Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+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_3b/README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: web_policy_sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# web_policy_sft
+
+This model is a fine-tuned version of [/data/hzy/models--Qwen--Qwen2.5-3B-Instruct/snapshots/aa8e72537993ba99e69dfaafa59ed015b17504d1](https://huggingface.co//data/hzy/models--Qwen--Qwen2.5-3B-Instruct/snapshots/aa8e72537993ba99e69dfaafa59ed015b17504d1) on the web_policy_sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1625
+
+## 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: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 2
+- optimizer: Use OptimizerNames.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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5121        | 0.0470 | 50   | 0.4876          |
+| 0.4615        | 0.0940 | 100  | 0.3849          |
+| 0.37          | 0.1409 | 150  | 0.3281          |
+| 0.3749        | 0.1879 | 200  | 0.2892          |
+| 0.2863        | 0.2349 | 250  | 0.2757          |
+| 0.3078        | 0.2819 | 300  | 0.2549          |
+| 0.2921        | 0.3289 | 350  | 0.2316          |
+| 0.3191        | 0.3759 | 400  | 0.2353          |
+| 0.313         | 0.4228 | 450  | 0.2231          |
+| 0.2037        | 0.4698 | 500  | 0.2138          |
+| 0.1729        | 0.5168 | 550  | 0.2074          |
+| 0.289         | 0.5638 | 600  | 0.1954          |
+| 0.2775        | 0.6108 | 650  | 0.1897          |
+| 0.1546        | 0.6577 | 700  | 0.1814          |
+| 0.1613        | 0.7047 | 750  | 0.1746          |
+| 0.0956        | 0.7517 | 800  | 0.1725          |
+| 0.1692        | 0.7987 | 850  | 0.1683          |
+| 0.1885        | 0.8457 | 900  | 0.1653          |
+| 0.2799        | 0.8926 | 950  | 0.1637          |
+| 0.1971        | 0.9396 | 1000 | 0.1628          |
+| 0.1464        | 0.9866 | 1050 | 0.1626          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

web_rl_3b/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
+}

web_rl_3b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.16246147453784943,
+    "eval_runtime": 519.0801,
+    "eval_samples_per_second": 1.822,
+    "eval_steps_per_second": 0.911,
+    "total_flos": 57141526265856.0,
+    "train_loss": 0.2802479102018294,
+    "train_runtime": 34553.4877,
+    "train_samples_per_second": 0.246,
+    "train_steps_per_second": 0.031
+}

web_rl_3b/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 %}

web_rl_3b/checkpoint-1065/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
+}

web_rl_3b/checkpoint-1065/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 %}

web_rl_3b/checkpoint-1065/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

web_rl_3b/checkpoint-1065/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"
+}

web_rl_3b/checkpoint-1065/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bae34d001b0178e721fae3c92aa1abf3a047088cfe7f32947c9fff27df183d
+size 4957560304

web_rl_3b/checkpoint-1065/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd94dd66bb8aa93760dfc0c3ba73d9a7c7566ee65e461e3d59caebc6b131fd92
+size 1214366696

web_rl_3b/checkpoint-1065/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_parameters": 241664,
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

web_rl_3b/checkpoint-1065/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
+  }
+}

web_rl_3b/checkpoint-1065/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

web_rl_3b/checkpoint-1065/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
+}

web_rl_3b/checkpoint-1065/trainer_state.json

@@ -0,0 +1,944 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 1065,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009396288466055908,
+      "grad_norm": 77.32342529296875,
+      "learning_rate": 8.411214953271029e-07,
+      "loss": 1.6798,
+      "step": 10
+    },
+    {
+      "epoch": 0.018792576932111817,
+      "grad_norm": 33.60771179199219,
+      "learning_rate": 1.7757009345794394e-06,
+      "loss": 1.4918,
+      "step": 20
+    },
+    {
+      "epoch": 0.028188865398167725,
+      "grad_norm": 15.923619270324707,
+      "learning_rate": 2.7102803738317757e-06,
+      "loss": 0.832,
+      "step": 30
+    },
+    {
+      "epoch": 0.03758515386422363,
+      "grad_norm": 25.03349494934082,
+      "learning_rate": 3.6448598130841123e-06,
+      "loss": 0.6918,
+      "step": 40
+    },
+    {
+      "epoch": 0.04698144233027954,
+      "grad_norm": 10.101052284240723,
+      "learning_rate": 4.579439252336449e-06,
+      "loss": 0.5121,
+      "step": 50
+    },
+    {
+      "epoch": 0.04698144233027954,
+      "eval_loss": 0.4876191020011902,
+      "eval_runtime": 472.5825,
+      "eval_samples_per_second": 2.002,
+      "eval_steps_per_second": 1.001,
+      "step": 50
+    },
+    {
+      "epoch": 0.05637773079633545,
+      "grad_norm": 8.925775527954102,
+      "learning_rate": 5.514018691588785e-06,
+      "loss": 0.4886,
+      "step": 60
+    },
+    {
+      "epoch": 0.06577401926239136,
+      "grad_norm": 7.684209823608398,
+      "learning_rate": 6.448598130841122e-06,
+      "loss": 0.4985,
+      "step": 70
+    },
+    {
+      "epoch": 0.07517030772844727,
+      "grad_norm": 14.134685516357422,
+      "learning_rate": 7.383177570093458e-06,
+      "loss": 0.3483,
+      "step": 80
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 9.419997215270996,
+      "learning_rate": 8.317757009345795e-06,
+      "loss": 0.2995,
+      "step": 90
+    },
+    {
+      "epoch": 0.09396288466055908,
+      "grad_norm": 9.725701332092285,
+      "learning_rate": 9.252336448598132e-06,
+      "loss": 0.4615,
+      "step": 100
+    },
+    {
+      "epoch": 0.09396288466055908,
+      "eval_loss": 0.3848985433578491,
+      "eval_runtime": 485.2521,
+      "eval_samples_per_second": 1.95,
+      "eval_steps_per_second": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 7.37769889831543,
+      "learning_rate": 9.999892460708615e-06,
+      "loss": 0.372,
+      "step": 110
+    },
+    {
+      "epoch": 0.1127554615926709,
+      "grad_norm": 5.251932144165039,
+      "learning_rate": 9.996129071205167e-06,
+      "loss": 0.3499,
+      "step": 120
+    },
+    {
+      "epoch": 0.1221517500587268,
+      "grad_norm": 6.633662700653076,
+      "learning_rate": 9.98699334211771e-06,
+      "loss": 0.3497,
+      "step": 130
+    },
+    {
+      "epoch": 0.13154803852478272,
+      "grad_norm": 9.925003051757812,
+      "learning_rate": 9.972495097099379e-06,
+      "loss": 0.3527,
+      "step": 140
+    },
+    {
+      "epoch": 0.14094432699083861,
+      "grad_norm": 2.5581600666046143,
+      "learning_rate": 9.952649926118827e-06,
+      "loss": 0.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.14094432699083861,
+      "eval_loss": 0.32813695073127747,
+      "eval_runtime": 450.9285,
+      "eval_samples_per_second": 2.098,
+      "eval_steps_per_second": 1.049,
+      "step": 150
+    },
+    {
+      "epoch": 0.15034061545689453,
+      "grad_norm": 8.05836009979248,
+      "learning_rate": 9.927479168696327e-06,
+      "loss": 0.4364,
+      "step": 160
+    },
+    {
+      "epoch": 0.15973690392295042,
+      "grad_norm": 8.204833984375,
+      "learning_rate": 9.897009890957382e-06,
+      "loss": 0.3828,
+      "step": 170
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 4.883147716522217,
+      "learning_rate": 9.861274856528504e-06,
+      "loss": 0.3503,
+      "step": 180
+    },
+    {
+      "epoch": 0.17852948085506226,
+      "grad_norm": 4.023066520690918,
+      "learning_rate": 9.820312491306471e-06,
+      "loss": 0.4124,
+      "step": 190
+    },
+    {
+      "epoch": 0.18792576932111815,
+      "grad_norm": 3.1607863903045654,
+      "learning_rate": 9.77416684213896e-06,
+      "loss": 0.3749,
+      "step": 200
+    },
+    {
+      "epoch": 0.18792576932111815,
+      "eval_loss": 0.2891885042190552,
+      "eval_runtime": 458.85,
+      "eval_samples_per_second": 2.062,
+      "eval_steps_per_second": 1.031,
+      "step": 200
+    },
+    {
+      "epoch": 0.19732205778717407,
+      "grad_norm": 9.990116119384766,
+      "learning_rate": 9.722887529460928e-06,
+      "loss": 0.235,
+      "step": 210
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 4.4412760734558105,
+      "learning_rate": 9.666529693937763e-06,
+      "loss": 0.2777,
+      "step": 220
+    },
+    {
+      "epoch": 0.21611463471928588,
+      "grad_norm": 5.4278154373168945,
+      "learning_rate": 9.605153937172495e-06,
+      "loss": 0.3091,
+      "step": 230
+    },
+    {
+      "epoch": 0.2255109231853418,
+      "grad_norm": 4.043374061584473,
+      "learning_rate": 9.538826256540866e-06,
+      "loss": 0.287,
+      "step": 240
+    },
+    {
+      "epoch": 0.2349072116513977,
+      "grad_norm": 5.319589614868164,
+      "learning_rate": 9.467617974224326e-06,
+      "loss": 0.2863,
+      "step": 250
+    },
+    {
+      "epoch": 0.2349072116513977,
+      "eval_loss": 0.2756798267364502,
+      "eval_runtime": 504.1073,
+      "eval_samples_per_second": 1.877,
+      "eval_steps_per_second": 0.938,
+      "step": 250
+    },
+    {
+      "epoch": 0.2443035001174536,
+      "grad_norm": 8.62342643737793,
+      "learning_rate": 9.391605660517268e-06,
+      "loss": 0.2357,
+      "step": 260
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 2.7996938228607178,
+      "learning_rate": 9.310871051490953e-06,
+      "loss": 0.2237,
+      "step": 270
+    },
+    {
+      "epoch": 0.26309607704956545,
+      "grad_norm": 4.890498638153076,
+      "learning_rate": 9.225500961102685e-06,
+      "loss": 0.2974,
+      "step": 280
+    },
+    {
+      "epoch": 0.27249236551562134,
+      "grad_norm": 5.307254314422607,
+      "learning_rate": 9.135587187844727e-06,
+      "loss": 0.2556,
+      "step": 290
+    },
+    {
+      "epoch": 0.28188865398167723,
+      "grad_norm": 4.411228656768799,
+      "learning_rate": 9.041226416033344e-06,
+      "loss": 0.3078,
+      "step": 300
+    },
+    {
+      "epoch": 0.28188865398167723,
+      "eval_loss": 0.25494658946990967,
+      "eval_runtime": 518.8808,
+      "eval_samples_per_second": 1.823,
+      "eval_steps_per_second": 0.912,
+      "step": 300
+    },
+    {
+      "epoch": 0.2912849424477331,
+      "grad_norm": 2.772766351699829,
+      "learning_rate": 8.942520111844117e-06,
+      "loss": 0.2227,
+      "step": 310
+    },
+    {
+      "epoch": 0.30068123091378907,
+      "grad_norm": 5.582266807556152,
+      "learning_rate": 8.839574414205335e-06,
+      "loss": 0.2668,
+      "step": 320
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 4.721141815185547,
+      "learning_rate": 8.732500020666748e-06,
+      "loss": 0.2726,
+      "step": 330
+    },
+    {
+      "epoch": 0.31947380784590085,
+      "grad_norm": 4.359829425811768,
+      "learning_rate": 8.621412068366455e-06,
+      "loss": 0.2807,
+      "step": 340
+    },
+    {
+      "epoch": 0.3288700963119568,
+      "grad_norm": 2.9552581310272217,
+      "learning_rate": 8.506430010223899e-06,
+      "loss": 0.2921,
+      "step": 350
+    },
+    {
+      "epoch": 0.3288700963119568,
+      "eval_loss": 0.23158399760723114,
+      "eval_runtime": 528.3567,
+      "eval_samples_per_second": 1.79,
+      "eval_steps_per_second": 0.895,
+      "step": 350
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 4.709650039672852,
+      "learning_rate": 8.38767748649208e-06,
+      "loss": 0.306,
+      "step": 360
+    },
+    {
+      "epoch": 0.3476626732440686,
+      "grad_norm": 2.7597694396972656,
+      "learning_rate": 8.26528219180716e-06,
+      "loss": 0.2148,
+      "step": 370
+    },
+    {
+      "epoch": 0.3570589617101245,
+      "grad_norm": 6.239573001861572,
+      "learning_rate": 8.139375737878356e-06,
+      "loss": 0.1558,
+      "step": 380
+    },
+    {
+      "epoch": 0.3664552501761804,
+      "grad_norm": 2.6109910011291504,
+      "learning_rate": 8.01009351196582e-06,
+      "loss": 0.1945,
+      "step": 390
+    },
+    {
+      "epoch": 0.3758515386422363,
+      "grad_norm": 5.080913543701172,
+      "learning_rate": 7.877574531298666e-06,
+      "loss": 0.3191,
+      "step": 400
+    },
+    {
+      "epoch": 0.3758515386422363,
+      "eval_loss": 0.23533165454864502,
+      "eval_runtime": 491.1933,
+      "eval_samples_per_second": 1.926,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.38524782710829225,
+      "grad_norm": 3.903905153274536,
+      "learning_rate": 7.741961293589693e-06,
+      "loss": 0.2265,
+      "step": 410
+    },
+    {
+      "epoch": 0.39464411557434814,
+      "grad_norm": 5.586989879608154,
+      "learning_rate": 7.603399623807519e-06,
+      "loss": 0.2608,
+      "step": 420
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 3.9632835388183594,
+      "learning_rate": 7.462038517370962e-06,
+      "loss": 0.2456,
+      "step": 430
+    },
+    {
+      "epoch": 0.4134366925064599,
+      "grad_norm": 7.482256889343262,
+      "learning_rate": 7.318029979934181e-06,
+      "loss": 0.2898,
+      "step": 440
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "grad_norm": 3.7885382175445557,
+      "learning_rate": 7.17152886393495e-06,
+      "loss": 0.313,
+      "step": 450
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "eval_loss": 0.22310128808021545,
+      "eval_runtime": 516.4179,
+      "eval_samples_per_second": 1.832,
+      "eval_steps_per_second": 0.916,
+      "step": 450
+    },
+    {
+      "epoch": 0.43222926943857176,
+      "grad_norm": 4.9588093757629395,
+      "learning_rate": 7.022692702081766e-06,
+      "loss": 0.2691,
+      "step": 460
+    },
+    {
+      "epoch": 0.44162555790462765,
+      "grad_norm": 4.674664497375488,
+      "learning_rate": 6.871681537958862e-06,
+      "loss": 0.2254,
+      "step": 470
+    },
+    {
+      "epoch": 0.4510218463706836,
+      "grad_norm": 5.224850654602051,
+      "learning_rate": 6.718657753931284e-06,
+      "loss": 0.2315,
+      "step": 480
+    },
+    {
+      "epoch": 0.4604181348367395,
+      "grad_norm": 4.065497398376465,
+      "learning_rate": 6.56378589653506e-06,
+      "loss": 0.2944,
+      "step": 490
+    },
+    {
+      "epoch": 0.4698144233027954,
+      "grad_norm": 4.546512603759766,
+      "learning_rate": 6.40723249954025e-06,
+      "loss": 0.2037,
+      "step": 500
+    },
+    {
+      "epoch": 0.4698144233027954,
+      "eval_loss": 0.213790163397789,
+      "eval_runtime": 486.7052,
+      "eval_samples_per_second": 1.944,
+      "eval_steps_per_second": 0.972,
+      "step": 500
+    },
+    {
+      "epoch": 0.4792107117688513,
+      "grad_norm": 3.3908934593200684,
+      "learning_rate": 6.2491659048771215e-06,
+      "loss": 0.2189,
+      "step": 510
+    },
+    {
+      "epoch": 0.4886070002349072,
+      "grad_norm": 4.911809921264648,
+      "learning_rate": 6.089756081617987e-06,
+      "loss": 0.222,
+      "step": 520
+    },
+    {
+      "epoch": 0.4980032887009631,
+      "grad_norm": 2.711010694503784,
+      "learning_rate": 5.929174443209416e-06,
+      "loss": 0.2179,
+      "step": 530
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 3.0764307975769043,
+      "learning_rate": 5.767593663151265e-06,
+      "loss": 0.2111,
+      "step": 540
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "grad_norm": 4.922618389129639,
+      "learning_rate": 5.605187489320815e-06,
+      "loss": 0.1729,
+      "step": 550
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "eval_loss": 0.20741979777812958,
+      "eval_runtime": 508.5854,
+      "eval_samples_per_second": 1.86,
+      "eval_steps_per_second": 0.93,
+      "step": 550
+    },
+    {
+      "epoch": 0.5261921540991309,
+      "grad_norm": 3.6055169105529785,
+      "learning_rate": 5.442130557141595e-06,
+      "loss": 0.1785,
+      "step": 560
+    },
+    {
+      "epoch": 0.5355884425651868,
+      "grad_norm": 4.116625785827637,
+      "learning_rate": 5.278598201797844e-06,
+      "loss": 0.1761,
+      "step": 570
+    },
+    {
+      "epoch": 0.5449847310312427,
+      "grad_norm": 6.054320335388184,
+      "learning_rate": 5.1147662696965254e-06,
+      "loss": 0.2185,
+      "step": 580
+    },
+    {
+      "epoch": 0.5543810194972986,
+      "grad_norm": 3.523534059524536,
+      "learning_rate": 4.9508109293796015e-06,
+      "loss": 0.211,
+      "step": 590
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "grad_norm": 6.204962730407715,
+      "learning_rate": 4.7869084820899455e-06,
+      "loss": 0.289,
+      "step": 600
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "eval_loss": 0.1954464614391327,
+      "eval_runtime": 498.5386,
+      "eval_samples_per_second": 1.898,
+      "eval_steps_per_second": 0.949,
+      "step": 600
+    },
+    {
+      "epoch": 0.5731735964294103,
+      "grad_norm": 4.921229839324951,
+      "learning_rate": 4.623235172194532e-06,
+      "loss": 0.2154,
+      "step": 610
+    },
+    {
+      "epoch": 0.5825698848954662,
+      "grad_norm": 4.28684139251709,
+      "learning_rate": 4.459966997668812e-06,
+      "loss": 0.2147,
+      "step": 620
+    },
+    {
+      "epoch": 0.5919661733615222,
+      "grad_norm": 4.43740177154541,
+      "learning_rate": 4.297279520846002e-06,
+      "loss": 0.1491,
+      "step": 630
+    },
+    {
+      "epoch": 0.6013624618275781,
+      "grad_norm": 6.9565863609313965,
+      "learning_rate": 4.135347679634849e-06,
+      "loss": 0.2285,
+      "step": 640
+    },
+    {
+      "epoch": 0.610758750293634,
+      "grad_norm": 1.496799349784851,
+      "learning_rate": 3.974345599408833e-06,
+      "loss": 0.2775,
+      "step": 650
+    },
+    {
+      "epoch": 0.610758750293634,
+      "eval_loss": 0.18974561989307404,
+      "eval_runtime": 488.3923,
+      "eval_samples_per_second": 1.937,
+      "eval_steps_per_second": 0.968,
+      "step": 650
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 2.838442087173462,
+      "learning_rate": 3.814446405769069e-06,
+      "loss": 0.214,
+      "step": 660
+    },
+    {
+      "epoch": 0.6295513272257458,
+      "grad_norm": 7.474781513214111,
+      "learning_rate": 3.6558220383822824e-06,
+      "loss": 0.2392,
+      "step": 670
+    },
+    {
+      "epoch": 0.6389476156918017,
+      "grad_norm": 5.7680511474609375,
+      "learning_rate": 3.4986430660940283e-06,
+      "loss": 0.2062,
+      "step": 680
+    },
+    {
+      "epoch": 0.6483439041578577,
+      "grad_norm": 3.3340532779693604,
+      "learning_rate": 3.3430785035159297e-06,
+      "loss": 0.1738,
+      "step": 690
+    },
+    {
+      "epoch": 0.6577401926239136,
+      "grad_norm": 2.487337350845337,
+      "learning_rate": 3.1892956292842103e-06,
+      "loss": 0.1546,
+      "step": 700
+    },
+    {
+      "epoch": 0.6577401926239136,
+      "eval_loss": 0.18141551315784454,
+      "eval_runtime": 504.0426,
+      "eval_samples_per_second": 1.877,
+      "eval_steps_per_second": 0.938,
+      "step": 700
+    },
+    {
+      "epoch": 0.6671364810899695,
+      "grad_norm": 4.324577331542969,
+      "learning_rate": 3.0374598061848936e-06,
+      "loss": 0.2037,
+      "step": 710
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 3.728818893432617,
+      "learning_rate": 2.8877343033391523e-06,
+      "loss": 0.14,
+      "step": 720
+    },
+    {
+      "epoch": 0.6859290580220813,
+      "grad_norm": 3.1286537647247314,
+      "learning_rate": 2.7402801206399454e-06,
+      "loss": 0.1721,
+      "step": 730
+    },
+    {
+      "epoch": 0.6953253464881372,
+      "grad_norm": 7.396164417266846,
+      "learning_rate": 2.595255815628774e-06,
+      "loss": 0.2586,
+      "step": 740
+    },
+    {
+      "epoch": 0.704721634954193,
+      "grad_norm": 1.8540730476379395,
+      "learning_rate": 2.4528173329986855e-06,
+      "loss": 0.1613,
+      "step": 750
+    },
+    {
+      "epoch": 0.704721634954193,
+      "eval_loss": 0.1746373176574707,
+      "eval_runtime": 482.272,
+      "eval_samples_per_second": 1.962,
+      "eval_steps_per_second": 0.981,
+      "step": 750
+    },
+    {
+      "epoch": 0.714117923420249,
+      "grad_norm": 1.6450875997543335,
+      "learning_rate": 2.313117836906897e-06,
+      "loss": 0.2041,
+      "step": 760
+    },
+    {
+      "epoch": 0.7235142118863049,
+      "grad_norm": 1.6683011054992676,
+      "learning_rate": 2.1763075462773002e-06,
+      "loss": 0.2033,
+      "step": 770
+    },
+    {
+      "epoch": 0.7329105003523608,
+      "grad_norm": 5.101831912994385,
+      "learning_rate": 2.0425335732700075e-06,
+      "loss": 0.2497,
+      "step": 780
+    },
+    {
+      "epoch": 0.7423067888184167,
+      "grad_norm": 10.428893089294434,
+      "learning_rate": 1.9119397650915774e-06,
+      "loss": 0.2354,
+      "step": 790
+    },
+    {
+      "epoch": 0.7517030772844726,
+      "grad_norm": 3.380574941635132,
+      "learning_rate": 1.7846665493160548e-06,
+      "loss": 0.0956,
+      "step": 800
+    },
+    {
+      "epoch": 0.7517030772844726,
+      "eval_loss": 0.1724964827299118,
+      "eval_runtime": 494.611,
+      "eval_samples_per_second": 1.913,
+      "eval_steps_per_second": 0.956,
+      "step": 800
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 3.29054594039917,
+      "learning_rate": 1.6608507828831572e-06,
+      "loss": 0.1711,
+      "step": 810
+    },
+    {
+      "epoch": 0.7704956542165845,
+      "grad_norm": 1.7452706098556519,
+      "learning_rate": 1.5406256049359359e-06,
+      "loss": 0.2362,
+      "step": 820
+    },
+    {
+      "epoch": 0.7798919426826404,
+      "grad_norm": 3.282259464263916,
+      "learning_rate": 1.4241202936562164e-06,
+      "loss": 0.1692,
+      "step": 830
+    },
+    {
+      "epoch": 0.7892882311486963,
+      "grad_norm": 2.6481103897094727,
+      "learning_rate": 1.311460127251708e-06,
+      "loss": 0.1608,
+      "step": 840
+    },
+    {
+      "epoch": 0.7986845196147522,
+      "grad_norm": 4.806708335876465,
+      "learning_rate": 1.202766249244306e-06,
+      "loss": 0.1692,
+      "step": 850
+    },
+    {
+      "epoch": 0.7986845196147522,
+      "eval_loss": 0.1683204621076584,
+      "eval_runtime": 536.8401,
+      "eval_samples_per_second": 1.762,
+      "eval_steps_per_second": 0.881,
+      "step": 850
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 3.949918031692505,
+      "learning_rate": 1.098155538204404e-06,
+      "loss": 0.1718,
+      "step": 860
+    },
+    {
+      "epoch": 0.817477096546864,
+      "grad_norm": 4.87109899520874,
+      "learning_rate": 9.977404820713315e-07,
+      "loss": 0.1425,
+      "step": 870
+    },
+    {
+      "epoch": 0.8268733850129198,
+      "grad_norm": 2.2142727375030518,
+      "learning_rate": 9.016290571950171e-07,
+      "loss": 0.1196,
+      "step": 880
+    },
+    {
+      "epoch": 0.8362696734789759,
+      "grad_norm": 1.4838513135910034,
+      "learning_rate": 8.099246122289861e-07,
+      "loss": 0.2077,
+      "step": 890
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 3.8143913745880127,
+      "learning_rate": 7.227257569995061e-07,
+      "loss": 0.1885,
+      "step": 900
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "eval_loss": 0.16525517404079437,
+      "eval_runtime": 525.2309,
+      "eval_samples_per_second": 1.801,
+      "eval_steps_per_second": 0.901,
+      "step": 900
+    },
+    {
+      "epoch": 0.8550622504110876,
+      "grad_norm": 4.804526329040527,
+      "learning_rate": 6.401262564704019e-07,
+      "loss": 0.2379,
+      "step": 910
+    },
+    {
+      "epoch": 0.8644585388771435,
+      "grad_norm": 4.881964683532715,
+      "learning_rate": 5.622149299175539e-07,
+      "loss": 0.2253,
+      "step": 920
+    },
+    {
+      "epoch": 0.8738548273431994,
+      "grad_norm": 3.667691230773926,
+      "learning_rate": 4.890755554214954e-07,
+      "loss": 0.1952,
+      "step": 930
+    },
+    {
+      "epoch": 0.8832511158092553,
+      "grad_norm": 2.946258306503296,
+      "learning_rate": 4.207867797808102e-07,
+      "loss": 0.1522,
+      "step": 940
+    },
+    {
+      "epoch": 0.8926474042753113,
+      "grad_norm": 6.754327774047852,
+      "learning_rate": 3.5742203394319606e-07,
+      "loss": 0.2799,
+      "step": 950
+    },
+    {
+      "epoch": 0.8926474042753113,
+      "eval_loss": 0.163659006357193,
+      "eval_runtime": 541.8924,
+      "eval_samples_per_second": 1.746,
+      "eval_steps_per_second": 0.873,
+      "step": 950
+    },
+    {
+      "epoch": 0.9020436927413672,
+      "grad_norm": 6.084792137145996,
+      "learning_rate": 2.9904945404513606e-07,
+      "loss": 0.173,
+      "step": 960
+    },
+    {
+      "epoch": 0.9114399812074231,
+      "grad_norm": 7.379616737365723,
+      "learning_rate": 2.457318081450899e-07,
+      "loss": 0.184,
+      "step": 970
+    },
+    {
+      "epoch": 0.920836269673479,
+      "grad_norm": 1.6431665420532227,
+      "learning_rate": 1.9752642872897078e-07,
+      "loss": 0.1533,
+      "step": 980
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 2.5774223804473877,
+      "learning_rate": 1.5448515106050165e-07,
+      "loss": 0.2073,
+      "step": 990
+    },
+    {
+      "epoch": 0.9396288466055908,
+      "grad_norm": 3.7589077949523926,
+      "learning_rate": 1.166542574427354e-07,
+      "loss": 0.1971,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9396288466055908,
+      "eval_loss": 0.16281382739543915,
+      "eval_runtime": 517.5907,
+      "eval_samples_per_second": 1.828,
+      "eval_steps_per_second": 0.914,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9490251350716467,
+      "grad_norm": 2.6644127368927,
+      "learning_rate": 8.407442745067552e-08,
+      "loss": 0.1787,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9584214235377027,
+      "grad_norm": 2.4552407264709473,
+      "learning_rate": 5.678069418851351e-08,
+      "loss": 0.1581,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9678177120037585,
+      "grad_norm": 4.062498569488525,
+      "learning_rate": 3.4802406618518195e-08,
+      "loss": 0.1776,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9772140004698144,
+      "grad_norm": 5.595784664154053,
+      "learning_rate": 1.816319800208466e-08,
+      "loss": 0.1669,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9866102889358703,
+      "grad_norm": 3.4040722846984863,
+      "learning_rate": 6.880960486877475e-09,
+      "loss": 0.1464,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9866102889358703,
+      "eval_loss": 0.16257165372371674,
+      "eval_runtime": 534.9845,
+      "eval_samples_per_second": 1.768,
+      "eval_steps_per_second": 0.884,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9960065774019262,
+      "grad_norm": 2.6516175270080566,
+      "learning_rate": 9.678258673995189e-10,
+      "loss": 0.2124,
+      "step": 1060
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1065,
+  "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": 57141526265856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

web_rl_3b/checkpoint-1065/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63da21f419fbe8f8eed2994d1cd0666792bbccf954d1bdd55da81fbac49b6444
+size 8337

web_rl_3b/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

web_rl_3b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.16246147453784943,
+    "eval_runtime": 519.0801,
+    "eval_samples_per_second": 1.822,
+    "eval_steps_per_second": 0.911
+}

web_rl_3b/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"
+}

web_rl_3b/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bae34d001b0178e721fae3c92aa1abf3a047088cfe7f32947c9fff27df183d
+size 4957560304

web_rl_3b/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd94dd66bb8aa93760dfc0c3ba73d9a7c7566ee65e461e3d59caebc6b131fd92
+size 1214366696

web_rl_3b/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_parameters": 241664,
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

web_rl_3b/runs/Nov22_11-21-53_ubuntu/events.out.tfevents.1763810597.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91a5556c7e1668baab34f0771cdf378bbe190fd002257ef4a750e0dfc1e72d9
+size 34624

web_rl_3b/runs/Nov22_11-21-53_ubuntu/events.out.tfevents.1763845681.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad4abddf7fc486297d8b2deb2de9f428f5512535f77934f30e37ca8f7518a47
+size 311

web_rl_3b/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
+  }
+}

web_rl_3b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

web_rl_3b/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
+}

web_rl_3b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 57141526265856.0,
+    "train_loss": 0.2802479102018294,
+    "train_runtime": 34553.4877,
+    "train_samples_per_second": 0.246,
+    "train_steps_per_second": 0.031
+}

web_rl_3b/trainer_log.jsonl

@@ -0,0 +1,128 @@
+{"current_steps": 10, "total_steps": 1065, "loss": 1.6798, "lr": 8.411214953271029e-07, "epoch": 0.009396288466055908, "percentage": 0.94, "elapsed_time": "0:04:10", "remaining_time": "7:20:20"}
+{"current_steps": 20, "total_steps": 1065, "loss": 1.4918, "lr": 1.7757009345794394e-06, "epoch": 0.018792576932111817, "percentage": 1.88, "elapsed_time": "0:08:03", "remaining_time": "7:01:19"}
+{"current_steps": 30, "total_steps": 1065, "loss": 0.832, "lr": 2.7102803738317757e-06, "epoch": 0.028188865398167725, "percentage": 2.82, "elapsed_time": "0:11:45", "remaining_time": "6:45:44"}
+{"current_steps": 40, "total_steps": 1065, "loss": 0.6918, "lr": 3.6448598130841123e-06, "epoch": 0.03758515386422363, "percentage": 3.76, "elapsed_time": "0:15:31", "remaining_time": "6:37:41"}
+{"current_steps": 50, "total_steps": 1065, "loss": 0.5121, "lr": 4.579439252336449e-06, "epoch": 0.04698144233027954, "percentage": 4.69, "elapsed_time": "0:19:21", "remaining_time": "6:32:53"}
+{"current_steps": 50, "total_steps": 1065, "eval_loss": 0.4876191020011902, "epoch": 0.04698144233027954, "percentage": 4.69, "elapsed_time": "0:27:13", "remaining_time": "9:12:46"}
+{"current_steps": 60, "total_steps": 1065, "loss": 0.4886, "lr": 5.514018691588785e-06, "epoch": 0.05637773079633545, "percentage": 5.63, "elapsed_time": "0:31:04", "remaining_time": "8:40:32"}
+{"current_steps": 70, "total_steps": 1065, "loss": 0.4985, "lr": 6.448598130841122e-06, "epoch": 0.06577401926239136, "percentage": 6.57, "elapsed_time": "0:34:54", "remaining_time": "8:16:12"}
+{"current_steps": 80, "total_steps": 1065, "loss": 0.3483, "lr": 7.383177570093458e-06, "epoch": 0.07517030772844727, "percentage": 7.51, "elapsed_time": "0:39:28", "remaining_time": "8:06:04"}
+{"current_steps": 90, "total_steps": 1065, "loss": 0.2995, "lr": 8.317757009345795e-06, "epoch": 0.08456659619450317, "percentage": 8.45, "elapsed_time": "0:43:44", "remaining_time": "7:53:55"}
+{"current_steps": 100, "total_steps": 1065, "loss": 0.4615, "lr": 9.252336448598132e-06, "epoch": 0.09396288466055908, "percentage": 9.39, "elapsed_time": "0:47:31", "remaining_time": "7:38:39"}
+{"current_steps": 100, "total_steps": 1065, "eval_loss": 0.3848985433578491, "epoch": 0.09396288466055908, "percentage": 9.39, "elapsed_time": "0:55:37", "remaining_time": "8:56:42"}
+{"current_steps": 110, "total_steps": 1065, "loss": 0.372, "lr": 9.999892460708615e-06, "epoch": 0.10335917312661498, "percentage": 10.33, "elapsed_time": "0:59:28", "remaining_time": "8:36:20"}
+{"current_steps": 120, "total_steps": 1065, "loss": 0.3499, "lr": 9.996129071205167e-06, "epoch": 0.1127554615926709, "percentage": 11.27, "elapsed_time": "1:03:04", "remaining_time": "8:16:44"}
+{"current_steps": 130, "total_steps": 1065, "loss": 0.3497, "lr": 9.98699334211771e-06, "epoch": 0.1221517500587268, "percentage": 12.21, "elapsed_time": "1:06:45", "remaining_time": "8:00:07"}
+{"current_steps": 140, "total_steps": 1065, "loss": 0.3527, "lr": 9.972495097099379e-06, "epoch": 0.13154803852478272, "percentage": 13.15, "elapsed_time": "1:10:25", "remaining_time": "7:45:15"}
+{"current_steps": 150, "total_steps": 1065, "loss": 0.37, "lr": 9.952649926118827e-06, "epoch": 0.14094432699083861, "percentage": 14.08, "elapsed_time": "1:14:13", "remaining_time": "7:32:43"}
+{"current_steps": 150, "total_steps": 1065, "eval_loss": 0.32813695073127747, "epoch": 0.14094432699083861, "percentage": 14.08, "elapsed_time": "1:21:44", "remaining_time": "8:18:34"}
+{"current_steps": 160, "total_steps": 1065, "loss": 0.4364, "lr": 9.927479168696327e-06, "epoch": 0.15034061545689453, "percentage": 15.02, "elapsed_time": "1:25:14", "remaining_time": "8:02:08"}
+{"current_steps": 170, "total_steps": 1065, "loss": 0.3828, "lr": 9.897009890957382e-06, "epoch": 0.15973690392295042, "percentage": 15.96, "elapsed_time": "1:28:48", "remaining_time": "7:47:33"}
+{"current_steps": 180, "total_steps": 1065, "loss": 0.3503, "lr": 9.861274856528504e-06, "epoch": 0.16913319238900634, "percentage": 16.9, "elapsed_time": "1:32:15", "remaining_time": "7:33:34"}
+{"current_steps": 190, "total_steps": 1065, "loss": 0.4124, "lr": 9.820312491306471e-06, "epoch": 0.17852948085506226, "percentage": 17.84, "elapsed_time": "1:35:41", "remaining_time": "7:20:41"}
+{"current_steps": 200, "total_steps": 1065, "loss": 0.3749, "lr": 9.77416684213896e-06, "epoch": 0.18792576932111815, "percentage": 18.78, "elapsed_time": "1:39:16", "remaining_time": "7:09:20"}
+{"current_steps": 200, "total_steps": 1065, "eval_loss": 0.2891885042190552, "epoch": 0.18792576932111815, "percentage": 18.78, "elapsed_time": "1:46:55", "remaining_time": "7:42:25"}
+{"current_steps": 210, "total_steps": 1065, "loss": 0.235, "lr": 9.722887529460928e-06, "epoch": 0.19732205778717407, "percentage": 19.72, "elapsed_time": "1:50:24", "remaining_time": "7:29:33"}
+{"current_steps": 220, "total_steps": 1065, "loss": 0.2777, "lr": 9.666529693937763e-06, "epoch": 0.20671834625322996, "percentage": 20.66, "elapsed_time": "1:53:37", "remaining_time": "7:16:27"}
+{"current_steps": 230, "total_steps": 1065, "loss": 0.3091, "lr": 9.605153937172495e-06, "epoch": 0.21611463471928588, "percentage": 21.6, "elapsed_time": "1:57:11", "remaining_time": "7:05:28"}
+{"current_steps": 240, "total_steps": 1065, "loss": 0.287, "lr": 9.538826256540866e-06, "epoch": 0.2255109231853418, "percentage": 22.54, "elapsed_time": "2:00:44", "remaining_time": "6:55:03"}
+{"current_steps": 250, "total_steps": 1065, "loss": 0.2863, "lr": 9.467617974224326e-06, "epoch": 0.2349072116513977, "percentage": 23.47, "elapsed_time": "2:04:32", "remaining_time": "6:46:00"}
+{"current_steps": 250, "total_steps": 1065, "eval_loss": 0.2756798267364502, "epoch": 0.2349072116513977, "percentage": 23.47, "elapsed_time": "2:12:56", "remaining_time": "7:13:23"}
+{"current_steps": 260, "total_steps": 1065, "loss": 0.2357, "lr": 9.391605660517268e-06, "epoch": 0.2443035001174536, "percentage": 24.41, "elapsed_time": "2:16:43", "remaining_time": "7:03:18"}
+{"current_steps": 270, "total_steps": 1065, "loss": 0.2237, "lr": 9.310871051490953e-06, "epoch": 0.2536997885835095, "percentage": 25.35, "elapsed_time": "2:20:25", "remaining_time": "6:53:29"}
+{"current_steps": 280, "total_steps": 1065, "loss": 0.2974, "lr": 9.225500961102685e-06, "epoch": 0.26309607704956545, "percentage": 26.29, "elapsed_time": "2:24:20", "remaining_time": "6:44:40"}
+{"current_steps": 290, "total_steps": 1065, "loss": 0.2556, "lr": 9.135587187844727e-06, "epoch": 0.27249236551562134, "percentage": 27.23, "elapsed_time": "2:28:07", "remaining_time": "6:35:50"}
+{"current_steps": 300, "total_steps": 1065, "loss": 0.3078, "lr": 9.041226416033344e-06, "epoch": 0.28188865398167723, "percentage": 28.17, "elapsed_time": "2:31:53", "remaining_time": "6:27:18"}
+{"current_steps": 300, "total_steps": 1065, "eval_loss": 0.25494658946990967, "epoch": 0.28188865398167723, "percentage": 28.17, "elapsed_time": "2:40:32", "remaining_time": "6:49:22"}
+{"current_steps": 310, "total_steps": 1065, "loss": 0.2227, "lr": 8.942520111844117e-06, "epoch": 0.2912849424477331, "percentage": 29.11, "elapsed_time": "2:44:31", "remaining_time": "6:40:40"}
+{"current_steps": 320, "total_steps": 1065, "loss": 0.2668, "lr": 8.839574414205335e-06, "epoch": 0.30068123091378907, "percentage": 30.05, "elapsed_time": "2:48:20", "remaining_time": "6:31:55"}
+{"current_steps": 330, "total_steps": 1065, "loss": 0.2726, "lr": 8.732500020666748e-06, "epoch": 0.31007751937984496, "percentage": 30.99, "elapsed_time": "2:51:56", "remaining_time": "6:22:57"}
+{"current_steps": 340, "total_steps": 1065, "loss": 0.2807, "lr": 8.621412068366455e-06, "epoch": 0.31947380784590085, "percentage": 31.92, "elapsed_time": "2:55:32", "remaining_time": "6:14:18"}
+{"current_steps": 350, "total_steps": 1065, "loss": 0.2921, "lr": 8.506430010223899e-06, "epoch": 0.3288700963119568, "percentage": 32.86, "elapsed_time": "2:59:29", "remaining_time": "6:06:41"}
+{"current_steps": 350, "total_steps": 1065, "eval_loss": 0.23158399760723114, "epoch": 0.3288700963119568, "percentage": 32.86, "elapsed_time": "3:08:18", "remaining_time": "6:24:40"}
+{"current_steps": 360, "total_steps": 1065, "loss": 0.306, "lr": 8.38767748649208e-06, "epoch": 0.3382663847780127, "percentage": 33.8, "elapsed_time": "3:12:52", "remaining_time": "6:17:42"}
+{"current_steps": 370, "total_steps": 1065, "loss": 0.2148, "lr": 8.26528219180716e-06, "epoch": 0.3476626732440686, "percentage": 34.74, "elapsed_time": "3:17:14", "remaining_time": "6:10:29"}
+{"current_steps": 380, "total_steps": 1065, "loss": 0.1558, "lr": 8.139375737878356e-06, "epoch": 0.3570589617101245, "percentage": 35.68, "elapsed_time": "3:21:08", "remaining_time": "6:02:34"}
+{"current_steps": 390, "total_steps": 1065, "loss": 0.1945, "lr": 8.01009351196582e-06, "epoch": 0.3664552501761804, "percentage": 36.62, "elapsed_time": "3:24:44", "remaining_time": "5:54:21"}
+{"current_steps": 400, "total_steps": 1065, "loss": 0.3191, "lr": 7.877574531298666e-06, "epoch": 0.3758515386422363, "percentage": 37.56, "elapsed_time": "3:28:13", "remaining_time": "5:46:09"}
+{"current_steps": 400, "total_steps": 1065, "eval_loss": 0.23533165454864502, "epoch": 0.3758515386422363, "percentage": 37.56, "elapsed_time": "3:36:24", "remaining_time": "5:59:46"}
+{"current_steps": 410, "total_steps": 1065, "loss": 0.2265, "lr": 7.741961293589693e-06, "epoch": 0.38524782710829225, "percentage": 38.5, "elapsed_time": "3:40:04", "remaining_time": "5:51:34"}
+{"current_steps": 420, "total_steps": 1065, "loss": 0.2608, "lr": 7.603399623807519e-06, "epoch": 0.39464411557434814, "percentage": 39.44, "elapsed_time": "3:43:53", "remaining_time": "5:43:50"}
+{"current_steps": 430, "total_steps": 1065, "loss": 0.2456, "lr": 7.462038517370962e-06, "epoch": 0.40404040404040403, "percentage": 40.38, "elapsed_time": "3:47:38", "remaining_time": "5:36:09"}
+{"current_steps": 440, "total_steps": 1065, "loss": 0.2898, "lr": 7.318029979934181e-06, "epoch": 0.4134366925064599, "percentage": 41.31, "elapsed_time": "3:51:20", "remaining_time": "5:28:37"}
+{"current_steps": 450, "total_steps": 1065, "loss": 0.313, "lr": 7.17152886393495e-06, "epoch": 0.42283298097251587, "percentage": 42.25, "elapsed_time": "3:55:06", "remaining_time": "5:21:18"}
+{"current_steps": 450, "total_steps": 1065, "eval_loss": 0.22310128808021545, "epoch": 0.42283298097251587, "percentage": 42.25, "elapsed_time": "4:03:42", "remaining_time": "5:33:04"}
+{"current_steps": 460, "total_steps": 1065, "loss": 0.2691, "lr": 7.022692702081766e-06, "epoch": 0.43222926943857176, "percentage": 43.19, "elapsed_time": "4:07:41", "remaining_time": "5:25:46"}
+{"current_steps": 470, "total_steps": 1065, "loss": 0.2254, "lr": 6.871681537958862e-06, "epoch": 0.44162555790462765, "percentage": 44.13, "elapsed_time": "4:11:32", "remaining_time": "5:18:27"}
+{"current_steps": 480, "total_steps": 1065, "loss": 0.2315, "lr": 6.718657753931284e-06, "epoch": 0.4510218463706836, "percentage": 45.07, "elapsed_time": "4:15:28", "remaining_time": "5:11:21"}
+{"current_steps": 490, "total_steps": 1065, "loss": 0.2944, "lr": 6.56378589653506e-06, "epoch": 0.4604181348367395, "percentage": 46.01, "elapsed_time": "4:19:14", "remaining_time": "5:04:13"}
+{"current_steps": 500, "total_steps": 1065, "loss": 0.2037, "lr": 6.40723249954025e-06, "epoch": 0.4698144233027954, "percentage": 46.95, "elapsed_time": "4:22:56", "remaining_time": "4:57:07"}
+{"current_steps": 500, "total_steps": 1065, "eval_loss": 0.213790163397789, "epoch": 0.4698144233027954, "percentage": 46.95, "elapsed_time": "4:31:03", "remaining_time": "5:06:17"}
+{"current_steps": 510, "total_steps": 1065, "loss": 0.2189, "lr": 6.2491659048771215e-06, "epoch": 0.4792107117688513, "percentage": 47.89, "elapsed_time": "4:34:41", "remaining_time": "4:58:55"}
+{"current_steps": 520, "total_steps": 1065, "loss": 0.222, "lr": 6.089756081617987e-06, "epoch": 0.4886070002349072, "percentage": 48.83, "elapsed_time": "4:38:12", "remaining_time": "4:51:34"}
+{"current_steps": 530, "total_steps": 1065, "loss": 0.2179, "lr": 5.929174443209416e-06, "epoch": 0.4980032887009631, "percentage": 49.77, "elapsed_time": "4:42:01", "remaining_time": "4:44:40"}
+{"current_steps": 540, "total_steps": 1065, "loss": 0.2111, "lr": 5.767593663151265e-06, "epoch": 0.507399577167019, "percentage": 50.7, "elapsed_time": "4:45:47", "remaining_time": "4:37:50"}
+{"current_steps": 550, "total_steps": 1065, "loss": 0.1729, "lr": 5.605187489320815e-06, "epoch": 0.5167958656330749, "percentage": 51.64, "elapsed_time": "4:49:41", "remaining_time": "4:31:15"}
+{"current_steps": 550, "total_steps": 1065, "eval_loss": 0.20741979777812958, "epoch": 0.5167958656330749, "percentage": 51.64, "elapsed_time": "4:58:10", "remaining_time": "4:39:11"}
+{"current_steps": 560, "total_steps": 1065, "loss": 0.1785, "lr": 5.442130557141595e-06, "epoch": 0.5261921540991309, "percentage": 52.58, "elapsed_time": "5:01:48", "remaining_time": "4:32:10"}
+{"current_steps": 570, "total_steps": 1065, "loss": 0.1761, "lr": 5.278598201797844e-06, "epoch": 0.5355884425651868, "percentage": 53.52, "elapsed_time": "5:05:32", "remaining_time": "4:25:19"}
+{"current_steps": 580, "total_steps": 1065, "loss": 0.2185, "lr": 5.1147662696965254e-06, "epoch": 0.5449847310312427, "percentage": 54.46, "elapsed_time": "5:09:08", "remaining_time": "4:18:30"}
+{"current_steps": 590, "total_steps": 1065, "loss": 0.211, "lr": 4.9508109293796015e-06, "epoch": 0.5543810194972986, "percentage": 55.4, "elapsed_time": "5:12:35", "remaining_time": "4:11:40"}
+{"current_steps": 600, "total_steps": 1065, "loss": 0.289, "lr": 4.7869084820899455e-06, "epoch": 0.5637773079633545, "percentage": 56.34, "elapsed_time": "5:16:08", "remaining_time": "4:05:00"}
+{"current_steps": 600, "total_steps": 1065, "eval_loss": 0.1954464614391327, "epoch": 0.5637773079633545, "percentage": 56.34, "elapsed_time": "5:24:27", "remaining_time": "4:11:27"}
+{"current_steps": 610, "total_steps": 1065, "loss": 0.2154, "lr": 4.623235172194532e-06, "epoch": 0.5731735964294103, "percentage": 57.28, "elapsed_time": "5:28:23", "remaining_time": "4:04:56"}
+{"current_steps": 620, "total_steps": 1065, "loss": 0.2147, "lr": 4.459966997668812e-06, "epoch": 0.5825698848954662, "percentage": 58.22, "elapsed_time": "5:32:01", "remaining_time": "3:58:18"}
+{"current_steps": 630, "total_steps": 1065, "loss": 0.1491, "lr": 4.297279520846002e-06, "epoch": 0.5919661733615222, "percentage": 59.15, "elapsed_time": "5:35:29", "remaining_time": "3:51:38"}
+{"current_steps": 640, "total_steps": 1065, "loss": 0.2285, "lr": 4.135347679634849e-06, "epoch": 0.6013624618275781, "percentage": 60.09, "elapsed_time": "5:39:07", "remaining_time": "3:45:12"}
+{"current_steps": 650, "total_steps": 1065, "loss": 0.2775, "lr": 3.974345599408833e-06, "epoch": 0.610758750293634, "percentage": 61.03, "elapsed_time": "5:42:51", "remaining_time": "3:38:54"}
+{"current_steps": 650, "total_steps": 1065, "eval_loss": 0.18974561989307404, "epoch": 0.610758750293634, "percentage": 61.03, "elapsed_time": "5:51:00", "remaining_time": "3:44:06"}
+{"current_steps": 660, "total_steps": 1065, "loss": 0.214, "lr": 3.814446405769069e-06, "epoch": 0.6201550387596899, "percentage": 61.97, "elapsed_time": "5:54:34", "remaining_time": "3:37:34"}
+{"current_steps": 670, "total_steps": 1065, "loss": 0.2392, "lr": 3.6558220383822824e-06, "epoch": 0.6295513272257458, "percentage": 62.91, "elapsed_time": "5:58:10", "remaining_time": "3:31:09"}
+{"current_steps": 680, "total_steps": 1065, "loss": 0.2062, "lr": 3.4986430660940283e-06, "epoch": 0.6389476156918017, "percentage": 63.85, "elapsed_time": "6:01:37", "remaining_time": "3:24:44"}
+{"current_steps": 690, "total_steps": 1065, "loss": 0.1738, "lr": 3.3430785035159297e-06, "epoch": 0.6483439041578577, "percentage": 64.79, "elapsed_time": "6:05:15", "remaining_time": "3:18:30"}
+{"current_steps": 700, "total_steps": 1065, "loss": 0.1546, "lr": 3.1892956292842103e-06, "epoch": 0.6577401926239136, "percentage": 65.73, "elapsed_time": "6:08:45", "remaining_time": "3:12:16"}
+{"current_steps": 700, "total_steps": 1065, "eval_loss": 0.18141551315784454, "epoch": 0.6577401926239136, "percentage": 65.73, "elapsed_time": "6:17:09", "remaining_time": "3:16:39"}
+{"current_steps": 710, "total_steps": 1065, "loss": 0.2037, "lr": 3.0374598061848936e-06, "epoch": 0.6671364810899695, "percentage": 66.67, "elapsed_time": "6:20:55", "remaining_time": "3:10:27"}
+{"current_steps": 720, "total_steps": 1065, "loss": 0.14, "lr": 2.8877343033391523e-06, "epoch": 0.6765327695560254, "percentage": 67.61, "elapsed_time": "6:24:33", "remaining_time": "3:04:15"}
+{"current_steps": 730, "total_steps": 1065, "loss": 0.1721, "lr": 2.7402801206399454e-06, "epoch": 0.6859290580220813, "percentage": 68.54, "elapsed_time": "6:28:09", "remaining_time": "2:58:07"}
+{"current_steps": 740, "total_steps": 1065, "loss": 0.2586, "lr": 2.595255815628774e-06, "epoch": 0.6953253464881372, "percentage": 69.48, "elapsed_time": "6:31:45", "remaining_time": "2:52:03"}
+{"current_steps": 750, "total_steps": 1065, "loss": 0.1613, "lr": 2.4528173329986855e-06, "epoch": 0.704721634954193, "percentage": 70.42, "elapsed_time": "6:35:17", "remaining_time": "2:46:01"}
+{"current_steps": 750, "total_steps": 1065, "eval_loss": 0.1746373176574707, "epoch": 0.704721634954193, "percentage": 70.42, "elapsed_time": "6:43:20", "remaining_time": "2:49:24"}
+{"current_steps": 760, "total_steps": 1065, "loss": 0.2041, "lr": 2.313117836906897e-06, "epoch": 0.714117923420249, "percentage": 71.36, "elapsed_time": "6:47:01", "remaining_time": "2:43:20"}
+{"current_steps": 770, "total_steps": 1065, "loss": 0.2033, "lr": 2.1763075462773002e-06, "epoch": 0.7235142118863049, "percentage": 72.3, "elapsed_time": "6:50:40", "remaining_time": "2:37:20"}
+{"current_steps": 780, "total_steps": 1065, "loss": 0.2497, "lr": 2.0425335732700075e-06, "epoch": 0.7329105003523608, "percentage": 73.24, "elapsed_time": "6:54:08", "remaining_time": "2:31:19"}
+{"current_steps": 790, "total_steps": 1065, "loss": 0.2354, "lr": 1.9119397650915774e-06, "epoch": 0.7423067888184167, "percentage": 74.18, "elapsed_time": "6:57:38", "remaining_time": "2:25:22"}
+{"current_steps": 800, "total_steps": 1065, "loss": 0.0956, "lr": 1.7846665493160548e-06, "epoch": 0.7517030772844726, "percentage": 75.12, "elapsed_time": "7:01:16", "remaining_time": "2:19:32"}
+{"current_steps": 800, "total_steps": 1065, "eval_loss": 0.1724964827299118, "epoch": 0.7517030772844726, "percentage": 75.12, "elapsed_time": "7:09:31", "remaining_time": "2:22:16"}
+{"current_steps": 810, "total_steps": 1065, "loss": 0.1711, "lr": 1.6608507828831572e-06, "epoch": 0.7610993657505285, "percentage": 76.06, "elapsed_time": "7:12:54", "remaining_time": "2:16:17"}
+{"current_steps": 820, "total_steps": 1065, "loss": 0.2362, "lr": 1.5406256049359359e-06, "epoch": 0.7704956542165845, "percentage": 77.0, "elapsed_time": "7:16:28", "remaining_time": "2:10:24"}
+{"current_steps": 830, "total_steps": 1065, "loss": 0.1692, "lr": 1.4241202936562164e-06, "epoch": 0.7798919426826404, "percentage": 77.93, "elapsed_time": "7:20:00", "remaining_time": "2:04:34"}
+{"current_steps": 840, "total_steps": 1065, "loss": 0.1608, "lr": 1.311460127251708e-06, "epoch": 0.7892882311486963, "percentage": 78.87, "elapsed_time": "7:23:33", "remaining_time": "1:58:48"}
+{"current_steps": 850, "total_steps": 1065, "loss": 0.1692, "lr": 1.202766249244306e-06, "epoch": 0.7986845196147522, "percentage": 79.81, "elapsed_time": "7:27:21", "remaining_time": "1:53:09"}
+{"current_steps": 850, "total_steps": 1065, "eval_loss": 0.1683204621076584, "epoch": 0.7986845196147522, "percentage": 79.81, "elapsed_time": "7:36:18", "remaining_time": "1:55:25"}
+{"current_steps": 860, "total_steps": 1065, "loss": 0.1718, "lr": 1.098155538204404e-06, "epoch": 0.8080808080808081, "percentage": 80.75, "elapsed_time": "7:40:27", "remaining_time": "1:49:45"}
+{"current_steps": 870, "total_steps": 1065, "loss": 0.1425, "lr": 9.977404820713315e-07, "epoch": 0.817477096546864, "percentage": 81.69, "elapsed_time": "7:44:27", "remaining_time": "1:44:06"}
+{"current_steps": 880, "total_steps": 1065, "loss": 0.1196, "lr": 9.016290571950171e-07, "epoch": 0.8268733850129198, "percentage": 82.63, "elapsed_time": "7:48:26", "remaining_time": "1:38:28"}
+{"current_steps": 890, "total_steps": 1065, "loss": 0.2077, "lr": 8.099246122289861e-07, "epoch": 0.8362696734789759, "percentage": 83.57, "elapsed_time": "7:52:20", "remaining_time": "1:32:52"}
+{"current_steps": 900, "total_steps": 1065, "loss": 0.1885, "lr": 7.227257569995061e-07, "epoch": 0.8456659619450317, "percentage": 84.51, "elapsed_time": "7:56:12", "remaining_time": "1:27:18"}
+{"current_steps": 900, "total_steps": 1065, "eval_loss": 0.16525517404079437, "epoch": 0.8456659619450317, "percentage": 84.51, "elapsed_time": "8:04:57", "remaining_time": "1:28:54"}
+{"current_steps": 910, "total_steps": 1065, "loss": 0.2379, "lr": 6.401262564704019e-07, "epoch": 0.8550622504110876, "percentage": 85.45, "elapsed_time": "8:08:49", "remaining_time": "1:23:15"}
+{"current_steps": 920, "total_steps": 1065, "loss": 0.2253, "lr": 5.622149299175539e-07, "epoch": 0.8644585388771435, "percentage": 86.38, "elapsed_time": "8:12:37", "remaining_time": "1:17:38"}
+{"current_steps": 930, "total_steps": 1065, "loss": 0.1952, "lr": 4.890755554214954e-07, "epoch": 0.8738548273431994, "percentage": 87.32, "elapsed_time": "8:16:39", "remaining_time": "1:12:05"}
+{"current_steps": 940, "total_steps": 1065, "loss": 0.1522, "lr": 4.207867797808102e-07, "epoch": 0.8832511158092553, "percentage": 88.26, "elapsed_time": "8:20:26", "remaining_time": "1:06:32"}
+{"current_steps": 950, "total_steps": 1065, "loss": 0.2799, "lr": 3.5742203394319606e-07, "epoch": 0.8926474042753113, "percentage": 89.2, "elapsed_time": "8:24:25", "remaining_time": "1:01:03"}
+{"current_steps": 950, "total_steps": 1065, "eval_loss": 0.163659006357193, "epoch": 0.8926474042753113, "percentage": 89.2, "elapsed_time": "8:33:27", "remaining_time": "1:02:09"}
+{"current_steps": 960, "total_steps": 1065, "loss": 0.173, "lr": 2.9904945404513606e-07, "epoch": 0.9020436927413672, "percentage": 90.14, "elapsed_time": "8:37:25", "remaining_time": "0:56:35"}
+{"current_steps": 970, "total_steps": 1065, "loss": 0.184, "lr": 2.457318081450899e-07, "epoch": 0.9114399812074231, "percentage": 91.08, "elapsed_time": "8:41:22", "remaining_time": "0:51:03"}
+{"current_steps": 980, "total_steps": 1065, "loss": 0.1533, "lr": 1.9752642872897078e-07, "epoch": 0.920836269673479, "percentage": 92.02, "elapsed_time": "8:45:23", "remaining_time": "0:45:34"}
+{"current_steps": 990, "total_steps": 1065, "loss": 0.2073, "lr": 1.5448515106050165e-07, "epoch": 0.9302325581395349, "percentage": 92.96, "elapsed_time": "8:49:09", "remaining_time": "0:40:05"}
+{"current_steps": 1000, "total_steps": 1065, "loss": 0.1971, "lr": 1.166542574427354e-07, "epoch": 0.9396288466055908, "percentage": 93.9, "elapsed_time": "8:53:03", "remaining_time": "0:34:38"}
+{"current_steps": 1000, "total_steps": 1065, "eval_loss": 0.16281382739543915, "epoch": 0.9396288466055908, "percentage": 93.9, "elapsed_time": "9:01:41", "remaining_time": "0:35:12"}
+{"current_steps": 1010, "total_steps": 1065, "loss": 0.1787, "lr": 8.407442745067552e-08, "epoch": 0.9490251350716467, "percentage": 94.84, "elapsed_time": "9:05:27", "remaining_time": "0:29:42"}
+{"current_steps": 1020, "total_steps": 1065, "loss": 0.1581, "lr": 5.678069418851351e-08, "epoch": 0.9584214235377027, "percentage": 95.77, "elapsed_time": "9:09:32", "remaining_time": "0:24:14"}
+{"current_steps": 1030, "total_steps": 1065, "loss": 0.1776, "lr": 3.4802406618518195e-08, "epoch": 0.9678177120037585, "percentage": 96.71, "elapsed_time": "9:13:23", "remaining_time": "0:18:48"}
+{"current_steps": 1040, "total_steps": 1065, "loss": 0.1669, "lr": 1.816319800208466e-08, "epoch": 0.9772140004698144, "percentage": 97.65, "elapsed_time": "9:17:13", "remaining_time": "0:13:23"}
+{"current_steps": 1050, "total_steps": 1065, "loss": 0.1464, "lr": 6.880960486877475e-09, "epoch": 0.9866102889358703, "percentage": 98.59, "elapsed_time": "9:21:17", "remaining_time": "0:08:01"}
+{"current_steps": 1050, "total_steps": 1065, "eval_loss": 0.16257165372371674, "epoch": 0.9866102889358703, "percentage": 98.59, "elapsed_time": "9:30:12", "remaining_time": "0:08:08"}
+{"current_steps": 1060, "total_steps": 1065, "loss": 0.2124, "lr": 9.678258673995189e-10, "epoch": 0.9960065774019262, "percentage": 99.53, "elapsed_time": "9:34:09", "remaining_time": "0:02:42"}
+{"current_steps": 1065, "total_steps": 1065, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "9:35:53", "remaining_time": "0:00:00"}

web_rl_3b/trainer_state.json

@@ -0,0 +1,953 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 1065,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009396288466055908,
+      "grad_norm": 77.32342529296875,
+      "learning_rate": 8.411214953271029e-07,
+      "loss": 1.6798,
+      "step": 10
+    },
+    {
+      "epoch": 0.018792576932111817,
+      "grad_norm": 33.60771179199219,
+      "learning_rate": 1.7757009345794394e-06,
+      "loss": 1.4918,
+      "step": 20
+    },
+    {
+      "epoch": 0.028188865398167725,
+      "grad_norm": 15.923619270324707,
+      "learning_rate": 2.7102803738317757e-06,
+      "loss": 0.832,
+      "step": 30
+    },
+    {
+      "epoch": 0.03758515386422363,
+      "grad_norm": 25.03349494934082,
+      "learning_rate": 3.6448598130841123e-06,
+      "loss": 0.6918,
+      "step": 40
+    },
+    {
+      "epoch": 0.04698144233027954,
+      "grad_norm": 10.101052284240723,
+      "learning_rate": 4.579439252336449e-06,
+      "loss": 0.5121,
+      "step": 50
+    },
+    {
+      "epoch": 0.04698144233027954,
+      "eval_loss": 0.4876191020011902,
+      "eval_runtime": 472.5825,
+      "eval_samples_per_second": 2.002,
+      "eval_steps_per_second": 1.001,
+      "step": 50
+    },
+    {
+      "epoch": 0.05637773079633545,
+      "grad_norm": 8.925775527954102,
+      "learning_rate": 5.514018691588785e-06,
+      "loss": 0.4886,
+      "step": 60
+    },
+    {
+      "epoch": 0.06577401926239136,
+      "grad_norm": 7.684209823608398,
+      "learning_rate": 6.448598130841122e-06,
+      "loss": 0.4985,
+      "step": 70
+    },
+    {
+      "epoch": 0.07517030772844727,
+      "grad_norm": 14.134685516357422,
+      "learning_rate": 7.383177570093458e-06,
+      "loss": 0.3483,
+      "step": 80
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 9.419997215270996,
+      "learning_rate": 8.317757009345795e-06,
+      "loss": 0.2995,
+      "step": 90
+    },
+    {
+      "epoch": 0.09396288466055908,
+      "grad_norm": 9.725701332092285,
+      "learning_rate": 9.252336448598132e-06,
+      "loss": 0.4615,
+      "step": 100
+    },
+    {
+      "epoch": 0.09396288466055908,
+      "eval_loss": 0.3848985433578491,
+      "eval_runtime": 485.2521,
+      "eval_samples_per_second": 1.95,
+      "eval_steps_per_second": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 7.37769889831543,
+      "learning_rate": 9.999892460708615e-06,
+      "loss": 0.372,
+      "step": 110
+    },
+    {
+      "epoch": 0.1127554615926709,
+      "grad_norm": 5.251932144165039,
+      "learning_rate": 9.996129071205167e-06,
+      "loss": 0.3499,
+      "step": 120
+    },
+    {
+      "epoch": 0.1221517500587268,
+      "grad_norm": 6.633662700653076,
+      "learning_rate": 9.98699334211771e-06,
+      "loss": 0.3497,
+      "step": 130
+    },
+    {
+      "epoch": 0.13154803852478272,
+      "grad_norm": 9.925003051757812,
+      "learning_rate": 9.972495097099379e-06,
+      "loss": 0.3527,
+      "step": 140
+    },
+    {
+      "epoch": 0.14094432699083861,
+      "grad_norm": 2.5581600666046143,
+      "learning_rate": 9.952649926118827e-06,
+      "loss": 0.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.14094432699083861,
+      "eval_loss": 0.32813695073127747,
+      "eval_runtime": 450.9285,
+      "eval_samples_per_second": 2.098,
+      "eval_steps_per_second": 1.049,
+      "step": 150
+    },
+    {
+      "epoch": 0.15034061545689453,
+      "grad_norm": 8.05836009979248,
+      "learning_rate": 9.927479168696327e-06,
+      "loss": 0.4364,
+      "step": 160
+    },
+    {
+      "epoch": 0.15973690392295042,
+      "grad_norm": 8.204833984375,
+      "learning_rate": 9.897009890957382e-06,
+      "loss": 0.3828,
+      "step": 170
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 4.883147716522217,
+      "learning_rate": 9.861274856528504e-06,
+      "loss": 0.3503,
+      "step": 180
+    },
+    {
+      "epoch": 0.17852948085506226,
+      "grad_norm": 4.023066520690918,
+      "learning_rate": 9.820312491306471e-06,
+      "loss": 0.4124,
+      "step": 190
+    },
+    {
+      "epoch": 0.18792576932111815,
+      "grad_norm": 3.1607863903045654,
+      "learning_rate": 9.77416684213896e-06,
+      "loss": 0.3749,
+      "step": 200
+    },
+    {
+      "epoch": 0.18792576932111815,
+      "eval_loss": 0.2891885042190552,
+      "eval_runtime": 458.85,
+      "eval_samples_per_second": 2.062,
+      "eval_steps_per_second": 1.031,
+      "step": 200
+    },
+    {
+      "epoch": 0.19732205778717407,
+      "grad_norm": 9.990116119384766,
+      "learning_rate": 9.722887529460928e-06,
+      "loss": 0.235,
+      "step": 210
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 4.4412760734558105,
+      "learning_rate": 9.666529693937763e-06,
+      "loss": 0.2777,
+      "step": 220
+    },
+    {
+      "epoch": 0.21611463471928588,
+      "grad_norm": 5.4278154373168945,
+      "learning_rate": 9.605153937172495e-06,
+      "loss": 0.3091,
+      "step": 230
+    },
+    {
+      "epoch": 0.2255109231853418,
+      "grad_norm": 4.043374061584473,
+      "learning_rate": 9.538826256540866e-06,
+      "loss": 0.287,
+      "step": 240
+    },
+    {
+      "epoch": 0.2349072116513977,
+      "grad_norm": 5.319589614868164,
+      "learning_rate": 9.467617974224326e-06,
+      "loss": 0.2863,
+      "step": 250
+    },
+    {
+      "epoch": 0.2349072116513977,
+      "eval_loss": 0.2756798267364502,
+      "eval_runtime": 504.1073,
+      "eval_samples_per_second": 1.877,
+      "eval_steps_per_second": 0.938,
+      "step": 250
+    },
+    {
+      "epoch": 0.2443035001174536,
+      "grad_norm": 8.62342643737793,
+      "learning_rate": 9.391605660517268e-06,
+      "loss": 0.2357,
+      "step": 260
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 2.7996938228607178,
+      "learning_rate": 9.310871051490953e-06,
+      "loss": 0.2237,
+      "step": 270
+    },
+    {
+      "epoch": 0.26309607704956545,
+      "grad_norm": 4.890498638153076,
+      "learning_rate": 9.225500961102685e-06,
+      "loss": 0.2974,
+      "step": 280
+    },
+    {
+      "epoch": 0.27249236551562134,
+      "grad_norm": 5.307254314422607,
+      "learning_rate": 9.135587187844727e-06,
+      "loss": 0.2556,
+      "step": 290
+    },
+    {
+      "epoch": 0.28188865398167723,
+      "grad_norm": 4.411228656768799,
+      "learning_rate": 9.041226416033344e-06,
+      "loss": 0.3078,
+      "step": 300
+    },
+    {
+      "epoch": 0.28188865398167723,
+      "eval_loss": 0.25494658946990967,
+      "eval_runtime": 518.8808,
+      "eval_samples_per_second": 1.823,
+      "eval_steps_per_second": 0.912,
+      "step": 300
+    },
+    {
+      "epoch": 0.2912849424477331,
+      "grad_norm": 2.772766351699829,
+      "learning_rate": 8.942520111844117e-06,
+      "loss": 0.2227,
+      "step": 310
+    },
+    {
+      "epoch": 0.30068123091378907,
+      "grad_norm": 5.582266807556152,
+      "learning_rate": 8.839574414205335e-06,
+      "loss": 0.2668,
+      "step": 320
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 4.721141815185547,
+      "learning_rate": 8.732500020666748e-06,
+      "loss": 0.2726,
+      "step": 330
+    },
+    {
+      "epoch": 0.31947380784590085,
+      "grad_norm": 4.359829425811768,
+      "learning_rate": 8.621412068366455e-06,
+      "loss": 0.2807,
+      "step": 340
+    },
+    {
+      "epoch": 0.3288700963119568,
+      "grad_norm": 2.9552581310272217,
+      "learning_rate": 8.506430010223899e-06,
+      "loss": 0.2921,
+      "step": 350
+    },
+    {
+      "epoch": 0.3288700963119568,
+      "eval_loss": 0.23158399760723114,
+      "eval_runtime": 528.3567,
+      "eval_samples_per_second": 1.79,
+      "eval_steps_per_second": 0.895,
+      "step": 350
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 4.709650039672852,
+      "learning_rate": 8.38767748649208e-06,
+      "loss": 0.306,
+      "step": 360
+    },
+    {
+      "epoch": 0.3476626732440686,
+      "grad_norm": 2.7597694396972656,
+      "learning_rate": 8.26528219180716e-06,
+      "loss": 0.2148,
+      "step": 370
+    },
+    {
+      "epoch": 0.3570589617101245,
+      "grad_norm": 6.239573001861572,
+      "learning_rate": 8.139375737878356e-06,
+      "loss": 0.1558,
+      "step": 380
+    },
+    {
+      "epoch": 0.3664552501761804,
+      "grad_norm": 2.6109910011291504,
+      "learning_rate": 8.01009351196582e-06,
+      "loss": 0.1945,
+      "step": 390
+    },
+    {
+      "epoch": 0.3758515386422363,
+      "grad_norm": 5.080913543701172,
+      "learning_rate": 7.877574531298666e-06,
+      "loss": 0.3191,
+      "step": 400
+    },
+    {
+      "epoch": 0.3758515386422363,
+      "eval_loss": 0.23533165454864502,
+      "eval_runtime": 491.1933,
+      "eval_samples_per_second": 1.926,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.38524782710829225,
+      "grad_norm": 3.903905153274536,
+      "learning_rate": 7.741961293589693e-06,
+      "loss": 0.2265,
+      "step": 410
+    },
+    {
+      "epoch": 0.39464411557434814,
+      "grad_norm": 5.586989879608154,
+      "learning_rate": 7.603399623807519e-06,
+      "loss": 0.2608,
+      "step": 420
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 3.9632835388183594,
+      "learning_rate": 7.462038517370962e-06,
+      "loss": 0.2456,
+      "step": 430
+    },
+    {
+      "epoch": 0.4134366925064599,
+      "grad_norm": 7.482256889343262,
+      "learning_rate": 7.318029979934181e-06,
+      "loss": 0.2898,
+      "step": 440
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "grad_norm": 3.7885382175445557,
+      "learning_rate": 7.17152886393495e-06,
+      "loss": 0.313,
+      "step": 450
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "eval_loss": 0.22310128808021545,
+      "eval_runtime": 516.4179,
+      "eval_samples_per_second": 1.832,
+      "eval_steps_per_second": 0.916,
+      "step": 450
+    },
+    {
+      "epoch": 0.43222926943857176,
+      "grad_norm": 4.9588093757629395,
+      "learning_rate": 7.022692702081766e-06,
+      "loss": 0.2691,
+      "step": 460
+    },
+    {
+      "epoch": 0.44162555790462765,
+      "grad_norm": 4.674664497375488,
+      "learning_rate": 6.871681537958862e-06,
+      "loss": 0.2254,
+      "step": 470
+    },
+    {
+      "epoch": 0.4510218463706836,
+      "grad_norm": 5.224850654602051,
+      "learning_rate": 6.718657753931284e-06,
+      "loss": 0.2315,
+      "step": 480
+    },
+    {
+      "epoch": 0.4604181348367395,
+      "grad_norm": 4.065497398376465,
+      "learning_rate": 6.56378589653506e-06,
+      "loss": 0.2944,
+      "step": 490
+    },
+    {
+      "epoch": 0.4698144233027954,
+      "grad_norm": 4.546512603759766,
+      "learning_rate": 6.40723249954025e-06,
+      "loss": 0.2037,
+      "step": 500
+    },
+    {
+      "epoch": 0.4698144233027954,
+      "eval_loss": 0.213790163397789,
+      "eval_runtime": 486.7052,
+      "eval_samples_per_second": 1.944,
+      "eval_steps_per_second": 0.972,
+      "step": 500
+    },
+    {
+      "epoch": 0.4792107117688513,
+      "grad_norm": 3.3908934593200684,
+      "learning_rate": 6.2491659048771215e-06,
+      "loss": 0.2189,
+      "step": 510
+    },
+    {
+      "epoch": 0.4886070002349072,
+      "grad_norm": 4.911809921264648,
+      "learning_rate": 6.089756081617987e-06,
+      "loss": 0.222,
+      "step": 520
+    },
+    {
+      "epoch": 0.4980032887009631,
+      "grad_norm": 2.711010694503784,
+      "learning_rate": 5.929174443209416e-06,
+      "loss": 0.2179,
+      "step": 530
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 3.0764307975769043,
+      "learning_rate": 5.767593663151265e-06,
+      "loss": 0.2111,
+      "step": 540
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "grad_norm": 4.922618389129639,
+      "learning_rate": 5.605187489320815e-06,
+      "loss": 0.1729,
+      "step": 550
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "eval_loss": 0.20741979777812958,
+      "eval_runtime": 508.5854,
+      "eval_samples_per_second": 1.86,
+      "eval_steps_per_second": 0.93,
+      "step": 550
+    },
+    {
+      "epoch": 0.5261921540991309,
+      "grad_norm": 3.6055169105529785,
+      "learning_rate": 5.442130557141595e-06,
+      "loss": 0.1785,
+      "step": 560
+    },
+    {
+      "epoch": 0.5355884425651868,
+      "grad_norm": 4.116625785827637,
+      "learning_rate": 5.278598201797844e-06,
+      "loss": 0.1761,
+      "step": 570
+    },
+    {
+      "epoch": 0.5449847310312427,
+      "grad_norm": 6.054320335388184,
+      "learning_rate": 5.1147662696965254e-06,
+      "loss": 0.2185,
+      "step": 580
+    },
+    {
+      "epoch": 0.5543810194972986,
+      "grad_norm": 3.523534059524536,
+      "learning_rate": 4.9508109293796015e-06,
+      "loss": 0.211,
+      "step": 590
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "grad_norm": 6.204962730407715,
+      "learning_rate": 4.7869084820899455e-06,
+      "loss": 0.289,
+      "step": 600
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "eval_loss": 0.1954464614391327,
+      "eval_runtime": 498.5386,
+      "eval_samples_per_second": 1.898,
+      "eval_steps_per_second": 0.949,
+      "step": 600
+    },
+    {
+      "epoch": 0.5731735964294103,
+      "grad_norm": 4.921229839324951,
+      "learning_rate": 4.623235172194532e-06,
+      "loss": 0.2154,
+      "step": 610
+    },
+    {
+      "epoch": 0.5825698848954662,
+      "grad_norm": 4.28684139251709,
+      "learning_rate": 4.459966997668812e-06,
+      "loss": 0.2147,
+      "step": 620
+    },
+    {
+      "epoch": 0.5919661733615222,
+      "grad_norm": 4.43740177154541,
+      "learning_rate": 4.297279520846002e-06,
+      "loss": 0.1491,
+      "step": 630
+    },
+    {
+      "epoch": 0.6013624618275781,
+      "grad_norm": 6.9565863609313965,
+      "learning_rate": 4.135347679634849e-06,
+      "loss": 0.2285,
+      "step": 640
+    },
+    {
+      "epoch": 0.610758750293634,
+      "grad_norm": 1.496799349784851,
+      "learning_rate": 3.974345599408833e-06,
+      "loss": 0.2775,
+      "step": 650
+    },
+    {
+      "epoch": 0.610758750293634,
+      "eval_loss": 0.18974561989307404,
+      "eval_runtime": 488.3923,
+      "eval_samples_per_second": 1.937,
+      "eval_steps_per_second": 0.968,
+      "step": 650
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 2.838442087173462,
+      "learning_rate": 3.814446405769069e-06,
+      "loss": 0.214,
+      "step": 660
+    },
+    {
+      "epoch": 0.6295513272257458,
+      "grad_norm": 7.474781513214111,
+      "learning_rate": 3.6558220383822824e-06,
+      "loss": 0.2392,
+      "step": 670
+    },
+    {
+      "epoch": 0.6389476156918017,
+      "grad_norm": 5.7680511474609375,
+      "learning_rate": 3.4986430660940283e-06,
+      "loss": 0.2062,
+      "step": 680
+    },
+    {
+      "epoch": 0.6483439041578577,
+      "grad_norm": 3.3340532779693604,
+      "learning_rate": 3.3430785035159297e-06,
+      "loss": 0.1738,
+      "step": 690
+    },
+    {
+      "epoch": 0.6577401926239136,
+      "grad_norm": 2.487337350845337,
+      "learning_rate": 3.1892956292842103e-06,
+      "loss": 0.1546,
+      "step": 700
+    },
+    {
+      "epoch": 0.6577401926239136,
+      "eval_loss": 0.18141551315784454,
+      "eval_runtime": 504.0426,
+      "eval_samples_per_second": 1.877,
+      "eval_steps_per_second": 0.938,
+      "step": 700
+    },
+    {
+      "epoch": 0.6671364810899695,
+      "grad_norm": 4.324577331542969,
+      "learning_rate": 3.0374598061848936e-06,
+      "loss": 0.2037,
+      "step": 710
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 3.728818893432617,
+      "learning_rate": 2.8877343033391523e-06,
+      "loss": 0.14,
+      "step": 720
+    },
+    {
+      "epoch": 0.6859290580220813,
+      "grad_norm": 3.1286537647247314,
+      "learning_rate": 2.7402801206399454e-06,
+      "loss": 0.1721,
+      "step": 730
+    },
+    {
+      "epoch": 0.6953253464881372,
+      "grad_norm": 7.396164417266846,
+      "learning_rate": 2.595255815628774e-06,
+      "loss": 0.2586,
+      "step": 740
+    },
+    {
+      "epoch": 0.704721634954193,
+      "grad_norm": 1.8540730476379395,
+      "learning_rate": 2.4528173329986855e-06,
+      "loss": 0.1613,
+      "step": 750
+    },
+    {
+      "epoch": 0.704721634954193,
+      "eval_loss": 0.1746373176574707,
+      "eval_runtime": 482.272,
+      "eval_samples_per_second": 1.962,
+      "eval_steps_per_second": 0.981,
+      "step": 750
+    },
+    {
+      "epoch": 0.714117923420249,
+      "grad_norm": 1.6450875997543335,
+      "learning_rate": 2.313117836906897e-06,
+      "loss": 0.2041,
+      "step": 760
+    },
+    {
+      "epoch": 0.7235142118863049,
+      "grad_norm": 1.6683011054992676,
+      "learning_rate": 2.1763075462773002e-06,
+      "loss": 0.2033,
+      "step": 770
+    },
+    {
+      "epoch": 0.7329105003523608,
+      "grad_norm": 5.101831912994385,
+      "learning_rate": 2.0425335732700075e-06,
+      "loss": 0.2497,
+      "step": 780
+    },
+    {
+      "epoch": 0.7423067888184167,
+      "grad_norm": 10.428893089294434,
+      "learning_rate": 1.9119397650915774e-06,
+      "loss": 0.2354,
+      "step": 790
+    },
+    {
+      "epoch": 0.7517030772844726,
+      "grad_norm": 3.380574941635132,
+      "learning_rate": 1.7846665493160548e-06,
+      "loss": 0.0956,
+      "step": 800
+    },
+    {
+      "epoch": 0.7517030772844726,
+      "eval_loss": 0.1724964827299118,
+      "eval_runtime": 494.611,
+      "eval_samples_per_second": 1.913,
+      "eval_steps_per_second": 0.956,
+      "step": 800
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 3.29054594039917,
+      "learning_rate": 1.6608507828831572e-06,
+      "loss": 0.1711,
+      "step": 810
+    },
+    {
+      "epoch": 0.7704956542165845,
+      "grad_norm": 1.7452706098556519,
+      "learning_rate": 1.5406256049359359e-06,
+      "loss": 0.2362,
+      "step": 820
+    },
+    {
+      "epoch": 0.7798919426826404,
+      "grad_norm": 3.282259464263916,
+      "learning_rate": 1.4241202936562164e-06,
+      "loss": 0.1692,
+      "step": 830
+    },
+    {
+      "epoch": 0.7892882311486963,
+      "grad_norm": 2.6481103897094727,
+      "learning_rate": 1.311460127251708e-06,
+      "loss": 0.1608,
+      "step": 840
+    },
+    {
+      "epoch": 0.7986845196147522,
+      "grad_norm": 4.806708335876465,
+      "learning_rate": 1.202766249244306e-06,
+      "loss": 0.1692,
+      "step": 850
+    },
+    {
+      "epoch": 0.7986845196147522,
+      "eval_loss": 0.1683204621076584,
+      "eval_runtime": 536.8401,
+      "eval_samples_per_second": 1.762,
+      "eval_steps_per_second": 0.881,
+      "step": 850
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 3.949918031692505,
+      "learning_rate": 1.098155538204404e-06,
+      "loss": 0.1718,
+      "step": 860
+    },
+    {
+      "epoch": 0.817477096546864,
+      "grad_norm": 4.87109899520874,
+      "learning_rate": 9.977404820713315e-07,
+      "loss": 0.1425,
+      "step": 870
+    },
+    {
+      "epoch": 0.8268733850129198,
+      "grad_norm": 2.2142727375030518,
+      "learning_rate": 9.016290571950171e-07,
+      "loss": 0.1196,
+      "step": 880
+    },
+    {
+      "epoch": 0.8362696734789759,
+      "grad_norm": 1.4838513135910034,
+      "learning_rate": 8.099246122289861e-07,
+      "loss": 0.2077,
+      "step": 890
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 3.8143913745880127,
+      "learning_rate": 7.227257569995061e-07,
+      "loss": 0.1885,
+      "step": 900
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "eval_loss": 0.16525517404079437,
+      "eval_runtime": 525.2309,
+      "eval_samples_per_second": 1.801,
+      "eval_steps_per_second": 0.901,
+      "step": 900
+    },
+    {
+      "epoch": 0.8550622504110876,
+      "grad_norm": 4.804526329040527,
+      "learning_rate": 6.401262564704019e-07,
+      "loss": 0.2379,
+      "step": 910
+    },
+    {
+      "epoch": 0.8644585388771435,
+      "grad_norm": 4.881964683532715,
+      "learning_rate": 5.622149299175539e-07,
+      "loss": 0.2253,
+      "step": 920
+    },
+    {
+      "epoch": 0.8738548273431994,
+      "grad_norm": 3.667691230773926,
+      "learning_rate": 4.890755554214954e-07,
+      "loss": 0.1952,
+      "step": 930
+    },
+    {
+      "epoch": 0.8832511158092553,
+      "grad_norm": 2.946258306503296,
+      "learning_rate": 4.207867797808102e-07,
+      "loss": 0.1522,
+      "step": 940
+    },
+    {
+      "epoch": 0.8926474042753113,
+      "grad_norm": 6.754327774047852,
+      "learning_rate": 3.5742203394319606e-07,
+      "loss": 0.2799,
+      "step": 950
+    },
+    {
+      "epoch": 0.8926474042753113,
+      "eval_loss": 0.163659006357193,
+      "eval_runtime": 541.8924,
+      "eval_samples_per_second": 1.746,
+      "eval_steps_per_second": 0.873,
+      "step": 950
+    },
+    {
+      "epoch": 0.9020436927413672,
+      "grad_norm": 6.084792137145996,
+      "learning_rate": 2.9904945404513606e-07,
+      "loss": 0.173,
+      "step": 960
+    },
+    {
+      "epoch": 0.9114399812074231,
+      "grad_norm": 7.379616737365723,
+      "learning_rate": 2.457318081450899e-07,
+      "loss": 0.184,
+      "step": 970
+    },
+    {
+      "epoch": 0.920836269673479,
+      "grad_norm": 1.6431665420532227,
+      "learning_rate": 1.9752642872897078e-07,
+      "loss": 0.1533,
+      "step": 980
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 2.5774223804473877,
+      "learning_rate": 1.5448515106050165e-07,
+      "loss": 0.2073,
+      "step": 990
+    },
+    {
+      "epoch": 0.9396288466055908,
+      "grad_norm": 3.7589077949523926,
+      "learning_rate": 1.166542574427354e-07,
+      "loss": 0.1971,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9396288466055908,
+      "eval_loss": 0.16281382739543915,
+      "eval_runtime": 517.5907,
+      "eval_samples_per_second": 1.828,
+      "eval_steps_per_second": 0.914,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9490251350716467,
+      "grad_norm": 2.6644127368927,
+      "learning_rate": 8.407442745067552e-08,
+      "loss": 0.1787,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9584214235377027,
+      "grad_norm": 2.4552407264709473,
+      "learning_rate": 5.678069418851351e-08,
+      "loss": 0.1581,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9678177120037585,
+      "grad_norm": 4.062498569488525,
+      "learning_rate": 3.4802406618518195e-08,
+      "loss": 0.1776,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9772140004698144,
+      "grad_norm": 5.595784664154053,
+      "learning_rate": 1.816319800208466e-08,
+      "loss": 0.1669,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9866102889358703,
+      "grad_norm": 3.4040722846984863,
+      "learning_rate": 6.880960486877475e-09,
+      "loss": 0.1464,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9866102889358703,
+      "eval_loss": 0.16257165372371674,
+      "eval_runtime": 534.9845,
+      "eval_samples_per_second": 1.768,
+      "eval_steps_per_second": 0.884,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9960065774019262,
+      "grad_norm": 2.6516175270080566,
+      "learning_rate": 9.678258673995189e-10,
+      "loss": 0.2124,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0,
+      "step": 1065,
+      "total_flos": 57141526265856.0,
+      "train_loss": 0.2802479102018294,
+      "train_runtime": 34553.4877,
+      "train_samples_per_second": 0.246,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1065,
+  "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": 57141526265856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

web_rl_3b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63da21f419fbe8f8eed2994d1cd0666792bbccf954d1bdd55da81fbac49b6444
+size 8337