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/Qwen3-4B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen-4b-grade-v2
+  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. -->
+
+# qwen-4b-grade-v2
+
+This model is a fine-tuned version of [/home/aiops/xueyj/llms/Qwen3-4B-Base](https://huggingface.co//home/aiops/xueyj/llms/Qwen3-4B-Base) on the grade_model_training_data dataset.
+
+## 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: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch 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: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 159350737469440.0,
+    "train_loss": 0.46467527450543444,
+    "train_runtime": 10302.033,
+    "train_samples_per_second": 3.277,
+    "train_steps_per_second": 0.205
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9edf2a64c7357e1b7fcf15076863db5ad07ef37d25035cabba58304b9cd592f
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a456c8e63cb508011d505906c9486777d0bbc989329a37182de5a78b96f864c
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 159350737469440.0,
+    "train_loss": 0.46467527450543444,
+    "train_runtime": 10302.033,
+    "train_samples_per_second": 3.277,
+    "train_steps_per_second": 0.205
+}

trainer_log.jsonl

@@ -0,0 +1,212 @@
+{"current_steps": 10, "total_steps": 2110, "loss": 1.0344, "lr": 4.265402843601896e-07, "epoch": 0.009478672985781991, "percentage": 0.47, "elapsed_time": "0:00:55", "remaining_time": "3:13:00"}
+{"current_steps": 20, "total_steps": 2110, "loss": 1.0038, "lr": 9.004739336492892e-07, "epoch": 0.018957345971563982, "percentage": 0.95, "elapsed_time": "0:01:42", "remaining_time": "2:58:41"}
+{"current_steps": 30, "total_steps": 2110, "loss": 0.9018, "lr": 1.3744075829383887e-06, "epoch": 0.02843601895734597, "percentage": 1.42, "elapsed_time": "0:02:29", "remaining_time": "2:53:11"}
+{"current_steps": 40, "total_steps": 2110, "loss": 0.8064, "lr": 1.8483412322274883e-06, "epoch": 0.037914691943127965, "percentage": 1.9, "elapsed_time": "0:03:17", "remaining_time": "2:49:59"}
+{"current_steps": 50, "total_steps": 2110, "loss": 0.7376, "lr": 2.322274881516588e-06, "epoch": 0.04739336492890995, "percentage": 2.37, "elapsed_time": "0:04:08", "remaining_time": "2:50:52"}
+{"current_steps": 60, "total_steps": 2110, "loss": 0.6845, "lr": 2.7962085308056874e-06, "epoch": 0.05687203791469194, "percentage": 2.84, "elapsed_time": "0:05:00", "remaining_time": "2:51:01"}
+{"current_steps": 70, "total_steps": 2110, "loss": 0.6568, "lr": 3.2701421800947867e-06, "epoch": 0.06635071090047394, "percentage": 3.32, "elapsed_time": "0:05:46", "remaining_time": "2:48:16"}
+{"current_steps": 80, "total_steps": 2110, "loss": 0.6454, "lr": 3.7440758293838865e-06, "epoch": 0.07582938388625593, "percentage": 3.79, "elapsed_time": "0:06:37", "remaining_time": "2:48:09"}
+{"current_steps": 90, "total_steps": 2110, "loss": 0.6254, "lr": 4.218009478672986e-06, "epoch": 0.08530805687203792, "percentage": 4.27, "elapsed_time": "0:07:27", "remaining_time": "2:47:25"}
+{"current_steps": 100, "total_steps": 2110, "loss": 0.6049, "lr": 4.691943127962086e-06, "epoch": 0.0947867298578199, "percentage": 4.74, "elapsed_time": "0:08:15", "remaining_time": "2:45:55"}
+{"current_steps": 110, "total_steps": 2110, "loss": 0.6026, "lr": 5.165876777251185e-06, "epoch": 0.10426540284360189, "percentage": 5.21, "elapsed_time": "0:09:02", "remaining_time": "2:44:25"}
+{"current_steps": 120, "total_steps": 2110, "loss": 0.6005, "lr": 5.639810426540285e-06, "epoch": 0.11374407582938388, "percentage": 5.69, "elapsed_time": "0:09:48", "remaining_time": "2:42:37"}
+{"current_steps": 130, "total_steps": 2110, "loss": 0.6072, "lr": 6.1137440758293845e-06, "epoch": 0.12322274881516587, "percentage": 6.16, "elapsed_time": "0:10:38", "remaining_time": "2:42:02"}
+{"current_steps": 140, "total_steps": 2110, "loss": 0.5851, "lr": 6.587677725118484e-06, "epoch": 0.13270142180094788, "percentage": 6.64, "elapsed_time": "0:11:27", "remaining_time": "2:41:16"}
+{"current_steps": 150, "total_steps": 2110, "loss": 0.5812, "lr": 7.061611374407583e-06, "epoch": 0.14218009478672985, "percentage": 7.11, "elapsed_time": "0:12:16", "remaining_time": "2:40:28"}
+{"current_steps": 160, "total_steps": 2110, "loss": 0.5793, "lr": 7.535545023696683e-06, "epoch": 0.15165876777251186, "percentage": 7.58, "elapsed_time": "0:13:04", "remaining_time": "2:39:23"}
+{"current_steps": 170, "total_steps": 2110, "loss": 0.5832, "lr": 8.009478672985783e-06, "epoch": 0.16113744075829384, "percentage": 8.06, "elapsed_time": "0:13:52", "remaining_time": "2:38:16"}
+{"current_steps": 180, "total_steps": 2110, "loss": 0.568, "lr": 8.483412322274883e-06, "epoch": 0.17061611374407584, "percentage": 8.53, "elapsed_time": "0:14:38", "remaining_time": "2:36:59"}
+{"current_steps": 190, "total_steps": 2110, "loss": 0.5696, "lr": 8.957345971563981e-06, "epoch": 0.18009478672985782, "percentage": 9.0, "elapsed_time": "0:15:28", "remaining_time": "2:36:20"}
+{"current_steps": 200, "total_steps": 2110, "loss": 0.5674, "lr": 9.431279620853082e-06, "epoch": 0.1895734597156398, "percentage": 9.48, "elapsed_time": "0:16:21", "remaining_time": "2:36:16"}
+{"current_steps": 210, "total_steps": 2110, "loss": 0.5657, "lr": 9.905213270142182e-06, "epoch": 0.1990521327014218, "percentage": 9.95, "elapsed_time": "0:17:08", "remaining_time": "2:35:02"}
+{"current_steps": 220, "total_steps": 2110, "loss": 0.5646, "lr": 9.999562111581011e-06, "epoch": 0.20853080568720378, "percentage": 10.43, "elapsed_time": "0:17:55", "remaining_time": "2:34:02"}
+{"current_steps": 230, "total_steps": 2110, "loss": 0.5569, "lr": 9.997783321329104e-06, "epoch": 0.21800947867298578, "percentage": 10.9, "elapsed_time": "0:18:42", "remaining_time": "2:32:51"}
+{"current_steps": 240, "total_steps": 2110, "loss": 0.5551, "lr": 9.994636747659363e-06, "epoch": 0.22748815165876776, "percentage": 11.37, "elapsed_time": "0:19:32", "remaining_time": "2:32:15"}
+{"current_steps": 250, "total_steps": 2110, "loss": 0.5631, "lr": 9.990123251719826e-06, "epoch": 0.23696682464454977, "percentage": 11.85, "elapsed_time": "0:20:22", "remaining_time": "2:31:34"}
+{"current_steps": 260, "total_steps": 2110, "loss": 0.5544, "lr": 9.9842440687551e-06, "epoch": 0.24644549763033174, "percentage": 12.32, "elapsed_time": "0:21:11", "remaining_time": "2:30:46"}
+{"current_steps": 270, "total_steps": 2110, "loss": 0.5317, "lr": 9.977000807768306e-06, "epoch": 0.2559241706161137, "percentage": 12.8, "elapsed_time": "0:21:58", "remaining_time": "2:29:42"}
+{"current_steps": 280, "total_steps": 2110, "loss": 0.544, "lr": 9.968395451080736e-06, "epoch": 0.26540284360189575, "percentage": 13.27, "elapsed_time": "0:22:47", "remaining_time": "2:28:58"}
+{"current_steps": 290, "total_steps": 2110, "loss": 0.562, "lr": 9.958430353789321e-06, "epoch": 0.27488151658767773, "percentage": 13.74, "elapsed_time": "0:23:36", "remaining_time": "2:28:11"}
+{"current_steps": 300, "total_steps": 2110, "loss": 0.5408, "lr": 9.947108243122107e-06, "epoch": 0.2843601895734597, "percentage": 14.22, "elapsed_time": "0:24:25", "remaining_time": "2:27:19"}
+{"current_steps": 310, "total_steps": 2110, "loss": 0.5324, "lr": 9.934432217691862e-06, "epoch": 0.2938388625592417, "percentage": 14.69, "elapsed_time": "0:25:12", "remaining_time": "2:26:24"}
+{"current_steps": 320, "total_steps": 2110, "loss": 0.5336, "lr": 9.920405746648067e-06, "epoch": 0.3033175355450237, "percentage": 15.17, "elapsed_time": "0:26:00", "remaining_time": "2:25:31"}
+{"current_steps": 330, "total_steps": 2110, "loss": 0.5479, "lr": 9.905032668727467e-06, "epoch": 0.3127962085308057, "percentage": 15.64, "elapsed_time": "0:26:50", "remaining_time": "2:24:45"}
+{"current_steps": 340, "total_steps": 2110, "loss": 0.5273, "lr": 9.888317191203513e-06, "epoch": 0.3222748815165877, "percentage": 16.11, "elapsed_time": "0:27:36", "remaining_time": "2:23:45"}
+{"current_steps": 350, "total_steps": 2110, "loss": 0.5211, "lr": 9.870263888734905e-06, "epoch": 0.33175355450236965, "percentage": 16.59, "elapsed_time": "0:28:23", "remaining_time": "2:22:47"}
+{"current_steps": 360, "total_steps": 2110, "loss": 0.5401, "lr": 9.85087770211363e-06, "epoch": 0.3412322274881517, "percentage": 17.06, "elapsed_time": "0:29:11", "remaining_time": "2:21:54"}
+{"current_steps": 370, "total_steps": 2110, "loss": 0.5274, "lr": 9.830163936912752e-06, "epoch": 0.35071090047393366, "percentage": 17.54, "elapsed_time": "0:30:03", "remaining_time": "2:21:19"}
+{"current_steps": 380, "total_steps": 2110, "loss": 0.528, "lr": 9.808128262034411e-06, "epoch": 0.36018957345971564, "percentage": 18.01, "elapsed_time": "0:30:53", "remaining_time": "2:20:40"}
+{"current_steps": 390, "total_steps": 2110, "loss": 0.5216, "lr": 9.784776708158363e-06, "epoch": 0.3696682464454976, "percentage": 18.48, "elapsed_time": "0:31:43", "remaining_time": "2:19:55"}
+{"current_steps": 400, "total_steps": 2110, "loss": 0.5133, "lr": 9.760115666091518e-06, "epoch": 0.3791469194312796, "percentage": 18.96, "elapsed_time": "0:32:31", "remaining_time": "2:19:03"}
+{"current_steps": 410, "total_steps": 2110, "loss": 0.5228, "lr": 9.73415188501891e-06, "epoch": 0.3886255924170616, "percentage": 19.43, "elapsed_time": "0:33:21", "remaining_time": "2:18:19"}
+{"current_steps": 420, "total_steps": 2110, "loss": 0.5371, "lr": 9.706892470656601e-06, "epoch": 0.3981042654028436, "percentage": 19.91, "elapsed_time": "0:34:10", "remaining_time": "2:17:30"}
+{"current_steps": 430, "total_steps": 2110, "loss": 0.5335, "lr": 9.678344883306997e-06, "epoch": 0.4075829383886256, "percentage": 20.38, "elapsed_time": "0:35:00", "remaining_time": "2:16:48"}
+{"current_steps": 440, "total_steps": 2110, "loss": 0.5251, "lr": 9.648516935817133e-06, "epoch": 0.41706161137440756, "percentage": 20.85, "elapsed_time": "0:35:46", "remaining_time": "2:15:47"}
+{"current_steps": 450, "total_steps": 2110, "loss": 0.5412, "lr": 9.617416791440461e-06, "epoch": 0.4265402843601896, "percentage": 21.33, "elapsed_time": "0:36:34", "remaining_time": "2:14:54"}
+{"current_steps": 460, "total_steps": 2110, "loss": 0.5377, "lr": 9.585052961602759e-06, "epoch": 0.43601895734597157, "percentage": 21.8, "elapsed_time": "0:37:21", "remaining_time": "2:14:00"}
+{"current_steps": 470, "total_steps": 2110, "loss": 0.5164, "lr": 9.551434303572725e-06, "epoch": 0.44549763033175355, "percentage": 22.27, "elapsed_time": "0:38:09", "remaining_time": "2:13:10"}
+{"current_steps": 480, "total_steps": 2110, "loss": 0.5006, "lr": 9.51657001803795e-06, "epoch": 0.4549763033175355, "percentage": 22.75, "elapsed_time": "0:38:58", "remaining_time": "2:12:19"}
+{"current_steps": 490, "total_steps": 2110, "loss": 0.5243, "lr": 9.480469646586888e-06, "epoch": 0.46445497630331756, "percentage": 23.22, "elapsed_time": "0:39:46", "remaining_time": "2:11:31"}
+{"current_steps": 500, "total_steps": 2110, "loss": 0.539, "lr": 9.443143069097531e-06, "epoch": 0.47393364928909953, "percentage": 23.7, "elapsed_time": "0:40:34", "remaining_time": "2:10:38"}
+{"current_steps": 510, "total_steps": 2110, "loss": 0.501, "lr": 9.404600501033505e-06, "epoch": 0.4834123222748815, "percentage": 24.17, "elapsed_time": "0:41:20", "remaining_time": "2:09:42"}
+{"current_steps": 520, "total_steps": 2110, "loss": 0.5334, "lr": 9.364852490648327e-06, "epoch": 0.4928909952606635, "percentage": 24.64, "elapsed_time": "0:42:06", "remaining_time": "2:08:46"}
+{"current_steps": 530, "total_steps": 2110, "loss": 0.5094, "lr": 9.323909916098566e-06, "epoch": 0.5023696682464455, "percentage": 25.12, "elapsed_time": "0:42:58", "remaining_time": "2:08:05"}
+{"current_steps": 540, "total_steps": 2110, "loss": 0.5109, "lr": 9.28178398246675e-06, "epoch": 0.5118483412322274, "percentage": 25.59, "elapsed_time": "0:43:44", "remaining_time": "2:07:10"}
+{"current_steps": 550, "total_steps": 2110, "loss": 0.4997, "lr": 9.238486218694767e-06, "epoch": 0.5213270142180095, "percentage": 26.07, "elapsed_time": "0:44:32", "remaining_time": "2:06:20"}
+{"current_steps": 560, "total_steps": 2110, "loss": 0.5146, "lr": 9.194028474428651e-06, "epoch": 0.5308056872037915, "percentage": 26.54, "elapsed_time": "0:45:23", "remaining_time": "2:05:37"}
+{"current_steps": 570, "total_steps": 2110, "loss": 0.5126, "lr": 9.148422916775596e-06, "epoch": 0.5402843601895735, "percentage": 27.01, "elapsed_time": "0:46:12", "remaining_time": "2:04:50"}
+{"current_steps": 580, "total_steps": 2110, "loss": 0.5269, "lr": 9.101682026974086e-06, "epoch": 0.5497630331753555, "percentage": 27.49, "elapsed_time": "0:47:04", "remaining_time": "2:04:11"}
+{"current_steps": 590, "total_steps": 2110, "loss": 0.5123, "lr": 9.053818596978051e-06, "epoch": 0.5592417061611374, "percentage": 27.96, "elapsed_time": "0:47:51", "remaining_time": "2:03:18"}
+{"current_steps": 600, "total_steps": 2110, "loss": 0.5185, "lr": 9.004845725955993e-06, "epoch": 0.5687203791469194, "percentage": 28.44, "elapsed_time": "0:48:39", "remaining_time": "2:02:26"}
+{"current_steps": 610, "total_steps": 2110, "loss": 0.5104, "lr": 8.954776816706034e-06, "epoch": 0.5781990521327014, "percentage": 28.91, "elapsed_time": "0:49:26", "remaining_time": "2:01:35"}
+{"current_steps": 620, "total_steps": 2110, "loss": 0.5064, "lr": 8.903625571987863e-06, "epoch": 0.5876777251184834, "percentage": 29.38, "elapsed_time": "0:50:16", "remaining_time": "2:00:49"}
+{"current_steps": 630, "total_steps": 2110, "loss": 0.5075, "lr": 8.851405990772588e-06, "epoch": 0.5971563981042654, "percentage": 29.86, "elapsed_time": "0:51:01", "remaining_time": "1:59:50"}
+{"current_steps": 640, "total_steps": 2110, "loss": 0.5316, "lr": 8.798132364411532e-06, "epoch": 0.6066350710900474, "percentage": 30.33, "elapsed_time": "0:51:49", "remaining_time": "1:59:01"}
+{"current_steps": 650, "total_steps": 2110, "loss": 0.5107, "lr": 8.743819272724996e-06, "epoch": 0.6161137440758294, "percentage": 30.81, "elapsed_time": "0:52:40", "remaining_time": "1:58:20"}
+{"current_steps": 660, "total_steps": 2110, "loss": 0.5025, "lr": 8.688481580012092e-06, "epoch": 0.6255924170616114, "percentage": 31.28, "elapsed_time": "0:53:32", "remaining_time": "1:57:38"}
+{"current_steps": 670, "total_steps": 2110, "loss": 0.5203, "lr": 8.632134430982708e-06, "epoch": 0.6350710900473934, "percentage": 31.75, "elapsed_time": "0:54:19", "remaining_time": "1:56:46"}
+{"current_steps": 680, "total_steps": 2110, "loss": 0.5229, "lr": 8.574793246612727e-06, "epoch": 0.6445497630331753, "percentage": 32.23, "elapsed_time": "0:55:09", "remaining_time": "1:55:59"}
+{"current_steps": 690, "total_steps": 2110, "loss": 0.5127, "lr": 8.516473719923658e-06, "epoch": 0.6540284360189573, "percentage": 32.7, "elapsed_time": "0:55:57", "remaining_time": "1:55:10"}
+{"current_steps": 700, "total_steps": 2110, "loss": 0.5215, "lr": 8.457191811687788e-06, "epoch": 0.6635071090047393, "percentage": 33.18, "elapsed_time": "0:56:44", "remaining_time": "1:54:18"}
+{"current_steps": 710, "total_steps": 2110, "loss": 0.5195, "lr": 8.396963746060076e-06, "epoch": 0.6729857819905213, "percentage": 33.65, "elapsed_time": "0:57:35", "remaining_time": "1:53:33"}
+{"current_steps": 720, "total_steps": 2110, "loss": 0.511, "lr": 8.335806006137962e-06, "epoch": 0.6824644549763034, "percentage": 34.12, "elapsed_time": "0:58:24", "remaining_time": "1:52:45"}
+{"current_steps": 730, "total_steps": 2110, "loss": 0.497, "lr": 8.273735329450296e-06, "epoch": 0.6919431279620853, "percentage": 34.6, "elapsed_time": "0:59:16", "remaining_time": "1:52:03"}
+{"current_steps": 740, "total_steps": 2110, "loss": 0.5036, "lr": 8.210768703376651e-06, "epoch": 0.7014218009478673, "percentage": 35.07, "elapsed_time": "1:00:02", "remaining_time": "1:51:09"}
+{"current_steps": 750, "total_steps": 2110, "loss": 0.5071, "lr": 8.146923360498252e-06, "epoch": 0.7109004739336493, "percentage": 35.55, "elapsed_time": "1:00:52", "remaining_time": "1:50:22"}
+{"current_steps": 760, "total_steps": 2110, "loss": 0.5022, "lr": 8.082216773881792e-06, "epoch": 0.7203791469194313, "percentage": 36.02, "elapsed_time": "1:01:42", "remaining_time": "1:49:37"}
+{"current_steps": 770, "total_steps": 2110, "loss": 0.5073, "lr": 8.016666652297443e-06, "epoch": 0.7298578199052133, "percentage": 36.49, "elapsed_time": "1:02:29", "remaining_time": "1:48:45"}
+{"current_steps": 780, "total_steps": 2110, "loss": 0.4973, "lr": 7.950290935372346e-06, "epoch": 0.7393364928909952, "percentage": 36.97, "elapsed_time": "1:03:17", "remaining_time": "1:47:54"}
+{"current_steps": 790, "total_steps": 2110, "loss": 0.4997, "lr": 7.883107788680946e-06, "epoch": 0.7488151658767772, "percentage": 37.44, "elapsed_time": "1:04:04", "remaining_time": "1:47:02"}
+{"current_steps": 800, "total_steps": 2110, "loss": 0.5061, "lr": 7.815135598773455e-06, "epoch": 0.7582938388625592, "percentage": 37.91, "elapsed_time": "1:04:55", "remaining_time": "1:46:18"}
+{"current_steps": 810, "total_steps": 2110, "loss": 0.4849, "lr": 7.746392968143872e-06, "epoch": 0.7677725118483413, "percentage": 38.39, "elapsed_time": "1:05:40", "remaining_time": "1:45:24"}
+{"current_steps": 820, "total_steps": 2110, "loss": 0.5013, "lr": 7.676898710138878e-06, "epoch": 0.7772511848341233, "percentage": 38.86, "elapsed_time": "1:06:27", "remaining_time": "1:44:33"}
+{"current_steps": 830, "total_steps": 2110, "loss": 0.5186, "lr": 7.606671843809045e-06, "epoch": 0.7867298578199052, "percentage": 39.34, "elapsed_time": "1:07:15", "remaining_time": "1:43:43"}
+{"current_steps": 840, "total_steps": 2110, "loss": 0.5156, "lr": 7.5357315887037365e-06, "epoch": 0.7962085308056872, "percentage": 39.81, "elapsed_time": "1:08:03", "remaining_time": "1:42:53"}
+{"current_steps": 850, "total_steps": 2110, "loss": 0.4956, "lr": 7.46409735961114e-06, "epoch": 0.8056872037914692, "percentage": 40.28, "elapsed_time": "1:08:51", "remaining_time": "1:42:04"}
+{"current_steps": 860, "total_steps": 2110, "loss": 0.486, "lr": 7.3917887612448665e-06, "epoch": 0.8151658767772512, "percentage": 40.76, "elapsed_time": "1:09:36", "remaining_time": "1:41:10"}
+{"current_steps": 870, "total_steps": 2110, "loss": 0.4865, "lr": 7.318825582878571e-06, "epoch": 0.8246445497630331, "percentage": 41.23, "elapsed_time": "1:10:27", "remaining_time": "1:40:24"}
+{"current_steps": 880, "total_steps": 2110, "loss": 0.5036, "lr": 7.245227792930062e-06, "epoch": 0.8341232227488151, "percentage": 41.71, "elapsed_time": "1:11:13", "remaining_time": "1:39:32"}
+{"current_steps": 890, "total_steps": 2110, "loss": 0.4854, "lr": 7.1710155334963875e-06, "epoch": 0.8436018957345972, "percentage": 42.18, "elapsed_time": "1:12:04", "remaining_time": "1:38:47"}
+{"current_steps": 900, "total_steps": 2110, "loss": 0.4835, "lr": 7.096209114841384e-06, "epoch": 0.8530805687203792, "percentage": 42.65, "elapsed_time": "1:12:52", "remaining_time": "1:37:58"}
+{"current_steps": 910, "total_steps": 2110, "loss": 0.4944, "lr": 7.0208290098372026e-06, "epoch": 0.8625592417061612, "percentage": 43.13, "elapsed_time": "1:13:39", "remaining_time": "1:37:07"}
+{"current_steps": 920, "total_steps": 2110, "loss": 0.4856, "lr": 6.944895848361338e-06, "epoch": 0.8720379146919431, "percentage": 43.6, "elapsed_time": "1:14:25", "remaining_time": "1:36:16"}
+{"current_steps": 930, "total_steps": 2110, "loss": 0.4955, "lr": 6.868430411650682e-06, "epoch": 0.8815165876777251, "percentage": 44.08, "elapsed_time": "1:15:14", "remaining_time": "1:35:27"}
+{"current_steps": 940, "total_steps": 2110, "loss": 0.4739, "lr": 6.791453626614155e-06, "epoch": 0.8909952606635071, "percentage": 44.55, "elapsed_time": "1:16:06", "remaining_time": "1:34:43"}
+{"current_steps": 950, "total_steps": 2110, "loss": 0.5094, "lr": 6.71398656010547e-06, "epoch": 0.9004739336492891, "percentage": 45.02, "elapsed_time": "1:16:53", "remaining_time": "1:33:53"}
+{"current_steps": 960, "total_steps": 2110, "loss": 0.4901, "lr": 6.636050413157605e-06, "epoch": 0.909952606635071, "percentage": 45.5, "elapsed_time": "1:17:46", "remaining_time": "1:33:10"}
+{"current_steps": 970, "total_steps": 2110, "loss": 0.5103, "lr": 6.557666515180539e-06, "epoch": 0.919431279620853, "percentage": 45.97, "elapsed_time": "1:18:37", "remaining_time": "1:32:23"}
+{"current_steps": 980, "total_steps": 2110, "loss": 0.5073, "lr": 6.478856318123861e-06, "epoch": 0.9289099526066351, "percentage": 46.45, "elapsed_time": "1:19:26", "remaining_time": "1:31:36"}
+{"current_steps": 990, "total_steps": 2110, "loss": 0.4936, "lr": 6.399641390605849e-06, "epoch": 0.9383886255924171, "percentage": 46.92, "elapsed_time": "1:20:16", "remaining_time": "1:30:48"}
+{"current_steps": 1000, "total_steps": 2110, "loss": 0.4827, "lr": 6.32004341201061e-06, "epoch": 0.9478672985781991, "percentage": 47.39, "elapsed_time": "1:21:06", "remaining_time": "1:30:01"}
+{"current_steps": 1010, "total_steps": 2110, "loss": 0.4942, "lr": 6.240084166554909e-06, "epoch": 0.957345971563981, "percentage": 47.87, "elapsed_time": "1:21:52", "remaining_time": "1:29:09"}
+{"current_steps": 1020, "total_steps": 2110, "loss": 0.5088, "lr": 6.159785537326307e-06, "epoch": 0.966824644549763, "percentage": 48.34, "elapsed_time": "1:22:42", "remaining_time": "1:28:23"}
+{"current_steps": 1030, "total_steps": 2110, "loss": 0.4876, "lr": 6.079169500294247e-06, "epoch": 0.976303317535545, "percentage": 48.82, "elapsed_time": "1:23:33", "remaining_time": "1:27:36"}
+{"current_steps": 1040, "total_steps": 2110, "loss": 0.5026, "lr": 5.998258118295699e-06, "epoch": 0.985781990521327, "percentage": 49.29, "elapsed_time": "1:24:20", "remaining_time": "1:26:46"}
+{"current_steps": 1050, "total_steps": 2110, "loss": 0.4721, "lr": 5.91707353499707e-06, "epoch": 0.995260663507109, "percentage": 49.76, "elapsed_time": "1:25:08", "remaining_time": "1:25:56"}
+{"current_steps": 1060, "total_steps": 2110, "loss": 0.4411, "lr": 5.835637968833947e-06, "epoch": 1.004739336492891, "percentage": 50.24, "elapsed_time": "1:26:00", "remaining_time": "1:25:12"}
+{"current_steps": 1070, "total_steps": 2110, "loss": 0.4078, "lr": 5.753973706930414e-06, "epoch": 1.014218009478673, "percentage": 50.71, "elapsed_time": "1:26:52", "remaining_time": "1:24:26"}
+{"current_steps": 1080, "total_steps": 2110, "loss": 0.387, "lr": 5.6721030989995475e-06, "epoch": 1.0236966824644549, "percentage": 51.18, "elapsed_time": "1:27:39", "remaining_time": "1:23:36"}
+{"current_steps": 1090, "total_steps": 2110, "loss": 0.4002, "lr": 5.590048551226802e-06, "epoch": 1.033175355450237, "percentage": 51.66, "elapsed_time": "1:28:30", "remaining_time": "1:22:49"}
+{"current_steps": 1100, "total_steps": 2110, "loss": 0.4001, "lr": 5.507832520137913e-06, "epoch": 1.042654028436019, "percentage": 52.13, "elapsed_time": "1:29:21", "remaining_time": "1:22:02"}
+{"current_steps": 1110, "total_steps": 2110, "loss": 0.3855, "lr": 5.425477506453057e-06, "epoch": 1.052132701421801, "percentage": 52.61, "elapsed_time": "1:30:09", "remaining_time": "1:21:13"}
+{"current_steps": 1120, "total_steps": 2110, "loss": 0.3798, "lr": 5.34300604892889e-06, "epoch": 1.061611374407583, "percentage": 53.08, "elapsed_time": "1:31:00", "remaining_time": "1:20:26"}
+{"current_steps": 1130, "total_steps": 2110, "loss": 0.3933, "lr": 5.260440718190183e-06, "epoch": 1.0710900473933649, "percentage": 53.55, "elapsed_time": "1:31:45", "remaining_time": "1:19:34"}
+{"current_steps": 1140, "total_steps": 2110, "loss": 0.384, "lr": 5.177804110552745e-06, "epoch": 1.080568720379147, "percentage": 54.03, "elapsed_time": "1:32:34", "remaining_time": "1:18:45"}
+{"current_steps": 1150, "total_steps": 2110, "loss": 0.3814, "lr": 5.095118841839307e-06, "epoch": 1.0900473933649288, "percentage": 54.5, "elapsed_time": "1:33:22", "remaining_time": "1:17:56"}
+{"current_steps": 1160, "total_steps": 2110, "loss": 0.3993, "lr": 5.0124075411900655e-06, "epoch": 1.099526066350711, "percentage": 54.98, "elapsed_time": "1:34:08", "remaining_time": "1:17:05"}
+{"current_steps": 1170, "total_steps": 2110, "loss": 0.3898, "lr": 4.929692844869579e-06, "epoch": 1.1090047393364928, "percentage": 55.45, "elapsed_time": "1:34:56", "remaining_time": "1:16:16"}
+{"current_steps": 1180, "total_steps": 2110, "loss": 0.3849, "lr": 4.846997390071737e-06, "epoch": 1.1184834123222749, "percentage": 55.92, "elapsed_time": "1:35:41", "remaining_time": "1:15:25"}
+{"current_steps": 1190, "total_steps": 2110, "loss": 0.4007, "lr": 4.764343808724442e-06, "epoch": 1.1279620853080567, "percentage": 56.4, "elapsed_time": "1:36:25", "remaining_time": "1:14:33"}
+{"current_steps": 1200, "total_steps": 2110, "loss": 0.3828, "lr": 4.681754721295751e-06, "epoch": 1.1374407582938388, "percentage": 56.87, "elapsed_time": "1:37:14", "remaining_time": "1:13:44"}
+{"current_steps": 1210, "total_steps": 2110, "loss": 0.3847, "lr": 4.599252730603159e-06, "epoch": 1.146919431279621, "percentage": 57.35, "elapsed_time": "1:38:02", "remaining_time": "1:12:55"}
+{"current_steps": 1220, "total_steps": 2110, "loss": 0.3821, "lr": 4.5168604156276954e-06, "epoch": 1.1563981042654028, "percentage": 57.82, "elapsed_time": "1:38:50", "remaining_time": "1:12:06"}
+{"current_steps": 1230, "total_steps": 2110, "loss": 0.3883, "lr": 4.434600325334561e-06, "epoch": 1.1658767772511849, "percentage": 58.29, "elapsed_time": "1:39:39", "remaining_time": "1:11:17"}
+{"current_steps": 1240, "total_steps": 2110, "loss": 0.4052, "lr": 4.352494972501963e-06, "epoch": 1.1753554502369667, "percentage": 58.77, "elapsed_time": "1:40:25", "remaining_time": "1:10:27"}
+{"current_steps": 1250, "total_steps": 2110, "loss": 0.409, "lr": 4.270566827559868e-06, "epoch": 1.1848341232227488, "percentage": 59.24, "elapsed_time": "1:41:14", "remaining_time": "1:09:39"}
+{"current_steps": 1260, "total_steps": 2110, "loss": 0.3843, "lr": 4.188838312440344e-06, "epoch": 1.1943127962085307, "percentage": 59.72, "elapsed_time": "1:42:03", "remaining_time": "1:08:51"}
+{"current_steps": 1270, "total_steps": 2110, "loss": 0.3821, "lr": 4.107331794441165e-06, "epoch": 1.2037914691943128, "percentage": 60.19, "elapsed_time": "1:42:53", "remaining_time": "1:08:03"}
+{"current_steps": 1280, "total_steps": 2110, "loss": 0.3884, "lr": 4.0260695801043626e-06, "epoch": 1.2132701421800949, "percentage": 60.66, "elapsed_time": "1:43:45", "remaining_time": "1:07:16"}
+{"current_steps": 1290, "total_steps": 2110, "loss": 0.3671, "lr": 3.945073909111442e-06, "epoch": 1.2227488151658767, "percentage": 61.14, "elapsed_time": "1:44:34", "remaining_time": "1:06:28"}
+{"current_steps": 1300, "total_steps": 2110, "loss": 0.4127, "lr": 3.86436694819685e-06, "epoch": 1.2322274881516588, "percentage": 61.61, "elapsed_time": "1:45:20", "remaining_time": "1:05:38"}
+{"current_steps": 1310, "total_steps": 2110, "loss": 0.3857, "lr": 3.7839707850814243e-06, "epoch": 1.2417061611374407, "percentage": 62.09, "elapsed_time": "1:46:13", "remaining_time": "1:04:52"}
+{"current_steps": 1320, "total_steps": 2110, "loss": 0.4019, "lr": 3.7039074224274906e-06, "epoch": 1.2511848341232228, "percentage": 62.56, "elapsed_time": "1:47:02", "remaining_time": "1:04:03"}
+{"current_steps": 1330, "total_steps": 2110, "loss": 0.3808, "lr": 3.624198771817197e-06, "epoch": 1.2606635071090047, "percentage": 63.03, "elapsed_time": "1:47:46", "remaining_time": "1:03:12"}
+{"current_steps": 1340, "total_steps": 2110, "loss": 0.3861, "lr": 3.5448666477558058e-06, "epoch": 1.2701421800947867, "percentage": 63.51, "elapsed_time": "1:48:38", "remaining_time": "1:02:25"}
+{"current_steps": 1350, "total_steps": 2110, "loss": 0.3976, "lr": 3.465932761701541e-06, "epoch": 1.2796208530805688, "percentage": 63.98, "elapsed_time": "1:49:32", "remaining_time": "1:01:40"}
+{"current_steps": 1360, "total_steps": 2110, "loss": 0.3732, "lr": 3.387418716123638e-06, "epoch": 1.2890995260663507, "percentage": 64.45, "elapsed_time": "1:50:19", "remaining_time": "1:00:50"}
+{"current_steps": 1370, "total_steps": 2110, "loss": 0.3777, "lr": 3.309345998590228e-06, "epoch": 1.2985781990521326, "percentage": 64.93, "elapsed_time": "1:51:07", "remaining_time": "1:00:01"}
+{"current_steps": 1380, "total_steps": 2110, "loss": 0.3885, "lr": 3.2317359758876538e-06, "epoch": 1.3080568720379147, "percentage": 65.4, "elapsed_time": "1:51:59", "remaining_time": "0:59:14"}
+{"current_steps": 1390, "total_steps": 2110, "loss": 0.3841, "lr": 3.154609888172859e-06, "epoch": 1.3175355450236967, "percentage": 65.88, "elapsed_time": "1:52:49", "remaining_time": "0:58:26"}
+{"current_steps": 1400, "total_steps": 2110, "loss": 0.3889, "lr": 3.0779888431604186e-06, "epoch": 1.3270142180094786, "percentage": 66.35, "elapsed_time": "1:53:38", "remaining_time": "0:57:37"}
+{"current_steps": 1410, "total_steps": 2110, "loss": 0.3862, "lr": 3.0018938103458256e-06, "epoch": 1.3364928909952607, "percentage": 66.82, "elapsed_time": "1:54:26", "remaining_time": "0:56:48"}
+{"current_steps": 1420, "total_steps": 2110, "loss": 0.3849, "lr": 2.926345615266598e-06, "epoch": 1.3459715639810428, "percentage": 67.3, "elapsed_time": "1:55:12", "remaining_time": "0:55:58"}
+{"current_steps": 1430, "total_steps": 2110, "loss": 0.398, "lr": 2.8513649338027853e-06, "epoch": 1.3554502369668247, "percentage": 67.77, "elapsed_time": "1:55:59", "remaining_time": "0:55:09"}
+{"current_steps": 1440, "total_steps": 2110, "loss": 0.3629, "lr": 2.77697228651844e-06, "epoch": 1.3649289099526065, "percentage": 68.25, "elapsed_time": "1:56:47", "remaining_time": "0:54:20"}
+{"current_steps": 1450, "total_steps": 2110, "loss": 0.3869, "lr": 2.7031880330455927e-06, "epoch": 1.3744075829383886, "percentage": 68.72, "elapsed_time": "1:57:37", "remaining_time": "0:53:32"}
+{"current_steps": 1460, "total_steps": 2110, "loss": 0.3796, "lr": 2.6300323665122496e-06, "epoch": 1.3838862559241707, "percentage": 69.19, "elapsed_time": "1:58:22", "remaining_time": "0:52:42"}
+{"current_steps": 1470, "total_steps": 2110, "loss": 0.385, "lr": 2.5575253080160034e-06, "epoch": 1.3933649289099526, "percentage": 69.67, "elapsed_time": "1:59:08", "remaining_time": "0:51:52"}
+{"current_steps": 1480, "total_steps": 2110, "loss": 0.393, "lr": 2.4856867011446856e-06, "epoch": 1.4028436018957346, "percentage": 70.14, "elapsed_time": "1:59:57", "remaining_time": "0:51:03"}
+{"current_steps": 1490, "total_steps": 2110, "loss": 0.3748, "lr": 2.4145362065456097e-06, "epoch": 1.4123222748815165, "percentage": 70.62, "elapsed_time": "2:00:45", "remaining_time": "0:50:14"}
+{"current_steps": 1500, "total_steps": 2110, "loss": 0.3829, "lr": 2.3440932965448878e-06, "epoch": 1.4218009478672986, "percentage": 71.09, "elapsed_time": "2:01:33", "remaining_time": "0:49:25"}
+{"current_steps": 1510, "total_steps": 2110, "loss": 0.3808, "lr": 2.27437724981829e-06, "epoch": 1.4312796208530805, "percentage": 71.56, "elapsed_time": "2:02:23", "remaining_time": "0:48:37"}
+{"current_steps": 1520, "total_steps": 2110, "loss": 0.3893, "lr": 2.2054071461150817e-06, "epoch": 1.4407582938388626, "percentage": 72.04, "elapsed_time": "2:03:09", "remaining_time": "0:47:48"}
+{"current_steps": 1530, "total_steps": 2110, "loss": 0.3862, "lr": 2.137201861036329e-06, "epoch": 1.4502369668246446, "percentage": 72.51, "elapsed_time": "2:03:59", "remaining_time": "0:47:00"}
+{"current_steps": 1540, "total_steps": 2110, "loss": 0.3875, "lr": 2.0697800608690505e-06, "epoch": 1.4597156398104265, "percentage": 72.99, "elapsed_time": "2:04:50", "remaining_time": "0:46:12"}
+{"current_steps": 1550, "total_steps": 2110, "loss": 0.3648, "lr": 2.0031601974776686e-06, "epoch": 1.4691943127962086, "percentage": 73.46, "elapsed_time": "2:05:35", "remaining_time": "0:45:22"}
+{"current_steps": 1560, "total_steps": 2110, "loss": 0.3879, "lr": 1.9373605032541466e-06, "epoch": 1.4786729857819905, "percentage": 73.93, "elapsed_time": "2:06:20", "remaining_time": "0:44:32"}
+{"current_steps": 1570, "total_steps": 2110, "loss": 0.366, "lr": 1.8723989861281732e-06, "epoch": 1.4881516587677726, "percentage": 74.41, "elapsed_time": "2:07:08", "remaining_time": "0:43:43"}
+{"current_steps": 1580, "total_steps": 2110, "loss": 0.3792, "lr": 1.8082934246387935e-06, "epoch": 1.4976303317535544, "percentage": 74.88, "elapsed_time": "2:07:56", "remaining_time": "0:42:55"}
+{"current_steps": 1590, "total_steps": 2110, "loss": 0.3886, "lr": 1.7450613630688163e-06, "epoch": 1.5071090047393365, "percentage": 75.36, "elapsed_time": "2:08:46", "remaining_time": "0:42:06"}
+{"current_steps": 1600, "total_steps": 2110, "loss": 0.3888, "lr": 1.6827201066433229e-06, "epoch": 1.5165876777251186, "percentage": 75.83, "elapsed_time": "2:09:30", "remaining_time": "0:41:16"}
+{"current_steps": 1610, "total_steps": 2110, "loss": 0.3826, "lr": 1.621286716793612e-06, "epoch": 1.5260663507109005, "percentage": 76.3, "elapsed_time": "2:10:21", "remaining_time": "0:40:29"}
+{"current_steps": 1620, "total_steps": 2110, "loss": 0.391, "lr": 1.560778006487863e-06, "epoch": 1.5355450236966823, "percentage": 76.78, "elapsed_time": "2:11:11", "remaining_time": "0:39:40"}
+{"current_steps": 1630, "total_steps": 2110, "loss": 0.3961, "lr": 1.5012105356297884e-06, "epoch": 1.5450236966824644, "percentage": 77.25, "elapsed_time": "2:12:02", "remaining_time": "0:38:52"}
+{"current_steps": 1640, "total_steps": 2110, "loss": 0.3803, "lr": 1.442600606526563e-06, "epoch": 1.5545023696682465, "percentage": 77.73, "elapsed_time": "2:12:50", "remaining_time": "0:38:04"}
+{"current_steps": 1650, "total_steps": 2110, "loss": 0.3845, "lr": 1.38496425942723e-06, "epoch": 1.5639810426540284, "percentage": 78.2, "elapsed_time": "2:13:34", "remaining_time": "0:37:14"}
+{"current_steps": 1660, "total_steps": 2110, "loss": 0.3797, "lr": 1.3283172681328438e-06, "epoch": 1.5734597156398105, "percentage": 78.67, "elapsed_time": "2:14:24", "remaining_time": "0:36:26"}
+{"current_steps": 1670, "total_steps": 2110, "loss": 0.3806, "lr": 1.2726751356795275e-06, "epoch": 1.5829383886255926, "percentage": 79.15, "elapsed_time": "2:15:13", "remaining_time": "0:35:37"}
+{"current_steps": 1680, "total_steps": 2110, "loss": 0.3765, "lr": 1.2180530900956333e-06, "epoch": 1.5924170616113744, "percentage": 79.62, "elapsed_time": "2:16:00", "remaining_time": "0:34:48"}
+{"current_steps": 1690, "total_steps": 2110, "loss": 0.3767, "lr": 1.1644660802341568e-06, "epoch": 1.6018957345971563, "percentage": 80.09, "elapsed_time": "2:16:48", "remaining_time": "0:34:00"}
+{"current_steps": 1700, "total_steps": 2110, "loss": 0.3818, "lr": 1.111928771681579e-06, "epoch": 1.6113744075829384, "percentage": 80.57, "elapsed_time": "2:17:40", "remaining_time": "0:33:12"}
+{"current_steps": 1710, "total_steps": 2110, "loss": 0.387, "lr": 1.0604555427442092e-06, "epoch": 1.6208530805687205, "percentage": 81.04, "elapsed_time": "2:18:30", "remaining_time": "0:32:23"}
+{"current_steps": 1720, "total_steps": 2110, "loss": 0.3751, "lr": 1.0100604805131576e-06, "epoch": 1.6303317535545023, "percentage": 81.52, "elapsed_time": "2:19:18", "remaining_time": "0:31:35"}
+{"current_steps": 1730, "total_steps": 2110, "loss": 0.3838, "lr": 9.607573770090102e-07, "epoch": 1.6398104265402842, "percentage": 81.99, "elapsed_time": "2:20:07", "remaining_time": "0:30:46"}
+{"current_steps": 1740, "total_steps": 2110, "loss": 0.3826, "lr": 9.12559725407261e-07, "epoch": 1.6492890995260665, "percentage": 82.46, "elapsed_time": "2:20:57", "remaining_time": "0:29:58"}
+{"current_steps": 1750, "total_steps": 2110, "loss": 0.376, "lr": 8.65480716345517e-07, "epoch": 1.6587677725118484, "percentage": 82.94, "elapsed_time": "2:21:44", "remaining_time": "0:29:09"}
+{"current_steps": 1760, "total_steps": 2110, "loss": 0.3843, "lr": 8.195332343135171e-07, "epoch": 1.6682464454976302, "percentage": 83.41, "elapsed_time": "2:22:33", "remaining_time": "0:28:20"}
+{"current_steps": 1770, "total_steps": 2110, "loss": 0.3677, "lr": 7.747298541269315e-07, "epoch": 1.6777251184834123, "percentage": 83.89, "elapsed_time": "2:23:20", "remaining_time": "0:27:32"}
+{"current_steps": 1780, "total_steps": 2110, "loss": 0.3716, "lr": 7.310828374859036e-07, "epoch": 1.6872037914691944, "percentage": 84.36, "elapsed_time": "2:24:11", "remaining_time": "0:26:44"}
+{"current_steps": 1790, "total_steps": 2110, "loss": 0.3977, "lr": 6.88604129619303e-07, "epoch": 1.6966824644549763, "percentage": 84.83, "elapsed_time": "2:24:59", "remaining_time": "0:25:55"}
+{"current_steps": 1800, "total_steps": 2110, "loss": 0.395, "lr": 6.473053560155684e-07, "epoch": 1.7061611374407581, "percentage": 85.31, "elapsed_time": "2:25:46", "remaining_time": "0:25:06"}
+{"current_steps": 1810, "total_steps": 2110, "loss": 0.3799, "lr": 6.071978192410737e-07, "epoch": 1.7156398104265402, "percentage": 85.78, "elapsed_time": "2:26:31", "remaining_time": "0:24:17"}
+{"current_steps": 1820, "total_steps": 2110, "loss": 0.3824, "lr": 5.682924958468639e-07, "epoch": 1.7251184834123223, "percentage": 86.26, "elapsed_time": "2:27:16", "remaining_time": "0:23:28"}
+{"current_steps": 1830, "total_steps": 2110, "loss": 0.378, "lr": 5.306000333646094e-07, "epoch": 1.7345971563981042, "percentage": 86.73, "elapsed_time": "2:28:04", "remaining_time": "0:22:39"}
+{"current_steps": 1840, "total_steps": 2110, "loss": 0.3748, "lr": 4.94130747392616e-07, "epoch": 1.7440758293838863, "percentage": 87.2, "elapsed_time": "2:28:52", "remaining_time": "0:21:50"}
+{"current_steps": 1850, "total_steps": 2110, "loss": 0.3787, "lr": 4.588946187726706e-07, "epoch": 1.7535545023696684, "percentage": 87.68, "elapsed_time": "2:29:40", "remaining_time": "0:21:02"}
+{"current_steps": 1860, "total_steps": 2110, "loss": 0.3659, "lr": 4.2490129085850317e-07, "epoch": 1.7630331753554502, "percentage": 88.15, "elapsed_time": "2:30:27", "remaining_time": "0:20:13"}
+{"current_steps": 1870, "total_steps": 2110, "loss": 0.3769, "lr": 3.921600668766146e-07, "epoch": 1.772511848341232, "percentage": 88.63, "elapsed_time": "2:31:15", "remaining_time": "0:19:24"}
+{"current_steps": 1880, "total_steps": 2110, "loss": 0.39, "lr": 3.6067990738018587e-07, "epoch": 1.7819905213270142, "percentage": 89.1, "elapsed_time": "2:32:04", "remaining_time": "0:18:36"}
+{"current_steps": 1890, "total_steps": 2110, "loss": 0.3654, "lr": 3.3046942779677404e-07, "epoch": 1.7914691943127963, "percentage": 89.57, "elapsed_time": "2:32:54", "remaining_time": "0:17:47"}
+{"current_steps": 1900, "total_steps": 2110, "loss": 0.3773, "lr": 3.015368960704584e-07, "epoch": 1.8009478672985781, "percentage": 90.05, "elapsed_time": "2:33:42", "remaining_time": "0:16:59"}
+{"current_steps": 1910, "total_steps": 2110, "loss": 0.3938, "lr": 2.7389023039908536e-07, "epoch": 1.8104265402843602, "percentage": 90.52, "elapsed_time": "2:34:29", "remaining_time": "0:16:10"}
+{"current_steps": 1920, "total_steps": 2110, "loss": 0.3666, "lr": 2.4753699706723035e-07, "epoch": 1.8199052132701423, "percentage": 91.0, "elapsed_time": "2:35:13", "remaining_time": "0:15:21"}
+{"current_steps": 1930, "total_steps": 2110, "loss": 0.3831, "lr": 2.2248440837547736e-07, "epoch": 1.8293838862559242, "percentage": 91.47, "elapsed_time": "2:36:04", "remaining_time": "0:14:33"}
+{"current_steps": 1940, "total_steps": 2110, "loss": 0.3669, "lr": 1.9873932066656555e-07, "epoch": 1.838862559241706, "percentage": 91.94, "elapsed_time": "2:36:51", "remaining_time": "0:13:44"}
+{"current_steps": 1950, "total_steps": 2110, "loss": 0.3874, "lr": 1.76308232448959e-07, "epoch": 1.8483412322274881, "percentage": 92.42, "elapsed_time": "2:37:43", "remaining_time": "0:12:56"}
+{"current_steps": 1960, "total_steps": 2110, "loss": 0.3807, "lr": 1.5519728261835176e-07, "epoch": 1.8578199052132702, "percentage": 92.89, "elapsed_time": "2:38:34", "remaining_time": "0:12:08"}
+{"current_steps": 1970, "total_steps": 2110, "loss": 0.387, "lr": 1.3541224877758498e-07, "epoch": 1.867298578199052, "percentage": 93.36, "elapsed_time": "2:39:23", "remaining_time": "0:11:19"}
+{"current_steps": 1980, "total_steps": 2110, "loss": 0.3827, "lr": 1.1695854565544229e-07, "epoch": 1.876777251184834, "percentage": 93.84, "elapsed_time": "2:40:14", "remaining_time": "0:10:31"}
+{"current_steps": 1990, "total_steps": 2110, "loss": 0.3713, "lr": 9.984122362476035e-08, "epoch": 1.8862559241706163, "percentage": 94.31, "elapsed_time": "2:41:03", "remaining_time": "0:09:42"}
+{"current_steps": 2000, "total_steps": 2110, "loss": 0.3786, "lr": 8.406496732025149e-08, "epoch": 1.8957345971563981, "percentage": 94.79, "elapsed_time": "2:41:54", "remaining_time": "0:08:54"}
+{"current_steps": 2010, "total_steps": 2110, "loss": 0.3813, "lr": 6.963409435642165e-08, "epoch": 1.90521327014218, "percentage": 95.26, "elapsed_time": "2:42:43", "remaining_time": "0:08:05"}
+{"current_steps": 2020, "total_steps": 2110, "loss": 0.3671, "lr": 5.655255414593663e-08, "epoch": 1.914691943127962, "percentage": 95.73, "elapsed_time": "2:43:27", "remaining_time": "0:07:16"}
+{"current_steps": 2030, "total_steps": 2110, "loss": 0.3941, "lr": 4.482392681875114e-08, "epoch": 1.9241706161137442, "percentage": 96.21, "elapsed_time": "2:44:20", "remaining_time": "0:06:28"}
+{"current_steps": 2040, "total_steps": 2110, "loss": 0.3768, "lr": 3.445142224230869e-08, "epoch": 1.933649289099526, "percentage": 96.68, "elapsed_time": "2:45:05", "remaining_time": "0:05:39"}
+{"current_steps": 2050, "total_steps": 2110, "loss": 0.3695, "lr": 2.5437879143070387e-08, "epoch": 1.943127962085308, "percentage": 97.16, "elapsed_time": "2:45:57", "remaining_time": "0:04:51"}
+{"current_steps": 2060, "total_steps": 2110, "loss": 0.3747, "lr": 1.7785764329618092e-08, "epoch": 1.95260663507109, "percentage": 97.63, "elapsed_time": "2:46:46", "remaining_time": "0:04:02"}
+{"current_steps": 2070, "total_steps": 2110, "loss": 0.3628, "lr": 1.14971720175433e-08, "epoch": 1.962085308056872, "percentage": 98.1, "elapsed_time": "2:47:32", "remaining_time": "0:03:14"}
+{"current_steps": 2080, "total_steps": 2110, "loss": 0.3824, "lr": 6.573823256305067e-09, "epoch": 1.971563981042654, "percentage": 98.58, "elapsed_time": "2:48:22", "remaining_time": "0:02:25"}
+{"current_steps": 2090, "total_steps": 2110, "loss": 0.3722, "lr": 3.017065458219559e-09, "epoch": 1.981042654028436, "percentage": 99.05, "elapsed_time": "2:49:08", "remaining_time": "0:01:37"}
+{"current_steps": 2100, "total_steps": 2110, "loss": 0.3781, "lr": 8.278720296994725e-10, "epoch": 1.9905213270142181, "percentage": 99.53, "elapsed_time": "2:49:55", "remaining_time": "0:00:48"}
+{"current_steps": 2110, "total_steps": 2110, "loss": 0.3715, "lr": 6.842104856574772e-12, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:50:46", "remaining_time": "0:00:00"}
+{"current_steps": 2110, "total_steps": 2110, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:51:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1520 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009478672985781991,
+      "grad_norm": 5.002547365321731,
+      "learning_rate": 4.265402843601896e-07,
+      "loss": 1.0344,
+      "step": 10
+    },
+    {
+      "epoch": 0.018957345971563982,
+      "grad_norm": 3.658396676061602,
+      "learning_rate": 9.004739336492892e-07,
+      "loss": 1.0038,
+      "step": 20
+    },
+    {
+      "epoch": 0.02843601895734597,
+      "grad_norm": 3.081402704877802,
+      "learning_rate": 1.3744075829383887e-06,
+      "loss": 0.9018,
+      "step": 30
+    },
+    {
+      "epoch": 0.037914691943127965,
+      "grad_norm": 2.6034042818587126,
+      "learning_rate": 1.8483412322274883e-06,
+      "loss": 0.8064,
+      "step": 40
+    },
+    {
+      "epoch": 0.04739336492890995,
+      "grad_norm": 1.913748130325827,
+      "learning_rate": 2.322274881516588e-06,
+      "loss": 0.7376,
+      "step": 50
+    },
+    {
+      "epoch": 0.05687203791469194,
+      "grad_norm": 1.9015096332513717,
+      "learning_rate": 2.7962085308056874e-06,
+      "loss": 0.6845,
+      "step": 60
+    },
+    {
+      "epoch": 0.06635071090047394,
+      "grad_norm": 2.055142812949458,
+      "learning_rate": 3.2701421800947867e-06,
+      "loss": 0.6568,
+      "step": 70
+    },
+    {
+      "epoch": 0.07582938388625593,
+      "grad_norm": 1.992092781950205,
+      "learning_rate": 3.7440758293838865e-06,
+      "loss": 0.6454,
+      "step": 80
+    },
+    {
+      "epoch": 0.08530805687203792,
+      "grad_norm": 1.9041249926938342,
+      "learning_rate": 4.218009478672986e-06,
+      "loss": 0.6254,
+      "step": 90
+    },
+    {
+      "epoch": 0.0947867298578199,
+      "grad_norm": 1.854172268857651,
+      "learning_rate": 4.691943127962086e-06,
+      "loss": 0.6049,
+      "step": 100
+    },
+    {
+      "epoch": 0.10426540284360189,
+      "grad_norm": 1.7928806532682156,
+      "learning_rate": 5.165876777251185e-06,
+      "loss": 0.6026,
+      "step": 110
+    },
+    {
+      "epoch": 0.11374407582938388,
+      "grad_norm": 1.8581634338330837,
+      "learning_rate": 5.639810426540285e-06,
+      "loss": 0.6005,
+      "step": 120
+    },
+    {
+      "epoch": 0.12322274881516587,
+      "grad_norm": 1.9150110591624738,
+      "learning_rate": 6.1137440758293845e-06,
+      "loss": 0.6072,
+      "step": 130
+    },
+    {
+      "epoch": 0.13270142180094788,
+      "grad_norm": 1.871727297072966,
+      "learning_rate": 6.587677725118484e-06,
+      "loss": 0.5851,
+      "step": 140
+    },
+    {
+      "epoch": 0.14218009478672985,
+      "grad_norm": 1.9026025919745162,
+      "learning_rate": 7.061611374407583e-06,
+      "loss": 0.5812,
+      "step": 150
+    },
+    {
+      "epoch": 0.15165876777251186,
+      "grad_norm": 2.0280418005203273,
+      "learning_rate": 7.535545023696683e-06,
+      "loss": 0.5793,
+      "step": 160
+    },
+    {
+      "epoch": 0.16113744075829384,
+      "grad_norm": 1.9001373787309122,
+      "learning_rate": 8.009478672985783e-06,
+      "loss": 0.5832,
+      "step": 170
+    },
+    {
+      "epoch": 0.17061611374407584,
+      "grad_norm": 2.0380332465897366,
+      "learning_rate": 8.483412322274883e-06,
+      "loss": 0.568,
+      "step": 180
+    },
+    {
+      "epoch": 0.18009478672985782,
+      "grad_norm": 1.7317686234173122,
+      "learning_rate": 8.957345971563981e-06,
+      "loss": 0.5696,
+      "step": 190
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 1.8116008164409596,
+      "learning_rate": 9.431279620853082e-06,
+      "loss": 0.5674,
+      "step": 200
+    },
+    {
+      "epoch": 0.1990521327014218,
+      "grad_norm": 1.771663543122235,
+      "learning_rate": 9.905213270142182e-06,
+      "loss": 0.5657,
+      "step": 210
+    },
+    {
+      "epoch": 0.20853080568720378,
+      "grad_norm": 1.779363270621716,
+      "learning_rate": 9.999562111581011e-06,
+      "loss": 0.5646,
+      "step": 220
+    },
+    {
+      "epoch": 0.21800947867298578,
+      "grad_norm": 1.7627075856828176,
+      "learning_rate": 9.997783321329104e-06,
+      "loss": 0.5569,
+      "step": 230
+    },
+    {
+      "epoch": 0.22748815165876776,
+      "grad_norm": 1.688436736255634,
+      "learning_rate": 9.994636747659363e-06,
+      "loss": 0.5551,
+      "step": 240
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "grad_norm": 1.6492256335278235,
+      "learning_rate": 9.990123251719826e-06,
+      "loss": 0.5631,
+      "step": 250
+    },
+    {
+      "epoch": 0.24644549763033174,
+      "grad_norm": 1.5563069402094531,
+      "learning_rate": 9.9842440687551e-06,
+      "loss": 0.5544,
+      "step": 260
+    },
+    {
+      "epoch": 0.2559241706161137,
+      "grad_norm": 1.6255710435415285,
+      "learning_rate": 9.977000807768306e-06,
+      "loss": 0.5317,
+      "step": 270
+    },
+    {
+      "epoch": 0.26540284360189575,
+      "grad_norm": 1.7205478187506846,
+      "learning_rate": 9.968395451080736e-06,
+      "loss": 0.544,
+      "step": 280
+    },
+    {
+      "epoch": 0.27488151658767773,
+      "grad_norm": 1.722150709769103,
+      "learning_rate": 9.958430353789321e-06,
+      "loss": 0.562,
+      "step": 290
+    },
+    {
+      "epoch": 0.2843601895734597,
+      "grad_norm": 1.6598904490497792,
+      "learning_rate": 9.947108243122107e-06,
+      "loss": 0.5408,
+      "step": 300
+    },
+    {
+      "epoch": 0.2938388625592417,
+      "grad_norm": 1.6747111886252184,
+      "learning_rate": 9.934432217691862e-06,
+      "loss": 0.5324,
+      "step": 310
+    },
+    {
+      "epoch": 0.3033175355450237,
+      "grad_norm": 1.5291653328320371,
+      "learning_rate": 9.920405746648067e-06,
+      "loss": 0.5336,
+      "step": 320
+    },
+    {
+      "epoch": 0.3127962085308057,
+      "grad_norm": 1.6174339767319996,
+      "learning_rate": 9.905032668727467e-06,
+      "loss": 0.5479,
+      "step": 330
+    },
+    {
+      "epoch": 0.3222748815165877,
+      "grad_norm": 1.5822952001481942,
+      "learning_rate": 9.888317191203513e-06,
+      "loss": 0.5273,
+      "step": 340
+    },
+    {
+      "epoch": 0.33175355450236965,
+      "grad_norm": 1.6193027925604444,
+      "learning_rate": 9.870263888734905e-06,
+      "loss": 0.5211,
+      "step": 350
+    },
+    {
+      "epoch": 0.3412322274881517,
+      "grad_norm": 1.5274666838384185,
+      "learning_rate": 9.85087770211363e-06,
+      "loss": 0.5401,
+      "step": 360
+    },
+    {
+      "epoch": 0.35071090047393366,
+      "grad_norm": 1.5199875931973836,
+      "learning_rate": 9.830163936912752e-06,
+      "loss": 0.5274,
+      "step": 370
+    },
+    {
+      "epoch": 0.36018957345971564,
+      "grad_norm": 1.5602022573845324,
+      "learning_rate": 9.808128262034411e-06,
+      "loss": 0.528,
+      "step": 380
+    },
+    {
+      "epoch": 0.3696682464454976,
+      "grad_norm": 1.5610497196879198,
+      "learning_rate": 9.784776708158363e-06,
+      "loss": 0.5216,
+      "step": 390
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 1.5784966686202415,
+      "learning_rate": 9.760115666091518e-06,
+      "loss": 0.5133,
+      "step": 400
+    },
+    {
+      "epoch": 0.3886255924170616,
+      "grad_norm": 1.6340384121071343,
+      "learning_rate": 9.73415188501891e-06,
+      "loss": 0.5228,
+      "step": 410
+    },
+    {
+      "epoch": 0.3981042654028436,
+      "grad_norm": 1.5225266102541877,
+      "learning_rate": 9.706892470656601e-06,
+      "loss": 0.5371,
+      "step": 420
+    },
+    {
+      "epoch": 0.4075829383886256,
+      "grad_norm": 1.6515765748506515,
+      "learning_rate": 9.678344883306997e-06,
+      "loss": 0.5335,
+      "step": 430
+    },
+    {
+      "epoch": 0.41706161137440756,
+      "grad_norm": 1.5605246633787762,
+      "learning_rate": 9.648516935817133e-06,
+      "loss": 0.5251,
+      "step": 440
+    },
+    {
+      "epoch": 0.4265402843601896,
+      "grad_norm": 1.5731837340598396,
+      "learning_rate": 9.617416791440461e-06,
+      "loss": 0.5412,
+      "step": 450
+    },
+    {
+      "epoch": 0.43601895734597157,
+      "grad_norm": 1.6231560042620659,
+      "learning_rate": 9.585052961602759e-06,
+      "loss": 0.5377,
+      "step": 460
+    },
+    {
+      "epoch": 0.44549763033175355,
+      "grad_norm": 1.646638728552254,
+      "learning_rate": 9.551434303572725e-06,
+      "loss": 0.5164,
+      "step": 470
+    },
+    {
+      "epoch": 0.4549763033175355,
+      "grad_norm": 1.3956624693346211,
+      "learning_rate": 9.51657001803795e-06,
+      "loss": 0.5006,
+      "step": 480
+    },
+    {
+      "epoch": 0.46445497630331756,
+      "grad_norm": 1.443185690667246,
+      "learning_rate": 9.480469646586888e-06,
+      "loss": 0.5243,
+      "step": 490
+    },
+    {
+      "epoch": 0.47393364928909953,
+      "grad_norm": 1.5455523927242236,
+      "learning_rate": 9.443143069097531e-06,
+      "loss": 0.539,
+      "step": 500
+    },
+    {
+      "epoch": 0.4834123222748815,
+      "grad_norm": 1.3240575637186844,
+      "learning_rate": 9.404600501033505e-06,
+      "loss": 0.501,
+      "step": 510
+    },
+    {
+      "epoch": 0.4928909952606635,
+      "grad_norm": 1.526764619856022,
+      "learning_rate": 9.364852490648327e-06,
+      "loss": 0.5334,
+      "step": 520
+    },
+    {
+      "epoch": 0.5023696682464455,
+      "grad_norm": 1.6777377738004218,
+      "learning_rate": 9.323909916098566e-06,
+      "loss": 0.5094,
+      "step": 530
+    },
+    {
+      "epoch": 0.5118483412322274,
+      "grad_norm": 1.4818575272700827,
+      "learning_rate": 9.28178398246675e-06,
+      "loss": 0.5109,
+      "step": 540
+    },
+    {
+      "epoch": 0.5213270142180095,
+      "grad_norm": 1.3639688498372662,
+      "learning_rate": 9.238486218694767e-06,
+      "loss": 0.4997,
+      "step": 550
+    },
+    {
+      "epoch": 0.5308056872037915,
+      "grad_norm": 2.0226457522273282,
+      "learning_rate": 9.194028474428651e-06,
+      "loss": 0.5146,
+      "step": 560
+    },
+    {
+      "epoch": 0.5402843601895735,
+      "grad_norm": 1.5493076322420674,
+      "learning_rate": 9.148422916775596e-06,
+      "loss": 0.5126,
+      "step": 570
+    },
+    {
+      "epoch": 0.5497630331753555,
+      "grad_norm": 1.589658451208532,
+      "learning_rate": 9.101682026974086e-06,
+      "loss": 0.5269,
+      "step": 580
+    },
+    {
+      "epoch": 0.5592417061611374,
+      "grad_norm": 1.4177385362318415,
+      "learning_rate": 9.053818596978051e-06,
+      "loss": 0.5123,
+      "step": 590
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 1.510693061602022,
+      "learning_rate": 9.004845725955993e-06,
+      "loss": 0.5185,
+      "step": 600
+    },
+    {
+      "epoch": 0.5781990521327014,
+      "grad_norm": 1.523134392385588,
+      "learning_rate": 8.954776816706034e-06,
+      "loss": 0.5104,
+      "step": 610
+    },
+    {
+      "epoch": 0.5876777251184834,
+      "grad_norm": 1.5510651970737526,
+      "learning_rate": 8.903625571987863e-06,
+      "loss": 0.5064,
+      "step": 620
+    },
+    {
+      "epoch": 0.5971563981042654,
+      "grad_norm": 1.4532508496103183,
+      "learning_rate": 8.851405990772588e-06,
+      "loss": 0.5075,
+      "step": 630
+    },
+    {
+      "epoch": 0.6066350710900474,
+      "grad_norm": 1.4454473897444817,
+      "learning_rate": 8.798132364411532e-06,
+      "loss": 0.5316,
+      "step": 640
+    },
+    {
+      "epoch": 0.6161137440758294,
+      "grad_norm": 1.5404382999982151,
+      "learning_rate": 8.743819272724996e-06,
+      "loss": 0.5107,
+      "step": 650
+    },
+    {
+      "epoch": 0.6255924170616114,
+      "grad_norm": 1.4529866969683547,
+      "learning_rate": 8.688481580012092e-06,
+      "loss": 0.5025,
+      "step": 660
+    },
+    {
+      "epoch": 0.6350710900473934,
+      "grad_norm": 1.4869529917225628,
+      "learning_rate": 8.632134430982708e-06,
+      "loss": 0.5203,
+      "step": 670
+    },
+    {
+      "epoch": 0.6445497630331753,
+      "grad_norm": 1.493386235135509,
+      "learning_rate": 8.574793246612727e-06,
+      "loss": 0.5229,
+      "step": 680
+    },
+    {
+      "epoch": 0.6540284360189573,
+      "grad_norm": 1.4905028344972993,
+      "learning_rate": 8.516473719923658e-06,
+      "loss": 0.5127,
+      "step": 690
+    },
+    {
+      "epoch": 0.6635071090047393,
+      "grad_norm": 1.5083812194152073,
+      "learning_rate": 8.457191811687788e-06,
+      "loss": 0.5215,
+      "step": 700
+    },
+    {
+      "epoch": 0.6729857819905213,
+      "grad_norm": 1.4454285504543494,
+      "learning_rate": 8.396963746060076e-06,
+      "loss": 0.5195,
+      "step": 710
+    },
+    {
+      "epoch": 0.6824644549763034,
+      "grad_norm": 1.3553224308142846,
+      "learning_rate": 8.335806006137962e-06,
+      "loss": 0.511,
+      "step": 720
+    },
+    {
+      "epoch": 0.6919431279620853,
+      "grad_norm": 1.6047592970172526,
+      "learning_rate": 8.273735329450296e-06,
+      "loss": 0.497,
+      "step": 730
+    },
+    {
+      "epoch": 0.7014218009478673,
+      "grad_norm": 1.3760210742074075,
+      "learning_rate": 8.210768703376651e-06,
+      "loss": 0.5036,
+      "step": 740
+    },
+    {
+      "epoch": 0.7109004739336493,
+      "grad_norm": 1.4614034536702043,
+      "learning_rate": 8.146923360498252e-06,
+      "loss": 0.5071,
+      "step": 750
+    },
+    {
+      "epoch": 0.7203791469194313,
+      "grad_norm": 1.4418499608763105,
+      "learning_rate": 8.082216773881792e-06,
+      "loss": 0.5022,
+      "step": 760
+    },
+    {
+      "epoch": 0.7298578199052133,
+      "grad_norm": 1.4499065824015291,
+      "learning_rate": 8.016666652297443e-06,
+      "loss": 0.5073,
+      "step": 770
+    },
+    {
+      "epoch": 0.7393364928909952,
+      "grad_norm": 1.392396296239011,
+      "learning_rate": 7.950290935372346e-06,
+      "loss": 0.4973,
+      "step": 780
+    },
+    {
+      "epoch": 0.7488151658767772,
+      "grad_norm": 1.461032758162232,
+      "learning_rate": 7.883107788680946e-06,
+      "loss": 0.4997,
+      "step": 790
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 1.4585430939057935,
+      "learning_rate": 7.815135598773455e-06,
+      "loss": 0.5061,
+      "step": 800
+    },
+    {
+      "epoch": 0.7677725118483413,
+      "grad_norm": 1.3397056062356951,
+      "learning_rate": 7.746392968143872e-06,
+      "loss": 0.4849,
+      "step": 810
+    },
+    {
+      "epoch": 0.7772511848341233,
+      "grad_norm": 1.28472835722118,
+      "learning_rate": 7.676898710138878e-06,
+      "loss": 0.5013,
+      "step": 820
+    },
+    {
+      "epoch": 0.7867298578199052,
+      "grad_norm": 1.3968717101034185,
+      "learning_rate": 7.606671843809045e-06,
+      "loss": 0.5186,
+      "step": 830
+    },
+    {
+      "epoch": 0.7962085308056872,
+      "grad_norm": 1.427122604607973,
+      "learning_rate": 7.5357315887037365e-06,
+      "loss": 0.5156,
+      "step": 840
+    },
+    {
+      "epoch": 0.8056872037914692,
+      "grad_norm": 1.3443273452120659,
+      "learning_rate": 7.46409735961114e-06,
+      "loss": 0.4956,
+      "step": 850
+    },
+    {
+      "epoch": 0.8151658767772512,
+      "grad_norm": 1.6469302151610767,
+      "learning_rate": 7.3917887612448665e-06,
+      "loss": 0.486,
+      "step": 860
+    },
+    {
+      "epoch": 0.8246445497630331,
+      "grad_norm": 1.6164590725469863,
+      "learning_rate": 7.318825582878571e-06,
+      "loss": 0.4865,
+      "step": 870
+    },
+    {
+      "epoch": 0.8341232227488151,
+      "grad_norm": 1.5902724529947458,
+      "learning_rate": 7.245227792930062e-06,
+      "loss": 0.5036,
+      "step": 880
+    },
+    {
+      "epoch": 0.8436018957345972,
+      "grad_norm": 1.3516145211409656,
+      "learning_rate": 7.1710155334963875e-06,
+      "loss": 0.4854,
+      "step": 890
+    },
+    {
+      "epoch": 0.8530805687203792,
+      "grad_norm": 1.3534491272430955,
+      "learning_rate": 7.096209114841384e-06,
+      "loss": 0.4835,
+      "step": 900
+    },
+    {
+      "epoch": 0.8625592417061612,
+      "grad_norm": 1.3140548317627492,
+      "learning_rate": 7.0208290098372026e-06,
+      "loss": 0.4944,
+      "step": 910
+    },
+    {
+      "epoch": 0.8720379146919431,
+      "grad_norm": 1.4237344585256864,
+      "learning_rate": 6.944895848361338e-06,
+      "loss": 0.4856,
+      "step": 920
+    },
+    {
+      "epoch": 0.8815165876777251,
+      "grad_norm": 1.4875521812850687,
+      "learning_rate": 6.868430411650682e-06,
+      "loss": 0.4955,
+      "step": 930
+    },
+    {
+      "epoch": 0.8909952606635071,
+      "grad_norm": 1.3857141572995468,
+      "learning_rate": 6.791453626614155e-06,
+      "loss": 0.4739,
+      "step": 940
+    },
+    {
+      "epoch": 0.9004739336492891,
+      "grad_norm": 1.935786682207215,
+      "learning_rate": 6.71398656010547e-06,
+      "loss": 0.5094,
+      "step": 950
+    },
+    {
+      "epoch": 0.909952606635071,
+      "grad_norm": 1.3211114320017838,
+      "learning_rate": 6.636050413157605e-06,
+      "loss": 0.4901,
+      "step": 960
+    },
+    {
+      "epoch": 0.919431279620853,
+      "grad_norm": 1.3966497603249453,
+      "learning_rate": 6.557666515180539e-06,
+      "loss": 0.5103,
+      "step": 970
+    },
+    {
+      "epoch": 0.9289099526066351,
+      "grad_norm": 1.353875113467149,
+      "learning_rate": 6.478856318123861e-06,
+      "loss": 0.5073,
+      "step": 980
+    },
+    {
+      "epoch": 0.9383886255924171,
+      "grad_norm": 1.3598781819203754,
+      "learning_rate": 6.399641390605849e-06,
+      "loss": 0.4936,
+      "step": 990
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 1.4671024190361444,
+      "learning_rate": 6.32004341201061e-06,
+      "loss": 0.4827,
+      "step": 1000
+    },
+    {
+      "epoch": 0.957345971563981,
+      "grad_norm": 1.4025483947219903,
+      "learning_rate": 6.240084166554909e-06,
+      "loss": 0.4942,
+      "step": 1010
+    },
+    {
+      "epoch": 0.966824644549763,
+      "grad_norm": 1.3568472117501837,
+      "learning_rate": 6.159785537326307e-06,
+      "loss": 0.5088,
+      "step": 1020
+    },
+    {
+      "epoch": 0.976303317535545,
+      "grad_norm": 1.2697077607074232,
+      "learning_rate": 6.079169500294247e-06,
+      "loss": 0.4876,
+      "step": 1030
+    },
+    {
+      "epoch": 0.985781990521327,
+      "grad_norm": 1.4019217235060069,
+      "learning_rate": 5.998258118295699e-06,
+      "loss": 0.5026,
+      "step": 1040
+    },
+    {
+      "epoch": 0.995260663507109,
+      "grad_norm": 1.6656103746082294,
+      "learning_rate": 5.91707353499707e-06,
+      "loss": 0.4721,
+      "step": 1050
+    },
+    {
+      "epoch": 1.004739336492891,
+      "grad_norm": 1.2966884591738475,
+      "learning_rate": 5.835637968833947e-06,
+      "loss": 0.4411,
+      "step": 1060
+    },
+    {
+      "epoch": 1.014218009478673,
+      "grad_norm": 1.36952754231243,
+      "learning_rate": 5.753973706930414e-06,
+      "loss": 0.4078,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0236966824644549,
+      "grad_norm": 1.3814815751347376,
+      "learning_rate": 5.6721030989995475e-06,
+      "loss": 0.387,
+      "step": 1080
+    },
+    {
+      "epoch": 1.033175355450237,
+      "grad_norm": 1.4755794040744068,
+      "learning_rate": 5.590048551226802e-06,
+      "loss": 0.4002,
+      "step": 1090
+    },
+    {
+      "epoch": 1.042654028436019,
+      "grad_norm": 1.3564366142078452,
+      "learning_rate": 5.507832520137913e-06,
+      "loss": 0.4001,
+      "step": 1100
+    },
+    {
+      "epoch": 1.052132701421801,
+      "grad_norm": 1.5566688649431848,
+      "learning_rate": 5.425477506453057e-06,
+      "loss": 0.3855,
+      "step": 1110
+    },
+    {
+      "epoch": 1.061611374407583,
+      "grad_norm": 1.5407713272698218,
+      "learning_rate": 5.34300604892889e-06,
+      "loss": 0.3798,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0710900473933649,
+      "grad_norm": 1.3877155981885327,
+      "learning_rate": 5.260440718190183e-06,
+      "loss": 0.3933,
+      "step": 1130
+    },
+    {
+      "epoch": 1.080568720379147,
+      "grad_norm": 1.5611923524116407,
+      "learning_rate": 5.177804110552745e-06,
+      "loss": 0.384,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0900473933649288,
+      "grad_norm": 1.4155912996850115,
+      "learning_rate": 5.095118841839307e-06,
+      "loss": 0.3814,
+      "step": 1150
+    },
+    {
+      "epoch": 1.099526066350711,
+      "grad_norm": 1.4455961798737849,
+      "learning_rate": 5.0124075411900655e-06,
+      "loss": 0.3993,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1090047393364928,
+      "grad_norm": 1.6379687256648139,
+      "learning_rate": 4.929692844869579e-06,
+      "loss": 0.3898,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1184834123222749,
+      "grad_norm": 1.58568700123716,
+      "learning_rate": 4.846997390071737e-06,
+      "loss": 0.3849,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1279620853080567,
+      "grad_norm": 1.4568176931894607,
+      "learning_rate": 4.764343808724442e-06,
+      "loss": 0.4007,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1374407582938388,
+      "grad_norm": 1.453719083179016,
+      "learning_rate": 4.681754721295751e-06,
+      "loss": 0.3828,
+      "step": 1200
+    },
+    {
+      "epoch": 1.146919431279621,
+      "grad_norm": 1.5707935439416905,
+      "learning_rate": 4.599252730603159e-06,
+      "loss": 0.3847,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1563981042654028,
+      "grad_norm": 1.6525935716299354,
+      "learning_rate": 4.5168604156276954e-06,
+      "loss": 0.3821,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1658767772511849,
+      "grad_norm": 1.4501920339178778,
+      "learning_rate": 4.434600325334561e-06,
+      "loss": 0.3883,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1753554502369667,
+      "grad_norm": 1.4870188948067953,
+      "learning_rate": 4.352494972501963e-06,
+      "loss": 0.4052,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1848341232227488,
+      "grad_norm": 1.5016252392046023,
+      "learning_rate": 4.270566827559868e-06,
+      "loss": 0.409,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1943127962085307,
+      "grad_norm": 1.4073269672466402,
+      "learning_rate": 4.188838312440344e-06,
+      "loss": 0.3843,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2037914691943128,
+      "grad_norm": 1.5096245600290905,
+      "learning_rate": 4.107331794441165e-06,
+      "loss": 0.3821,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2132701421800949,
+      "grad_norm": 1.435155328700363,
+      "learning_rate": 4.0260695801043626e-06,
+      "loss": 0.3884,
+      "step": 1280
+    },
+    {
+      "epoch": 1.2227488151658767,
+      "grad_norm": 1.5004879335097303,
+      "learning_rate": 3.945073909111442e-06,
+      "loss": 0.3671,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2322274881516588,
+      "grad_norm": 1.4611792171291136,
+      "learning_rate": 3.86436694819685e-06,
+      "loss": 0.4127,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2417061611374407,
+      "grad_norm": 1.5291643460646795,
+      "learning_rate": 3.7839707850814243e-06,
+      "loss": 0.3857,
+      "step": 1310
+    },
+    {
+      "epoch": 1.2511848341232228,
+      "grad_norm": 1.6424036371915975,
+      "learning_rate": 3.7039074224274906e-06,
+      "loss": 0.4019,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2606635071090047,
+      "grad_norm": 1.4700137899387786,
+      "learning_rate": 3.624198771817197e-06,
+      "loss": 0.3808,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2701421800947867,
+      "grad_norm": 1.467341952085249,
+      "learning_rate": 3.5448666477558058e-06,
+      "loss": 0.3861,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2796208530805688,
+      "grad_norm": 1.4667444539107315,
+      "learning_rate": 3.465932761701541e-06,
+      "loss": 0.3976,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2890995260663507,
+      "grad_norm": 1.5624232263045241,
+      "learning_rate": 3.387418716123638e-06,
+      "loss": 0.3732,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2985781990521326,
+      "grad_norm": 1.4162780658848286,
+      "learning_rate": 3.309345998590228e-06,
+      "loss": 0.3777,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3080568720379147,
+      "grad_norm": 1.4625481529432485,
+      "learning_rate": 3.2317359758876538e-06,
+      "loss": 0.3885,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3175355450236967,
+      "grad_norm": 1.5185321828862155,
+      "learning_rate": 3.154609888172859e-06,
+      "loss": 0.3841,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3270142180094786,
+      "grad_norm": 1.576972704767674,
+      "learning_rate": 3.0779888431604186e-06,
+      "loss": 0.3889,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3364928909952607,
+      "grad_norm": 1.5379789103691697,
+      "learning_rate": 3.0018938103458256e-06,
+      "loss": 0.3862,
+      "step": 1410
+    },
+    {
+      "epoch": 1.3459715639810428,
+      "grad_norm": 1.5148699904929508,
+      "learning_rate": 2.926345615266598e-06,
+      "loss": 0.3849,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3554502369668247,
+      "grad_norm": 1.5071409477054654,
+      "learning_rate": 2.8513649338027853e-06,
+      "loss": 0.398,
+      "step": 1430
+    },
+    {
+      "epoch": 1.3649289099526065,
+      "grad_norm": 1.4585179152783647,
+      "learning_rate": 2.77697228651844e-06,
+      "loss": 0.3629,
+      "step": 1440
+    },
+    {
+      "epoch": 1.3744075829383886,
+      "grad_norm": 1.631622735411311,
+      "learning_rate": 2.7031880330455927e-06,
+      "loss": 0.3869,
+      "step": 1450
+    },
+    {
+      "epoch": 1.3838862559241707,
+      "grad_norm": 1.5684218581429454,
+      "learning_rate": 2.6300323665122496e-06,
+      "loss": 0.3796,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3933649289099526,
+      "grad_norm": 1.605199356495361,
+      "learning_rate": 2.5575253080160034e-06,
+      "loss": 0.385,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4028436018957346,
+      "grad_norm": 1.5582269880719388,
+      "learning_rate": 2.4856867011446856e-06,
+      "loss": 0.393,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4123222748815165,
+      "grad_norm": 1.4461786209982581,
+      "learning_rate": 2.4145362065456097e-06,
+      "loss": 0.3748,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4218009478672986,
+      "grad_norm": 1.5815719412629603,
+      "learning_rate": 2.3440932965448878e-06,
+      "loss": 0.3829,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4312796208530805,
+      "grad_norm": 1.5599698928236585,
+      "learning_rate": 2.27437724981829e-06,
+      "loss": 0.3808,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4407582938388626,
+      "grad_norm": 1.410010887703049,
+      "learning_rate": 2.2054071461150817e-06,
+      "loss": 0.3893,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4502369668246446,
+      "grad_norm": 1.4257698546769384,
+      "learning_rate": 2.137201861036329e-06,
+      "loss": 0.3862,
+      "step": 1530
+    },
+    {
+      "epoch": 1.4597156398104265,
+      "grad_norm": 1.5202109829470343,
+      "learning_rate": 2.0697800608690505e-06,
+      "loss": 0.3875,
+      "step": 1540
+    },
+    {
+      "epoch": 1.4691943127962086,
+      "grad_norm": 1.5042180266726983,
+      "learning_rate": 2.0031601974776686e-06,
+      "loss": 0.3648,
+      "step": 1550
+    },
+    {
+      "epoch": 1.4786729857819905,
+      "grad_norm": 1.5173592586474516,
+      "learning_rate": 1.9373605032541466e-06,
+      "loss": 0.3879,
+      "step": 1560
+    },
+    {
+      "epoch": 1.4881516587677726,
+      "grad_norm": 1.5854623835221053,
+      "learning_rate": 1.8723989861281732e-06,
+      "loss": 0.366,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4976303317535544,
+      "grad_norm": 1.659480818385221,
+      "learning_rate": 1.8082934246387935e-06,
+      "loss": 0.3792,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5071090047393365,
+      "grad_norm": 1.4029144415926478,
+      "learning_rate": 1.7450613630688163e-06,
+      "loss": 0.3886,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5165876777251186,
+      "grad_norm": 1.581784584290308,
+      "learning_rate": 1.6827201066433229e-06,
+      "loss": 0.3888,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5260663507109005,
+      "grad_norm": 1.3362684114694519,
+      "learning_rate": 1.621286716793612e-06,
+      "loss": 0.3826,
+      "step": 1610
+    },
+    {
+      "epoch": 1.5355450236966823,
+      "grad_norm": 1.3156523248786751,
+      "learning_rate": 1.560778006487863e-06,
+      "loss": 0.391,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5450236966824644,
+      "grad_norm": 1.8017984993997835,
+      "learning_rate": 1.5012105356297884e-06,
+      "loss": 0.3961,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5545023696682465,
+      "grad_norm": 1.4974869998167462,
+      "learning_rate": 1.442600606526563e-06,
+      "loss": 0.3803,
+      "step": 1640
+    },
+    {
+      "epoch": 1.5639810426540284,
+      "grad_norm": 1.4639395736629641,
+      "learning_rate": 1.38496425942723e-06,
+      "loss": 0.3845,
+      "step": 1650
+    },
+    {
+      "epoch": 1.5734597156398105,
+      "grad_norm": 1.486309344503289,
+      "learning_rate": 1.3283172681328438e-06,
+      "loss": 0.3797,
+      "step": 1660
+    },
+    {
+      "epoch": 1.5829383886255926,
+      "grad_norm": 1.6273629414883715,
+      "learning_rate": 1.2726751356795275e-06,
+      "loss": 0.3806,
+      "step": 1670
+    },
+    {
+      "epoch": 1.5924170616113744,
+      "grad_norm": 1.4308044976577479,
+      "learning_rate": 1.2180530900956333e-06,
+      "loss": 0.3765,
+      "step": 1680
+    },
+    {
+      "epoch": 1.6018957345971563,
+      "grad_norm": 1.5196322559118096,
+      "learning_rate": 1.1644660802341568e-06,
+      "loss": 0.3767,
+      "step": 1690
+    },
+    {
+      "epoch": 1.6113744075829384,
+      "grad_norm": 1.5157269178049864,
+      "learning_rate": 1.111928771681579e-06,
+      "loss": 0.3818,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6208530805687205,
+      "grad_norm": 1.532869812236632,
+      "learning_rate": 1.0604555427442092e-06,
+      "loss": 0.387,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6303317535545023,
+      "grad_norm": 1.4214843226202385,
+      "learning_rate": 1.0100604805131576e-06,
+      "loss": 0.3751,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6398104265402842,
+      "grad_norm": 1.356013290715747,
+      "learning_rate": 9.607573770090102e-07,
+      "loss": 0.3838,
+      "step": 1730
+    },
+    {
+      "epoch": 1.6492890995260665,
+      "grad_norm": 1.4160087589814112,
+      "learning_rate": 9.12559725407261e-07,
+      "loss": 0.3826,
+      "step": 1740
+    },
+    {
+      "epoch": 1.6587677725118484,
+      "grad_norm": 1.4144837726856385,
+      "learning_rate": 8.65480716345517e-07,
+      "loss": 0.376,
+      "step": 1750
+    },
+    {
+      "epoch": 1.6682464454976302,
+      "grad_norm": 1.4845309125278798,
+      "learning_rate": 8.195332343135171e-07,
+      "loss": 0.3843,
+      "step": 1760
+    },
+    {
+      "epoch": 1.6777251184834123,
+      "grad_norm": 1.5583282827898042,
+      "learning_rate": 7.747298541269315e-07,
+      "loss": 0.3677,
+      "step": 1770
+    },
+    {
+      "epoch": 1.6872037914691944,
+      "grad_norm": 1.4332941998525244,
+      "learning_rate": 7.310828374859036e-07,
+      "loss": 0.3716,
+      "step": 1780
+    },
+    {
+      "epoch": 1.6966824644549763,
+      "grad_norm": 1.5396461000120685,
+      "learning_rate": 6.88604129619303e-07,
+      "loss": 0.3977,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7061611374407581,
+      "grad_norm": 1.4764208452488277,
+      "learning_rate": 6.473053560155684e-07,
+      "loss": 0.395,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7156398104265402,
+      "grad_norm": 1.4084863032752903,
+      "learning_rate": 6.071978192410737e-07,
+      "loss": 0.3799,
+      "step": 1810
+    },
+    {
+      "epoch": 1.7251184834123223,
+      "grad_norm": 1.7592004607253005,
+      "learning_rate": 5.682924958468639e-07,
+      "loss": 0.3824,
+      "step": 1820
+    },
+    {
+      "epoch": 1.7345971563981042,
+      "grad_norm": 1.556872833429063,
+      "learning_rate": 5.306000333646094e-07,
+      "loss": 0.378,
+      "step": 1830
+    },
+    {
+      "epoch": 1.7440758293838863,
+      "grad_norm": 1.4834205488989711,
+      "learning_rate": 4.94130747392616e-07,
+      "loss": 0.3748,
+      "step": 1840
+    },
+    {
+      "epoch": 1.7535545023696684,
+      "grad_norm": 1.725343511617158,
+      "learning_rate": 4.588946187726706e-07,
+      "loss": 0.3787,
+      "step": 1850
+    },
+    {
+      "epoch": 1.7630331753554502,
+      "grad_norm": 1.410773998321812,
+      "learning_rate": 4.2490129085850317e-07,
+      "loss": 0.3659,
+      "step": 1860
+    },
+    {
+      "epoch": 1.772511848341232,
+      "grad_norm": 1.5188097906287266,
+      "learning_rate": 3.921600668766146e-07,
+      "loss": 0.3769,
+      "step": 1870
+    },
+    {
+      "epoch": 1.7819905213270142,
+      "grad_norm": 1.624243756215326,
+      "learning_rate": 3.6067990738018587e-07,
+      "loss": 0.39,
+      "step": 1880
+    },
+    {
+      "epoch": 1.7914691943127963,
+      "grad_norm": 1.3512974613137152,
+      "learning_rate": 3.3046942779677404e-07,
+      "loss": 0.3654,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8009478672985781,
+      "grad_norm": 1.5366049091330738,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.3773,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8104265402843602,
+      "grad_norm": 1.6341836079325431,
+      "learning_rate": 2.7389023039908536e-07,
+      "loss": 0.3938,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8199052132701423,
+      "grad_norm": 1.5792779779139723,
+      "learning_rate": 2.4753699706723035e-07,
+      "loss": 0.3666,
+      "step": 1920
+    },
+    {
+      "epoch": 1.8293838862559242,
+      "grad_norm": 1.4622420357417885,
+      "learning_rate": 2.2248440837547736e-07,
+      "loss": 0.3831,
+      "step": 1930
+    },
+    {
+      "epoch": 1.838862559241706,
+      "grad_norm": 1.524478109067551,
+      "learning_rate": 1.9873932066656555e-07,
+      "loss": 0.3669,
+      "step": 1940
+    },
+    {
+      "epoch": 1.8483412322274881,
+      "grad_norm": 1.5508867004439844,
+      "learning_rate": 1.76308232448959e-07,
+      "loss": 0.3874,
+      "step": 1950
+    },
+    {
+      "epoch": 1.8578199052132702,
+      "grad_norm": 1.5163467576632608,
+      "learning_rate": 1.5519728261835176e-07,
+      "loss": 0.3807,
+      "step": 1960
+    },
+    {
+      "epoch": 1.867298578199052,
+      "grad_norm": 1.5102205893393328,
+      "learning_rate": 1.3541224877758498e-07,
+      "loss": 0.387,
+      "step": 1970
+    },
+    {
+      "epoch": 1.876777251184834,
+      "grad_norm": 1.4412529586874316,
+      "learning_rate": 1.1695854565544229e-07,
+      "loss": 0.3827,
+      "step": 1980
+    },
+    {
+      "epoch": 1.8862559241706163,
+      "grad_norm": 1.5836467331810966,
+      "learning_rate": 9.984122362476035e-08,
+      "loss": 0.3713,
+      "step": 1990
+    },
+    {
+      "epoch": 1.8957345971563981,
+      "grad_norm": 1.419167266385221,
+      "learning_rate": 8.406496732025149e-08,
+      "loss": 0.3786,
+      "step": 2000
+    },
+    {
+      "epoch": 1.90521327014218,
+      "grad_norm": 1.5163142153280726,
+      "learning_rate": 6.963409435642165e-08,
+      "loss": 0.3813,
+      "step": 2010
+    },
+    {
+      "epoch": 1.914691943127962,
+      "grad_norm": 1.5110936156424504,
+      "learning_rate": 5.655255414593663e-08,
+      "loss": 0.3671,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9241706161137442,
+      "grad_norm": 1.5159345913192441,
+      "learning_rate": 4.482392681875114e-08,
+      "loss": 0.3941,
+      "step": 2030
+    },
+    {
+      "epoch": 1.933649289099526,
+      "grad_norm": 1.7330004437047792,
+      "learning_rate": 3.445142224230869e-08,
+      "loss": 0.3768,
+      "step": 2040
+    },
+    {
+      "epoch": 1.943127962085308,
+      "grad_norm": 1.638920135057764,
+      "learning_rate": 2.5437879143070387e-08,
+      "loss": 0.3695,
+      "step": 2050
+    },
+    {
+      "epoch": 1.95260663507109,
+      "grad_norm": 1.3820035254293206,
+      "learning_rate": 1.7785764329618092e-08,
+      "loss": 0.3747,
+      "step": 2060
+    },
+    {
+      "epoch": 1.962085308056872,
+      "grad_norm": 1.4717158912851318,
+      "learning_rate": 1.14971720175433e-08,
+      "loss": 0.3628,
+      "step": 2070
+    },
+    {
+      "epoch": 1.971563981042654,
+      "grad_norm": 1.4556766766961653,
+      "learning_rate": 6.573823256305067e-09,
+      "loss": 0.3824,
+      "step": 2080
+    },
+    {
+      "epoch": 1.981042654028436,
+      "grad_norm": 1.5779609136336825,
+      "learning_rate": 3.017065458219559e-09,
+      "loss": 0.3722,
+      "step": 2090
+    },
+    {
+      "epoch": 1.9905213270142181,
+      "grad_norm": 1.4435975491308937,
+      "learning_rate": 8.278720296994725e-10,
+      "loss": 0.3781,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3425853280120728,
+      "learning_rate": 6.842104856574772e-12,
+      "loss": 0.3715,
+      "step": 2110
+    },
+    {
+      "epoch": 2.0,
+      "step": 2110,
+      "total_flos": 159350737469440.0,
+      "train_loss": 0.46467527450543444,
+      "train_runtime": 10302.033,
+      "train_samples_per_second": 3.277,
+      "train_steps_per_second": 0.205
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 159350737469440.0,
+  "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 sha256:051f7843521ac48c068d9f605e7394fba444563ea27ed0641c676fedce24e514
+size 7544