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-num06
+  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-num06
+
+This model is a fine-tuned version of [/mmu-vcg-hdd/multimodal/models/Qwen2.5-Coder-7B-Instruct](https://huggingface.co//mmu-vcg-hdd/multimodal/models/Qwen2.5-Coder-7B-Instruct) on 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": 8.530187773318005e+18,
+    "train_loss": 0.4728999632081421,
+    "train_runtime": 62323.8697,
+    "train_samples_per_second": 6.767,
+    "train_steps_per_second": 0.053
+}

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:becdeef6875cb146a4ff27a6becb82c3e74254bf701d58d6dfb802c8f05d21d4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3414b56c79e3cd1950fb15c262e8cc166de299b3cd149381cd0399320d582ee
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9d0127945f7fbb1af0303f6faa12f61e50fec41c25b9d34443f0ec86a20a08
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2387cef64dc2a88fbab3f9f9b67cfe9c4aa0059a4de29d38c28e9ed59012a034
+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": 8.530187773318005e+18,
+    "train_loss": 0.4728999632081421,
+    "train_runtime": 62323.8697,
+    "train_samples_per_second": 6.767,
+    "train_steps_per_second": 0.053
+}

trainer_log.jsonl

@@ -0,0 +1,330 @@
+{"current_steps": 10, "total_steps": 3295, "loss": 0.789, "lr": 2.7272727272727274e-07, "epoch": 0.0030350165029022344, "percentage": 0.3, "elapsed_time": "0:15:07", "remaining_time": "3 days, 10:47:43"}
+{"current_steps": 20, "total_steps": 3295, "loss": 0.7904, "lr": 5.757575757575758e-07, "epoch": 0.006070033005804469, "percentage": 0.61, "elapsed_time": "0:29:14", "remaining_time": "3 days, 7:49:16"}
+{"current_steps": 30, "total_steps": 3295, "loss": 0.744, "lr": 8.787878787878788e-07, "epoch": 0.009105049508706704, "percentage": 0.91, "elapsed_time": "0:43:09", "remaining_time": "3 days, 6:17:00"}
+{"current_steps": 40, "total_steps": 3295, "loss": 0.693, "lr": 1.181818181818182e-06, "epoch": 0.012140066011608937, "percentage": 1.21, "elapsed_time": "0:57:52", "remaining_time": "3 days, 6:28:56"}
+{"current_steps": 50, "total_steps": 3295, "loss": 0.6656, "lr": 1.484848484848485e-06, "epoch": 0.015175082514511173, "percentage": 1.52, "elapsed_time": "1:05:27", "remaining_time": "2 days, 22:48:31"}
+{"current_steps": 60, "total_steps": 3295, "loss": 0.6313, "lr": 1.787878787878788e-06, "epoch": 0.018210099017413408, "percentage": 1.82, "elapsed_time": "1:08:46", "remaining_time": "2 days, 13:47:58"}
+{"current_steps": 70, "total_steps": 3295, "loss": 0.6098, "lr": 2.090909090909091e-06, "epoch": 0.021245115520315643, "percentage": 2.12, "elapsed_time": "1:11:52", "remaining_time": "2 days, 7:11:19"}
+{"current_steps": 80, "total_steps": 3295, "loss": 0.5885, "lr": 2.393939393939394e-06, "epoch": 0.024280132023217875, "percentage": 2.43, "elapsed_time": "1:14:43", "remaining_time": "2 days, 2:03:12"}
+{"current_steps": 90, "total_steps": 3295, "loss": 0.5916, "lr": 2.6969696969696972e-06, "epoch": 0.02731514852612011, "percentage": 2.73, "elapsed_time": "1:18:02", "remaining_time": "1 day, 22:19:15"}
+{"current_steps": 100, "total_steps": 3295, "loss": 0.5753, "lr": 3e-06, "epoch": 0.030350165029022345, "percentage": 3.03, "elapsed_time": "1:20:42", "remaining_time": "1 day, 18:58:48"}
+{"current_steps": 110, "total_steps": 3295, "loss": 0.5597, "lr": 3.3030303030303033e-06, "epoch": 0.03338518153192458, "percentage": 3.34, "elapsed_time": "1:24:02", "remaining_time": "1 day, 16:33:19"}
+{"current_steps": 120, "total_steps": 3295, "loss": 0.5684, "lr": 3.606060606060606e-06, "epoch": 0.036420198034826816, "percentage": 3.64, "elapsed_time": "1:27:04", "remaining_time": "1 day, 14:23:39"}
+{"current_steps": 130, "total_steps": 3295, "loss": 0.5569, "lr": 3.90909090909091e-06, "epoch": 0.03945521453772905, "percentage": 3.95, "elapsed_time": "1:29:56", "remaining_time": "1 day, 12:29:46"}
+{"current_steps": 140, "total_steps": 3295, "loss": 0.5551, "lr": 4.212121212121212e-06, "epoch": 0.042490231040631286, "percentage": 4.25, "elapsed_time": "1:33:06", "remaining_time": "1 day, 10:58:24"}
+{"current_steps": 150, "total_steps": 3295, "loss": 0.5565, "lr": 4.5151515151515155e-06, "epoch": 0.045525247543533515, "percentage": 4.55, "elapsed_time": "1:35:49", "remaining_time": "1 day, 9:28:58"}
+{"current_steps": 160, "total_steps": 3295, "loss": 0.5482, "lr": 4.818181818181819e-06, "epoch": 0.04856026404643575, "percentage": 4.86, "elapsed_time": "1:39:06", "remaining_time": "1 day, 8:21:50"}
+{"current_steps": 170, "total_steps": 3295, "loss": 0.5482, "lr": 5.121212121212121e-06, "epoch": 0.051595280549337985, "percentage": 5.16, "elapsed_time": "1:42:05", "remaining_time": "1 day, 7:16:38"}
+{"current_steps": 180, "total_steps": 3295, "loss": 0.5397, "lr": 5.424242424242425e-06, "epoch": 0.05463029705224022, "percentage": 5.46, "elapsed_time": "1:44:58", "remaining_time": "1 day, 6:16:47"}
+{"current_steps": 190, "total_steps": 3295, "loss": 0.5379, "lr": 5.727272727272728e-06, "epoch": 0.057665313555142456, "percentage": 5.77, "elapsed_time": "1:48:10", "remaining_time": "1 day, 5:27:41"}
+{"current_steps": 200, "total_steps": 3295, "loss": 0.5487, "lr": 6.030303030303031e-06, "epoch": 0.06070033005804469, "percentage": 6.07, "elapsed_time": "1:50:46", "remaining_time": "1 day, 4:34:15"}
+{"current_steps": 210, "total_steps": 3295, "loss": 0.5354, "lr": 6.333333333333333e-06, "epoch": 0.06373534656094693, "percentage": 6.37, "elapsed_time": "1:54:05", "remaining_time": "1 day, 3:55:59"}
+{"current_steps": 220, "total_steps": 3295, "loss": 0.5321, "lr": 6.6363636363636375e-06, "epoch": 0.06677036306384916, "percentage": 6.68, "elapsed_time": "1:57:12", "remaining_time": "1 day, 3:18:18"}
+{"current_steps": 230, "total_steps": 3295, "loss": 0.5286, "lr": 6.93939393939394e-06, "epoch": 0.0698053795667514, "percentage": 6.98, "elapsed_time": "2:00:02", "remaining_time": "1 day, 2:39:38"}
+{"current_steps": 240, "total_steps": 3295, "loss": 0.5277, "lr": 7.242424242424243e-06, "epoch": 0.07284039606965363, "percentage": 7.28, "elapsed_time": "2:03:12", "remaining_time": "1 day, 2:08:24"}
+{"current_steps": 250, "total_steps": 3295, "loss": 0.5333, "lr": 7.545454545454546e-06, "epoch": 0.07587541257255587, "percentage": 7.59, "elapsed_time": "2:05:51", "remaining_time": "1 day, 1:32:56"}
+{"current_steps": 260, "total_steps": 3295, "loss": 0.5272, "lr": 7.848484848484849e-06, "epoch": 0.0789104290754581, "percentage": 7.89, "elapsed_time": "2:09:08", "remaining_time": "1 day, 1:07:27"}
+{"current_steps": 270, "total_steps": 3295, "loss": 0.5283, "lr": 8.151515151515152e-06, "epoch": 0.08194544557836034, "percentage": 8.19, "elapsed_time": "2:12:08", "remaining_time": "1 day, 0:40:30"}
+{"current_steps": 280, "total_steps": 3295, "loss": 0.5212, "lr": 8.454545454545455e-06, "epoch": 0.08498046208126257, "percentage": 8.5, "elapsed_time": "2:14:57", "remaining_time": "1 day, 0:13:15"}
+{"current_steps": 290, "total_steps": 3295, "loss": 0.5161, "lr": 8.757575757575759e-06, "epoch": 0.08801547858416481, "percentage": 8.8, "elapsed_time": "2:18:12", "remaining_time": "23:52:06"}
+{"current_steps": 300, "total_steps": 3295, "loss": 0.5281, "lr": 9.06060606060606e-06, "epoch": 0.09105049508706703, "percentage": 9.1, "elapsed_time": "2:20:51", "remaining_time": "23:26:09"}
+{"current_steps": 310, "total_steps": 3295, "loss": 0.5154, "lr": 9.363636363636365e-06, "epoch": 0.09408551158996926, "percentage": 9.41, "elapsed_time": "2:24:02", "remaining_time": "23:07:03"}
+{"current_steps": 320, "total_steps": 3295, "loss": 0.5218, "lr": 9.666666666666667e-06, "epoch": 0.0971205280928715, "percentage": 9.71, "elapsed_time": "2:27:05", "remaining_time": "22:47:29"}
+{"current_steps": 330, "total_steps": 3295, "loss": 0.5169, "lr": 9.96969696969697e-06, "epoch": 0.10015554459577374, "percentage": 10.02, "elapsed_time": "2:30:00", "remaining_time": "22:27:49"}
+{"current_steps": 340, "total_steps": 3295, "loss": 0.5133, "lr": 9.999772661973056e-06, "epoch": 0.10319056109867597, "percentage": 10.32, "elapsed_time": "2:33:14", "remaining_time": "22:11:50"}
+{"current_steps": 350, "total_steps": 3295, "loss": 0.52, "lr": 9.99898682866784e-06, "epoch": 0.1062255776015782, "percentage": 10.62, "elapsed_time": "2:35:48", "remaining_time": "21:51:03"}
+{"current_steps": 360, "total_steps": 3295, "loss": 0.5008, "lr": 9.997639781643002e-06, "epoch": 0.10926059410448044, "percentage": 10.93, "elapsed_time": "2:39:03", "remaining_time": "21:36:42"}
+{"current_steps": 370, "total_steps": 3295, "loss": 0.517, "lr": 9.99573167212544e-06, "epoch": 0.11229561060738268, "percentage": 11.23, "elapsed_time": "2:42:10", "remaining_time": "21:22:01"}
+{"current_steps": 380, "total_steps": 3295, "loss": 0.5092, "lr": 9.993262714330009e-06, "epoch": 0.11533062711028491, "percentage": 11.53, "elapsed_time": "2:44:57", "remaining_time": "21:05:23"}
+{"current_steps": 390, "total_steps": 3295, "loss": 0.513, "lr": 9.990233185435473e-06, "epoch": 0.11836564361318715, "percentage": 11.84, "elapsed_time": "2:48:05", "remaining_time": "20:52:06"}
+{"current_steps": 400, "total_steps": 3295, "loss": 0.5129, "lr": 9.986643425553386e-06, "epoch": 0.12140066011608938, "percentage": 12.14, "elapsed_time": "2:50:45", "remaining_time": "20:35:49"}
+{"current_steps": 410, "total_steps": 3295, "loss": 0.5073, "lr": 9.98249383768991e-06, "epoch": 0.12443567661899162, "percentage": 12.44, "elapsed_time": "2:53:54", "remaining_time": "20:23:41"}
+{"current_steps": 420, "total_steps": 3295, "loss": 0.5088, "lr": 9.977784887700572e-06, "epoch": 0.12747069312189385, "percentage": 12.75, "elapsed_time": "2:56:55", "remaining_time": "20:11:08"}
+{"current_steps": 430, "total_steps": 3295, "loss": 0.4991, "lr": 9.972517104237961e-06, "epoch": 0.13050570962479607, "percentage": 13.05, "elapsed_time": "2:59:43", "remaining_time": "19:57:30"}
+{"current_steps": 440, "total_steps": 3295, "loss": 0.506, "lr": 9.966691078692386e-06, "epoch": 0.13354072612769832, "percentage": 13.35, "elapsed_time": "3:02:57", "remaining_time": "19:47:10"}
+{"current_steps": 450, "total_steps": 3295, "loss": 0.5025, "lr": 9.960307465125472e-06, "epoch": 0.13657574263060054, "percentage": 13.66, "elapsed_time": "3:05:37", "remaining_time": "19:33:36"}
+{"current_steps": 460, "total_steps": 3295, "loss": 0.4976, "lr": 9.953366980196746e-06, "epoch": 0.1396107591335028, "percentage": 13.96, "elapsed_time": "3:08:55", "remaining_time": "19:24:19"}
+{"current_steps": 470, "total_steps": 3295, "loss": 0.503, "lr": 9.945870403083164e-06, "epoch": 0.14264577563640501, "percentage": 14.26, "elapsed_time": "3:12:00", "remaining_time": "19:14:05"}
+{"current_steps": 480, "total_steps": 3295, "loss": 0.5044, "lr": 9.937818575391654e-06, "epoch": 0.14568079213930726, "percentage": 14.57, "elapsed_time": "3:14:50", "remaining_time": "19:02:41"}
+{"current_steps": 490, "total_steps": 3295, "loss": 0.505, "lr": 9.929212401064616e-06, "epoch": 0.14871580864220948, "percentage": 14.87, "elapsed_time": "3:17:58", "remaining_time": "18:53:20"}
+{"current_steps": 500, "total_steps": 3295, "loss": 0.4991, "lr": 9.920052846278455e-06, "epoch": 0.15175082514511173, "percentage": 15.17, "elapsed_time": "3:20:33", "remaining_time": "18:41:05"}
+{"current_steps": 510, "total_steps": 3295, "loss": 0.4889, "lr": 9.910340939335098e-06, "epoch": 0.15478584164801396, "percentage": 15.48, "elapsed_time": "3:23:50", "remaining_time": "18:33:06"}
+{"current_steps": 520, "total_steps": 3295, "loss": 0.488, "lr": 9.900077770546567e-06, "epoch": 0.1578208581509162, "percentage": 15.78, "elapsed_time": "3:26:54", "remaining_time": "18:24:12"}
+{"current_steps": 530, "total_steps": 3295, "loss": 0.5025, "lr": 9.889264492112563e-06, "epoch": 0.16085587465381843, "percentage": 16.08, "elapsed_time": "3:29:44", "remaining_time": "18:14:12"}
+{"current_steps": 540, "total_steps": 3295, "loss": 0.4946, "lr": 9.877902317991116e-06, "epoch": 0.16389089115672067, "percentage": 16.39, "elapsed_time": "3:33:00", "remaining_time": "18:06:42"}
+{"current_steps": 550, "total_steps": 3295, "loss": 0.4989, "lr": 9.865992523762306e-06, "epoch": 0.1669259076596229, "percentage": 16.69, "elapsed_time": "3:35:39", "remaining_time": "17:56:17"}
+{"current_steps": 560, "total_steps": 3295, "loss": 0.503, "lr": 9.853536446485048e-06, "epoch": 0.16996092416252515, "percentage": 17.0, "elapsed_time": "3:38:52", "remaining_time": "17:48:57"}
+{"current_steps": 570, "total_steps": 3295, "loss": 0.4903, "lr": 9.840535484546996e-06, "epoch": 0.17299594066542737, "percentage": 17.3, "elapsed_time": "3:41:51", "remaining_time": "17:40:40"}
+{"current_steps": 580, "total_steps": 3295, "loss": 0.4958, "lr": 9.826991097507548e-06, "epoch": 0.17603095716832962, "percentage": 17.6, "elapsed_time": "3:44:40", "remaining_time": "17:31:42"}
+{"current_steps": 590, "total_steps": 3295, "loss": 0.4922, "lr": 9.812904805933989e-06, "epoch": 0.17906597367123184, "percentage": 17.91, "elapsed_time": "3:47:52", "remaining_time": "17:24:43"}
+{"current_steps": 600, "total_steps": 3295, "loss": 0.5004, "lr": 9.798278191230783e-06, "epoch": 0.18210099017413406, "percentage": 18.21, "elapsed_time": "3:50:32", "remaining_time": "17:15:30"}
+{"current_steps": 610, "total_steps": 3295, "loss": 0.4802, "lr": 9.78311289546204e-06, "epoch": 0.1851360066770363, "percentage": 18.51, "elapsed_time": "3:53:51", "remaining_time": "17:09:20"}
+{"current_steps": 620, "total_steps": 3295, "loss": 0.4945, "lr": 9.76741062116716e-06, "epoch": 0.18817102317993853, "percentage": 18.82, "elapsed_time": "3:56:52", "remaining_time": "17:02:00"}
+{"current_steps": 630, "total_steps": 3295, "loss": 0.4906, "lr": 9.751173131169705e-06, "epoch": 0.19120603968284078, "percentage": 19.12, "elapsed_time": "3:59:45", "remaining_time": "16:54:11"}
+{"current_steps": 640, "total_steps": 3295, "loss": 0.496, "lr": 9.73440224837949e-06, "epoch": 0.194241056185743, "percentage": 19.42, "elapsed_time": "4:03:03", "remaining_time": "16:48:17"}
+{"current_steps": 650, "total_steps": 3295, "loss": 0.486, "lr": 9.717099855587935e-06, "epoch": 0.19727607268864525, "percentage": 19.73, "elapsed_time": "4:05:43", "remaining_time": "16:39:55"}
+{"current_steps": 660, "total_steps": 3295, "loss": 0.4769, "lr": 9.699267895256695e-06, "epoch": 0.20031108919154747, "percentage": 20.03, "elapsed_time": "4:09:07", "remaining_time": "16:34:36"}
+{"current_steps": 670, "total_steps": 3295, "loss": 0.4918, "lr": 9.68090836929958e-06, "epoch": 0.20334610569444972, "percentage": 20.33, "elapsed_time": "4:12:10", "remaining_time": "16:27:58"}
+{"current_steps": 680, "total_steps": 3295, "loss": 0.485, "lr": 9.662023338857822e-06, "epoch": 0.20638112219735194, "percentage": 20.64, "elapsed_time": "4:14:56", "remaining_time": "16:20:23"}
+{"current_steps": 690, "total_steps": 3295, "loss": 0.4902, "lr": 9.642614924068667e-06, "epoch": 0.2094161387002542, "percentage": 20.94, "elapsed_time": "4:18:07", "remaining_time": "16:14:29"}
+{"current_steps": 700, "total_steps": 3295, "loss": 0.4881, "lr": 9.622685303827366e-06, "epoch": 0.2124511552031564, "percentage": 21.24, "elapsed_time": "4:20:41", "remaining_time": "16:06:24"}
+{"current_steps": 710, "total_steps": 3295, "loss": 0.4848, "lr": 9.602236715542557e-06, "epoch": 0.21548617170605866, "percentage": 21.55, "elapsed_time": "4:23:57", "remaining_time": "16:01:03"}
+{"current_steps": 720, "total_steps": 3295, "loss": 0.4903, "lr": 9.581271454885077e-06, "epoch": 0.21852118820896088, "percentage": 21.85, "elapsed_time": "4:27:01", "remaining_time": "15:54:57"}
+{"current_steps": 730, "total_steps": 3295, "loss": 0.489, "lr": 9.559791875530247e-06, "epoch": 0.22155620471186313, "percentage": 22.15, "elapsed_time": "4:29:52", "remaining_time": "15:48:15"}
+{"current_steps": 740, "total_steps": 3295, "loss": 0.4864, "lr": 9.537800388893628e-06, "epoch": 0.22459122121476535, "percentage": 22.46, "elapsed_time": "4:33:03", "remaining_time": "15:42:48"}
+{"current_steps": 750, "total_steps": 3295, "loss": 0.4858, "lr": 9.515299463860301e-06, "epoch": 0.2276262377176676, "percentage": 22.76, "elapsed_time": "4:35:40", "remaining_time": "15:35:29"}
+{"current_steps": 760, "total_steps": 3295, "loss": 0.4874, "lr": 9.492291626507705e-06, "epoch": 0.23066125422056982, "percentage": 23.07, "elapsed_time": "4:38:55", "remaining_time": "15:30:20"}
+{"current_steps": 770, "total_steps": 3295, "loss": 0.4865, "lr": 9.468779459822034e-06, "epoch": 0.23369627072347207, "percentage": 23.37, "elapsed_time": "4:42:03", "remaining_time": "15:24:56"}
+{"current_steps": 780, "total_steps": 3295, "loss": 0.4834, "lr": 9.444765603408273e-06, "epoch": 0.2367312872263743, "percentage": 23.67, "elapsed_time": "4:44:56", "remaining_time": "15:18:43"}
+{"current_steps": 790, "total_steps": 3295, "loss": 0.4725, "lr": 9.420252753193842e-06, "epoch": 0.23976630372927651, "percentage": 23.98, "elapsed_time": "4:48:13", "remaining_time": "15:13:54"}
+{"current_steps": 800, "total_steps": 3295, "loss": 0.4882, "lr": 9.395243661125948e-06, "epoch": 0.24280132023217876, "percentage": 24.28, "elapsed_time": "4:50:54", "remaining_time": "15:07:14"}
+{"current_steps": 810, "total_steps": 3295, "loss": 0.4752, "lr": 9.369741134862636e-06, "epoch": 0.24583633673508098, "percentage": 24.58, "elapsed_time": "4:54:10", "remaining_time": "15:02:30"}
+{"current_steps": 820, "total_steps": 3295, "loss": 0.4869, "lr": 9.343748037457585e-06, "epoch": 0.24887135323798323, "percentage": 24.89, "elapsed_time": "4:57:06", "remaining_time": "14:56:45"}
+{"current_steps": 830, "total_steps": 3295, "loss": 0.4884, "lr": 9.317267287038682e-06, "epoch": 0.2519063697408855, "percentage": 25.19, "elapsed_time": "4:59:53", "remaining_time": "14:50:37"}
+{"current_steps": 840, "total_steps": 3295, "loss": 0.4797, "lr": 9.290301856480425e-06, "epoch": 0.2549413862437877, "percentage": 25.49, "elapsed_time": "5:03:04", "remaining_time": "14:45:46"}
+{"current_steps": 850, "total_steps": 3295, "loss": 0.4869, "lr": 9.262854773070157e-06, "epoch": 0.2579764027466899, "percentage": 25.8, "elapsed_time": "5:05:43", "remaining_time": "14:39:24"}
+{"current_steps": 860, "total_steps": 3295, "loss": 0.4712, "lr": 9.234929118168228e-06, "epoch": 0.26101141924959215, "percentage": 26.1, "elapsed_time": "5:09:03", "remaining_time": "14:35:04"}
+{"current_steps": 870, "total_steps": 3295, "loss": 0.4765, "lr": 9.206528026862043e-06, "epoch": 0.2640464357524944, "percentage": 26.4, "elapsed_time": "5:12:06", "remaining_time": "14:29:57"}
+{"current_steps": 880, "total_steps": 3295, "loss": 0.4824, "lr": 9.177654687614112e-06, "epoch": 0.26708145225539665, "percentage": 26.71, "elapsed_time": "5:14:53", "remaining_time": "14:24:08"}
+{"current_steps": 890, "total_steps": 3295, "loss": 0.4768, "lr": 9.148312341904095e-06, "epoch": 0.27011646875829887, "percentage": 27.01, "elapsed_time": "5:18:03", "remaining_time": "14:19:29"}
+{"current_steps": 900, "total_steps": 3295, "loss": 0.4763, "lr": 9.118504283864891e-06, "epoch": 0.2731514852612011, "percentage": 27.31, "elapsed_time": "5:20:40", "remaining_time": "14:13:20"}
+{"current_steps": 910, "total_steps": 3295, "loss": 0.4774, "lr": 9.088233859912823e-06, "epoch": 0.27618650176410336, "percentage": 27.62, "elapsed_time": "5:23:59", "remaining_time": "14:09:08"}
+{"current_steps": 920, "total_steps": 3295, "loss": 0.4774, "lr": 9.057504468371954e-06, "epoch": 0.2792215182670056, "percentage": 27.92, "elapsed_time": "5:27:00", "remaining_time": "14:04:10"}
+{"current_steps": 930, "total_steps": 3295, "loss": 0.4822, "lr": 9.026319559092566e-06, "epoch": 0.2822565347699078, "percentage": 28.22, "elapsed_time": "5:29:49", "remaining_time": "13:58:45"}
+{"current_steps": 940, "total_steps": 3295, "loss": 0.4737, "lr": 8.994682633063868e-06, "epoch": 0.28529155127281003, "percentage": 28.53, "elapsed_time": "5:33:03", "remaining_time": "13:54:25"}
+{"current_steps": 950, "total_steps": 3295, "loss": 0.4772, "lr": 8.962597242020947e-06, "epoch": 0.2883265677757123, "percentage": 28.83, "elapsed_time": "5:35:43", "remaining_time": "13:48:43"}
+{"current_steps": 960, "total_steps": 3295, "loss": 0.4688, "lr": 8.930066988046042e-06, "epoch": 0.2913615842786145, "percentage": 29.14, "elapsed_time": "5:39:03", "remaining_time": "13:44:41"}
+{"current_steps": 970, "total_steps": 3295, "loss": 0.4742, "lr": 8.897095523164141e-06, "epoch": 0.29439660078151675, "percentage": 29.44, "elapsed_time": "5:42:08", "remaining_time": "13:40:05"}
+{"current_steps": 980, "total_steps": 3295, "loss": 0.4786, "lr": 8.863686548933001e-06, "epoch": 0.29743161728441897, "percentage": 29.74, "elapsed_time": "5:44:57", "remaining_time": "13:34:52"}
+{"current_steps": 990, "total_steps": 3295, "loss": 0.4706, "lr": 8.829843816027575e-06, "epoch": 0.3004666337873212, "percentage": 30.05, "elapsed_time": "5:48:14", "remaining_time": "13:30:47"}
+{"current_steps": 1000, "total_steps": 3295, "loss": 0.4733, "lr": 8.795571123818948e-06, "epoch": 0.30350165029022347, "percentage": 30.35, "elapsed_time": "5:50:57", "remaining_time": "13:25:26"}
+{"current_steps": 1010, "total_steps": 3295, "loss": 0.467, "lr": 8.760872319947796e-06, "epoch": 0.3065366667931257, "percentage": 30.65, "elapsed_time": "5:54:15", "remaining_time": "13:21:27"}
+{"current_steps": 1020, "total_steps": 3295, "loss": 0.4714, "lr": 8.72575129989244e-06, "epoch": 0.3095716832960279, "percentage": 30.96, "elapsed_time": "5:57:16", "remaining_time": "13:16:52"}
+{"current_steps": 1030, "total_steps": 3295, "loss": 0.4778, "lr": 8.690212006531498e-06, "epoch": 0.31260669979893013, "percentage": 31.26, "elapsed_time": "6:00:06", "remaining_time": "13:11:53"}
+{"current_steps": 1040, "total_steps": 3295, "loss": 0.4766, "lr": 8.654258429701254e-06, "epoch": 0.3156417163018324, "percentage": 31.56, "elapsed_time": "6:03:21", "remaining_time": "13:07:51"}
+{"current_steps": 1050, "total_steps": 3295, "loss": 0.471, "lr": 8.617894605747728e-06, "epoch": 0.31867673280473463, "percentage": 31.87, "elapsed_time": "6:06:00", "remaining_time": "13:02:33"}
+{"current_steps": 1060, "total_steps": 3295, "loss": 0.4754, "lr": 8.581124617073531e-06, "epoch": 0.32171174930763685, "percentage": 32.17, "elapsed_time": "6:09:12", "remaining_time": "12:58:27"}
+{"current_steps": 1070, "total_steps": 3295, "loss": 0.4757, "lr": 8.543952591679565e-06, "epoch": 0.3247467658105391, "percentage": 32.47, "elapsed_time": "6:12:11", "remaining_time": "12:53:56"}
+{"current_steps": 1080, "total_steps": 3295, "loss": 0.4682, "lr": 8.506382702701575e-06, "epoch": 0.32778178231344135, "percentage": 32.78, "elapsed_time": "6:14:58", "remaining_time": "12:49:03"}
+{"current_steps": 1090, "total_steps": 3295, "loss": 0.4631, "lr": 8.468419167941658e-06, "epoch": 0.33081679881634357, "percentage": 33.08, "elapsed_time": "6:18:11", "remaining_time": "12:45:03"}
+{"current_steps": 1100, "total_steps": 3295, "loss": 0.4786, "lr": 8.430066249394754e-06, "epoch": 0.3338518153192458, "percentage": 33.38, "elapsed_time": "6:20:45", "remaining_time": "12:39:47"}
+{"current_steps": 1110, "total_steps": 3295, "loss": 0.4648, "lr": 8.391328252770165e-06, "epoch": 0.336886831822148, "percentage": 33.69, "elapsed_time": "6:24:04", "remaining_time": "12:36:01"}
+{"current_steps": 1120, "total_steps": 3295, "loss": 0.4785, "lr": 8.352209527008164e-06, "epoch": 0.3399218483250503, "percentage": 33.99, "elapsed_time": "6:27:05", "remaining_time": "12:31:43"}
+{"current_steps": 1130, "total_steps": 3295, "loss": 0.4684, "lr": 8.31271446379178e-06, "epoch": 0.3429568648279525, "percentage": 34.29, "elapsed_time": "6:29:53", "remaining_time": "12:27:01"}
+{"current_steps": 1140, "total_steps": 3295, "loss": 0.467, "lr": 8.272847497053745e-06, "epoch": 0.34599188133085473, "percentage": 34.6, "elapsed_time": "6:33:08", "remaining_time": "12:23:10"}
+{"current_steps": 1150, "total_steps": 3295, "loss": 0.4734, "lr": 8.232613102478722e-06, "epoch": 0.34902689783375695, "percentage": 34.9, "elapsed_time": "6:35:44", "remaining_time": "12:18:08"}
+{"current_steps": 1160, "total_steps": 3295, "loss": 0.4634, "lr": 8.192015797000849e-06, "epoch": 0.35206191433665923, "percentage": 35.2, "elapsed_time": "6:38:57", "remaining_time": "12:14:16"}
+{"current_steps": 1170, "total_steps": 3295, "loss": 0.4769, "lr": 8.151060138296624e-06, "epoch": 0.35509693083956145, "percentage": 35.51, "elapsed_time": "6:41:56", "remaining_time": "12:10:01"}
+{"current_steps": 1180, "total_steps": 3295, "loss": 0.4631, "lr": 8.10975072427326e-06, "epoch": 0.3581319473424637, "percentage": 35.81, "elapsed_time": "6:44:51", "remaining_time": "12:05:38"}
+{"current_steps": 1190, "total_steps": 3295, "loss": 0.4621, "lr": 8.068092192552473e-06, "epoch": 0.3611669638453659, "percentage": 36.12, "elapsed_time": "6:48:02", "remaining_time": "12:01:47"}
+{"current_steps": 1200, "total_steps": 3295, "loss": 0.4707, "lr": 8.026089219949856e-06, "epoch": 0.3642019803482681, "percentage": 36.42, "elapsed_time": "6:50:42", "remaining_time": "11:57:01"}
+{"current_steps": 1210, "total_steps": 3295, "loss": 0.4691, "lr": 7.983746521949822e-06, "epoch": 0.3672369968511704, "percentage": 36.72, "elapsed_time": "6:53:59", "remaining_time": "11:53:21"}
+{"current_steps": 1220, "total_steps": 3295, "loss": 0.4673, "lr": 7.941068852176233e-06, "epoch": 0.3702720133540726, "percentage": 37.03, "elapsed_time": "6:57:00", "remaining_time": "11:49:15"}
+{"current_steps": 1230, "total_steps": 3295, "loss": 0.4652, "lr": 7.898061001858712e-06, "epoch": 0.37330702985697484, "percentage": 37.33, "elapsed_time": "6:59:46", "remaining_time": "11:44:43"}
+{"current_steps": 1240, "total_steps": 3295, "loss": 0.4648, "lr": 7.854727799294768e-06, "epoch": 0.37634204635987706, "percentage": 37.63, "elapsed_time": "7:03:01", "remaining_time": "11:41:04"}
+{"current_steps": 1250, "total_steps": 3295, "loss": 0.474, "lr": 7.81107410930774e-06, "epoch": 0.37937706286277934, "percentage": 37.94, "elapsed_time": "7:05:36", "remaining_time": "11:36:17"}
+{"current_steps": 1260, "total_steps": 3295, "loss": 0.4557, "lr": 7.767104832700645e-06, "epoch": 0.38241207936568156, "percentage": 38.24, "elapsed_time": "7:08:49", "remaining_time": "11:32:35"}
+{"current_steps": 1270, "total_steps": 3295, "loss": 0.4655, "lr": 7.72282490570599e-06, "epoch": 0.3854470958685838, "percentage": 38.54, "elapsed_time": "7:11:51", "remaining_time": "11:28:35"}
+{"current_steps": 1280, "total_steps": 3295, "loss": 0.4675, "lr": 7.678239299431594e-06, "epoch": 0.388482112371486, "percentage": 38.85, "elapsed_time": "7:14:37", "remaining_time": "11:24:10"}
+{"current_steps": 1290, "total_steps": 3295, "loss": 0.4628, "lr": 7.633353019302519e-06, "epoch": 0.3915171288743883, "percentage": 39.15, "elapsed_time": "7:17:51", "remaining_time": "11:20:33"}
+{"current_steps": 1300, "total_steps": 3295, "loss": 0.4705, "lr": 7.58817110449912e-06, "epoch": 0.3945521453772905, "percentage": 39.45, "elapsed_time": "7:20:29", "remaining_time": "11:15:58"}
+{"current_steps": 1310, "total_steps": 3295, "loss": 0.4633, "lr": 7.5426986273913275e-06, "epoch": 0.3975871618801927, "percentage": 39.76, "elapsed_time": "7:23:50", "remaining_time": "11:12:32"}
+{"current_steps": 1320, "total_steps": 3295, "loss": 0.4664, "lr": 7.496940692969188e-06, "epoch": 0.40062217838309494, "percentage": 40.06, "elapsed_time": "7:26:52", "remaining_time": "11:08:37"}
+{"current_steps": 1330, "total_steps": 3295, "loss": 0.466, "lr": 7.450902438269761e-06, "epoch": 0.4036571948859972, "percentage": 40.36, "elapsed_time": "7:29:42", "remaining_time": "11:04:25"}
+{"current_steps": 1340, "total_steps": 3295, "loss": 0.466, "lr": 7.404589031800395e-06, "epoch": 0.40669221138889944, "percentage": 40.67, "elapsed_time": "7:32:57", "remaining_time": "11:00:51"}
+{"current_steps": 1350, "total_steps": 3295, "loss": 0.4638, "lr": 7.358005672958488e-06, "epoch": 0.40972722789180166, "percentage": 40.97, "elapsed_time": "7:35:33", "remaining_time": "10:56:19"}
+{"current_steps": 1360, "total_steps": 3295, "loss": 0.4574, "lr": 7.311157591447775e-06, "epoch": 0.4127622443947039, "percentage": 41.27, "elapsed_time": "7:38:42", "remaining_time": "10:52:38"}
+{"current_steps": 1370, "total_steps": 3295, "loss": 0.4631, "lr": 7.264050046691211e-06, "epoch": 0.41579726089760616, "percentage": 41.58, "elapsed_time": "7:41:42", "remaining_time": "10:48:45"}
+{"current_steps": 1380, "total_steps": 3295, "loss": 0.4672, "lr": 7.216688327240523e-06, "epoch": 0.4188322774005084, "percentage": 41.88, "elapsed_time": "7:44:34", "remaining_time": "10:44:40"}
+{"current_steps": 1390, "total_steps": 3295, "loss": 0.4613, "lr": 7.16907775018248e-06, "epoch": 0.4218672939034106, "percentage": 42.19, "elapsed_time": "7:47:48", "remaining_time": "10:41:07"}
+{"current_steps": 1400, "total_steps": 3295, "loss": 0.4666, "lr": 7.1212236605419795e-06, "epoch": 0.4249023104063128, "percentage": 42.49, "elapsed_time": "7:50:29", "remaining_time": "10:36:50"}
+{"current_steps": 1410, "total_steps": 3295, "loss": 0.454, "lr": 7.0731314306819725e-06, "epoch": 0.42793732690921504, "percentage": 42.79, "elapsed_time": "7:53:52", "remaining_time": "10:33:30"}
+{"current_steps": 1420, "total_steps": 3295, "loss": 0.4745, "lr": 7.024806459700344e-06, "epoch": 0.4309723434121173, "percentage": 43.1, "elapsed_time": "7:56:52", "remaining_time": "10:29:40"}
+{"current_steps": 1430, "total_steps": 3295, "loss": 0.4578, "lr": 6.976254172823773e-06, "epoch": 0.43400735991501954, "percentage": 43.4, "elapsed_time": "7:59:42", "remaining_time": "10:25:38"}
+{"current_steps": 1440, "total_steps": 3295, "loss": 0.4652, "lr": 6.92748002079867e-06, "epoch": 0.43704237641792176, "percentage": 43.7, "elapsed_time": "8:02:55", "remaining_time": "10:22:06"}
+{"current_steps": 1450, "total_steps": 3295, "loss": 0.4634, "lr": 6.878489479279248e-06, "epoch": 0.440077392920824, "percentage": 44.01, "elapsed_time": "8:05:33", "remaining_time": "10:17:49"}
+{"current_steps": 1460, "total_steps": 3295, "loss": 0.4583, "lr": 6.829288048212789e-06, "epoch": 0.44311240942372626, "percentage": 44.31, "elapsed_time": "8:08:46", "remaining_time": "10:14:18"}
+{"current_steps": 1470, "total_steps": 3295, "loss": 0.4654, "lr": 6.779881251222198e-06, "epoch": 0.4461474259266285, "percentage": 44.61, "elapsed_time": "8:11:46", "remaining_time": "10:10:32"}
+{"current_steps": 1480, "total_steps": 3295, "loss": 0.4671, "lr": 6.730274634985883e-06, "epoch": 0.4491824424295307, "percentage": 44.92, "elapsed_time": "8:14:32", "remaining_time": "10:06:28"}
+{"current_steps": 1490, "total_steps": 3295, "loss": 0.4698, "lr": 6.6804737686150615e-06, "epoch": 0.4522174589324329, "percentage": 45.22, "elapsed_time": "8:17:42", "remaining_time": "10:02:55"}
+{"current_steps": 1500, "total_steps": 3295, "loss": 0.4737, "lr": 6.630484243028534e-06, "epoch": 0.4552524754353352, "percentage": 45.52, "elapsed_time": "8:20:21", "remaining_time": "9:58:45"}
+{"current_steps": 1510, "total_steps": 3295, "loss": 0.4556, "lr": 6.580311670325029e-06, "epoch": 0.4582874919382374, "percentage": 45.83, "elapsed_time": "8:23:36", "remaining_time": "9:55:19"}
+{"current_steps": 1520, "total_steps": 3295, "loss": 0.4604, "lr": 6.529961683153136e-06, "epoch": 0.46132250844113964, "percentage": 46.13, "elapsed_time": "8:26:39", "remaining_time": "9:51:39"}
+{"current_steps": 1530, "total_steps": 3295, "loss": 0.4559, "lr": 6.479439934078983e-06, "epoch": 0.46435752494404187, "percentage": 46.43, "elapsed_time": "8:29:28", "remaining_time": "9:47:43"}
+{"current_steps": 1540, "total_steps": 3295, "loss": 0.4589, "lr": 6.428752094951621e-06, "epoch": 0.46739254144694414, "percentage": 46.74, "elapsed_time": "8:32:39", "remaining_time": "9:44:13"}
+{"current_steps": 1550, "total_steps": 3295, "loss": 0.4656, "lr": 6.377903856266285e-06, "epoch": 0.47042755794984636, "percentage": 47.04, "elapsed_time": "8:35:15", "remaining_time": "9:40:04"}
+{"current_steps": 1560, "total_steps": 3295, "loss": 0.4587, "lr": 6.326900926525552e-06, "epoch": 0.4734625744527486, "percentage": 47.34, "elapsed_time": "8:38:34", "remaining_time": "9:36:44"}
+{"current_steps": 1570, "total_steps": 3295, "loss": 0.4596, "lr": 6.275749031598457e-06, "epoch": 0.4764975909556508, "percentage": 47.65, "elapsed_time": "8:41:36", "remaining_time": "9:33:05"}
+{"current_steps": 1580, "total_steps": 3295, "loss": 0.4599, "lr": 6.224453914077691e-06, "epoch": 0.47953260745855303, "percentage": 47.95, "elapsed_time": "8:44:22", "remaining_time": "9:29:11"}
+{"current_steps": 1590, "total_steps": 3295, "loss": 0.4609, "lr": 6.173021332634899e-06, "epoch": 0.4825676239614553, "percentage": 48.25, "elapsed_time": "8:47:37", "remaining_time": "9:25:47"}
+{"current_steps": 1600, "total_steps": 3295, "loss": 0.4659, "lr": 6.121457061374182e-06, "epoch": 0.4856026404643575, "percentage": 48.56, "elapsed_time": "8:50:17", "remaining_time": "9:21:46"}
+{"current_steps": 1610, "total_steps": 3295, "loss": 0.4552, "lr": 6.06976688918386e-06, "epoch": 0.48863765696725975, "percentage": 48.86, "elapsed_time": "8:53:40", "remaining_time": "9:18:31"}
+{"current_steps": 1620, "total_steps": 3295, "loss": 0.4652, "lr": 6.017956619086585e-06, "epoch": 0.49167267347016197, "percentage": 49.17, "elapsed_time": "8:56:42", "remaining_time": "9:14:55"}
+{"current_steps": 1630, "total_steps": 3295, "loss": 0.4596, "lr": 5.966032067587862e-06, "epoch": 0.49470768997306425, "percentage": 49.47, "elapsed_time": "8:59:34", "remaining_time": "9:11:09"}
+{"current_steps": 1640, "total_steps": 3295, "loss": 0.4572, "lr": 5.913999064023046e-06, "epoch": 0.49774270647596647, "percentage": 49.77, "elapsed_time": "9:02:43", "remaining_time": "9:07:41"}
+{"current_steps": 1650, "total_steps": 3295, "loss": 0.4628, "lr": 5.861863449902926e-06, "epoch": 0.5007777229788687, "percentage": 50.08, "elapsed_time": "9:05:24", "remaining_time": "9:03:45"}
+{"current_steps": 1660, "total_steps": 3295, "loss": 0.4568, "lr": 5.80963107825791e-06, "epoch": 0.503812739481771, "percentage": 50.38, "elapsed_time": "9:08:39", "remaining_time": "9:00:23"}
+{"current_steps": 1670, "total_steps": 3295, "loss": 0.4604, "lr": 5.7573078129809386e-06, "epoch": 0.5068477559846731, "percentage": 50.68, "elapsed_time": "9:11:39", "remaining_time": "8:56:47"}
+{"current_steps": 1680, "total_steps": 3295, "loss": 0.4698, "lr": 5.704899528169175e-06, "epoch": 0.5098827724875754, "percentage": 50.99, "elapsed_time": "9:14:27", "remaining_time": "8:53:00"}
+{"current_steps": 1690, "total_steps": 3295, "loss": 0.4559, "lr": 5.652412107464532e-06, "epoch": 0.5129177889904777, "percentage": 51.29, "elapsed_time": "9:17:39", "remaining_time": "8:49:36"}
+{"current_steps": 1700, "total_steps": 3295, "loss": 0.4657, "lr": 5.5998514433931636e-06, "epoch": 0.5159528054933799, "percentage": 51.59, "elapsed_time": "9:20:15", "remaining_time": "8:45:39"}
+{"current_steps": 1710, "total_steps": 3295, "loss": 0.4555, "lr": 5.547223436703919e-06, "epoch": 0.5189878219962821, "percentage": 51.9, "elapsed_time": "9:23:34", "remaining_time": "8:42:22"}
+{"current_steps": 1720, "total_steps": 3295, "loss": 0.4587, "lr": 5.494533995705904e-06, "epoch": 0.5220228384991843, "percentage": 52.2, "elapsed_time": "9:26:34", "remaining_time": "8:38:48"}
+{"current_steps": 1730, "total_steps": 3295, "loss": 0.4605, "lr": 5.441789035605174e-06, "epoch": 0.5250578550020866, "percentage": 52.5, "elapsed_time": "9:29:23", "remaining_time": "8:35:05"}
+{"current_steps": 1740, "total_steps": 3295, "loss": 0.4601, "lr": 5.3889944778406656e-06, "epoch": 0.5280928715049888, "percentage": 52.81, "elapsed_time": "9:32:30", "remaining_time": "8:31:38"}
+{"current_steps": 1750, "total_steps": 3295, "loss": 0.4583, "lr": 5.336156249419422e-06, "epoch": 0.531127888007891, "percentage": 53.11, "elapsed_time": "9:35:07", "remaining_time": "8:27:44"}
+{"current_steps": 1760, "total_steps": 3295, "loss": 0.451, "lr": 5.283280282251192e-06, "epoch": 0.5341629045107933, "percentage": 53.41, "elapsed_time": "9:38:25", "remaining_time": "8:24:29"}
+{"current_steps": 1770, "total_steps": 3295, "loss": 0.4569, "lr": 5.230372512482485e-06, "epoch": 0.5371979210136956, "percentage": 53.72, "elapsed_time": "9:41:30", "remaining_time": "8:21:00"}
+{"current_steps": 1780, "total_steps": 3295, "loss": 0.4546, "lr": 5.177438879830148e-06, "epoch": 0.5402329375165977, "percentage": 54.02, "elapsed_time": "9:44:16", "remaining_time": "8:17:17"}
+{"current_steps": 1790, "total_steps": 3295, "loss": 0.4522, "lr": 5.1244853269145315e-06, "epoch": 0.5432679540195, "percentage": 54.32, "elapsed_time": "9:47:28", "remaining_time": "8:13:56"}
+{"current_steps": 1800, "total_steps": 3295, "loss": 0.4575, "lr": 5.0715177985923454e-06, "epoch": 0.5463029705224022, "percentage": 54.63, "elapsed_time": "9:50:09", "remaining_time": "8:10:09"}
+{"current_steps": 1810, "total_steps": 3295, "loss": 0.4504, "lr": 5.0185422412892615e-06, "epoch": 0.5493379870253045, "percentage": 54.93, "elapsed_time": "9:53:29", "remaining_time": "8:06:55"}
+{"current_steps": 1820, "total_steps": 3295, "loss": 0.4565, "lr": 4.96556460233232e-06, "epoch": 0.5523730035282067, "percentage": 55.24, "elapsed_time": "9:56:28", "remaining_time": "8:03:24"}
+{"current_steps": 1830, "total_steps": 3295, "loss": 0.4552, "lr": 4.912590829282269e-06, "epoch": 0.5554080200311089, "percentage": 55.54, "elapsed_time": "9:59:15", "remaining_time": "7:59:43"}
+{"current_steps": 1840, "total_steps": 3295, "loss": 0.4646, "lr": 4.859626869265838e-06, "epoch": 0.5584430365340112, "percentage": 55.84, "elapsed_time": "10:02:25", "remaining_time": "7:56:22"}
+{"current_steps": 1850, "total_steps": 3295, "loss": 0.4593, "lr": 4.806678668308102e-06, "epoch": 0.5614780530369133, "percentage": 56.15, "elapsed_time": "10:05:01", "remaining_time": "7:52:34"}
+{"current_steps": 1860, "total_steps": 3295, "loss": 0.4518, "lr": 4.753752170664926e-06, "epoch": 0.5645130695398156, "percentage": 56.45, "elapsed_time": "10:08:19", "remaining_time": "7:49:19"}
+{"current_steps": 1870, "total_steps": 3295, "loss": 0.4537, "lr": 4.700853318155655e-06, "epoch": 0.5675480860427179, "percentage": 56.75, "elapsed_time": "10:11:19", "remaining_time": "7:45:51"}
+{"current_steps": 1880, "total_steps": 3295, "loss": 0.456, "lr": 4.647988049496026e-06, "epoch": 0.5705831025456201, "percentage": 57.06, "elapsed_time": "10:14:11", "remaining_time": "7:42:16"}
+{"current_steps": 1890, "total_steps": 3295, "loss": 0.4544, "lr": 4.5951622996314785e-06, "epoch": 0.5736181190485223, "percentage": 57.36, "elapsed_time": "10:17:25", "remaining_time": "7:38:59"}
+{"current_steps": 1900, "total_steps": 3295, "loss": 0.4576, "lr": 4.542381999070851e-06, "epoch": 0.5766531355514246, "percentage": 57.66, "elapsed_time": "10:20:04", "remaining_time": "7:35:15"}
+{"current_steps": 1910, "total_steps": 3295, "loss": 0.4479, "lr": 4.489653073220593e-06, "epoch": 0.5796881520543268, "percentage": 57.97, "elapsed_time": "10:23:17", "remaining_time": "7:31:58"}
+{"current_steps": 1920, "total_steps": 3295, "loss": 0.4566, "lr": 4.43698144171955e-06, "epoch": 0.582723168557229, "percentage": 58.27, "elapsed_time": "10:26:16", "remaining_time": "7:28:30"}
+{"current_steps": 1930, "total_steps": 3295, "loss": 0.4522, "lr": 4.3843730177743835e-06, "epoch": 0.5857581850601312, "percentage": 58.57, "elapsed_time": "10:29:05", "remaining_time": "7:24:55"}
+{"current_steps": 1940, "total_steps": 3295, "loss": 0.4497, "lr": 4.331833707495735e-06, "epoch": 0.5887932015630335, "percentage": 58.88, "elapsed_time": "10:32:20", "remaining_time": "7:21:39"}
+{"current_steps": 1950, "total_steps": 3295, "loss": 0.4557, "lr": 4.279369409235159e-06, "epoch": 0.5918282180659358, "percentage": 59.18, "elapsed_time": "10:34:57", "remaining_time": "7:17:57"}
+{"current_steps": 1960, "total_steps": 3295, "loss": 0.4527, "lr": 4.226986012922954e-06, "epoch": 0.5948632345688379, "percentage": 59.48, "elapsed_time": "10:38:09", "remaining_time": "7:14:39"}
+{"current_steps": 1970, "total_steps": 3295, "loss": 0.4474, "lr": 4.174689399406917e-06, "epoch": 0.5978982510717402, "percentage": 59.79, "elapsed_time": "10:41:12", "remaining_time": "7:11:16"}
+{"current_steps": 1980, "total_steps": 3295, "loss": 0.4525, "lr": 4.122485439792139e-06, "epoch": 0.6009332675746424, "percentage": 60.09, "elapsed_time": "10:44:05", "remaining_time": "7:07:46"}
+{"current_steps": 1990, "total_steps": 3295, "loss": 0.446, "lr": 4.070379994781865e-06, "epoch": 0.6039682840775447, "percentage": 60.39, "elapsed_time": "10:47:15", "remaining_time": "7:04:27"}
+{"current_steps": 2000, "total_steps": 3295, "loss": 0.4596, "lr": 4.018378914019556e-06, "epoch": 0.6070033005804469, "percentage": 60.7, "elapsed_time": "10:49:51", "remaining_time": "7:00:46"}
+{"current_steps": 2010, "total_steps": 3295, "loss": 0.4421, "lr": 3.966488035432169e-06, "epoch": 0.6100383170833491, "percentage": 61.0, "elapsed_time": "10:53:12", "remaining_time": "6:57:35"}
+{"current_steps": 2020, "total_steps": 3295, "loss": 0.4569, "lr": 3.914713184574759e-06, "epoch": 0.6130733335862514, "percentage": 61.31, "elapsed_time": "10:56:11", "remaining_time": "6:54:10"}
+{"current_steps": 2030, "total_steps": 3295, "loss": 0.4541, "lr": 3.863060173976466e-06, "epoch": 0.6161083500891537, "percentage": 61.61, "elapsed_time": "10:59:00", "remaining_time": "6:50:39"}
+{"current_steps": 2040, "total_steps": 3295, "loss": 0.4551, "lr": 3.811534802487983e-06, "epoch": 0.6191433665920558, "percentage": 61.91, "elapsed_time": "11:02:12", "remaining_time": "6:47:23"}
+{"current_steps": 2050, "total_steps": 3295, "loss": 0.4523, "lr": 3.7601428546305246e-06, "epoch": 0.6221783830949581, "percentage": 62.22, "elapsed_time": "11:04:52", "remaining_time": "6:43:47"}
+{"current_steps": 2060, "total_steps": 3295, "loss": 0.446, "lr": 3.7088900999464432e-06, "epoch": 0.6252133995978603, "percentage": 62.52, "elapsed_time": "11:08:10", "remaining_time": "6:40:34"}
+{"current_steps": 2070, "total_steps": 3295, "loss": 0.4566, "lr": 3.657782292351501e-06, "epoch": 0.6282484161007625, "percentage": 62.82, "elapsed_time": "11:11:09", "remaining_time": "6:37:11"}
+{"current_steps": 2080, "total_steps": 3295, "loss": 0.4508, "lr": 3.6068251694888973e-06, "epoch": 0.6312834326036648, "percentage": 63.13, "elapsed_time": "11:14:00", "remaining_time": "6:33:42"}
+{"current_steps": 2090, "total_steps": 3295, "loss": 0.4431, "lr": 3.556024452085144e-06, "epoch": 0.634318449106567, "percentage": 63.43, "elapsed_time": "11:17:10", "remaining_time": "6:30:25"}
+{"current_steps": 2100, "total_steps": 3295, "loss": 0.4473, "lr": 3.505385843307809e-06, "epoch": 0.6373534656094693, "percentage": 63.73, "elapsed_time": "11:19:50", "remaining_time": "6:26:51"}
+{"current_steps": 2110, "total_steps": 3295, "loss": 0.4472, "lr": 3.4549150281252635e-06, "epoch": 0.6403884821123715, "percentage": 64.04, "elapsed_time": "11:23:01", "remaining_time": "6:23:35"}
+{"current_steps": 2120, "total_steps": 3295, "loss": 0.4536, "lr": 3.404617672668441e-06, "epoch": 0.6434234986152737, "percentage": 64.34, "elapsed_time": "11:26:06", "remaining_time": "6:20:16"}
+{"current_steps": 2130, "total_steps": 3295, "loss": 0.4522, "lr": 3.354499423594737e-06, "epoch": 0.646458515118176, "percentage": 64.64, "elapsed_time": "11:28:56", "remaining_time": "6:16:48"}
+{"current_steps": 2140, "total_steps": 3295, "loss": 0.4441, "lr": 3.3045659074540797e-06, "epoch": 0.6494935316210781, "percentage": 64.95, "elapsed_time": "11:32:11", "remaining_time": "6:13:35"}
+{"current_steps": 2150, "total_steps": 3295, "loss": 0.4551, "lr": 3.254822730057266e-06, "epoch": 0.6525285481239804, "percentage": 65.25, "elapsed_time": "11:34:47", "remaining_time": "6:10:01"}
+{"current_steps": 2160, "total_steps": 3295, "loss": 0.4496, "lr": 3.205275475846614e-06, "epoch": 0.6555635646268827, "percentage": 65.55, "elapsed_time": "11:38:05", "remaining_time": "6:06:49"}
+{"current_steps": 2170, "total_steps": 3295, "loss": 0.4509, "lr": 3.1559297072690376e-06, "epoch": 0.6585985811297849, "percentage": 65.86, "elapsed_time": "11:41:08", "remaining_time": "6:03:29"}
+{"current_steps": 2180, "total_steps": 3295, "loss": 0.4469, "lr": 3.106790964151556e-06, "epoch": 0.6616335976326871, "percentage": 66.16, "elapsed_time": "11:44:00", "remaining_time": "6:00:04"}
+{"current_steps": 2190, "total_steps": 3295, "loss": 0.45, "lr": 3.0578647630793845e-06, "epoch": 0.6646686141355893, "percentage": 66.46, "elapsed_time": "11:47:12", "remaining_time": "5:56:50"}
+{"current_steps": 2200, "total_steps": 3295, "loss": 0.4506, "lr": 3.0091565967765903e-06, "epoch": 0.6677036306384916, "percentage": 66.77, "elapsed_time": "11:49:47", "remaining_time": "5:53:17"}
+{"current_steps": 2210, "total_steps": 3295, "loss": 0.4411, "lr": 2.9606719334894673e-06, "epoch": 0.6707386471413939, "percentage": 67.07, "elapsed_time": "11:53:09", "remaining_time": "5:50:07"}
+{"current_steps": 2220, "total_steps": 3295, "loss": 0.4581, "lr": 2.9124162163726333e-06, "epoch": 0.673773663644296, "percentage": 67.37, "elapsed_time": "11:56:12", "remaining_time": "5:46:48"}
+{"current_steps": 2230, "total_steps": 3295, "loss": 0.4392, "lr": 2.864394862877945e-06, "epoch": 0.6768086801471983, "percentage": 67.68, "elapsed_time": "11:58:59", "remaining_time": "5:43:22"}
+{"current_steps": 2240, "total_steps": 3295, "loss": 0.4514, "lr": 2.8166132641463174e-06, "epoch": 0.6798436966501006, "percentage": 67.98, "elapsed_time": "12:02:13", "remaining_time": "5:40:09"}
+{"current_steps": 2250, "total_steps": 3295, "loss": 0.456, "lr": 2.7690767844024757e-06, "epoch": 0.6828787131530027, "percentage": 68.29, "elapsed_time": "12:04:51", "remaining_time": "5:36:39"}
+{"current_steps": 2260, "total_steps": 3295, "loss": 0.4502, "lr": 2.7217907603527425e-06, "epoch": 0.685913729655905, "percentage": 68.59, "elapsed_time": "12:08:08", "remaining_time": "5:33:27"}
+{"current_steps": 2270, "total_steps": 3295, "loss": 0.4368, "lr": 2.67476050058591e-06, "epoch": 0.6889487461588072, "percentage": 68.89, "elapsed_time": "12:11:13", "remaining_time": "5:30:10"}
+{"current_steps": 2280, "total_steps": 3295, "loss": 0.4427, "lr": 2.627991284977265e-06, "epoch": 0.6919837626617095, "percentage": 69.2, "elapsed_time": "12:14:01", "remaining_time": "5:26:46"}
+{"current_steps": 2290, "total_steps": 3295, "loss": 0.4492, "lr": 2.5814883640958425e-06, "epoch": 0.6950187791646117, "percentage": 69.5, "elapsed_time": "12:17:14", "remaining_time": "5:23:32"}
+{"current_steps": 2300, "total_steps": 3295, "loss": 0.4521, "lr": 2.535256958614972e-06, "epoch": 0.6980537956675139, "percentage": 69.8, "elapsed_time": "12:19:48", "remaining_time": "5:20:03"}
+{"current_steps": 2310, "total_steps": 3295, "loss": 0.445, "lr": 2.489302258726169e-06, "epoch": 0.7010888121704162, "percentage": 70.11, "elapsed_time": "12:23:11", "remaining_time": "5:16:54"}
+{"current_steps": 2320, "total_steps": 3295, "loss": 0.4487, "lr": 2.4436294235564616e-06, "epoch": 0.7041238286733185, "percentage": 70.41, "elapsed_time": "12:26:14", "remaining_time": "5:13:36"}
+{"current_steps": 2330, "total_steps": 3295, "loss": 0.4467, "lr": 2.398243580589197e-06, "epoch": 0.7071588451762206, "percentage": 70.71, "elapsed_time": "12:29:00", "remaining_time": "5:10:12"}
+{"current_steps": 2340, "total_steps": 3295, "loss": 0.4424, "lr": 2.353149825088401e-06, "epoch": 0.7101938616791229, "percentage": 71.02, "elapsed_time": "12:32:15", "remaining_time": "5:07:00"}
+{"current_steps": 2350, "total_steps": 3295, "loss": 0.4492, "lr": 2.30835321952675e-06, "epoch": 0.7132288781820251, "percentage": 71.32, "elapsed_time": "12:34:54", "remaining_time": "5:03:34"}
+{"current_steps": 2360, "total_steps": 3295, "loss": 0.4399, "lr": 2.263858793017247e-06, "epoch": 0.7162638946849273, "percentage": 71.62, "elapsed_time": "12:38:13", "remaining_time": "5:00:23"}
+{"current_steps": 2370, "total_steps": 3295, "loss": 0.4486, "lr": 2.219671540748607e-06, "epoch": 0.7192989111878296, "percentage": 71.93, "elapsed_time": "12:41:15", "remaining_time": "4:57:07"}
+{"current_steps": 2380, "total_steps": 3295, "loss": 0.4516, "lr": 2.1757964234244806e-06, "epoch": 0.7223339276907318, "percentage": 72.23, "elapsed_time": "12:44:02", "remaining_time": "4:53:44"}
+{"current_steps": 2390, "total_steps": 3295, "loss": 0.4459, "lr": 2.1322383667065328e-06, "epoch": 0.7253689441936341, "percentage": 72.53, "elapsed_time": "12:47:09", "remaining_time": "4:50:29"}
+{"current_steps": 2400, "total_steps": 3295, "loss": 0.4519, "lr": 2.0890022606614658e-06, "epoch": 0.7284039606965362, "percentage": 72.84, "elapsed_time": "12:49:47", "remaining_time": "4:47:03"}
+{"current_steps": 2410, "total_steps": 3295, "loss": 0.4421, "lr": 2.0460929592120286e-06, "epoch": 0.7314389771994385, "percentage": 73.14, "elapsed_time": "12:53:04", "remaining_time": "4:43:53"}
+{"current_steps": 2420, "total_steps": 3295, "loss": 0.4474, "lr": 2.0035152795920943e-06, "epoch": 0.7344739937023408, "percentage": 73.44, "elapsed_time": "12:56:08", "remaining_time": "4:40:37"}
+{"current_steps": 2430, "total_steps": 3295, "loss": 0.4506, "lr": 1.961274001805844e-06, "epoch": 0.737509010205243, "percentage": 73.75, "elapsed_time": "12:58:56", "remaining_time": "4:37:16"}
+{"current_steps": 2440, "total_steps": 3295, "loss": 0.4435, "lr": 1.9193738680911444e-06, "epoch": 0.7405440267081452, "percentage": 74.05, "elapsed_time": "13:02:07", "remaining_time": "4:34:03"}
+{"current_steps": 2450, "total_steps": 3295, "loss": 0.4473, "lr": 1.8778195823871537e-06, "epoch": 0.7435790432110475, "percentage": 74.36, "elapsed_time": "13:04:49", "remaining_time": "4:30:41"}
+{"current_steps": 2460, "total_steps": 3295, "loss": 0.441, "lr": 1.836615809806232e-06, "epoch": 0.7466140597139497, "percentage": 74.66, "elapsed_time": "13:08:05", "remaining_time": "4:27:30"}
+{"current_steps": 2470, "total_steps": 3295, "loss": 0.4394, "lr": 1.7957671761102142e-06, "epoch": 0.749649076216852, "percentage": 74.96, "elapsed_time": "13:11:08", "remaining_time": "4:24:14"}
+{"current_steps": 2480, "total_steps": 3295, "loss": 0.4491, "lr": 1.7552782671910845e-06, "epoch": 0.7526840927197541, "percentage": 75.27, "elapsed_time": "13:13:53", "remaining_time": "4:20:53"}
+{"current_steps": 2490, "total_steps": 3295, "loss": 0.4429, "lr": 1.715153628556162e-06, "epoch": 0.7557191092226564, "percentage": 75.57, "elapsed_time": "13:17:07", "remaining_time": "4:17:42"}
+{"current_steps": 2500, "total_steps": 3295, "loss": 0.452, "lr": 1.6753977648177682e-06, "epoch": 0.7587541257255587, "percentage": 75.87, "elapsed_time": "13:19:49", "remaining_time": "4:14:20"}
+{"current_steps": 2510, "total_steps": 3295, "loss": 0.4482, "lr": 1.6360151391875395e-06, "epoch": 0.7617891422284608, "percentage": 76.18, "elapsed_time": "13:23:03", "remaining_time": "4:11:09"}
+{"current_steps": 2520, "total_steps": 3295, "loss": 0.4411, "lr": 1.5970101729753485e-06, "epoch": 0.7648241587313631, "percentage": 76.48, "elapsed_time": "13:26:06", "remaining_time": "4:07:54"}
+{"current_steps": 2530, "total_steps": 3295, "loss": 0.4466, "lr": 1.5583872450929455e-06, "epoch": 0.7678591752342654, "percentage": 76.78, "elapsed_time": "13:28:56", "remaining_time": "4:04:35"}
+{"current_steps": 2540, "total_steps": 3295, "loss": 0.443, "lr": 1.5201506915623621e-06, "epoch": 0.7708941917371676, "percentage": 77.09, "elapsed_time": "13:32:10", "remaining_time": "4:01:24"}
+{"current_steps": 2550, "total_steps": 3295, "loss": 0.452, "lr": 1.4823048050291211e-06, "epoch": 0.7739292082400698, "percentage": 77.39, "elapsed_time": "13:34:48", "remaining_time": "3:58:03"}
+{"current_steps": 2560, "total_steps": 3295, "loss": 0.4405, "lr": 1.4448538342803242e-06, "epoch": 0.776964224742972, "percentage": 77.69, "elapsed_time": "13:38:00", "remaining_time": "3:54:51"}
+{"current_steps": 2570, "total_steps": 3295, "loss": 0.4452, "lr": 1.407801983767656e-06, "epoch": 0.7799992412458743, "percentage": 78.0, "elapsed_time": "13:40:59", "remaining_time": "3:51:36"}
+{"current_steps": 2580, "total_steps": 3295, "loss": 0.4481, "lr": 1.3711534131353738e-06, "epoch": 0.7830342577487766, "percentage": 78.3, "elapsed_time": "13:43:46", "remaining_time": "3:48:17"}
+{"current_steps": 2590, "total_steps": 3295, "loss": 0.4443, "lr": 1.3349122367533135e-06, "epoch": 0.7860692742516787, "percentage": 78.6, "elapsed_time": "13:47:05", "remaining_time": "3:45:08"}
+{"current_steps": 2600, "total_steps": 3295, "loss": 0.4441, "lr": 1.2990825232550065e-06, "epoch": 0.789104290754581, "percentage": 78.91, "elapsed_time": "13:49:42", "remaining_time": "3:41:47"}
+{"current_steps": 2610, "total_steps": 3295, "loss": 0.4414, "lr": 1.2636682950808882e-06, "epoch": 0.7921393072574832, "percentage": 79.21, "elapsed_time": "13:52:58", "remaining_time": "3:38:37"}
+{"current_steps": 2620, "total_steps": 3295, "loss": 0.443, "lr": 1.228673528026741e-06, "epoch": 0.7951743237603854, "percentage": 79.51, "elapsed_time": "13:56:04", "remaining_time": "3:35:23"}
+{"current_steps": 2630, "total_steps": 3295, "loss": 0.445, "lr": 1.194102150797326e-06, "epoch": 0.7982093402632877, "percentage": 79.82, "elapsed_time": "13:58:54", "remaining_time": "3:32:07"}
+{"current_steps": 2640, "total_steps": 3295, "loss": 0.4416, "lr": 1.1599580445653496e-06, "epoch": 0.8012443567661899, "percentage": 80.12, "elapsed_time": "14:02:07", "remaining_time": "3:28:56"}
+{"current_steps": 2650, "total_steps": 3295, "loss": 0.4527, "lr": 1.1262450425357175e-06, "epoch": 0.8042793732690922, "percentage": 80.42, "elapsed_time": "14:04:47", "remaining_time": "3:25:37"}
+{"current_steps": 2660, "total_steps": 3295, "loss": 0.44, "lr": 1.092966929515218e-06, "epoch": 0.8073143897719944, "percentage": 80.73, "elapsed_time": "14:08:05", "remaining_time": "3:22:27"}
+{"current_steps": 2670, "total_steps": 3295, "loss": 0.4455, "lr": 1.0601274414876067e-06, "epoch": 0.8103494062748966, "percentage": 81.03, "elapsed_time": "14:11:08", "remaining_time": "3:19:14"}
+{"current_steps": 2680, "total_steps": 3295, "loss": 0.4446, "lr": 1.0277302651941894e-06, "epoch": 0.8133844227777989, "percentage": 81.34, "elapsed_time": "14:13:58", "remaining_time": "3:15:58"}
+{"current_steps": 2690, "total_steps": 3295, "loss": 0.4397, "lr": 9.95779037719926e-07, "epoch": 0.816419439280701, "percentage": 81.64, "elapsed_time": "14:17:12", "remaining_time": "3:12:47"}
+{"current_steps": 2700, "total_steps": 3295, "loss": 0.4473, "lr": 9.642773460851141e-07, "epoch": 0.8194544557836033, "percentage": 81.94, "elapsed_time": "14:19:53", "remaining_time": "3:09:29"}
+{"current_steps": 2710, "total_steps": 3295, "loss": 0.4425, "lr": 9.332287268426881e-07, "epoch": 0.8224894722865056, "percentage": 82.25, "elapsed_time": "14:23:17", "remaining_time": "3:06:21"}
+{"current_steps": 2720, "total_steps": 3295, "loss": 0.4401, "lr": 9.026366656811835e-07, "epoch": 0.8255244887894078, "percentage": 82.55, "elapsed_time": "14:26:19", "remaining_time": "3:03:08"}
+{"current_steps": 2730, "total_steps": 3295, "loss": 0.4504, "lr": 8.725045970334262e-07, "epoch": 0.82855950529231, "percentage": 82.85, "elapsed_time": "14:29:11", "remaining_time": "2:59:53"}
+{"current_steps": 2740, "total_steps": 3295, "loss": 0.4391, "lr": 8.428359036909455e-07, "epoch": 0.8315945217952123, "percentage": 83.16, "elapsed_time": "14:32:26", "remaining_time": "2:56:43"}
+{"current_steps": 2750, "total_steps": 3295, "loss": 0.4467, "lr": 8.136339164242241e-07, "epoch": 0.8346295382981145, "percentage": 83.46, "elapsed_time": "14:35:05", "remaining_time": "2:53:25"}
+{"current_steps": 2760, "total_steps": 3295, "loss": 0.4398, "lr": 7.849019136087477e-07, "epoch": 0.8376645548010168, "percentage": 83.76, "elapsed_time": "14:38:21", "remaining_time": "2:50:15"}
+{"current_steps": 2770, "total_steps": 3295, "loss": 0.4413, "lr": 7.566431208569747e-07, "epoch": 0.8406995713039189, "percentage": 84.07, "elapsed_time": "14:41:25", "remaining_time": "2:47:03"}
+{"current_steps": 2780, "total_steps": 3295, "loss": 0.4451, "lr": 7.288607106561935e-07, "epoch": 0.8437345878068212, "percentage": 84.37, "elapsed_time": "14:44:12", "remaining_time": "2:43:48"}
+{"current_steps": 2790, "total_steps": 3295, "loss": 0.439, "lr": 7.015578020123804e-07, "epoch": 0.8467696043097235, "percentage": 84.67, "elapsed_time": "14:47:32", "remaining_time": "2:40:38"}
+{"current_steps": 2800, "total_steps": 3295, "loss": 0.4451, "lr": 6.747374601000229e-07, "epoch": 0.8498046208126256, "percentage": 84.98, "elapsed_time": "14:50:08", "remaining_time": "2:37:21"}
+{"current_steps": 2810, "total_steps": 3295, "loss": 0.439, "lr": 6.484026959180256e-07, "epoch": 0.8528396373155279, "percentage": 85.28, "elapsed_time": "14:53:27", "remaining_time": "2:34:12"}
+{"current_steps": 2820, "total_steps": 3295, "loss": 0.4427, "lr": 6.225564659516653e-07, "epoch": 0.8558746538184301, "percentage": 85.58, "elapsed_time": "14:56:30", "remaining_time": "2:31:00"}
+{"current_steps": 2830, "total_steps": 3295, "loss": 0.445, "lr": 5.972016718406832e-07, "epoch": 0.8589096703213324, "percentage": 85.89, "elapsed_time": "14:59:24", "remaining_time": "2:27:47"}
+{"current_steps": 2840, "total_steps": 3295, "loss": 0.4493, "lr": 5.723411600535378e-07, "epoch": 0.8619446868242346, "percentage": 86.19, "elapsed_time": "15:02:39", "remaining_time": "2:24:37"}
+{"current_steps": 2850, "total_steps": 3295, "loss": 0.4436, "lr": 5.4797772156783e-07, "epoch": 0.8649797033271368, "percentage": 86.49, "elapsed_time": "15:05:18", "remaining_time": "2:21:21"}
+{"current_steps": 2860, "total_steps": 3295, "loss": 0.4405, "lr": 5.24114091556992e-07, "epoch": 0.8680147198300391, "percentage": 86.8, "elapsed_time": "15:08:33", "remaining_time": "2:18:11"}
+{"current_steps": 2870, "total_steps": 3295, "loss": 0.4534, "lr": 5.00752949083202e-07, "epoch": 0.8710497363329414, "percentage": 87.1, "elapsed_time": "15:11:34", "remaining_time": "2:14:59"}
+{"current_steps": 2880, "total_steps": 3295, "loss": 0.444, "lr": 4.778969167966346e-07, "epoch": 0.8740847528358435, "percentage": 87.41, "elapsed_time": "15:14:24", "remaining_time": "2:11:45"}
+{"current_steps": 2890, "total_steps": 3295, "loss": 0.436, "lr": 4.5554856064101314e-07, "epoch": 0.8771197693387458, "percentage": 87.71, "elapsed_time": "15:17:38", "remaining_time": "2:08:35"}
+{"current_steps": 2900, "total_steps": 3295, "loss": 0.4531, "lr": 4.337103895655581e-07, "epoch": 0.880154785841648, "percentage": 88.01, "elapsed_time": "15:20:16", "remaining_time": "2:05:20"}
+{"current_steps": 2910, "total_steps": 3295, "loss": 0.4375, "lr": 4.123848552433019e-07, "epoch": 0.8831898023445502, "percentage": 88.32, "elapsed_time": "15:23:31", "remaining_time": "2:02:11"}
+{"current_steps": 2920, "total_steps": 3295, "loss": 0.4374, "lr": 3.9157435179586756e-07, "epoch": 0.8862248188474525, "percentage": 88.62, "elapsed_time": "15:26:35", "remaining_time": "1:58:59"}
+{"current_steps": 2930, "total_steps": 3295, "loss": 0.4441, "lr": 3.712812155246759e-07, "epoch": 0.8892598353503547, "percentage": 88.92, "elapsed_time": "15:29:23", "remaining_time": "1:55:46"}
+{"current_steps": 2940, "total_steps": 3295, "loss": 0.4441, "lr": 3.5150772464867314e-07, "epoch": 0.892294851853257, "percentage": 89.23, "elapsed_time": "15:32:33", "remaining_time": "1:52:36"}
+{"current_steps": 2950, "total_steps": 3295, "loss": 0.4475, "lr": 3.322560990485535e-07, "epoch": 0.8953298683561592, "percentage": 89.53, "elapsed_time": "15:35:08", "remaining_time": "1:49:21"}
+{"current_steps": 2960, "total_steps": 3295, "loss": 0.437, "lr": 3.135285000175531e-07, "epoch": 0.8983648848590614, "percentage": 89.83, "elapsed_time": "15:38:23", "remaining_time": "1:46:12"}
+{"current_steps": 2970, "total_steps": 3295, "loss": 0.4461, "lr": 2.953270300188038e-07, "epoch": 0.9013999013619637, "percentage": 90.14, "elapsed_time": "15:41:21", "remaining_time": "1:43:00"}
+{"current_steps": 2980, "total_steps": 3295, "loss": 0.4411, "lr": 2.776537324493045e-07, "epoch": 0.9044349178648659, "percentage": 90.44, "elapsed_time": "15:44:10", "remaining_time": "1:39:48"}
+{"current_steps": 2990, "total_steps": 3295, "loss": 0.4463, "lr": 2.6051059141051713e-07, "epoch": 0.9074699343677681, "percentage": 90.74, "elapsed_time": "15:47:21", "remaining_time": "1:36:38"}
+{"current_steps": 3000, "total_steps": 3295, "loss": 0.4541, "lr": 2.4389953148561574e-07, "epoch": 0.9105049508706704, "percentage": 91.05, "elapsed_time": "15:49:56", "remaining_time": "1:33:24"}
+{"current_steps": 3010, "total_steps": 3295, "loss": 0.4392, "lr": 2.2782241752343004e-07, "epoch": 0.9135399673735726, "percentage": 91.35, "elapsed_time": "15:53:15", "remaining_time": "1:30:15"}
+{"current_steps": 3020, "total_steps": 3295, "loss": 0.4459, "lr": 2.122810544290782e-07, "epoch": 0.9165749838764748, "percentage": 91.65, "elapsed_time": "15:56:16", "remaining_time": "1:27:04"}
+{"current_steps": 3030, "total_steps": 3295, "loss": 0.4408, "lr": 1.972771869613499e-07, "epoch": 0.919610000379377, "percentage": 91.96, "elapsed_time": "15:59:08", "remaining_time": "1:23:53"}
+{"current_steps": 3040, "total_steps": 3295, "loss": 0.4524, "lr": 1.8281249953681633e-07, "epoch": 0.9226450168822793, "percentage": 92.26, "elapsed_time": "16:02:18", "remaining_time": "1:20:43"}
+{"current_steps": 3050, "total_steps": 3295, "loss": 0.4547, "lr": 1.6888861604074158e-07, "epoch": 0.9256800333851816, "percentage": 92.56, "elapsed_time": "16:04:52", "remaining_time": "1:17:30"}
+{"current_steps": 3060, "total_steps": 3295, "loss": 0.4343, "lr": 1.5550709964476606e-07, "epoch": 0.9287150498880837, "percentage": 92.87, "elapsed_time": "16:08:07", "remaining_time": "1:14:20"}
+{"current_steps": 3070, "total_steps": 3295, "loss": 0.4442, "lr": 1.4266945263142152e-07, "epoch": 0.931750066390986, "percentage": 93.17, "elapsed_time": "16:11:07", "remaining_time": "1:11:10"}
+{"current_steps": 3080, "total_steps": 3295, "loss": 0.4402, "lr": 1.3037711622547633e-07, "epoch": 0.9347850828938883, "percentage": 93.47, "elapsed_time": "16:14:00", "remaining_time": "1:07:59"}
+{"current_steps": 3090, "total_steps": 3295, "loss": 0.4463, "lr": 1.1863147043213453e-07, "epoch": 0.9378200993967905, "percentage": 93.78, "elapsed_time": "16:17:12", "remaining_time": "1:04:49"}
+{"current_steps": 3100, "total_steps": 3295, "loss": 0.4509, "lr": 1.0743383388210849e-07, "epoch": 0.9408551158996927, "percentage": 94.08, "elapsed_time": "16:19:51", "remaining_time": "1:01:38"}
+{"current_steps": 3110, "total_steps": 3295, "loss": 0.4469, "lr": 9.678546368358299e-08, "epoch": 0.9438901324025949, "percentage": 94.39, "elapsed_time": "16:23:10", "remaining_time": "0:58:29"}
+{"current_steps": 3120, "total_steps": 3295, "loss": 0.446, "lr": 8.668755528108586e-08, "epoch": 0.9469251489054972, "percentage": 94.69, "elapsed_time": "16:26:08", "remaining_time": "0:55:18"}
+{"current_steps": 3130, "total_steps": 3295, "loss": 0.447, "lr": 7.714124232127974e-08, "epoch": 0.9499601654083994, "percentage": 94.99, "elapsed_time": "16:29:00", "remaining_time": "0:52:08"}
+{"current_steps": 3140, "total_steps": 3295, "loss": 0.4471, "lr": 6.814759652569391e-08, "epoch": 0.9529951819113016, "percentage": 95.3, "elapsed_time": "16:32:12", "remaining_time": "0:48:58"}
+{"current_steps": 3150, "total_steps": 3295, "loss": 0.4581, "lr": 5.970762757040339e-08, "epoch": 0.9560301984142039, "percentage": 95.6, "elapsed_time": "16:34:49", "remaining_time": "0:45:47"}
+{"current_steps": 3160, "total_steps": 3295, "loss": 0.4377, "lr": 5.182228297268388e-08, "epoch": 0.9590652149171061, "percentage": 95.9, "elapsed_time": "16:38:02", "remaining_time": "0:42:38"}
+{"current_steps": 3170, "total_steps": 3295, "loss": 0.4466, "lr": 4.449244798463037e-08, "epoch": 0.9621002314200083, "percentage": 96.21, "elapsed_time": "16:41:00", "remaining_time": "0:39:28"}
+{"current_steps": 3180, "total_steps": 3295, "loss": 0.4457, "lr": 3.7718945493781523e-08, "epoch": 0.9651352479229106, "percentage": 96.51, "elapsed_time": "16:43:49", "remaining_time": "0:36:18"}
+{"current_steps": 3190, "total_steps": 3295, "loss": 0.4373, "lr": 3.150253593073027e-08, "epoch": 0.9681702644258128, "percentage": 96.81, "elapsed_time": "16:47:03", "remaining_time": "0:33:08"}
+{"current_steps": 3200, "total_steps": 3295, "loss": 0.4541, "lr": 2.5843917183761002e-08, "epoch": 0.971205280928715, "percentage": 97.12, "elapsed_time": "16:49:39", "remaining_time": "0:29:58"}
+{"current_steps": 3210, "total_steps": 3295, "loss": 0.4372, "lr": 2.0743724520495e-08, "epoch": 0.9742402974316173, "percentage": 97.42, "elapsed_time": "16:52:58", "remaining_time": "0:26:49"}
+{"current_steps": 3220, "total_steps": 3295, "loss": 0.4495, "lr": 1.6202530516574165e-08, "epoch": 0.9772753139345195, "percentage": 97.72, "elapsed_time": "16:55:57", "remaining_time": "0:23:39"}
+{"current_steps": 3230, "total_steps": 3295, "loss": 0.4408, "lr": 1.222084499138243e-08, "epoch": 0.9803103304374218, "percentage": 98.03, "elapsed_time": "16:58:50", "remaining_time": "0:20:30"}
+{"current_steps": 3240, "total_steps": 3295, "loss": 0.4419, "lr": 8.799114950806542e-09, "epoch": 0.9833453469403239, "percentage": 98.33, "elapsed_time": "17:02:04", "remaining_time": "0:17:21"}
+{"current_steps": 3250, "total_steps": 3295, "loss": 0.4453, "lr": 5.9377245370551005e-09, "epoch": 0.9863803634432262, "percentage": 98.63, "elapsed_time": "17:04:38", "remaining_time": "0:14:11"}
+{"current_steps": 3260, "total_steps": 3295, "loss": 0.4345, "lr": 3.636994985534159e-09, "epoch": 0.9894153799461285, "percentage": 98.94, "elapsed_time": "17:07:54", "remaining_time": "0:11:02"}
+{"current_steps": 3270, "total_steps": 3295, "loss": 0.4468, "lr": 1.8971845887794105e-09, "epoch": 0.9924503964490307, "percentage": 99.24, "elapsed_time": "17:10:58", "remaining_time": "0:07:52"}
+{"current_steps": 3280, "total_steps": 3295, "loss": 0.4384, "lr": 7.184886674627134e-10, "epoch": 0.9954854129519329, "percentage": 99.54, "elapsed_time": "17:13:50", "remaining_time": "0:04:43"}
+{"current_steps": 3290, "total_steps": 3295, "loss": 0.44, "lr": 1.010395484624116e-10, "epoch": 0.9985204294548352, "percentage": 99.85, "elapsed_time": "17:17:07", "remaining_time": "0:01:34"}
+{"current_steps": 3295, "total_steps": 3295, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "17:18:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2346 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3295,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030350165029022344,
+      "grad_norm": 2.2979175122091453,
+      "learning_rate": 2.7272727272727274e-07,
+      "loss": 0.789,
+      "step": 10
+    },
+    {
+      "epoch": 0.006070033005804469,
+      "grad_norm": 1.7852801501566888,
+      "learning_rate": 5.757575757575758e-07,
+      "loss": 0.7904,
+      "step": 20
+    },
+    {
+      "epoch": 0.009105049508706704,
+      "grad_norm": 1.1632800870309477,
+      "learning_rate": 8.787878787878788e-07,
+      "loss": 0.744,
+      "step": 30
+    },
+    {
+      "epoch": 0.012140066011608937,
+      "grad_norm": 0.8818693207084786,
+      "learning_rate": 1.181818181818182e-06,
+      "loss": 0.693,
+      "step": 40
+    },
+    {
+      "epoch": 0.015175082514511173,
+      "grad_norm": 0.657250412764622,
+      "learning_rate": 1.484848484848485e-06,
+      "loss": 0.6656,
+      "step": 50
+    },
+    {
+      "epoch": 0.018210099017413408,
+      "grad_norm": 0.5316521889428266,
+      "learning_rate": 1.787878787878788e-06,
+      "loss": 0.6313,
+      "step": 60
+    },
+    {
+      "epoch": 0.021245115520315643,
+      "grad_norm": 0.4575711828032985,
+      "learning_rate": 2.090909090909091e-06,
+      "loss": 0.6098,
+      "step": 70
+    },
+    {
+      "epoch": 0.024280132023217875,
+      "grad_norm": 0.4548384308100045,
+      "learning_rate": 2.393939393939394e-06,
+      "loss": 0.5885,
+      "step": 80
+    },
+    {
+      "epoch": 0.02731514852612011,
+      "grad_norm": 0.4458364948040082,
+      "learning_rate": 2.6969696969696972e-06,
+      "loss": 0.5916,
+      "step": 90
+    },
+    {
+      "epoch": 0.030350165029022345,
+      "grad_norm": 0.4794166169125783,
+      "learning_rate": 3e-06,
+      "loss": 0.5753,
+      "step": 100
+    },
+    {
+      "epoch": 0.03338518153192458,
+      "grad_norm": 0.4567719754046465,
+      "learning_rate": 3.3030303030303033e-06,
+      "loss": 0.5597,
+      "step": 110
+    },
+    {
+      "epoch": 0.036420198034826816,
+      "grad_norm": 0.4307419720442758,
+      "learning_rate": 3.606060606060606e-06,
+      "loss": 0.5684,
+      "step": 120
+    },
+    {
+      "epoch": 0.03945521453772905,
+      "grad_norm": 0.4458642819812865,
+      "learning_rate": 3.90909090909091e-06,
+      "loss": 0.5569,
+      "step": 130
+    },
+    {
+      "epoch": 0.042490231040631286,
+      "grad_norm": 0.45568817442378473,
+      "learning_rate": 4.212121212121212e-06,
+      "loss": 0.5551,
+      "step": 140
+    },
+    {
+      "epoch": 0.045525247543533515,
+      "grad_norm": 0.4950300651709512,
+      "learning_rate": 4.5151515151515155e-06,
+      "loss": 0.5565,
+      "step": 150
+    },
+    {
+      "epoch": 0.04856026404643575,
+      "grad_norm": 0.4441786811205893,
+      "learning_rate": 4.818181818181819e-06,
+      "loss": 0.5482,
+      "step": 160
+    },
+    {
+      "epoch": 0.051595280549337985,
+      "grad_norm": 0.4926559856436913,
+      "learning_rate": 5.121212121212121e-06,
+      "loss": 0.5482,
+      "step": 170
+    },
+    {
+      "epoch": 0.05463029705224022,
+      "grad_norm": 0.46505669754342027,
+      "learning_rate": 5.424242424242425e-06,
+      "loss": 0.5397,
+      "step": 180
+    },
+    {
+      "epoch": 0.057665313555142456,
+      "grad_norm": 0.4862932493508676,
+      "learning_rate": 5.727272727272728e-06,
+      "loss": 0.5379,
+      "step": 190
+    },
+    {
+      "epoch": 0.06070033005804469,
+      "grad_norm": 0.5633080158535704,
+      "learning_rate": 6.030303030303031e-06,
+      "loss": 0.5487,
+      "step": 200
+    },
+    {
+      "epoch": 0.06373534656094693,
+      "grad_norm": 0.5144964810224658,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.5354,
+      "step": 210
+    },
+    {
+      "epoch": 0.06677036306384916,
+      "grad_norm": 0.623858354223414,
+      "learning_rate": 6.6363636363636375e-06,
+      "loss": 0.5321,
+      "step": 220
+    },
+    {
+      "epoch": 0.0698053795667514,
+      "grad_norm": 0.5384794963785807,
+      "learning_rate": 6.93939393939394e-06,
+      "loss": 0.5286,
+      "step": 230
+    },
+    {
+      "epoch": 0.07284039606965363,
+      "grad_norm": 0.535110770579217,
+      "learning_rate": 7.242424242424243e-06,
+      "loss": 0.5277,
+      "step": 240
+    },
+    {
+      "epoch": 0.07587541257255587,
+      "grad_norm": 0.5036293665682129,
+      "learning_rate": 7.545454545454546e-06,
+      "loss": 0.5333,
+      "step": 250
+    },
+    {
+      "epoch": 0.0789104290754581,
+      "grad_norm": 0.47084801964860584,
+      "learning_rate": 7.848484848484849e-06,
+      "loss": 0.5272,
+      "step": 260
+    },
+    {
+      "epoch": 0.08194544557836034,
+      "grad_norm": 0.6020093296202623,
+      "learning_rate": 8.151515151515152e-06,
+      "loss": 0.5283,
+      "step": 270
+    },
+    {
+      "epoch": 0.08498046208126257,
+      "grad_norm": 0.5024737305172274,
+      "learning_rate": 8.454545454545455e-06,
+      "loss": 0.5212,
+      "step": 280
+    },
+    {
+      "epoch": 0.08801547858416481,
+      "grad_norm": 0.4994326809453112,
+      "learning_rate": 8.757575757575759e-06,
+      "loss": 0.5161,
+      "step": 290
+    },
+    {
+      "epoch": 0.09105049508706703,
+      "grad_norm": 0.5231140922773104,
+      "learning_rate": 9.06060606060606e-06,
+      "loss": 0.5281,
+      "step": 300
+    },
+    {
+      "epoch": 0.09408551158996926,
+      "grad_norm": 0.5098295511036418,
+      "learning_rate": 9.363636363636365e-06,
+      "loss": 0.5154,
+      "step": 310
+    },
+    {
+      "epoch": 0.0971205280928715,
+      "grad_norm": 0.5892467794961541,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.5218,
+      "step": 320
+    },
+    {
+      "epoch": 0.10015554459577374,
+      "grad_norm": 0.4951705896851936,
+      "learning_rate": 9.96969696969697e-06,
+      "loss": 0.5169,
+      "step": 330
+    },
+    {
+      "epoch": 0.10319056109867597,
+      "grad_norm": 0.6364271310354288,
+      "learning_rate": 9.999772661973056e-06,
+      "loss": 0.5133,
+      "step": 340
+    },
+    {
+      "epoch": 0.1062255776015782,
+      "grad_norm": 0.5028738085648048,
+      "learning_rate": 9.99898682866784e-06,
+      "loss": 0.52,
+      "step": 350
+    },
+    {
+      "epoch": 0.10926059410448044,
+      "grad_norm": 0.5217859360497503,
+      "learning_rate": 9.997639781643002e-06,
+      "loss": 0.5008,
+      "step": 360
+    },
+    {
+      "epoch": 0.11229561060738268,
+      "grad_norm": 0.5157314231456531,
+      "learning_rate": 9.99573167212544e-06,
+      "loss": 0.517,
+      "step": 370
+    },
+    {
+      "epoch": 0.11533062711028491,
+      "grad_norm": 0.524618846108783,
+      "learning_rate": 9.993262714330009e-06,
+      "loss": 0.5092,
+      "step": 380
+    },
+    {
+      "epoch": 0.11836564361318715,
+      "grad_norm": 0.5191412167795787,
+      "learning_rate": 9.990233185435473e-06,
+      "loss": 0.513,
+      "step": 390
+    },
+    {
+      "epoch": 0.12140066011608938,
+      "grad_norm": 0.5047990336080693,
+      "learning_rate": 9.986643425553386e-06,
+      "loss": 0.5129,
+      "step": 400
+    },
+    {
+      "epoch": 0.12443567661899162,
+      "grad_norm": 0.49678214945335275,
+      "learning_rate": 9.98249383768991e-06,
+      "loss": 0.5073,
+      "step": 410
+    },
+    {
+      "epoch": 0.12747069312189385,
+      "grad_norm": 0.5341967716757828,
+      "learning_rate": 9.977784887700572e-06,
+      "loss": 0.5088,
+      "step": 420
+    },
+    {
+      "epoch": 0.13050570962479607,
+      "grad_norm": 0.49917946146850173,
+      "learning_rate": 9.972517104237961e-06,
+      "loss": 0.4991,
+      "step": 430
+    },
+    {
+      "epoch": 0.13354072612769832,
+      "grad_norm": 0.49221501327780853,
+      "learning_rate": 9.966691078692386e-06,
+      "loss": 0.506,
+      "step": 440
+    },
+    {
+      "epoch": 0.13657574263060054,
+      "grad_norm": 0.5448393355182506,
+      "learning_rate": 9.960307465125472e-06,
+      "loss": 0.5025,
+      "step": 450
+    },
+    {
+      "epoch": 0.1396107591335028,
+      "grad_norm": 0.9165522381667764,
+      "learning_rate": 9.953366980196746e-06,
+      "loss": 0.4976,
+      "step": 460
+    },
+    {
+      "epoch": 0.14264577563640501,
+      "grad_norm": 0.5122649698502958,
+      "learning_rate": 9.945870403083164e-06,
+      "loss": 0.503,
+      "step": 470
+    },
+    {
+      "epoch": 0.14568079213930726,
+      "grad_norm": 0.48003844926471007,
+      "learning_rate": 9.937818575391654e-06,
+      "loss": 0.5044,
+      "step": 480
+    },
+    {
+      "epoch": 0.14871580864220948,
+      "grad_norm": 0.5083116253946615,
+      "learning_rate": 9.929212401064616e-06,
+      "loss": 0.505,
+      "step": 490
+    },
+    {
+      "epoch": 0.15175082514511173,
+      "grad_norm": 0.4997990195713387,
+      "learning_rate": 9.920052846278455e-06,
+      "loss": 0.4991,
+      "step": 500
+    },
+    {
+      "epoch": 0.15478584164801396,
+      "grad_norm": 0.4863244820808186,
+      "learning_rate": 9.910340939335098e-06,
+      "loss": 0.4889,
+      "step": 510
+    },
+    {
+      "epoch": 0.1578208581509162,
+      "grad_norm": 0.519835159370644,
+      "learning_rate": 9.900077770546567e-06,
+      "loss": 0.488,
+      "step": 520
+    },
+    {
+      "epoch": 0.16085587465381843,
+      "grad_norm": 0.5247955372337217,
+      "learning_rate": 9.889264492112563e-06,
+      "loss": 0.5025,
+      "step": 530
+    },
+    {
+      "epoch": 0.16389089115672067,
+      "grad_norm": 0.47839854894729905,
+      "learning_rate": 9.877902317991116e-06,
+      "loss": 0.4946,
+      "step": 540
+    },
+    {
+      "epoch": 0.1669259076596229,
+      "grad_norm": 0.4889470867795177,
+      "learning_rate": 9.865992523762306e-06,
+      "loss": 0.4989,
+      "step": 550
+    },
+    {
+      "epoch": 0.16996092416252515,
+      "grad_norm": 0.4753575663441252,
+      "learning_rate": 9.853536446485048e-06,
+      "loss": 0.503,
+      "step": 560
+    },
+    {
+      "epoch": 0.17299594066542737,
+      "grad_norm": 0.5422582939397118,
+      "learning_rate": 9.840535484546996e-06,
+      "loss": 0.4903,
+      "step": 570
+    },
+    {
+      "epoch": 0.17603095716832962,
+      "grad_norm": 0.4706321475205836,
+      "learning_rate": 9.826991097507548e-06,
+      "loss": 0.4958,
+      "step": 580
+    },
+    {
+      "epoch": 0.17906597367123184,
+      "grad_norm": 0.4839096225021675,
+      "learning_rate": 9.812904805933989e-06,
+      "loss": 0.4922,
+      "step": 590
+    },
+    {
+      "epoch": 0.18210099017413406,
+      "grad_norm": 0.4732593571246822,
+      "learning_rate": 9.798278191230783e-06,
+      "loss": 0.5004,
+      "step": 600
+    },
+    {
+      "epoch": 0.1851360066770363,
+      "grad_norm": 0.4505029818283895,
+      "learning_rate": 9.78311289546204e-06,
+      "loss": 0.4802,
+      "step": 610
+    },
+    {
+      "epoch": 0.18817102317993853,
+      "grad_norm": 0.5055436622019127,
+      "learning_rate": 9.76741062116716e-06,
+      "loss": 0.4945,
+      "step": 620
+    },
+    {
+      "epoch": 0.19120603968284078,
+      "grad_norm": 0.49572149753193984,
+      "learning_rate": 9.751173131169705e-06,
+      "loss": 0.4906,
+      "step": 630
+    },
+    {
+      "epoch": 0.194241056185743,
+      "grad_norm": 0.4448394645138839,
+      "learning_rate": 9.73440224837949e-06,
+      "loss": 0.496,
+      "step": 640
+    },
+    {
+      "epoch": 0.19727607268864525,
+      "grad_norm": 0.49316009769902025,
+      "learning_rate": 9.717099855587935e-06,
+      "loss": 0.486,
+      "step": 650
+    },
+    {
+      "epoch": 0.20031108919154747,
+      "grad_norm": 0.47797040662070445,
+      "learning_rate": 9.699267895256695e-06,
+      "loss": 0.4769,
+      "step": 660
+    },
+    {
+      "epoch": 0.20334610569444972,
+      "grad_norm": 0.5092952568059224,
+      "learning_rate": 9.68090836929958e-06,
+      "loss": 0.4918,
+      "step": 670
+    },
+    {
+      "epoch": 0.20638112219735194,
+      "grad_norm": 0.45202984420347087,
+      "learning_rate": 9.662023338857822e-06,
+      "loss": 0.485,
+      "step": 680
+    },
+    {
+      "epoch": 0.2094161387002542,
+      "grad_norm": 0.4983093319634588,
+      "learning_rate": 9.642614924068667e-06,
+      "loss": 0.4902,
+      "step": 690
+    },
+    {
+      "epoch": 0.2124511552031564,
+      "grad_norm": 0.492174959560037,
+      "learning_rate": 9.622685303827366e-06,
+      "loss": 0.4881,
+      "step": 700
+    },
+    {
+      "epoch": 0.21548617170605866,
+      "grad_norm": 0.47815379215317105,
+      "learning_rate": 9.602236715542557e-06,
+      "loss": 0.4848,
+      "step": 710
+    },
+    {
+      "epoch": 0.21852118820896088,
+      "grad_norm": 0.48589573091096694,
+      "learning_rate": 9.581271454885077e-06,
+      "loss": 0.4903,
+      "step": 720
+    },
+    {
+      "epoch": 0.22155620471186313,
+      "grad_norm": 0.46478604800112194,
+      "learning_rate": 9.559791875530247e-06,
+      "loss": 0.489,
+      "step": 730
+    },
+    {
+      "epoch": 0.22459122121476535,
+      "grad_norm": 0.5035008932669235,
+      "learning_rate": 9.537800388893628e-06,
+      "loss": 0.4864,
+      "step": 740
+    },
+    {
+      "epoch": 0.2276262377176676,
+      "grad_norm": 0.49713803635487736,
+      "learning_rate": 9.515299463860301e-06,
+      "loss": 0.4858,
+      "step": 750
+    },
+    {
+      "epoch": 0.23066125422056982,
+      "grad_norm": 0.48728829894131276,
+      "learning_rate": 9.492291626507705e-06,
+      "loss": 0.4874,
+      "step": 760
+    },
+    {
+      "epoch": 0.23369627072347207,
+      "grad_norm": 0.5654089866669252,
+      "learning_rate": 9.468779459822034e-06,
+      "loss": 0.4865,
+      "step": 770
+    },
+    {
+      "epoch": 0.2367312872263743,
+      "grad_norm": 0.456617843862989,
+      "learning_rate": 9.444765603408273e-06,
+      "loss": 0.4834,
+      "step": 780
+    },
+    {
+      "epoch": 0.23976630372927651,
+      "grad_norm": 0.7108327075954629,
+      "learning_rate": 9.420252753193842e-06,
+      "loss": 0.4725,
+      "step": 790
+    },
+    {
+      "epoch": 0.24280132023217876,
+      "grad_norm": 0.49021009503467355,
+      "learning_rate": 9.395243661125948e-06,
+      "loss": 0.4882,
+      "step": 800
+    },
+    {
+      "epoch": 0.24583633673508098,
+      "grad_norm": 0.48115706251944507,
+      "learning_rate": 9.369741134862636e-06,
+      "loss": 0.4752,
+      "step": 810
+    },
+    {
+      "epoch": 0.24887135323798323,
+      "grad_norm": 0.5131051402999688,
+      "learning_rate": 9.343748037457585e-06,
+      "loss": 0.4869,
+      "step": 820
+    },
+    {
+      "epoch": 0.2519063697408855,
+      "grad_norm": 0.4658252213252816,
+      "learning_rate": 9.317267287038682e-06,
+      "loss": 0.4884,
+      "step": 830
+    },
+    {
+      "epoch": 0.2549413862437877,
+      "grad_norm": 0.4751568661396783,
+      "learning_rate": 9.290301856480425e-06,
+      "loss": 0.4797,
+      "step": 840
+    },
+    {
+      "epoch": 0.2579764027466899,
+      "grad_norm": 0.47930138340752015,
+      "learning_rate": 9.262854773070157e-06,
+      "loss": 0.4869,
+      "step": 850
+    },
+    {
+      "epoch": 0.26101141924959215,
+      "grad_norm": 0.47733793569696137,
+      "learning_rate": 9.234929118168228e-06,
+      "loss": 0.4712,
+      "step": 860
+    },
+    {
+      "epoch": 0.2640464357524944,
+      "grad_norm": 0.4566798290905438,
+      "learning_rate": 9.206528026862043e-06,
+      "loss": 0.4765,
+      "step": 870
+    },
+    {
+      "epoch": 0.26708145225539665,
+      "grad_norm": 0.4466757545533174,
+      "learning_rate": 9.177654687614112e-06,
+      "loss": 0.4824,
+      "step": 880
+    },
+    {
+      "epoch": 0.27011646875829887,
+      "grad_norm": 0.47012964956941894,
+      "learning_rate": 9.148312341904095e-06,
+      "loss": 0.4768,
+      "step": 890
+    },
+    {
+      "epoch": 0.2731514852612011,
+      "grad_norm": 0.4650672010975063,
+      "learning_rate": 9.118504283864891e-06,
+      "loss": 0.4763,
+      "step": 900
+    },
+    {
+      "epoch": 0.27618650176410336,
+      "grad_norm": 0.4522875610929074,
+      "learning_rate": 9.088233859912823e-06,
+      "loss": 0.4774,
+      "step": 910
+    },
+    {
+      "epoch": 0.2792215182670056,
+      "grad_norm": 0.9218754990609884,
+      "learning_rate": 9.057504468371954e-06,
+      "loss": 0.4774,
+      "step": 920
+    },
+    {
+      "epoch": 0.2822565347699078,
+      "grad_norm": 0.4446080760553245,
+      "learning_rate": 9.026319559092566e-06,
+      "loss": 0.4822,
+      "step": 930
+    },
+    {
+      "epoch": 0.28529155127281003,
+      "grad_norm": 0.45974314278861356,
+      "learning_rate": 8.994682633063868e-06,
+      "loss": 0.4737,
+      "step": 940
+    },
+    {
+      "epoch": 0.2883265677757123,
+      "grad_norm": 0.46640835738246217,
+      "learning_rate": 8.962597242020947e-06,
+      "loss": 0.4772,
+      "step": 950
+    },
+    {
+      "epoch": 0.2913615842786145,
+      "grad_norm": 0.45954793881402833,
+      "learning_rate": 8.930066988046042e-06,
+      "loss": 0.4688,
+      "step": 960
+    },
+    {
+      "epoch": 0.29439660078151675,
+      "grad_norm": 0.5238237149613728,
+      "learning_rate": 8.897095523164141e-06,
+      "loss": 0.4742,
+      "step": 970
+    },
+    {
+      "epoch": 0.29743161728441897,
+      "grad_norm": 0.45541775923959604,
+      "learning_rate": 8.863686548933001e-06,
+      "loss": 0.4786,
+      "step": 980
+    },
+    {
+      "epoch": 0.3004666337873212,
+      "grad_norm": 0.46811147224647004,
+      "learning_rate": 8.829843816027575e-06,
+      "loss": 0.4706,
+      "step": 990
+    },
+    {
+      "epoch": 0.30350165029022347,
+      "grad_norm": 0.47480506009090023,
+      "learning_rate": 8.795571123818948e-06,
+      "loss": 0.4733,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3065366667931257,
+      "grad_norm": 0.46579935990440124,
+      "learning_rate": 8.760872319947796e-06,
+      "loss": 0.467,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3095716832960279,
+      "grad_norm": 0.4713650285222608,
+      "learning_rate": 8.72575129989244e-06,
+      "loss": 0.4714,
+      "step": 1020
+    },
+    {
+      "epoch": 0.31260669979893013,
+      "grad_norm": 0.5172958915739383,
+      "learning_rate": 8.690212006531498e-06,
+      "loss": 0.4778,
+      "step": 1030
+    },
+    {
+      "epoch": 0.3156417163018324,
+      "grad_norm": 0.4636306902344978,
+      "learning_rate": 8.654258429701254e-06,
+      "loss": 0.4766,
+      "step": 1040
+    },
+    {
+      "epoch": 0.31867673280473463,
+      "grad_norm": 0.4630632755815923,
+      "learning_rate": 8.617894605747728e-06,
+      "loss": 0.471,
+      "step": 1050
+    },
+    {
+      "epoch": 0.32171174930763685,
+      "grad_norm": 0.4726631111043291,
+      "learning_rate": 8.581124617073531e-06,
+      "loss": 0.4754,
+      "step": 1060
+    },
+    {
+      "epoch": 0.3247467658105391,
+      "grad_norm": 0.449173460165581,
+      "learning_rate": 8.543952591679565e-06,
+      "loss": 0.4757,
+      "step": 1070
+    },
+    {
+      "epoch": 0.32778178231344135,
+      "grad_norm": 0.4593115406956091,
+      "learning_rate": 8.506382702701575e-06,
+      "loss": 0.4682,
+      "step": 1080
+    },
+    {
+      "epoch": 0.33081679881634357,
+      "grad_norm": 0.49121579493660045,
+      "learning_rate": 8.468419167941658e-06,
+      "loss": 0.4631,
+      "step": 1090
+    },
+    {
+      "epoch": 0.3338518153192458,
+      "grad_norm": 0.4799330378295981,
+      "learning_rate": 8.430066249394754e-06,
+      "loss": 0.4786,
+      "step": 1100
+    },
+    {
+      "epoch": 0.336886831822148,
+      "grad_norm": 0.46743240892192656,
+      "learning_rate": 8.391328252770165e-06,
+      "loss": 0.4648,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3399218483250503,
+      "grad_norm": 0.49238589329434995,
+      "learning_rate": 8.352209527008164e-06,
+      "loss": 0.4785,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3429568648279525,
+      "grad_norm": 0.463123088401655,
+      "learning_rate": 8.31271446379178e-06,
+      "loss": 0.4684,
+      "step": 1130
+    },
+    {
+      "epoch": 0.34599188133085473,
+      "grad_norm": 0.45804967626699783,
+      "learning_rate": 8.272847497053745e-06,
+      "loss": 0.467,
+      "step": 1140
+    },
+    {
+      "epoch": 0.34902689783375695,
+      "grad_norm": 0.49208327340861874,
+      "learning_rate": 8.232613102478722e-06,
+      "loss": 0.4734,
+      "step": 1150
+    },
+    {
+      "epoch": 0.35206191433665923,
+      "grad_norm": 0.4834727766246894,
+      "learning_rate": 8.192015797000849e-06,
+      "loss": 0.4634,
+      "step": 1160
+    },
+    {
+      "epoch": 0.35509693083956145,
+      "grad_norm": 0.45802821271745225,
+      "learning_rate": 8.151060138296624e-06,
+      "loss": 0.4769,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3581319473424637,
+      "grad_norm": 0.47069229829560316,
+      "learning_rate": 8.10975072427326e-06,
+      "loss": 0.4631,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3611669638453659,
+      "grad_norm": 0.4638785009109008,
+      "learning_rate": 8.068092192552473e-06,
+      "loss": 0.4621,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3642019803482681,
+      "grad_norm": 0.5267368501556567,
+      "learning_rate": 8.026089219949856e-06,
+      "loss": 0.4707,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3672369968511704,
+      "grad_norm": 0.4603778748004369,
+      "learning_rate": 7.983746521949822e-06,
+      "loss": 0.4691,
+      "step": 1210
+    },
+    {
+      "epoch": 0.3702720133540726,
+      "grad_norm": 0.5044371212314646,
+      "learning_rate": 7.941068852176233e-06,
+      "loss": 0.4673,
+      "step": 1220
+    },
+    {
+      "epoch": 0.37330702985697484,
+      "grad_norm": 0.5023326078920469,
+      "learning_rate": 7.898061001858712e-06,
+      "loss": 0.4652,
+      "step": 1230
+    },
+    {
+      "epoch": 0.37634204635987706,
+      "grad_norm": 0.5465382069712866,
+      "learning_rate": 7.854727799294768e-06,
+      "loss": 0.4648,
+      "step": 1240
+    },
+    {
+      "epoch": 0.37937706286277934,
+      "grad_norm": 0.46811731936405077,
+      "learning_rate": 7.81107410930774e-06,
+      "loss": 0.474,
+      "step": 1250
+    },
+    {
+      "epoch": 0.38241207936568156,
+      "grad_norm": 0.4582110078248361,
+      "learning_rate": 7.767104832700645e-06,
+      "loss": 0.4557,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3854470958685838,
+      "grad_norm": 0.47816100008054285,
+      "learning_rate": 7.72282490570599e-06,
+      "loss": 0.4655,
+      "step": 1270
+    },
+    {
+      "epoch": 0.388482112371486,
+      "grad_norm": 0.4587552509577914,
+      "learning_rate": 7.678239299431594e-06,
+      "loss": 0.4675,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3915171288743883,
+      "grad_norm": 0.48955107625039307,
+      "learning_rate": 7.633353019302519e-06,
+      "loss": 0.4628,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3945521453772905,
+      "grad_norm": 0.4697573855941327,
+      "learning_rate": 7.58817110449912e-06,
+      "loss": 0.4705,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3975871618801927,
+      "grad_norm": 0.4586083541834714,
+      "learning_rate": 7.5426986273913275e-06,
+      "loss": 0.4633,
+      "step": 1310
+    },
+    {
+      "epoch": 0.40062217838309494,
+      "grad_norm": 0.4943303423222579,
+      "learning_rate": 7.496940692969188e-06,
+      "loss": 0.4664,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4036571948859972,
+      "grad_norm": 0.4472430460309261,
+      "learning_rate": 7.450902438269761e-06,
+      "loss": 0.466,
+      "step": 1330
+    },
+    {
+      "epoch": 0.40669221138889944,
+      "grad_norm": 0.45151069440310115,
+      "learning_rate": 7.404589031800395e-06,
+      "loss": 0.466,
+      "step": 1340
+    },
+    {
+      "epoch": 0.40972722789180166,
+      "grad_norm": 0.4931709679843594,
+      "learning_rate": 7.358005672958488e-06,
+      "loss": 0.4638,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4127622443947039,
+      "grad_norm": 0.4458955481322604,
+      "learning_rate": 7.311157591447775e-06,
+      "loss": 0.4574,
+      "step": 1360
+    },
+    {
+      "epoch": 0.41579726089760616,
+      "grad_norm": 0.5037362623251065,
+      "learning_rate": 7.264050046691211e-06,
+      "loss": 0.4631,
+      "step": 1370
+    },
+    {
+      "epoch": 0.4188322774005084,
+      "grad_norm": 0.5401075737360693,
+      "learning_rate": 7.216688327240523e-06,
+      "loss": 0.4672,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4218672939034106,
+      "grad_norm": 0.46823354166024683,
+      "learning_rate": 7.16907775018248e-06,
+      "loss": 0.4613,
+      "step": 1390
+    },
+    {
+      "epoch": 0.4249023104063128,
+      "grad_norm": 0.4780876891839522,
+      "learning_rate": 7.1212236605419795e-06,
+      "loss": 0.4666,
+      "step": 1400
+    },
+    {
+      "epoch": 0.42793732690921504,
+      "grad_norm": 0.5119425577262322,
+      "learning_rate": 7.0731314306819725e-06,
+      "loss": 0.454,
+      "step": 1410
+    },
+    {
+      "epoch": 0.4309723434121173,
+      "grad_norm": 0.47436698182963066,
+      "learning_rate": 7.024806459700344e-06,
+      "loss": 0.4745,
+      "step": 1420
+    },
+    {
+      "epoch": 0.43400735991501954,
+      "grad_norm": 0.47009240919947903,
+      "learning_rate": 6.976254172823773e-06,
+      "loss": 0.4578,
+      "step": 1430
+    },
+    {
+      "epoch": 0.43704237641792176,
+      "grad_norm": 0.4505894481894143,
+      "learning_rate": 6.92748002079867e-06,
+      "loss": 0.4652,
+      "step": 1440
+    },
+    {
+      "epoch": 0.440077392920824,
+      "grad_norm": 0.4739852546862808,
+      "learning_rate": 6.878489479279248e-06,
+      "loss": 0.4634,
+      "step": 1450
+    },
+    {
+      "epoch": 0.44311240942372626,
+      "grad_norm": 0.43339777098222865,
+      "learning_rate": 6.829288048212789e-06,
+      "loss": 0.4583,
+      "step": 1460
+    },
+    {
+      "epoch": 0.4461474259266285,
+      "grad_norm": 0.48444826933680063,
+      "learning_rate": 6.779881251222198e-06,
+      "loss": 0.4654,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4491824424295307,
+      "grad_norm": 0.43409574874106044,
+      "learning_rate": 6.730274634985883e-06,
+      "loss": 0.4671,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4522174589324329,
+      "grad_norm": 0.4532708590504662,
+      "learning_rate": 6.6804737686150615e-06,
+      "loss": 0.4698,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4552524754353352,
+      "grad_norm": 0.473135305256464,
+      "learning_rate": 6.630484243028534e-06,
+      "loss": 0.4737,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4582874919382374,
+      "grad_norm": 0.4685015310135646,
+      "learning_rate": 6.580311670325029e-06,
+      "loss": 0.4556,
+      "step": 1510
+    },
+    {
+      "epoch": 0.46132250844113964,
+      "grad_norm": 0.46358839605143787,
+      "learning_rate": 6.529961683153136e-06,
+      "loss": 0.4604,
+      "step": 1520
+    },
+    {
+      "epoch": 0.46435752494404187,
+      "grad_norm": 0.45388131225935224,
+      "learning_rate": 6.479439934078983e-06,
+      "loss": 0.4559,
+      "step": 1530
+    },
+    {
+      "epoch": 0.46739254144694414,
+      "grad_norm": 0.435672967522485,
+      "learning_rate": 6.428752094951621e-06,
+      "loss": 0.4589,
+      "step": 1540
+    },
+    {
+      "epoch": 0.47042755794984636,
+      "grad_norm": 0.4681448507359377,
+      "learning_rate": 6.377903856266285e-06,
+      "loss": 0.4656,
+      "step": 1550
+    },
+    {
+      "epoch": 0.4734625744527486,
+      "grad_norm": 0.4866196593408997,
+      "learning_rate": 6.326900926525552e-06,
+      "loss": 0.4587,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4764975909556508,
+      "grad_norm": 0.5334135903943417,
+      "learning_rate": 6.275749031598457e-06,
+      "loss": 0.4596,
+      "step": 1570
+    },
+    {
+      "epoch": 0.47953260745855303,
+      "grad_norm": 0.545053303736673,
+      "learning_rate": 6.224453914077691e-06,
+      "loss": 0.4599,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4825676239614553,
+      "grad_norm": 0.43049803862728125,
+      "learning_rate": 6.173021332634899e-06,
+      "loss": 0.4609,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4856026404643575,
+      "grad_norm": 0.4679235070374552,
+      "learning_rate": 6.121457061374182e-06,
+      "loss": 0.4659,
+      "step": 1600
+    },
+    {
+      "epoch": 0.48863765696725975,
+      "grad_norm": 0.48596466698858914,
+      "learning_rate": 6.06976688918386e-06,
+      "loss": 0.4552,
+      "step": 1610
+    },
+    {
+      "epoch": 0.49167267347016197,
+      "grad_norm": 0.4654168221541189,
+      "learning_rate": 6.017956619086585e-06,
+      "loss": 0.4652,
+      "step": 1620
+    },
+    {
+      "epoch": 0.49470768997306425,
+      "grad_norm": 0.43813429165646467,
+      "learning_rate": 5.966032067587862e-06,
+      "loss": 0.4596,
+      "step": 1630
+    },
+    {
+      "epoch": 0.49774270647596647,
+      "grad_norm": 0.6681280851162651,
+      "learning_rate": 5.913999064023046e-06,
+      "loss": 0.4572,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5007777229788687,
+      "grad_norm": 0.5204323449742513,
+      "learning_rate": 5.861863449902926e-06,
+      "loss": 0.4628,
+      "step": 1650
+    },
+    {
+      "epoch": 0.503812739481771,
+      "grad_norm": 0.4296041756151093,
+      "learning_rate": 5.80963107825791e-06,
+      "loss": 0.4568,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5068477559846731,
+      "grad_norm": 0.4687304772565422,
+      "learning_rate": 5.7573078129809386e-06,
+      "loss": 0.4604,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5098827724875754,
+      "grad_norm": 0.4554317567297939,
+      "learning_rate": 5.704899528169175e-06,
+      "loss": 0.4698,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5129177889904777,
+      "grad_norm": 0.4550611945171018,
+      "learning_rate": 5.652412107464532e-06,
+      "loss": 0.4559,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5159528054933799,
+      "grad_norm": 0.4737844991440093,
+      "learning_rate": 5.5998514433931636e-06,
+      "loss": 0.4657,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5189878219962821,
+      "grad_norm": 0.44176755708702975,
+      "learning_rate": 5.547223436703919e-06,
+      "loss": 0.4555,
+      "step": 1710
+    },
+    {
+      "epoch": 0.5220228384991843,
+      "grad_norm": 0.4602868804162559,
+      "learning_rate": 5.494533995705904e-06,
+      "loss": 0.4587,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5250578550020866,
+      "grad_norm": 0.4619636659852323,
+      "learning_rate": 5.441789035605174e-06,
+      "loss": 0.4605,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5280928715049888,
+      "grad_norm": 0.4918743050797947,
+      "learning_rate": 5.3889944778406656e-06,
+      "loss": 0.4601,
+      "step": 1740
+    },
+    {
+      "epoch": 0.531127888007891,
+      "grad_norm": 0.5108035906034613,
+      "learning_rate": 5.336156249419422e-06,
+      "loss": 0.4583,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5341629045107933,
+      "grad_norm": 0.4644351963738344,
+      "learning_rate": 5.283280282251192e-06,
+      "loss": 0.451,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5371979210136956,
+      "grad_norm": 0.466505558488539,
+      "learning_rate": 5.230372512482485e-06,
+      "loss": 0.4569,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5402329375165977,
+      "grad_norm": 0.4395984838919295,
+      "learning_rate": 5.177438879830148e-06,
+      "loss": 0.4546,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5432679540195,
+      "grad_norm": 0.5081543080746838,
+      "learning_rate": 5.1244853269145315e-06,
+      "loss": 0.4522,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5463029705224022,
+      "grad_norm": 0.4739999458440851,
+      "learning_rate": 5.0715177985923454e-06,
+      "loss": 0.4575,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5493379870253045,
+      "grad_norm": 0.44986425269809655,
+      "learning_rate": 5.0185422412892615e-06,
+      "loss": 0.4504,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5523730035282067,
+      "grad_norm": 0.493838430904318,
+      "learning_rate": 4.96556460233232e-06,
+      "loss": 0.4565,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5554080200311089,
+      "grad_norm": 0.4597123498494703,
+      "learning_rate": 4.912590829282269e-06,
+      "loss": 0.4552,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5584430365340112,
+      "grad_norm": 0.45249866862931715,
+      "learning_rate": 4.859626869265838e-06,
+      "loss": 0.4646,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5614780530369133,
+      "grad_norm": 0.47693139933323253,
+      "learning_rate": 4.806678668308102e-06,
+      "loss": 0.4593,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5645130695398156,
+      "grad_norm": 0.4441745555089401,
+      "learning_rate": 4.753752170664926e-06,
+      "loss": 0.4518,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5675480860427179,
+      "grad_norm": 0.5407791277506199,
+      "learning_rate": 4.700853318155655e-06,
+      "loss": 0.4537,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5705831025456201,
+      "grad_norm": 0.43766170865780535,
+      "learning_rate": 4.647988049496026e-06,
+      "loss": 0.456,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5736181190485223,
+      "grad_norm": 0.4381830382862563,
+      "learning_rate": 4.5951622996314785e-06,
+      "loss": 0.4544,
+      "step": 1890
+    },
+    {
+      "epoch": 0.5766531355514246,
+      "grad_norm": 0.5008063102656403,
+      "learning_rate": 4.542381999070851e-06,
+      "loss": 0.4576,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5796881520543268,
+      "grad_norm": 0.4449319997966233,
+      "learning_rate": 4.489653073220593e-06,
+      "loss": 0.4479,
+      "step": 1910
+    },
+    {
+      "epoch": 0.582723168557229,
+      "grad_norm": 0.4325405045901816,
+      "learning_rate": 4.43698144171955e-06,
+      "loss": 0.4566,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5857581850601312,
+      "grad_norm": 0.4558072435464798,
+      "learning_rate": 4.3843730177743835e-06,
+      "loss": 0.4522,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5887932015630335,
+      "grad_norm": 0.46993480403343113,
+      "learning_rate": 4.331833707495735e-06,
+      "loss": 0.4497,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5918282180659358,
+      "grad_norm": 0.48201210672220995,
+      "learning_rate": 4.279369409235159e-06,
+      "loss": 0.4557,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5948632345688379,
+      "grad_norm": 0.48886046384215476,
+      "learning_rate": 4.226986012922954e-06,
+      "loss": 0.4527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5978982510717402,
+      "grad_norm": 0.496378890478507,
+      "learning_rate": 4.174689399406917e-06,
+      "loss": 0.4474,
+      "step": 1970
+    },
+    {
+      "epoch": 0.6009332675746424,
+      "grad_norm": 0.5586162522102414,
+      "learning_rate": 4.122485439792139e-06,
+      "loss": 0.4525,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6039682840775447,
+      "grad_norm": 0.446752242572371,
+      "learning_rate": 4.070379994781865e-06,
+      "loss": 0.446,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6070033005804469,
+      "grad_norm": 0.47706411203661847,
+      "learning_rate": 4.018378914019556e-06,
+      "loss": 0.4596,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6100383170833491,
+      "grad_norm": 0.538309740370942,
+      "learning_rate": 3.966488035432169e-06,
+      "loss": 0.4421,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6130733335862514,
+      "grad_norm": 0.5230632035555158,
+      "learning_rate": 3.914713184574759e-06,
+      "loss": 0.4569,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6161083500891537,
+      "grad_norm": 0.4338338834185748,
+      "learning_rate": 3.863060173976466e-06,
+      "loss": 0.4541,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6191433665920558,
+      "grad_norm": 0.5603785317621145,
+      "learning_rate": 3.811534802487983e-06,
+      "loss": 0.4551,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6221783830949581,
+      "grad_norm": 0.47642244684394447,
+      "learning_rate": 3.7601428546305246e-06,
+      "loss": 0.4523,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6252133995978603,
+      "grad_norm": 0.46992960142430185,
+      "learning_rate": 3.7088900999464432e-06,
+      "loss": 0.446,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6282484161007625,
+      "grad_norm": 0.4845504298042459,
+      "learning_rate": 3.657782292351501e-06,
+      "loss": 0.4566,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6312834326036648,
+      "grad_norm": 0.47017322226992764,
+      "learning_rate": 3.6068251694888973e-06,
+      "loss": 0.4508,
+      "step": 2080
+    },
+    {
+      "epoch": 0.634318449106567,
+      "grad_norm": 0.5121234005197363,
+      "learning_rate": 3.556024452085144e-06,
+      "loss": 0.4431,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6373534656094693,
+      "grad_norm": 0.487255052511626,
+      "learning_rate": 3.505385843307809e-06,
+      "loss": 0.4473,
+      "step": 2100
+    },
+    {
+      "epoch": 0.6403884821123715,
+      "grad_norm": 0.4564465966378128,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.4472,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6434234986152737,
+      "grad_norm": 0.4806890404068221,
+      "learning_rate": 3.404617672668441e-06,
+      "loss": 0.4536,
+      "step": 2120
+    },
+    {
+      "epoch": 0.646458515118176,
+      "grad_norm": 0.45235070380959885,
+      "learning_rate": 3.354499423594737e-06,
+      "loss": 0.4522,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6494935316210781,
+      "grad_norm": 0.45955408837797435,
+      "learning_rate": 3.3045659074540797e-06,
+      "loss": 0.4441,
+      "step": 2140
+    },
+    {
+      "epoch": 0.6525285481239804,
+      "grad_norm": 0.4923322956992551,
+      "learning_rate": 3.254822730057266e-06,
+      "loss": 0.4551,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6555635646268827,
+      "grad_norm": 0.48682070386464155,
+      "learning_rate": 3.205275475846614e-06,
+      "loss": 0.4496,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6585985811297849,
+      "grad_norm": 0.47952708737796373,
+      "learning_rate": 3.1559297072690376e-06,
+      "loss": 0.4509,
+      "step": 2170
+    },
+    {
+      "epoch": 0.6616335976326871,
+      "grad_norm": 0.4543123589314356,
+      "learning_rate": 3.106790964151556e-06,
+      "loss": 0.4469,
+      "step": 2180
+    },
+    {
+      "epoch": 0.6646686141355893,
+      "grad_norm": 0.4820597535972369,
+      "learning_rate": 3.0578647630793845e-06,
+      "loss": 0.45,
+      "step": 2190
+    },
+    {
+      "epoch": 0.6677036306384916,
+      "grad_norm": 0.47560501988050274,
+      "learning_rate": 3.0091565967765903e-06,
+      "loss": 0.4506,
+      "step": 2200
+    },
+    {
+      "epoch": 0.6707386471413939,
+      "grad_norm": 0.4590471436665147,
+      "learning_rate": 2.9606719334894673e-06,
+      "loss": 0.4411,
+      "step": 2210
+    },
+    {
+      "epoch": 0.673773663644296,
+      "grad_norm": 0.4871582819595622,
+      "learning_rate": 2.9124162163726333e-06,
+      "loss": 0.4581,
+      "step": 2220
+    },
+    {
+      "epoch": 0.6768086801471983,
+      "grad_norm": 0.4621936812853514,
+      "learning_rate": 2.864394862877945e-06,
+      "loss": 0.4392,
+      "step": 2230
+    },
+    {
+      "epoch": 0.6798436966501006,
+      "grad_norm": 0.5106734882471429,
+      "learning_rate": 2.8166132641463174e-06,
+      "loss": 0.4514,
+      "step": 2240
+    },
+    {
+      "epoch": 0.6828787131530027,
+      "grad_norm": 0.4872901241863599,
+      "learning_rate": 2.7690767844024757e-06,
+      "loss": 0.456,
+      "step": 2250
+    },
+    {
+      "epoch": 0.685913729655905,
+      "grad_norm": 0.5327159140172049,
+      "learning_rate": 2.7217907603527425e-06,
+      "loss": 0.4502,
+      "step": 2260
+    },
+    {
+      "epoch": 0.6889487461588072,
+      "grad_norm": 0.46596161967531874,
+      "learning_rate": 2.67476050058591e-06,
+      "loss": 0.4368,
+      "step": 2270
+    },
+    {
+      "epoch": 0.6919837626617095,
+      "grad_norm": 0.4756057088646994,
+      "learning_rate": 2.627991284977265e-06,
+      "loss": 0.4427,
+      "step": 2280
+    },
+    {
+      "epoch": 0.6950187791646117,
+      "grad_norm": 0.457554867967829,
+      "learning_rate": 2.5814883640958425e-06,
+      "loss": 0.4492,
+      "step": 2290
+    },
+    {
+      "epoch": 0.6980537956675139,
+      "grad_norm": 0.4914134735789525,
+      "learning_rate": 2.535256958614972e-06,
+      "loss": 0.4521,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7010888121704162,
+      "grad_norm": 0.4514454510170551,
+      "learning_rate": 2.489302258726169e-06,
+      "loss": 0.445,
+      "step": 2310
+    },
+    {
+      "epoch": 0.7041238286733185,
+      "grad_norm": 0.5541195252480908,
+      "learning_rate": 2.4436294235564616e-06,
+      "loss": 0.4487,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7071588451762206,
+      "grad_norm": 0.4701102512963565,
+      "learning_rate": 2.398243580589197e-06,
+      "loss": 0.4467,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7101938616791229,
+      "grad_norm": 0.5033348530844566,
+      "learning_rate": 2.353149825088401e-06,
+      "loss": 0.4424,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7132288781820251,
+      "grad_norm": 0.4896392329694068,
+      "learning_rate": 2.30835321952675e-06,
+      "loss": 0.4492,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7162638946849273,
+      "grad_norm": 0.45357241678052895,
+      "learning_rate": 2.263858793017247e-06,
+      "loss": 0.4399,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7192989111878296,
+      "grad_norm": 0.47254537181545697,
+      "learning_rate": 2.219671540748607e-06,
+      "loss": 0.4486,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7223339276907318,
+      "grad_norm": 1.0513237554990393,
+      "learning_rate": 2.1757964234244806e-06,
+      "loss": 0.4516,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7253689441936341,
+      "grad_norm": 1.211615701259343,
+      "learning_rate": 2.1322383667065328e-06,
+      "loss": 0.4459,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7284039606965362,
+      "grad_norm": 0.49549117242754526,
+      "learning_rate": 2.0890022606614658e-06,
+      "loss": 0.4519,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7314389771994385,
+      "grad_norm": 0.441302787437587,
+      "learning_rate": 2.0460929592120286e-06,
+      "loss": 0.4421,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7344739937023408,
+      "grad_norm": 0.47459997274968196,
+      "learning_rate": 2.0035152795920943e-06,
+      "loss": 0.4474,
+      "step": 2420
+    },
+    {
+      "epoch": 0.737509010205243,
+      "grad_norm": 0.5534394858546283,
+      "learning_rate": 1.961274001805844e-06,
+      "loss": 0.4506,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7405440267081452,
+      "grad_norm": 0.5940641703049439,
+      "learning_rate": 1.9193738680911444e-06,
+      "loss": 0.4435,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7435790432110475,
+      "grad_norm": 0.47749388420290173,
+      "learning_rate": 1.8778195823871537e-06,
+      "loss": 0.4473,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7466140597139497,
+      "grad_norm": 0.46649043860109973,
+      "learning_rate": 1.836615809806232e-06,
+      "loss": 0.441,
+      "step": 2460
+    },
+    {
+      "epoch": 0.749649076216852,
+      "grad_norm": 0.47765577041447577,
+      "learning_rate": 1.7957671761102142e-06,
+      "loss": 0.4394,
+      "step": 2470
+    },
+    {
+      "epoch": 0.7526840927197541,
+      "grad_norm": 0.4609425591065501,
+      "learning_rate": 1.7552782671910845e-06,
+      "loss": 0.4491,
+      "step": 2480
+    },
+    {
+      "epoch": 0.7557191092226564,
+      "grad_norm": 0.4952386048466494,
+      "learning_rate": 1.715153628556162e-06,
+      "loss": 0.4429,
+      "step": 2490
+    },
+    {
+      "epoch": 0.7587541257255587,
+      "grad_norm": 0.45327322111640855,
+      "learning_rate": 1.6753977648177682e-06,
+      "loss": 0.452,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7617891422284608,
+      "grad_norm": 0.560152662522095,
+      "learning_rate": 1.6360151391875395e-06,
+      "loss": 0.4482,
+      "step": 2510
+    },
+    {
+      "epoch": 0.7648241587313631,
+      "grad_norm": 0.5588616468957155,
+      "learning_rate": 1.5970101729753485e-06,
+      "loss": 0.4411,
+      "step": 2520
+    },
+    {
+      "epoch": 0.7678591752342654,
+      "grad_norm": 0.5012865331807312,
+      "learning_rate": 1.5583872450929455e-06,
+      "loss": 0.4466,
+      "step": 2530
+    },
+    {
+      "epoch": 0.7708941917371676,
+      "grad_norm": 0.4458865832841834,
+      "learning_rate": 1.5201506915623621e-06,
+      "loss": 0.443,
+      "step": 2540
+    },
+    {
+      "epoch": 0.7739292082400698,
+      "grad_norm": 0.5048770346419175,
+      "learning_rate": 1.4823048050291211e-06,
+      "loss": 0.452,
+      "step": 2550
+    },
+    {
+      "epoch": 0.776964224742972,
+      "grad_norm": 0.46420339110163,
+      "learning_rate": 1.4448538342803242e-06,
+      "loss": 0.4405,
+      "step": 2560
+    },
+    {
+      "epoch": 0.7799992412458743,
+      "grad_norm": 0.5148070470946807,
+      "learning_rate": 1.407801983767656e-06,
+      "loss": 0.4452,
+      "step": 2570
+    },
+    {
+      "epoch": 0.7830342577487766,
+      "grad_norm": 0.4919925143595241,
+      "learning_rate": 1.3711534131353738e-06,
+      "loss": 0.4481,
+      "step": 2580
+    },
+    {
+      "epoch": 0.7860692742516787,
+      "grad_norm": 0.8295554704623347,
+      "learning_rate": 1.3349122367533135e-06,
+      "loss": 0.4443,
+      "step": 2590
+    },
+    {
+      "epoch": 0.789104290754581,
+      "grad_norm": 0.4715835221582969,
+      "learning_rate": 1.2990825232550065e-06,
+      "loss": 0.4441,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7921393072574832,
+      "grad_norm": 0.4888383711595245,
+      "learning_rate": 1.2636682950808882e-06,
+      "loss": 0.4414,
+      "step": 2610
+    },
+    {
+      "epoch": 0.7951743237603854,
+      "grad_norm": 0.46367852635576223,
+      "learning_rate": 1.228673528026741e-06,
+      "loss": 0.443,
+      "step": 2620
+    },
+    {
+      "epoch": 0.7982093402632877,
+      "grad_norm": 0.458931669471863,
+      "learning_rate": 1.194102150797326e-06,
+      "loss": 0.445,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8012443567661899,
+      "grad_norm": 0.5805342428508335,
+      "learning_rate": 1.1599580445653496e-06,
+      "loss": 0.4416,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8042793732690922,
+      "grad_norm": 0.47446300706665095,
+      "learning_rate": 1.1262450425357175e-06,
+      "loss": 0.4527,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8073143897719944,
+      "grad_norm": 0.4585780912736001,
+      "learning_rate": 1.092966929515218e-06,
+      "loss": 0.44,
+      "step": 2660
+    },
+    {
+      "epoch": 0.8103494062748966,
+      "grad_norm": 0.48233598242441533,
+      "learning_rate": 1.0601274414876067e-06,
+      "loss": 0.4455,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8133844227777989,
+      "grad_norm": 0.46200584695129754,
+      "learning_rate": 1.0277302651941894e-06,
+      "loss": 0.4446,
+      "step": 2680
+    },
+    {
+      "epoch": 0.816419439280701,
+      "grad_norm": 0.4874246650348082,
+      "learning_rate": 9.95779037719926e-07,
+      "loss": 0.4397,
+      "step": 2690
+    },
+    {
+      "epoch": 0.8194544557836033,
+      "grad_norm": 0.4547919796548769,
+      "learning_rate": 9.642773460851141e-07,
+      "loss": 0.4473,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8224894722865056,
+      "grad_norm": 0.4972539970599672,
+      "learning_rate": 9.332287268426881e-07,
+      "loss": 0.4425,
+      "step": 2710
+    },
+    {
+      "epoch": 0.8255244887894078,
+      "grad_norm": 0.43865232063488374,
+      "learning_rate": 9.026366656811835e-07,
+      "loss": 0.4401,
+      "step": 2720
+    },
+    {
+      "epoch": 0.82855950529231,
+      "grad_norm": 1.1602238104916722,
+      "learning_rate": 8.725045970334262e-07,
+      "loss": 0.4504,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8315945217952123,
+      "grad_norm": 0.4663648778218256,
+      "learning_rate": 8.428359036909455e-07,
+      "loss": 0.4391,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8346295382981145,
+      "grad_norm": 0.48682417123785116,
+      "learning_rate": 8.136339164242241e-07,
+      "loss": 0.4467,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8376645548010168,
+      "grad_norm": 0.4673166286188927,
+      "learning_rate": 7.849019136087477e-07,
+      "loss": 0.4398,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8406995713039189,
+      "grad_norm": 0.4903812570342262,
+      "learning_rate": 7.566431208569747e-07,
+      "loss": 0.4413,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8437345878068212,
+      "grad_norm": 0.485844612436569,
+      "learning_rate": 7.288607106561935e-07,
+      "loss": 0.4451,
+      "step": 2780
+    },
+    {
+      "epoch": 0.8467696043097235,
+      "grad_norm": 0.4585651698156433,
+      "learning_rate": 7.015578020123804e-07,
+      "loss": 0.439,
+      "step": 2790
+    },
+    {
+      "epoch": 0.8498046208126256,
+      "grad_norm": 0.4839043585723541,
+      "learning_rate": 6.747374601000229e-07,
+      "loss": 0.4451,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8528396373155279,
+      "grad_norm": 0.45692832107739795,
+      "learning_rate": 6.484026959180256e-07,
+      "loss": 0.439,
+      "step": 2810
+    },
+    {
+      "epoch": 0.8558746538184301,
+      "grad_norm": 0.8934971320404392,
+      "learning_rate": 6.225564659516653e-07,
+      "loss": 0.4427,
+      "step": 2820
+    },
+    {
+      "epoch": 0.8589096703213324,
+      "grad_norm": 0.42447350665857003,
+      "learning_rate": 5.972016718406832e-07,
+      "loss": 0.445,
+      "step": 2830
+    },
+    {
+      "epoch": 0.8619446868242346,
+      "grad_norm": 0.5221390912623963,
+      "learning_rate": 5.723411600535378e-07,
+      "loss": 0.4493,
+      "step": 2840
+    },
+    {
+      "epoch": 0.8649797033271368,
+      "grad_norm": 0.470728180227603,
+      "learning_rate": 5.4797772156783e-07,
+      "loss": 0.4436,
+      "step": 2850
+    },
+    {
+      "epoch": 0.8680147198300391,
+      "grad_norm": 0.47672096853939294,
+      "learning_rate": 5.24114091556992e-07,
+      "loss": 0.4405,
+      "step": 2860
+    },
+    {
+      "epoch": 0.8710497363329414,
+      "grad_norm": 0.4546129075040933,
+      "learning_rate": 5.00752949083202e-07,
+      "loss": 0.4534,
+      "step": 2870
+    },
+    {
+      "epoch": 0.8740847528358435,
+      "grad_norm": 0.463106848164873,
+      "learning_rate": 4.778969167966346e-07,
+      "loss": 0.444,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8771197693387458,
+      "grad_norm": 0.4491761462781034,
+      "learning_rate": 4.5554856064101314e-07,
+      "loss": 0.436,
+      "step": 2890
+    },
+    {
+      "epoch": 0.880154785841648,
+      "grad_norm": 0.4675366494918407,
+      "learning_rate": 4.337103895655581e-07,
+      "loss": 0.4531,
+      "step": 2900
+    },
+    {
+      "epoch": 0.8831898023445502,
+      "grad_norm": 0.44541163156936503,
+      "learning_rate": 4.123848552433019e-07,
+      "loss": 0.4375,
+      "step": 2910
+    },
+    {
+      "epoch": 0.8862248188474525,
+      "grad_norm": 0.49240823007466994,
+      "learning_rate": 3.9157435179586756e-07,
+      "loss": 0.4374,
+      "step": 2920
+    },
+    {
+      "epoch": 0.8892598353503547,
+      "grad_norm": 0.4733511579541881,
+      "learning_rate": 3.712812155246759e-07,
+      "loss": 0.4441,
+      "step": 2930
+    },
+    {
+      "epoch": 0.892294851853257,
+      "grad_norm": 0.5930159408214484,
+      "learning_rate": 3.5150772464867314e-07,
+      "loss": 0.4441,
+      "step": 2940
+    },
+    {
+      "epoch": 0.8953298683561592,
+      "grad_norm": 0.4915855850221476,
+      "learning_rate": 3.322560990485535e-07,
+      "loss": 0.4475,
+      "step": 2950
+    },
+    {
+      "epoch": 0.8983648848590614,
+      "grad_norm": 0.4400578392570043,
+      "learning_rate": 3.135285000175531e-07,
+      "loss": 0.437,
+      "step": 2960
+    },
+    {
+      "epoch": 0.9013999013619637,
+      "grad_norm": 1.0625536086809468,
+      "learning_rate": 2.953270300188038e-07,
+      "loss": 0.4461,
+      "step": 2970
+    },
+    {
+      "epoch": 0.9044349178648659,
+      "grad_norm": 0.47898803434881615,
+      "learning_rate": 2.776537324493045e-07,
+      "loss": 0.4411,
+      "step": 2980
+    },
+    {
+      "epoch": 0.9074699343677681,
+      "grad_norm": 0.48013757465246243,
+      "learning_rate": 2.6051059141051713e-07,
+      "loss": 0.4463,
+      "step": 2990
+    },
+    {
+      "epoch": 0.9105049508706704,
+      "grad_norm": 0.46792544413322756,
+      "learning_rate": 2.4389953148561574e-07,
+      "loss": 0.4541,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9135399673735726,
+      "grad_norm": 0.47509286467451683,
+      "learning_rate": 2.2782241752343004e-07,
+      "loss": 0.4392,
+      "step": 3010
+    },
+    {
+      "epoch": 0.9165749838764748,
+      "grad_norm": 0.5355760986925688,
+      "learning_rate": 2.122810544290782e-07,
+      "loss": 0.4459,
+      "step": 3020
+    },
+    {
+      "epoch": 0.919610000379377,
+      "grad_norm": 0.4481951370049728,
+      "learning_rate": 1.972771869613499e-07,
+      "loss": 0.4408,
+      "step": 3030
+    },
+    {
+      "epoch": 0.9226450168822793,
+      "grad_norm": 1.212596637597613,
+      "learning_rate": 1.8281249953681633e-07,
+      "loss": 0.4524,
+      "step": 3040
+    },
+    {
+      "epoch": 0.9256800333851816,
+      "grad_norm": 0.4653062821594877,
+      "learning_rate": 1.6888861604074158e-07,
+      "loss": 0.4547,
+      "step": 3050
+    },
+    {
+      "epoch": 0.9287150498880837,
+      "grad_norm": 0.4417864126009544,
+      "learning_rate": 1.5550709964476606e-07,
+      "loss": 0.4343,
+      "step": 3060
+    },
+    {
+      "epoch": 0.931750066390986,
+      "grad_norm": 0.4636627611118036,
+      "learning_rate": 1.4266945263142152e-07,
+      "loss": 0.4442,
+      "step": 3070
+    },
+    {
+      "epoch": 0.9347850828938883,
+      "grad_norm": 0.4750602636819015,
+      "learning_rate": 1.3037711622547633e-07,
+      "loss": 0.4402,
+      "step": 3080
+    },
+    {
+      "epoch": 0.9378200993967905,
+      "grad_norm": 0.5641879257431062,
+      "learning_rate": 1.1863147043213453e-07,
+      "loss": 0.4463,
+      "step": 3090
+    },
+    {
+      "epoch": 0.9408551158996927,
+      "grad_norm": 0.48298472160583994,
+      "learning_rate": 1.0743383388210849e-07,
+      "loss": 0.4509,
+      "step": 3100
+    },
+    {
+      "epoch": 0.9438901324025949,
+      "grad_norm": 0.4709867848354663,
+      "learning_rate": 9.678546368358299e-08,
+      "loss": 0.4469,
+      "step": 3110
+    },
+    {
+      "epoch": 0.9469251489054972,
+      "grad_norm": 0.45111687792423893,
+      "learning_rate": 8.668755528108586e-08,
+      "loss": 0.446,
+      "step": 3120
+    },
+    {
+      "epoch": 0.9499601654083994,
+      "grad_norm": 0.4640080663242888,
+      "learning_rate": 7.714124232127974e-08,
+      "loss": 0.447,
+      "step": 3130
+    },
+    {
+      "epoch": 0.9529951819113016,
+      "grad_norm": 0.4835533725431675,
+      "learning_rate": 6.814759652569391e-08,
+      "loss": 0.4471,
+      "step": 3140
+    },
+    {
+      "epoch": 0.9560301984142039,
+      "grad_norm": 0.4775784576850005,
+      "learning_rate": 5.970762757040339e-08,
+      "loss": 0.4581,
+      "step": 3150
+    },
+    {
+      "epoch": 0.9590652149171061,
+      "grad_norm": 0.4406150853474837,
+      "learning_rate": 5.182228297268388e-08,
+      "loss": 0.4377,
+      "step": 3160
+    },
+    {
+      "epoch": 0.9621002314200083,
+      "grad_norm": 0.4875065749326578,
+      "learning_rate": 4.449244798463037e-08,
+      "loss": 0.4466,
+      "step": 3170
+    },
+    {
+      "epoch": 0.9651352479229106,
+      "grad_norm": 0.5331920537623118,
+      "learning_rate": 3.7718945493781523e-08,
+      "loss": 0.4457,
+      "step": 3180
+    },
+    {
+      "epoch": 0.9681702644258128,
+      "grad_norm": 0.4829553299763894,
+      "learning_rate": 3.150253593073027e-08,
+      "loss": 0.4373,
+      "step": 3190
+    },
+    {
+      "epoch": 0.971205280928715,
+      "grad_norm": 0.4683361415791196,
+      "learning_rate": 2.5843917183761002e-08,
+      "loss": 0.4541,
+      "step": 3200
+    },
+    {
+      "epoch": 0.9742402974316173,
+      "grad_norm": 0.4647148561695759,
+      "learning_rate": 2.0743724520495e-08,
+      "loss": 0.4372,
+      "step": 3210
+    },
+    {
+      "epoch": 0.9772753139345195,
+      "grad_norm": 0.45464384300389377,
+      "learning_rate": 1.6202530516574165e-08,
+      "loss": 0.4495,
+      "step": 3220
+    },
+    {
+      "epoch": 0.9803103304374218,
+      "grad_norm": 0.4823468219123769,
+      "learning_rate": 1.222084499138243e-08,
+      "loss": 0.4408,
+      "step": 3230
+    },
+    {
+      "epoch": 0.9833453469403239,
+      "grad_norm": 0.4802790220017127,
+      "learning_rate": 8.799114950806542e-09,
+      "loss": 0.4419,
+      "step": 3240
+    },
+    {
+      "epoch": 0.9863803634432262,
+      "grad_norm": 0.46706355617957335,
+      "learning_rate": 5.9377245370551005e-09,
+      "loss": 0.4453,
+      "step": 3250
+    },
+    {
+      "epoch": 0.9894153799461285,
+      "grad_norm": 0.440626466158207,
+      "learning_rate": 3.636994985534159e-09,
+      "loss": 0.4345,
+      "step": 3260
+    },
+    {
+      "epoch": 0.9924503964490307,
+      "grad_norm": 0.4555769223211312,
+      "learning_rate": 1.8971845887794105e-09,
+      "loss": 0.4468,
+      "step": 3270
+    },
+    {
+      "epoch": 0.9954854129519329,
+      "grad_norm": 0.4398220412821882,
+      "learning_rate": 7.184886674627134e-10,
+      "loss": 0.4384,
+      "step": 3280
+    },
+    {
+      "epoch": 0.9985204294548352,
+      "grad_norm": 0.45149244572807423,
+      "learning_rate": 1.010395484624116e-10,
+      "loss": 0.44,
+      "step": 3290
+    },
+    {
+      "epoch": 1.0,
+      "step": 3295,
+      "total_flos": 8.530187773318005e+18,
+      "train_loss": 0.4728999632081421,
+      "train_runtime": 62323.8697,
+      "train_samples_per_second": 6.767,
+      "train_steps_per_second": 0.053
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3295,
+  "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": 8.530187773318005e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafbfc3ba6af5d060b5d81aa37ec528d53bafe2a3b06bee39c5897774193a0dc
+size 8209