Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ web_rl_3b/checkpoint-1065/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 web_rl_3b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 web_rl_7b_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+web_rl_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

web_rl_7b/README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-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 [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the web_policy_sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1644
+
+## 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: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2649        | 0.3758 | 200  | 0.2261          |
+| 0.1551        | 0.7515 | 400  | 0.1739          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

web_rl_7b/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_7b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.16435356438159943,
+    "eval_runtime": 221.923,
+    "eval_samples_per_second": 4.263,
+    "eval_steps_per_second": 1.068,
+    "total_flos": 78811436154880.0,
+    "train_loss": 0.27306876374901345,
+    "train_runtime": 11552.2832,
+    "train_samples_per_second": 0.737,
+    "train_steps_per_second": 0.046
+}

web_rl_7b/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_7b/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

web_rl_7b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.16435356438159943,
+    "eval_runtime": 221.923,
+    "eval_samples_per_second": 4.263,
+    "eval_steps_per_second": 1.068
+}

web_rl_7b/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_7b/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271b5676143dcf230969f3e5eea6e3a41cfe34a9b91e5546fb8e9c51272af92a
+size 4877660776

web_rl_7b/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b87f1157593b4d9707108b5286705a44b65873fbb3e34ebfdec91cb8bd85e5
+size 4932751008

web_rl_7b/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82573a29c2891b078a2a3a61f31a1f336155ab94daf7ed437051736bad46cb7
+size 4330865200

web_rl_7b/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1629a3cb96b7f16b707eb77e0452dca30662dcd9e82f535d9cb0059178bc105
+size 1089994880

web_rl_7b/model.safetensors.index.json

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

web_rl_7b/runs/Nov24_12-59-55_hgx007/events.out.tfevents.1763961404.hgx007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7d2defb13ee11652528b07e369d38c2ec76b182bc7cf64f981fd16a6f49d5a
+size 18128

web_rl_7b/runs/Nov24_12-59-55_hgx007/events.out.tfevents.1763973209.hgx007

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953d1808710b9ee4e9cfdf8de830c65547468653901453abc1afad294193e7e0
+size 311

web_rl_7b/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_7b/tokenizer.json

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

web_rl_7b/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_7b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 78811436154880.0,
+    "train_loss": 0.27306876374901345,
+    "train_runtime": 11552.2832,
+    "train_samples_per_second": 0.737,
+    "train_steps_per_second": 0.046
+}

web_rl_7b/trainer_log.jsonl

@@ -0,0 +1,56 @@
+{"current_steps": 10, "total_steps": 533, "loss": 1.7708, "lr": 1.6666666666666667e-06, "epoch": 0.018788163457022077, "percentage": 1.88, "elapsed_time": "0:03:56", "remaining_time": "3:26:02"}
+{"current_steps": 20, "total_steps": 533, "loss": 0.8157, "lr": 3.5185185185185187e-06, "epoch": 0.03757632691404415, "percentage": 3.75, "elapsed_time": "0:07:18", "remaining_time": "3:07:31"}
+{"current_steps": 30, "total_steps": 533, "loss": 0.5049, "lr": 5.370370370370371e-06, "epoch": 0.05636449037106623, "percentage": 5.63, "elapsed_time": "0:10:40", "remaining_time": "2:59:02"}
+{"current_steps": 40, "total_steps": 533, "loss": 0.4008, "lr": 7.222222222222223e-06, "epoch": 0.0751526538280883, "percentage": 7.5, "elapsed_time": "0:14:12", "remaining_time": "2:55:03"}
+{"current_steps": 50, "total_steps": 533, "loss": 0.3481, "lr": 9.074074074074075e-06, "epoch": 0.09394081728511038, "percentage": 9.38, "elapsed_time": "0:17:34", "remaining_time": "2:49:44"}
+{"current_steps": 60, "total_steps": 533, "loss": 0.3233, "lr": 9.997311749002358e-06, "epoch": 0.11272898074213246, "percentage": 11.26, "elapsed_time": "0:21:00", "remaining_time": "2:45:36"}
+{"current_steps": 70, "total_steps": 533, "loss": 0.2962, "lr": 9.975823081977089e-06, "epoch": 0.13151714419915453, "percentage": 13.13, "elapsed_time": "0:24:20", "remaining_time": "2:41:02"}
+{"current_steps": 80, "total_steps": 533, "loss": 0.3505, "lr": 9.93293815016874e-06, "epoch": 0.1503053076561766, "percentage": 15.01, "elapsed_time": "0:27:53", "remaining_time": "2:37:54"}
+{"current_steps": 90, "total_steps": 533, "loss": 0.341, "lr": 9.868841360727856e-06, "epoch": 0.1690934711131987, "percentage": 16.89, "elapsed_time": "0:31:24", "remaining_time": "2:34:37"}
+{"current_steps": 100, "total_steps": 533, "loss": 0.3644, "lr": 9.783808332754242e-06, "epoch": 0.18788163457022075, "percentage": 18.76, "elapsed_time": "0:34:50", "remaining_time": "2:30:52"}
+{"current_steps": 110, "total_steps": 533, "loss": 0.2572, "lr": 9.678204712122328e-06, "epoch": 0.20666979802724283, "percentage": 20.64, "elapsed_time": "0:38:15", "remaining_time": "2:27:05"}
+{"current_steps": 120, "total_steps": 533, "loss": 0.2801, "lr": 9.552484599187344e-06, "epoch": 0.22545796148426492, "percentage": 22.51, "elapsed_time": "0:41:45", "remaining_time": "2:23:43"}
+{"current_steps": 130, "total_steps": 533, "loss": 0.2438, "lr": 9.407188596133212e-06, "epoch": 0.244246124941287, "percentage": 24.39, "elapsed_time": "0:45:13", "remaining_time": "2:20:11"}
+{"current_steps": 140, "total_steps": 533, "loss": 0.2426, "lr": 9.242941482358646e-06, "epoch": 0.26303428839830906, "percentage": 26.27, "elapsed_time": "0:48:39", "remaining_time": "2:16:35"}
+{"current_steps": 150, "total_steps": 533, "loss": 0.2699, "lr": 9.060449527897424e-06, "epoch": 0.28182245185533117, "percentage": 28.14, "elapsed_time": "0:52:08", "remaining_time": "2:13:06"}
+{"current_steps": 160, "total_steps": 533, "loss": 0.2438, "lr": 8.860497456425226e-06, "epoch": 0.3006106153123532, "percentage": 30.02, "elapsed_time": "0:55:48", "remaining_time": "2:10:05"}
+{"current_steps": 170, "total_steps": 533, "loss": 0.2703, "lr": 8.643945070912269e-06, "epoch": 0.3193987787693753, "percentage": 31.89, "elapsed_time": "0:59:09", "remaining_time": "2:06:18"}
+{"current_steps": 180, "total_steps": 533, "loss": 0.2858, "lr": 8.411723556431555e-06, "epoch": 0.3381869422263974, "percentage": 33.77, "elapsed_time": "1:02:33", "remaining_time": "2:02:41"}
+{"current_steps": 190, "total_steps": 533, "loss": 0.1675, "lr": 8.164831476020856e-06, "epoch": 0.35697510568341945, "percentage": 35.65, "elapsed_time": "1:06:05", "remaining_time": "1:59:18"}
+{"current_steps": 200, "total_steps": 533, "loss": 0.2649, "lr": 7.904330476816391e-06, "epoch": 0.3757632691404415, "percentage": 37.52, "elapsed_time": "1:09:28", "remaining_time": "1:55:40"}
+{"current_steps": 200, "total_steps": 533, "eval_loss": 0.22606511414051056, "epoch": 0.3757632691404415, "percentage": 37.52, "elapsed_time": "1:13:11", "remaining_time": "2:01:51"}
+{"current_steps": 210, "total_steps": 533, "loss": 0.2252, "lr": 7.631340724922023e-06, "epoch": 0.3945514325974636, "percentage": 39.4, "elapsed_time": "1:16:35", "remaining_time": "1:57:48"}
+{"current_steps": 220, "total_steps": 533, "loss": 0.2396, "lr": 7.347036088644232e-06, "epoch": 0.41333959605448567, "percentage": 41.28, "elapsed_time": "1:19:59", "remaining_time": "1:53:48"}
+{"current_steps": 230, "total_steps": 533, "loss": 0.2902, "lr": 7.0526390908052e-06, "epoch": 0.4321277595115077, "percentage": 43.15, "elapsed_time": "1:23:28", "remaining_time": "1:49:57"}
+{"current_steps": 240, "total_steps": 533, "loss": 0.2185, "lr": 6.7494156518392625e-06, "epoch": 0.45091592296852984, "percentage": 45.03, "elapsed_time": "1:27:07", "remaining_time": "1:46:22"}
+{"current_steps": 250, "total_steps": 533, "loss": 0.2483, "lr": 6.43866964627766e-06, "epoch": 0.4697040864255519, "percentage": 46.9, "elapsed_time": "1:30:37", "remaining_time": "1:42:34"}
+{"current_steps": 260, "total_steps": 533, "loss": 0.2132, "lr": 6.121737296028959e-06, "epoch": 0.488492249882574, "percentage": 48.78, "elapsed_time": "1:33:52", "remaining_time": "1:38:33"}
+{"current_steps": 270, "total_steps": 533, "loss": 0.2062, "lr": 5.799981424564275e-06, "epoch": 0.5072804133395961, "percentage": 50.66, "elapsed_time": "1:37:24", "remaining_time": "1:34:52"}
+{"current_steps": 280, "total_steps": 533, "loss": 0.1665, "lr": 5.474785596714581e-06, "epoch": 0.5260685767966181, "percentage": 52.53, "elapsed_time": "1:40:47", "remaining_time": "1:31:03"}
+{"current_steps": 290, "total_steps": 533, "loss": 0.1902, "lr": 5.1475481692792235e-06, "epoch": 0.5448567402536402, "percentage": 54.41, "elapsed_time": "1:44:10", "remaining_time": "1:27:17"}
+{"current_steps": 300, "total_steps": 533, "loss": 0.2333, "lr": 4.819676278028305e-06, "epoch": 0.5636449037106623, "percentage": 56.29, "elapsed_time": "1:47:31", "remaining_time": "1:23:30"}
+{"current_steps": 310, "total_steps": 533, "loss": 0.2023, "lr": 4.4925797869550865e-06, "epoch": 0.5824330671676844, "percentage": 58.16, "elapsed_time": "1:51:12", "remaining_time": "1:19:59"}
+{"current_steps": 320, "total_steps": 533, "loss": 0.1776, "lr": 4.167665225796925e-06, "epoch": 0.6012212306247064, "percentage": 60.04, "elapsed_time": "1:54:30", "remaining_time": "1:16:12"}
+{"current_steps": 330, "total_steps": 533, "loss": 0.2364, "lr": 3.846329741893646e-06, "epoch": 0.6200093940817285, "percentage": 61.91, "elapsed_time": "1:58:02", "remaining_time": "1:12:37"}
+{"current_steps": 340, "total_steps": 533, "loss": 0.2192, "lr": 3.52995509239065e-06, "epoch": 0.6387975575387506, "percentage": 63.79, "elapsed_time": "2:01:28", "remaining_time": "1:08:57"}
+{"current_steps": 350, "total_steps": 533, "loss": 0.1601, "lr": 3.2199017026205744e-06, "epoch": 0.6575857209957726, "percentage": 65.67, "elapsed_time": "2:04:51", "remaining_time": "1:05:17"}
+{"current_steps": 360, "total_steps": 533, "loss": 0.1688, "lr": 2.917502816212685e-06, "epoch": 0.6763738844527948, "percentage": 67.54, "elapsed_time": "2:08:21", "remaining_time": "1:01:40"}
+{"current_steps": 370, "total_steps": 533, "loss": 0.2083, "lr": 2.6240587620848512e-06, "epoch": 0.6951620479098168, "percentage": 69.42, "elapsed_time": "2:11:47", "remaining_time": "0:58:03"}
+{"current_steps": 380, "total_steps": 533, "loss": 0.181, "lr": 2.340831362970257e-06, "epoch": 0.7139502113668389, "percentage": 71.29, "elapsed_time": "2:15:15", "remaining_time": "0:54:27"}
+{"current_steps": 390, "total_steps": 533, "loss": 0.2234, "lr": 2.0690385095224557e-06, "epoch": 0.732738374823861, "percentage": 73.17, "elapsed_time": "2:18:42", "remaining_time": "0:50:51"}
+{"current_steps": 400, "total_steps": 533, "loss": 0.1551, "lr": 1.8098489233303595e-06, "epoch": 0.751526538280883, "percentage": 75.05, "elapsed_time": "2:22:16", "remaining_time": "0:47:18"}
+{"current_steps": 400, "total_steps": 533, "eval_loss": 0.17390167713165283, "epoch": 0.751526538280883, "percentage": 75.05, "elapsed_time": "2:25:58", "remaining_time": "0:48:32"}
+{"current_steps": 410, "total_steps": 533, "loss": 0.1899, "lr": 1.5643771313624394e-06, "epoch": 0.7703147017379052, "percentage": 76.92, "elapsed_time": "2:29:27", "remaining_time": "0:44:50"}
+{"current_steps": 420, "total_steps": 533, "loss": 0.1615, "lr": 1.3336786734502294e-06, "epoch": 0.7891028651949272, "percentage": 78.8, "elapsed_time": "2:33:05", "remaining_time": "0:41:11"}
+{"current_steps": 430, "total_steps": 533, "loss": 0.1671, "lr": 1.1187455634192307e-06, "epoch": 0.8078910286519493, "percentage": 80.68, "elapsed_time": "2:36:42", "remaining_time": "0:37:32"}
+{"current_steps": 440, "total_steps": 533, "loss": 0.1275, "lr": 9.205020233844736e-07, "epoch": 0.8266791921089713, "percentage": 82.55, "elapsed_time": "2:40:21", "remaining_time": "0:33:53"}
+{"current_steps": 450, "total_steps": 533, "loss": 0.1797, "lr": 7.398005095535565e-07, "epoch": 0.8454673555659934, "percentage": 84.43, "elapsed_time": "2:43:39", "remaining_time": "0:30:11"}
+{"current_steps": 460, "total_steps": 533, "loss": 0.2238, "lr": 5.774180466262985e-07, "epoch": 0.8642555190230155, "percentage": 86.3, "elapsed_time": "2:47:05", "remaining_time": "0:26:30"}
+{"current_steps": 470, "total_steps": 533, "loss": 0.1766, "lr": 4.340528865533161e-07, "epoch": 0.8830436824800376, "percentage": 88.18, "elapsed_time": "2:50:31", "remaining_time": "0:22:51"}
+{"current_steps": 480, "total_steps": 533, "loss": 0.2085, "lr": 3.103215060209902e-07, "epoch": 0.9018318459370597, "percentage": 90.06, "elapsed_time": "2:54:03", "remaining_time": "0:19:13"}
+{"current_steps": 490, "total_steps": 533, "loss": 0.1595, "lr": 2.0675595557376916e-07, "epoch": 0.9206200093940817, "percentage": 91.93, "elapsed_time": "2:57:32", "remaining_time": "0:15:34"}
+{"current_steps": 500, "total_steps": 533, "loss": 0.2025, "lr": 1.2380157177271369e-07, "epoch": 0.9394081728511038, "percentage": 93.81, "elapsed_time": "3:00:58", "remaining_time": "0:11:56"}
+{"current_steps": 510, "total_steps": 533, "loss": 0.1641, "lr": 6.181506222809885e-08, "epoch": 0.9581963363081258, "percentage": 95.68, "elapsed_time": "3:04:27", "remaining_time": "0:08:19"}
+{"current_steps": 520, "total_steps": 533, "loss": 0.1658, "lr": 2.1062971740523076e-08, "epoch": 0.976984499765148, "percentage": 97.56, "elapsed_time": "3:07:46", "remaining_time": "0:04:41"}
+{"current_steps": 530, "total_steps": 533, "loss": 0.1645, "lr": 1.7205361461825054e-09, "epoch": 0.9957726632221701, "percentage": 99.44, "elapsed_time": "3:11:15", "remaining_time": "0:01:04"}
+{"current_steps": 533, "total_steps": 533, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:12:32", "remaining_time": "0:00:00"}

web_rl_7b/trainer_state.json

@@ -0,0 +1,430 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 533,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018788163457022077,
+      "grad_norm": 39.5539436340332,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.7708,
+      "step": 10
+    },
+    {
+      "epoch": 0.03757632691404415,
+      "grad_norm": 15.056221961975098,
+      "learning_rate": 3.5185185185185187e-06,
+      "loss": 0.8157,
+      "step": 20
+    },
+    {
+      "epoch": 0.05636449037106623,
+      "grad_norm": 8.456525802612305,
+      "learning_rate": 5.370370370370371e-06,
+      "loss": 0.5049,
+      "step": 30
+    },
+    {
+      "epoch": 0.0751526538280883,
+      "grad_norm": 9.841835021972656,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.4008,
+      "step": 40
+    },
+    {
+      "epoch": 0.09394081728511038,
+      "grad_norm": 8.734881401062012,
+      "learning_rate": 9.074074074074075e-06,
+      "loss": 0.3481,
+      "step": 50
+    },
+    {
+      "epoch": 0.11272898074213246,
+      "grad_norm": 5.559770107269287,
+      "learning_rate": 9.997311749002358e-06,
+      "loss": 0.3233,
+      "step": 60
+    },
+    {
+      "epoch": 0.13151714419915453,
+      "grad_norm": 9.457917213439941,
+      "learning_rate": 9.975823081977089e-06,
+      "loss": 0.2962,
+      "step": 70
+    },
+    {
+      "epoch": 0.1503053076561766,
+      "grad_norm": 8.458663940429688,
+      "learning_rate": 9.93293815016874e-06,
+      "loss": 0.3505,
+      "step": 80
+    },
+    {
+      "epoch": 0.1690934711131987,
+      "grad_norm": 5.281663417816162,
+      "learning_rate": 9.868841360727856e-06,
+      "loss": 0.341,
+      "step": 90
+    },
+    {
+      "epoch": 0.18788163457022075,
+      "grad_norm": 4.8133440017700195,
+      "learning_rate": 9.783808332754242e-06,
+      "loss": 0.3644,
+      "step": 100
+    },
+    {
+      "epoch": 0.20666979802724283,
+      "grad_norm": 5.978756904602051,
+      "learning_rate": 9.678204712122328e-06,
+      "loss": 0.2572,
+      "step": 110
+    },
+    {
+      "epoch": 0.22545796148426492,
+      "grad_norm": 3.6604723930358887,
+      "learning_rate": 9.552484599187344e-06,
+      "loss": 0.2801,
+      "step": 120
+    },
+    {
+      "epoch": 0.244246124941287,
+      "grad_norm": 5.864062786102295,
+      "learning_rate": 9.407188596133212e-06,
+      "loss": 0.2438,
+      "step": 130
+    },
+    {
+      "epoch": 0.26303428839830906,
+      "grad_norm": 4.652751445770264,
+      "learning_rate": 9.242941482358646e-06,
+      "loss": 0.2426,
+      "step": 140
+    },
+    {
+      "epoch": 0.28182245185533117,
+      "grad_norm": 7.59506368637085,
+      "learning_rate": 9.060449527897424e-06,
+      "loss": 0.2699,
+      "step": 150
+    },
+    {
+      "epoch": 0.3006106153123532,
+      "grad_norm": 5.299258232116699,
+      "learning_rate": 8.860497456425226e-06,
+      "loss": 0.2438,
+      "step": 160
+    },
+    {
+      "epoch": 0.3193987787693753,
+      "grad_norm": 6.822812080383301,
+      "learning_rate": 8.643945070912269e-06,
+      "loss": 0.2703,
+      "step": 170
+    },
+    {
+      "epoch": 0.3381869422263974,
+      "grad_norm": 4.299904823303223,
+      "learning_rate": 8.411723556431555e-06,
+      "loss": 0.2858,
+      "step": 180
+    },
+    {
+      "epoch": 0.35697510568341945,
+      "grad_norm": 4.70183801651001,
+      "learning_rate": 8.164831476020856e-06,
+      "loss": 0.1675,
+      "step": 190
+    },
+    {
+      "epoch": 0.3757632691404415,
+      "grad_norm": 6.74561071395874,
+      "learning_rate": 7.904330476816391e-06,
+      "loss": 0.2649,
+      "step": 200
+    },
+    {
+      "epoch": 0.3757632691404415,
+      "eval_loss": 0.22606511414051056,
+      "eval_runtime": 222.2942,
+      "eval_samples_per_second": 4.256,
+      "eval_steps_per_second": 1.066,
+      "step": 200
+    },
+    {
+      "epoch": 0.3945514325974636,
+      "grad_norm": 5.191539287567139,
+      "learning_rate": 7.631340724922023e-06,
+      "loss": 0.2252,
+      "step": 210
+    },
+    {
+      "epoch": 0.41333959605448567,
+      "grad_norm": 6.738773822784424,
+      "learning_rate": 7.347036088644232e-06,
+      "loss": 0.2396,
+      "step": 220
+    },
+    {
+      "epoch": 0.4321277595115077,
+      "grad_norm": 5.1947808265686035,
+      "learning_rate": 7.0526390908052e-06,
+      "loss": 0.2902,
+      "step": 230
+    },
+    {
+      "epoch": 0.45091592296852984,
+      "grad_norm": 4.540430545806885,
+      "learning_rate": 6.7494156518392625e-06,
+      "loss": 0.2185,
+      "step": 240
+    },
+    {
+      "epoch": 0.4697040864255519,
+      "grad_norm": 7.267935752868652,
+      "learning_rate": 6.43866964627766e-06,
+      "loss": 0.2483,
+      "step": 250
+    },
+    {
+      "epoch": 0.488492249882574,
+      "grad_norm": 6.775832653045654,
+      "learning_rate": 6.121737296028959e-06,
+      "loss": 0.2132,
+      "step": 260
+    },
+    {
+      "epoch": 0.5072804133395961,
+      "grad_norm": 4.134191036224365,
+      "learning_rate": 5.799981424564275e-06,
+      "loss": 0.2062,
+      "step": 270
+    },
+    {
+      "epoch": 0.5260685767966181,
+      "grad_norm": 3.4992332458496094,
+      "learning_rate": 5.474785596714581e-06,
+      "loss": 0.1665,
+      "step": 280
+    },
+    {
+      "epoch": 0.5448567402536402,
+      "grad_norm": 3.856785297393799,
+      "learning_rate": 5.1475481692792235e-06,
+      "loss": 0.1902,
+      "step": 290
+    },
+    {
+      "epoch": 0.5636449037106623,
+      "grad_norm": 5.150210857391357,
+      "learning_rate": 4.819676278028305e-06,
+      "loss": 0.2333,
+      "step": 300
+    },
+    {
+      "epoch": 0.5824330671676844,
+      "grad_norm": 5.201061725616455,
+      "learning_rate": 4.4925797869550865e-06,
+      "loss": 0.2023,
+      "step": 310
+    },
+    {
+      "epoch": 0.6012212306247064,
+      "grad_norm": 5.331509590148926,
+      "learning_rate": 4.167665225796925e-06,
+      "loss": 0.1776,
+      "step": 320
+    },
+    {
+      "epoch": 0.6200093940817285,
+      "grad_norm": 3.550278902053833,
+      "learning_rate": 3.846329741893646e-06,
+      "loss": 0.2364,
+      "step": 330
+    },
+    {
+      "epoch": 0.6387975575387506,
+      "grad_norm": 5.495516300201416,
+      "learning_rate": 3.52995509239065e-06,
+      "loss": 0.2192,
+      "step": 340
+    },
+    {
+      "epoch": 0.6575857209957726,
+      "grad_norm": 4.215266704559326,
+      "learning_rate": 3.2199017026205744e-06,
+      "loss": 0.1601,
+      "step": 350
+    },
+    {
+      "epoch": 0.6763738844527948,
+      "grad_norm": 3.173532247543335,
+      "learning_rate": 2.917502816212685e-06,
+      "loss": 0.1688,
+      "step": 360
+    },
+    {
+      "epoch": 0.6951620479098168,
+      "grad_norm": 6.164701461791992,
+      "learning_rate": 2.6240587620848512e-06,
+      "loss": 0.2083,
+      "step": 370
+    },
+    {
+      "epoch": 0.7139502113668389,
+      "grad_norm": 2.307567596435547,
+      "learning_rate": 2.340831362970257e-06,
+      "loss": 0.181,
+      "step": 380
+    },
+    {
+      "epoch": 0.732738374823861,
+      "grad_norm": 5.143068313598633,
+      "learning_rate": 2.0690385095224557e-06,
+      "loss": 0.2234,
+      "step": 390
+    },
+    {
+      "epoch": 0.751526538280883,
+      "grad_norm": 2.648653030395508,
+      "learning_rate": 1.8098489233303595e-06,
+      "loss": 0.1551,
+      "step": 400
+    },
+    {
+      "epoch": 0.751526538280883,
+      "eval_loss": 0.17390167713165283,
+      "eval_runtime": 222.2168,
+      "eval_samples_per_second": 4.257,
+      "eval_steps_per_second": 1.067,
+      "step": 400
+    },
+    {
+      "epoch": 0.7703147017379052,
+      "grad_norm": 3.061445713043213,
+      "learning_rate": 1.5643771313624394e-06,
+      "loss": 0.1899,
+      "step": 410
+    },
+    {
+      "epoch": 0.7891028651949272,
+      "grad_norm": 3.341491460800171,
+      "learning_rate": 1.3336786734502294e-06,
+      "loss": 0.1615,
+      "step": 420
+    },
+    {
+      "epoch": 0.8078910286519493,
+      "grad_norm": 3.6715078353881836,
+      "learning_rate": 1.1187455634192307e-06,
+      "loss": 0.1671,
+      "step": 430
+    },
+    {
+      "epoch": 0.8266791921089713,
+      "grad_norm": 2.944624423980713,
+      "learning_rate": 9.205020233844736e-07,
+      "loss": 0.1275,
+      "step": 440
+    },
+    {
+      "epoch": 0.8454673555659934,
+      "grad_norm": 4.107908725738525,
+      "learning_rate": 7.398005095535565e-07,
+      "loss": 0.1797,
+      "step": 450
+    },
+    {
+      "epoch": 0.8642555190230155,
+      "grad_norm": 5.744738578796387,
+      "learning_rate": 5.774180466262985e-07,
+      "loss": 0.2238,
+      "step": 460
+    },
+    {
+      "epoch": 0.8830436824800376,
+      "grad_norm": 3.282698631286621,
+      "learning_rate": 4.340528865533161e-07,
+      "loss": 0.1766,
+      "step": 470
+    },
+    {
+      "epoch": 0.9018318459370597,
+      "grad_norm": 6.375194549560547,
+      "learning_rate": 3.103215060209902e-07,
+      "loss": 0.2085,
+      "step": 480
+    },
+    {
+      "epoch": 0.9206200093940817,
+      "grad_norm": 2.820821523666382,
+      "learning_rate": 2.0675595557376916e-07,
+      "loss": 0.1595,
+      "step": 490
+    },
+    {
+      "epoch": 0.9394081728511038,
+      "grad_norm": 3.918117046356201,
+      "learning_rate": 1.2380157177271369e-07,
+      "loss": 0.2025,
+      "step": 500
+    },
+    {
+      "epoch": 0.9581963363081258,
+      "grad_norm": 2.6554410457611084,
+      "learning_rate": 6.181506222809885e-08,
+      "loss": 0.1641,
+      "step": 510
+    },
+    {
+      "epoch": 0.976984499765148,
+      "grad_norm": 4.8615899085998535,
+      "learning_rate": 2.1062971740523076e-08,
+      "loss": 0.1658,
+      "step": 520
+    },
+    {
+      "epoch": 0.9957726632221701,
+      "grad_norm": 3.5291943550109863,
+      "learning_rate": 1.7205361461825054e-09,
+      "loss": 0.1645,
+      "step": 530
+    },
+    {
+      "epoch": 1.0,
+      "step": 533,
+      "total_flos": 78811436154880.0,
+      "train_loss": 0.27306876374901345,
+      "train_runtime": 11552.2832,
+      "train_samples_per_second": 0.737,
+      "train_steps_per_second": 0.046
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 533,
+  "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": 78811436154880.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

web_rl_7b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fdbcc4824b2971a1119d8f38b0c5fb8bdd2e575b8cef483a3da9c2ed86f95d
+size 8337