Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the agthoughts 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- 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: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 306663055425536.0,
+    "train_loss": 0.5762376924754328,
+    "train_runtime": 90627.2697,
+    "train_samples_per_second": 1.477,
+    "train_steps_per_second": 0.023
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4ab4d5c72ba503a791e80ed1d17e63a442124802f400c5b8d8e459842eabaf
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81775e69a943e431951e68d2f56d0fe716a308c3a1e6bda1857fc54c6c77db0
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 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": 3.0,
+    "total_flos": 306663055425536.0,
+    "train_loss": 0.5762376924754328,
+    "train_runtime": 90627.2697,
+    "train_samples_per_second": 1.477,
+    "train_steps_per_second": 0.023
+}

trainer_log.jsonl

@@ -0,0 +1,210 @@
+{"current_steps": 10, "total_steps": 2094, "loss": 1.5266, "lr": 4.285714285714286e-06, "epoch": 0.014344629729245113, "percentage": 0.48, "elapsed_time": "0:08:47", "remaining_time": "1 day, 6:31:12"}
+{"current_steps": 20, "total_steps": 2094, "loss": 1.3066, "lr": 9.047619047619047e-06, "epoch": 0.028689259458490227, "percentage": 0.96, "elapsed_time": "0:16:18", "remaining_time": "1 day, 4:11:49"}
+{"current_steps": 30, "total_steps": 2094, "loss": 1.1436, "lr": 1.3809523809523811e-05, "epoch": 0.04303388918773534, "percentage": 1.43, "elapsed_time": "0:23:49", "remaining_time": "1 day, 3:19:32"}
+{"current_steps": 40, "total_steps": 2094, "loss": 1.0535, "lr": 1.8571428571428572e-05, "epoch": 0.05737851891698045, "percentage": 1.91, "elapsed_time": "0:31:14", "remaining_time": "1 day, 2:44:13"}
+{"current_steps": 50, "total_steps": 2094, "loss": 1.0172, "lr": 2.3333333333333336e-05, "epoch": 0.07172314864622557, "percentage": 2.39, "elapsed_time": "0:38:38", "remaining_time": "1 day, 2:19:30"}
+{"current_steps": 60, "total_steps": 2094, "loss": 0.9859, "lr": 2.8095238095238096e-05, "epoch": 0.08606777837547068, "percentage": 2.87, "elapsed_time": "0:45:57", "remaining_time": "1 day, 1:57:46"}
+{"current_steps": 70, "total_steps": 2094, "loss": 0.9528, "lr": 3.285714285714286e-05, "epoch": 0.1004124081047158, "percentage": 3.34, "elapsed_time": "0:53:17", "remaining_time": "1 day, 1:40:46"}
+{"current_steps": 80, "total_steps": 2094, "loss": 0.9397, "lr": 3.761904761904762e-05, "epoch": 0.1147570378339609, "percentage": 3.82, "elapsed_time": "1:00:43", "remaining_time": "1 day, 1:28:54"}
+{"current_steps": 90, "total_steps": 2094, "loss": 0.9282, "lr": 4.2380952380952385e-05, "epoch": 0.129101667563206, "percentage": 4.3, "elapsed_time": "1:08:00", "remaining_time": "1 day, 1:14:22"}
+{"current_steps": 100, "total_steps": 2094, "loss": 0.9186, "lr": 4.714285714285714e-05, "epoch": 0.14344629729245115, "percentage": 4.78, "elapsed_time": "1:15:23", "remaining_time": "1 day, 1:03:17"}
+{"current_steps": 110, "total_steps": 2094, "loss": 0.9074, "lr": 5.1904761904761913e-05, "epoch": 0.15779092702169625, "percentage": 5.25, "elapsed_time": "1:22:43", "remaining_time": "1 day, 0:52:01"}
+{"current_steps": 120, "total_steps": 2094, "loss": 0.9002, "lr": 5.666666666666667e-05, "epoch": 0.17213555675094136, "percentage": 5.73, "elapsed_time": "1:30:04", "remaining_time": "1 day, 0:41:51"}
+{"current_steps": 130, "total_steps": 2094, "loss": 0.8887, "lr": 6.142857142857143e-05, "epoch": 0.1864801864801865, "percentage": 6.21, "elapsed_time": "1:37:25", "remaining_time": "1 day, 0:31:55"}
+{"current_steps": 140, "total_steps": 2094, "loss": 0.884, "lr": 6.619047619047619e-05, "epoch": 0.2008248162094316, "percentage": 6.69, "elapsed_time": "1:44:43", "remaining_time": "1 day, 0:21:42"}
+{"current_steps": 150, "total_steps": 2094, "loss": 0.8809, "lr": 7.095238095238096e-05, "epoch": 0.2151694459386767, "percentage": 7.16, "elapsed_time": "1:52:09", "remaining_time": "1 day, 0:13:37"}
+{"current_steps": 160, "total_steps": 2094, "loss": 0.8799, "lr": 7.571428571428571e-05, "epoch": 0.2295140756679218, "percentage": 7.64, "elapsed_time": "1:59:36", "remaining_time": "1 day, 0:05:47"}
+{"current_steps": 170, "total_steps": 2094, "loss": 0.8802, "lr": 8.047619047619048e-05, "epoch": 0.24385870539716695, "percentage": 8.12, "elapsed_time": "2:06:50", "remaining_time": "23:55:31"}
+{"current_steps": 180, "total_steps": 2094, "loss": 0.8692, "lr": 8.523809523809524e-05, "epoch": 0.258203335126412, "percentage": 8.6, "elapsed_time": "2:14:12", "remaining_time": "23:47:05"}
+{"current_steps": 190, "total_steps": 2094, "loss": 0.8675, "lr": 9e-05, "epoch": 0.2725479648556572, "percentage": 9.07, "elapsed_time": "2:21:38", "remaining_time": "23:39:21"}
+{"current_steps": 200, "total_steps": 2094, "loss": 0.8651, "lr": 9.476190476190476e-05, "epoch": 0.2868925945849023, "percentage": 9.55, "elapsed_time": "2:29:06", "remaining_time": "23:32:04"}
+{"current_steps": 210, "total_steps": 2094, "loss": 0.8743, "lr": 9.952380952380953e-05, "epoch": 0.3012372243141474, "percentage": 10.03, "elapsed_time": "2:36:28", "remaining_time": "23:23:45"}
+{"current_steps": 220, "total_steps": 2094, "loss": 0.8831, "lr": 9.999436939807164e-05, "epoch": 0.3155818540433925, "percentage": 10.51, "elapsed_time": "2:43:47", "remaining_time": "23:15:15"}
+{"current_steps": 230, "total_steps": 2094, "loss": 0.8753, "lr": 9.99749072170404e-05, "epoch": 0.3299264837726376, "percentage": 10.98, "elapsed_time": "2:51:10", "remaining_time": "23:07:12"}
+{"current_steps": 240, "total_steps": 2094, "loss": 0.8553, "lr": 9.994154935353517e-05, "epoch": 0.3442711135018827, "percentage": 11.46, "elapsed_time": "2:58:32", "remaining_time": "22:59:13"}
+{"current_steps": 250, "total_steps": 2094, "loss": 0.8577, "lr": 9.98943050828164e-05, "epoch": 0.3586157432311278, "percentage": 11.94, "elapsed_time": "3:06:01", "remaining_time": "22:52:06"}
+{"current_steps": 260, "total_steps": 2094, "loss": 0.842, "lr": 9.983318754130435e-05, "epoch": 0.372960372960373, "percentage": 12.42, "elapsed_time": "3:13:32", "remaining_time": "22:45:14"}
+{"current_steps": 270, "total_steps": 2094, "loss": 0.8346, "lr": 9.975821372292653e-05, "epoch": 0.3873050026896181, "percentage": 12.89, "elapsed_time": "3:20:55", "remaining_time": "22:37:21"}
+{"current_steps": 280, "total_steps": 2094, "loss": 0.8272, "lr": 9.966940447439245e-05, "epoch": 0.4016496324188632, "percentage": 13.37, "elapsed_time": "3:28:12", "remaining_time": "22:28:55"}
+{"current_steps": 290, "total_steps": 2094, "loss": 0.8161, "lr": 9.956678448939718e-05, "epoch": 0.4159942621481083, "percentage": 13.85, "elapsed_time": "3:35:30", "remaining_time": "22:20:39"}
+{"current_steps": 300, "total_steps": 2094, "loss": 0.8263, "lr": 9.945038230175509e-05, "epoch": 0.4303388918773534, "percentage": 14.33, "elapsed_time": "3:42:49", "remaining_time": "22:12:29"}
+{"current_steps": 310, "total_steps": 2094, "loss": 0.8119, "lr": 9.932023027746602e-05, "epoch": 0.4446835216065985, "percentage": 14.8, "elapsed_time": "3:50:10", "remaining_time": "22:04:40"}
+{"current_steps": 320, "total_steps": 2094, "loss": 0.8195, "lr": 9.917636460571578e-05, "epoch": 0.4590281513358436, "percentage": 15.28, "elapsed_time": "3:57:31", "remaining_time": "21:56:48"}
+{"current_steps": 330, "total_steps": 2094, "loss": 0.8152, "lr": 9.901882528881363e-05, "epoch": 0.47337278106508873, "percentage": 15.76, "elapsed_time": "4:04:51", "remaining_time": "21:48:55"}
+{"current_steps": 340, "total_steps": 2094, "loss": 0.8056, "lr": 9.884765613106948e-05, "epoch": 0.4877174107943339, "percentage": 16.24, "elapsed_time": "4:12:20", "remaining_time": "21:41:46"}
+{"current_steps": 350, "total_steps": 2094, "loss": 0.8143, "lr": 9.866290472661406e-05, "epoch": 0.502062040523579, "percentage": 16.71, "elapsed_time": "4:19:43", "remaining_time": "21:34:10"}
+{"current_steps": 360, "total_steps": 2094, "loss": 0.8139, "lr": 9.846462244616508e-05, "epoch": 0.516406670252824, "percentage": 17.19, "elapsed_time": "4:27:00", "remaining_time": "21:26:06"}
+{"current_steps": 370, "total_steps": 2094, "loss": 0.8052, "lr": 9.825286442274357e-05, "epoch": 0.5307512999820692, "percentage": 17.67, "elapsed_time": "4:34:20", "remaining_time": "21:18:17"}
+{"current_steps": 380, "total_steps": 2094, "loss": 0.7918, "lr": 9.802768953634388e-05, "epoch": 0.5450959297113144, "percentage": 18.15, "elapsed_time": "4:41:36", "remaining_time": "21:10:12"}
+{"current_steps": 390, "total_steps": 2094, "loss": 0.7859, "lr": 9.778916039756193e-05, "epoch": 0.5594405594405595, "percentage": 18.62, "elapsed_time": "4:48:54", "remaining_time": "21:02:17"}
+{"current_steps": 400, "total_steps": 2094, "loss": 0.776, "lr": 9.753734333018616e-05, "epoch": 0.5737851891698046, "percentage": 19.1, "elapsed_time": "4:56:10", "remaining_time": "20:54:16"}
+{"current_steps": 410, "total_steps": 2094, "loss": 0.7811, "lr": 9.727230835275598e-05, "epoch": 0.5881298188990497, "percentage": 19.58, "elapsed_time": "5:03:25", "remaining_time": "20:46:17"}
+{"current_steps": 420, "total_steps": 2094, "loss": 0.7819, "lr": 9.699412915909284e-05, "epoch": 0.6024744486282948, "percentage": 20.06, "elapsed_time": "5:10:44", "remaining_time": "20:38:30"}
+{"current_steps": 430, "total_steps": 2094, "loss": 0.7679, "lr": 9.670288309780953e-05, "epoch": 0.6168190783575399, "percentage": 20.53, "elapsed_time": "5:17:59", "remaining_time": "20:30:34"}
+{"current_steps": 440, "total_steps": 2094, "loss": 0.779, "lr": 9.639865115080304e-05, "epoch": 0.631163708086785, "percentage": 21.01, "elapsed_time": "5:25:15", "remaining_time": "20:22:40"}
+{"current_steps": 450, "total_steps": 2094, "loss": 0.7739, "lr": 9.608151791073737e-05, "epoch": 0.6455083378160301, "percentage": 21.49, "elapsed_time": "5:32:29", "remaining_time": "20:14:43"}
+{"current_steps": 460, "total_steps": 2094, "loss": 0.7643, "lr": 9.575157155752222e-05, "epoch": 0.6598529675452752, "percentage": 21.97, "elapsed_time": "5:39:46", "remaining_time": "20:06:54"}
+{"current_steps": 470, "total_steps": 2094, "loss": 0.7556, "lr": 9.54089038337943e-05, "epoch": 0.6741975972745203, "percentage": 22.45, "elapsed_time": "5:46:55", "remaining_time": "19:58:44"}
+{"current_steps": 480, "total_steps": 2094, "loss": 0.7596, "lr": 9.5053610019408e-05, "epoch": 0.6885422270037654, "percentage": 22.92, "elapsed_time": "5:54:08", "remaining_time": "19:50:48"}
+{"current_steps": 490, "total_steps": 2094, "loss": 0.7534, "lr": 9.468578890494256e-05, "epoch": 0.7028868567330105, "percentage": 23.4, "elapsed_time": "6:01:25", "remaining_time": "19:43:06"}
+{"current_steps": 500, "total_steps": 2094, "loss": 0.7552, "lr": 9.430554276423292e-05, "epoch": 0.7172314864622557, "percentage": 23.88, "elapsed_time": "6:08:43", "remaining_time": "19:35:30"}
+{"current_steps": 510, "total_steps": 2094, "loss": 0.7526, "lr": 9.391297732593229e-05, "epoch": 0.7315761161915008, "percentage": 24.36, "elapsed_time": "6:17:24", "remaining_time": "19:32:10"}
+{"current_steps": 520, "total_steps": 2094, "loss": 0.7537, "lr": 9.350820174411386e-05, "epoch": 0.745920745920746, "percentage": 24.83, "elapsed_time": "6:24:37", "remaining_time": "19:24:13"}
+{"current_steps": 530, "total_steps": 2094, "loss": 0.7499, "lr": 9.309132856792023e-05, "epoch": 0.7602653756499911, "percentage": 25.31, "elapsed_time": "6:31:54", "remaining_time": "19:16:30"}
+{"current_steps": 540, "total_steps": 2094, "loss": 0.7447, "lr": 9.266247371026873e-05, "epoch": 0.7746100053792362, "percentage": 25.79, "elapsed_time": "6:39:10", "remaining_time": "19:08:45"}
+{"current_steps": 550, "total_steps": 2094, "loss": 0.7496, "lr": 9.222175641562143e-05, "epoch": 0.7889546351084813, "percentage": 26.27, "elapsed_time": "6:46:31", "remaining_time": "19:01:12"}
+{"current_steps": 560, "total_steps": 2094, "loss": 0.74, "lr": 9.176929922682891e-05, "epoch": 0.8032992648377264, "percentage": 26.74, "elapsed_time": "6:53:53", "remaining_time": "18:53:44"}
+{"current_steps": 570, "total_steps": 2094, "loss": 0.7411, "lr": 9.130522795105676e-05, "epoch": 0.8176438945669715, "percentage": 27.22, "elapsed_time": "7:01:10", "remaining_time": "18:46:05"}
+{"current_steps": 580, "total_steps": 2094, "loss": 0.7323, "lr": 9.082967162480459e-05, "epoch": 0.8319885242962166, "percentage": 27.7, "elapsed_time": "7:08:20", "remaining_time": "18:38:08"}
+{"current_steps": 590, "total_steps": 2094, "loss": 0.7231, "lr": 9.034276247802688e-05, "epoch": 0.8463331540254617, "percentage": 28.18, "elapsed_time": "7:15:28", "remaining_time": "18:30:05"}
+{"current_steps": 600, "total_steps": 2094, "loss": 0.7288, "lr": 8.984463589736614e-05, "epoch": 0.8606777837547068, "percentage": 28.65, "elapsed_time": "7:22:46", "remaining_time": "18:22:29"}
+{"current_steps": 610, "total_steps": 2094, "loss": 0.732, "lr": 8.933543038850816e-05, "epoch": 0.8750224134839519, "percentage": 29.13, "elapsed_time": "7:29:49", "remaining_time": "18:14:19"}
+{"current_steps": 620, "total_steps": 2094, "loss": 0.728, "lr": 8.881528753767007e-05, "epoch": 0.889367043213197, "percentage": 29.61, "elapsed_time": "7:36:53", "remaining_time": "18:06:12"}
+{"current_steps": 630, "total_steps": 2094, "loss": 0.7263, "lr": 8.82843519722319e-05, "epoch": 0.9037116729424421, "percentage": 30.09, "elapsed_time": "7:43:57", "remaining_time": "17:58:08"}
+{"current_steps": 640, "total_steps": 2094, "loss": 0.7189, "lr": 8.774277132052237e-05, "epoch": 0.9180563026716873, "percentage": 30.56, "elapsed_time": "7:50:58", "remaining_time": "17:49:59"}
+{"current_steps": 650, "total_steps": 2094, "loss": 0.7254, "lr": 8.719069617077046e-05, "epoch": 0.9324009324009324, "percentage": 31.04, "elapsed_time": "7:58:09", "remaining_time": "17:42:14"}
+{"current_steps": 660, "total_steps": 2094, "loss": 0.7218, "lr": 8.662828002923378e-05, "epoch": 0.9467455621301775, "percentage": 31.52, "elapsed_time": "8:05:18", "remaining_time": "17:34:26"}
+{"current_steps": 670, "total_steps": 2094, "loss": 0.719, "lr": 8.605567927751576e-05, "epoch": 0.9610901918594227, "percentage": 32.0, "elapsed_time": "8:12:26", "remaining_time": "17:26:37"}
+{"current_steps": 680, "total_steps": 2094, "loss": 0.7089, "lr": 8.547305312908318e-05, "epoch": 0.9754348215886678, "percentage": 32.47, "elapsed_time": "8:19:29", "remaining_time": "17:18:38"}
+{"current_steps": 690, "total_steps": 2094, "loss": 0.7075, "lr": 8.48805635849964e-05, "epoch": 0.9897794513179129, "percentage": 32.95, "elapsed_time": "8:26:48", "remaining_time": "17:11:13"}
+{"current_steps": 700, "total_steps": 2094, "loss": 0.6894, "lr": 8.427837538886437e-05, "epoch": 1.002868925945849, "percentage": 33.43, "elapsed_time": "8:33:20", "remaining_time": "17:02:17"}
+{"current_steps": 710, "total_steps": 2094, "loss": 0.5865, "lr": 8.366665598103727e-05, "epoch": 1.017213555675094, "percentage": 33.91, "elapsed_time": "8:40:29", "remaining_time": "16:54:35"}
+{"current_steps": 720, "total_steps": 2094, "loss": 0.5931, "lr": 8.304557545204908e-05, "epoch": 1.0315581854043392, "percentage": 34.38, "elapsed_time": "8:47:43", "remaining_time": "16:47:04"}
+{"current_steps": 730, "total_steps": 2094, "loss": 0.5859, "lr": 8.241530649532339e-05, "epoch": 1.0459028151335843, "percentage": 34.86, "elapsed_time": "8:54:53", "remaining_time": "16:39:25"}
+{"current_steps": 740, "total_steps": 2094, "loss": 0.5833, "lr": 8.177602435915546e-05, "epoch": 1.0602474448628294, "percentage": 35.34, "elapsed_time": "9:02:04", "remaining_time": "16:31:50"}
+{"current_steps": 750, "total_steps": 2094, "loss": 0.5805, "lr": 8.11279067979839e-05, "epoch": 1.0745920745920745, "percentage": 35.82, "elapsed_time": "9:09:21", "remaining_time": "16:24:27"}
+{"current_steps": 760, "total_steps": 2094, "loss": 0.5733, "lr": 8.04711340229654e-05, "epoch": 1.0889367043213196, "percentage": 36.29, "elapsed_time": "9:16:28", "remaining_time": "16:16:45"}
+{"current_steps": 770, "total_steps": 2094, "loss": 0.5812, "lr": 7.980588865186649e-05, "epoch": 1.1032813340505647, "percentage": 36.77, "elapsed_time": "9:23:37", "remaining_time": "16:09:08"}
+{"current_steps": 780, "total_steps": 2094, "loss": 0.5811, "lr": 7.913235565828613e-05, "epoch": 1.11762596377981, "percentage": 37.25, "elapsed_time": "9:30:52", "remaining_time": "16:01:42"}
+{"current_steps": 790, "total_steps": 2094, "loss": 0.5755, "lr": 7.845072232022311e-05, "epoch": 1.1319705935090552, "percentage": 37.73, "elapsed_time": "9:38:07", "remaining_time": "15:54:15"}
+{"current_steps": 800, "total_steps": 2094, "loss": 0.5916, "lr": 7.776117816800288e-05, "epoch": 1.1463152232383003, "percentage": 38.2, "elapsed_time": "9:45:14", "remaining_time": "15:46:38"}
+{"current_steps": 810, "total_steps": 2094, "loss": 0.5822, "lr": 7.706391493157805e-05, "epoch": 1.1606598529675454, "percentage": 38.68, "elapsed_time": "9:52:29", "remaining_time": "15:39:12"}
+{"current_steps": 820, "total_steps": 2094, "loss": 0.5811, "lr": 7.635912648721718e-05, "epoch": 1.1750044826967905, "percentage": 39.16, "elapsed_time": "9:59:31", "remaining_time": "15:31:27"}
+{"current_steps": 830, "total_steps": 2094, "loss": 0.5799, "lr": 7.564700880359696e-05, "epoch": 1.1893491124260356, "percentage": 39.64, "elapsed_time": "10:06:41", "remaining_time": "15:23:54"}
+{"current_steps": 840, "total_steps": 2094, "loss": 0.5673, "lr": 7.492775988731243e-05, "epoch": 1.2036937421552807, "percentage": 40.11, "elapsed_time": "10:13:53", "remaining_time": "15:16:27"}
+{"current_steps": 850, "total_steps": 2094, "loss": 0.5754, "lr": 7.420157972782063e-05, "epoch": 1.2180383718845258, "percentage": 40.59, "elapsed_time": "10:21:03", "remaining_time": "15:08:56"}
+{"current_steps": 860, "total_steps": 2094, "loss": 0.579, "lr": 7.346867024183291e-05, "epoch": 1.232383001613771, "percentage": 41.07, "elapsed_time": "10:28:11", "remaining_time": "15:01:22"}
+{"current_steps": 870, "total_steps": 2094, "loss": 0.5756, "lr": 7.272923521717133e-05, "epoch": 1.246727631343016, "percentage": 41.55, "elapsed_time": "10:35:21", "remaining_time": "14:53:52"}
+{"current_steps": 880, "total_steps": 2094, "loss": 0.5769, "lr": 7.198348025610481e-05, "epoch": 1.2610722610722611, "percentage": 42.02, "elapsed_time": "10:42:28", "remaining_time": "14:46:18"}
+{"current_steps": 890, "total_steps": 2094, "loss": 0.5685, "lr": 7.12316127181808e-05, "epoch": 1.2754168908015062, "percentage": 42.5, "elapsed_time": "10:49:30", "remaining_time": "14:38:39"}
+{"current_steps": 900, "total_steps": 2094, "loss": 0.5801, "lr": 7.047384166256815e-05, "epoch": 1.2897615205307513, "percentage": 42.98, "elapsed_time": "10:56:40", "remaining_time": "14:31:11"}
+{"current_steps": 910, "total_steps": 2094, "loss": 0.5795, "lr": 6.971037778992775e-05, "epoch": 1.3041061502599964, "percentage": 43.46, "elapsed_time": "11:03:49", "remaining_time": "14:23:42"}
+{"current_steps": 920, "total_steps": 2094, "loss": 0.5768, "lr": 6.894143338382639e-05, "epoch": 1.3184507799892415, "percentage": 43.94, "elapsed_time": "11:11:03", "remaining_time": "14:16:19"}
+{"current_steps": 930, "total_steps": 2094, "loss": 0.578, "lr": 6.81672222517107e-05, "epoch": 1.3327954097184866, "percentage": 44.41, "elapsed_time": "11:18:02", "remaining_time": "14:08:39"}
+{"current_steps": 940, "total_steps": 2094, "loss": 0.5682, "lr": 6.73879596654573e-05, "epoch": 1.3471400394477318, "percentage": 44.89, "elapsed_time": "11:25:08", "remaining_time": "14:01:06"}
+{"current_steps": 950, "total_steps": 2094, "loss": 0.5735, "lr": 6.660386230151571e-05, "epoch": 1.3614846691769769, "percentage": 45.37, "elapsed_time": "11:32:15", "remaining_time": "13:53:37"}
+{"current_steps": 960, "total_steps": 2094, "loss": 0.5739, "lr": 6.581514818066088e-05, "epoch": 1.375829298906222, "percentage": 45.85, "elapsed_time": "11:39:24", "remaining_time": "13:46:10"}
+{"current_steps": 970, "total_steps": 2094, "loss": 0.5688, "lr": 6.502203660737169e-05, "epoch": 1.390173928635467, "percentage": 46.32, "elapsed_time": "11:46:22", "remaining_time": "13:38:30"}
+{"current_steps": 980, "total_steps": 2094, "loss": 0.5669, "lr": 6.422474810885278e-05, "epoch": 1.4045185583647122, "percentage": 46.8, "elapsed_time": "11:53:33", "remaining_time": "13:31:07"}
+{"current_steps": 990, "total_steps": 2094, "loss": 0.5702, "lr": 6.342350437371614e-05, "epoch": 1.4188631880939573, "percentage": 47.28, "elapsed_time": "12:00:46", "remaining_time": "13:23:46"}
+{"current_steps": 1000, "total_steps": 2094, "loss": 0.5685, "lr": 6.26185281903399e-05, "epoch": 1.4332078178232024, "percentage": 47.76, "elapsed_time": "12:07:55", "remaining_time": "13:16:21"}
+{"current_steps": 1010, "total_steps": 2094, "loss": 0.5651, "lr": 6.181004338492141e-05, "epoch": 1.4475524475524475, "percentage": 48.23, "elapsed_time": "12:16:28", "remaining_time": "13:10:25"}
+{"current_steps": 1020, "total_steps": 2094, "loss": 0.5615, "lr": 6.09982747592415e-05, "epoch": 1.4618970772816926, "percentage": 48.71, "elapsed_time": "12:23:47", "remaining_time": "13:03:09"}
+{"current_steps": 1030, "total_steps": 2094, "loss": 0.5679, "lr": 6.018344802815778e-05, "epoch": 1.4762417070109377, "percentage": 49.19, "elapsed_time": "12:31:03", "remaining_time": "12:55:51"}
+{"current_steps": 1040, "total_steps": 2094, "loss": 0.5701, "lr": 5.936578975684378e-05, "epoch": 1.4905863367401828, "percentage": 49.67, "elapsed_time": "12:38:12", "remaining_time": "12:48:24"}
+{"current_steps": 1050, "total_steps": 2094, "loss": 0.5627, "lr": 5.854552729779184e-05, "epoch": 1.504930966469428, "percentage": 50.14, "elapsed_time": "12:45:21", "remaining_time": "12:40:59"}
+{"current_steps": 1060, "total_steps": 2094, "loss": 0.5625, "lr": 5.772288872759702e-05, "epoch": 1.519275596198673, "percentage": 50.62, "elapsed_time": "12:52:24", "remaining_time": "12:33:27"}
+{"current_steps": 1070, "total_steps": 2094, "loss": 0.5606, "lr": 5.6898102783539665e-05, "epoch": 1.5336202259279181, "percentage": 51.1, "elapsed_time": "12:59:29", "remaining_time": "12:25:58"}
+{"current_steps": 1080, "total_steps": 2094, "loss": 0.5595, "lr": 5.607139879998427e-05, "epoch": 1.5479648556571632, "percentage": 51.58, "elapsed_time": "13:06:34", "remaining_time": "12:18:30"}
+{"current_steps": 1090, "total_steps": 2094, "loss": 0.5575, "lr": 5.524300664461235e-05, "epoch": 1.5623094853864083, "percentage": 52.05, "elapsed_time": "13:13:42", "remaining_time": "12:11:05"}
+{"current_steps": 1100, "total_steps": 2094, "loss": 0.5589, "lr": 5.441315665450697e-05, "epoch": 1.5766541151156535, "percentage": 52.53, "elapsed_time": "13:20:52", "remaining_time": "12:03:41"}
+{"current_steps": 1110, "total_steps": 2094, "loss": 0.5534, "lr": 5.3582079572106794e-05, "epoch": 1.5909987448448986, "percentage": 53.01, "elapsed_time": "13:28:01", "remaining_time": "11:56:18"}
+{"current_steps": 1120, "total_steps": 2094, "loss": 0.5569, "lr": 5.275000648104743e-05, "epoch": 1.6053433745741437, "percentage": 53.49, "elapsed_time": "13:35:09", "remaining_time": "11:48:53"}
+{"current_steps": 1130, "total_steps": 2094, "loss": 0.5564, "lr": 5.191716874190785e-05, "epoch": 1.6196880043033888, "percentage": 53.96, "elapsed_time": "13:42:22", "remaining_time": "11:41:33"}
+{"current_steps": 1140, "total_steps": 2094, "loss": 0.5552, "lr": 5.1083797927879896e-05, "epoch": 1.6340326340326339, "percentage": 54.44, "elapsed_time": "13:49:23", "remaining_time": "11:34:04"}
+{"current_steps": 1150, "total_steps": 2094, "loss": 0.564, "lr": 5.025012576037855e-05, "epoch": 1.648377263761879, "percentage": 54.92, "elapsed_time": "13:56:22", "remaining_time": "11:26:33"}
+{"current_steps": 1160, "total_steps": 2094, "loss": 0.5579, "lr": 4.9416384044611124e-05, "epoch": 1.6627218934911243, "percentage": 55.4, "elapsed_time": "14:03:25", "remaining_time": "11:19:06"}
+{"current_steps": 1170, "total_steps": 2094, "loss": 0.5551, "lr": 4.858280460512302e-05, "epoch": 1.6770665232203694, "percentage": 55.87, "elapsed_time": "14:10:33", "remaining_time": "11:11:43"}
+{"current_steps": 1180, "total_steps": 2094, "loss": 0.5553, "lr": 4.7749619221338227e-05, "epoch": 1.6914111529496145, "percentage": 56.35, "elapsed_time": "14:17:56", "remaining_time": "11:04:32"}
+{"current_steps": 1190, "total_steps": 2094, "loss": 0.554, "lr": 4.691705956311225e-05, "epoch": 1.7057557826788596, "percentage": 56.83, "elapsed_time": "14:25:26", "remaining_time": "10:57:26"}
+{"current_steps": 1200, "total_steps": 2094, "loss": 0.553, "lr": 4.608535712631566e-05, "epoch": 1.7201004124081047, "percentage": 57.31, "elapsed_time": "14:32:33", "remaining_time": "10:50:03"}
+{"current_steps": 1210, "total_steps": 2094, "loss": 0.5455, "lr": 4.525474316846581e-05, "epoch": 1.7344450421373498, "percentage": 57.78, "elapsed_time": "14:39:42", "remaining_time": "10:42:41"}
+{"current_steps": 1220, "total_steps": 2094, "loss": 0.5487, "lr": 4.4425448644425066e-05, "epoch": 1.748789671866595, "percentage": 58.26, "elapsed_time": "14:46:47", "remaining_time": "10:35:17"}
+{"current_steps": 1230, "total_steps": 2094, "loss": 0.5401, "lr": 4.359770414218296e-05, "epoch": 1.76313430159584, "percentage": 58.74, "elapsed_time": "14:53:58", "remaining_time": "10:27:57"}
+{"current_steps": 1240, "total_steps": 2094, "loss": 0.5496, "lr": 4.2771739818740565e-05, "epoch": 1.7774789313250852, "percentage": 59.22, "elapsed_time": "15:01:07", "remaining_time": "10:20:36"}
+{"current_steps": 1250, "total_steps": 2094, "loss": 0.5413, "lr": 4.194778533611451e-05, "epoch": 1.7918235610543303, "percentage": 59.69, "elapsed_time": "15:08:21", "remaining_time": "10:13:19"}
+{"current_steps": 1260, "total_steps": 2094, "loss": 0.544, "lr": 4.112606979747881e-05, "epoch": 1.8061681907835754, "percentage": 60.17, "elapsed_time": "15:15:32", "remaining_time": "10:06:00"}
+{"current_steps": 1270, "total_steps": 2094, "loss": 0.5358, "lr": 4.030682168346192e-05, "epoch": 1.8205128205128205, "percentage": 60.65, "elapsed_time": "15:22:43", "remaining_time": "9:58:40"}
+{"current_steps": 1280, "total_steps": 2094, "loss": 0.539, "lr": 3.949026878861704e-05, "epoch": 1.8348574502420656, "percentage": 61.13, "elapsed_time": "15:29:53", "remaining_time": "9:51:21"}
+{"current_steps": 1290, "total_steps": 2094, "loss": 0.5389, "lr": 3.867663815808303e-05, "epoch": 1.8492020799713107, "percentage": 61.6, "elapsed_time": "15:37:01", "remaining_time": "9:44:00"}
+{"current_steps": 1300, "total_steps": 2094, "loss": 0.5363, "lr": 3.78661560244539e-05, "epoch": 1.8635467097005558, "percentage": 62.08, "elapsed_time": "15:44:05", "remaining_time": "9:36:37"}
+{"current_steps": 1310, "total_steps": 2094, "loss": 0.5319, "lr": 3.705904774487396e-05, "epoch": 1.8778913394298011, "percentage": 62.56, "elapsed_time": "15:51:07", "remaining_time": "9:29:13"}
+{"current_steps": 1320, "total_steps": 2094, "loss": 0.5402, "lr": 3.6255537738376706e-05, "epoch": 1.8922359691590462, "percentage": 63.04, "elapsed_time": "15:58:12", "remaining_time": "9:21:51"}
+{"current_steps": 1330, "total_steps": 2094, "loss": 0.5309, "lr": 3.545584942348426e-05, "epoch": 1.9065805988882913, "percentage": 63.51, "elapsed_time": "16:05:28", "remaining_time": "9:14:36"}
+{"current_steps": 1340, "total_steps": 2094, "loss": 0.5298, "lr": 3.466020515608525e-05, "epoch": 1.9209252286175365, "percentage": 63.99, "elapsed_time": "16:12:29", "remaining_time": "9:07:12"}
+{"current_steps": 1350, "total_steps": 2094, "loss": 0.5319, "lr": 3.386882616760794e-05, "epoch": 1.9352698583467816, "percentage": 64.47, "elapsed_time": "16:19:34", "remaining_time": "8:59:51"}
+{"current_steps": 1360, "total_steps": 2094, "loss": 0.5287, "lr": 3.30819325035062e-05, "epoch": 1.9496144880760267, "percentage": 64.95, "elapsed_time": "16:26:42", "remaining_time": "8:52:31"}
+{"current_steps": 1370, "total_steps": 2094, "loss": 0.5385, "lr": 3.229974296207513e-05, "epoch": 1.9639591178052718, "percentage": 65.43, "elapsed_time": "16:33:55", "remaining_time": "8:45:15"}
+{"current_steps": 1380, "total_steps": 2094, "loss": 0.527, "lr": 3.152247503361353e-05, "epoch": 1.9783037475345169, "percentage": 65.9, "elapsed_time": "16:41:01", "remaining_time": "8:37:55"}
+{"current_steps": 1390, "total_steps": 2094, "loss": 0.5257, "lr": 3.075034483994997e-05, "epoch": 1.992648377263762, "percentage": 66.38, "elapsed_time": "16:48:02", "remaining_time": "8:30:32"}
+{"current_steps": 1400, "total_steps": 2094, "loss": 0.4623, "lr": 2.998356707434947e-05, "epoch": 2.005737851891698, "percentage": 66.86, "elapsed_time": "16:54:21", "remaining_time": "8:22:49"}
+{"current_steps": 1410, "total_steps": 2094, "loss": 0.3606, "lr": 2.9222354941817375e-05, "epoch": 2.020082481620943, "percentage": 67.34, "elapsed_time": "17:01:30", "remaining_time": "8:15:32"}
+{"current_steps": 1420, "total_steps": 2094, "loss": 0.3527, "lr": 2.846692009981693e-05, "epoch": 2.034427111350188, "percentage": 67.81, "elapsed_time": "17:08:38", "remaining_time": "8:08:14"}
+{"current_steps": 1430, "total_steps": 2094, "loss": 0.3462, "lr": 2.771747259941734e-05, "epoch": 2.0487717410794333, "percentage": 68.29, "elapsed_time": "17:15:44", "remaining_time": "8:00:55"}
+{"current_steps": 1440, "total_steps": 2094, "loss": 0.342, "lr": 2.6974220826888374e-05, "epoch": 2.0631163708086784, "percentage": 68.77, "elapsed_time": "17:22:47", "remaining_time": "7:53:35"}
+{"current_steps": 1450, "total_steps": 2094, "loss": 0.3462, "lr": 2.623737144575787e-05, "epoch": 2.0774610005379235, "percentage": 69.25, "elapsed_time": "17:29:53", "remaining_time": "7:46:17"}
+{"current_steps": 1460, "total_steps": 2094, "loss": 0.3487, "lr": 2.5507129339348335e-05, "epoch": 2.0918056302671686, "percentage": 69.72, "elapsed_time": "17:36:58", "remaining_time": "7:38:59"}
+{"current_steps": 1470, "total_steps": 2094, "loss": 0.3465, "lr": 2.478369755380839e-05, "epoch": 2.1061502599964137, "percentage": 70.2, "elapsed_time": "17:44:02", "remaining_time": "7:31:40"}
+{"current_steps": 1480, "total_steps": 2094, "loss": 0.3451, "lr": 2.406727724165524e-05, "epoch": 2.120494889725659, "percentage": 70.68, "elapsed_time": "17:51:10", "remaining_time": "7:24:23"}
+{"current_steps": 1490, "total_steps": 2094, "loss": 0.3442, "lr": 2.3358067605843537e-05, "epoch": 2.134839519454904, "percentage": 71.16, "elapsed_time": "17:58:15", "remaining_time": "7:17:05"}
+{"current_steps": 1500, "total_steps": 2094, "loss": 0.3449, "lr": 2.2656265844376367e-05, "epoch": 2.149184149184149, "percentage": 71.63, "elapsed_time": "18:05:24", "remaining_time": "7:09:49"}
+{"current_steps": 1510, "total_steps": 2094, "loss": 0.3443, "lr": 2.1962067095473648e-05, "epoch": 2.163528778913394, "percentage": 72.11, "elapsed_time": "18:13:46", "remaining_time": "7:03:01"}
+{"current_steps": 1520, "total_steps": 2094, "loss": 0.3443, "lr": 2.127566438331345e-05, "epoch": 2.1778734086426392, "percentage": 72.59, "elapsed_time": "18:20:58", "remaining_time": "6:55:45"}
+{"current_steps": 1530, "total_steps": 2094, "loss": 0.34, "lr": 2.059724856436092e-05, "epoch": 2.1922180383718843, "percentage": 73.07, "elapsed_time": "18:28:01", "remaining_time": "6:48:27"}
+{"current_steps": 1540, "total_steps": 2094, "loss": 0.3447, "lr": 1.992700827430007e-05, "epoch": 2.2065626681011294, "percentage": 73.54, "elapsed_time": "18:35:15", "remaining_time": "6:41:12"}
+{"current_steps": 1550, "total_steps": 2094, "loss": 0.3402, "lr": 1.9265129875582954e-05, "epoch": 2.2209072978303745, "percentage": 74.02, "elapsed_time": "18:42:21", "remaining_time": "6:33:54"}
+{"current_steps": 1560, "total_steps": 2094, "loss": 0.3434, "lr": 1.8611797405611097e-05, "epoch": 2.23525192755962, "percentage": 74.5, "elapsed_time": "18:49:18", "remaining_time": "6:26:34"}
+{"current_steps": 1570, "total_steps": 2094, "loss": 0.3429, "lr": 1.7967192525563254e-05, "epoch": 2.249596557288865, "percentage": 74.98, "elapsed_time": "18:56:27", "remaining_time": "6:19:18"}
+{"current_steps": 1580, "total_steps": 2094, "loss": 0.3402, "lr": 1.733149446988394e-05, "epoch": 2.2639411870181103, "percentage": 75.45, "elapsed_time": "19:03:42", "remaining_time": "6:12:03"}
+{"current_steps": 1590, "total_steps": 2094, "loss": 0.3413, "lr": 1.670487999644669e-05, "epoch": 2.2782858167473554, "percentage": 75.93, "elapsed_time": "19:10:51", "remaining_time": "6:04:48"}
+{"current_steps": 1600, "total_steps": 2094, "loss": 0.3407, "lr": 1.6087523337406024e-05, "epoch": 2.2926304464766005, "percentage": 76.41, "elapsed_time": "19:17:51", "remaining_time": "5:57:29"}
+{"current_steps": 1610, "total_steps": 2094, "loss": 0.3343, "lr": 1.547959615075164e-05, "epoch": 2.3069750762058456, "percentage": 76.89, "elapsed_time": "19:25:05", "remaining_time": "5:50:15"}
+{"current_steps": 1620, "total_steps": 2094, "loss": 0.3415, "lr": 1.4881267472578325e-05, "epoch": 2.3213197059350907, "percentage": 77.36, "elapsed_time": "19:32:12", "remaining_time": "5:42:58"}
+{"current_steps": 1630, "total_steps": 2094, "loss": 0.3392, "lr": 1.4292703670084916e-05, "epoch": 2.335664335664336, "percentage": 77.84, "elapsed_time": "19:39:22", "remaining_time": "5:35:43"}
+{"current_steps": 1640, "total_steps": 2094, "loss": 0.3349, "lr": 1.3714068395315427e-05, "epoch": 2.350008965393581, "percentage": 78.32, "elapsed_time": "19:46:27", "remaining_time": "5:28:26"}
+{"current_steps": 1650, "total_steps": 2094, "loss": 0.3354, "lr": 1.3145522539655041e-05, "epoch": 2.364353595122826, "percentage": 78.8, "elapsed_time": "19:53:34", "remaining_time": "5:21:10"}
+{"current_steps": 1660, "total_steps": 2094, "loss": 0.3302, "lr": 1.2587224189093755e-05, "epoch": 2.378698224852071, "percentage": 79.27, "elapsed_time": "20:00:48", "remaining_time": "5:13:56"}
+{"current_steps": 1670, "total_steps": 2094, "loss": 0.3333, "lr": 1.2039328580270065e-05, "epoch": 2.3930428545813163, "percentage": 79.75, "elapsed_time": "20:07:55", "remaining_time": "5:06:40"}
+{"current_steps": 1680, "total_steps": 2094, "loss": 0.3329, "lr": 1.150198805730689e-05, "epoch": 2.4073874843105614, "percentage": 80.23, "elapsed_time": "20:14:59", "remaining_time": "4:59:24"}
+{"current_steps": 1690, "total_steps": 2094, "loss": 0.3337, "lr": 1.0975352029451863e-05, "epoch": 2.4217321140398065, "percentage": 80.71, "elapsed_time": "20:22:00", "remaining_time": "4:52:07"}
+{"current_steps": 1700, "total_steps": 2094, "loss": 0.3345, "lr": 1.0459566929533588e-05, "epoch": 2.4360767437690516, "percentage": 81.18, "elapsed_time": "20:29:05", "remaining_time": "4:44:51"}
+{"current_steps": 1710, "total_steps": 2094, "loss": 0.3369, "lr": 9.954776173245511e-06, "epoch": 2.4504213734982967, "percentage": 81.66, "elapsed_time": "20:36:04", "remaining_time": "4:37:34"}
+{"current_steps": 1720, "total_steps": 2094, "loss": 0.3338, "lr": 9.461120119268713e-06, "epoch": 2.464766003227542, "percentage": 82.14, "elapsed_time": "20:43:15", "remaining_time": "4:30:20"}
+{"current_steps": 1730, "total_steps": 2094, "loss": 0.331, "lr": 8.978736030244783e-06, "epoch": 2.479110632956787, "percentage": 82.62, "elapsed_time": "20:50:21", "remaining_time": "4:23:04"}
+{"current_steps": 1740, "total_steps": 2094, "loss": 0.3336, "lr": 8.50775803460948e-06, "epoch": 2.493455262686032, "percentage": 83.09, "elapsed_time": "20:57:22", "remaining_time": "4:15:48"}
+{"current_steps": 1750, "total_steps": 2094, "loss": 0.331, "lr": 8.048317089297875e-06, "epoch": 2.507799892415277, "percentage": 83.57, "elapsed_time": "21:04:31", "remaining_time": "4:08:34"}
+{"current_steps": 1760, "total_steps": 2094, "loss": 0.3316, "lr": 7.600540943331347e-06, "epoch": 2.5221445221445222, "percentage": 84.05, "elapsed_time": "21:11:40", "remaining_time": "4:01:19"}
+{"current_steps": 1770, "total_steps": 2094, "loss": 0.3322, "lr": 7.164554102296617e-06, "epoch": 2.5364891518737673, "percentage": 84.53, "elapsed_time": "21:18:43", "remaining_time": "3:54:04"}
+{"current_steps": 1780, "total_steps": 2094, "loss": 0.3302, "lr": 6.740477793726529e-06, "epoch": 2.5508337816030124, "percentage": 85.0, "elapsed_time": "21:25:43", "remaining_time": "3:46:48"}
+{"current_steps": 1790, "total_steps": 2094, "loss": 0.3278, "lr": 6.32842993339236e-06, "epoch": 2.5651784113322575, "percentage": 85.48, "elapsed_time": "21:32:46", "remaining_time": "3:39:33"}
+{"current_steps": 1800, "total_steps": 2094, "loss": 0.3334, "lr": 5.928525092516934e-06, "epoch": 2.5795230410615027, "percentage": 85.96, "elapsed_time": "21:39:50", "remaining_time": "3:32:18"}
+{"current_steps": 1810, "total_steps": 2094, "loss": 0.3325, "lr": 5.540874465917778e-06, "epoch": 2.5938676707907478, "percentage": 86.44, "elapsed_time": "21:46:47", "remaining_time": "3:25:02"}
+{"current_steps": 1820, "total_steps": 2094, "loss": 0.3246, "lr": 5.165585841089021e-06, "epoch": 2.608212300519993, "percentage": 86.91, "elapsed_time": "21:53:56", "remaining_time": "3:17:48"}
+{"current_steps": 1830, "total_steps": 2094, "loss": 0.325, "lr": 4.8027635682307445e-06, "epoch": 2.622556930249238, "percentage": 87.39, "elapsed_time": "22:01:06", "remaining_time": "3:10:35"}
+{"current_steps": 1840, "total_steps": 2094, "loss": 0.3267, "lr": 4.45250853123404e-06, "epoch": 2.636901559978483, "percentage": 87.87, "elapsed_time": "22:08:14", "remaining_time": "3:03:21"}
+{"current_steps": 1850, "total_steps": 2094, "loss": 0.3277, "lr": 4.1149181196299905e-06, "epoch": 2.651246189707728, "percentage": 88.35, "elapsed_time": "22:15:21", "remaining_time": "2:56:07"}
+{"current_steps": 1860, "total_steps": 2094, "loss": 0.3285, "lr": 3.7900862015101457e-06, "epoch": 2.6655908194369733, "percentage": 88.83, "elapsed_time": "22:22:29", "remaining_time": "2:48:53"}
+{"current_steps": 1870, "total_steps": 2094, "loss": 0.3268, "lr": 3.4781030974262108e-06, "epoch": 2.6799354491662184, "percentage": 89.3, "elapsed_time": "22:29:38", "remaining_time": "2:41:40"}
+{"current_steps": 1880, "total_steps": 2094, "loss": 0.3246, "lr": 3.1790555552761615e-06, "epoch": 2.6942800788954635, "percentage": 89.78, "elapsed_time": "22:36:48", "remaining_time": "2:34:26"}
+{"current_steps": 1890, "total_steps": 2094, "loss": 0.3231, "lr": 2.8930267261836395e-06, "epoch": 2.7086247086247086, "percentage": 90.26, "elapsed_time": "22:43:56", "remaining_time": "2:27:13"}
+{"current_steps": 1900, "total_steps": 2094, "loss": 0.324, "lr": 2.6200961413776094e-06, "epoch": 2.7229693383539537, "percentage": 90.74, "elapsed_time": "22:51:04", "remaining_time": "2:19:59"}
+{"current_steps": 1910, "total_steps": 2094, "loss": 0.3251, "lr": 2.3603396900783724e-06, "epoch": 2.737313968083199, "percentage": 91.21, "elapsed_time": "22:58:06", "remaining_time": "2:12:45"}
+{"current_steps": 1920, "total_steps": 2094, "loss": 0.322, "lr": 2.113829598396383e-06, "epoch": 2.751658597812444, "percentage": 91.69, "elapsed_time": "23:05:05", "remaining_time": "2:05:31"}
+{"current_steps": 1930, "total_steps": 2094, "loss": 0.3248, "lr": 1.8806344092494932e-06, "epoch": 2.766003227541689, "percentage": 92.17, "elapsed_time": "23:12:01", "remaining_time": "1:58:17"}
+{"current_steps": 1940, "total_steps": 2094, "loss": 0.325, "lr": 1.6608189633044113e-06, "epoch": 2.780347857270934, "percentage": 92.65, "elapsed_time": "23:19:13", "remaining_time": "1:51:04"}
+{"current_steps": 1950, "total_steps": 2094, "loss": 0.3247, "lr": 1.4544443809475561e-06, "epoch": 2.7946924870001792, "percentage": 93.12, "elapsed_time": "23:26:19", "remaining_time": "1:43:51"}
+{"current_steps": 1960, "total_steps": 2094, "loss": 0.3234, "lr": 1.2615680452903067e-06, "epoch": 2.8090371167294244, "percentage": 93.6, "elapsed_time": "23:33:27", "remaining_time": "1:36:38"}
+{"current_steps": 1970, "total_steps": 2094, "loss": 0.3219, "lr": 1.082243586213455e-06, "epoch": 2.8233817464586695, "percentage": 94.08, "elapsed_time": "23:40:41", "remaining_time": "1:29:25"}
+{"current_steps": 1980, "total_steps": 2094, "loss": 0.321, "lr": 9.165208654552671e-07, "epoch": 2.8377263761879146, "percentage": 94.56, "elapsed_time": "23:47:42", "remaining_time": "1:22:12"}
+{"current_steps": 1990, "total_steps": 2094, "loss": 0.3229, "lr": 7.6444596274724e-07, "epoch": 2.8520710059171597, "percentage": 95.03, "elapsed_time": "23:54:49", "remaining_time": "1:14:59"}
+{"current_steps": 2000, "total_steps": 2094, "loss": 0.3221, "lr": 6.260611630015067e-07, "epoch": 2.866415635646405, "percentage": 95.51, "elapsed_time": "1 day, 0:01:52", "remaining_time": "1:07:46"}
+{"current_steps": 2010, "total_steps": 2094, "loss": 0.3219, "lr": 5.01404944553363e-07, "epoch": 2.88076026537565, "percentage": 95.99, "elapsed_time": "1 day, 0:10:18", "remaining_time": "1:00:36"}
+{"current_steps": 2020, "total_steps": 2094, "loss": 0.3251, "lr": 3.9051196846225935e-07, "epoch": 2.895104895104895, "percentage": 96.47, "elapsed_time": "1 day, 0:17:23", "remaining_time": "0:53:23"}
+{"current_steps": 2030, "total_steps": 2094, "loss": 0.3213, "lr": 2.9341306887417653e-07, "epoch": 2.90944952483414, "percentage": 96.94, "elapsed_time": "1 day, 0:24:30", "remaining_time": "0:46:10"}
+{"current_steps": 2040, "total_steps": 2094, "loss": 0.3241, "lr": 2.101352444480842e-07, "epoch": 2.923794154563385, "percentage": 97.42, "elapsed_time": "1 day, 0:31:35", "remaining_time": "0:38:57"}
+{"current_steps": 2050, "total_steps": 2094, "loss": 0.3199, "lr": 1.4070165084889008e-07, "epoch": 2.9381387842926303, "percentage": 97.9, "elapsed_time": "1 day, 0:38:40", "remaining_time": "0:31:44"}
+{"current_steps": 2060, "total_steps": 2094, "loss": 0.3225, "lr": 8.513159430892925e-08, "epoch": 2.9524834140218754, "percentage": 98.38, "elapsed_time": "1 day, 0:45:40", "remaining_time": "0:24:31"}
+{"current_steps": 2070, "total_steps": 2094, "loss": 0.3219, "lr": 4.344052625981365e-08, "epoch": 2.9668280437511205, "percentage": 98.85, "elapsed_time": "1 day, 0:52:50", "remaining_time": "0:17:18"}
+{"current_steps": 2080, "total_steps": 2094, "loss": 0.3187, "lr": 1.5640039036085575e-08, "epoch": 2.9811726734803656, "percentage": 99.33, "elapsed_time": "1 day, 0:59:53", "remaining_time": "0:10:05"}
+{"current_steps": 2090, "total_steps": 2094, "loss": 0.3238, "lr": 1.7378626519626296e-09, "epoch": 2.9955173032096107, "percentage": 99.81, "elapsed_time": "1 day, 1:07:00", "remaining_time": "0:02:53"}
+{"current_steps": 2094, "total_steps": 2094, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 1:10:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1506 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2094,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014344629729245113,
+      "grad_norm": 3.3866311674749072,
+      "learning_rate": 4.285714285714286e-06,
+      "loss": 1.5266,
+      "step": 10
+    },
+    {
+      "epoch": 0.028689259458490227,
+      "grad_norm": 1.8728384521077752,
+      "learning_rate": 9.047619047619047e-06,
+      "loss": 1.3066,
+      "step": 20
+    },
+    {
+      "epoch": 0.04303388918773534,
+      "grad_norm": 1.1126841032649692,
+      "learning_rate": 1.3809523809523811e-05,
+      "loss": 1.1436,
+      "step": 30
+    },
+    {
+      "epoch": 0.05737851891698045,
+      "grad_norm": 1.1207104465369435,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 1.0535,
+      "step": 40
+    },
+    {
+      "epoch": 0.07172314864622557,
+      "grad_norm": 1.1391226479086436,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.0172,
+      "step": 50
+    },
+    {
+      "epoch": 0.08606777837547068,
+      "grad_norm": 1.146545389971907,
+      "learning_rate": 2.8095238095238096e-05,
+      "loss": 0.9859,
+      "step": 60
+    },
+    {
+      "epoch": 0.1004124081047158,
+      "grad_norm": 1.1888015259911366,
+      "learning_rate": 3.285714285714286e-05,
+      "loss": 0.9528,
+      "step": 70
+    },
+    {
+      "epoch": 0.1147570378339609,
+      "grad_norm": 1.2903823343286538,
+      "learning_rate": 3.761904761904762e-05,
+      "loss": 0.9397,
+      "step": 80
+    },
+    {
+      "epoch": 0.129101667563206,
+      "grad_norm": 1.2943713329149742,
+      "learning_rate": 4.2380952380952385e-05,
+      "loss": 0.9282,
+      "step": 90
+    },
+    {
+      "epoch": 0.14344629729245115,
+      "grad_norm": 1.2718909502396083,
+      "learning_rate": 4.714285714285714e-05,
+      "loss": 0.9186,
+      "step": 100
+    },
+    {
+      "epoch": 0.15779092702169625,
+      "grad_norm": 1.4791012823315328,
+      "learning_rate": 5.1904761904761913e-05,
+      "loss": 0.9074,
+      "step": 110
+    },
+    {
+      "epoch": 0.17213555675094136,
+      "grad_norm": 1.336532460075517,
+      "learning_rate": 5.666666666666667e-05,
+      "loss": 0.9002,
+      "step": 120
+    },
+    {
+      "epoch": 0.1864801864801865,
+      "grad_norm": 1.6094057366302217,
+      "learning_rate": 6.142857142857143e-05,
+      "loss": 0.8887,
+      "step": 130
+    },
+    {
+      "epoch": 0.2008248162094316,
+      "grad_norm": 1.070539230983606,
+      "learning_rate": 6.619047619047619e-05,
+      "loss": 0.884,
+      "step": 140
+    },
+    {
+      "epoch": 0.2151694459386767,
+      "grad_norm": 1.1200792510458928,
+      "learning_rate": 7.095238095238096e-05,
+      "loss": 0.8809,
+      "step": 150
+    },
+    {
+      "epoch": 0.2295140756679218,
+      "grad_norm": 1.087537431311211,
+      "learning_rate": 7.571428571428571e-05,
+      "loss": 0.8799,
+      "step": 160
+    },
+    {
+      "epoch": 0.24385870539716695,
+      "grad_norm": 0.9999716597796505,
+      "learning_rate": 8.047619047619048e-05,
+      "loss": 0.8802,
+      "step": 170
+    },
+    {
+      "epoch": 0.258203335126412,
+      "grad_norm": 1.2050995451812405,
+      "learning_rate": 8.523809523809524e-05,
+      "loss": 0.8692,
+      "step": 180
+    },
+    {
+      "epoch": 0.2725479648556572,
+      "grad_norm": 0.9483149209977663,
+      "learning_rate": 9e-05,
+      "loss": 0.8675,
+      "step": 190
+    },
+    {
+      "epoch": 0.2868925945849023,
+      "grad_norm": 0.9047494721372505,
+      "learning_rate": 9.476190476190476e-05,
+      "loss": 0.8651,
+      "step": 200
+    },
+    {
+      "epoch": 0.3012372243141474,
+      "grad_norm": 0.9614336061705705,
+      "learning_rate": 9.952380952380953e-05,
+      "loss": 0.8743,
+      "step": 210
+    },
+    {
+      "epoch": 0.3155818540433925,
+      "grad_norm": 0.840798357905234,
+      "learning_rate": 9.999436939807164e-05,
+      "loss": 0.8831,
+      "step": 220
+    },
+    {
+      "epoch": 0.3299264837726376,
+      "grad_norm": 0.894805005888125,
+      "learning_rate": 9.99749072170404e-05,
+      "loss": 0.8753,
+      "step": 230
+    },
+    {
+      "epoch": 0.3442711135018827,
+      "grad_norm": 0.9621522988496558,
+      "learning_rate": 9.994154935353517e-05,
+      "loss": 0.8553,
+      "step": 240
+    },
+    {
+      "epoch": 0.3586157432311278,
+      "grad_norm": 0.8338221919665476,
+      "learning_rate": 9.98943050828164e-05,
+      "loss": 0.8577,
+      "step": 250
+    },
+    {
+      "epoch": 0.372960372960373,
+      "grad_norm": 0.8401540225438021,
+      "learning_rate": 9.983318754130435e-05,
+      "loss": 0.842,
+      "step": 260
+    },
+    {
+      "epoch": 0.3873050026896181,
+      "grad_norm": 0.7967631358112257,
+      "learning_rate": 9.975821372292653e-05,
+      "loss": 0.8346,
+      "step": 270
+    },
+    {
+      "epoch": 0.4016496324188632,
+      "grad_norm": 0.7572726108984663,
+      "learning_rate": 9.966940447439245e-05,
+      "loss": 0.8272,
+      "step": 280
+    },
+    {
+      "epoch": 0.4159942621481083,
+      "grad_norm": 0.7862046452006615,
+      "learning_rate": 9.956678448939718e-05,
+      "loss": 0.8161,
+      "step": 290
+    },
+    {
+      "epoch": 0.4303388918773534,
+      "grad_norm": 0.8007930832524255,
+      "learning_rate": 9.945038230175509e-05,
+      "loss": 0.8263,
+      "step": 300
+    },
+    {
+      "epoch": 0.4446835216065985,
+      "grad_norm": 0.6882798627741967,
+      "learning_rate": 9.932023027746602e-05,
+      "loss": 0.8119,
+      "step": 310
+    },
+    {
+      "epoch": 0.4590281513358436,
+      "grad_norm": 0.7191586339334445,
+      "learning_rate": 9.917636460571578e-05,
+      "loss": 0.8195,
+      "step": 320
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 0.6479226154771014,
+      "learning_rate": 9.901882528881363e-05,
+      "loss": 0.8152,
+      "step": 330
+    },
+    {
+      "epoch": 0.4877174107943339,
+      "grad_norm": 0.7520756414640943,
+      "learning_rate": 9.884765613106948e-05,
+      "loss": 0.8056,
+      "step": 340
+    },
+    {
+      "epoch": 0.502062040523579,
+      "grad_norm": 0.7496882676872738,
+      "learning_rate": 9.866290472661406e-05,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.516406670252824,
+      "grad_norm": 0.8849980877887388,
+      "learning_rate": 9.846462244616508e-05,
+      "loss": 0.8139,
+      "step": 360
+    },
+    {
+      "epoch": 0.5307512999820692,
+      "grad_norm": 0.689970676364689,
+      "learning_rate": 9.825286442274357e-05,
+      "loss": 0.8052,
+      "step": 370
+    },
+    {
+      "epoch": 0.5450959297113144,
+      "grad_norm": 0.7192552702117557,
+      "learning_rate": 9.802768953634388e-05,
+      "loss": 0.7918,
+      "step": 380
+    },
+    {
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.6975024662772501,
+      "learning_rate": 9.778916039756193e-05,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.5737851891698046,
+      "grad_norm": 0.6553934247634706,
+      "learning_rate": 9.753734333018616e-05,
+      "loss": 0.776,
+      "step": 400
+    },
+    {
+      "epoch": 0.5881298188990497,
+      "grad_norm": 0.757809076489788,
+      "learning_rate": 9.727230835275598e-05,
+      "loss": 0.7811,
+      "step": 410
+    },
+    {
+      "epoch": 0.6024744486282948,
+      "grad_norm": 0.7082602077432336,
+      "learning_rate": 9.699412915909284e-05,
+      "loss": 0.7819,
+      "step": 420
+    },
+    {
+      "epoch": 0.6168190783575399,
+      "grad_norm": 0.6348735880274488,
+      "learning_rate": 9.670288309780953e-05,
+      "loss": 0.7679,
+      "step": 430
+    },
+    {
+      "epoch": 0.631163708086785,
+      "grad_norm": 0.6405240862226912,
+      "learning_rate": 9.639865115080304e-05,
+      "loss": 0.779,
+      "step": 440
+    },
+    {
+      "epoch": 0.6455083378160301,
+      "grad_norm": 0.6634767779062684,
+      "learning_rate": 9.608151791073737e-05,
+      "loss": 0.7739,
+      "step": 450
+    },
+    {
+      "epoch": 0.6598529675452752,
+      "grad_norm": 0.5759274474197833,
+      "learning_rate": 9.575157155752222e-05,
+      "loss": 0.7643,
+      "step": 460
+    },
+    {
+      "epoch": 0.6741975972745203,
+      "grad_norm": 0.6640199963749864,
+      "learning_rate": 9.54089038337943e-05,
+      "loss": 0.7556,
+      "step": 470
+    },
+    {
+      "epoch": 0.6885422270037654,
+      "grad_norm": 0.6203004765144989,
+      "learning_rate": 9.5053610019408e-05,
+      "loss": 0.7596,
+      "step": 480
+    },
+    {
+      "epoch": 0.7028868567330105,
+      "grad_norm": 0.5775087991410168,
+      "learning_rate": 9.468578890494256e-05,
+      "loss": 0.7534,
+      "step": 490
+    },
+    {
+      "epoch": 0.7172314864622557,
+      "grad_norm": 0.6714966253079345,
+      "learning_rate": 9.430554276423292e-05,
+      "loss": 0.7552,
+      "step": 500
+    },
+    {
+      "epoch": 0.7315761161915008,
+      "grad_norm": 0.5888288333456809,
+      "learning_rate": 9.391297732593229e-05,
+      "loss": 0.7526,
+      "step": 510
+    },
+    {
+      "epoch": 0.745920745920746,
+      "grad_norm": 0.6259226612543665,
+      "learning_rate": 9.350820174411386e-05,
+      "loss": 0.7537,
+      "step": 520
+    },
+    {
+      "epoch": 0.7602653756499911,
+      "grad_norm": 0.5499968625723676,
+      "learning_rate": 9.309132856792023e-05,
+      "loss": 0.7499,
+      "step": 530
+    },
+    {
+      "epoch": 0.7746100053792362,
+      "grad_norm": 0.6500285934875327,
+      "learning_rate": 9.266247371026873e-05,
+      "loss": 0.7447,
+      "step": 540
+    },
+    {
+      "epoch": 0.7889546351084813,
+      "grad_norm": 0.5672171674827838,
+      "learning_rate": 9.222175641562143e-05,
+      "loss": 0.7496,
+      "step": 550
+    },
+    {
+      "epoch": 0.8032992648377264,
+      "grad_norm": 0.6465733807975256,
+      "learning_rate": 9.176929922682891e-05,
+      "loss": 0.74,
+      "step": 560
+    },
+    {
+      "epoch": 0.8176438945669715,
+      "grad_norm": 0.6101304041389433,
+      "learning_rate": 9.130522795105676e-05,
+      "loss": 0.7411,
+      "step": 570
+    },
+    {
+      "epoch": 0.8319885242962166,
+      "grad_norm": 0.5489063036723607,
+      "learning_rate": 9.082967162480459e-05,
+      "loss": 0.7323,
+      "step": 580
+    },
+    {
+      "epoch": 0.8463331540254617,
+      "grad_norm": 0.5516558559909698,
+      "learning_rate": 9.034276247802688e-05,
+      "loss": 0.7231,
+      "step": 590
+    },
+    {
+      "epoch": 0.8606777837547068,
+      "grad_norm": 0.6477118047968917,
+      "learning_rate": 8.984463589736614e-05,
+      "loss": 0.7288,
+      "step": 600
+    },
+    {
+      "epoch": 0.8750224134839519,
+      "grad_norm": 0.5962486006428408,
+      "learning_rate": 8.933543038850816e-05,
+      "loss": 0.732,
+      "step": 610
+    },
+    {
+      "epoch": 0.889367043213197,
+      "grad_norm": 0.5713715183887016,
+      "learning_rate": 8.881528753767007e-05,
+      "loss": 0.728,
+      "step": 620
+    },
+    {
+      "epoch": 0.9037116729424421,
+      "grad_norm": 0.6301745705273146,
+      "learning_rate": 8.82843519722319e-05,
+      "loss": 0.7263,
+      "step": 630
+    },
+    {
+      "epoch": 0.9180563026716873,
+      "grad_norm": 0.5819941044165688,
+      "learning_rate": 8.774277132052237e-05,
+      "loss": 0.7189,
+      "step": 640
+    },
+    {
+      "epoch": 0.9324009324009324,
+      "grad_norm": 0.5336149445366645,
+      "learning_rate": 8.719069617077046e-05,
+      "loss": 0.7254,
+      "step": 650
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 0.6083401813961216,
+      "learning_rate": 8.662828002923378e-05,
+      "loss": 0.7218,
+      "step": 660
+    },
+    {
+      "epoch": 0.9610901918594227,
+      "grad_norm": 0.5371262960983777,
+      "learning_rate": 8.605567927751576e-05,
+      "loss": 0.719,
+      "step": 670
+    },
+    {
+      "epoch": 0.9754348215886678,
+      "grad_norm": 0.5551868136565808,
+      "learning_rate": 8.547305312908318e-05,
+      "loss": 0.7089,
+      "step": 680
+    },
+    {
+      "epoch": 0.9897794513179129,
+      "grad_norm": 0.5899796664828114,
+      "learning_rate": 8.48805635849964e-05,
+      "loss": 0.7075,
+      "step": 690
+    },
+    {
+      "epoch": 1.002868925945849,
+      "grad_norm": 0.608174630463498,
+      "learning_rate": 8.427837538886437e-05,
+      "loss": 0.6894,
+      "step": 700
+    },
+    {
+      "epoch": 1.017213555675094,
+      "grad_norm": 0.6116990279567732,
+      "learning_rate": 8.366665598103727e-05,
+      "loss": 0.5865,
+      "step": 710
+    },
+    {
+      "epoch": 1.0315581854043392,
+      "grad_norm": 0.5768126568975168,
+      "learning_rate": 8.304557545204908e-05,
+      "loss": 0.5931,
+      "step": 720
+    },
+    {
+      "epoch": 1.0459028151335843,
+      "grad_norm": 0.5727241793491287,
+      "learning_rate": 8.241530649532339e-05,
+      "loss": 0.5859,
+      "step": 730
+    },
+    {
+      "epoch": 1.0602474448628294,
+      "grad_norm": 0.5834066080830065,
+      "learning_rate": 8.177602435915546e-05,
+      "loss": 0.5833,
+      "step": 740
+    },
+    {
+      "epoch": 1.0745920745920745,
+      "grad_norm": 0.6168394884857555,
+      "learning_rate": 8.11279067979839e-05,
+      "loss": 0.5805,
+      "step": 750
+    },
+    {
+      "epoch": 1.0889367043213196,
+      "grad_norm": 0.4885078172344663,
+      "learning_rate": 8.04711340229654e-05,
+      "loss": 0.5733,
+      "step": 760
+    },
+    {
+      "epoch": 1.1032813340505647,
+      "grad_norm": 0.5289947493535304,
+      "learning_rate": 7.980588865186649e-05,
+      "loss": 0.5812,
+      "step": 770
+    },
+    {
+      "epoch": 1.11762596377981,
+      "grad_norm": 0.5672904537751536,
+      "learning_rate": 7.913235565828613e-05,
+      "loss": 0.5811,
+      "step": 780
+    },
+    {
+      "epoch": 1.1319705935090552,
+      "grad_norm": 0.6107186114378813,
+      "learning_rate": 7.845072232022311e-05,
+      "loss": 0.5755,
+      "step": 790
+    },
+    {
+      "epoch": 1.1463152232383003,
+      "grad_norm": 0.6696900109358123,
+      "learning_rate": 7.776117816800288e-05,
+      "loss": 0.5916,
+      "step": 800
+    },
+    {
+      "epoch": 1.1606598529675454,
+      "grad_norm": 0.5412095989289454,
+      "learning_rate": 7.706391493157805e-05,
+      "loss": 0.5822,
+      "step": 810
+    },
+    {
+      "epoch": 1.1750044826967905,
+      "grad_norm": 0.5408330429359739,
+      "learning_rate": 7.635912648721718e-05,
+      "loss": 0.5811,
+      "step": 820
+    },
+    {
+      "epoch": 1.1893491124260356,
+      "grad_norm": 0.5952577265784902,
+      "learning_rate": 7.564700880359696e-05,
+      "loss": 0.5799,
+      "step": 830
+    },
+    {
+      "epoch": 1.2036937421552807,
+      "grad_norm": 0.5026109808475954,
+      "learning_rate": 7.492775988731243e-05,
+      "loss": 0.5673,
+      "step": 840
+    },
+    {
+      "epoch": 1.2180383718845258,
+      "grad_norm": 0.5302543029902266,
+      "learning_rate": 7.420157972782063e-05,
+      "loss": 0.5754,
+      "step": 850
+    },
+    {
+      "epoch": 1.232383001613771,
+      "grad_norm": 0.5532266667153597,
+      "learning_rate": 7.346867024183291e-05,
+      "loss": 0.579,
+      "step": 860
+    },
+    {
+      "epoch": 1.246727631343016,
+      "grad_norm": 0.5669382050811871,
+      "learning_rate": 7.272923521717133e-05,
+      "loss": 0.5756,
+      "step": 870
+    },
+    {
+      "epoch": 1.2610722610722611,
+      "grad_norm": 0.5338735116713776,
+      "learning_rate": 7.198348025610481e-05,
+      "loss": 0.5769,
+      "step": 880
+    },
+    {
+      "epoch": 1.2754168908015062,
+      "grad_norm": 0.5863122040109188,
+      "learning_rate": 7.12316127181808e-05,
+      "loss": 0.5685,
+      "step": 890
+    },
+    {
+      "epoch": 1.2897615205307513,
+      "grad_norm": 0.5541827820189409,
+      "learning_rate": 7.047384166256815e-05,
+      "loss": 0.5801,
+      "step": 900
+    },
+    {
+      "epoch": 1.3041061502599964,
+      "grad_norm": 0.5753955062923616,
+      "learning_rate": 6.971037778992775e-05,
+      "loss": 0.5795,
+      "step": 910
+    },
+    {
+      "epoch": 1.3184507799892415,
+      "grad_norm": 0.47433414173616173,
+      "learning_rate": 6.894143338382639e-05,
+      "loss": 0.5768,
+      "step": 920
+    },
+    {
+      "epoch": 1.3327954097184866,
+      "grad_norm": 0.5274791181928579,
+      "learning_rate": 6.81672222517107e-05,
+      "loss": 0.578,
+      "step": 930
+    },
+    {
+      "epoch": 1.3471400394477318,
+      "grad_norm": 0.5774970902851654,
+      "learning_rate": 6.73879596654573e-05,
+      "loss": 0.5682,
+      "step": 940
+    },
+    {
+      "epoch": 1.3614846691769769,
+      "grad_norm": 0.5662099451295628,
+      "learning_rate": 6.660386230151571e-05,
+      "loss": 0.5735,
+      "step": 950
+    },
+    {
+      "epoch": 1.375829298906222,
+      "grad_norm": 0.5574084243877258,
+      "learning_rate": 6.581514818066088e-05,
+      "loss": 0.5739,
+      "step": 960
+    },
+    {
+      "epoch": 1.390173928635467,
+      "grad_norm": 0.539589642853108,
+      "learning_rate": 6.502203660737169e-05,
+      "loss": 0.5688,
+      "step": 970
+    },
+    {
+      "epoch": 1.4045185583647122,
+      "grad_norm": 0.49293926542133193,
+      "learning_rate": 6.422474810885278e-05,
+      "loss": 0.5669,
+      "step": 980
+    },
+    {
+      "epoch": 1.4188631880939573,
+      "grad_norm": 0.49620916916034896,
+      "learning_rate": 6.342350437371614e-05,
+      "loss": 0.5702,
+      "step": 990
+    },
+    {
+      "epoch": 1.4332078178232024,
+      "grad_norm": 0.5152950617397968,
+      "learning_rate": 6.26185281903399e-05,
+      "loss": 0.5685,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4475524475524475,
+      "grad_norm": 0.545911912027696,
+      "learning_rate": 6.181004338492141e-05,
+      "loss": 0.5651,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4618970772816926,
+      "grad_norm": 0.5074263813146201,
+      "learning_rate": 6.09982747592415e-05,
+      "loss": 0.5615,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4762417070109377,
+      "grad_norm": 0.5094909684862107,
+      "learning_rate": 6.018344802815778e-05,
+      "loss": 0.5679,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4905863367401828,
+      "grad_norm": 0.5103259058296251,
+      "learning_rate": 5.936578975684378e-05,
+      "loss": 0.5701,
+      "step": 1040
+    },
+    {
+      "epoch": 1.504930966469428,
+      "grad_norm": 0.5278709818430807,
+      "learning_rate": 5.854552729779184e-05,
+      "loss": 0.5627,
+      "step": 1050
+    },
+    {
+      "epoch": 1.519275596198673,
+      "grad_norm": 0.510686482301255,
+      "learning_rate": 5.772288872759702e-05,
+      "loss": 0.5625,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5336202259279181,
+      "grad_norm": 0.5278526048784437,
+      "learning_rate": 5.6898102783539665e-05,
+      "loss": 0.5606,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5479648556571632,
+      "grad_norm": 0.5559268236737518,
+      "learning_rate": 5.607139879998427e-05,
+      "loss": 0.5595,
+      "step": 1080
+    },
+    {
+      "epoch": 1.5623094853864083,
+      "grad_norm": 0.5583305948616533,
+      "learning_rate": 5.524300664461235e-05,
+      "loss": 0.5575,
+      "step": 1090
+    },
+    {
+      "epoch": 1.5766541151156535,
+      "grad_norm": 0.5186185461448056,
+      "learning_rate": 5.441315665450697e-05,
+      "loss": 0.5589,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5909987448448986,
+      "grad_norm": 0.5168193702732372,
+      "learning_rate": 5.3582079572106794e-05,
+      "loss": 0.5534,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6053433745741437,
+      "grad_norm": 0.5037158486433893,
+      "learning_rate": 5.275000648104743e-05,
+      "loss": 0.5569,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6196880043033888,
+      "grad_norm": 0.49884254214328216,
+      "learning_rate": 5.191716874190785e-05,
+      "loss": 0.5564,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6340326340326339,
+      "grad_norm": 0.5071669705468655,
+      "learning_rate": 5.1083797927879896e-05,
+      "loss": 0.5552,
+      "step": 1140
+    },
+    {
+      "epoch": 1.648377263761879,
+      "grad_norm": 0.5410568223255828,
+      "learning_rate": 5.025012576037855e-05,
+      "loss": 0.564,
+      "step": 1150
+    },
+    {
+      "epoch": 1.6627218934911243,
+      "grad_norm": 0.4850296619715352,
+      "learning_rate": 4.9416384044611124e-05,
+      "loss": 0.5579,
+      "step": 1160
+    },
+    {
+      "epoch": 1.6770665232203694,
+      "grad_norm": 0.5039355867374112,
+      "learning_rate": 4.858280460512302e-05,
+      "loss": 0.5551,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6914111529496145,
+      "grad_norm": 0.5354526153870778,
+      "learning_rate": 4.7749619221338227e-05,
+      "loss": 0.5553,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7057557826788596,
+      "grad_norm": 0.5149848285267117,
+      "learning_rate": 4.691705956311225e-05,
+      "loss": 0.554,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7201004124081047,
+      "grad_norm": 0.5076867052953596,
+      "learning_rate": 4.608535712631566e-05,
+      "loss": 0.553,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7344450421373498,
+      "grad_norm": 0.5245034600250137,
+      "learning_rate": 4.525474316846581e-05,
+      "loss": 0.5455,
+      "step": 1210
+    },
+    {
+      "epoch": 1.748789671866595,
+      "grad_norm": 0.5044035057693634,
+      "learning_rate": 4.4425448644425066e-05,
+      "loss": 0.5487,
+      "step": 1220
+    },
+    {
+      "epoch": 1.76313430159584,
+      "grad_norm": 0.5182301310051464,
+      "learning_rate": 4.359770414218296e-05,
+      "loss": 0.5401,
+      "step": 1230
+    },
+    {
+      "epoch": 1.7774789313250852,
+      "grad_norm": 0.5066048824304953,
+      "learning_rate": 4.2771739818740565e-05,
+      "loss": 0.5496,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7918235610543303,
+      "grad_norm": 0.5337687629976401,
+      "learning_rate": 4.194778533611451e-05,
+      "loss": 0.5413,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8061681907835754,
+      "grad_norm": 0.5207289329535878,
+      "learning_rate": 4.112606979747881e-05,
+      "loss": 0.544,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8205128205128205,
+      "grad_norm": 0.5450234045888507,
+      "learning_rate": 4.030682168346192e-05,
+      "loss": 0.5358,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8348574502420656,
+      "grad_norm": 0.48504143892984203,
+      "learning_rate": 3.949026878861704e-05,
+      "loss": 0.539,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8492020799713107,
+      "grad_norm": 0.49111142317889844,
+      "learning_rate": 3.867663815808303e-05,
+      "loss": 0.5389,
+      "step": 1290
+    },
+    {
+      "epoch": 1.8635467097005558,
+      "grad_norm": 0.5008380643048362,
+      "learning_rate": 3.78661560244539e-05,
+      "loss": 0.5363,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8778913394298011,
+      "grad_norm": 0.4952709952315973,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5319,
+      "step": 1310
+    },
+    {
+      "epoch": 1.8922359691590462,
+      "grad_norm": 0.5164716516662802,
+      "learning_rate": 3.6255537738376706e-05,
+      "loss": 0.5402,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9065805988882913,
+      "grad_norm": 0.5240016137645628,
+      "learning_rate": 3.545584942348426e-05,
+      "loss": 0.5309,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9209252286175365,
+      "grad_norm": 0.5058856022275582,
+      "learning_rate": 3.466020515608525e-05,
+      "loss": 0.5298,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9352698583467816,
+      "grad_norm": 0.5019184399441088,
+      "learning_rate": 3.386882616760794e-05,
+      "loss": 0.5319,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9496144880760267,
+      "grad_norm": 0.471920743317965,
+      "learning_rate": 3.30819325035062e-05,
+      "loss": 0.5287,
+      "step": 1360
+    },
+    {
+      "epoch": 1.9639591178052718,
+      "grad_norm": 0.5094525188470136,
+      "learning_rate": 3.229974296207513e-05,
+      "loss": 0.5385,
+      "step": 1370
+    },
+    {
+      "epoch": 1.9783037475345169,
+      "grad_norm": 0.5606826371060244,
+      "learning_rate": 3.152247503361353e-05,
+      "loss": 0.527,
+      "step": 1380
+    },
+    {
+      "epoch": 1.992648377263762,
+      "grad_norm": 0.5085670056810321,
+      "learning_rate": 3.075034483994997e-05,
+      "loss": 0.5257,
+      "step": 1390
+    },
+    {
+      "epoch": 2.005737851891698,
+      "grad_norm": 0.5719992437170487,
+      "learning_rate": 2.998356707434947e-05,
+      "loss": 0.4623,
+      "step": 1400
+    },
+    {
+      "epoch": 2.020082481620943,
+      "grad_norm": 0.5387964274909228,
+      "learning_rate": 2.9222354941817375e-05,
+      "loss": 0.3606,
+      "step": 1410
+    },
+    {
+      "epoch": 2.034427111350188,
+      "grad_norm": 0.5698349863645911,
+      "learning_rate": 2.846692009981693e-05,
+      "loss": 0.3527,
+      "step": 1420
+    },
+    {
+      "epoch": 2.0487717410794333,
+      "grad_norm": 0.5324199413342471,
+      "learning_rate": 2.771747259941734e-05,
+      "loss": 0.3462,
+      "step": 1430
+    },
+    {
+      "epoch": 2.0631163708086784,
+      "grad_norm": 0.53215786873291,
+      "learning_rate": 2.6974220826888374e-05,
+      "loss": 0.342,
+      "step": 1440
+    },
+    {
+      "epoch": 2.0774610005379235,
+      "grad_norm": 0.5110033203467198,
+      "learning_rate": 2.623737144575787e-05,
+      "loss": 0.3462,
+      "step": 1450
+    },
+    {
+      "epoch": 2.0918056302671686,
+      "grad_norm": 0.5246624681955846,
+      "learning_rate": 2.5507129339348335e-05,
+      "loss": 0.3487,
+      "step": 1460
+    },
+    {
+      "epoch": 2.1061502599964137,
+      "grad_norm": 0.5070575905086573,
+      "learning_rate": 2.478369755380839e-05,
+      "loss": 0.3465,
+      "step": 1470
+    },
+    {
+      "epoch": 2.120494889725659,
+      "grad_norm": 0.5132555087524301,
+      "learning_rate": 2.406727724165524e-05,
+      "loss": 0.3451,
+      "step": 1480
+    },
+    {
+      "epoch": 2.134839519454904,
+      "grad_norm": 0.5143913782142077,
+      "learning_rate": 2.3358067605843537e-05,
+      "loss": 0.3442,
+      "step": 1490
+    },
+    {
+      "epoch": 2.149184149184149,
+      "grad_norm": 0.4894675520933593,
+      "learning_rate": 2.2656265844376367e-05,
+      "loss": 0.3449,
+      "step": 1500
+    },
+    {
+      "epoch": 2.163528778913394,
+      "grad_norm": 0.5118938379622366,
+      "learning_rate": 2.1962067095473648e-05,
+      "loss": 0.3443,
+      "step": 1510
+    },
+    {
+      "epoch": 2.1778734086426392,
+      "grad_norm": 0.5264199925745078,
+      "learning_rate": 2.127566438331345e-05,
+      "loss": 0.3443,
+      "step": 1520
+    },
+    {
+      "epoch": 2.1922180383718843,
+      "grad_norm": 0.5517034745554297,
+      "learning_rate": 2.059724856436092e-05,
+      "loss": 0.34,
+      "step": 1530
+    },
+    {
+      "epoch": 2.2065626681011294,
+      "grad_norm": 0.5153912300862288,
+      "learning_rate": 1.992700827430007e-05,
+      "loss": 0.3447,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2209072978303745,
+      "grad_norm": 0.49999210085621454,
+      "learning_rate": 1.9265129875582954e-05,
+      "loss": 0.3402,
+      "step": 1550
+    },
+    {
+      "epoch": 2.23525192755962,
+      "grad_norm": 0.5117332103404209,
+      "learning_rate": 1.8611797405611097e-05,
+      "loss": 0.3434,
+      "step": 1560
+    },
+    {
+      "epoch": 2.249596557288865,
+      "grad_norm": 0.5334345620530477,
+      "learning_rate": 1.7967192525563254e-05,
+      "loss": 0.3429,
+      "step": 1570
+    },
+    {
+      "epoch": 2.2639411870181103,
+      "grad_norm": 0.5052797787039551,
+      "learning_rate": 1.733149446988394e-05,
+      "loss": 0.3402,
+      "step": 1580
+    },
+    {
+      "epoch": 2.2782858167473554,
+      "grad_norm": 0.5115033156660913,
+      "learning_rate": 1.670487999644669e-05,
+      "loss": 0.3413,
+      "step": 1590
+    },
+    {
+      "epoch": 2.2926304464766005,
+      "grad_norm": 0.4961174768714891,
+      "learning_rate": 1.6087523337406024e-05,
+      "loss": 0.3407,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3069750762058456,
+      "grad_norm": 0.5181202897712733,
+      "learning_rate": 1.547959615075164e-05,
+      "loss": 0.3343,
+      "step": 1610
+    },
+    {
+      "epoch": 2.3213197059350907,
+      "grad_norm": 0.5076475142323975,
+      "learning_rate": 1.4881267472578325e-05,
+      "loss": 0.3415,
+      "step": 1620
+    },
+    {
+      "epoch": 2.335664335664336,
+      "grad_norm": 0.4921735423850851,
+      "learning_rate": 1.4292703670084916e-05,
+      "loss": 0.3392,
+      "step": 1630
+    },
+    {
+      "epoch": 2.350008965393581,
+      "grad_norm": 0.5151996030919073,
+      "learning_rate": 1.3714068395315427e-05,
+      "loss": 0.3349,
+      "step": 1640
+    },
+    {
+      "epoch": 2.364353595122826,
+      "grad_norm": 0.5104074354031792,
+      "learning_rate": 1.3145522539655041e-05,
+      "loss": 0.3354,
+      "step": 1650
+    },
+    {
+      "epoch": 2.378698224852071,
+      "grad_norm": 0.5380960601841327,
+      "learning_rate": 1.2587224189093755e-05,
+      "loss": 0.3302,
+      "step": 1660
+    },
+    {
+      "epoch": 2.3930428545813163,
+      "grad_norm": 0.5049847193289703,
+      "learning_rate": 1.2039328580270065e-05,
+      "loss": 0.3333,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4073874843105614,
+      "grad_norm": 0.5040716684214055,
+      "learning_rate": 1.150198805730689e-05,
+      "loss": 0.3329,
+      "step": 1680
+    },
+    {
+      "epoch": 2.4217321140398065,
+      "grad_norm": 0.5040857331959766,
+      "learning_rate": 1.0975352029451863e-05,
+      "loss": 0.3337,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4360767437690516,
+      "grad_norm": 0.5091871791617659,
+      "learning_rate": 1.0459566929533588e-05,
+      "loss": 0.3345,
+      "step": 1700
+    },
+    {
+      "epoch": 2.4504213734982967,
+      "grad_norm": 0.4986671760440932,
+      "learning_rate": 9.954776173245511e-06,
+      "loss": 0.3369,
+      "step": 1710
+    },
+    {
+      "epoch": 2.464766003227542,
+      "grad_norm": 0.5146311314437344,
+      "learning_rate": 9.461120119268713e-06,
+      "loss": 0.3338,
+      "step": 1720
+    },
+    {
+      "epoch": 2.479110632956787,
+      "grad_norm": 0.5052152754810867,
+      "learning_rate": 8.978736030244783e-06,
+      "loss": 0.331,
+      "step": 1730
+    },
+    {
+      "epoch": 2.493455262686032,
+      "grad_norm": 0.5060074098914322,
+      "learning_rate": 8.50775803460948e-06,
+      "loss": 0.3336,
+      "step": 1740
+    },
+    {
+      "epoch": 2.507799892415277,
+      "grad_norm": 0.5047637166351485,
+      "learning_rate": 8.048317089297875e-06,
+      "loss": 0.331,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5221445221445222,
+      "grad_norm": 0.5051085483525463,
+      "learning_rate": 7.600540943331347e-06,
+      "loss": 0.3316,
+      "step": 1760
+    },
+    {
+      "epoch": 2.5364891518737673,
+      "grad_norm": 0.5291232815833027,
+      "learning_rate": 7.164554102296617e-06,
+      "loss": 0.3322,
+      "step": 1770
+    },
+    {
+      "epoch": 2.5508337816030124,
+      "grad_norm": 0.4950112167812311,
+      "learning_rate": 6.740477793726529e-06,
+      "loss": 0.3302,
+      "step": 1780
+    },
+    {
+      "epoch": 2.5651784113322575,
+      "grad_norm": 0.5171790095780296,
+      "learning_rate": 6.32842993339236e-06,
+      "loss": 0.3278,
+      "step": 1790
+    },
+    {
+      "epoch": 2.5795230410615027,
+      "grad_norm": 0.5041803659831317,
+      "learning_rate": 5.928525092516934e-06,
+      "loss": 0.3334,
+      "step": 1800
+    },
+    {
+      "epoch": 2.5938676707907478,
+      "grad_norm": 0.5073754782012652,
+      "learning_rate": 5.540874465917778e-06,
+      "loss": 0.3325,
+      "step": 1810
+    },
+    {
+      "epoch": 2.608212300519993,
+      "grad_norm": 0.48715355421051987,
+      "learning_rate": 5.165585841089021e-06,
+      "loss": 0.3246,
+      "step": 1820
+    },
+    {
+      "epoch": 2.622556930249238,
+      "grad_norm": 0.5162975920861064,
+      "learning_rate": 4.8027635682307445e-06,
+      "loss": 0.325,
+      "step": 1830
+    },
+    {
+      "epoch": 2.636901559978483,
+      "grad_norm": 0.5030085273093482,
+      "learning_rate": 4.45250853123404e-06,
+      "loss": 0.3267,
+      "step": 1840
+    },
+    {
+      "epoch": 2.651246189707728,
+      "grad_norm": 0.5261872357667398,
+      "learning_rate": 4.1149181196299905e-06,
+      "loss": 0.3277,
+      "step": 1850
+    },
+    {
+      "epoch": 2.6655908194369733,
+      "grad_norm": 0.49678770417028423,
+      "learning_rate": 3.7900862015101457e-06,
+      "loss": 0.3285,
+      "step": 1860
+    },
+    {
+      "epoch": 2.6799354491662184,
+      "grad_norm": 0.4889164865698146,
+      "learning_rate": 3.4781030974262108e-06,
+      "loss": 0.3268,
+      "step": 1870
+    },
+    {
+      "epoch": 2.6942800788954635,
+      "grad_norm": 0.4884408260663131,
+      "learning_rate": 3.1790555552761615e-06,
+      "loss": 0.3246,
+      "step": 1880
+    },
+    {
+      "epoch": 2.7086247086247086,
+      "grad_norm": 0.49292610830996564,
+      "learning_rate": 2.8930267261836395e-06,
+      "loss": 0.3231,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7229693383539537,
+      "grad_norm": 0.4890311152459734,
+      "learning_rate": 2.6200961413776094e-06,
+      "loss": 0.324,
+      "step": 1900
+    },
+    {
+      "epoch": 2.737313968083199,
+      "grad_norm": 0.5165429385071639,
+      "learning_rate": 2.3603396900783724e-06,
+      "loss": 0.3251,
+      "step": 1910
+    },
+    {
+      "epoch": 2.751658597812444,
+      "grad_norm": 0.5024981727502739,
+      "learning_rate": 2.113829598396383e-06,
+      "loss": 0.322,
+      "step": 1920
+    },
+    {
+      "epoch": 2.766003227541689,
+      "grad_norm": 0.49038298209467507,
+      "learning_rate": 1.8806344092494932e-06,
+      "loss": 0.3248,
+      "step": 1930
+    },
+    {
+      "epoch": 2.780347857270934,
+      "grad_norm": 0.4917027026533285,
+      "learning_rate": 1.6608189633044113e-06,
+      "loss": 0.325,
+      "step": 1940
+    },
+    {
+      "epoch": 2.7946924870001792,
+      "grad_norm": 0.4869252686371276,
+      "learning_rate": 1.4544443809475561e-06,
+      "loss": 0.3247,
+      "step": 1950
+    },
+    {
+      "epoch": 2.8090371167294244,
+      "grad_norm": 0.48253239623178734,
+      "learning_rate": 1.2615680452903067e-06,
+      "loss": 0.3234,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8233817464586695,
+      "grad_norm": 0.5096600620224961,
+      "learning_rate": 1.082243586213455e-06,
+      "loss": 0.3219,
+      "step": 1970
+    },
+    {
+      "epoch": 2.8377263761879146,
+      "grad_norm": 0.48655701646749633,
+      "learning_rate": 9.165208654552671e-07,
+      "loss": 0.321,
+      "step": 1980
+    },
+    {
+      "epoch": 2.8520710059171597,
+      "grad_norm": 0.47440137878879957,
+      "learning_rate": 7.6444596274724e-07,
+      "loss": 0.3229,
+      "step": 1990
+    },
+    {
+      "epoch": 2.866415635646405,
+      "grad_norm": 0.5034996226878241,
+      "learning_rate": 6.260611630015067e-07,
+      "loss": 0.3221,
+      "step": 2000
+    },
+    {
+      "epoch": 2.88076026537565,
+      "grad_norm": 0.47683170425958754,
+      "learning_rate": 5.01404944553363e-07,
+      "loss": 0.3219,
+      "step": 2010
+    },
+    {
+      "epoch": 2.895104895104895,
+      "grad_norm": 0.4909218835510976,
+      "learning_rate": 3.9051196846225935e-07,
+      "loss": 0.3251,
+      "step": 2020
+    },
+    {
+      "epoch": 2.90944952483414,
+      "grad_norm": 0.48456217220790176,
+      "learning_rate": 2.9341306887417653e-07,
+      "loss": 0.3213,
+      "step": 2030
+    },
+    {
+      "epoch": 2.923794154563385,
+      "grad_norm": 0.4779578566731188,
+      "learning_rate": 2.101352444480842e-07,
+      "loss": 0.3241,
+      "step": 2040
+    },
+    {
+      "epoch": 2.9381387842926303,
+      "grad_norm": 0.49966345259743034,
+      "learning_rate": 1.4070165084889008e-07,
+      "loss": 0.3199,
+      "step": 2050
+    },
+    {
+      "epoch": 2.9524834140218754,
+      "grad_norm": 0.4754785997240394,
+      "learning_rate": 8.513159430892925e-08,
+      "loss": 0.3225,
+      "step": 2060
+    },
+    {
+      "epoch": 2.9668280437511205,
+      "grad_norm": 0.4903628137644153,
+      "learning_rate": 4.344052625981365e-08,
+      "loss": 0.3219,
+      "step": 2070
+    },
+    {
+      "epoch": 2.9811726734803656,
+      "grad_norm": 0.4992880216120249,
+      "learning_rate": 1.5640039036085575e-08,
+      "loss": 0.3187,
+      "step": 2080
+    },
+    {
+      "epoch": 2.9955173032096107,
+      "grad_norm": 0.4963785468111048,
+      "learning_rate": 1.7378626519626296e-09,
+      "loss": 0.3238,
+      "step": 2090
+    },
+    {
+      "epoch": 3.0,
+      "step": 2094,
+      "total_flos": 306663055425536.0,
+      "train_loss": 0.5762376924754328,
+      "train_runtime": 90627.2697,
+      "train_samples_per_second": 1.477,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 306663055425536.0,
+  "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 sha256:7af00fb74678a8b03b41aaf1f484fcf497e6376602b84c4175eb9175ebb87fe5
+size 7953