_steps": 4954, "loss": 0.48, "lr": 8.386817156572298e-06, "epoch": 0.3371608832807571, "percentage": 33.71, "elapsed_time": "7:39:16", "remaining_time": "15:03:09"}
+{"current_steps": 1680, "total_steps": 4954, "loss": 0.469, "lr": 8.360812367332342e-06, "epoch": 0.33917981072555203, "percentage": 33.91, "elapsed_time": "7:41:51", "remaining_time": "15:00:04"}
+{"current_steps": 1690, "total_steps": 4954, "loss": 0.4701, "lr": 8.33464067588272e-06, "epoch": 0.341198738170347, "percentage": 34.11, "elapsed_time": "7:44:44", "remaining_time": "14:57:34"}
+{"current_steps": 1700, "total_steps": 4954, "loss": 0.4742, "lr": 8.30830338194286e-06, "epoch": 0.34321766561514194, "percentage": 34.32, "elapsed_time": "7:47:07", "remaining_time": "14:54:08"}
+{"current_steps": 1710, "total_steps": 4954, "loss": 0.4563, "lr": 8.281801793456223e-06, "epoch": 0.3452365930599369, "percentage": 34.52, "elapsed_time": "7:50:06", "remaining_time": "14:51:49"}
+{"current_steps": 1720, "total_steps": 4954, "loss": 0.4678, "lr": 8.255137226525346e-06, "epoch": 0.34725552050473185, "percentage": 34.72, "elapsed_time": "7:52:55", "remaining_time": "14:49:13"}
+{"current_steps": 1730, "total_steps": 4954, "loss": 0.4688, "lr": 8.22831100534648e-06, "epoch": 0.34927444794952683, "percentage": 34.92, "elapsed_time": "7:55:28", "remaining_time": "14:46:04"}
+{"current_steps": 1740, "total_steps": 4954, "loss": 0.4542, "lr": 8.201324462143827e-06, "epoch": 0.35129337539432176, "percentage": 35.12, "elapsed_time": "7:58:21", "remaining_time": "14:43:36"}
+{"current_steps": 1750, "total_steps": 4954, "loss": 0.4743, "lr": 8.174178937103397e-06, "epoch": 0.35331230283911674, "percentage": 35.32, "elapsed_time": "8:00:47", "remaining_time": "14:40:15"}
+{"current_steps": 1760, "total_steps": 4954, "loss": 0.4604, "lr": 8.14687577830643e-06, "epoch": 0.35533123028391167, "percentage": 35.53, "elapsed_time": "8:03:46", "remaining_time": "14:37:56"}
+{"current_steps": 1770, "total_steps": 4954, "loss": 0.4712, "lr": 8.11941634166246e-06, "epoch": 0.35735015772870665, "percentage": 35.73, "elapsed_time": "8:06:34", "remaining_time": "14:35:17"}
+{"current_steps": 1780, "total_steps": 4954, "loss": 0.4668, "lr": 8.09180199084198e-06, "epoch": 0.3593690851735016, "percentage": 35.93, "elapsed_time": "8:09:06", "remaining_time": "14:32:08"}
+{"current_steps": 1790, "total_steps": 4954, "loss": 0.4596, "lr": 8.064034097208712e-06, "epoch": 0.3613880126182965, "percentage": 36.13, "elapsed_time": "8:12:03", "remaining_time": "14:29:45"}
+{"current_steps": 1800, "total_steps": 4954, "loss": 0.4667, "lr": 8.036114039751516e-06, "epoch": 0.3634069400630915, "percentage": 36.33, "elapsed_time": "8:14:29", "remaining_time": "14:26:27"}
+{"current_steps": 1810, "total_steps": 4954, "loss": 0.4604, "lr": 8.0080432050159e-06, "epoch": 0.3654258675078864, "percentage": 36.54, "elapsed_time": "8:17:30", "remaining_time": "14:24:10"}
+{"current_steps": 1820, "total_steps": 4954, "loss": 0.4644, "lr": 7.979822987035157e-06, "epoch": 0.3674447949526814, "percentage": 36.74, "elapsed_time": "8:20:14", "remaining_time": "14:21:23"}
+{"current_steps": 1830, "total_steps": 4954, "loss": 0.4677, "lr": 7.951454787261148e-06, "epoch": 0.3694637223974763, "percentage": 36.94, "elapsed_time": "8:22:47", "remaining_time": "14:18:18"}
+{"current_steps": 1840, "total_steps": 4954, "loss": 0.4593, "lr": 7.922940014494693e-06, "epoch": 0.3714826498422713, "percentage": 37.14, "elapsed_time": "8:25:45", "remaining_time": "14:15:55"}
+{"current_steps": 1850, "total_steps": 4954, "loss": 0.4689, "lr": 7.894280084815618e-06, "epoch": 0.37350157728706623, "percentage": 37.34, "elapsed_time": "8:28:10", "remaining_time": "14:12:38"}
+{"current_steps": 1860, "total_steps": 4954, "loss": 0.4611, "lr": 7.86547642151242e-06, "epoch": 0.3755205047318612, "percentage": 37.55, "elapsed_time": "8:31:09", "remaining_time": "14:10:16"}
+{"current_steps": 1870, "total_steps": 4954, "loss": 0.4647, "lr": 7.836530455011594e-06, "epoch": 0.37753943217665614, "percentage": 37.75, "elapsed_time": "8:33:58", "remaining_time": "14:07:38"}
+{"current_steps": 1880, "total_steps": 4954, "loss": 0.4643, "lr": 7.807443622806592e-06, "epoch": 0.3795583596214511, "percentage": 37.95, "elapsed_time": "8:36:30", "remaining_time": "14:04:33"}
+{"current_steps": 1890, "total_steps": 4954, "loss": 0.4621, "lr": 7.778217369386434e-06, "epoch": 0.38157728706624605, "percentage": 38.15, "elapsed_time": "8:39:23", "remaining_time": "14:02:01"}
+{"current_steps": 1900, "total_steps": 4954, "loss": 0.4702, "lr": 7.748853146163978e-06, "epoch": 0.38359621451104103, "percentage": 38.35, "elapsed_time": "8:41:50", "remaining_time": "13:58:48"}
+{"current_steps": 1910, "total_steps": 4954, "loss": 0.4584, "lr": 7.719352411403836e-06, "epoch": 0.38561514195583596, "percentage": 38.55, "elapsed_time": "8:44:55", "remaining_time": "13:56:35"}
+{"current_steps": 1920, "total_steps": 4954, "loss": 0.4581, "lr": 7.68971663014995e-06, "epoch": 0.3876340694006309, "percentage": 38.76, "elapsed_time": "8:47:44", "remaining_time": "13:53:56"}
+{"current_steps": 1930, "total_steps": 4954, "loss": 0.4595, "lr": 7.659947274152857e-06, "epoch": 0.38965299684542587, "percentage": 38.96, "elapsed_time": "8:50:21", "remaining_time": "13:50:59"}
+{"current_steps": 1940, "total_steps": 4954, "loss": 0.4603, "lr": 7.630045821796567e-06, "epoch": 0.3916719242902208, "percentage": 39.16, "elapsed_time": "8:53:22", "remaining_time": "13:48:39"}
+{"current_steps": 1950, "total_steps": 4954, "loss": 0.4726, "lr": 7.60001375802518e-06, "epoch": 0.3936908517350158, "percentage": 39.36, "elapsed_time": "8:55:45", "remaining_time": "13:45:20"}
+{"current_steps": 1960, "total_steps": 4954, "loss": 0.4553, "lr": 7.5698525742691145e-06, "epoch": 0.3957097791798107, "percentage": 39.56, "elapsed_time": "8:58:47", "remaining_time": "13:43:01"}
+{"current_steps": 1970, "total_steps": 4954, "loss": 0.4652, "lr": 7.5395637683710534e-06, "epoch": 0.3977287066246057, "percentage": 39.77, "elapsed_time": "9:01:34", "remaining_time": "13:40:20"}
+{"current_steps": 1980, "total_steps": 4954, "loss": 0.4569, "lr": 7.509148844511556e-06, "epoch": 0.3997476340694006, "percentage": 39.97, "elapsed_time": "9:04:05", "remaining_time": "13:37:13"}
+{"current_steps": 1990, "total_steps": 4954, "loss": 0.4608, "lr": 7.478609313134367e-06, "epoch": 0.4017665615141956, "percentage": 40.17, "elapsed_time": "9:07:03", "remaining_time": "13:34:49"}
+{"current_steps": 2000, "total_steps": 4954, "loss": 0.4618, "lr": 7.447946690871387e-06, "epoch": 0.4037854889589905, "percentage": 40.37, "elapsed_time": "9:09:31", "remaining_time": "13:31:38"}
+{"current_steps": 2010, "total_steps": 4954, "loss": 0.4549, "lr": 7.4171625004673765e-06, "epoch": 0.4058044164037855, "percentage": 40.57, "elapsed_time": "9:12:34", "remaining_time": "13:29:20"}
+{"current_steps": 2020, "total_steps": 4954, "loss": 0.4648, "lr": 7.386258270704318e-06, "epoch": 0.40782334384858043, "percentage": 40.78, "elapsed_time": "9:15:20", "remaining_time": "13:26:37"}
+{"current_steps": 2030, "total_steps": 4954, "loss": 0.4618, "lr": 7.355235536325507e-06, "epoch": 0.4098422712933754, "percentage": 40.98, "elapsed_time": "9:17:53", "remaining_time": "13:23:34"}
+{"current_steps": 2040, "total_steps": 4954, "loss": 0.4556, "lr": 7.32409583795932e-06, "epoch": 0.41186119873817034, "percentage": 41.18, "elapsed_time": "9:20:46", "remaining_time": "13:21:02"}
+{"current_steps": 2050, "total_steps": 4954, "loss": 0.4649, "lr": 7.292840722042721e-06, "epoch": 0.4138801261829653, "percentage": 41.38, "elapsed_time": "9:23:08", "remaining_time": "13:17:44"}
+{"current_steps": 2060, "total_steps": 4954, "loss": 0.4546, "lr": 7.261471740744453e-06, "epoch": 0.41589905362776025, "percentage": 41.58, "elapsed_time": "9:26:04", "remaining_time": "13:15:14"}
+{"current_steps": 2070, "total_steps": 4954, "loss": 0.459, "lr": 7.229990451887961e-06, "epoch": 0.4179179810725552, "percentage": 41.78, "elapsed_time": "9:28:55", "remaining_time": "13:12:38"}
+{"current_steps": 2080, "total_steps": 4954, "loss": 0.4627, "lr": 7.1983984188740215e-06, "epoch": 0.41993690851735016, "percentage": 41.99, "elapsed_time": "9:31:30", "remaining_time": "13:09:40"}
+{"current_steps": 2090, "total_steps": 4954, "loss": 0.4584, "lr": 7.1666972106031105e-06, "epoch": 0.4219558359621451, "percentage": 42.19, "elapsed_time": "9:34:27", "remaining_time": "13:07:11"}
+{"current_steps": 2100, "total_steps": 4954, "loss": 0.4629, "lr": 7.134888401397484e-06, "epoch": 0.42397476340694007, "percentage": 42.39, "elapsed_time": "9:36:51", "remaining_time": "13:03:59"}
+{"current_steps": 2110, "total_steps": 4954, "loss": 0.4549, "lr": 7.102973570922997e-06, "epoch": 0.425993690851735, "percentage": 42.59, "elapsed_time": "9:39:51", "remaining_time": "13:01:34"}
+{"current_steps": 2120, "total_steps": 4954, "loss": 0.4632, "lr": 7.070954304110656e-06, "epoch": 0.42801261829653, "percentage": 42.79, "elapsed_time": "9:42:40", "remaining_time": "12:58:54"}
+{"current_steps": 2130, "total_steps": 4954, "loss": 0.4581, "lr": 7.03883219107791e-06, "epoch": 0.4300315457413249, "percentage": 43.0, "elapsed_time": "9:45:12", "remaining_time": "12:55:53"}
+{"current_steps": 2140, "total_steps": 4954, "loss": 0.4596, "lr": 7.0066088270496775e-06, "epoch": 0.4320504731861199, "percentage": 43.2, "elapsed_time": "9:48:07", "remaining_time": "12:53:20"}
+{"current_steps": 2150, "total_steps": 4954, "loss": 0.4648, "lr": 6.9742858122791355e-06, "epoch": 0.4340694006309148, "percentage": 43.4, "elapsed_time": "9:50:31", "remaining_time": "12:50:09"}
+{"current_steps": 2160, "total_steps": 4954, "loss": 0.4548, "lr": 6.941864751968239e-06, "epoch": 0.4360883280757098, "percentage": 43.6, "elapsed_time": "9:53:31", "remaining_time": "12:47:43"}
+{"current_steps": 2170, "total_steps": 4954, "loss": 0.461, "lr": 6.90934725618801e-06, "epoch": 0.4381072555205047, "percentage": 43.8, "elapsed_time": "9:56:23", "remaining_time": "12:45:08"}
+{"current_steps": 2180, "total_steps": 4954, "loss": 0.4631, "lr": 6.876734939798584e-06, "epoch": 0.4401261829652997, "percentage": 44.0, "elapsed_time": "9:58:58", "remaining_time": "12:42:10"}
+{"current_steps": 2190, "total_steps": 4954, "loss": 0.4567, "lr": 6.844029422368998e-06, "epoch": 0.44214511041009463, "percentage": 44.21, "elapsed_time": "10:01:59", "remaining_time": "12:39:46"}
+{"current_steps": 2200, "total_steps": 4954, "loss": 0.4619, "lr": 6.811232328096778e-06, "epoch": 0.4441640378548896, "percentage": 44.41, "elapsed_time": "10:04:23", "remaining_time": "12:36:35"}
+{"current_steps": 2210, "total_steps": 4954, "loss": 0.4472, "lr": 6.7783452857272725e-06, "epoch": 0.44618296529968454, "percentage": 44.61, "elapsed_time": "10:07:28", "remaining_time": "12:34:15"}
+{"current_steps": 2220, "total_steps": 4954, "loss": 0.4634, "lr": 6.745369928472764e-06, "epoch": 0.44820189274447947, "percentage": 44.81, "elapsed_time": "10:10:15", "remaining_time": "12:31:33"}
+{"current_steps": 2230, "total_steps": 4954, "loss": 0.4595, "lr": 6.712307893931364e-06, "epoch": 0.45022082018927445, "percentage": 45.01, "elapsed_time": "10:12:46", "remaining_time": "12:28:31"}
+{"current_steps": 2240, "total_steps": 4954, "loss": 0.457, "lr": 6.67916082400569e-06, "epoch": 0.4522397476340694, "percentage": 45.22, "elapsed_time": "10:15:46", "remaining_time": "12:26:04"}
+{"current_steps": 2250, "total_steps": 4954, "loss": 0.465, "lr": 6.645930364821327e-06, "epoch": 0.45425867507886436, "percentage": 45.42, "elapsed_time": "10:18:12", "remaining_time": "12:22:56"}
+{"current_steps": 2260, "total_steps": 4954, "loss": 0.4521, "lr": 6.612618166645068e-06, "epoch": 0.4562776025236593, "percentage": 45.62, "elapsed_time": "10:21:13", "remaining_time": "12:20:30"}
+{"current_steps": 2270, "total_steps": 4954, "loss": 0.4621, "lr": 6.579225883802981e-06, "epoch": 0.45829652996845427, "percentage": 45.82, "elapsed_time": "10:24:01", "remaining_time": "12:17:50"}
+{"current_steps": 2280, "total_steps": 4954, "loss": 0.4553, "lr": 6.5457551745982275e-06, "epoch": 0.4603154574132492, "percentage": 46.02, "elapsed_time": "10:26:37", "remaining_time": "12:14:54"}
+{"current_steps": 2290, "total_steps": 4954, "loss": 0.4585, "lr": 6.512207701228727e-06, "epoch": 0.4623343848580442, "percentage": 46.23, "elapsed_time": "10:29:30", "remaining_time": "12:12:19"}
+{"current_steps": 2300, "total_steps": 4954, "loss": 0.4579, "lr": 6.478585129704608e-06, "epoch": 0.4643533123028391, "percentage": 46.43, "elapsed_time": "10:31:58", "remaining_time": "12:09:14"}
+{"current_steps": 2310, "total_steps": 4954, "loss": 0.453, "lr": 6.444889129765465e-06, "epoch": 0.4663722397476341, "percentage": 46.63, "elapsed_time": "10:35:00", "remaining_time": "12:06:49"}
+{"current_steps": 2320, "total_steps": 4954, "loss": 0.4606, "lr": 6.4111213747974385e-06, "epoch": 0.468391167192429, "percentage": 46.83, "elapsed_time": "10:37:49", "remaining_time": "12:04:08"}
+{"current_steps": 2330, "total_steps": 4954, "loss": 0.4528, "lr": 6.377283541750123e-06, "epoch": 0.470410094637224, "percentage": 47.03, "elapsed_time": "10:40:20", "remaining_time": "12:01:07"}
+{"current_steps": 2340, "total_steps": 4954, "loss": 0.4614, "lr": 6.343377311053271e-06, "epoch": 0.4724290220820189, "percentage": 47.23, "elapsed_time": "10:43:13", "remaining_time": "11:58:33"}
+{"current_steps": 2350, "total_steps": 4954, "loss": 0.4662, "lr": 6.309404366533355e-06, "epoch": 0.4744479495268139, "percentage": 47.44, "elapsed_time": "10:45:39", "remaining_time": "11:55:26"}
+{"current_steps": 2360, "total_steps": 4954, "loss": 0.4484, "lr": 6.275366395329934e-06, "epoch": 0.47646687697160883, "percentage": 47.64, "elapsed_time": "10:48:37", "remaining_time": "11:52:56"}
+{"current_steps": 2370, "total_steps": 4954, "loss": 0.461, "lr": 6.241265087811883e-06, "epoch": 0.47848580441640376, "percentage": 47.84, "elapsed_time": "10:51:26", "remaining_time": "11:50:15"}
+{"current_steps": 2380, "total_steps": 4954, "loss": 0.4572, "lr": 6.207102137493433e-06, "epoch": 0.48050473186119874, "percentage": 48.04, "elapsed_time": "10:54:04", "remaining_time": "11:47:23"}
+{"current_steps": 2390, "total_steps": 4954, "loss": 0.4586, "lr": 6.172879240950075e-06, "epoch": 0.48252365930599367, "percentage": 48.24, "elapsed_time": "10:56:54", "remaining_time": "11:44:44"}
+{"current_steps": 2400, "total_steps": 4954, "loss": 0.4613, "lr": 6.138598097734308e-06, "epoch": 0.48454258675078865, "percentage": 48.45, "elapsed_time": "10:59:22", "remaining_time": "11:41:40"}
+{"current_steps": 2410, "total_steps": 4954, "loss": 0.4524, "lr": 6.104260410291237e-06, "epoch": 0.4865615141955836, "percentage": 48.65, "elapsed_time": "11:02:19", "remaining_time": "11:39:09"}
+{"current_steps": 2420, "total_steps": 4954, "loss": 0.4546, "lr": 6.069867883874017e-06, "epoch": 0.48858044164037856, "percentage": 48.85, "elapsed_time": "11:05:10", "remaining_time": "11:36:30"}
+{"current_steps": 2430, "total_steps": 4954, "loss": 0.4601, "lr": 6.035422226459183e-06, "epoch": 0.4905993690851735, "percentage": 49.05, "elapsed_time": "11:07:43", "remaining_time": "11:33:33"}
+{"current_steps": 2440, "total_steps": 4954, "loss": 0.4552, "lr": 6.000925148661822e-06, "epoch": 0.49261829652996847, "percentage": 49.25, "elapsed_time": "11:10:44", "remaining_time": "11:31:04"}
+{"current_steps": 2450, "total_steps": 4954, "loss": 0.4534, "lr": 5.966378363650618e-06, "epoch": 0.4946372239747634, "percentage": 49.45, "elapsed_time": "11:13:05", "remaining_time": "11:27:55"}
+{"current_steps": 2460, "total_steps": 4954, "loss": 0.4478, "lr": 5.931783587062785e-06, "epoch": 0.4966561514195584, "percentage": 49.66, "elapsed_time": "11:16:05", "remaining_time": "11:25:26"}
+{"current_steps": 2470, "total_steps": 4954, "loss": 0.4606, "lr": 5.897142536918854e-06, "epoch": 0.4986750788643533, "percentage": 49.86, "elapsed_time": "11:18:57", "remaining_time": "11:22:48"}
+{"current_steps": 2480, "total_steps": 4954, "loss": 0.4512, "lr": 5.8624569335373625e-06, "epoch": 0.5006940063091483, "percentage": 50.06, "elapsed_time": "11:21:33", "remaining_time": "11:19:54"}
+{"current_steps": 2490, "total_steps": 4954, "loss": 0.4503, "lr": 5.827728499449417e-06, "epoch": 0.5027129337539432, "percentage": 50.26, "elapsed_time": "11:24:28", "remaining_time": "11:17:19"}
+{"current_steps": 2500, "total_steps": 4954, "loss": 0.4586, "lr": 5.792958959313155e-06, "epoch": 0.5047318611987381, "percentage": 50.46, "elapsed_time": "11:26:52", "remaining_time": "11:14:14"}
+{"current_steps": 2510, "total_steps": 4954, "loss": 0.442, "lr": 5.758150039828084e-06, "epoch": 0.5067507886435331, "percentage": 50.67, "elapsed_time": "11:29:52", "remaining_time": "11:11:44"}
+{"current_steps": 2520, "total_steps": 4954, "loss": 0.4524, "lr": 5.723303469649352e-06, "epoch": 0.5087697160883281, "percentage": 50.87, "elapsed_time": "11:32:44", "remaining_time": "11:09:06"}
+{"current_steps": 2530, "total_steps": 4954, "loss": 0.4533, "lr": 5.688420979301876e-06, "epoch": 0.510788643533123, "percentage": 51.07, "elapsed_time": "11:35:17", "remaining_time": "11:06:09"}
+{"current_steps": 2540, "total_steps": 4954, "loss": 0.4537, "lr": 5.6535043010944226e-06, "epoch": 0.512807570977918, "percentage": 51.27, "elapsed_time": "11:38:12", "remaining_time": "11:03:34"}
+{"current_steps": 2550, "total_steps": 4954, "loss": 0.4624, "lr": 5.618555169033567e-06, "epoch": 0.5148264984227129, "percentage": 51.47, "elapsed_time": "11:40:39", "remaining_time": "11:00:32"}
+{"current_steps": 2560, "total_steps": 4954, "loss": 0.4394, "lr": 5.583575318737588e-06, "epoch": 0.5168454258675079, "percentage": 51.68, "elapsed_time": "11:43:39", "remaining_time": "10:58:01"}
+{"current_steps": 2570, "total_steps": 4954, "loss": 0.4482, "lr": 5.548566487350264e-06, "epoch": 0.5188643533123029, "percentage": 51.88, "elapsed_time": "11:46:26", "remaining_time": "10:55:18"}
+{"current_steps": 2580, "total_steps": 4954, "loss": 0.4488, "lr": 5.513530413454618e-06, "epoch": 0.5208832807570978, "percentage": 52.08, "elapsed_time": "11:48:56", "remaining_time": "10:52:20"}
+{"current_steps": 2590, "total_steps": 4954, "loss": 0.4547, "lr": 5.478468836986568e-06, "epoch": 0.5229022082018927, "percentage": 52.28, "elapsed_time": "11:51:50", "remaining_time": "10:49:43"}
+{"current_steps": 2600, "total_steps": 4954, "loss": 0.4536, "lr": 5.443383499148519e-06, "epoch": 0.5249211356466877, "percentage": 52.48, "elapsed_time": "11:54:13", "remaining_time": "10:46:38"}
+{"current_steps": 2610, "total_steps": 4954, "loss": 0.4489, "lr": 5.408276142322904e-06, "epoch": 0.5269400630914827, "percentage": 52.68, "elapsed_time": "11:57:13", "remaining_time": "10:44:07"}
+{"current_steps": 2620, "total_steps": 4954, "loss": 0.457, "lr": 5.373148509985636e-06, "epoch": 0.5289589905362776, "percentage": 52.89, "elapsed_time": "12:00:02", "remaining_time": "10:41:26"}
+{"current_steps": 2630, "total_steps": 4954, "loss": 0.4491, "lr": 5.3380023466195455e-06, "epoch": 0.5309779179810725, "percentage": 53.09, "elapsed_time": "12:02:37", "remaining_time": "10:38:32"}
+{"current_steps": 2640, "total_steps": 4954, "loss": 0.4509, "lr": 5.302839397627732e-06, "epoch": 0.5329968454258676, "percentage": 53.29, "elapsed_time": "12:05:35", "remaining_time": "10:35:59"}
+{"current_steps": 2650, "total_steps": 4954, "loss": 0.4497, "lr": 5.267661409246893e-06, "epoch": 0.5350157728706625, "percentage": 53.49, "elapsed_time": "12:08:03", "remaining_time": "10:33:00"}
+{"current_steps": 2660, "total_steps": 4954, "loss": 0.4455, "lr": 5.232470128460597e-06, "epoch": 0.5370347003154574, "percentage": 53.69, "elapsed_time": "12:11:07", "remaining_time": "10:30:31"}
+{"current_steps": 2670, "total_steps": 4954, "loss": 0.4633, "lr": 5.197267302912535e-06, "epoch": 0.5390536277602523, "percentage": 53.9, "elapsed_time": "12:13:57", "remaining_time": "10:27:50"}
+{"current_steps": 2680, "total_steps": 4954, "loss": 0.455, "lr": 5.162054680819724e-06, "epoch": 0.5410725552050473, "percentage": 54.1, "elapsed_time": "12:16:32", "remaining_time": "10:24:57"}
+{"current_steps": 2690, "total_steps": 4954, "loss": 0.4527, "lr": 5.12683401088569e-06, "epoch": 0.5430914826498423, "percentage": 54.3, "elapsed_time": "12:19:28", "remaining_time": "10:22:22"}
+{"current_steps": 2700, "total_steps": 4954, "loss": 0.4507, "lr": 5.091607042213621e-06, "epoch": 0.5451104100946372, "percentage": 54.5, "elapsed_time": "12:21:55", "remaining_time": "10:19:22"}
+{"current_steps": 2710, "total_steps": 4954, "loss": 0.4467, "lr": 5.056375524219516e-06, "epoch": 0.5471293375394322, "percentage": 54.7, "elapsed_time": "12:24:58", "remaining_time": "10:16:52"}
+{"current_steps": 2720, "total_steps": 4954, "loss": 0.4481, "lr": 5.021141206545293e-06, "epoch": 0.5491482649842271, "percentage": 54.91, "elapsed_time": "12:27:48", "remaining_time": "10:14:11"}
+{"current_steps": 2730, "total_steps": 4954, "loss": 0.4467, "lr": 4.9859058389719095e-06, "epoch": 0.5511671924290221, "percentage": 55.11, "elapsed_time": "12:30:19", "remaining_time": "10:11:15"}
+{"current_steps": 2740, "total_steps": 4954, "loss": 0.4438, "lr": 4.950671171332458e-06, "epoch": 0.553186119873817, "percentage": 55.31, "elapsed_time": "12:33:18", "remaining_time": "10:08:41"}
+{"current_steps": 2750, "total_steps": 4954, "loss": 0.455, "lr": 4.915438953425277e-06, "epoch": 0.555205047318612, "percentage": 55.51, "elapsed_time": "12:35:44", "remaining_time": "10:05:41"}
+{"current_steps": 2760, "total_steps": 4954, "loss": 0.4431, "lr": 4.8802109349270415e-06, "epoch": 0.5572239747634069, "percentage": 55.71, "elapsed_time": "12:38:42", "remaining_time": "10:03:07"}
+{"current_steps": 2770, "total_steps": 4954, "loss": 0.4457, "lr": 4.844988865305883e-06, "epoch": 0.5592429022082019, "percentage": 55.91, "elapsed_time": "12:41:32", "remaining_time": "10:00:26"}
+{"current_steps": 2780, "total_steps": 4954, "loss": 0.4468, "lr": 4.809774493734507e-06, "epoch": 0.5612618296529969, "percentage": 56.12, "elapsed_time": "12:44:05", "remaining_time": "9:57:31"}
+{"current_steps": 2790, "total_steps": 4954, "loss": 0.4531, "lr": 4.774569569003314e-06, "epoch": 0.5632807570977918, "percentage": 56.32, "elapsed_time": "12:46:57", "remaining_time": "9:54:52"}
+{"current_steps": 2800, "total_steps": 4954, "loss": 0.4559, "lr": 4.739375839433575e-06, "epoch": 0.5652996845425867, "percentage": 56.52, "elapsed_time": "12:49:24", "remaining_time": "9:51:53"}
+{"current_steps": 2810, "total_steps": 4954, "loss": 0.4463, "lr": 4.704195052790584e-06, "epoch": 0.5673186119873816, "percentage": 56.72, "elapsed_time": "12:52:26", "remaining_time": "9:49:22"}
+{"current_steps": 2820, "total_steps": 4954, "loss": 0.4494, "lr": 4.66902895619688e-06, "epoch": 0.5693375394321767, "percentage": 56.92, "elapsed_time": "12:55:17", "remaining_time": "9:46:41"}
+{"current_steps": 2830, "total_steps": 4954, "loss": 0.4477, "lr": 4.633879296045474e-06, "epoch": 0.5713564668769716, "percentage": 57.13, "elapsed_time": "12:57:52", "remaining_time": "9:43:48"}
+{"current_steps": 2840, "total_steps": 4954, "loss": 0.4502, "lr": 4.59874781791312e-06, "epoch": 0.5733753943217665, "percentage": 57.33, "elapsed_time": "13:00:44", "remaining_time": "9:41:09"}
+{"current_steps": 2850, "total_steps": 4954, "loss": 0.4553, "lr": 4.56363626647363e-06, "epoch": 0.5753943217665615, "percentage": 57.53, "elapsed_time": "13:03:09", "remaining_time": "9:38:09"}
+{"current_steps": 2860, "total_steps": 4954, "loss": 0.4373, "lr": 4.528546385411239e-06, "epoch": 0.5774132492113565, "percentage": 57.73, "elapsed_time": "13:06:09", "remaining_time": "9:35:36"}
+{"current_steps": 2870, "total_steps": 4954, "loss": 0.453, "lr": 4.493479917333989e-06, "epoch": 0.5794321766561514, "percentage": 57.93, "elapsed_time": "13:08:59", "remaining_time": "9:32:54"}
+{"current_steps": 2880, "total_steps": 4954, "loss": 0.4527, "lr": 4.4584386036872155e-06, "epoch": 0.5814511041009464, "percentage": 58.13, "elapsed_time": "13:11:33", "remaining_time": "9:30:02"}
+{"current_steps": 2890, "total_steps": 4954, "loss": 0.4426, "lr": 4.42342418466705e-06, "epoch": 0.5834700315457413, "percentage": 58.34, "elapsed_time": "13:14:27", "remaining_time": "9:27:23"}
+{"current_steps": 2900, "total_steps": 4954, "loss": 0.4547, "lr": 4.388438399134e-06, "epoch": 0.5854889589905363, "percentage": 58.54, "elapsed_time": "13:16:50", "remaining_time": "9:24:23"}
+{"current_steps": 2910, "total_steps": 4954, "loss": 0.4441, "lr": 4.3534829845265996e-06, "epoch": 0.5875078864353313, "percentage": 58.74, "elapsed_time": "13:19:51", "remaining_time": "9:21:49"}
+{"current_steps": 2920, "total_steps": 4954, "loss": 0.4472, "lr": 4.318559676775126e-06, "epoch": 0.5895268138801262, "percentage": 58.94, "elapsed_time": "13:22:37", "remaining_time": "9:19:05"}
+{"current_steps": 2930, "total_steps": 4954, "loss": 0.4516, "lr": 4.283670210215384e-06, "epoch": 0.5915457413249211, "percentage": 59.14, "elapsed_time": "13:25:10", "remaining_time": "9:16:12"}
+{"current_steps": 2940, "total_steps": 4954, "loss": 0.4468, "lr": 4.248816317502585e-06, "epoch": 0.5935646687697161, "percentage": 59.35, "elapsed_time": "13:28:07", "remaining_time": "9:13:35"}
+{"current_steps": 2950, "total_steps": 4954, "loss": 0.452, "lr": 4.213999729525304e-06, "epoch": 0.5955835962145111, "percentage": 59.55, "elapsed_time": "13:30:34", "remaining_time": "9:10:38"}
+{"current_steps": 2960, "total_steps": 4954, "loss": 0.4418, "lr": 4.179222175319502e-06, "epoch": 0.597602523659306, "percentage": 59.75, "elapsed_time": "13:33:38", "remaining_time": "9:08:06"}
+{"current_steps": 2970, "total_steps": 4954, "loss": 0.4503, "lr": 4.1444853819826845e-06, "epoch": 0.5996214511041009, "percentage": 59.95, "elapsed_time": "13:36:25", "remaining_time": "9:05:23"}
+{"current_steps": 2980, "total_steps": 4954, "loss": 0.4421, "lr": 4.1097910745881175e-06, "epoch": 0.6016403785488958, "percentage": 60.15, "elapsed_time": "13:38:59", "remaining_time": "9:02:30"}
+{"current_steps": 2990, "total_steps": 4954, "loss": 0.4469, "lr": 4.0751409760991585e-06, "epoch": 0.6036593059936909, "percentage": 60.36, "elapsed_time": "13:41:54", "remaining_time": "8:59:52"}
+{"current_steps": 3000, "total_steps": 4954, "loss": 0.4502, "lr": 4.040536807283696e-06, "epoch": 0.6056782334384858, "percentage": 60.56, "elapsed_time": "13:44:19", "remaining_time": "8:56:54"}
+{"current_steps": 3010, "total_steps": 4954, "loss": 0.4505, "lr": 4.005980286628698e-06, "epoch": 0.6076971608832807, "percentage": 60.76, "elapsed_time": "13:47:19", "remaining_time": "8:54:19"}
+{"current_steps": 3020, "total_steps": 4954, "loss": 0.4486, "lr": 3.9714731302548525e-06, "epoch": 0.6097160883280757, "percentage": 60.96, "elapsed_time": "13:50:08", "remaining_time": "8:51:37"}
+{"current_steps": 3030, "total_steps": 4954, "loss": 0.4478, "lr": 3.937017051831367e-06, "epoch": 0.6117350157728707, "percentage": 61.16, "elapsed_time": "13:52:43", "remaining_time": "8:48:46"}
+{"current_steps": 3040, "total_steps": 4954, "loss": 0.4492, "lr": 3.9026137624908466e-06, "epoch": 0.6137539432176656, "percentage": 61.36, "elapsed_time": "13:55:38", "remaining_time": "8:46:07"}
+{"current_steps": 3050, "total_steps": 4954, "loss": 0.4513, "lr": 3.868264970744324e-06, "epoch": 0.6157728706624606, "percentage": 61.57, "elapsed_time": "13:58:06", "remaining_time": "8:43:12"}
+{"current_steps": 3060, "total_steps": 4954, "loss": 0.4482, "lr": 3.833972382396412e-06, "epoch": 0.6177917981072555, "percentage": 61.77, "elapsed_time": "14:01:05", "remaining_time": "8:40:35"}
+{"current_steps": 3070, "total_steps": 4954, "loss": 0.4441, "lr": 3.799737700460594e-06, "epoch": 0.6198107255520505, "percentage": 61.97, "elapsed_time": "14:03:55", "remaining_time": "8:37:53"}
+{"current_steps": 3080, "total_steps": 4954, "loss": 0.4443, "lr": 3.7655626250746446e-06, "epoch": 0.6218296529968455, "percentage": 62.17, "elapsed_time": "14:06:31", "remaining_time": "8:35:03"}
+{"current_steps": 3090, "total_steps": 4954, "loss": 0.4509, "lr": 3.7314488534162007e-06, "epoch": 0.6238485804416404, "percentage": 62.37, "elapsed_time": "14:09:25", "remaining_time": "8:32:24"}
+{"current_steps": 3100, "total_steps": 4954, "loss": 0.4573, "lr": 3.6973980796184843e-06, "epoch": 0.6258675078864353, "percentage": 62.58, "elapsed_time": "14:11:49", "remaining_time": "8:29:26"}
+{"current_steps": 3110, "total_steps": 4954, "loss": 0.4442, "lr": 3.6634119946861556e-06, "epoch": 0.6278864353312302, "percentage": 62.78, "elapsed_time": "14:14:46", "remaining_time": "8:26:48"}
+{"current_steps": 3120, "total_steps": 4954, "loss": 0.4515, "lr": 3.629492286411349e-06, "epoch": 0.6299053627760253, "percentage": 62.98, "elapsed_time": "14:17:35", "remaining_time": "8:24:06"}
+{"current_steps": 3130, "total_steps": 4954, "loss": 0.4481, "lr": 3.5956406392898484e-06, "epoch": 0.6319242902208202, "percentage": 63.18, "elapsed_time": "14:20:08", "remaining_time": "8:21:14"}
+{"current_steps": 3140, "total_steps": 4954, "loss": 0.4553, "lr": 3.561858734437432e-06, "epoch": 0.6339432176656151, "percentage": 63.38, "elapsed_time": "14:23:07", "remaining_time": "8:18:38"}
+{"current_steps": 3150, "total_steps": 4954, "loss": 0.4541, "lr": 3.528148249506391e-06, "epoch": 0.63596214511041, "percentage": 63.58, "elapsed_time": "14:25:33", "remaining_time": "8:15:42"}
+{"current_steps": 3160, "total_steps": 4954, "loss": 0.448, "lr": 3.494510858602217e-06, "epoch": 0.6379810725552051, "percentage": 63.79, "elapsed_time": "14:28:33", "remaining_time": "8:13:06"}
+{"current_steps": 3170, "total_steps": 4954, "loss": 0.45, "lr": 3.4609482322004463e-06, "epoch": 0.64, "percentage": 63.99, "elapsed_time": "14:31:24", "remaining_time": "8:10:24"}
+{"current_steps": 3180, "total_steps": 4954, "loss": 0.4499, "lr": 3.427462037063729e-06, "epoch": 0.6420189274447949, "percentage": 64.19, "elapsed_time": "14:34:01", "remaining_time": "8:07:35"}
+{"current_steps": 3190, "total_steps": 4954, "loss": 0.4451, "lr": 3.394053936159035e-06, "epoch": 0.6440378548895899, "percentage": 64.39, "elapsed_time": "14:36:55", "remaining_time": "8:04:55"}
+{"current_steps": 3200, "total_steps": 4954, "loss": 0.4488, "lr": 3.3607255885750756e-06, "epoch": 0.6460567823343849, "percentage": 64.59, "elapsed_time": "14:39:21", "remaining_time": "8:01:59"}
+{"current_steps": 3210, "total_steps": 4954, "loss": 0.4461, "lr": 3.3274786494399102e-06, "epoch": 0.6480757097791798, "percentage": 64.8, "elapsed_time": "14:42:25", "remaining_time": "7:59:25"}
+{"current_steps": 3220, "total_steps": 4954, "loss": 0.4497, "lr": 3.2943147698387562e-06, "epoch": 0.6500946372239748, "percentage": 65.0, "elapsed_time": "14:45:10", "remaining_time": "7:56:40"}
+{"current_steps": 3230, "total_steps": 4954, "loss": 0.4457, "lr": 3.261235596731982e-06, "epoch": 0.6521135646687697, "percentage": 65.2, "elapsed_time": "14:47:37", "remaining_time": "7:53:45"}
+{"current_steps": 3240, "total_steps": 4954, "loss": 0.4437, "lr": 3.228242772873328e-06, "epoch": 0.6541324921135647, "percentage": 65.4, "elapsed_time": "14:50:38", "remaining_time": "7:51:09"}
+{"current_steps": 3250, "total_steps": 4954, "loss": 0.4488, "lr": 3.195337936728323e-06, "epoch": 0.6561514195583596, "percentage": 65.6, "elapsed_time": "14:53:02", "remaining_time": "7:48:13"}
+{"current_steps": 3260, "total_steps": 4954, "loss": 0.4415, "lr": 3.1625227223929105e-06, "epoch": 0.6581703470031546, "percentage": 65.81, "elapsed_time": "14:56:02", "remaining_time": "7:45:36"}
+{"current_steps": 3270, "total_steps": 4954, "loss": 0.4423, "lr": 3.1297987595123024e-06, "epoch": 0.6601892744479495, "percentage": 66.01, "elapsed_time": "14:58:51", "remaining_time": "7:42:53"}
+{"current_steps": 3280, "total_steps": 4954, "loss": 0.4488, "lr": 3.0971676732000494e-06, "epoch": 0.6622082018927444, "percentage": 66.21, "elapsed_time": "15:01:23", "remaining_time": "7:40:02"}
+{"current_steps": 3290, "total_steps": 4954, "loss": 0.441, "lr": 3.0646310839573302e-06, "epoch": 0.6642271293375395, "percentage": 66.41, "elapsed_time": "15:04:17", "remaining_time": "7:37:21"}
+{"current_steps": 3300, "total_steps": 4954, "loss": 0.454, "lr": 3.03219060759248e-06, "epoch": 0.6662460567823344, "percentage": 66.61, "elapsed_time": "15:06:40", "remaining_time": "7:34:26"}
+{"current_steps": 3310, "total_steps": 4954, "loss": 0.4378, "lr": 2.9998478551407524e-06, "epoch": 0.6682649842271293, "percentage": 66.81, "elapsed_time": "15:09:41", "remaining_time": "7:31:49"}
+{"current_steps": 3320, "total_steps": 4954, "loss": 0.4475, "lr": 2.9676044327842963e-06, "epoch": 0.6702839116719242, "percentage": 67.02, "elapsed_time": "15:12:27", "remaining_time": "7:29:04"}
+{"current_steps": 3330, "total_steps": 4954, "loss": 0.4418, "lr": 2.935461941772412e-06, "epoch": 0.6723028391167193, "percentage": 67.22, "elapsed_time": "15:14:58", "remaining_time": "7:26:13"}
+{"current_steps": 3340, "total_steps": 4954, "loss": 0.438, "lr": 2.9034219783420183e-06, "epoch": 0.6743217665615142, "percentage": 67.42, "elapsed_time": "15:17:56", "remaining_time": "7:23:34"}
+{"current_steps": 3350, "total_steps": 4954, "loss": 0.4498, "lr": 2.871486133638378e-06, "epoch": 0.6763406940063091, "percentage": 67.62, "elapsed_time": "15:20:20", "remaining_time": "7:20:39"}
+{"current_steps": 3360, "total_steps": 4954, "loss": 0.4444, "lr": 2.8396559936360934e-06, "epoch": 0.6783596214511041, "percentage": 67.82, "elapsed_time": "15:23:19", "remaining_time": "7:18:01"}
+{"current_steps": 3370, "total_steps": 4954, "loss": 0.4481, "lr": 2.807933139060337e-06, "epoch": 0.6803785488958991, "percentage": 68.03, "elapsed_time": "15:26:13", "remaining_time": "7:15:21"}
+{"current_steps": 3380, "total_steps": 4954, "loss": 0.4397, "lr": 2.776319145308345e-06, "epoch": 0.682397476340694, "percentage": 68.23, "elapsed_time": "15:28:45", "remaining_time": "7:12:30"}
+{"current_steps": 3390, "total_steps": 4954, "loss": 0.4415, "lr": 2.7448155823711897e-06, "epoch": 0.684416403785489, "percentage": 68.43, "elapsed_time": "15:31:43", "remaining_time": "7:09:51"}
+{"current_steps": 3400, "total_steps": 4954, "loss": 0.4494, "lr": 2.7134240147558124e-06, "epoch": 0.6864353312302839, "percentage": 68.63, "elapsed_time": "15:34:05", "remaining_time": "7:06:55"}
+{"current_steps": 3410, "total_steps": 4954, "loss": 0.4359, "lr": 2.6821460014073187e-06, "epoch": 0.6884542586750788, "percentage": 68.83, "elapsed_time": "15:37:03", "remaining_time": "7:04:17"}
+{"current_steps": 3420, "total_steps": 4954, "loss": 0.4516, "lr": 2.6509830956315684e-06, "epoch": 0.6904731861198738, "percentage": 69.04, "elapsed_time": "15:39:49", "remaining_time": "7:01:32"}
+{"current_steps": 3430, "total_steps": 4954, "loss": 0.4357, "lr": 2.619936845018031e-06, "epoch": 0.6924921135646688, "percentage": 69.24, "elapsed_time": "15:42:21", "remaining_time": "6:58:42"}
+{"current_steps": 3440, "total_steps": 4954, "loss": 0.4467, "lr": 2.5890087913629358e-06, "epoch": 0.6945110410094637, "percentage": 69.44, "elapsed_time": "15:45:19", "remaining_time": "6:56:03"}
+{"current_steps": 3450, "total_steps": 4954, "loss": 0.449, "lr": 2.558200470592701e-06, "epoch": 0.6965299684542586, "percentage": 69.64, "elapsed_time": "15:47:43", "remaining_time": "6:53:08"}
+{"current_steps": 3460, "total_steps": 4954, "loss": 0.436, "lr": 2.527513412687654e-06, "epoch": 0.6985488958990537, "percentage": 69.84, "elapsed_time": "15:50:38", "remaining_time": "6:50:28"}
+{"current_steps": 3470, "total_steps": 4954, "loss": 0.4393, "lr": 2.4969491416060542e-06, "epoch": 0.7005678233438486, "percentage": 70.04, "elapsed_time": "15:53:21", "remaining_time": "6:47:43"}
+{"current_steps": 3480, "total_steps": 4954, "loss": 0.4423, "lr": 2.4665091752084175e-06, "epoch": 0.7025867507886435, "percentage": 70.25, "elapsed_time": "15:55:52", "remaining_time": "6:44:52"}
+{"current_steps": 3490, "total_steps": 4954, "loss": 0.4351, "lr": 2.4361950251821253e-06, "epoch": 0.7046056782334384, "percentage": 70.45, "elapsed_time": "15:58:51", "remaining_time": "6:42:13"}
+{"current_steps": 3500, "total_steps": 4954, "loss": 0.445, "lr": 2.406008196966359e-06, "epoch": 0.7066246056782335, "percentage": 70.65, "elapsed_time": "16:01:16", "remaining_time": "6:39:20"}
+{"current_steps": 3510, "total_steps": 4954, "loss": 0.4322, "lr": 2.375950189677342e-06, "epoch": 0.7086435331230284, "percentage": 70.85, "elapsed_time": "16:04:13", "remaining_time": "6:36:40"}
+{"current_steps": 3520, "total_steps": 4954, "loss": 0.439, "lr": 2.346022496033879e-06, "epoch": 0.7106624605678233, "percentage": 71.05, "elapsed_time": "16:06:58", "remaining_time": "6:33:55"}
+{"current_steps": 3530, "total_steps": 4954, "loss": 0.445, "lr": 2.316226602283243e-06, "epoch": 0.7126813880126183, "percentage": 71.26, "elapsed_time": "16:09:30", "remaining_time": "6:31:06"}
+{"current_steps": 3540, "total_steps": 4954, "loss": 0.4402, "lr": 2.2865639881273494e-06, "epoch": 0.7147003154574133, "percentage": 71.46, "elapsed_time": "16:12:30", "remaining_time": "6:28:27"}
+{"current_steps": 3550, "total_steps": 4954, "loss": 0.445, "lr": 2.25703612664928e-06, "epoch": 0.7167192429022082, "percentage": 71.66, "elapsed_time": "16:14:54", "remaining_time": "6:25:34"}
+{"current_steps": 3560, "total_steps": 4954, "loss": 0.4356, "lr": 2.227644484240135e-06, "epoch": 0.7187381703470032, "percentage": 71.86, "elapsed_time": "16:17:55", "remaining_time": "6:22:55"}
+{"current_steps": 3570, "total_steps": 4954, "loss": 0.4438, "lr": 2.198390520526194e-06, "epoch": 0.7207570977917981, "percentage": 72.06, "elapsed_time": "16:20:37", "remaining_time": "6:20:09"}
+{"current_steps": 3580, "total_steps": 4954, "loss": 0.4464, "lr": 2.1692756882964404e-06, "epoch": 0.722776025236593, "percentage": 72.26, "elapsed_time": "16:23:11", "remaining_time": "6:17:20"}
+{"current_steps": 3590, "total_steps": 4954, "loss": 0.4436, "lr": 2.140301433430414e-06, "epoch": 0.724794952681388, "percentage": 72.47, "elapsed_time": "16:26:10", "remaining_time": "6:14:41"}
+{"current_steps": 3600, "total_steps": 4954, "loss": 0.4433, "lr": 2.1114691948264038e-06, "epoch": 0.726813880126183, "percentage": 72.67, "elapsed_time": "16:28:38", "remaining_time": "6:11:50"}
+{"current_steps": 3610, "total_steps": 4954, "loss": 0.4429, "lr": 2.082780404329988e-06, "epoch": 0.7288328075709779, "percentage": 72.87, "elapsed_time": "16:31:41", "remaining_time": "6:09:12"}
+{"current_steps": 3620, "total_steps": 4954, "loss": 0.4402, "lr": 2.0542364866629292e-06, "epoch": 0.7308517350157728, "percentage": 73.07, "elapsed_time": "16:34:30", "remaining_time": "6:06:29"}
+{"current_steps": 3630, "total_steps": 4954, "loss": 0.4462, "lr": 2.025838859352428e-06, "epoch": 0.7328706624605679, "percentage": 73.27, "elapsed_time": "16:37:00", "remaining_time": "6:03:38"}
+{"current_steps": 3640, "total_steps": 4954, "loss": 0.4298, "lr": 1.997588932660713e-06, "epoch": 0.7348895899053628, "percentage": 73.48, "elapsed_time": "16:39:55", "remaining_time": "6:00:57"}
+{"current_steps": 3650, "total_steps": 4954, "loss": 0.4429, "lr": 1.9694881095150125e-06, "epoch": 0.7369085173501577, "percentage": 73.68, "elapsed_time": "16:42:22", "remaining_time": "5:58:06"}
+{"current_steps": 3660, "total_steps": 4954, "loss": 0.4423, "lr": 1.9415377854378903e-06, "epoch": 0.7389274447949526, "percentage": 73.88, "elapsed_time": "16:45:20", "remaining_time": "5:55:26"}
+{"current_steps": 3670, "total_steps": 4954, "loss": 0.444, "lr": 1.913739348477927e-06, "epoch": 0.7409463722397477, "percentage": 74.08, "elapsed_time": "16:48:05", "remaining_time": "5:52:41"}
+{"current_steps": 3680, "total_steps": 4954, "loss": 0.4432, "lr": 1.8860941791408038e-06, "epoch": 0.7429652996845426, "percentage": 74.28, "elapsed_time": "16:50:38", "remaining_time": "5:49:52"}
+{"current_steps": 3690, "total_steps": 4954, "loss": 0.4351, "lr": 1.8586036503207316e-06, "epoch": 0.7449842271293375, "percentage": 74.49, "elapsed_time": "16:53:35", "remaining_time": "5:47:12"}
+{"current_steps": 3700, "total_steps": 4954, "loss": 0.4445, "lr": 1.8312691272322768e-06, "epoch": 0.7470031545741325, "percentage": 74.69, "elapsed_time": "16:55:59", "remaining_time": "5:44:20"}
+{"current_steps": 3710, "total_steps": 4954, "loss": 0.4392, "lr": 1.804091967342569e-06, "epoch": 0.7490220820189274, "percentage": 74.89, "elapsed_time": "16:58:57", "remaining_time": "5:41:39"}
+{"current_steps": 3720, "total_steps": 4954, "loss": 0.4406, "lr": 1.777073520303874e-06, "epoch": 0.7510410094637224, "percentage": 75.09, "elapsed_time": "17:01:43", "remaining_time": "5:38:55"}
+{"current_steps": 3730, "total_steps": 4954, "loss": 0.4391, "lr": 1.7502151278865798e-06, "epoch": 0.7530599369085174, "percentage": 75.29, "elapsed_time": "17:04:20", "remaining_time": "5:36:08"}
+{"current_steps": 3740, "total_steps": 4954, "loss": 0.4411, "lr": 1.7235181239125587e-06, "epoch": 0.7550788643533123, "percentage": 75.49, "elapsed_time": "17:07:09", "remaining_time": "5:33:24"}
+{"current_steps": 3750, "total_steps": 4954, "loss": 0.4412, "lr": 1.6969838341889288e-06, "epoch": 0.7570977917981072, "percentage": 75.7, "elapsed_time": "17:09:35", "remaining_time": "5:30:34"}
+{"current_steps": 3760, "total_steps": 4954, "loss": 0.4327, "lr": 1.67061357644221e-06, "epoch": 0.7591167192429022, "percentage": 75.9, "elapsed_time": "17:12:31", "remaining_time": "5:27:52"}
+{"current_steps": 3770, "total_steps": 4954, "loss": 0.4403, "lr": 1.6444086602528835e-06, "epoch": 0.7611356466876972, "percentage": 76.1, "elapsed_time": "17:15:21", "remaining_time": "5:25:09"}
+{"current_steps": 3780, "total_steps": 4954, "loss": 0.4399, "lr": 1.6183703869903666e-06, "epoch": 0.7631545741324921, "percentage": 76.3, "elapsed_time": "17:17:57", "remaining_time": "5:22:22"}
+{"current_steps": 3790, "total_steps": 4954, "loss": 0.4484, "lr": 1.59250004974837e-06, "epoch": 0.765173501577287, "percentage": 76.5, "elapsed_time": "17:20:51", "remaining_time": "5:19:40"}
+{"current_steps": 3800, "total_steps": 4954, "loss": 0.442, "lr": 1.5667989332806894e-06, "epoch": 0.7671924290220821, "percentage": 76.71, "elapsed_time": "17:23:16", "remaining_time": "5:16:49"}
+{"current_steps": 3810, "total_steps": 4954, "loss": 0.4339, "lr": 1.5412683139374068e-06, "epoch": 0.769211356466877, "percentage": 76.91, "elapsed_time": "17:26:17", "remaining_time": "5:14:09"}
+{"current_steps": 3820, "total_steps": 4954, "loss": 0.4478, "lr": 1.5159094596014934e-06, "epoch": 0.7712302839116719, "percentage": 77.11, "elapsed_time": "17:29:01", "remaining_time": "5:11:24"}
+{"current_steps": 3830, "total_steps": 4954, "loss": 0.4423, "lr": 1.4907236296258598e-06, "epoch": 0.7732492113564668, "percentage": 77.31, "elapsed_time": "17:31:41", "remaining_time": "5:08:38"}
+{"current_steps": 3840, "total_steps": 4954, "loss": 0.4417, "lr": 1.4657120747708014e-06, "epoch": 0.7752681388012618, "percentage": 77.51, "elapsed_time": "17:34:40", "remaining_time": "5:05:57"}
+{"current_steps": 3850, "total_steps": 4954, "loss": 0.4397, "lr": 1.4408760371418895e-06, "epoch": 0.7772870662460568, "percentage": 77.71, "elapsed_time": "17:37:22", "remaining_time": "5:03:12"}
+{"current_steps": 3860, "total_steps": 4954, "loss": 0.4416, "lr": 1.4162167501282925e-06, "epoch": 0.7793059936908517, "percentage": 77.92, "elapsed_time": "17:40:20", "remaining_time": "5:00:31"}
+{"current_steps": 3870, "total_steps": 4954, "loss": 0.437, "lr": 1.391735438341514e-06, "epoch": 0.7813249211356467, "percentage": 78.12, "elapsed_time": "17:43:09", "remaining_time": "4:57:47"}
+{"current_steps": 3880, "total_steps": 4954, "loss": 0.4425, "lr": 1.3674333175545818e-06, "epoch": 0.7833438485804416, "percentage": 78.32, "elapsed_time": "17:45:39", "remaining_time": "4:54:58"}
+{"current_steps": 3890, "total_steps": 4954, "loss": 0.4371, "lr": 1.343311594641674e-06, "epoch": 0.7853627760252366, "percentage": 78.52, "elapsed_time": "17:48:34", "remaining_time": "4:52:16"}
+{"current_steps": 3900, "total_steps": 4954, "loss": 0.4428, "lr": 1.3193714675181813e-06, "epoch": 0.7873817034700316, "percentage": 78.72, "elapsed_time": "17:50:56", "remaining_time": "4:49:25"}
+{"current_steps": 3910, "total_steps": 4954, "loss": 0.4307, "lr": 1.2956141250812144e-06, "epoch": 0.7894006309148265, "percentage": 78.93, "elapsed_time": "17:53:58", "remaining_time": "4:46:45"}
+{"current_steps": 3920, "total_steps": 4954, "loss": 0.447, "lr": 1.272040747150563e-06, "epoch": 0.7914195583596214, "percentage": 79.13, "elapsed_time": "17:56:48", "remaining_time": "4:44:02"}
+{"current_steps": 3930, "total_steps": 4954, "loss": 0.4333, "lr": 1.2486525044101123e-06, "epoch": 0.7934384858044164, "percentage": 79.33, "elapsed_time": "17:59:21", "remaining_time": "4:41:14"}
+{"current_steps": 3940, "total_steps": 4954, "loss": 0.4403, "lr": 1.2254505583496922e-06, "epoch": 0.7954574132492114, "percentage": 79.53, "elapsed_time": "18:02:14", "remaining_time": "4:38:31"}
+{"current_steps": 3950, "total_steps": 4954, "loss": 0.4454, "lr": 1.2024360612074055e-06, "epoch": 0.7974763406940063, "percentage": 79.73, "elapsed_time": "18:04:39", "remaining_time": "4:35:41"}
+{"current_steps": 3960, "total_steps": 4954, "loss": 0.436, "lr": 1.179610155912405e-06, "epoch": 0.7994952681388012, "percentage": 79.94, "elapsed_time": "18:07:39", "remaining_time": "4:33:00"}
+{"current_steps": 3970, "total_steps": 4954, "loss": 0.4393, "lr": 1.1569739760281295e-06, "epoch": 0.8015141955835963, "percentage": 80.14, "elapsed_time": "18:10:29", "remaining_time": "4:30:17"}
+{"current_steps": 3980, "total_steps": 4954, "loss": 0.4439, "lr": 1.1345286456960186e-06, "epoch": 0.8035331230283912, "percentage": 80.34, "elapsed_time": "18:13:04", "remaining_time": "4:27:29"}
+{"current_steps": 3990, "total_steps": 4954, "loss": 0.4413, "lr": 1.1122752795796748e-06, "epoch": 0.8055520504731861, "percentage": 80.54, "elapsed_time": "18:16:03", "remaining_time": "4:24:48"}
+{"current_steps": 4000, "total_steps": 4954, "loss": 0.4422, "lr": 1.0902149828095154e-06, "epoch": 0.807570977917981, "percentage": 80.74, "elapsed_time": "18:18:27", "remaining_time": "4:21:58"}
+{"current_steps": 4010, "total_steps": 4954, "loss": 0.4386, "lr": 1.0683488509278928e-06, "epoch": 0.809589905362776, "percentage": 80.94, "elapsed_time": "18:21:24", "remaining_time": "4:19:17"}
+{"current_steps": 4020, "total_steps": 4954, "loss": 0.4363, "lr": 1.0466779698346797e-06, "epoch": 0.811608832807571, "percentage": 81.15, "elapsed_time": "18:24:10", "remaining_time": "4:16:32"}
+{"current_steps": 4030, "total_steps": 4954, "loss": 0.4365, "lr": 1.025203415733348e-06, "epoch": 0.8136277602523659, "percentage": 81.35, "elapsed_time": "18:26:44", "remaining_time": "4:13:45"}
+{"current_steps": 4040, "total_steps": 4954, "loss": 0.4345, "lr": 1.0039262550775235e-06, "epoch": 0.8156466876971609, "percentage": 81.55, "elapsed_time": "18:29:36", "remaining_time": "4:11:02"}
+{"current_steps": 4050, "total_steps": 4954, "loss": 0.4404, "lr": 9.828475445180212e-07, "epoch": 0.8176656151419558, "percentage": 81.75, "elapsed_time": "18:32:04", "remaining_time": "4:08:13"}
+{"current_steps": 4060, "total_steps": 4954, "loss": 0.4369, "lr": 9.61968330850374e-07, "epoch": 0.8196845425867508, "percentage": 81.95, "elapsed_time": "18:35:04", "remaining_time": "4:05:32"}
+{"current_steps": 4070, "total_steps": 4954, "loss": 0.4434, "lr": 9.412896509628439e-07, "epoch": 0.8217034700315458, "percentage": 82.16, "elapsed_time": "18:37:54", "remaining_time": "4:02:48"}
+{"current_steps": 4080, "total_steps": 4954, "loss": 0.4395, "lr": 9.208125317849304e-07, "epoch": 0.8237223974763407, "percentage": 82.36, "elapsed_time": "18:40:26", "remaining_time": "4:00:00"}
+{"current_steps": 4090, "total_steps": 4954, "loss": 0.4405, "lr": 9.005379902363753e-07, "epoch": 0.8257413249211356, "percentage": 82.56, "elapsed_time": "18:43:25", "remaining_time": "3:57:19"}
+{"current_steps": 4100, "total_steps": 4954, "loss": 0.4449, "lr": 8.804670331766557e-07, "epoch": 0.8277602523659306, "percentage": 82.76, "elapsed_time": "18:45:52", "remaining_time": "3:54:30"}
+{"current_steps": 4110, "total_steps": 4954, "loss": 0.4359, "lr": 8.606006573549836e-07, "epoch": 0.8297791798107256, "percentage": 82.96, "elapsed_time": "18:48:56", "remaining_time": "3:51:49"}
+{"current_steps": 4120, "total_steps": 4954, "loss": 0.4413, "lr": 8.409398493608089e-07, "epoch": 0.8317981072555205, "percentage": 83.17, "elapsed_time": "18:51:42", "remaining_time": "3:49:05"}
+{"current_steps": 4130, "total_steps": 4954, "loss": 0.4409, "lr": 8.214855855748249e-07, "epoch": 0.8338170347003154, "percentage": 83.37, "elapsed_time": "18:54:17", "remaining_time": "3:46:18"}
+{"current_steps": 4140, "total_steps": 4954, "loss": 0.4354, "lr": 8.022388321204688e-07, "epoch": 0.8358359621451104, "percentage": 83.57, "elapsed_time": "18:57:13", "remaining_time": "3:43:36"}
+{"current_steps": 4150, "total_steps": 4954, "loss": 0.4445, "lr": 7.832005448159585e-07, "epoch": 0.8378548895899054, "percentage": 83.77, "elapsed_time": "18:59:37", "remaining_time": "3:40:47"}
+{"current_steps": 4160, "total_steps": 4954, "loss": 0.4374, "lr": 7.643716691268171e-07, "epoch": 0.8398738170347003, "percentage": 83.97, "elapsed_time": "19:02:37", "remaining_time": "3:38:05"}
+{"current_steps": 4170, "total_steps": 4954, "loss": 0.4408, "lr": 7.457531401189188e-07, "epoch": 0.8418927444794952, "percentage": 84.17, "elapsed_time": "19:05:21", "remaining_time": "3:35:20"}
+{"current_steps": 4180, "total_steps": 4954, "loss": 0.4376, "lr": 7.273458824120555e-07, "epoch": 0.8439116719242902, "percentage": 84.38, "elapsed_time": "19:07:56", "remaining_time": "3:32:33"}
+{"current_steps": 4190, "total_steps": 4954, "loss": 0.4407, "lr": 7.091508101340189e-07, "epoch": 0.8459305993690852, "percentage": 84.58, "elapsed_time": "19:10:53", "remaining_time": "3:29:51"}
+{"current_steps": 4200, "total_steps": 4954, "loss": 0.4489, "lr": 6.91168826875201e-07, "epoch": 0.8479495268138801, "percentage": 84.78, "elapsed_time": "19:13:20", "remaining_time": "3:27:03"}
+{"current_steps": 4210, "total_steps": 4954, "loss": 0.435, "lr": 6.734008256437253e-07, "epoch": 0.8499684542586751, "percentage": 84.98, "elapsed_time": "19:16:22", "remaining_time": "3:24:21"}
+{"current_steps": 4220, "total_steps": 4954, "loss": 0.4375, "lr": 6.558476888210935e-07, "epoch": 0.85198738170347, "percentage": 85.18, "elapsed_time": "19:19:11", "remaining_time": "3:21:37"}
+{"current_steps": 4230, "total_steps": 4954, "loss": 0.4409, "lr": 6.38510288118368e-07, "epoch": 0.854006309148265, "percentage": 85.39, "elapsed_time": "19:21:44", "remaining_time": "3:18:50"}
+{"current_steps": 4240, "total_steps": 4954, "loss": 0.4418, "lr": 6.213894845328844e-07, "epoch": 0.85602523659306, "percentage": 85.59, "elapsed_time": "19:24:39", "remaining_time": "3:16:07"}
+{"current_steps": 4250, "total_steps": 4954, "loss": 0.4452, "lr": 6.044861283054876e-07, "epoch": 0.8580441640378549, "percentage": 85.79, "elapsed_time": "19:27:10", "remaining_time": "3:13:20"}
+{"current_steps": 4260, "total_steps": 4954, "loss": 0.4423, "lr": 5.878010588783101e-07, "epoch": 0.8600630914826498, "percentage": 85.99, "elapsed_time": "19:30:07", "remaining_time": "3:10:37"}
+{"current_steps": 4270, "total_steps": 4954, "loss": 0.4429, "lr": 5.713351048530874e-07, "epoch": 0.8620820189274448, "percentage": 86.19, "elapsed_time": "19:32:55", "remaining_time": "3:07:53"}
+{"current_steps": 4280, "total_steps": 4954, "loss": 0.4511, "lr": 5.550890839500067e-07, "epoch": 0.8641009463722398, "percentage": 86.39, "elapsed_time": "19:35:28", "remaining_time": "3:05:06"}
+{"current_steps": 4290, "total_steps": 4954, "loss": 0.4322, "lr": 5.390638029670908e-07, "epoch": 0.8661198738170347, "percentage": 86.6, "elapsed_time": "19:38:26", "remaining_time": "3:02:23"}
+{"current_steps": 4300, "total_steps": 4954, "loss": 0.4457, "lr": 5.232600577401436e-07, "epoch": 0.8681388012618296, "percentage": 86.8, "elapsed_time": "19:40:53", "remaining_time": "2:59:36"}
+{"current_steps": 4310, "total_steps": 4954, "loss": 0.4327, "lr": 5.076786331032224e-07, "epoch": 0.8701577287066246, "percentage": 87.0, "elapsed_time": "19:43:56", "remaining_time": "2:56:54"}
+{"current_steps": 4320, "total_steps": 4954, "loss": 0.4447, "lr": 4.923203028496576e-07, "epoch": 0.8721766561514196, "percentage": 87.2, "elapsed_time": "19:46:46", "remaining_time": "2:54:10"}
+{"current_steps": 4330, "total_steps": 4954, "loss": 0.4402, "lr": 4.771858296936311e-07, "epoch": 0.8741955835962145, "percentage": 87.4, "elapsed_time": "19:49:18", "remaining_time": "2:51:23"}
+{"current_steps": 4340, "total_steps": 4954, "loss": 0.4455, "lr": 4.622759652322989e-07, "epoch": 0.8762145110410094, "percentage": 87.61, "elapsed_time": "19:52:14", "remaining_time": "2:48:40"}
+{"current_steps": 4350, "total_steps": 4954, "loss": 0.4467, "lr": 4.475914499084605e-07, "epoch": 0.8782334384858044, "percentage": 87.81, "elapsed_time": "19:54:39", "remaining_time": "2:45:52"}
+{"current_steps": 4360, "total_steps": 4954, "loss": 0.4287, "lr": 4.331330129737954e-07, "epoch": 0.8802523659305994, "percentage": 88.01, "elapsed_time": "19:57:38", "remaining_time": "2:43:09"}
+{"current_steps": 4370, "total_steps": 4954, "loss": 0.4446, "lr": 4.189013724526392e-07, "epoch": 0.8822712933753943, "percentage": 88.21, "elapsed_time": "20:00:27", "remaining_time": "2:40:25"}
+{"current_steps": 4380, "total_steps": 4954, "loss": 0.4354, "lr": 4.048972351063313e-07, "epoch": 0.8842902208201893, "percentage": 88.41, "elapsed_time": "20:03:02", "remaining_time": "2:37:39"}
+{"current_steps": 4390, "total_steps": 4954, "loss": 0.4346, "lr": 3.9112129639811535e-07, "epoch": 0.8863091482649842, "percentage": 88.62, "elapsed_time": "20:05:55", "remaining_time": "2:34:55"}
+{"current_steps": 4400, "total_steps": 4954, "loss": 0.4372, "lr": 3.7757424045860025e-07, "epoch": 0.8883280757097792, "percentage": 88.82, "elapsed_time": "20:08:20", "remaining_time": "2:32:08"}
+{"current_steps": 4410, "total_steps": 4954, "loss": 0.4314, "lr": 3.642567400517838e-07, "epoch": 0.8903470031545742, "percentage": 89.02, "elapsed_time": "20:11:16", "remaining_time": "2:29:25"}
+{"current_steps": 4420, "total_steps": 4954, "loss": 0.4382, "lr": 3.511694565416485e-07, "epoch": 0.8923659305993691, "percentage": 89.22, "elapsed_time": "20:14:03", "remaining_time": "2:26:40"}
+{"current_steps": 4430, "total_steps": 4954, "loss": 0.4399, "lr": 3.383130398593121e-07, "epoch": 0.894384858044164, "percentage": 89.42, "elapsed_time": "20:16:40", "remaining_time": "2:23:54"}
+{"current_steps": 4440, "total_steps": 4954, "loss": 0.4437, "lr": 3.2568812847074913e-07, "epoch": 0.8964037854889589, "percentage": 89.62, "elapsed_time": "20:19:33", "remaining_time": "2:21:10"}
+{"current_steps": 4450, "total_steps": 4954, "loss": 0.4415, "lr": 3.1329534934509186e-07, "epoch": 0.898422712933754, "percentage": 89.83, "elapsed_time": "20:22:01", "remaining_time": "2:18:24"}
+{"current_steps": 4460, "total_steps": 4954, "loss": 0.4317, "lr": 3.011353179234888e-07, "epoch": 0.9004416403785489, "percentage": 90.03, "elapsed_time": "20:24:59", "remaining_time": "2:15:40"}
+{"current_steps": 4470, "total_steps": 4954, "loss": 0.444, "lr": 2.8920863808853947e-07, "epoch": 0.9024605678233438, "percentage": 90.23, "elapsed_time": "20:27:53", "remaining_time": "2:12:57"}
+{"current_steps": 4480, "total_steps": 4954, "loss": 0.4367, "lr": 2.775159021343082e-07, "epoch": 0.9044794952681388, "percentage": 90.43, "elapsed_time": "20:30:28", "remaining_time": "2:10:11"}
+{"current_steps": 4490, "total_steps": 4954, "loss": 0.4412, "lr": 2.660576907369111e-07, "epoch": 0.9064984227129338, "percentage": 90.63, "elapsed_time": "20:33:23", "remaining_time": "2:07:27"}
+{"current_steps": 4500, "total_steps": 4954, "loss": 0.4403, "lr": 2.5483457292567517e-07, "epoch": 0.9085173501577287, "percentage": 90.84, "elapsed_time": "20:35:46", "remaining_time": "2:04:40"}
+{"current_steps": 4510, "total_steps": 4954, "loss": 0.4402, "lr": 2.4384710605488195e-07, "epoch": 0.9105362776025236, "percentage": 91.04, "elapsed_time": "20:38:44", "remaining_time": "2:01:57"}
+{"current_steps": 4520, "total_steps": 4954, "loss": 0.4399, "lr": 2.330958357760882e-07, "epoch": 0.9125552050473186, "percentage": 91.24, "elapsed_time": "20:41:36", "remaining_time": "1:59:12"}
+{"current_steps": 4530, "total_steps": 4954, "loss": 0.4316, "lr": 2.225812960110263e-07, "epoch": 0.9145741324921136, "percentage": 91.44, "elapsed_time": "20:44:11", "remaining_time": "1:56:27"}
+{"current_steps": 4540, "total_steps": 4954, "loss": 0.4402, "lr": 2.123040089250944e-07, "epoch": 0.9165930599369085, "percentage": 91.64, "elapsed_time": "20:47:04", "remaining_time": "1:53:43"}
+{"current_steps": 4550, "total_steps": 4954, "loss": 0.4481, "lr": 2.0226448490141715e-07, "epoch": 0.9186119873817035, "percentage": 91.84, "elapsed_time": "20:49:27", "remaining_time": "1:50:56"}
+{"current_steps": 4560, "total_steps": 4954, "loss": 0.4317, "lr": 1.9246322251550653e-07, "epoch": 0.9206309148264984, "percentage": 92.05, "elapsed_time": "20:52:26", "remaining_time": "1:48:12"}
+{"current_steps": 4570, "total_steps": 4954, "loss": 0.4427, "lr": 1.829007085104978e-07, "epoch": 0.9226498422712934, "percentage": 92.25, "elapsed_time": "20:55:15", "remaining_time": "1:45:28"}
+{"current_steps": 4580, "total_steps": 4954, "loss": 0.4485, "lr": 1.7357741777297987e-07, "epoch": 0.9246687697160884, "percentage": 92.45, "elapsed_time": "20:57:51", "remaining_time": "1:42:42"}
+{"current_steps": 4590, "total_steps": 4954, "loss": 0.4312, "lr": 1.644938133094076e-07, "epoch": 0.9266876971608833, "percentage": 92.65, "elapsed_time": "21:00:50", "remaining_time": "1:39:59"}
+{"current_steps": 4600, "total_steps": 4954, "loss": 0.4461, "lr": 1.5565034622311349e-07, "epoch": 0.9287066246056782, "percentage": 92.85, "elapsed_time": "21:03:17", "remaining_time": "1:37:13"}
+{"current_steps": 4610, "total_steps": 4954, "loss": 0.4375, "lr": 1.4704745569190327e-07, "epoch": 0.9307255520504731, "percentage": 93.06, "elapsed_time": "21:06:19", "remaining_time": "1:34:29"}
+{"current_steps": 4620, "total_steps": 4954, "loss": 0.4399, "lr": 1.3868556894624353e-07, "epoch": 0.9327444794952682, "percentage": 93.26, "elapsed_time": "21:09:09", "remaining_time": "1:31:45"}
+{"current_steps": 4630, "total_steps": 4954, "loss": 0.4385, "lr": 1.30565101248048e-07, "epoch": 0.9347634069400631, "percentage": 93.46, "elapsed_time": "21:11:45", "remaining_time": "1:28:59"}
+{"current_steps": 4640, "total_steps": 4954, "loss": 0.4416, "lr": 1.226864558700541e-07, "epoch": 0.936782334384858, "percentage": 93.66, "elapsed_time": "21:14:37", "remaining_time": "1:26:15"}
+{"current_steps": 4650, "total_steps": 4954, "loss": 0.4424, "lr": 1.1505002407579512e-07, "epoch": 0.938801261829653, "percentage": 93.86, "elapsed_time": "21:17:03", "remaining_time": "1:23:29"}
+{"current_steps": 4660, "total_steps": 4954, "loss": 0.4368, "lr": 1.0765618510017118e-07, "epoch": 0.940820189274448, "percentage": 94.07, "elapsed_time": "21:19:57", "remaining_time": "1:20:45"}
+{"current_steps": 4670, "total_steps": 4954, "loss": 0.4353, "lr": 1.0050530613061327e-07, "epoch": 0.9428391167192429, "percentage": 94.27, "elapsed_time": "21:22:48", "remaining_time": "1:18:00"}
+{"current_steps": 4680, "total_steps": 4954, "loss": 0.4391, "lr": 9.359774228885177e-08, "epoch": 0.9448580441640378, "percentage": 94.47, "elapsed_time": "21:25:22", "remaining_time": "1:15:15"}
+{"current_steps": 4690, "total_steps": 4954, "loss": 0.4388, "lr": 8.693383661327882e-08, "epoch": 0.9468769716088328, "percentage": 94.67, "elapsed_time": "21:28:19", "remaining_time": "1:12:31"}
+{"current_steps": 4700, "total_steps": 4954, "loss": 0.4486, "lr": 8.051392004191139e-08, "epoch": 0.9488958990536278, "percentage": 94.87, "elapsed_time": "21:30:45", "remaining_time": "1:09:45"}
+{"current_steps": 4710, "total_steps": 4954, "loss": 0.4385, "lr": 7.433831139595727e-08, "epoch": 0.9509148264984227, "percentage": 95.07, "elapsed_time": "21:33:39", "remaining_time": "1:07:01"}
+{"current_steps": 4720, "total_steps": 4954, "loss": 0.4362, "lr": 6.840731736398542e-08, "epoch": 0.9529337539432177, "percentage": 95.28, "elapsed_time": "21:36:29", "remaining_time": "1:04:16"}
+{"current_steps": 4730, "total_steps": 4954, "loss": 0.4356, "lr": 6.272123248668993e-08, "epoch": 0.9549526813880126, "percentage": 95.48, "elapsed_time": "21:39:02", "remaining_time": "1:01:31"}
+{"current_steps": 4740, "total_steps": 4954, "loss": 0.4406, "lr": 5.728033914226494e-08, "epoch": 0.9569716088328075, "percentage": 95.68, "elapsed_time": "21:41:59", "remaining_time": "0:58:46"}
+{"current_steps": 4750, "total_steps": 4954, "loss": 0.4457, "lr": 5.2084907532383156e-08, "epoch": 0.9589905362776026, "percentage": 95.88, "elapsed_time": "21:44:21", "remaining_time": "0:56:01"}
+{"current_steps": 4760, "total_steps": 4954, "loss": 0.4337, "lr": 4.7135195668776e-08, "epoch": 0.9610094637223975, "percentage": 96.08, "elapsed_time": "21:47:18", "remaining_time": "0:53:16"}
+{"current_steps": 4770, "total_steps": 4954, "loss": 0.4413, "lr": 4.243144936041943e-08, "epoch": 0.9630283911671924, "percentage": 96.29, "elapsed_time": "21:50:09", "remaining_time": "0:50:32"}
+{"current_steps": 4780, "total_steps": 4954, "loss": 0.4325, "lr": 3.797390220132757e-08, "epoch": 0.9650473186119873, "percentage": 96.49, "elapsed_time": "21:52:43", "remaining_time": "0:47:47"}
+{"current_steps": 4790, "total_steps": 4954, "loss": 0.4377, "lr": 3.3762775558952576e-08, "epoch": 0.9670662460567824, "percentage": 96.69, "elapsed_time": "21:55:46", "remaining_time": "0:45:02"}
+{"current_steps": 4800, "total_steps": 4954, "loss": 0.4439, "lr": 2.9798278563190618e-08, "epoch": 0.9690851735015773, "percentage": 96.89, "elapsed_time": "21:58:15", "remaining_time": "0:42:17"}
+{"current_steps": 4810, "total_steps": 4954, "loss": 0.4377, "lr": 2.6080608095997438e-08, "epoch": 0.9711041009463722, "percentage": 97.09, "elapsed_time": "22:01:07", "remaining_time": "0:39:33"}
+{"current_steps": 4820, "total_steps": 4954, "loss": 0.4424, "lr": 2.2609948781607827e-08, "epoch": 0.9731230283911672, "percentage": 97.3, "elapsed_time": "22:03:53", "remaining_time": "0:36:48"}
+{"current_steps": 4830, "total_steps": 4954, "loss": 0.4412, "lr": 1.9386472977370728e-08, "epoch": 0.9751419558359622, "percentage": 97.5, "elapsed_time": "22:06:30", "remaining_time": "0:34:03"}
+{"current_steps": 4840, "total_steps": 4954, "loss": 0.4382, "lr": 1.6410340765187772e-08, "epoch": 0.9771608832807571, "percentage": 97.7, "elapsed_time": "22:09:28", "remaining_time": "0:31:18"}
+{"current_steps": 4850, "total_steps": 4954, "loss": 0.4387, "lr": 1.3681699943564053e-08, "epoch": 0.979179810725552, "percentage": 97.9, "elapsed_time": "22:11:57", "remaining_time": "0:28:33"}
+{"current_steps": 4860, "total_steps": 4954, "loss": 0.4431, "lr": 1.1200686020266805e-08, "epoch": 0.981198738170347, "percentage": 98.1, "elapsed_time": "22:15:00", "remaining_time": "0:25:49"}
+{"current_steps": 4870, "total_steps": 4954, "loss": 0.4393, "lr": 8.967422205598541e-09, "epoch": 0.983217665615142, "percentage": 98.3, "elapsed_time": "22:17:52", "remaining_time": "0:23:04"}
+{"current_steps": 4880, "total_steps": 4954, "loss": 0.436, "lr": 6.982019406275853e-09, "epoch": 0.9852365930599369, "percentage": 98.51, "elapsed_time": "22:20:22", "remaining_time": "0:20:19"}
+{"current_steps": 4890, "total_steps": 4954, "loss": 0.4316, "lr": 5.244576219922693e-09, "epoch": 0.9872555205047319, "percentage": 98.71, "elapsed_time": "22:23:18", "remaining_time": "0:17:34"}
+{"current_steps": 4900, "total_steps": 4954, "loss": 0.4463, "lr": 3.755178930173742e-09, "epoch": 0.9892744479495268, "percentage": 98.91, "elapsed_time": "22:25:44", "remaining_time": "0:14:49"}
+{"current_steps": 4910, "total_steps": 4954, "loss": 0.4327, "lr": 2.513901502389504e-09, "epoch": 0.9912933753943217, "percentage": 99.11, "elapsed_time": "22:28:43", "remaining_time": "0:12:05"}
+{"current_steps": 4920, "total_steps": 4954, "loss": 0.4403, "lr": 1.520805579983131e-09, "epoch": 0.9933123028391168, "percentage": 99.31, "elapsed_time": "22:31:28", "remaining_time": "0:09:20"}
+{"current_steps": 4930, "total_steps": 4954, "loss": 0.4385, "lr": 7.759404813600935e-10, "epoch": 0.9953312302839117, "percentage": 99.52, "elapsed_time": "22:34:00", "remaining_time": "0:06:35"}
+{"current_steps": 4940, "total_steps": 4954, "loss": 0.4387, "lr": 2.7934319746625306e-10, "epoch": 0.9973501577287066, "percentage": 99.72, "elapsed_time": "22:36:56", "remaining_time": "0:03:50"}
+{"current_steps": 4950, "total_steps": 4954, "loss": 0.4391, "lr": 3.103838995321962e-11, "epoch": 0.9993690851735015, "percentage": 99.92, "elapsed_time": "22:39:22", "remaining_time": "0:01:05"}
+{"current_steps": 4954, "total_steps": 4954, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "22:40:48", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,3508 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4954,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002018927444794953,
+      "grad_norm": 2.3389563305266345,
+      "learning_rate": 1.8145161290322583e-07,
+      "loss": 0.7881,
+      "step": 10
+    },
+    {
+      "epoch": 0.004037854889589906,
+      "grad_norm": 2.024167058240825,
+      "learning_rate": 3.830645161290323e-07,
+      "loss": 0.8121,
+      "step": 20
+    },
+    {
+      "epoch": 0.006056782334384858,
+      "grad_norm": 1.4351269819866417,
+      "learning_rate": 5.846774193548388e-07,
+      "loss": 0.7797,
+      "step": 30
+    },
+    {
+      "epoch": 0.008075709779179811,
+      "grad_norm": 0.9310252821124614,
+      "learning_rate": 7.862903225806453e-07,
+      "loss": 0.7318,
+      "step": 40
+    },
+    {
+      "epoch": 0.010094637223974764,
+      "grad_norm": 0.9557517206875442,
+      "learning_rate": 9.879032258064516e-07,
+      "loss": 0.7018,
+      "step": 50
+    },
+    {
+      "epoch": 0.012113564668769715,
+      "grad_norm": 0.5829217778568054,
+      "learning_rate": 1.1895161290322582e-06,
+      "loss": 0.6708,
+      "step": 60
+    },
+    {
+      "epoch": 0.014132492113564668,
+      "grad_norm": 0.5112881851342524,
+      "learning_rate": 1.3911290322580644e-06,
+      "loss": 0.6417,
+      "step": 70
+    },
+    {
+      "epoch": 0.016151419558359623,
+      "grad_norm": 0.5140187941233466,
+      "learning_rate": 1.5927419354838712e-06,
+      "loss": 0.6227,
+      "step": 80
+    },
+    {
+      "epoch": 0.018170347003154574,
+      "grad_norm": 0.4872446144280347,
+      "learning_rate": 1.7943548387096777e-06,
+      "loss": 0.615,
+      "step": 90
+    },
+    {
+      "epoch": 0.02018927444794953,
+      "grad_norm": 0.5191969395080858,
+      "learning_rate": 1.9959677419354837e-06,
+      "loss": 0.6105,
+      "step": 100
+    },
+    {
+      "epoch": 0.02220820189274448,
+      "grad_norm": 0.451802382492337,
+      "learning_rate": 2.1975806451612907e-06,
+      "loss": 0.5911,
+      "step": 110
+    },
+    {
+      "epoch": 0.02422712933753943,
+      "grad_norm": 0.42163928465445194,
+      "learning_rate": 2.399193548387097e-06,
+      "loss": 0.5921,
+      "step": 120
+    },
+    {
+      "epoch": 0.026246056782334385,
+      "grad_norm": 0.4552027864136731,
+      "learning_rate": 2.6008064516129032e-06,
+      "loss": 0.5818,
+      "step": 130
+    },
+    {
+      "epoch": 0.028264984227129336,
+      "grad_norm": 0.44985963500335385,
+      "learning_rate": 2.8024193548387097e-06,
+      "loss": 0.5876,
+      "step": 140
+    },
+    {
+      "epoch": 0.03028391167192429,
+      "grad_norm": 0.5111630527751778,
+      "learning_rate": 3.0040322580645167e-06,
+      "loss": 0.5728,
+      "step": 150
+    },
+    {
+      "epoch": 0.032302839116719245,
+      "grad_norm": 0.44240607593167414,
+      "learning_rate": 3.2056451612903228e-06,
+      "loss": 0.5643,
+      "step": 160
+    },
+    {
+      "epoch": 0.03432176656151419,
+      "grad_norm": 0.4865981695157576,
+      "learning_rate": 3.4072580645161293e-06,
+      "loss": 0.5617,
+      "step": 170
+    },
+    {
+      "epoch": 0.03634069400630915,
+      "grad_norm": 0.6085288533687223,
+      "learning_rate": 3.6088709677419358e-06,
+      "loss": 0.5501,
+      "step": 180
+    },
+    {
+      "epoch": 0.0383596214511041,
+      "grad_norm": 0.47289717909858964,
+      "learning_rate": 3.8104838709677423e-06,
+      "loss": 0.559,
+      "step": 190
+    },
+    {
+      "epoch": 0.04037854889589906,
+      "grad_norm": 0.5389683685989423,
+      "learning_rate": 4.012096774193548e-06,
+      "loss": 0.5601,
+      "step": 200
+    },
+    {
+      "epoch": 0.042397476340694004,
+      "grad_norm": 0.44905068010794785,
+      "learning_rate": 4.213709677419355e-06,
+      "loss": 0.546,
+      "step": 210
+    },
+    {
+      "epoch": 0.04441640378548896,
+      "grad_norm": 0.4738265544351665,
+      "learning_rate": 4.415322580645161e-06,
+      "loss": 0.5527,
+      "step": 220
+    },
+    {
+      "epoch": 0.04643533123028391,
+      "grad_norm": 0.48116551901846,
+      "learning_rate": 4.616935483870968e-06,
+      "loss": 0.5428,
+      "step": 230
+    },
+    {
+      "epoch": 0.04845425867507886,
+      "grad_norm": 0.4514773717137442,
+      "learning_rate": 4.818548387096774e-06,
+      "loss": 0.5338,
+      "step": 240
+    },
+    {
+      "epoch": 0.050473186119873815,
+      "grad_norm": 0.5092040454559039,
+      "learning_rate": 5.020161290322581e-06,
+      "loss": 0.5546,
+      "step": 250
+    },
+    {
+      "epoch": 0.05249211356466877,
+      "grad_norm": 0.45858657596184155,
+      "learning_rate": 5.221774193548388e-06,
+      "loss": 0.5408,
+      "step": 260
+    },
+    {
+      "epoch": 0.054511041009463725,
+      "grad_norm": 0.47766211942842146,
+      "learning_rate": 5.423387096774194e-06,
+      "loss": 0.5427,
+      "step": 270
+    },
+    {
+      "epoch": 0.05652996845425867,
+      "grad_norm": 0.5108229913280311,
+      "learning_rate": 5.625e-06,
+      "loss": 0.5357,
+      "step": 280
+    },
+    {
+      "epoch": 0.05854889589905363,
+      "grad_norm": 0.5232937676969737,
+      "learning_rate": 5.8266129032258064e-06,
+      "loss": 0.5316,
+      "step": 290
+    },
+    {
+      "epoch": 0.06056782334384858,
+      "grad_norm": 0.5241114539289579,
+      "learning_rate": 6.028225806451613e-06,
+      "loss": 0.5444,
+      "step": 300
+    },
+    {
+      "epoch": 0.06258675078864354,
+      "grad_norm": 0.9566252867340465,
+      "learning_rate": 6.2298387096774194e-06,
+      "loss": 0.5256,
+      "step": 310
+    },
+    {
+      "epoch": 0.06460567823343849,
+      "grad_norm": 0.4700069264487592,
+      "learning_rate": 6.431451612903226e-06,
+      "loss": 0.535,
+      "step": 320
+    },
+    {
+      "epoch": 0.06662460567823345,
+      "grad_norm": 0.46343674018411934,
+      "learning_rate": 6.633064516129033e-06,
+      "loss": 0.5281,
+      "step": 330
+    },
+    {
+      "epoch": 0.06864353312302839,
+      "grad_norm": 0.46610206235853135,
+      "learning_rate": 6.834677419354839e-06,
+      "loss": 0.5324,
+      "step": 340
+    },
+    {
+      "epoch": 0.07066246056782334,
+      "grad_norm": 0.5217091961421014,
+      "learning_rate": 7.0362903225806454e-06,
+      "loss": 0.5321,
+      "step": 350
+    },
+    {
+      "epoch": 0.0726813880126183,
+      "grad_norm": 0.4532872443875366,
+      "learning_rate": 7.2379032258064515e-06,
+      "loss": 0.5235,
+      "step": 360
+    },
+    {
+      "epoch": 0.07470031545741325,
+      "grad_norm": 0.5481191485070994,
+      "learning_rate": 7.4395161290322585e-06,
+      "loss": 0.5203,
+      "step": 370
+    },
+    {
+      "epoch": 0.0767192429022082,
+      "grad_norm": 0.4817884817896886,
+      "learning_rate": 7.641129032258065e-06,
+      "loss": 0.5289,
+      "step": 380
+    },
+    {
+      "epoch": 0.07873817034700316,
+      "grad_norm": 0.463062633118143,
+      "learning_rate": 7.842741935483872e-06,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 0.08075709779179811,
+      "grad_norm": 0.5267129255916911,
+      "learning_rate": 8.044354838709678e-06,
+      "loss": 0.5239,
+      "step": 400
+    },
+    {
+      "epoch": 0.08277602523659305,
+      "grad_norm": 0.4703183395271576,
+      "learning_rate": 8.245967741935484e-06,
+      "loss": 0.5217,
+      "step": 410
+    },
+    {
+      "epoch": 0.08479495268138801,
+      "grad_norm": 0.4559407675951848,
+      "learning_rate": 8.447580645161291e-06,
+      "loss": 0.5187,
+      "step": 420
+    },
+    {
+      "epoch": 0.08681388012618296,
+      "grad_norm": 0.4638358181971901,
+      "learning_rate": 8.649193548387097e-06,
+      "loss": 0.5194,
+      "step": 430
+    },
+    {
+      "epoch": 0.08883280757097792,
+      "grad_norm": 0.47768712570505284,
+      "learning_rate": 8.850806451612905e-06,
+      "loss": 0.513,
+      "step": 440
+    },
+    {
+      "epoch": 0.09085173501577287,
+      "grad_norm": 0.5140723294282747,
+      "learning_rate": 9.05241935483871e-06,
+      "loss": 0.5161,
+      "step": 450
+    },
+    {
+      "epoch": 0.09287066246056783,
+      "grad_norm": 0.4719590441343577,
+      "learning_rate": 9.254032258064517e-06,
+      "loss": 0.5033,
+      "step": 460
+    },
+    {
+      "epoch": 0.09488958990536278,
+      "grad_norm": 0.5031363320062582,
+      "learning_rate": 9.455645161290323e-06,
+      "loss": 0.5145,
+      "step": 470
+    },
+    {
+      "epoch": 0.09690851735015772,
+      "grad_norm": 0.5027908604602157,
+      "learning_rate": 9.65725806451613e-06,
+      "loss": 0.5178,
+      "step": 480
+    },
+    {
+      "epoch": 0.09892744479495268,
+      "grad_norm": 0.5046628095943158,
+      "learning_rate": 9.858870967741936e-06,
+      "loss": 0.5069,
+      "step": 490
+    },
+    {
+      "epoch": 0.10094637223974763,
+      "grad_norm": 0.5522780839548007,
+      "learning_rate": 9.99998882617222e-06,
+      "loss": 0.5169,
+      "step": 500
+    },
+    {
+      "epoch": 0.10296529968454259,
+      "grad_norm": 0.48260445699138166,
+      "learning_rate": 9.999790181734308e-06,
+      "loss": 0.5067,
+      "step": 510
+    },
+    {
+      "epoch": 0.10498422712933754,
+      "grad_norm": 0.4875096921972213,
+      "learning_rate": 9.999343241367322e-06,
+      "loss": 0.5152,
+      "step": 520
+    },
+    {
+      "epoch": 0.1070031545741325,
+      "grad_norm": 0.5080882476390746,
+      "learning_rate": 9.998648027266884e-06,
+      "loss": 0.5131,
+      "step": 530
+    },
+    {
+      "epoch": 0.10902208201892745,
+      "grad_norm": 0.5107719615388011,
+      "learning_rate": 9.997704573958209e-06,
+      "loss": 0.5053,
+      "step": 540
+    },
+    {
+      "epoch": 0.1110410094637224,
+      "grad_norm": 0.5361602322829081,
+      "learning_rate": 9.996512928294389e-06,
+      "loss": 0.5083,
+      "step": 550
+    },
+    {
+      "epoch": 0.11305993690851734,
+      "grad_norm": 0.4851941991561818,
+      "learning_rate": 9.995073149454057e-06,
+      "loss": 0.4997,
+      "step": 560
+    },
+    {
+      "epoch": 0.1150788643533123,
+      "grad_norm": 0.49258962377904003,
+      "learning_rate": 9.99338530893846e-06,
+      "loss": 0.516,
+      "step": 570
+    },
+    {
+      "epoch": 0.11709779179810725,
+      "grad_norm": 0.4835880405802275,
+      "learning_rate": 9.991449490567901e-06,
+      "loss": 0.5073,
+      "step": 580
+    },
+    {
+      "epoch": 0.11911671924290221,
+      "grad_norm": 0.507245673357914,
+      "learning_rate": 9.989265790477581e-06,
+      "loss": 0.5014,
+      "step": 590
+    },
+    {
+      "epoch": 0.12113564668769716,
+      "grad_norm": 0.5146575464998254,
+      "learning_rate": 9.986834317112817e-06,
+      "loss": 0.5177,
+      "step": 600
+    },
+    {
+      "epoch": 0.12315457413249212,
+      "grad_norm": 0.4662328996304102,
+      "learning_rate": 9.984155191223663e-06,
+      "loss": 0.5054,
+      "step": 610
+    },
+    {
+      "epoch": 0.12517350157728707,
+      "grad_norm": 0.4571893765964666,
+      "learning_rate": 9.981228545858913e-06,
+      "loss": 0.5086,
+      "step": 620
+    },
+    {
+      "epoch": 0.12719242902208203,
+      "grad_norm": 0.4697827268486345,
+      "learning_rate": 9.978054526359493e-06,
+      "loss": 0.5029,
+      "step": 630
+    },
+    {
+      "epoch": 0.12921135646687698,
+      "grad_norm": 0.5031062337107917,
+      "learning_rate": 9.97463329035124e-06,
+      "loss": 0.5021,
+      "step": 640
+    },
+    {
+      "epoch": 0.13123028391167194,
+      "grad_norm": 0.571029993720401,
+      "learning_rate": 9.970965007737081e-06,
+      "loss": 0.5077,
+      "step": 650
+    },
+    {
+      "epoch": 0.1332492113564669,
+      "grad_norm": 0.45753840087765046,
+      "learning_rate": 9.967049860688587e-06,
+      "loss": 0.4961,
+      "step": 660
+    },
+    {
+      "epoch": 0.13526813880126182,
+      "grad_norm": 0.5189371422618692,
+      "learning_rate": 9.962888043636931e-06,
+      "loss": 0.5036,
+      "step": 670
+    },
+    {
+      "epoch": 0.13728706624605677,
+      "grad_norm": 0.47066047930695143,
+      "learning_rate": 9.958479763263234e-06,
+      "loss": 0.4972,
+      "step": 680
+    },
+    {
+      "epoch": 0.13930599369085173,
+      "grad_norm": 0.49380951082560154,
+      "learning_rate": 9.953825238488296e-06,
+      "loss": 0.4955,
+      "step": 690
+    },
+    {
+      "epoch": 0.14132492113564668,
+      "grad_norm": 0.49487805704511495,
+      "learning_rate": 9.948924700461727e-06,
+      "loss": 0.5013,
+      "step": 700
+    },
+    {
+      "epoch": 0.14334384858044164,
+      "grad_norm": 0.4768179474157311,
+      "learning_rate": 9.94377839255047e-06,
+      "loss": 0.4945,
+      "step": 710
+    },
+    {
+      "epoch": 0.1453627760252366,
+      "grad_norm": 0.5086022999656893,
+      "learning_rate": 9.938386570326707e-06,
+      "loss": 0.5033,
+      "step": 720
+    },
+    {
+      "epoch": 0.14738170347003154,
+      "grad_norm": 0.4947936431118982,
+      "learning_rate": 9.93274950155518e-06,
+      "loss": 0.5013,
+      "step": 730
+    },
+    {
+      "epoch": 0.1494006309148265,
+      "grad_norm": 0.49370518434763616,
+      "learning_rate": 9.926867466179883e-06,
+      "loss": 0.4923,
+      "step": 740
+    },
+    {
+      "epoch": 0.15141955835962145,
+      "grad_norm": 0.49665569470371385,
+      "learning_rate": 9.920740756310156e-06,
+      "loss": 0.5038,
+      "step": 750
+    },
+    {
+      "epoch": 0.1534384858044164,
+      "grad_norm": 0.46813454785234254,
+      "learning_rate": 9.914369676206195e-06,
+      "loss": 0.4875,
+      "step": 760
+    },
+    {
+      "epoch": 0.15545741324921136,
+      "grad_norm": 0.49814972796278695,
+      "learning_rate": 9.907754542263926e-06,
+      "loss": 0.4939,
+      "step": 770
+    },
+    {
+      "epoch": 0.15747634069400632,
+      "grad_norm": 0.5218798292518447,
+      "learning_rate": 9.900895682999301e-06,
+      "loss": 0.501,
+      "step": 780
+    },
+    {
+      "epoch": 0.15949526813880127,
+      "grad_norm": 0.5913103279447773,
+      "learning_rate": 9.893793439031982e-06,
+      "loss": 0.4927,
+      "step": 790
+    },
+    {
+      "epoch": 0.16151419558359623,
+      "grad_norm": 0.5125446596453367,
+      "learning_rate": 9.88644816306842e-06,
+      "loss": 0.4971,
+      "step": 800
+    },
+    {
+      "epoch": 0.16353312302839118,
+      "grad_norm": 0.4483762668624327,
+      "learning_rate": 9.878860219884347e-06,
+      "loss": 0.4981,
+      "step": 810
+    },
+    {
+      "epoch": 0.1655520504731861,
+      "grad_norm": 0.4787860866647759,
+      "learning_rate": 9.871029986306658e-06,
+      "loss": 0.4964,
+      "step": 820
+    },
+    {
+      "epoch": 0.16757097791798106,
+      "grad_norm": 0.5030394247546482,
+      "learning_rate": 9.862957851194694e-06,
+      "loss": 0.4891,
+      "step": 830
+    },
+    {
+      "epoch": 0.16958990536277602,
+      "grad_norm": 0.5239985323894606,
+      "learning_rate": 9.854644215420933e-06,
+      "loss": 0.501,
+      "step": 840
+    },
+    {
+      "epoch": 0.17160883280757097,
+      "grad_norm": 0.4934736601735223,
+      "learning_rate": 9.846089491851089e-06,
+      "loss": 0.5012,
+      "step": 850
+    },
+    {
+      "epoch": 0.17362776025236593,
+      "grad_norm": 0.5649851363661309,
+      "learning_rate": 9.837294105323592e-06,
+      "loss": 0.501,
+      "step": 860
+    },
+    {
+      "epoch": 0.17564668769716088,
+      "grad_norm": 0.5032183289408247,
+      "learning_rate": 9.828258492628506e-06,
+      "loss": 0.5019,
+      "step": 870
+    },
+    {
+      "epoch": 0.17766561514195583,
+      "grad_norm": 0.5408394773542722,
+      "learning_rate": 9.818983102485832e-06,
+      "loss": 0.4914,
+      "step": 880
+    },
+    {
+      "epoch": 0.1796845425867508,
+      "grad_norm": 0.47080262308715565,
+      "learning_rate": 9.809468395523225e-06,
+      "loss": 0.4874,
+      "step": 890
+    },
+    {
+      "epoch": 0.18170347003154574,
+      "grad_norm": 0.5707749159791521,
+      "learning_rate": 9.799714844253109e-06,
+      "loss": 0.4995,
+      "step": 900
+    },
+    {
+      "epoch": 0.1837223974763407,
+      "grad_norm": 0.48122327046673424,
+      "learning_rate": 9.789722933049227e-06,
+      "loss": 0.4892,
+      "step": 910
+    },
+    {
+      "epoch": 0.18574132492113565,
+      "grad_norm": 0.45082444705324104,
+      "learning_rate": 9.779493158122578e-06,
+      "loss": 0.4909,
+      "step": 920
+    },
+    {
+      "epoch": 0.1877602523659306,
+      "grad_norm": 0.5068314998947344,
+      "learning_rate": 9.769026027496773e-06,
+      "loss": 0.4881,
+      "step": 930
+    },
+    {
+      "epoch": 0.18977917981072556,
+      "grad_norm": 0.44089908003969003,
+      "learning_rate": 9.758322060982813e-06,
+      "loss": 0.4923,
+      "step": 940
+    },
+    {
+      "epoch": 0.19179810725552052,
+      "grad_norm": 0.4786006068183123,
+      "learning_rate": 9.747381790153262e-06,
+      "loss": 0.4912,
+      "step": 950
+    },
+    {
+      "epoch": 0.19381703470031544,
+      "grad_norm": 0.4531421936277408,
+      "learning_rate": 9.736205758315864e-06,
+      "loss": 0.4744,
+      "step": 960
+    },
+    {
+      "epoch": 0.1958359621451104,
+      "grad_norm": 0.4492650045467347,
+      "learning_rate": 9.724794520486551e-06,
+      "loss": 0.485,
+      "step": 970
+    },
+    {
+      "epoch": 0.19785488958990535,
+      "grad_norm": 0.4616235423638888,
+      "learning_rate": 9.713148643361884e-06,
+      "loss": 0.488,
+      "step": 980
+    },
+    {
+      "epoch": 0.1998738170347003,
+      "grad_norm": 0.5078516721505932,
+      "learning_rate": 9.701268705290907e-06,
+      "loss": 0.4886,
+      "step": 990
+    },
+    {
+      "epoch": 0.20189274447949526,
+      "grad_norm": 0.5292871585531458,
+      "learning_rate": 9.689155296246431e-06,
+      "loss": 0.4897,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20391167192429022,
+      "grad_norm": 0.4614297555636878,
+      "learning_rate": 9.67680901779573e-06,
+      "loss": 0.4809,
+      "step": 1010
+    },
+    {
+      "epoch": 0.20593059936908517,
+      "grad_norm": 0.4853770956696164,
+      "learning_rate": 9.664230483070669e-06,
+      "loss": 0.4848,
+      "step": 1020
+    },
+    {
+      "epoch": 0.20794952681388013,
+      "grad_norm": 0.45954875393494693,
+      "learning_rate": 9.651420316737254e-06,
+      "loss": 0.4817,
+      "step": 1030
+    },
+    {
+      "epoch": 0.20996845425867508,
+      "grad_norm": 0.4539790244117171,
+      "learning_rate": 9.638379154964615e-06,
+      "loss": 0.4927,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21198738170347003,
+      "grad_norm": 0.4999117191134038,
+      "learning_rate": 9.625107645393398e-06,
+      "loss": 0.4906,
+      "step": 1050
+    },
+    {
+      "epoch": 0.214006309148265,
+      "grad_norm": 0.5315614747354604,
+      "learning_rate": 9.611606447103625e-06,
+      "loss": 0.4701,
+      "step": 1060
+    },
+    {
+      "epoch": 0.21602523659305994,
+      "grad_norm": 0.4465543761029164,
+      "learning_rate": 9.597876230581946e-06,
+      "loss": 0.4844,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2180441640378549,
+      "grad_norm": 0.5240713468337838,
+      "learning_rate": 9.583917677688348e-06,
+      "loss": 0.4802,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22006309148264985,
+      "grad_norm": 0.4797396408083518,
+      "learning_rate": 9.56973148162229e-06,
+      "loss": 0.4822,
+      "step": 1090
+    },
+    {
+      "epoch": 0.2220820189274448,
+      "grad_norm": 0.5124904557581254,
+      "learning_rate": 9.555318346888287e-06,
+      "loss": 0.4887,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22410094637223973,
+      "grad_norm": 0.448720333545146,
+      "learning_rate": 9.540678989260907e-06,
+      "loss": 0.4804,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2261198738170347,
+      "grad_norm": 0.4479157257263002,
+      "learning_rate": 9.525814135749238e-06,
+      "loss": 0.4776,
+      "step": 1120
+    },
+    {
+      "epoch": 0.22813880126182964,
+      "grad_norm": 0.4630993156519356,
+      "learning_rate": 9.510724524560783e-06,
+      "loss": 0.4753,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2301577287066246,
+      "grad_norm": 0.46574160333254905,
+      "learning_rate": 9.495410905064795e-06,
+      "loss": 0.4802,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23217665615141955,
+      "grad_norm": 0.532351729710861,
+      "learning_rate": 9.479874037755061e-06,
+      "loss": 0.4826,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2341955835962145,
+      "grad_norm": 0.4629220502691385,
+      "learning_rate": 9.46411469421214e-06,
+      "loss": 0.4802,
+      "step": 1160
+    },
+    {
+      "epoch": 0.23621451104100946,
+      "grad_norm": 0.459458980682449,
+      "learning_rate": 9.448133657065045e-06,
+      "loss": 0.4863,
+      "step": 1170
+    },
+    {
+      "epoch": 0.23823343848580442,
+      "grad_norm": 0.4652002127480942,
+      "learning_rate": 9.431931719952372e-06,
+      "loss": 0.4785,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24025236593059937,
+      "grad_norm": 0.466540922054408,
+      "learning_rate": 9.415509687482892e-06,
+      "loss": 0.4719,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24227129337539433,
+      "grad_norm": 0.49341259273484933,
+      "learning_rate": 9.398868375195587e-06,
+      "loss": 0.4926,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24429022082018928,
+      "grad_norm": 0.4728385366149605,
+      "learning_rate": 9.382008609519159e-06,
+      "loss": 0.4741,
+      "step": 1210
+    },
+    {
+      "epoch": 0.24630914826498423,
+      "grad_norm": 0.5027959432042377,
+      "learning_rate": 9.364931227730978e-06,
+      "loss": 0.4826,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2483280757097792,
+      "grad_norm": 0.4883346568815589,
+      "learning_rate": 9.34763707791551e-06,
+      "loss": 0.4837,
+      "step": 1230
+    },
+    {
+      "epoch": 0.25034700315457414,
+      "grad_norm": 0.4689919758806841,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4834,
+      "step": 1240
+    },
+    {
+      "epoch": 0.25236593059936907,
+      "grad_norm": 0.5054719137784303,
+      "learning_rate": 9.312401920322793e-06,
+      "loss": 0.4858,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25438485804416405,
+      "grad_norm": 0.4829012063372003,
+      "learning_rate": 9.294462662368211e-06,
+      "loss": 0.4757,
+      "step": 1260
+    },
+    {
+      "epoch": 0.256403785488959,
+      "grad_norm": 0.4627206332424085,
+      "learning_rate": 9.276310135944777e-06,
+      "loss": 0.4783,
+      "step": 1270
+    },
+    {
+      "epoch": 0.25842271293375396,
+      "grad_norm": 0.4497460790448332,
+      "learning_rate": 9.257945242530002e-06,
+      "loss": 0.4785,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2604416403785489,
+      "grad_norm": 0.44985051561838785,
+      "learning_rate": 9.239368894147812e-06,
+      "loss": 0.4786,
+      "step": 1290
+    },
+    {
+      "epoch": 0.26246056782334387,
+      "grad_norm": 0.48240095905903635,
+      "learning_rate": 9.220582013323258e-06,
+      "loss": 0.4807,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2644794952681388,
+      "grad_norm": 0.48132105969556493,
+      "learning_rate": 9.201585533036696e-06,
+      "loss": 0.4706,
+      "step": 1310
+    },
+    {
+      "epoch": 0.2664984227129338,
+      "grad_norm": 0.46675857398369297,
+      "learning_rate": 9.18238039667746e-06,
+      "loss": 0.4879,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2685173501577287,
+      "grad_norm": 0.4665634722250575,
+      "learning_rate": 9.162967557997003e-06,
+      "loss": 0.4799,
+      "step": 1330
+    },
+    {
+      "epoch": 0.27053627760252363,
+      "grad_norm": 0.4432315628923224,
+      "learning_rate": 9.14334798106155e-06,
+      "loss": 0.4757,
+      "step": 1340
+    },
+    {
+      "epoch": 0.2725552050473186,
+      "grad_norm": 0.5000831797296084,
+      "learning_rate": 9.123522640204198e-06,
+      "loss": 0.4805,
+      "step": 1350
+    },
+    {
+      "epoch": 0.27457413249211354,
+      "grad_norm": 0.4441933490286196,
+      "learning_rate": 9.103492519976555e-06,
+      "loss": 0.4769,
+      "step": 1360
+    },
+    {
+      "epoch": 0.2765930599369085,
+      "grad_norm": 0.4805005293661477,
+      "learning_rate": 9.083258615099819e-06,
+      "loss": 0.4777,
+      "step": 1370
+    },
+    {
+      "epoch": 0.27861198738170345,
+      "grad_norm": 0.4445460559749252,
+      "learning_rate": 9.062821930415404e-06,
+      "loss": 0.4728,
+      "step": 1380
+    },
+    {
+      "epoch": 0.28063091482649843,
+      "grad_norm": 0.4333540273890526,
+      "learning_rate": 9.042183480835018e-06,
+      "loss": 0.4705,
+      "step": 1390
+    },
+    {
+      "epoch": 0.28264984227129336,
+      "grad_norm": 0.48259999792627817,
+      "learning_rate": 9.021344291290275e-06,
+      "loss": 0.4782,
+      "step": 1400
+    },
+    {
+      "epoch": 0.28466876971608834,
+      "grad_norm": 0.439829603884435,
+      "learning_rate": 9.000305396681788e-06,
+      "loss": 0.4705,
+      "step": 1410
+    },
+    {
+      "epoch": 0.28668769716088327,
+      "grad_norm": 0.4776753948778827,
+      "learning_rate": 8.97906784182778e-06,
+      "loss": 0.4694,
+      "step": 1420
+    },
+    {
+      "epoch": 0.28870662460567825,
+      "grad_norm": 0.49821375314109334,
+      "learning_rate": 8.95763268141219e-06,
+      "loss": 0.4698,
+      "step": 1430
+    },
+    {
+      "epoch": 0.2907255520504732,
+      "grad_norm": 0.4626475218122892,
+      "learning_rate": 8.936000979932304e-06,
+      "loss": 0.4766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.29274447949526816,
+      "grad_norm": 0.4797061046529278,
+      "learning_rate": 8.914173811645884e-06,
+      "loss": 0.4773,
+      "step": 1450
+    },
+    {
+      "epoch": 0.2947634069400631,
+      "grad_norm": 0.5067089149884695,
+      "learning_rate": 8.892152260517824e-06,
+      "loss": 0.4652,
+      "step": 1460
+    },
+    {
+      "epoch": 0.29678233438485807,
+      "grad_norm": 0.5216910139465747,
+      "learning_rate": 8.869937420166312e-06,
+      "loss": 0.475,
+      "step": 1470
+    },
+    {
+      "epoch": 0.298801261829653,
+      "grad_norm": 0.4655884354714463,
+      "learning_rate": 8.847530393808534e-06,
+      "loss": 0.4811,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3008201892744479,
+      "grad_norm": 0.47533704121654896,
+      "learning_rate": 8.824932294205868e-06,
+      "loss": 0.4723,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3028391167192429,
+      "grad_norm": 0.479585079565894,
+      "learning_rate": 8.802144243608633e-06,
+      "loss": 0.4728,
+      "step": 1500
+    },
+    {
+      "epoch": 0.30485804416403783,
+      "grad_norm": 0.4338897481002412,
+      "learning_rate": 8.779167373700359e-06,
+      "loss": 0.4687,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3068769716088328,
+      "grad_norm": 0.51284609503485,
+      "learning_rate": 8.756002825541583e-06,
+      "loss": 0.4795,
+      "step": 1520
+    },
+    {
+      "epoch": 0.30889589905362774,
+      "grad_norm": 0.5019515223957067,
+      "learning_rate": 8.73265174951318e-06,
+      "loss": 0.4782,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3109148264984227,
+      "grad_norm": 0.5764514697725889,
+      "learning_rate": 8.709115305259233e-06,
+      "loss": 0.4722,
+      "step": 1540
+    },
+    {
+      "epoch": 0.31293375394321765,
+      "grad_norm": 0.48602580093856246,
+      "learning_rate": 8.685394661629453e-06,
+      "loss": 0.4764,
+      "step": 1550
+    },
+    {
+      "epoch": 0.31495268138801263,
+      "grad_norm": 0.43106495742778833,
+      "learning_rate": 8.661490996621125e-06,
+      "loss": 0.4749,
+      "step": 1560
+    },
+    {
+      "epoch": 0.31697160883280756,
+      "grad_norm": 0.4879400234119546,
+      "learning_rate": 8.637405497320599e-06,
+      "loss": 0.4685,
+      "step": 1570
+    },
+    {
+      "epoch": 0.31899053627760254,
+      "grad_norm": 0.48144632266967335,
+      "learning_rate": 8.61313935984436e-06,
+      "loss": 0.473,
+      "step": 1580
+    },
+    {
+      "epoch": 0.32100946372239747,
+      "grad_norm": 0.4824945838927638,
+      "learning_rate": 8.588693789279605e-06,
+      "loss": 0.467,
+      "step": 1590
+    },
+    {
+      "epoch": 0.32302839116719245,
+      "grad_norm": 0.48854234491790616,
+      "learning_rate": 8.56406999962441e-06,
+      "loss": 0.4715,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3250473186119874,
+      "grad_norm": 0.43356661154496373,
+      "learning_rate": 8.539269213727434e-06,
+      "loss": 0.4643,
+      "step": 1610
+    },
+    {
+      "epoch": 0.32706624605678236,
+      "grad_norm": 0.45038524364573934,
+      "learning_rate": 8.514292663227196e-06,
+      "loss": 0.4753,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3290851735015773,
+      "grad_norm": 0.5390076730569227,
+      "learning_rate": 8.489141588490914e-06,
+      "loss": 0.4692,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3311041009463722,
+      "grad_norm": 0.5166665541948204,
+      "learning_rate": 8.46381723855289e-06,
+      "loss": 0.4626,
+      "step": 1640
+    },
+    {
+      "epoch": 0.3331230283911672,
+      "grad_norm": 0.4973742178832253,
+      "learning_rate": 8.438320871052501e-06,
+      "loss": 0.4722,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3351419558359621,
+      "grad_norm": 0.4625137579015689,
+      "learning_rate": 8.412653752171732e-06,
+      "loss": 0.4591,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3371608832807571,
+      "grad_norm": 0.48424933592035946,
+      "learning_rate": 8.386817156572298e-06,
+      "loss": 0.48,
+      "step": 1670
+    },
+    {
+      "epoch": 0.33917981072555203,
+      "grad_norm": 0.4532582849486311,
+      "learning_rate": 8.360812367332342e-06,
+      "loss": 0.469,
+      "step": 1680
+    },
+    {
+      "epoch": 0.341198738170347,
+      "grad_norm": 0.4456128521040015,
+      "learning_rate": 8.33464067588272e-06,
+      "loss": 0.4701,
+      "step": 1690
+    },
+    {
+      "epoch": 0.34321766561514194,
+      "grad_norm": 0.47975070454468693,
+      "learning_rate": 8.30830338194286e-06,
+      "loss": 0.4742,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3452365930599369,
+      "grad_norm": 0.44758135515111036,
+      "learning_rate": 8.281801793456223e-06,
+      "loss": 0.4563,
+      "step": 1710
+    },
+    {
+      "epoch": 0.34725552050473185,
+      "grad_norm": 0.539530429343652,
+      "learning_rate": 8.255137226525346e-06,
+      "loss": 0.4678,
+      "step": 1720
+    },
+    {
+      "epoch": 0.34927444794952683,
+      "grad_norm": 0.44634229380095736,
+      "learning_rate": 8.22831100534648e-06,
+      "loss": 0.4688,
+      "step": 1730
+    },
+    {
+      "epoch": 0.35129337539432176,
+      "grad_norm": 0.41960408937669463,
+      "learning_rate": 8.201324462143827e-06,
+      "loss": 0.4542,
+      "step": 1740
+    },
+    {
+      "epoch": 0.35331230283911674,
+      "grad_norm": 0.4791531544406239,
+      "learning_rate": 8.174178937103397e-06,
+      "loss": 0.4743,
+      "step": 1750
+    },
+    {
+      "epoch": 0.35533123028391167,
+      "grad_norm": 0.4352818312435405,
+      "learning_rate": 8.14687577830643e-06,
+      "loss": 0.4604,
+      "step": 1760
+    },
+    {
+      "epoch": 0.35735015772870665,
+      "grad_norm": 0.4672874879206997,
+      "learning_rate": 8.11941634166246e-06,
+      "loss": 0.4712,
+      "step": 1770
+    },
+    {
+      "epoch": 0.3593690851735016,
+      "grad_norm": 0.4637056308756207,
+      "learning_rate": 8.09180199084198e-06,
+      "loss": 0.4668,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3613880126182965,
+      "grad_norm": 0.44264459219210456,
+      "learning_rate": 8.064034097208712e-06,
+      "loss": 0.4596,
+      "step": 1790
+    },
+    {
+      "epoch": 0.3634069400630915,
+      "grad_norm": 0.49462230789807315,
+      "learning_rate": 8.036114039751516e-06,
+      "loss": 0.4667,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3654258675078864,
+      "grad_norm": 0.4634309345247295,
+      "learning_rate": 8.0080432050159e-06,
+      "loss": 0.4604,
+      "step": 1810
+    },
+    {
+      "epoch": 0.3674447949526814,
+      "grad_norm": 0.4999816402185204,
+      "learning_rate": 7.979822987035157e-06,
+      "loss": 0.4644,
+      "step": 1820
+    },
+    {
+      "epoch": 0.3694637223974763,
+      "grad_norm": 0.47642327436037435,
+      "learning_rate": 7.951454787261148e-06,
+      "loss": 0.4677,
+      "step": 1830
+    },
+    {
+      "epoch": 0.3714826498422713,
+      "grad_norm": 0.4953986824691425,
+      "learning_rate": 7.922940014494693e-06,
+      "loss": 0.4593,
+      "step": 1840
+    },
+    {
+      "epoch": 0.37350157728706623,
+      "grad_norm": 0.4817430868786167,
+      "learning_rate": 7.894280084815618e-06,
+      "loss": 0.4689,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3755205047318612,
+      "grad_norm": 0.4356746961237441,
+      "learning_rate": 7.86547642151242e-06,
+      "loss": 0.4611,
+      "step": 1860
+    },
+    {
+      "epoch": 0.37753943217665614,
+      "grad_norm": 0.4905696785040258,
+      "learning_rate": 7.836530455011594e-06,
+      "loss": 0.4647,
+      "step": 1870
+    },
+    {
+      "epoch": 0.3795583596214511,
+      "grad_norm": 0.4730705035791906,
+      "learning_rate": 7.807443622806592e-06,
+      "loss": 0.4643,
+      "step": 1880
+    },
+    {
+      "epoch": 0.38157728706624605,
+      "grad_norm": 0.4626721574097504,
+      "learning_rate": 7.778217369386434e-06,
+      "loss": 0.4621,
+      "step": 1890
+    },
+    {
+      "epoch": 0.38359621451104103,
+      "grad_norm": 0.5095748907639542,
+      "learning_rate": 7.748853146163978e-06,
+      "loss": 0.4702,
+      "step": 1900
+    },
+    {
+      "epoch": 0.38561514195583596,
+      "grad_norm": 0.45666908318697785,
+      "learning_rate": 7.719352411403836e-06,
+      "loss": 0.4584,
+      "step": 1910
+    },
+    {
+      "epoch": 0.3876340694006309,
+      "grad_norm": 0.5831960484166556,
+      "learning_rate": 7.68971663014995e-06,
+      "loss": 0.4581,
+      "step": 1920
+    },
+    {
+      "epoch": 0.38965299684542587,
+      "grad_norm": 0.43083136772614855,
+      "learning_rate": 7.659947274152857e-06,
+      "loss": 0.4595,
+      "step": 1930
+    },
+    {
+      "epoch": 0.3916719242902208,
+      "grad_norm": 0.44527597409724967,
+      "learning_rate": 7.630045821796567e-06,
+      "loss": 0.4603,
+      "step": 1940
+    },
+    {
+      "epoch": 0.3936908517350158,
+      "grad_norm": 0.5085813030698595,
+      "learning_rate": 7.60001375802518e-06,
+      "loss": 0.4726,
+      "step": 1950
+    },
+    {
+      "epoch": 0.3957097791798107,
+      "grad_norm": 0.5516780680340057,
+      "learning_rate": 7.5698525742691145e-06,
+      "loss": 0.4553,
+      "step": 1960
+    },
+    {
+      "epoch": 0.3977287066246057,
+      "grad_norm": 0.4473799858576117,
+      "learning_rate": 7.5395637683710534e-06,
+      "loss": 0.4652,
+      "step": 1970
+    },
+    {
+      "epoch": 0.3997476340694006,
+      "grad_norm": 0.4594068744960154,
+      "learning_rate": 7.509148844511556e-06,
+      "loss": 0.4569,
+      "step": 1980
+    },
+    {
+      "epoch": 0.4017665615141956,
+      "grad_norm": 0.4195303708920141,
+      "learning_rate": 7.478609313134367e-06,
+      "loss": 0.4608,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4037854889589905,
+      "grad_norm": 0.5224611450690858,
+      "learning_rate": 7.447946690871387e-06,
+      "loss": 0.4618,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4058044164037855,
+      "grad_norm": 0.5037868351130359,
+      "learning_rate": 7.4171625004673765e-06,
+      "loss": 0.4549,
+      "step": 2010
+    },
+    {
+      "epoch": 0.40782334384858043,
+      "grad_norm": 0.6617292048565804,
+      "learning_rate": 7.386258270704318e-06,
+      "loss": 0.4648,
+      "step": 2020
+    },
+    {
+      "epoch": 0.4098422712933754,
+      "grad_norm": 0.46778481767707863,
+      "learning_rate": 7.355235536325507e-06,
+      "loss": 0.4618,
+      "step": 2030
+    },
+    {
+      "epoch": 0.41186119873817034,
+      "grad_norm": 0.4467025867029599,
+      "learning_rate": 7.32409583795932e-06,
+      "loss": 0.4556,
+      "step": 2040
+    },
+    {
+      "epoch": 0.4138801261829653,
+      "grad_norm": 0.4864826536631601,
+      "learning_rate": 7.292840722042721e-06,
+      "loss": 0.4649,
+      "step": 2050
+    },
+    {
+      "epoch": 0.41589905362776025,
+      "grad_norm": 0.44674303304698915,
+      "learning_rate": 7.261471740744453e-06,
+      "loss": 0.4546,
+      "step": 2060
+    },
+    {
+      "epoch": 0.4179179810725552,
+      "grad_norm": 0.4638264920705765,
+      "learning_rate": 7.229990451887961e-06,
+      "loss": 0.459,
+      "step": 2070
+    },
+    {
+      "epoch": 0.41993690851735016,
+      "grad_norm": 0.44062835097290626,
+      "learning_rate": 7.1983984188740215e-06,
+      "loss": 0.4627,
+      "step": 2080
+    },
+    {
+      "epoch": 0.4219558359621451,
+      "grad_norm": 0.4596889143174662,
+      "learning_rate": 7.1666972106031105e-06,
+      "loss": 0.4584,
+      "step": 2090
+    },
+    {
+      "epoch": 0.42397476340694007,
+      "grad_norm": 0.4866244769293159,
+      "learning_rate": 7.134888401397484e-06,
+      "loss": 0.4629,
+      "step": 2100
+    },
+    {
+      "epoch": 0.425993690851735,
+      "grad_norm": 0.5201676761862537,
+      "learning_rate": 7.102973570922997e-06,
+      "loss": 0.4549,
+      "step": 2110
+    },
+    {
+      "epoch": 0.42801261829653,
+      "grad_norm": 0.4790871394995968,
+      "learning_rate": 7.070954304110656e-06,
+      "loss": 0.4632,
+      "step": 2120
+    },
+    {
+      "epoch": 0.4300315457413249,
+      "grad_norm": 0.4659786396553266,
+      "learning_rate": 7.03883219107791e-06,
+      "loss": 0.4581,
+      "step": 2130
+    },
+    {
+      "epoch": 0.4320504731861199,
+      "grad_norm": 0.4104121258537053,
+      "learning_rate": 7.0066088270496775e-06,
+      "loss": 0.4596,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4340694006309148,
+      "grad_norm": 0.46988504036618683,
+      "learning_rate": 6.9742858122791355e-06,
+      "loss": 0.4648,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4360883280757098,
+      "grad_norm": 0.6098242782979109,
+      "learning_rate": 6.941864751968239e-06,
+      "loss": 0.4548,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4381072555205047,
+      "grad_norm": 0.7557069029520974,
+      "learning_rate": 6.90934725618801e-06,
+      "loss": 0.461,
+      "step": 2170
+    },
+    {
+      "epoch": 0.4401261829652997,
+      "grad_norm": 0.46196984209426056,
+      "learning_rate": 6.876734939798584e-06,
+      "loss": 0.4631,
+      "step": 2180
+    },
+    {
+      "epoch": 0.44214511041009463,
+      "grad_norm": 0.45367052105694244,
+      "learning_rate": 6.844029422368998e-06,
+      "loss": 0.4567,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4441640378548896,
+      "grad_norm": 0.4923825492028847,
+      "learning_rate": 6.811232328096778e-06,
+      "loss": 0.4619,
+      "step": 2200
+    },
+    {
+      "epoch": 0.44618296529968454,
+      "grad_norm": 0.4412882669817311,
+      "learning_rate": 6.7783452857272725e-06,
+      "loss": 0.4472,
+      "step": 2210
+    },
+    {
+      "epoch": 0.44820189274447947,
+      "grad_norm": 0.4804805684578094,
+      "learning_rate": 6.745369928472764e-06,
+      "loss": 0.4634,
+      "step": 2220
+    },
+    {
+      "epoch": 0.45022082018927445,
+      "grad_norm": 0.46765384977250785,
+      "learning_rate": 6.712307893931364e-06,
+      "loss": 0.4595,
+      "step": 2230
+    },
+    {
+      "epoch": 0.4522397476340694,
+      "grad_norm": 1.0068029764875739,
+      "learning_rate": 6.67916082400569e-06,
+      "loss": 0.457,
+      "step": 2240
+    },
+    {
+      "epoch": 0.45425867507886436,
+      "grad_norm": 0.4828558935559972,
+      "learning_rate": 6.645930364821327e-06,
+      "loss": 0.465,
+      "step": 2250
+    },
+    {
+      "epoch": 0.4562776025236593,
+      "grad_norm": 0.4571716607551568,
+      "learning_rate": 6.612618166645068e-06,
+      "loss": 0.4521,
+      "step": 2260
+    },
+    {
+      "epoch": 0.45829652996845427,
+      "grad_norm": 0.49891810921169605,
+      "learning_rate": 6.579225883802981e-06,
+      "loss": 0.4621,
+      "step": 2270
+    },
+    {
+      "epoch": 0.4603154574132492,
+      "grad_norm": 0.6812817990255348,
+      "learning_rate": 6.5457551745982275e-06,
+      "loss": 0.4553,
+      "step": 2280
+    },
+    {
+      "epoch": 0.4623343848580442,
+      "grad_norm": 0.466296009966539,
+      "learning_rate": 6.512207701228727e-06,
+      "loss": 0.4585,
+      "step": 2290
+    },
+    {
+      "epoch": 0.4643533123028391,
+      "grad_norm": 0.48144166164862184,
+      "learning_rate": 6.478585129704608e-06,
+      "loss": 0.4579,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4663722397476341,
+      "grad_norm": 0.4575454070862058,
+      "learning_rate": 6.444889129765465e-06,
+      "loss": 0.453,
+      "step": 2310
+    },
+    {
+      "epoch": 0.468391167192429,
+      "grad_norm": 0.5049212463992705,
+      "learning_rate": 6.4111213747974385e-06,
+      "loss": 0.4606,
+      "step": 2320
+    },
+    {
+      "epoch": 0.470410094637224,
+      "grad_norm": 0.44196403700173553,
+      "learning_rate": 6.377283541750123e-06,
+      "loss": 0.4528,
+      "step": 2330
+    },
+    {
+      "epoch": 0.4724290220820189,
+      "grad_norm": 0.44557725863878417,
+      "learning_rate": 6.343377311053271e-06,
+      "loss": 0.4614,
+      "step": 2340
+    },
+    {
+      "epoch": 0.4744479495268139,
+      "grad_norm": 0.485138333868983,
+      "learning_rate": 6.309404366533355e-06,
+      "loss": 0.4662,
+      "step": 2350
+    },
+    {
+      "epoch": 0.47646687697160883,
+      "grad_norm": 0.44703181568848005,
+      "learning_rate": 6.275366395329934e-06,
+      "loss": 0.4484,
+      "step": 2360
+    },
+    {
+      "epoch": 0.47848580441640376,
+      "grad_norm": 0.46684239360571517,
+      "learning_rate": 6.241265087811883e-06,
+      "loss": 0.461,
+      "step": 2370
+    },
+    {
+      "epoch": 0.48050473186119874,
+      "grad_norm": 0.4308686375763305,
+      "learning_rate": 6.207102137493433e-06,
+      "loss": 0.4572,
+      "step": 2380
+    },
+    {
+      "epoch": 0.48252365930599367,
+      "grad_norm": 0.4349332573681559,
+      "learning_rate": 6.172879240950075e-06,
+      "loss": 0.4586,
+      "step": 2390
+    },
+    {
+      "epoch": 0.48454258675078865,
+      "grad_norm": 0.4946893193107334,
+      "learning_rate": 6.138598097734308e-06,
+      "loss": 0.4613,
+      "step": 2400
+    },
+    {
+      "epoch": 0.4865615141955836,
+      "grad_norm": 0.4278600145969151,
+      "learning_rate": 6.104260410291237e-06,
+      "loss": 0.4524,
+      "step": 2410
+    },
+    {
+      "epoch": 0.48858044164037856,
+      "grad_norm": 0.438261930357501,
+      "learning_rate": 6.069867883874017e-06,
+      "loss": 0.4546,
+      "step": 2420
+    },
+    {
+      "epoch": 0.4905993690851735,
+      "grad_norm": 0.4834328335496326,
+      "learning_rate": 6.035422226459183e-06,
+      "loss": 0.4601,
+      "step": 2430
+    },
+    {
+      "epoch": 0.49261829652996847,
+      "grad_norm": 0.4560202224259225,
+      "learning_rate": 6.000925148661822e-06,
+      "loss": 0.4552,
+      "step": 2440
+    },
+    {
+      "epoch": 0.4946372239747634,
+      "grad_norm": 0.46242134458299394,
+      "learning_rate": 5.966378363650618e-06,
+      "loss": 0.4534,
+      "step": 2450
+    },
+    {
+      "epoch": 0.4966561514195584,
+      "grad_norm": 0.509798379798209,
+      "learning_rate": 5.931783587062785e-06,
+      "loss": 0.4478,
+      "step": 2460
+    },
+    {
+      "epoch": 0.4986750788643533,
+      "grad_norm": 0.4916270732208669,
+      "learning_rate": 5.897142536918854e-06,
+      "loss": 0.4606,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5006940063091483,
+      "grad_norm": 0.4493237090311729,
+      "learning_rate": 5.8624569335373625e-06,
+      "loss": 0.4512,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5027129337539432,
+      "grad_norm": 0.4570244860395198,
+      "learning_rate": 5.827728499449417e-06,
+      "loss": 0.4503,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5047318611987381,
+      "grad_norm": 0.5044698787582333,
+      "learning_rate": 5.792958959313155e-06,
+      "loss": 0.4586,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5067507886435331,
+      "grad_norm": 0.4567238497826546,
+      "learning_rate": 5.758150039828084e-06,
+      "loss": 0.442,
+      "step": 2510
+    },
+    {
+      "epoch": 0.5087697160883281,
+      "grad_norm": 0.49456514738525703,
+      "learning_rate": 5.723303469649352e-06,
+      "loss": 0.4524,
+      "step": 2520
+    },
+    {
+      "epoch": 0.510788643533123,
+      "grad_norm": 0.46129063291343286,
+      "learning_rate": 5.688420979301876e-06,
+      "loss": 0.4533,
+      "step": 2530
+    },
+    {
+      "epoch": 0.512807570977918,
+      "grad_norm": 0.46780830492612324,
+      "learning_rate": 5.6535043010944226e-06,
+      "loss": 0.4537,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5148264984227129,
+      "grad_norm": 0.49663726459668367,
+      "learning_rate": 5.618555169033567e-06,
+      "loss": 0.4624,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5168454258675079,
+      "grad_norm": 0.4323698197626643,
+      "learning_rate": 5.583575318737588e-06,
+      "loss": 0.4394,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5188643533123029,
+      "grad_norm": 0.433967581020834,
+      "learning_rate": 5.548566487350264e-06,
+      "loss": 0.4482,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5208832807570978,
+      "grad_norm": 0.5093937708469708,
+      "learning_rate": 5.513530413454618e-06,
+      "loss": 0.4488,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5229022082018927,
+      "grad_norm": 0.4479313579903872,
+      "learning_rate": 5.478468836986568e-06,
+      "loss": 0.4547,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5249211356466877,
+      "grad_norm": 0.4784953987086218,
+      "learning_rate": 5.443383499148519e-06,
+      "loss": 0.4536,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5269400630914827,
+      "grad_norm": 0.4311672354723456,
+      "learning_rate": 5.408276142322904e-06,
+      "loss": 0.4489,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5289589905362776,
+      "grad_norm": 0.4320377418884208,
+      "learning_rate": 5.373148509985636e-06,
+      "loss": 0.457,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5309779179810725,
+      "grad_norm": 0.4475608921551904,
+      "learning_rate": 5.3380023466195455e-06,
+      "loss": 0.4491,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5329968454258676,
+      "grad_norm": 0.4150312768857391,
+      "learning_rate": 5.302839397627732e-06,
+      "loss": 0.4509,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5350157728706625,
+      "grad_norm": 0.4842663915075593,
+      "learning_rate": 5.267661409246893e-06,
+      "loss": 0.4497,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5370347003154574,
+      "grad_norm": 0.48020608359904937,
+      "learning_rate": 5.232470128460597e-06,
+      "loss": 0.4455,
+      "step": 2660
+    },
+    {
+      "epoch": 0.5390536277602523,
+      "grad_norm": 0.460861374110654,
+      "learning_rate": 5.197267302912535e-06,
+      "loss": 0.4633,
+      "step": 2670
+    },
+    {
+      "epoch": 0.5410725552050473,
+      "grad_norm": 0.4861656655295904,
+      "learning_rate": 5.162054680819724e-06,
+      "loss": 0.455,
+      "step": 2680
+    },
+    {
+      "epoch": 0.5430914826498423,
+      "grad_norm": 0.4280331150720691,
+      "learning_rate": 5.12683401088569e-06,
+      "loss": 0.4527,
+      "step": 2690
+    },
+    {
+      "epoch": 0.5451104100946372,
+      "grad_norm": 0.4803934844859794,
+      "learning_rate": 5.091607042213621e-06,
+      "loss": 0.4507,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5471293375394322,
+      "grad_norm": 0.44679887041219724,
+      "learning_rate": 5.056375524219516e-06,
+      "loss": 0.4467,
+      "step": 2710
+    },
+    {
+      "epoch": 0.5491482649842271,
+      "grad_norm": 0.4562693718725788,
+      "learning_rate": 5.021141206545293e-06,
+      "loss": 0.4481,
+      "step": 2720
+    },
+    {
+      "epoch": 0.5511671924290221,
+      "grad_norm": 0.4568391909726876,
+      "learning_rate": 4.9859058389719095e-06,
+      "loss": 0.4467,
+      "step": 2730
+    },
+    {
+      "epoch": 0.553186119873817,
+      "grad_norm": 0.4402113900197009,
+      "learning_rate": 4.950671171332458e-06,
+      "loss": 0.4438,
+      "step": 2740
+    },
+    {
+      "epoch": 0.555205047318612,
+      "grad_norm": 0.4694901686129437,
+      "learning_rate": 4.915438953425277e-06,
+      "loss": 0.455,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5572239747634069,
+      "grad_norm": 0.5092377388071306,
+      "learning_rate": 4.8802109349270415e-06,
+      "loss": 0.4431,
+      "step": 2760
+    },
+    {
+      "epoch": 0.5592429022082019,
+      "grad_norm": 0.5334478668234227,
+      "learning_rate": 4.844988865305883e-06,
+      "loss": 0.4457,
+      "step": 2770
+    },
+    {
+      "epoch": 0.5612618296529969,
+      "grad_norm": 0.450190134489615,
+      "learning_rate": 4.809774493734507e-06,
+      "loss": 0.4468,
+      "step": 2780
+    },
+    {
+      "epoch": 0.5632807570977918,
+      "grad_norm": 0.6136460189487958,
+      "learning_rate": 4.774569569003314e-06,
+      "loss": 0.4531,
+      "step": 2790
+    },
+    {
+      "epoch": 0.5652996845425867,
+      "grad_norm": 0.47669716943494894,
+      "learning_rate": 4.739375839433575e-06,
+      "loss": 0.4559,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5673186119873816,
+      "grad_norm": 0.47396268716032475,
+      "learning_rate": 4.704195052790584e-06,
+      "loss": 0.4463,
+      "step": 2810
+    },
+    {
+      "epoch": 0.5693375394321767,
+      "grad_norm": 0.5115114860936024,
+      "learning_rate": 4.66902895619688e-06,
+      "loss": 0.4494,
+      "step": 2820
+    },
+    {
+      "epoch": 0.5713564668769716,
+      "grad_norm": 0.4561358589231192,
+      "learning_rate": 4.633879296045474e-06,
+      "loss": 0.4477,
+      "step": 2830
+    },
+    {
+      "epoch": 0.5733753943217665,
+      "grad_norm": 0.4547946639578122,
+      "learning_rate": 4.59874781791312e-06,
+      "loss": 0.4502,
+      "step": 2840
+    },
+    {
+      "epoch": 0.5753943217665615,
+      "grad_norm": 0.5036899795994354,
+      "learning_rate": 4.56363626647363e-06,
+      "loss": 0.4553,
+      "step": 2850
+    },
+    {
+      "epoch": 0.5774132492113565,
+      "grad_norm": 0.46515739613875146,
+      "learning_rate": 4.528546385411239e-06,
+      "loss": 0.4373,
+      "step": 2860
+    },
+    {
+      "epoch": 0.5794321766561514,
+      "grad_norm": 0.4834989187992637,
+      "learning_rate": 4.493479917333989e-06,
+      "loss": 0.453,
+      "step": 2870
+    },
+    {
+      "epoch": 0.5814511041009464,
+      "grad_norm": 0.45922181466381384,
+      "learning_rate": 4.4584386036872155e-06,
+      "loss": 0.4527,
+      "step": 2880
+    },
+    {
+      "epoch": 0.5834700315457413,
+      "grad_norm": 0.46803871925708684,
+      "learning_rate": 4.42342418466705e-06,
+      "loss": 0.4426,
+      "step": 2890
+    },
+    {
+      "epoch": 0.5854889589905363,
+      "grad_norm": 0.47319916436776355,
+      "learning_rate": 4.388438399134e-06,
+      "loss": 0.4547,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5875078864353313,
+      "grad_norm": 0.4598569796278221,
+      "learning_rate": 4.3534829845265996e-06,
+      "loss": 0.4441,
+      "step": 2910
+    },
+    {
+      "epoch": 0.5895268138801262,
+      "grad_norm": 0.47100191118178447,
+      "learning_rate": 4.318559676775126e-06,
+      "loss": 0.4472,
+      "step": 2920
+    },
+    {
+      "epoch": 0.5915457413249211,
+      "grad_norm": 0.495923691841689,
+      "learning_rate": 4.283670210215384e-06,
+      "loss": 0.4516,
+      "step": 2930
+    },
+    {
+      "epoch": 0.5935646687697161,
+      "grad_norm": 0.4391764043906036,
+      "learning_rate": 4.248816317502585e-06,
+      "loss": 0.4468,
+      "step": 2940
+    },
+    {
+      "epoch": 0.5955835962145111,
+      "grad_norm": 0.47900304182889214,
+      "learning_rate": 4.213999729525304e-06,
+      "loss": 0.452,
+      "step": 2950
+    },
+    {
+      "epoch": 0.597602523659306,
+      "grad_norm": 0.4894376668991494,
+      "learning_rate": 4.179222175319502e-06,
+      "loss": 0.4418,
+      "step": 2960
+    },
+    {
+      "epoch": 0.5996214511041009,
+      "grad_norm": 0.4698266233405637,
+      "learning_rate": 4.1444853819826845e-06,
+      "loss": 0.4503,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6016403785488958,
+      "grad_norm": 0.4601994675920038,
+      "learning_rate": 4.1097910745881175e-06,
+      "loss": 0.4421,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6036593059936909,
+      "grad_norm": 0.6167906848346414,
+      "learning_rate": 4.0751409760991585e-06,
+      "loss": 0.4469,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6056782334384858,
+      "grad_norm": 0.5051790895352023,
+      "learning_rate": 4.040536807283696e-06,
+      "loss": 0.4502,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6076971608832807,
+      "grad_norm": 0.45322450050363433,
+      "learning_rate": 4.005980286628698e-06,
+      "loss": 0.4505,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6097160883280757,
+      "grad_norm": 0.4910869337898713,
+      "learning_rate": 3.9714731302548525e-06,
+      "loss": 0.4486,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6117350157728707,
+      "grad_norm": 0.447631013542978,
+      "learning_rate": 3.937017051831367e-06,
+      "loss": 0.4478,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6137539432176656,
+      "grad_norm": 0.7018069369756337,
+      "learning_rate": 3.9026137624908466e-06,
+      "loss": 0.4492,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6157728706624606,
+      "grad_norm": 0.4762076148803905,
+      "learning_rate": 3.868264970744324e-06,
+      "loss": 0.4513,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6177917981072555,
+      "grad_norm": 0.5020509623933802,
+      "learning_rate": 3.833972382396412e-06,
+      "loss": 0.4482,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6198107255520505,
+      "grad_norm": 0.44347011131653674,
+      "learning_rate": 3.799737700460594e-06,
+      "loss": 0.4441,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6218296529968455,
+      "grad_norm": 0.45353690385677753,
+      "learning_rate": 3.7655626250746446e-06,
+      "loss": 0.4443,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6238485804416404,
+      "grad_norm": 0.44404552147051596,
+      "learning_rate": 3.7314488534162007e-06,
+      "loss": 0.4509,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6258675078864353,
+      "grad_norm": 0.4759693579595236,
+      "learning_rate": 3.6973980796184843e-06,
+      "loss": 0.4573,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6278864353312302,
+      "grad_norm": 0.45248182104327295,
+      "learning_rate": 3.6634119946861556e-06,
+      "loss": 0.4442,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6299053627760253,
+      "grad_norm": 0.44605725901650006,
+      "learning_rate": 3.629492286411349e-06,
+      "loss": 0.4515,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6319242902208202,
+      "grad_norm": 0.4770842161429305,
+      "learning_rate": 3.5956406392898484e-06,
+      "loss": 0.4481,
+      "step": 3130
+    },
+    {
+      "epoch": 0.6339432176656151,
+      "grad_norm": 0.4611511904942963,
+      "learning_rate": 3.561858734437432e-06,
+      "loss": 0.4553,
+      "step": 3140
+    },
+    {
+      "epoch": 0.63596214511041,
+      "grad_norm": 0.4886490480648605,
+      "learning_rate": 3.528148249506391e-06,
+      "loss": 0.4541,
+      "step": 3150
+    },
+    {
+      "epoch": 0.6379810725552051,
+      "grad_norm": 0.5063011038652176,
+      "learning_rate": 3.494510858602217e-06,
+      "loss": 0.448,
+      "step": 3160
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5297665998286369,
+      "learning_rate": 3.4609482322004463e-06,
+      "loss": 0.45,
+      "step": 3170
+    },
+    {
+      "epoch": 0.6420189274447949,
+      "grad_norm": 0.789602090268308,
+      "learning_rate": 3.427462037063729e-06,
+      "loss": 0.4499,
+      "step": 3180
+    },
+    {
+      "epoch": 0.6440378548895899,
+      "grad_norm": 0.4595511607863831,
+      "learning_rate": 3.394053936159035e-06,
+      "loss": 0.4451,
+      "step": 3190
+    },
+    {
+      "epoch": 0.6460567823343849,
+      "grad_norm": 0.5053416927018038,
+      "learning_rate": 3.3607255885750756e-06,
+      "loss": 0.4488,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6480757097791798,
+      "grad_norm": 0.47050871567377006,
+      "learning_rate": 3.3274786494399102e-06,
+      "loss": 0.4461,
+      "step": 3210
+    },
+    {
+      "epoch": 0.6500946372239748,
+      "grad_norm": 0.46433780403203007,
+      "learning_rate": 3.2943147698387562e-06,
+      "loss": 0.4497,
+      "step": 3220
+    },
+    {
+      "epoch": 0.6521135646687697,
+      "grad_norm": 0.45409078162209787,
+      "learning_rate": 3.261235596731982e-06,
+      "loss": 0.4457,
+      "step": 3230
+    },
+    {
+      "epoch": 0.6541324921135647,
+      "grad_norm": 0.4218245687222197,
+      "learning_rate": 3.228242772873328e-06,
+      "loss": 0.4437,
+      "step": 3240
+    },
+    {
+      "epoch": 0.6561514195583596,
+      "grad_norm": 0.47127385494827945,
+      "learning_rate": 3.195337936728323e-06,
+      "loss": 0.4488,
+      "step": 3250
+    },
+    {
+      "epoch": 0.6581703470031546,
+      "grad_norm": 0.43568607166498186,
+      "learning_rate": 3.1625227223929105e-06,
+      "loss": 0.4415,
+      "step": 3260
+    },
+    {
+      "epoch": 0.6601892744479495,
+      "grad_norm": 0.4200623699882891,
+      "learning_rate": 3.1297987595123024e-06,
+      "loss": 0.4423,
+      "step": 3270
+    },
+    {
+      "epoch": 0.6622082018927444,
+      "grad_norm": 0.45902924831849934,
+      "learning_rate": 3.0971676732000494e-06,
+      "loss": 0.4488,
+      "step": 3280
+    },
+    {
+      "epoch": 0.6642271293375395,
+      "grad_norm": 0.48610535709106045,
+      "learning_rate": 3.0646310839573302e-06,
+      "loss": 0.441,
+      "step": 3290
+    },
+    {
+      "epoch": 0.6662460567823344,
+      "grad_norm": 0.5237594196219926,
+      "learning_rate": 3.03219060759248e-06,
+      "loss": 0.454,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6682649842271293,
+      "grad_norm": 0.4228282553579445,
+      "learning_rate": 2.9998478551407524e-06,
+      "loss": 0.4378,
+      "step": 3310
+    },
+    {
+      "epoch": 0.6702839116719242,
+      "grad_norm": 0.46926328208349977,
+      "learning_rate": 2.9676044327842963e-06,
+      "loss": 0.4475,
+      "step": 3320
+    },
+    {
+      "epoch": 0.6723028391167193,
+      "grad_norm": 0.47029450291352376,
+      "learning_rate": 2.935461941772412e-06,
+      "loss": 0.4418,
+      "step": 3330
+    },
+    {
+      "epoch": 0.6743217665615142,
+      "grad_norm": 0.461936788764074,
+      "learning_rate": 2.9034219783420183e-06,
+      "loss": 0.438,
+      "step": 3340
+    },
+    {
+      "epoch": 0.6763406940063091,
+      "grad_norm": 0.4879384251763818,
+      "learning_rate": 2.871486133638378e-06,
+      "loss": 0.4498,
+      "step": 3350
+    },
+    {
+      "epoch": 0.6783596214511041,
+      "grad_norm": 0.47390435742643133,
+      "learning_rate": 2.8396559936360934e-06,
+      "loss": 0.4444,
+      "step": 3360
+    },
+    {
+      "epoch": 0.6803785488958991,
+      "grad_norm": 0.43781719559966065,
+      "learning_rate": 2.807933139060337e-06,
+      "loss": 0.4481,
+      "step": 3370
+    },
+    {
+      "epoch": 0.682397476340694,
+      "grad_norm": 0.452166890113836,
+      "learning_rate": 2.776319145308345e-06,
+      "loss": 0.4397,
+      "step": 3380
+    },
+    {
+      "epoch": 0.684416403785489,
+      "grad_norm": 0.4480696892989974,
+      "learning_rate": 2.7448155823711897e-06,
+      "loss": 0.4415,
+      "step": 3390
+    },
+    {
+      "epoch": 0.6864353312302839,
+      "grad_norm": 0.482631983733039,
+      "learning_rate": 2.7134240147558124e-06,
+      "loss": 0.4494,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6884542586750788,
+      "grad_norm": 0.4215351521880855,
+      "learning_rate": 2.6821460014073187e-06,
+      "loss": 0.4359,
+      "step": 3410
+    },
+    {
+      "epoch": 0.6904731861198738,
+      "grad_norm": 0.44170545621316426,
+      "learning_rate": 2.6509830956315684e-06,
+      "loss": 0.4516,
+      "step": 3420
+    },
+    {
+      "epoch": 0.6924921135646688,
+      "grad_norm": 0.43846533524679027,
+      "learning_rate": 2.619936845018031e-06,
+      "loss": 0.4357,
+      "step": 3430
+    },
+    {
+      "epoch": 0.6945110410094637,
+      "grad_norm": 0.5008934216933979,
+      "learning_rate": 2.5890087913629358e-06,
+      "loss": 0.4467,
+      "step": 3440
+    },
+    {
+      "epoch": 0.6965299684542586,
+      "grad_norm": 0.5250213600953301,
+      "learning_rate": 2.558200470592701e-06,
+      "loss": 0.449,
+      "step": 3450
+    },
+    {
+      "epoch": 0.6985488958990537,
+      "grad_norm": 0.5362972001626155,
+      "learning_rate": 2.527513412687654e-06,
+      "loss": 0.436,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7005678233438486,
+      "grad_norm": 0.4447368579357635,
+      "learning_rate": 2.4969491416060542e-06,
+      "loss": 0.4393,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7025867507886435,
+      "grad_norm": 0.42761346324330285,
+      "learning_rate": 2.4665091752084175e-06,
+      "loss": 0.4423,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7046056782334384,
+      "grad_norm": 0.45180644732668995,
+      "learning_rate": 2.4361950251821253e-06,
+      "loss": 0.4351,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7066246056782335,
+      "grad_norm": 0.4655597774869552,
+      "learning_rate": 2.406008196966359e-06,
+      "loss": 0.445,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7086435331230284,
+      "grad_norm": 0.44607134328593223,
+      "learning_rate": 2.375950189677342e-06,
+      "loss": 0.4322,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7106624605678233,
+      "grad_norm": 0.45886523824853853,
+      "learning_rate": 2.346022496033879e-06,
+      "loss": 0.439,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7126813880126183,
+      "grad_norm": 0.439206301308698,
+      "learning_rate": 2.316226602283243e-06,
+      "loss": 0.445,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7147003154574133,
+      "grad_norm": 0.42444173885080955,
+      "learning_rate": 2.2865639881273494e-06,
+      "loss": 0.4402,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7167192429022082,
+      "grad_norm": 0.48281990057391616,
+      "learning_rate": 2.25703612664928e-06,
+      "loss": 0.445,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7187381703470032,
+      "grad_norm": 0.46127829547820787,
+      "learning_rate": 2.227644484240135e-06,
+      "loss": 0.4356,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7207570977917981,
+      "grad_norm": 0.4610423355631118,
+      "learning_rate": 2.198390520526194e-06,
+      "loss": 0.4438,
+      "step": 3570
+    },
+    {
+      "epoch": 0.722776025236593,
+      "grad_norm": 0.4711885745663891,
+      "learning_rate": 2.1692756882964404e-06,
+      "loss": 0.4464,
+      "step": 3580
+    },
+    {
+      "epoch": 0.724794952681388,
+      "grad_norm": 0.5420237747030388,
+      "learning_rate": 2.140301433430414e-06,
+      "loss": 0.4436,
+      "step": 3590
+    },
+    {
+      "epoch": 0.726813880126183,
+      "grad_norm": 0.47745493287406926,
+      "learning_rate": 2.1114691948264038e-06,
+      "loss": 0.4433,
+      "step": 3600
+    },
+    {
+      "epoch": 0.7288328075709779,
+      "grad_norm": 0.43683824200923127,
+      "learning_rate": 2.082780404329988e-06,
+      "loss": 0.4429,
+      "step": 3610
+    },
+    {
+      "epoch": 0.7308517350157728,
+      "grad_norm": 0.42141576682539833,
+      "learning_rate": 2.0542364866629292e-06,
+      "loss": 0.4402,
+      "step": 3620
+    },
+    {
+      "epoch": 0.7328706624605679,
+      "grad_norm": 0.4304526228372951,
+      "learning_rate": 2.025838859352428e-06,
+      "loss": 0.4462,
+      "step": 3630
+    },
+    {
+      "epoch": 0.7348895899053628,
+      "grad_norm": 0.4960972537231228,
+      "learning_rate": 1.997588932660713e-06,
+      "loss": 0.4298,
+      "step": 3640
+    },
+    {
+      "epoch": 0.7369085173501577,
+      "grad_norm": 0.5055917828329974,
+      "learning_rate": 1.9694881095150125e-06,
+      "loss": 0.4429,
+      "step": 3650
+    },
+    {
+      "epoch": 0.7389274447949526,
+      "grad_norm": 0.4756073151541865,
+      "learning_rate": 1.9415377854378903e-06,
+      "loss": 0.4423,
+      "step": 3660
+    },
+    {
+      "epoch": 0.7409463722397477,
+      "grad_norm": 0.4293238953341605,
+      "learning_rate": 1.913739348477927e-06,
+      "loss": 0.444,
+      "step": 3670
+    },
+    {
+      "epoch": 0.7429652996845426,
+      "grad_norm": 0.4476184732471472,
+      "learning_rate": 1.8860941791408038e-06,
+      "loss": 0.4432,
+      "step": 3680
+    },
+    {
+      "epoch": 0.7449842271293375,
+      "grad_norm": 0.4453341449071723,
+      "learning_rate": 1.8586036503207316e-06,
+      "loss": 0.4351,
+      "step": 3690
+    },
+    {
+      "epoch": 0.7470031545741325,
+      "grad_norm": 0.4741404781356218,
+      "learning_rate": 1.8312691272322768e-06,
+      "loss": 0.4445,
+      "step": 3700
+    },
+    {
+      "epoch": 0.7490220820189274,
+      "grad_norm": 0.4314595245056323,
+      "learning_rate": 1.804091967342569e-06,
+      "loss": 0.4392,
+      "step": 3710
+    },
+    {
+      "epoch": 0.7510410094637224,
+      "grad_norm": 0.4960471983973586,
+      "learning_rate": 1.777073520303874e-06,
+      "loss": 0.4406,
+      "step": 3720
+    },
+    {
+      "epoch": 0.7530599369085174,
+      "grad_norm": 0.47724657720097824,
+      "learning_rate": 1.7502151278865798e-06,
+      "loss": 0.4391,
+      "step": 3730
+    },
+    {
+      "epoch": 0.7550788643533123,
+      "grad_norm": 0.45566327509907684,
+      "learning_rate": 1.7235181239125587e-06,
+      "loss": 0.4411,
+      "step": 3740
+    },
+    {
+      "epoch": 0.7570977917981072,
+      "grad_norm": 0.47859031492685,
+      "learning_rate": 1.6969838341889288e-06,
+      "loss": 0.4412,
+      "step": 3750
+    },
+    {
+      "epoch": 0.7591167192429022,
+      "grad_norm": 0.4239970850626806,
+      "learning_rate": 1.67061357644221e-06,
+      "loss": 0.4327,
+      "step": 3760
+    },
+    {
+      "epoch": 0.7611356466876972,
+      "grad_norm": 0.41439508221708543,
+      "learning_rate": 1.6444086602528835e-06,
+      "loss": 0.4403,
+      "step": 3770
+    },
+    {
+      "epoch": 0.7631545741324921,
+      "grad_norm": 0.4724942386548484,
+      "learning_rate": 1.6183703869903666e-06,
+      "loss": 0.4399,
+      "step": 3780
+    },
+    {
+      "epoch": 0.765173501577287,
+      "grad_norm": 0.5068083200686946,
+      "learning_rate": 1.59250004974837e-06,
+      "loss": 0.4484,
+      "step": 3790
+    },
+    {
+      "epoch": 0.7671924290220821,
+      "grad_norm": 0.47623913375530136,
+      "learning_rate": 1.5667989332806894e-06,
+      "loss": 0.442,
+      "step": 3800
+    },
+    {
+      "epoch": 0.769211356466877,
+      "grad_norm": 0.5448383844625657,
+      "learning_rate": 1.5412683139374068e-06,
+      "loss": 0.4339,
+      "step": 3810
+    },
+    {
+      "epoch": 0.7712302839116719,
+      "grad_norm": 0.4819612793724808,
+      "learning_rate": 1.5159094596014934e-06,
+      "loss": 0.4478,
+      "step": 3820
+    },
+    {
+      "epoch": 0.7732492113564668,
+      "grad_norm": 0.4456007417706316,
+      "learning_rate": 1.4907236296258598e-06,
+      "loss": 0.4423,
+      "step": 3830
+    },
+    {
+      "epoch": 0.7752681388012618,
+      "grad_norm": 0.43979298393219013,
+      "learning_rate": 1.4657120747708014e-06,
+      "loss": 0.4417,
+      "step": 3840
+    },
+    {
+      "epoch": 0.7772870662460568,
+      "grad_norm": 0.5066920888924865,
+      "learning_rate": 1.4408760371418895e-06,
+      "loss": 0.4397,
+      "step": 3850
+    },
+    {
+      "epoch": 0.7793059936908517,
+      "grad_norm": 0.47046124228822955,
+      "learning_rate": 1.4162167501282925e-06,
+      "loss": 0.4416,
+      "step": 3860
+    },
+    {
+      "epoch": 0.7813249211356467,
+      "grad_norm": 0.4558898604297212,
+      "learning_rate": 1.391735438341514e-06,
+      "loss": 0.437,
+      "step": 3870
+    },
+    {
+      "epoch": 0.7833438485804416,
+      "grad_norm": 0.4635342780752439,
+      "learning_rate": 1.3674333175545818e-06,
+      "loss": 0.4425,
+      "step": 3880
+    },
+    {
+      "epoch": 0.7853627760252366,
+      "grad_norm": 0.450134125379297,
+      "learning_rate": 1.343311594641674e-06,
+      "loss": 0.4371,
+      "step": 3890
+    },
+    {
+      "epoch": 0.7873817034700316,
+      "grad_norm": 0.48501901287598154,
+      "learning_rate": 1.3193714675181813e-06,
+      "loss": 0.4428,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7894006309148265,
+      "grad_norm": 0.41955405495588977,
+      "learning_rate": 1.2956141250812144e-06,
+      "loss": 0.4307,
+      "step": 3910
+    },
+    {
+      "epoch": 0.7914195583596214,
+      "grad_norm": 0.41659445986128424,
+      "learning_rate": 1.272040747150563e-06,
+      "loss": 0.447,
+      "step": 3920
+    },
+    {
+      "epoch": 0.7934384858044164,
+      "grad_norm": 0.44707673152149113,
+      "learning_rate": 1.2486525044101123e-06,
+      "loss": 0.4333,
+      "step": 3930
+    },
+    {
+      "epoch": 0.7954574132492114,
+      "grad_norm": 0.4698766268506151,
+      "learning_rate": 1.2254505583496922e-06,
+      "loss": 0.4403,
+      "step": 3940
+    },
+    {
+      "epoch": 0.7974763406940063,
+      "grad_norm": 0.47512471796296707,
+      "learning_rate": 1.2024360612074055e-06,
+      "loss": 0.4454,
+      "step": 3950
+    },
+    {
+      "epoch": 0.7994952681388012,
+      "grad_norm": 0.4585910400457452,
+      "learning_rate": 1.179610155912405e-06,
+      "loss": 0.436,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8015141955835963,
+      "grad_norm": 0.4557389746705491,
+      "learning_rate": 1.1569739760281295e-06,
+      "loss": 0.4393,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8035331230283912,
+      "grad_norm": 0.4553106102818403,
+      "learning_rate": 1.1345286456960186e-06,
+      "loss": 0.4439,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8055520504731861,
+      "grad_norm": 0.4443887135897382,
+      "learning_rate": 1.1122752795796748e-06,
+      "loss": 0.4413,
+      "step": 3990
+    },
+    {
+      "epoch": 0.807570977917981,
+      "grad_norm": 0.47272003456758904,
+      "learning_rate": 1.0902149828095154e-06,
+      "loss": 0.4422,
+      "step": 4000
+    },
+    {
+      "epoch": 0.809589905362776,
+      "grad_norm": 0.43703108025040205,
+      "learning_rate": 1.0683488509278928e-06,
+      "loss": 0.4386,
+      "step": 4010
+    },
+    {
+      "epoch": 0.811608832807571,
+      "grad_norm": 0.4441202945224273,
+      "learning_rate": 1.0466779698346797e-06,
+      "loss": 0.4363,
+      "step": 4020
+    },
+    {
+      "epoch": 0.8136277602523659,
+      "grad_norm": 0.42622028909468485,
+      "learning_rate": 1.025203415733348e-06,
+      "loss": 0.4365,
+      "step": 4030
+    },
+    {
+      "epoch": 0.8156466876971609,
+      "grad_norm": 0.440821020950604,
+      "learning_rate": 1.0039262550775235e-06,
+      "loss": 0.4345,
+      "step": 4040
+    },
+    {
+      "epoch": 0.8176656151419558,
+      "grad_norm": 0.4670601139166515,
+      "learning_rate": 9.828475445180212e-07,
+      "loss": 0.4404,
+      "step": 4050
+    },
+    {
+      "epoch": 0.8196845425867508,
+      "grad_norm": 0.4363041969561276,
+      "learning_rate": 9.61968330850374e-07,
+      "loss": 0.4369,
+      "step": 4060
+    },
+    {
+      "epoch": 0.8217034700315458,
+      "grad_norm": 0.4866069797752605,
+      "learning_rate": 9.412896509628439e-07,
+      "loss": 0.4434,
+      "step": 4070
+    },
+    {
+      "epoch": 0.8237223974763407,
+      "grad_norm": 0.4360948594973755,
+      "learning_rate": 9.208125317849304e-07,
+      "loss": 0.4395,
+      "step": 4080
+    },
+    {
+      "epoch": 0.8257413249211356,
+      "grad_norm": 0.4490621547393745,
+      "learning_rate": 9.005379902363753e-07,
+      "loss": 0.4405,
+      "step": 4090
+    },
+    {
+      "epoch": 0.8277602523659306,
+      "grad_norm": 0.4809678412101839,
+      "learning_rate": 8.804670331766557e-07,
+      "loss": 0.4449,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8297791798107256,
+      "grad_norm": 0.4626290445825763,
+      "learning_rate": 8.606006573549836e-07,
+      "loss": 0.4359,
+      "step": 4110
+    },
+    {
+      "epoch": 0.8317981072555205,
+      "grad_norm": 0.5187638972410576,
+      "learning_rate": 8.409398493608089e-07,
+      "loss": 0.4413,
+      "step": 4120
+    },
+    {
+      "epoch": 0.8338170347003154,
+      "grad_norm": 0.46587792642977804,
+      "learning_rate": 8.214855855748249e-07,
+      "loss": 0.4409,
+      "step": 4130
+    },
+    {
+      "epoch": 0.8358359621451104,
+      "grad_norm": 0.4706901825283824,
+      "learning_rate": 8.022388321204688e-07,
+      "loss": 0.4354,
+      "step": 4140
+    },
+    {
+      "epoch": 0.8378548895899054,
+      "grad_norm": 0.562791948402191,
+      "learning_rate": 7.832005448159585e-07,
+      "loss": 0.4445,
+      "step": 4150
+    },
+    {
+      "epoch": 0.8398738170347003,
+      "grad_norm": 0.4543738469403552,
+      "learning_rate": 7.643716691268171e-07,
+      "loss": 0.4374,
+      "step": 4160
+    },
+    {
+      "epoch": 0.8418927444794952,
+      "grad_norm": 1.6174532184269235,
+      "learning_rate": 7.457531401189188e-07,
+      "loss": 0.4408,
+      "step": 4170
+    },
+    {
+      "epoch": 0.8439116719242902,
+      "grad_norm": 0.46922997370194347,
+      "learning_rate": 7.273458824120555e-07,
+      "loss": 0.4376,
+      "step": 4180
+    },
+    {
+      "epoch": 0.8459305993690852,
+      "grad_norm": 0.44210687899012985,
+      "learning_rate": 7.091508101340189e-07,
+      "loss": 0.4407,
+      "step": 4190
+    },
+    {
+      "epoch": 0.8479495268138801,
+      "grad_norm": 0.488809217492704,
+      "learning_rate": 6.91168826875201e-07,
+      "loss": 0.4489,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8499684542586751,
+      "grad_norm": 0.4335482219101724,
+      "learning_rate": 6.734008256437253e-07,
+      "loss": 0.435,
+      "step": 4210
+    },
+    {
+      "epoch": 0.85198738170347,
+      "grad_norm": 0.4549494452467777,
+      "learning_rate": 6.558476888210935e-07,
+      "loss": 0.4375,
+      "step": 4220
+    },
+    {
+      "epoch": 0.854006309148265,
+      "grad_norm": 0.44896647048001603,
+      "learning_rate": 6.38510288118368e-07,
+      "loss": 0.4409,
+      "step": 4230
+    },
+    {
+      "epoch": 0.85602523659306,
+      "grad_norm": 0.43685823117883865,
+      "learning_rate": 6.213894845328844e-07,
+      "loss": 0.4418,
+      "step": 4240
+    },
+    {
+      "epoch": 0.8580441640378549,
+      "grad_norm": 0.47792243578520655,
+      "learning_rate": 6.044861283054876e-07,
+      "loss": 0.4452,
+      "step": 4250
+    },
+    {
+      "epoch": 0.8600630914826498,
+      "grad_norm": 0.43885235740502504,
+      "learning_rate": 5.878010588783101e-07,
+      "loss": 0.4423,
+      "step": 4260
+    },
+    {
+      "epoch": 0.8620820189274448,
+      "grad_norm": 0.5121668333108534,
+      "learning_rate": 5.713351048530874e-07,
+      "loss": 0.4429,
+      "step": 4270
+    },
+    {
+      "epoch": 0.8641009463722398,
+      "grad_norm": 0.44403508398564756,
+      "learning_rate": 5.550890839500067e-07,
+      "loss": 0.4511,
+      "step": 4280
+    },
+    {
+      "epoch": 0.8661198738170347,
+      "grad_norm": 0.42769598938785636,
+      "learning_rate": 5.390638029670908e-07,
+      "loss": 0.4322,
+      "step": 4290
+    },
+    {
+      "epoch": 0.8681388012618296,
+      "grad_norm": 0.4949663561795469,
+      "learning_rate": 5.232600577401436e-07,
+      "loss": 0.4457,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8701577287066246,
+      "grad_norm": 0.4489314407451146,
+      "learning_rate": 5.076786331032224e-07,
+      "loss": 0.4327,
+      "step": 4310
+    },
+    {
+      "epoch": 0.8721766561514196,
+      "grad_norm": 0.48025463446625855,
+      "learning_rate": 4.923203028496576e-07,
+      "loss": 0.4447,
+      "step": 4320
+    },
+    {
+      "epoch": 0.8741955835962145,
+      "grad_norm": 0.5743773868003562,
+      "learning_rate": 4.771858296936311e-07,
+      "loss": 0.4402,
+      "step": 4330
+    },
+    {
+      "epoch": 0.8762145110410094,
+      "grad_norm": 0.4329672101913256,
+      "learning_rate": 4.622759652322989e-07,
+      "loss": 0.4455,
+      "step": 4340
+    },
+    {
+      "epoch": 0.8782334384858044,
+      "grad_norm": 0.49048963795844497,
+      "learning_rate": 4.475914499084605e-07,
+      "loss": 0.4467,
+      "step": 4350
+    },
+    {
+      "epoch": 0.8802523659305994,
+      "grad_norm": 0.4829611101804599,
+      "learning_rate": 4.331330129737954e-07,
+      "loss": 0.4287,
+      "step": 4360
+    },
+    {
+      "epoch": 0.8822712933753943,
+      "grad_norm": 0.44140910883095635,
+      "learning_rate": 4.189013724526392e-07,
+      "loss": 0.4446,
+      "step": 4370
+    },
+    {
+      "epoch": 0.8842902208201893,
+      "grad_norm": 0.45272062627566334,
+      "learning_rate": 4.048972351063313e-07,
+      "loss": 0.4354,
+      "step": 4380
+    },
+    {
+      "epoch": 0.8863091482649842,
+      "grad_norm": 0.7049959167129851,
+      "learning_rate": 3.9112129639811535e-07,
+      "loss": 0.4346,
+      "step": 4390
+    },
+    {
+      "epoch": 0.8883280757097792,
+      "grad_norm": 0.4811238411002169,
+      "learning_rate": 3.7757424045860025e-07,
+      "loss": 0.4372,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8903470031545742,
+      "grad_norm": 0.4540483251684103,
+      "learning_rate": 3.642567400517838e-07,
+      "loss": 0.4314,
+      "step": 4410
+    },
+    {
+      "epoch": 0.8923659305993691,
+      "grad_norm": 0.47603601308214405,
+      "learning_rate": 3.511694565416485e-07,
+      "loss": 0.4382,
+      "step": 4420
+    },
+    {
+      "epoch": 0.894384858044164,
+      "grad_norm": 0.4286142580967842,
+      "learning_rate": 3.383130398593121e-07,
+      "loss": 0.4399,
+      "step": 4430
+    },
+    {
+      "epoch": 0.8964037854889589,
+      "grad_norm": 0.4337017987281163,
+      "learning_rate": 3.2568812847074913e-07,
+      "loss": 0.4437,
+      "step": 4440
+    },
+    {
+      "epoch": 0.898422712933754,
+      "grad_norm": 0.48386529314250487,
+      "learning_rate": 3.1329534934509186e-07,
+      "loss": 0.4415,
+      "step": 4450
+    },
+    {
+      "epoch": 0.9004416403785489,
+      "grad_norm": 0.46990087367597777,
+      "learning_rate": 3.011353179234888e-07,
+      "loss": 0.4317,
+      "step": 4460
+    },
+    {
+      "epoch": 0.9024605678233438,
+      "grad_norm": 0.42506034975479673,
+      "learning_rate": 2.8920863808853947e-07,
+      "loss": 0.444,
+      "step": 4470
+    },
+    {
+      "epoch": 0.9044794952681388,
+      "grad_norm": 0.6216117310744336,
+      "learning_rate": 2.775159021343082e-07,
+      "loss": 0.4367,
+      "step": 4480
+    },
+    {
+      "epoch": 0.9064984227129338,
+      "grad_norm": 0.4583995655944248,
+      "learning_rate": 2.660576907369111e-07,
+      "loss": 0.4412,
+      "step": 4490
+    },
+    {
+      "epoch": 0.9085173501577287,
+      "grad_norm": 0.4889160958013681,
+      "learning_rate": 2.5483457292567517e-07,
+      "loss": 0.4403,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9105362776025236,
+      "grad_norm": 0.4267838945833425,
+      "learning_rate": 2.4384710605488195e-07,
+      "loss": 0.4402,
+      "step": 4510
+    },
+    {
+      "epoch": 0.9125552050473186,
+      "grad_norm": 0.4986776395611631,
+      "learning_rate": 2.330958357760882e-07,
+      "loss": 0.4399,
+      "step": 4520
+    },
+    {
+      "epoch": 0.9145741324921136,
+      "grad_norm": 0.459784020601065,
+      "learning_rate": 2.225812960110263e-07,
+      "loss": 0.4316,
+      "step": 4530
+    },
+    {
+      "epoch": 0.9165930599369085,
+      "grad_norm": 0.44426443349474987,
+      "learning_rate": 2.123040089250944e-07,
+      "loss": 0.4402,
+      "step": 4540
+    },
+    {
+      "epoch": 0.9186119873817035,
+      "grad_norm": 0.49235316049109906,
+      "learning_rate": 2.0226448490141715e-07,
+      "loss": 0.4481,
+      "step": 4550
+    },
+    {
+      "epoch": 0.9206309148264984,
+      "grad_norm": 0.43058790479448,
+      "learning_rate": 1.9246322251550653e-07,
+      "loss": 0.4317,
+      "step": 4560
+    },
+    {
+      "epoch": 0.9226498422712934,
+      "grad_norm": 0.4966838385984267,
+      "learning_rate": 1.829007085104978e-07,
+      "loss": 0.4427,
+      "step": 4570
+    },
+    {
+      "epoch": 0.9246687697160884,
+      "grad_norm": 0.4666275183152453,
+      "learning_rate": 1.7357741777297987e-07,
+      "loss": 0.4485,
+      "step": 4580
+    },
+    {
+      "epoch": 0.9266876971608833,
+      "grad_norm": 0.4412830191687912,
+      "learning_rate": 1.644938133094076e-07,
+      "loss": 0.4312,
+      "step": 4590
+    },
+    {
+      "epoch": 0.9287066246056782,
+      "grad_norm": 0.4886548137136921,
+      "learning_rate": 1.5565034622311349e-07,
+      "loss": 0.4461,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9307255520504731,
+      "grad_norm": 0.4652701957357695,
+      "learning_rate": 1.4704745569190327e-07,
+      "loss": 0.4375,
+      "step": 4610
+    },
+    {
+      "epoch": 0.9327444794952682,
+      "grad_norm": 0.5298674695548953,
+      "learning_rate": 1.3868556894624353e-07,
+      "loss": 0.4399,
+      "step": 4620
+    },
+    {
+      "epoch": 0.9347634069400631,
+      "grad_norm": 0.4562802443840814,
+      "learning_rate": 1.30565101248048e-07,
+      "loss": 0.4385,
+      "step": 4630
+    },
+    {
+      "epoch": 0.936782334384858,
+      "grad_norm": 0.4578530629768795,
+      "learning_rate": 1.226864558700541e-07,
+      "loss": 0.4416,
+      "step": 4640
+    },
+    {
+      "epoch": 0.938801261829653,
+      "grad_norm": 0.4951660779551572,
+      "learning_rate": 1.1505002407579512e-07,
+      "loss": 0.4424,
+      "step": 4650
+    },
+    {
+      "epoch": 0.940820189274448,
+      "grad_norm": 0.44757841438265406,
+      "learning_rate": 1.0765618510017118e-07,
+      "loss": 0.4368,
+      "step": 4660
+    },
+    {
+      "epoch": 0.9428391167192429,
+      "grad_norm": 1.5035499500846865,
+      "learning_rate": 1.0050530613061327e-07,
+      "loss": 0.4353,
+      "step": 4670
+    },
+    {
+      "epoch": 0.9448580441640378,
+      "grad_norm": 0.4938389329390479,
+      "learning_rate": 9.359774228885177e-08,
+      "loss": 0.4391,
+      "step": 4680
+    },
+    {
+      "epoch": 0.9468769716088328,
+      "grad_norm": 0.4711850612472287,
+      "learning_rate": 8.693383661327882e-08,
+      "loss": 0.4388,
+      "step": 4690
+    },
+    {
+      "epoch": 0.9488958990536278,
+      "grad_norm": 0.48652374519922575,
+      "learning_rate": 8.051392004191139e-08,
+      "loss": 0.4486,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9509148264984227,
+      "grad_norm": 0.4473704324045684,
+      "learning_rate": 7.433831139595727e-08,
+      "loss": 0.4385,
+      "step": 4710
+    },
+    {
+      "epoch": 0.9529337539432177,
+      "grad_norm": 0.509944701555344,
+      "learning_rate": 6.840731736398542e-08,
+      "loss": 0.4362,
+      "step": 4720
+    },
+    {
+      "epoch": 0.9549526813880126,
+      "grad_norm": 0.4468123798191573,
+      "learning_rate": 6.272123248668993e-08,
+      "loss": 0.4356,
+      "step": 4730
+    },
+    {
+      "epoch": 0.9569716088328075,
+      "grad_norm": 0.4432856047100861,
+      "learning_rate": 5.728033914226494e-08,
+      "loss": 0.4406,
+      "step": 4740
+    },
+    {
+      "epoch": 0.9589905362776026,
+      "grad_norm": 0.8312641118207356,
+      "learning_rate": 5.2084907532383156e-08,
+      "loss": 0.4457,
+      "step": 4750
+    },
+    {
+      "epoch": 0.9610094637223975,
+      "grad_norm": 0.4308428180533281,
+      "learning_rate": 4.7135195668776e-08,
+      "loss": 0.4337,
+      "step": 4760
+    },
+    {
+      "epoch": 0.9630283911671924,
+      "grad_norm": 0.47706748470749133,
+      "learning_rate": 4.243144936041943e-08,
+      "loss": 0.4413,
+      "step": 4770
+    },
+    {
+      "epoch": 0.9650473186119873,
+      "grad_norm": 0.46426542825118344,
+      "learning_rate": 3.797390220132757e-08,
+      "loss": 0.4325,
+      "step": 4780
+    },
+    {
+      "epoch": 0.9670662460567824,
+      "grad_norm": 0.4324982289321672,
+      "learning_rate": 3.3762775558952576e-08,
+      "loss": 0.4377,
+      "step": 4790
+    },
+    {
+      "epoch": 0.9690851735015773,
+      "grad_norm": 0.47719223462129745,
+      "learning_rate": 2.9798278563190618e-08,
+      "loss": 0.4439,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9711041009463722,
+      "grad_norm": 0.4540530080947163,
+      "learning_rate": 2.6080608095997438e-08,
+      "loss": 0.4377,
+      "step": 4810
+    },
+    {
+      "epoch": 0.9731230283911672,
+      "grad_norm": 0.4413909184803219,
+      "learning_rate": 2.2609948781607827e-08,
+      "loss": 0.4424,
+      "step": 4820
+    },
+    {
+      "epoch": 0.9751419558359622,
+      "grad_norm": 0.4712177319951425,
+      "learning_rate": 1.9386472977370728e-08,
+      "loss": 0.4412,
+      "step": 4830
+    },
+    {
+      "epoch": 0.9771608832807571,
+      "grad_norm": 0.443140708468747,
+      "learning_rate": 1.6410340765187772e-08,
+      "loss": 0.4382,
+      "step": 4840
+    },
+    {
+      "epoch": 0.979179810725552,
+      "grad_norm": 0.4782858905945508,
+      "learning_rate": 1.3681699943564053e-08,
+      "loss": 0.4387,
+      "step": 4850
+    },
+    {
+      "epoch": 0.981198738170347,
+      "grad_norm": 0.6206662222549734,
+      "learning_rate": 1.1200686020266805e-08,
+      "loss": 0.4431,
+      "step": 4860
+    },
+    {
+      "epoch": 0.983217665615142,
+      "grad_norm": 2.8460570799996985,
+      "learning_rate": 8.967422205598541e-09,
+      "loss": 0.4393,
+      "step": 4870
+    },
+    {
+      "epoch": 0.9852365930599369,
+      "grad_norm": 0.4435087118229933,
+      "learning_rate": 6.982019406275853e-09,
+      "loss": 0.436,
+      "step": 4880
+    },
+    {
+      "epoch": 0.9872555205047319,
+      "grad_norm": 0.4300508595922509,
+      "learning_rate": 5.244576219922693e-09,
+      "loss": 0.4316,
+      "step": 4890
+    },
+    {
+      "epoch": 0.9892744479495268,
+      "grad_norm": 0.49712300151356087,
+      "learning_rate": 3.755178930173742e-09,
+      "loss": 0.4463,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9912933753943217,
+      "grad_norm": 0.4798533947795922,
+      "learning_rate": 2.513901502389504e-09,
+      "loss": 0.4327,
+      "step": 4910
+    },
+    {
+      "epoch": 0.9933123028391168,
+      "grad_norm": 0.4936501161499046,
+      "learning_rate": 1.520805579983131e-09,
+      "loss": 0.4403,
+      "step": 4920
+    },
+    {
+      "epoch": 0.9953312302839117,
+      "grad_norm": 0.4638813307919199,
+      "learning_rate": 7.759404813600935e-10,
+      "loss": 0.4385,
+      "step": 4930
+    },
+    {
+      "epoch": 0.9973501577287066,
+      "grad_norm": 0.43789683220104403,
+      "learning_rate": 2.7934319746625306e-10,
+      "loss": 0.4387,
+      "step": 4940
+    },
+    {
+      "epoch": 0.9993690851735015,
+      "grad_norm": 0.4980004114526748,
+      "learning_rate": 3.103838995321962e-11,
+      "loss": 0.4391,
+      "step": 4950
+    },
+    {
+      "epoch": 1.0,
+      "step": 4954,
+      "total_flos": 1.1092292323919266e+19,
+      "train_loss": 0.46906891030845593,
+      "train_runtime": 81648.0087,
+      "train_samples_per_second": 7.765,
+      "train_steps_per_second": 0.061
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4954,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1092292323919266e+19,
+  "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 sha256:812409ecb32d8b6ca20e2ea10e260d5e87968d1c1e0f5a1c678da806fc4ddf59
+size 8209