Add files using upload-large-folder tool

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 web_rl_3b/checkpoint-1065/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 web_rl_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 web_rl_7b_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,72 @@
----
-license: mit
----
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: agent_trek
+  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. -->
+
+# agent_trek
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct) on the agent_trek dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2893
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- 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: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3906        | 0.1352 | 200  | 0.4129          |
+| 0.3823        | 0.2704 | 400  | 0.3794          |
+| 0.3507        | 0.4056 | 600  | 0.3506          |
+| 0.3065        | 0.5408 | 800  | 0.3299          |
+| 0.3042        | 0.6760 | 1000 | 0.3088          |
+| 0.2977        | 0.8112 | 1200 | 0.2946          |
+| 0.2908        | 0.9464 | 1400 | 0.2895          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

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 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.2892742156982422,
+    "eval_runtime": 1270.027,
+    "eval_samples_per_second": 4.142,
+    "eval_steps_per_second": 0.518,
+    "total_flos": 760407761879040.0,
+    "train_loss": 0.35166695085731714,
+    "train_runtime": 62991.4895,
+    "train_samples_per_second": 0.751,
+    "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 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.2892742156982422,
+    "eval_runtime": 1270.027,
+    "eval_samples_per_second": 4.142,
+    "eval_steps_per_second": 0.518
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26cceaf01aeeaed0e84622ab54de4e0bf8cd61a93fc6686f1c4bda52b35108b1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9bde5300bbfdbcaf3442b90008fbf915d857eb9ee9bafe485d872f3c93bb00
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c8c6b4f5bf865e31e913fe53348ff9a3bc2328963cc1ff5d5138a192cd48ea
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3460f04c0392dc0037e0c9eafbc350a85bb05e75120855d8097ffb6f7168b1e
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/Dec03_00-15-48_hgx007/events.out.tfevents.1764694143.hgx007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93f8aba116aa3b64389af2ffd999aedce18eeff1bda33c68172b64476207de0
+size 6296

runs/Dec03_15-28-38_hgx007/events.out.tfevents.1764749579.hgx007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b6b1d060a7ceb3b9635fc7a09d2ac50ea10489a2e376051e1ae4ec672f515d
+size 39520

runs/Dec03_15-28-38_hgx007/events.out.tfevents.1764813875.hgx007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bbd8b09837234b1a1cb50ffb22b1caccfc98b30635dd515b73c9c9ff4e0b6b
+size 311

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": 1.0,
+    "total_flos": 760407761879040.0,
+    "train_loss": 0.35166695085731714,
+    "train_runtime": 62991.4895,
+    "train_samples_per_second": 0.751,
+    "train_steps_per_second": 0.023
+}

trainer_log.jsonl

@@ -0,0 +1,156 @@
+{"current_steps": 10, "total_steps": 1480, "loss": 1.028, "lr": 6.081081081081082e-07, "epoch": 0.006760182524928173, "percentage": 0.68, "elapsed_time": "0:08:40", "remaining_time": "21:15:37"}
+{"current_steps": 20, "total_steps": 1480, "loss": 0.8412, "lr": 1.2837837837837838e-06, "epoch": 0.013520365049856346, "percentage": 1.35, "elapsed_time": "0:15:17", "remaining_time": "18:36:32"}
+{"current_steps": 30, "total_steps": 1480, "loss": 0.6928, "lr": 1.9594594594594595e-06, "epoch": 0.020280547574784518, "percentage": 2.03, "elapsed_time": "0:21:01", "remaining_time": "16:56:21"}
+{"current_steps": 40, "total_steps": 1480, "loss": 0.5823, "lr": 2.6351351351351353e-06, "epoch": 0.027040730099712692, "percentage": 2.7, "elapsed_time": "0:26:59", "remaining_time": "16:11:33"}
+{"current_steps": 50, "total_steps": 1480, "loss": 0.5195, "lr": 3.310810810810811e-06, "epoch": 0.03380091262464086, "percentage": 3.38, "elapsed_time": "0:32:50", "remaining_time": "15:39:19"}
+{"current_steps": 60, "total_steps": 1480, "loss": 0.4697, "lr": 3.986486486486487e-06, "epoch": 0.040561095149569036, "percentage": 4.05, "elapsed_time": "0:39:01", "remaining_time": "15:23:38"}
+{"current_steps": 70, "total_steps": 1480, "loss": 0.4567, "lr": 4.6621621621621625e-06, "epoch": 0.04732127767449721, "percentage": 4.73, "elapsed_time": "0:44:43", "remaining_time": "15:00:50"}
+{"current_steps": 80, "total_steps": 1480, "loss": 0.4675, "lr": 5.337837837837838e-06, "epoch": 0.054081460199425384, "percentage": 5.41, "elapsed_time": "0:50:40", "remaining_time": "14:46:41"}
+{"current_steps": 90, "total_steps": 1480, "loss": 0.4531, "lr": 6.013513513513514e-06, "epoch": 0.06084164272435356, "percentage": 6.08, "elapsed_time": "0:56:20", "remaining_time": "14:30:10"}
+{"current_steps": 100, "total_steps": 1480, "loss": 0.4368, "lr": 6.689189189189191e-06, "epoch": 0.06760182524928172, "percentage": 6.76, "elapsed_time": "1:02:03", "remaining_time": "14:16:24"}
+{"current_steps": 110, "total_steps": 1480, "loss": 0.4185, "lr": 7.3648648648648655e-06, "epoch": 0.0743620077742099, "percentage": 7.43, "elapsed_time": "1:07:43", "remaining_time": "14:03:24"}
+{"current_steps": 120, "total_steps": 1480, "loss": 0.4202, "lr": 8.040540540540541e-06, "epoch": 0.08112219029913807, "percentage": 8.11, "elapsed_time": "1:13:12", "remaining_time": "13:49:43"}
+{"current_steps": 130, "total_steps": 1480, "loss": 0.4299, "lr": 8.716216216216217e-06, "epoch": 0.08788237282406625, "percentage": 8.78, "elapsed_time": "1:18:50", "remaining_time": "13:38:40"}
+{"current_steps": 140, "total_steps": 1480, "loss": 0.4134, "lr": 9.391891891891893e-06, "epoch": 0.09464255534899442, "percentage": 9.46, "elapsed_time": "1:24:45", "remaining_time": "13:31:13"}
+{"current_steps": 150, "total_steps": 1480, "loss": 0.4138, "lr": 9.999986093075303e-06, "epoch": 0.1014027378739226, "percentage": 10.14, "elapsed_time": "1:30:35", "remaining_time": "13:23:16"}
+{"current_steps": 160, "total_steps": 1480, "loss": 0.4063, "lr": 9.998317355716393e-06, "epoch": 0.10816292039885077, "percentage": 10.81, "elapsed_time": "1:36:00", "remaining_time": "13:12:02"}
+{"current_steps": 170, "total_steps": 1480, "loss": 0.4265, "lr": 9.993868297034709e-06, "epoch": 0.11492310292377894, "percentage": 11.49, "elapsed_time": "1:41:42", "remaining_time": "13:03:42"}
+{"current_steps": 180, "total_steps": 1480, "loss": 0.4437, "lr": 9.986641391825633e-06, "epoch": 0.12168328544870712, "percentage": 12.16, "elapsed_time": "1:47:16", "remaining_time": "12:54:42"}
+{"current_steps": 190, "total_steps": 1480, "loss": 0.3854, "lr": 9.976640660065733e-06, "epoch": 0.1284434679736353, "percentage": 12.84, "elapsed_time": "1:53:14", "remaining_time": "12:48:53"}
+{"current_steps": 200, "total_steps": 1480, "loss": 0.3906, "lr": 9.963871664676647e-06, "epoch": 0.13520365049856345, "percentage": 13.51, "elapsed_time": "1:58:58", "remaining_time": "12:41:23"}
+{"current_steps": 200, "total_steps": 1480, "eval_loss": 0.4129255712032318, "epoch": 0.13520365049856345, "percentage": 13.51, "elapsed_time": "2:20:13", "remaining_time": "14:57:23"}
+{"current_steps": 210, "total_steps": 1480, "loss": 0.416, "lr": 9.948341508430691e-06, "epoch": 0.14196383302349164, "percentage": 14.19, "elapsed_time": "2:26:05", "remaining_time": "14:43:31"}
+{"current_steps": 220, "total_steps": 1480, "loss": 0.4055, "lr": 9.93005882999994e-06, "epoch": 0.1487240155484198, "percentage": 14.86, "elapsed_time": "2:31:56", "remaining_time": "14:30:11"}
+{"current_steps": 230, "total_steps": 1480, "loss": 0.4093, "lr": 9.909033799150947e-06, "epoch": 0.15548419807334798, "percentage": 15.54, "elapsed_time": "2:37:24", "remaining_time": "14:15:29"}
+{"current_steps": 240, "total_steps": 1480, "loss": 0.4183, "lr": 9.885278111087803e-06, "epoch": 0.16224438059827614, "percentage": 16.22, "elapsed_time": "2:43:14", "remaining_time": "14:03:23"}
+{"current_steps": 250, "total_steps": 1480, "loss": 0.3845, "lr": 9.85880497994666e-06, "epoch": 0.16900456312320433, "percentage": 16.89, "elapsed_time": "2:48:56", "remaining_time": "13:51:11"}
+{"current_steps": 260, "total_steps": 1480, "loss": 0.3886, "lr": 9.829629131445342e-06, "epoch": 0.1757647456481325, "percentage": 17.57, "elapsed_time": "2:54:42", "remaining_time": "13:39:47"}
+{"current_steps": 270, "total_steps": 1480, "loss": 0.4016, "lr": 9.797766794692156e-06, "epoch": 0.18252492817306068, "percentage": 18.24, "elapsed_time": "3:00:49", "remaining_time": "13:30:19"}
+{"current_steps": 280, "total_steps": 1480, "loss": 0.3855, "lr": 9.76323569315841e-06, "epoch": 0.18928511069798884, "percentage": 18.92, "elapsed_time": "3:06:19", "remaining_time": "13:18:33"}
+{"current_steps": 290, "total_steps": 1480, "loss": 0.3987, "lr": 9.726055034819726e-06, "epoch": 0.19604529322291703, "percentage": 19.59, "elapsed_time": "3:12:02", "remaining_time": "13:07:59"}
+{"current_steps": 300, "total_steps": 1480, "loss": 0.3903, "lr": 9.686245501471555e-06, "epoch": 0.2028054757478452, "percentage": 20.27, "elapsed_time": "3:18:01", "remaining_time": "12:58:54"}
+{"current_steps": 310, "total_steps": 1480, "loss": 0.4012, "lr": 9.64382923722492e-06, "epoch": 0.20956565827277338, "percentage": 20.95, "elapsed_time": "3:23:38", "remaining_time": "12:48:33"}
+{"current_steps": 320, "total_steps": 1480, "loss": 0.3823, "lr": 9.598829836188694e-06, "epoch": 0.21632584079770154, "percentage": 21.62, "elapsed_time": "3:29:20", "remaining_time": "12:38:52"}
+{"current_steps": 330, "total_steps": 1480, "loss": 0.3722, "lr": 9.551272329345373e-06, "epoch": 0.22308602332262972, "percentage": 22.3, "elapsed_time": "3:35:15", "remaining_time": "12:30:09"}
+{"current_steps": 340, "total_steps": 1480, "loss": 0.3863, "lr": 9.501183170627535e-06, "epoch": 0.22984620584755788, "percentage": 22.97, "elapsed_time": "3:41:02", "remaining_time": "12:21:07"}
+{"current_steps": 350, "total_steps": 1480, "loss": 0.3713, "lr": 9.448590222202808e-06, "epoch": 0.23660638837248607, "percentage": 23.65, "elapsed_time": "3:47:02", "remaining_time": "12:13:01"}
+{"current_steps": 360, "total_steps": 1480, "loss": 0.3817, "lr": 9.393522738975497e-06, "epoch": 0.24336657089741423, "percentage": 24.32, "elapsed_time": "3:52:54", "remaining_time": "12:04:37"}
+{"current_steps": 370, "total_steps": 1480, "loss": 0.3826, "lr": 9.336011352313502e-06, "epoch": 0.2501267534223424, "percentage": 25.0, "elapsed_time": "3:58:43", "remaining_time": "11:56:11"}
+{"current_steps": 380, "total_steps": 1480, "loss": 0.3629, "lr": 9.276088053009578e-06, "epoch": 0.2568869359472706, "percentage": 25.68, "elapsed_time": "4:04:41", "remaining_time": "11:48:18"}
+{"current_steps": 390, "total_steps": 1480, "loss": 0.3887, "lr": 9.213786173486403e-06, "epoch": 0.26364711847219874, "percentage": 26.35, "elapsed_time": "4:10:26", "remaining_time": "11:39:57"}
+{"current_steps": 400, "total_steps": 1480, "loss": 0.3823, "lr": 9.149140369255377e-06, "epoch": 0.2704073009971269, "percentage": 27.03, "elapsed_time": "4:16:37", "remaining_time": "11:32:53"}
+{"current_steps": 400, "total_steps": 1480, "eval_loss": 0.3794357478618622, "epoch": 0.2704073009971269, "percentage": 27.03, "elapsed_time": "4:37:52", "remaining_time": "12:30:15"}
+{"current_steps": 410, "total_steps": 1480, "loss": 0.3783, "lr": 9.082186599639429e-06, "epoch": 0.2771674835220551, "percentage": 27.7, "elapsed_time": "4:43:29", "remaining_time": "12:19:51"}
+{"current_steps": 420, "total_steps": 1480, "loss": 0.3824, "lr": 9.012962107770615e-06, "epoch": 0.2839276660469833, "percentage": 28.38, "elapsed_time": "4:51:18", "remaining_time": "12:15:11"}
+{"current_steps": 430, "total_steps": 1480, "loss": 0.3722, "lr": 8.941505399873549e-06, "epoch": 0.29068784857191143, "percentage": 29.05, "elapsed_time": "4:58:37", "remaining_time": "12:09:13"}
+{"current_steps": 440, "total_steps": 1480, "loss": 0.3725, "lr": 8.86785622384627e-06, "epoch": 0.2974480310968396, "percentage": 29.73, "elapsed_time": "5:06:39", "remaining_time": "12:04:50"}
+{"current_steps": 450, "total_steps": 1480, "loss": 0.368, "lr": 8.792055547150413e-06, "epoch": 0.3042082136217678, "percentage": 30.41, "elapsed_time": "5:14:23", "remaining_time": "11:59:35"}
+{"current_steps": 460, "total_steps": 1480, "loss": 0.3576, "lr": 8.714145534022999e-06, "epoch": 0.31096839614669597, "percentage": 31.08, "elapsed_time": "5:22:35", "remaining_time": "11:55:18"}
+{"current_steps": 470, "total_steps": 1480, "loss": 0.3585, "lr": 8.634169522022522e-06, "epoch": 0.31772857867162413, "percentage": 31.76, "elapsed_time": "5:30:11", "remaining_time": "11:49:33"}
+{"current_steps": 480, "total_steps": 1480, "loss": 0.3495, "lr": 8.552171997922358e-06, "epoch": 0.3244887611965523, "percentage": 32.43, "elapsed_time": "5:38:02", "remaining_time": "11:44:14"}
+{"current_steps": 490, "total_steps": 1480, "loss": 0.3662, "lr": 8.46819857296494e-06, "epoch": 0.3312489437214805, "percentage": 33.11, "elapsed_time": "5:46:24", "remaining_time": "11:39:52"}
+{"current_steps": 500, "total_steps": 1480, "loss": 0.3616, "lr": 8.382295957490435e-06, "epoch": 0.33800912624640866, "percentage": 33.78, "elapsed_time": "5:54:33", "remaining_time": "11:34:56"}
+{"current_steps": 510, "total_steps": 1480, "loss": 0.3595, "lr": 8.294511934954054e-06, "epoch": 0.3447693087713368, "percentage": 34.46, "elapsed_time": "6:02:26", "remaining_time": "11:29:20"}
+{"current_steps": 520, "total_steps": 1480, "loss": 0.3549, "lr": 8.20489533534643e-06, "epoch": 0.351529491296265, "percentage": 35.14, "elapsed_time": "6:10:02", "remaining_time": "11:23:09"}
+{"current_steps": 530, "total_steps": 1480, "loss": 0.3426, "lr": 8.113496008031863e-06, "epoch": 0.3582896738211932, "percentage": 35.81, "elapsed_time": "6:17:30", "remaining_time": "11:16:39"}
+{"current_steps": 540, "total_steps": 1480, "loss": 0.351, "lr": 8.020364794019546e-06, "epoch": 0.36504985634612136, "percentage": 36.49, "elapsed_time": "6:25:24", "remaining_time": "11:10:53"}
+{"current_steps": 550, "total_steps": 1480, "loss": 0.3413, "lr": 7.925553497683169e-06, "epoch": 0.3718100388710495, "percentage": 37.16, "elapsed_time": "6:32:55", "remaining_time": "11:04:23"}
+{"current_steps": 560, "total_steps": 1480, "loss": 0.3589, "lr": 7.829114857944672e-06, "epoch": 0.3785702213959777, "percentage": 37.84, "elapsed_time": "6:40:59", "remaining_time": "10:58:47"}
+{"current_steps": 570, "total_steps": 1480, "loss": 0.3483, "lr": 7.731102518938137e-06, "epoch": 0.38533040392090584, "percentage": 38.51, "elapsed_time": "6:49:02", "remaining_time": "10:53:02"}
+{"current_steps": 580, "total_steps": 1480, "loss": 0.356, "lr": 7.631571000170156e-06, "epoch": 0.39209058644583406, "percentage": 39.19, "elapsed_time": "6:56:31", "remaining_time": "10:46:19"}
+{"current_steps": 590, "total_steps": 1480, "loss": 0.3544, "lr": 7.530575666193283e-06, "epoch": 0.3988507689707622, "percentage": 39.86, "elapsed_time": "7:04:35", "remaining_time": "10:40:28"}
+{"current_steps": 600, "total_steps": 1480, "loss": 0.3507, "lr": 7.4281726958094146e-06, "epoch": 0.4056109514956904, "percentage": 40.54, "elapsed_time": "7:11:39", "remaining_time": "10:33:06"}
+{"current_steps": 600, "total_steps": 1480, "eval_loss": 0.35060280561447144, "epoch": 0.4056109514956904, "percentage": 40.54, "elapsed_time": "7:32:50", "remaining_time": "11:04:10"}
+{"current_steps": 610, "total_steps": 1480, "loss": 0.3511, "lr": 7.32441905082026e-06, "epoch": 0.41237113402061853, "percentage": 41.22, "elapsed_time": "7:39:00", "remaining_time": "10:54:39"}
+{"current_steps": 620, "total_steps": 1480, "loss": 0.3547, "lr": 7.2193724443422405e-06, "epoch": 0.41913131654554675, "percentage": 41.89, "elapsed_time": "7:44:50", "remaining_time": "10:44:46"}
+{"current_steps": 630, "total_steps": 1480, "loss": 0.3313, "lr": 7.113091308703498e-06, "epoch": 0.4258914990704749, "percentage": 42.57, "elapsed_time": "7:50:40", "remaining_time": "10:35:02"}
+{"current_steps": 640, "total_steps": 1480, "loss": 0.3513, "lr": 7.005634762940818e-06, "epoch": 0.43265168159540307, "percentage": 43.24, "elapsed_time": "7:56:28", "remaining_time": "10:25:22"}
+{"current_steps": 650, "total_steps": 1480, "loss": 0.3311, "lr": 6.897062579914587e-06, "epoch": 0.43941186412033123, "percentage": 43.92, "elapsed_time": "8:02:15", "remaining_time": "10:15:48"}
+{"current_steps": 660, "total_steps": 1480, "loss": 0.3335, "lr": 6.787435153060039e-06, "epoch": 0.44617204664525945, "percentage": 44.59, "elapsed_time": "8:08:06", "remaining_time": "10:06:26"}
+{"current_steps": 670, "total_steps": 1480, "loss": 0.3339, "lr": 6.676813462793337e-06, "epoch": 0.4529322291701876, "percentage": 45.27, "elapsed_time": "8:13:43", "remaining_time": "9:56:53"}
+{"current_steps": 680, "total_steps": 1480, "loss": 0.3446, "lr": 6.565259042591112e-06, "epoch": 0.45969241169511577, "percentage": 45.95, "elapsed_time": "8:19:45", "remaining_time": "9:47:57"}
+{"current_steps": 690, "total_steps": 1480, "loss": 0.3475, "lr": 6.452833944762385e-06, "epoch": 0.4664525942200439, "percentage": 46.62, "elapsed_time": "8:25:45", "remaining_time": "9:39:03"}
+{"current_steps": 700, "total_steps": 1480, "loss": 0.3274, "lr": 6.339600705931876e-06, "epoch": 0.47321277674497214, "percentage": 47.3, "elapsed_time": "8:31:25", "remaining_time": "9:29:52"}
+{"current_steps": 710, "total_steps": 1480, "loss": 0.3347, "lr": 6.225622312253916e-06, "epoch": 0.4799729592699003, "percentage": 47.97, "elapsed_time": "8:37:16", "remaining_time": "9:20:59"}
+{"current_steps": 720, "total_steps": 1480, "loss": 0.3419, "lr": 6.110962164376309e-06, "epoch": 0.48673314179482846, "percentage": 48.65, "elapsed_time": "8:43:11", "remaining_time": "9:12:15"}
+{"current_steps": 730, "total_steps": 1480, "loss": 0.3344, "lr": 5.995684042173626e-06, "epoch": 0.4934933243197566, "percentage": 49.32, "elapsed_time": "8:49:11", "remaining_time": "9:03:41"}
+{"current_steps": 740, "total_steps": 1480, "loss": 0.3115, "lr": 5.8798520692695605e-06, "epoch": 0.5002535068446848, "percentage": 50.0, "elapsed_time": "8:54:56", "remaining_time": "8:54:56"}
+{"current_steps": 750, "total_steps": 1480, "loss": 0.3248, "lr": 5.763530677368065e-06, "epoch": 0.507013689369613, "percentage": 50.68, "elapsed_time": "9:00:38", "remaining_time": "8:46:13"}
+{"current_steps": 760, "total_steps": 1480, "loss": 0.3381, "lr": 5.64678457041312e-06, "epoch": 0.5137738718945412, "percentage": 51.35, "elapsed_time": "9:06:27", "remaining_time": "8:37:42"}
+{"current_steps": 770, "total_steps": 1480, "loss": 0.3272, "lr": 5.529678688597081e-06, "epoch": 0.5205340544194693, "percentage": 52.03, "elapsed_time": "9:12:19", "remaining_time": "8:29:16"}
+{"current_steps": 780, "total_steps": 1480, "loss": 0.3283, "lr": 5.412278172237591e-06, "epoch": 0.5272942369443975, "percentage": 52.7, "elapsed_time": "9:18:01", "remaining_time": "8:20:47"}
+{"current_steps": 790, "total_steps": 1480, "loss": 0.3201, "lr": 5.294648325543188e-06, "epoch": 0.5340544194693256, "percentage": 53.38, "elapsed_time": "9:23:53", "remaining_time": "8:12:31"}
+{"current_steps": 800, "total_steps": 1480, "loss": 0.3065, "lr": 5.176854580287744e-06, "epoch": 0.5408146019942538, "percentage": 54.05, "elapsed_time": "9:29:40", "remaining_time": "8:04:13"}
+{"current_steps": 800, "total_steps": 1480, "eval_loss": 0.329855740070343, "epoch": 0.5408146019942538, "percentage": 54.05, "elapsed_time": "9:50:57", "remaining_time": "8:22:18"}
+{"current_steps": 810, "total_steps": 1480, "loss": 0.3207, "lr": 5.0589624594139455e-06, "epoch": 0.5475747845191821, "percentage": 54.73, "elapsed_time": "9:56:44", "remaining_time": "8:13:36"}
+{"current_steps": 820, "total_steps": 1480, "loss": 0.3062, "lr": 4.941037540586057e-06, "epoch": 0.5543349670441102, "percentage": 55.41, "elapsed_time": "10:02:03", "remaining_time": "8:04:35"}
+{"current_steps": 830, "total_steps": 1480, "loss": 0.3114, "lr": 4.8231454197122575e-06, "epoch": 0.5610951495690384, "percentage": 56.08, "elapsed_time": "10:07:49", "remaining_time": "7:56:00"}
+{"current_steps": 840, "total_steps": 1480, "loss": 0.3267, "lr": 4.705351674456813e-06, "epoch": 0.5678553320939665, "percentage": 56.76, "elapsed_time": "10:13:28", "remaining_time": "7:47:24"}
+{"current_steps": 850, "total_steps": 1480, "loss": 0.3231, "lr": 4.587721827762411e-06, "epoch": 0.5746155146188947, "percentage": 57.43, "elapsed_time": "10:19:19", "remaining_time": "7:39:01"}
+{"current_steps": 860, "total_steps": 1480, "loss": 0.328, "lr": 4.47032131140292e-06, "epoch": 0.5813756971438229, "percentage": 58.11, "elapsed_time": "10:25:06", "remaining_time": "7:30:39"}
+{"current_steps": 870, "total_steps": 1480, "loss": 0.3215, "lr": 4.353215429586882e-06, "epoch": 0.588135879668751, "percentage": 58.78, "elapsed_time": "10:30:47", "remaining_time": "7:22:16"}
+{"current_steps": 880, "total_steps": 1480, "loss": 0.328, "lr": 4.236469322631938e-06, "epoch": 0.5948960621936792, "percentage": 59.46, "elapsed_time": "10:36:22", "remaining_time": "7:13:53"}
+{"current_steps": 890, "total_steps": 1480, "loss": 0.3036, "lr": 4.12014793073044e-06, "epoch": 0.6016562447186073, "percentage": 60.14, "elapsed_time": "10:42:06", "remaining_time": "7:05:40"}
+{"current_steps": 900, "total_steps": 1480, "loss": 0.3024, "lr": 4.004315957826375e-06, "epoch": 0.6084164272435356, "percentage": 60.81, "elapsed_time": "10:47:30", "remaining_time": "6:57:17"}
+{"current_steps": 910, "total_steps": 1480, "loss": 0.3144, "lr": 3.889037835623693e-06, "epoch": 0.6151766097684638, "percentage": 61.49, "elapsed_time": "10:53:19", "remaining_time": "6:49:13"}
+{"current_steps": 920, "total_steps": 1480, "loss": 0.3228, "lr": 3.7743776877460864e-06, "epoch": 0.6219367922933919, "percentage": 62.16, "elapsed_time": "10:58:55", "remaining_time": "6:41:05"}
+{"current_steps": 930, "total_steps": 1480, "loss": 0.3055, "lr": 3.6603992940681263e-06, "epoch": 0.6286969748183201, "percentage": 62.84, "elapsed_time": "11:04:53", "remaining_time": "6:33:13"}
+{"current_steps": 940, "total_steps": 1480, "loss": 0.3264, "lr": 3.5471660552376176e-06, "epoch": 0.6354571573432483, "percentage": 63.51, "elapsed_time": "11:10:39", "remaining_time": "6:25:16"}
+{"current_steps": 950, "total_steps": 1480, "loss": 0.316, "lr": 3.4347409574088896e-06, "epoch": 0.6422173398681764, "percentage": 64.19, "elapsed_time": "11:16:31", "remaining_time": "6:17:25"}
+{"current_steps": 960, "total_steps": 1480, "loss": 0.3071, "lr": 3.323186537206665e-06, "epoch": 0.6489775223931046, "percentage": 64.86, "elapsed_time": "11:21:54", "remaining_time": "6:09:22"}
+{"current_steps": 970, "total_steps": 1480, "loss": 0.3193, "lr": 3.2125648469399628e-06, "epoch": 0.6557377049180327, "percentage": 65.54, "elapsed_time": "11:27:53", "remaining_time": "6:01:40"}
+{"current_steps": 980, "total_steps": 1480, "loss": 0.3001, "lr": 3.1029374200854167e-06, "epoch": 0.662497887442961, "percentage": 66.22, "elapsed_time": "11:33:43", "remaining_time": "5:53:56"}
+{"current_steps": 990, "total_steps": 1480, "loss": 0.3059, "lr": 2.9943652370591835e-06, "epoch": 0.6692580699678892, "percentage": 66.89, "elapsed_time": "11:39:13", "remaining_time": "5:46:04"}
+{"current_steps": 1000, "total_steps": 1480, "loss": 0.3042, "lr": 2.886908691296504e-06, "epoch": 0.6760182524928173, "percentage": 67.57, "elapsed_time": "11:45:04", "remaining_time": "5:38:26"}
+{"current_steps": 1000, "total_steps": 1480, "eval_loss": 0.30882763862609863, "epoch": 0.6760182524928173, "percentage": 67.57, "elapsed_time": "12:06:15", "remaining_time": "5:48:36"}
+{"current_steps": 1010, "total_steps": 1480, "loss": 0.3064, "lr": 2.7806275556577624e-06, "epoch": 0.6827784350177455, "percentage": 68.24, "elapsed_time": "12:12:16", "remaining_time": "5:40:45"}
+{"current_steps": 1020, "total_steps": 1480, "loss": 0.3103, "lr": 2.6755809491797426e-06, "epoch": 0.6895386175426736, "percentage": 68.92, "elapsed_time": "12:18:11", "remaining_time": "5:32:54"}
+{"current_steps": 1030, "total_steps": 1480, "loss": 0.2969, "lr": 2.5718273041905863e-06, "epoch": 0.6962988000676018, "percentage": 69.59, "elapsed_time": "12:23:59", "remaining_time": "5:25:02"}
+{"current_steps": 1040, "total_steps": 1480, "loss": 0.3062, "lr": 2.469424333806718e-06, "epoch": 0.70305898259253, "percentage": 70.27, "elapsed_time": "12:29:44", "remaining_time": "5:17:11"}
+{"current_steps": 1050, "total_steps": 1480, "loss": 0.317, "lr": 2.3684289998298453e-06, "epoch": 0.7098191651174581, "percentage": 70.95, "elapsed_time": "12:35:38", "remaining_time": "5:09:27"}
+{"current_steps": 1060, "total_steps": 1480, "loss": 0.2845, "lr": 2.268897481061863e-06, "epoch": 0.7165793476423864, "percentage": 71.62, "elapsed_time": "12:41:34", "remaining_time": "5:01:45"}
+{"current_steps": 1070, "total_steps": 1480, "loss": 0.3041, "lr": 2.1708851420553277e-06, "epoch": 0.7233395301673146, "percentage": 72.3, "elapsed_time": "12:47:40", "remaining_time": "4:54:09"}
+{"current_steps": 1080, "total_steps": 1480, "loss": 0.3023, "lr": 2.0744465023168313e-06, "epoch": 0.7300997126922427, "percentage": 72.97, "elapsed_time": "12:53:31", "remaining_time": "4:46:29"}
+{"current_steps": 1090, "total_steps": 1480, "loss": 0.3089, "lr": 1.9796352059804565e-06, "epoch": 0.7368598952171709, "percentage": 73.65, "elapsed_time": "12:59:25", "remaining_time": "4:38:52"}
+{"current_steps": 1100, "total_steps": 1480, "loss": 0.2941, "lr": 1.8865039919681377e-06, "epoch": 0.743620077742099, "percentage": 74.32, "elapsed_time": "13:05:08", "remaining_time": "4:31:13"}
+{"current_steps": 1110, "total_steps": 1480, "loss": 0.2856, "lr": 1.7951046646535714e-06, "epoch": 0.7503802602670272, "percentage": 75.0, "elapsed_time": "13:10:46", "remaining_time": "4:23:35"}
+{"current_steps": 1120, "total_steps": 1480, "loss": 0.2919, "lr": 1.705488065045946e-06, "epoch": 0.7571404427919554, "percentage": 75.68, "elapsed_time": "13:16:24", "remaining_time": "4:15:59"}
+{"current_steps": 1130, "total_steps": 1480, "loss": 0.2985, "lr": 1.6177040425095664e-06, "epoch": 0.7639006253168835, "percentage": 76.35, "elapsed_time": "13:22:11", "remaining_time": "4:08:28"}
+{"current_steps": 1140, "total_steps": 1480, "loss": 0.2893, "lr": 1.5318014270350617e-06, "epoch": 0.7706608078418117, "percentage": 77.03, "elapsed_time": "13:28:11", "remaining_time": "4:01:02"}
+{"current_steps": 1150, "total_steps": 1480, "loss": 0.2862, "lr": 1.4478280020776442e-06, "epoch": 0.77742099036674, "percentage": 77.7, "elapsed_time": "13:34:00", "remaining_time": "3:53:35"}
+{"current_steps": 1160, "total_steps": 1480, "loss": 0.2967, "lr": 1.3658304779774784e-06, "epoch": 0.7841811728916681, "percentage": 78.38, "elapsed_time": "13:40:22", "remaining_time": "3:46:18"}
+{"current_steps": 1170, "total_steps": 1480, "loss": 0.2924, "lr": 1.2858544659770001e-06, "epoch": 0.7909413554165963, "percentage": 79.05, "elapsed_time": "13:46:09", "remaining_time": "3:38:53"}
+{"current_steps": 1180, "total_steps": 1480, "loss": 0.2921, "lr": 1.2079444528495887e-06, "epoch": 0.7977015379415244, "percentage": 79.73, "elapsed_time": "13:51:51", "remaining_time": "3:31:29"}
+{"current_steps": 1190, "total_steps": 1480, "loss": 0.2805, "lr": 1.1321437761537307e-06, "epoch": 0.8044617204664526, "percentage": 80.41, "elapsed_time": "13:57:33", "remaining_time": "3:24:06"}
+{"current_steps": 1200, "total_steps": 1480, "loss": 0.2977, "lr": 1.0584946001264523e-06, "epoch": 0.8112219029913807, "percentage": 81.08, "elapsed_time": "14:03:26", "remaining_time": "3:16:48"}
+{"current_steps": 1200, "total_steps": 1480, "eval_loss": 0.294592946767807, "epoch": 0.8112219029913807, "percentage": 81.08, "elapsed_time": "14:24:37", "remaining_time": "3:21:44"}
+{"current_steps": 1210, "total_steps": 1480, "loss": 0.2859, "lr": 9.870378922293855e-07, "epoch": 0.8179820855163089, "percentage": 81.76, "elapsed_time": "14:30:40", "remaining_time": "3:14:16"}
+{"current_steps": 1220, "total_steps": 1480, "loss": 0.2916, "lr": 9.178134003605721e-07, "epoch": 0.8247422680412371, "percentage": 82.43, "elapsed_time": "14:36:36", "remaining_time": "3:06:49"}
+{"current_steps": 1230, "total_steps": 1480, "loss": 0.2867, "lr": 8.508596307446254e-07, "epoch": 0.8315024505661653, "percentage": 83.11, "elapsed_time": "14:42:21", "remaining_time": "2:59:20"}
+{"current_steps": 1240, "total_steps": 1480, "loss": 0.2886, "lr": 7.862138265135983e-07, "epoch": 0.8382626330910935, "percentage": 83.78, "elapsed_time": "14:48:21", "remaining_time": "2:51:56"}
+{"current_steps": 1250, "total_steps": 1480, "loss": 0.2814, "lr": 7.239119469904227e-07, "epoch": 0.8450228156160217, "percentage": 84.46, "elapsed_time": "14:54:28", "remaining_time": "2:44:34"}
+{"current_steps": 1260, "total_steps": 1480, "loss": 0.2806, "lr": 6.639886476864993e-07, "epoch": 0.8517829981409498, "percentage": 85.14, "elapsed_time": "15:00:37", "remaining_time": "2:37:15"}
+{"current_steps": 1270, "total_steps": 1480, "loss": 0.2778, "lr": 6.064772610245051e-07, "epoch": 0.858543180665878, "percentage": 85.81, "elapsed_time": "15:06:18", "remaining_time": "2:29:51"}
+{"current_steps": 1280, "total_steps": 1480, "loss": 0.2966, "lr": 5.514097777971939e-07, "epoch": 0.8653033631908061, "percentage": 86.49, "elapsed_time": "15:11:51", "remaining_time": "2:22:28"}
+{"current_steps": 1290, "total_steps": 1480, "loss": 0.2858, "lr": 4.988168293724654e-07, "epoch": 0.8720635457157343, "percentage": 87.16, "elapsed_time": "15:17:31", "remaining_time": "2:15:08"}
+{"current_steps": 1300, "total_steps": 1480, "loss": 0.2871, "lr": 4.4872767065462787e-07, "epoch": 0.8788237282406625, "percentage": 87.84, "elapsed_time": "15:23:13", "remaining_time": "2:07:49"}
+{"current_steps": 1310, "total_steps": 1480, "loss": 0.2982, "lr": 4.0117016381130636e-07, "epoch": 0.8855839107655906, "percentage": 88.51, "elapsed_time": "15:28:45", "remaining_time": "2:00:31"}
+{"current_steps": 1320, "total_steps": 1480, "loss": 0.2772, "lr": 3.561707627750827e-07, "epoch": 0.8923440932905189, "percentage": 89.19, "elapsed_time": "15:34:24", "remaining_time": "1:53:15"}
+{"current_steps": 1330, "total_steps": 1480, "loss": 0.2939, "lr": 3.137544985284441e-07, "epoch": 0.899104275815447, "percentage": 89.86, "elapsed_time": "15:40:20", "remaining_time": "1:46:03"}
+{"current_steps": 1340, "total_steps": 1480, "loss": 0.2912, "lr": 2.739449651802756e-07, "epoch": 0.9058644583403752, "percentage": 90.54, "elapsed_time": "15:46:21", "remaining_time": "1:38:52"}
+{"current_steps": 1350, "total_steps": 1480, "loss": 0.28, "lr": 2.3676430684159035e-07, "epoch": 0.9126246408653034, "percentage": 91.22, "elapsed_time": "15:52:02", "remaining_time": "1:31:40"}
+{"current_steps": 1360, "total_steps": 1480, "loss": 0.2832, "lr": 2.0223320530784574e-07, "epoch": 0.9193848233902315, "percentage": 91.89, "elapsed_time": "15:57:51", "remaining_time": "1:24:31"}
+{"current_steps": 1370, "total_steps": 1480, "loss": 0.2857, "lr": 1.7037086855465902e-07, "epoch": 0.9261450059151597, "percentage": 92.57, "elapsed_time": "16:03:39", "remaining_time": "1:17:22"}
+{"current_steps": 1380, "total_steps": 1480, "loss": 0.2933, "lr": 1.4119502005334185e-07, "epoch": 0.9329051884400879, "percentage": 93.24, "elapsed_time": "16:09:34", "remaining_time": "1:10:15"}
+{"current_steps": 1390, "total_steps": 1480, "loss": 0.289, "lr": 1.1472188891219816e-07, "epoch": 0.939665370965016, "percentage": 93.92, "elapsed_time": "16:15:31", "remaining_time": "1:03:09"}
+{"current_steps": 1400, "total_steps": 1480, "loss": 0.2908, "lr": 9.096620084905472e-08, "epoch": 0.9464255534899443, "percentage": 94.59, "elapsed_time": "16:21:17", "remaining_time": "0:56:04"}
+{"current_steps": 1400, "total_steps": 1480, "eval_loss": 0.2895006537437439, "epoch": 0.9464255534899443, "percentage": 94.59, "elapsed_time": "16:42:27", "remaining_time": "0:57:16"}
+{"current_steps": 1410, "total_steps": 1480, "loss": 0.2998, "lr": 6.994117000006185e-08, "epoch": 0.9531857360148724, "percentage": 95.27, "elapsed_time": "16:48:29", "remaining_time": "0:50:04"}
+{"current_steps": 1420, "total_steps": 1480, "loss": 0.276, "lr": 5.165849156930969e-08, "epoch": 0.9599459185398006, "percentage": 95.95, "elapsed_time": "16:54:16", "remaining_time": "0:42:51"}
+{"current_steps": 1430, "total_steps": 1480, "loss": 0.2761, "lr": 3.6128335323353804e-08, "epoch": 0.9667061010647288, "percentage": 96.62, "elapsed_time": "17:00:08", "remaining_time": "0:35:40"}
+{"current_steps": 1440, "total_steps": 1480, "loss": 0.2995, "lr": 2.335933993426687e-08, "epoch": 0.9734662835896569, "percentage": 97.3, "elapsed_time": "17:06:04", "remaining_time": "0:28:30"}
+{"current_steps": 1450, "total_steps": 1480, "loss": 0.2772, "lr": 1.3358608174368626e-08, "epoch": 0.9802264661145851, "percentage": 97.97, "elapsed_time": "17:11:56", "remaining_time": "0:21:21"}
+{"current_steps": 1460, "total_steps": 1480, "loss": 0.3069, "lr": 6.1317029652929734e-09, "epoch": 0.9869866486395132, "percentage": 98.65, "elapsed_time": "17:17:43", "remaining_time": "0:14:12"}
+{"current_steps": 1470, "total_steps": 1480, "loss": 0.2764, "lr": 1.6826442836082035e-09, "epoch": 0.9937468311644414, "percentage": 99.32, "elapsed_time": "17:23:56", "remaining_time": "0:07:06"}
+{"current_steps": 1480, "total_steps": 1480, "loss": 0.2913, "lr": 1.3906924697382195e-11, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "17:29:23", "remaining_time": "0:00:00"}
+{"current_steps": 1480, "total_steps": 1480, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "17:29:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1135 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 1480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006760182524928173,
+      "grad_norm": 15.915069580078125,
+      "learning_rate": 6.081081081081082e-07,
+      "loss": 1.028,
+      "step": 10
+    },
+    {
+      "epoch": 0.013520365049856346,
+      "grad_norm": 7.203866004943848,
+      "learning_rate": 1.2837837837837838e-06,
+      "loss": 0.8412,
+      "step": 20
+    },
+    {
+      "epoch": 0.020280547574784518,
+      "grad_norm": 4.731671333312988,
+      "learning_rate": 1.9594594594594595e-06,
+      "loss": 0.6928,
+      "step": 30
+    },
+    {
+      "epoch": 0.027040730099712692,
+      "grad_norm": 4.059757709503174,
+      "learning_rate": 2.6351351351351353e-06,
+      "loss": 0.5823,
+      "step": 40
+    },
+    {
+      "epoch": 0.03380091262464086,
+      "grad_norm": 3.655268430709839,
+      "learning_rate": 3.310810810810811e-06,
+      "loss": 0.5195,
+      "step": 50
+    },
+    {
+      "epoch": 0.040561095149569036,
+      "grad_norm": 3.749523401260376,
+      "learning_rate": 3.986486486486487e-06,
+      "loss": 0.4697,
+      "step": 60
+    },
+    {
+      "epoch": 0.04732127767449721,
+      "grad_norm": 3.336225748062134,
+      "learning_rate": 4.6621621621621625e-06,
+      "loss": 0.4567,
+      "step": 70
+    },
+    {
+      "epoch": 0.054081460199425384,
+      "grad_norm": 3.8789913654327393,
+      "learning_rate": 5.337837837837838e-06,
+      "loss": 0.4675,
+      "step": 80
+    },
+    {
+      "epoch": 0.06084164272435356,
+      "grad_norm": 3.631592035293579,
+      "learning_rate": 6.013513513513514e-06,
+      "loss": 0.4531,
+      "step": 90
+    },
+    {
+      "epoch": 0.06760182524928172,
+      "grad_norm": 3.175447702407837,
+      "learning_rate": 6.689189189189191e-06,
+      "loss": 0.4368,
+      "step": 100
+    },
+    {
+      "epoch": 0.0743620077742099,
+      "grad_norm": 3.1399242877960205,
+      "learning_rate": 7.3648648648648655e-06,
+      "loss": 0.4185,
+      "step": 110
+    },
+    {
+      "epoch": 0.08112219029913807,
+      "grad_norm": 3.3930342197418213,
+      "learning_rate": 8.040540540540541e-06,
+      "loss": 0.4202,
+      "step": 120
+    },
+    {
+      "epoch": 0.08788237282406625,
+      "grad_norm": 3.535984516143799,
+      "learning_rate": 8.716216216216217e-06,
+      "loss": 0.4299,
+      "step": 130
+    },
+    {
+      "epoch": 0.09464255534899442,
+      "grad_norm": 3.0242111682891846,
+      "learning_rate": 9.391891891891893e-06,
+      "loss": 0.4134,
+      "step": 140
+    },
+    {
+      "epoch": 0.1014027378739226,
+      "grad_norm": 3.216952085494995,
+      "learning_rate": 9.999986093075303e-06,
+      "loss": 0.4138,
+      "step": 150
+    },
+    {
+      "epoch": 0.10816292039885077,
+      "grad_norm": 2.8959848880767822,
+      "learning_rate": 9.998317355716393e-06,
+      "loss": 0.4063,
+      "step": 160
+    },
+    {
+      "epoch": 0.11492310292377894,
+      "grad_norm": 2.8924849033355713,
+      "learning_rate": 9.993868297034709e-06,
+      "loss": 0.4265,
+      "step": 170
+    },
+    {
+      "epoch": 0.12168328544870712,
+      "grad_norm": 3.100831985473633,
+      "learning_rate": 9.986641391825633e-06,
+      "loss": 0.4437,
+      "step": 180
+    },
+    {
+      "epoch": 0.1284434679736353,
+      "grad_norm": 2.6609292030334473,
+      "learning_rate": 9.976640660065733e-06,
+      "loss": 0.3854,
+      "step": 190
+    },
+    {
+      "epoch": 0.13520365049856345,
+      "grad_norm": 2.6647753715515137,
+      "learning_rate": 9.963871664676647e-06,
+      "loss": 0.3906,
+      "step": 200
+    },
+    {
+      "epoch": 0.13520365049856345,
+      "eval_loss": 0.4129255712032318,
+      "eval_runtime": 1274.8086,
+      "eval_samples_per_second": 4.126,
+      "eval_steps_per_second": 0.516,
+      "step": 200
+    },
+    {
+      "epoch": 0.14196383302349164,
+      "grad_norm": 2.908745765686035,
+      "learning_rate": 9.948341508430691e-06,
+      "loss": 0.416,
+      "step": 210
+    },
+    {
+      "epoch": 0.1487240155484198,
+      "grad_norm": 2.6044161319732666,
+      "learning_rate": 9.93005882999994e-06,
+      "loss": 0.4055,
+      "step": 220
+    },
+    {
+      "epoch": 0.15548419807334798,
+      "grad_norm": 2.6734066009521484,
+      "learning_rate": 9.909033799150947e-06,
+      "loss": 0.4093,
+      "step": 230
+    },
+    {
+      "epoch": 0.16224438059827614,
+      "grad_norm": 2.681687116622925,
+      "learning_rate": 9.885278111087803e-06,
+      "loss": 0.4183,
+      "step": 240
+    },
+    {
+      "epoch": 0.16900456312320433,
+      "grad_norm": 2.633845806121826,
+      "learning_rate": 9.85880497994666e-06,
+      "loss": 0.3845,
+      "step": 250
+    },
+    {
+      "epoch": 0.1757647456481325,
+      "grad_norm": 2.317528486251831,
+      "learning_rate": 9.829629131445342e-06,
+      "loss": 0.3886,
+      "step": 260
+    },
+    {
+      "epoch": 0.18252492817306068,
+      "grad_norm": 2.4552831649780273,
+      "learning_rate": 9.797766794692156e-06,
+      "loss": 0.4016,
+      "step": 270
+    },
+    {
+      "epoch": 0.18928511069798884,
+      "grad_norm": 2.5544655323028564,
+      "learning_rate": 9.76323569315841e-06,
+      "loss": 0.3855,
+      "step": 280
+    },
+    {
+      "epoch": 0.19604529322291703,
+      "grad_norm": 2.6713716983795166,
+      "learning_rate": 9.726055034819726e-06,
+      "loss": 0.3987,
+      "step": 290
+    },
+    {
+      "epoch": 0.2028054757478452,
+      "grad_norm": 2.450104236602783,
+      "learning_rate": 9.686245501471555e-06,
+      "loss": 0.3903,
+      "step": 300
+    },
+    {
+      "epoch": 0.20956565827277338,
+      "grad_norm": 2.417210340499878,
+      "learning_rate": 9.64382923722492e-06,
+      "loss": 0.4012,
+      "step": 310
+    },
+    {
+      "epoch": 0.21632584079770154,
+      "grad_norm": 2.1763546466827393,
+      "learning_rate": 9.598829836188694e-06,
+      "loss": 0.3823,
+      "step": 320
+    },
+    {
+      "epoch": 0.22308602332262972,
+      "grad_norm": 2.173384428024292,
+      "learning_rate": 9.551272329345373e-06,
+      "loss": 0.3722,
+      "step": 330
+    },
+    {
+      "epoch": 0.22984620584755788,
+      "grad_norm": 2.3560631275177,
+      "learning_rate": 9.501183170627535e-06,
+      "loss": 0.3863,
+      "step": 340
+    },
+    {
+      "epoch": 0.23660638837248607,
+      "grad_norm": 2.427529811859131,
+      "learning_rate": 9.448590222202808e-06,
+      "loss": 0.3713,
+      "step": 350
+    },
+    {
+      "epoch": 0.24336657089741423,
+      "grad_norm": 2.119920492172241,
+      "learning_rate": 9.393522738975497e-06,
+      "loss": 0.3817,
+      "step": 360
+    },
+    {
+      "epoch": 0.2501267534223424,
+      "grad_norm": 2.0783591270446777,
+      "learning_rate": 9.336011352313502e-06,
+      "loss": 0.3826,
+      "step": 370
+    },
+    {
+      "epoch": 0.2568869359472706,
+      "grad_norm": 2.054614543914795,
+      "learning_rate": 9.276088053009578e-06,
+      "loss": 0.3629,
+      "step": 380
+    },
+    {
+      "epoch": 0.26364711847219874,
+      "grad_norm": 2.3898072242736816,
+      "learning_rate": 9.213786173486403e-06,
+      "loss": 0.3887,
+      "step": 390
+    },
+    {
+      "epoch": 0.2704073009971269,
+      "grad_norm": 2.4764063358306885,
+      "learning_rate": 9.149140369255377e-06,
+      "loss": 0.3823,
+      "step": 400
+    },
+    {
+      "epoch": 0.2704073009971269,
+      "eval_loss": 0.3794357478618622,
+      "eval_runtime": 1274.964,
+      "eval_samples_per_second": 4.126,
+      "eval_steps_per_second": 0.516,
+      "step": 400
+    },
+    {
+      "epoch": 0.2771674835220551,
+      "grad_norm": 2.2685487270355225,
+      "learning_rate": 9.082186599639429e-06,
+      "loss": 0.3783,
+      "step": 410
+    },
+    {
+      "epoch": 0.2839276660469833,
+      "grad_norm": 2.163623332977295,
+      "learning_rate": 9.012962107770615e-06,
+      "loss": 0.3824,
+      "step": 420
+    },
+    {
+      "epoch": 0.29068784857191143,
+      "grad_norm": 2.4199347496032715,
+      "learning_rate": 8.941505399873549e-06,
+      "loss": 0.3722,
+      "step": 430
+    },
+    {
+      "epoch": 0.2974480310968396,
+      "grad_norm": 2.7932002544403076,
+      "learning_rate": 8.86785622384627e-06,
+      "loss": 0.3725,
+      "step": 440
+    },
+    {
+      "epoch": 0.3042082136217678,
+      "grad_norm": 2.3451616764068604,
+      "learning_rate": 8.792055547150413e-06,
+      "loss": 0.368,
+      "step": 450
+    },
+    {
+      "epoch": 0.31096839614669597,
+      "grad_norm": 2.3174757957458496,
+      "learning_rate": 8.714145534022999e-06,
+      "loss": 0.3576,
+      "step": 460
+    },
+    {
+      "epoch": 0.31772857867162413,
+      "grad_norm": 2.2395827770233154,
+      "learning_rate": 8.634169522022522e-06,
+      "loss": 0.3585,
+      "step": 470
+    },
+    {
+      "epoch": 0.3244887611965523,
+      "grad_norm": 2.222054958343506,
+      "learning_rate": 8.552171997922358e-06,
+      "loss": 0.3495,
+      "step": 480
+    },
+    {
+      "epoch": 0.3312489437214805,
+      "grad_norm": 2.371980667114258,
+      "learning_rate": 8.46819857296494e-06,
+      "loss": 0.3662,
+      "step": 490
+    },
+    {
+      "epoch": 0.33800912624640866,
+      "grad_norm": 2.1474437713623047,
+      "learning_rate": 8.382295957490435e-06,
+      "loss": 0.3616,
+      "step": 500
+    },
+    {
+      "epoch": 0.3447693087713368,
+      "grad_norm": 2.476712465286255,
+      "learning_rate": 8.294511934954054e-06,
+      "loss": 0.3595,
+      "step": 510
+    },
+    {
+      "epoch": 0.351529491296265,
+      "grad_norm": 2.175936698913574,
+      "learning_rate": 8.20489533534643e-06,
+      "loss": 0.3549,
+      "step": 520
+    },
+    {
+      "epoch": 0.3582896738211932,
+      "grad_norm": 1.8972084522247314,
+      "learning_rate": 8.113496008031863e-06,
+      "loss": 0.3426,
+      "step": 530
+    },
+    {
+      "epoch": 0.36504985634612136,
+      "grad_norm": 1.9858911037445068,
+      "learning_rate": 8.020364794019546e-06,
+      "loss": 0.351,
+      "step": 540
+    },
+    {
+      "epoch": 0.3718100388710495,
+      "grad_norm": 1.843750238418579,
+      "learning_rate": 7.925553497683169e-06,
+      "loss": 0.3413,
+      "step": 550
+    },
+    {
+      "epoch": 0.3785702213959777,
+      "grad_norm": 2.026078224182129,
+      "learning_rate": 7.829114857944672e-06,
+      "loss": 0.3589,
+      "step": 560
+    },
+    {
+      "epoch": 0.38533040392090584,
+      "grad_norm": 2.246981620788574,
+      "learning_rate": 7.731102518938137e-06,
+      "loss": 0.3483,
+      "step": 570
+    },
+    {
+      "epoch": 0.39209058644583406,
+      "grad_norm": 2.0345938205718994,
+      "learning_rate": 7.631571000170156e-06,
+      "loss": 0.356,
+      "step": 580
+    },
+    {
+      "epoch": 0.3988507689707622,
+      "grad_norm": 2.166692018508911,
+      "learning_rate": 7.530575666193283e-06,
+      "loss": 0.3544,
+      "step": 590
+    },
+    {
+      "epoch": 0.4056109514956904,
+      "grad_norm": 2.0450754165649414,
+      "learning_rate": 7.4281726958094146e-06,
+      "loss": 0.3507,
+      "step": 600
+    },
+    {
+      "epoch": 0.4056109514956904,
+      "eval_loss": 0.35060280561447144,
+      "eval_runtime": 1270.966,
+      "eval_samples_per_second": 4.139,
+      "eval_steps_per_second": 0.518,
+      "step": 600
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 2.1229889392852783,
+      "learning_rate": 7.32441905082026e-06,
+      "loss": 0.3511,
+      "step": 610
+    },
+    {
+      "epoch": 0.41913131654554675,
+      "grad_norm": 1.8597893714904785,
+      "learning_rate": 7.2193724443422405e-06,
+      "loss": 0.3547,
+      "step": 620
+    },
+    {
+      "epoch": 0.4258914990704749,
+      "grad_norm": 1.9739303588867188,
+      "learning_rate": 7.113091308703498e-06,
+      "loss": 0.3313,
+      "step": 630
+    },
+    {
+      "epoch": 0.43265168159540307,
+      "grad_norm": 1.9213026762008667,
+      "learning_rate": 7.005634762940818e-06,
+      "loss": 0.3513,
+      "step": 640
+    },
+    {
+      "epoch": 0.43941186412033123,
+      "grad_norm": 1.9261809587478638,
+      "learning_rate": 6.897062579914587e-06,
+      "loss": 0.3311,
+      "step": 650
+    },
+    {
+      "epoch": 0.44617204664525945,
+      "grad_norm": 1.9443905353546143,
+      "learning_rate": 6.787435153060039e-06,
+      "loss": 0.3335,
+      "step": 660
+    },
+    {
+      "epoch": 0.4529322291701876,
+      "grad_norm": 2.0720746517181396,
+      "learning_rate": 6.676813462793337e-06,
+      "loss": 0.3339,
+      "step": 670
+    },
+    {
+      "epoch": 0.45969241169511577,
+      "grad_norm": 1.9223897457122803,
+      "learning_rate": 6.565259042591112e-06,
+      "loss": 0.3446,
+      "step": 680
+    },
+    {
+      "epoch": 0.4664525942200439,
+      "grad_norm": 2.407301664352417,
+      "learning_rate": 6.452833944762385e-06,
+      "loss": 0.3475,
+      "step": 690
+    },
+    {
+      "epoch": 0.47321277674497214,
+      "grad_norm": 1.946742057800293,
+      "learning_rate": 6.339600705931876e-06,
+      "loss": 0.3274,
+      "step": 700
+    },
+    {
+      "epoch": 0.4799729592699003,
+      "grad_norm": 1.9959310293197632,
+      "learning_rate": 6.225622312253916e-06,
+      "loss": 0.3347,
+      "step": 710
+    },
+    {
+      "epoch": 0.48673314179482846,
+      "grad_norm": 1.8777397871017456,
+      "learning_rate": 6.110962164376309e-06,
+      "loss": 0.3419,
+      "step": 720
+    },
+    {
+      "epoch": 0.4934933243197566,
+      "grad_norm": 2.0931403636932373,
+      "learning_rate": 5.995684042173626e-06,
+      "loss": 0.3344,
+      "step": 730
+    },
+    {
+      "epoch": 0.5002535068446848,
+      "grad_norm": 1.7780061960220337,
+      "learning_rate": 5.8798520692695605e-06,
+      "loss": 0.3115,
+      "step": 740
+    },
+    {
+      "epoch": 0.507013689369613,
+      "grad_norm": 1.8530755043029785,
+      "learning_rate": 5.763530677368065e-06,
+      "loss": 0.3248,
+      "step": 750
+    },
+    {
+      "epoch": 0.5137738718945412,
+      "grad_norm": 2.074946165084839,
+      "learning_rate": 5.64678457041312e-06,
+      "loss": 0.3381,
+      "step": 760
+    },
+    {
+      "epoch": 0.5205340544194693,
+      "grad_norm": 2.1300790309906006,
+      "learning_rate": 5.529678688597081e-06,
+      "loss": 0.3272,
+      "step": 770
+    },
+    {
+      "epoch": 0.5272942369443975,
+      "grad_norm": 1.9701505899429321,
+      "learning_rate": 5.412278172237591e-06,
+      "loss": 0.3283,
+      "step": 780
+    },
+    {
+      "epoch": 0.5340544194693256,
+      "grad_norm": 1.8419865369796753,
+      "learning_rate": 5.294648325543188e-06,
+      "loss": 0.3201,
+      "step": 790
+    },
+    {
+      "epoch": 0.5408146019942538,
+      "grad_norm": 1.948057770729065,
+      "learning_rate": 5.176854580287744e-06,
+      "loss": 0.3065,
+      "step": 800
+    },
+    {
+      "epoch": 0.5408146019942538,
+      "eval_loss": 0.329855740070343,
+      "eval_runtime": 1276.1984,
+      "eval_samples_per_second": 4.122,
+      "eval_steps_per_second": 0.516,
+      "step": 800
+    },
+    {
+      "epoch": 0.5475747845191821,
+      "grad_norm": 1.8223614692687988,
+      "learning_rate": 5.0589624594139455e-06,
+      "loss": 0.3207,
+      "step": 810
+    },
+    {
+      "epoch": 0.5543349670441102,
+      "grad_norm": 2.12894606590271,
+      "learning_rate": 4.941037540586057e-06,
+      "loss": 0.3062,
+      "step": 820
+    },
+    {
+      "epoch": 0.5610951495690384,
+      "grad_norm": 1.7402645349502563,
+      "learning_rate": 4.8231454197122575e-06,
+      "loss": 0.3114,
+      "step": 830
+    },
+    {
+      "epoch": 0.5678553320939665,
+      "grad_norm": 1.9146500825881958,
+      "learning_rate": 4.705351674456813e-06,
+      "loss": 0.3267,
+      "step": 840
+    },
+    {
+      "epoch": 0.5746155146188947,
+      "grad_norm": 1.9016306400299072,
+      "learning_rate": 4.587721827762411e-06,
+      "loss": 0.3231,
+      "step": 850
+    },
+    {
+      "epoch": 0.5813756971438229,
+      "grad_norm": 1.9831342697143555,
+      "learning_rate": 4.47032131140292e-06,
+      "loss": 0.328,
+      "step": 860
+    },
+    {
+      "epoch": 0.588135879668751,
+      "grad_norm": 1.9523651599884033,
+      "learning_rate": 4.353215429586882e-06,
+      "loss": 0.3215,
+      "step": 870
+    },
+    {
+      "epoch": 0.5948960621936792,
+      "grad_norm": 2.0452113151550293,
+      "learning_rate": 4.236469322631938e-06,
+      "loss": 0.328,
+      "step": 880
+    },
+    {
+      "epoch": 0.6016562447186073,
+      "grad_norm": 1.8030444383621216,
+      "learning_rate": 4.12014793073044e-06,
+      "loss": 0.3036,
+      "step": 890
+    },
+    {
+      "epoch": 0.6084164272435356,
+      "grad_norm": 1.8724502325057983,
+      "learning_rate": 4.004315957826375e-06,
+      "loss": 0.3024,
+      "step": 900
+    },
+    {
+      "epoch": 0.6151766097684638,
+      "grad_norm": 1.9722743034362793,
+      "learning_rate": 3.889037835623693e-06,
+      "loss": 0.3144,
+      "step": 910
+    },
+    {
+      "epoch": 0.6219367922933919,
+      "grad_norm": 1.9698827266693115,
+      "learning_rate": 3.7743776877460864e-06,
+      "loss": 0.3228,
+      "step": 920
+    },
+    {
+      "epoch": 0.6286969748183201,
+      "grad_norm": 1.863534688949585,
+      "learning_rate": 3.6603992940681263e-06,
+      "loss": 0.3055,
+      "step": 930
+    },
+    {
+      "epoch": 0.6354571573432483,
+      "grad_norm": 1.9991436004638672,
+      "learning_rate": 3.5471660552376176e-06,
+      "loss": 0.3264,
+      "step": 940
+    },
+    {
+      "epoch": 0.6422173398681764,
+      "grad_norm": 1.981311559677124,
+      "learning_rate": 3.4347409574088896e-06,
+      "loss": 0.316,
+      "step": 950
+    },
+    {
+      "epoch": 0.6489775223931046,
+      "grad_norm": 1.8221795558929443,
+      "learning_rate": 3.323186537206665e-06,
+      "loss": 0.3071,
+      "step": 960
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 1.8596502542495728,
+      "learning_rate": 3.2125648469399628e-06,
+      "loss": 0.3193,
+      "step": 970
+    },
+    {
+      "epoch": 0.662497887442961,
+      "grad_norm": 1.6564629077911377,
+      "learning_rate": 3.1029374200854167e-06,
+      "loss": 0.3001,
+      "step": 980
+    },
+    {
+      "epoch": 0.6692580699678892,
+      "grad_norm": 2.0445966720581055,
+      "learning_rate": 2.9943652370591835e-06,
+      "loss": 0.3059,
+      "step": 990
+    },
+    {
+      "epoch": 0.6760182524928173,
+      "grad_norm": 1.694770336151123,
+      "learning_rate": 2.886908691296504e-06,
+      "loss": 0.3042,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6760182524928173,
+      "eval_loss": 0.30882763862609863,
+      "eval_runtime": 1270.5948,
+      "eval_samples_per_second": 4.14,
+      "eval_steps_per_second": 0.518,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6827784350177455,
+      "grad_norm": 2.0789783000946045,
+      "learning_rate": 2.7806275556577624e-06,
+      "loss": 0.3064,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6895386175426736,
+      "grad_norm": 1.8919354677200317,
+      "learning_rate": 2.6755809491797426e-06,
+      "loss": 0.3103,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6962988000676018,
+      "grad_norm": 1.8415489196777344,
+      "learning_rate": 2.5718273041905863e-06,
+      "loss": 0.2969,
+      "step": 1030
+    },
+    {
+      "epoch": 0.70305898259253,
+      "grad_norm": 1.8690521717071533,
+      "learning_rate": 2.469424333806718e-06,
+      "loss": 0.3062,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7098191651174581,
+      "grad_norm": 2.0415210723876953,
+      "learning_rate": 2.3684289998298453e-06,
+      "loss": 0.317,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7165793476423864,
+      "grad_norm": 1.8409037590026855,
+      "learning_rate": 2.268897481061863e-06,
+      "loss": 0.2845,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7233395301673146,
+      "grad_norm": 2.023800849914551,
+      "learning_rate": 2.1708851420553277e-06,
+      "loss": 0.3041,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7300997126922427,
+      "grad_norm": 1.9210608005523682,
+      "learning_rate": 2.0744465023168313e-06,
+      "loss": 0.3023,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7368598952171709,
+      "grad_norm": 1.8132646083831787,
+      "learning_rate": 1.9796352059804565e-06,
+      "loss": 0.3089,
+      "step": 1090
+    },
+    {
+      "epoch": 0.743620077742099,
+      "grad_norm": 1.9919142723083496,
+      "learning_rate": 1.8865039919681377e-06,
+      "loss": 0.2941,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7503802602670272,
+      "grad_norm": 2.0446407794952393,
+      "learning_rate": 1.7951046646535714e-06,
+      "loss": 0.2856,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7571404427919554,
+      "grad_norm": 2.0371832847595215,
+      "learning_rate": 1.705488065045946e-06,
+      "loss": 0.2919,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7639006253168835,
+      "grad_norm": 1.980812430381775,
+      "learning_rate": 1.6177040425095664e-06,
+      "loss": 0.2985,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7706608078418117,
+      "grad_norm": 1.756753921508789,
+      "learning_rate": 1.5318014270350617e-06,
+      "loss": 0.2893,
+      "step": 1140
+    },
+    {
+      "epoch": 0.77742099036674,
+      "grad_norm": 1.7378242015838623,
+      "learning_rate": 1.4478280020776442e-06,
+      "loss": 0.2862,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7841811728916681,
+      "grad_norm": 1.8673665523529053,
+      "learning_rate": 1.3658304779774784e-06,
+      "loss": 0.2967,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7909413554165963,
+      "grad_norm": 2.001669406890869,
+      "learning_rate": 1.2858544659770001e-06,
+      "loss": 0.2924,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7977015379415244,
+      "grad_norm": 2.087536573410034,
+      "learning_rate": 1.2079444528495887e-06,
+      "loss": 0.2921,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8044617204664526,
+      "grad_norm": 1.8734593391418457,
+      "learning_rate": 1.1321437761537307e-06,
+      "loss": 0.2805,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8112219029913807,
+      "grad_norm": 1.8164645433425903,
+      "learning_rate": 1.0584946001264523e-06,
+      "loss": 0.2977,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8112219029913807,
+      "eval_loss": 0.294592946767807,
+      "eval_runtime": 1271.0164,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 0.518,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8179820855163089,
+      "grad_norm": 1.854030966758728,
+      "learning_rate": 9.870378922293855e-07,
+      "loss": 0.2859,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.7828032970428467,
+      "learning_rate": 9.178134003605721e-07,
+      "loss": 0.2916,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8315024505661653,
+      "grad_norm": 2.0216519832611084,
+      "learning_rate": 8.508596307446254e-07,
+      "loss": 0.2867,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8382626330910935,
+      "grad_norm": 1.7878661155700684,
+      "learning_rate": 7.862138265135983e-07,
+      "loss": 0.2886,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8450228156160217,
+      "grad_norm": 1.789251685142517,
+      "learning_rate": 7.239119469904227e-07,
+      "loss": 0.2814,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8517829981409498,
+      "grad_norm": 1.7281427383422852,
+      "learning_rate": 6.639886476864993e-07,
+      "loss": 0.2806,
+      "step": 1260
+    },
+    {
+      "epoch": 0.858543180665878,
+      "grad_norm": 1.7876800298690796,
+      "learning_rate": 6.064772610245051e-07,
+      "loss": 0.2778,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8653033631908061,
+      "grad_norm": 1.909987449645996,
+      "learning_rate": 5.514097777971939e-07,
+      "loss": 0.2966,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8720635457157343,
+      "grad_norm": 1.9117987155914307,
+      "learning_rate": 4.988168293724654e-07,
+      "loss": 0.2858,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8788237282406625,
+      "grad_norm": 1.9773385524749756,
+      "learning_rate": 4.4872767065462787e-07,
+      "loss": 0.2871,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8855839107655906,
+      "grad_norm": 1.7200452089309692,
+      "learning_rate": 4.0117016381130636e-07,
+      "loss": 0.2982,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8923440932905189,
+      "grad_norm": 1.9773083925247192,
+      "learning_rate": 3.561707627750827e-07,
+      "loss": 0.2772,
+      "step": 1320
+    },
+    {
+      "epoch": 0.899104275815447,
+      "grad_norm": 1.8127182722091675,
+      "learning_rate": 3.137544985284441e-07,
+      "loss": 0.2939,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9058644583403752,
+      "grad_norm": 1.8259408473968506,
+      "learning_rate": 2.739449651802756e-07,
+      "loss": 0.2912,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9126246408653034,
+      "grad_norm": 1.96041738986969,
+      "learning_rate": 2.3676430684159035e-07,
+      "loss": 0.28,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9193848233902315,
+      "grad_norm": 2.008439302444458,
+      "learning_rate": 2.0223320530784574e-07,
+      "loss": 0.2832,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9261450059151597,
+      "grad_norm": 1.8017557859420776,
+      "learning_rate": 1.7037086855465902e-07,
+      "loss": 0.2857,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9329051884400879,
+      "grad_norm": 1.8403921127319336,
+      "learning_rate": 1.4119502005334185e-07,
+      "loss": 0.2933,
+      "step": 1380
+    },
+    {
+      "epoch": 0.939665370965016,
+      "grad_norm": 1.755980134010315,
+      "learning_rate": 1.1472188891219816e-07,
+      "loss": 0.289,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9464255534899443,
+      "grad_norm": 1.820554256439209,
+      "learning_rate": 9.096620084905472e-08,
+      "loss": 0.2908,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9464255534899443,
+      "eval_loss": 0.2895006537437439,
+      "eval_runtime": 1270.2472,
+      "eval_samples_per_second": 4.141,
+      "eval_steps_per_second": 0.518,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9531857360148724,
+      "grad_norm": 2.062675952911377,
+      "learning_rate": 6.994117000006185e-08,
+      "loss": 0.2998,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9599459185398006,
+      "grad_norm": 1.8810018301010132,
+      "learning_rate": 5.165849156930969e-08,
+      "loss": 0.276,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9667061010647288,
+      "grad_norm": 2.032048225402832,
+      "learning_rate": 3.6128335323353804e-08,
+      "loss": 0.2761,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9734662835896569,
+      "grad_norm": 1.843258023262024,
+      "learning_rate": 2.335933993426687e-08,
+      "loss": 0.2995,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9802264661145851,
+      "grad_norm": 1.7969026565551758,
+      "learning_rate": 1.3358608174368626e-08,
+      "loss": 0.2772,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9869866486395132,
+      "grad_norm": 2.0245614051818848,
+      "learning_rate": 6.1317029652929734e-09,
+      "loss": 0.3069,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9937468311644414,
+      "grad_norm": 1.9319560527801514,
+      "learning_rate": 1.6826442836082035e-09,
+      "loss": 0.2764,
+      "step": 1470
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.367832660675049,
+      "learning_rate": 1.3906924697382195e-11,
+      "loss": 0.2913,
+      "step": 1480
+    },
+    {
+      "epoch": 1.0,
+      "step": 1480,
+      "total_flos": 760407761879040.0,
+      "train_loss": 0.35166695085731714,
+      "train_runtime": 62991.4895,
+      "train_samples_per_second": 0.751,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 760407761879040.0,
+  "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 sha256:288c92ba91cd7fdbd3e9389521d6f428fda05e7611ccee94b3952dee6d1814f2
+size 8273