Upload RL model and trajectories

.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
+*.jsonl filter=lfs diff=lfs merge=lfs -text
+**/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,35 @@
 ---
 license: mit
+library_name: transformers
+tags:
+- reinforcement-learning
+- grpo
+- math
+- trajectories
 ---
+
+# ES RL Model and Trajectories
+
+This repository contains the step-20 Hugging Face export for
+`qwen35-4b-math-grpo-dapo400-e15-seed1`, the corresponding RL trajectories,
+and the latest evaluation outputs.
+
+## Contents
+
+- `models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/`: Hugging Face model export with 4 safetensors shards, tokenizer files, and generation/config metadata.
+- `trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/`: raw train and validation trajectory JSONL files.
+- `trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/`: exported train/validation trajectory JSONL files for steps 1-20.
+- `eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/`: evaluation summary and per-sample outputs.
+
+## Evaluation
+
+Evaluation was run with 4 samples per item, temperature 1.0, top-p 1.0,
+top-k 40, presence penalty 2.0, and `paper_react_cli` mode.
+
+| Dataset | Records | Mean Score | Max@4 |
+| --- | ---: | ---: | ---: |
+| DAPO100 | 400 | 0.6875 | 0.8300 |
+| AIME2026 | 120 | 0.5833 | 0.7667 |
+
+The full optimizer state, Megatron/FSDP training checkpoint files, tool
+workspaces, server logs, and cache directories are not included in this repo.

eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/outputs/aime2026.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237263f4e2284a6399266cceaec1bfbc223bdef283cdc6ac9c91837100d6968e
+size 5703366

eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/outputs/dapo100.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6b977258e101c2dc5dd603199434d8d7c4f6d8a3b0477e050bac97f9f38176
+size 13129354

eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/summary.json

@@ -0,0 +1,98 @@
+{
+  "dapo100": {
+    "output": "/data/external/wangzk_team/chenrs/project/es/Dynamic-Agent/runs/multiturn_grpo/eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/outputs/dapo100.jsonl",
+    "records": 400,
+    "valid_records": 400,
+    "mean_score": 0.6875,
+    "max@4": 0.83,
+    "score_methods": {
+      "math_paper_react_cli_exact_fallback": 388,
+      "math_paper_react_cli_missing_final_answer": 12
+    },
+    "by_sample": {
+      "0": {
+        "count": 100,
+        "mean_score": 0.63
+      },
+      "1": {
+        "count": 100,
+        "mean_score": 0.73
+      },
+      "2": {
+        "count": 100,
+        "mean_score": 0.7
+      },
+      "3": {
+        "count": 100,
+        "mean_score": 0.69
+      }
+    },
+    "docvqa_diagnostics": null,
+    "dataset": "dapo100",
+    "kind": "math",
+    "data": "/data/external/wangzk_team/chenrs/project/es/Dynamic-Agent/data/trace2skill/math_reasoning/dapo_test.jsonl",
+    "items": 100,
+    "samples": 4,
+    "expected_records": 400,
+    "enable_thinking": false,
+    "mode": "paper_react_cli",
+    "math_max_turns": 50,
+    "docvqa_max_turns": null,
+    "sampling": {
+      "temperature": 1.0,
+      "top_p": 1.0,
+      "top_k": 40,
+      "min_p": 0.0,
+      "presence_penalty": 2.0,
+      "repetition_penalty": 1.0
+    }
+  },
+  "aime2026": {
+    "output": "/data/external/wangzk_team/chenrs/project/es/Dynamic-Agent/runs/multiturn_grpo/eval/qwen35-4b-math-grpo-dapo400-e15-seed1/step20_eval_50x4096_rerun_20260805/outputs/aime2026.jsonl",
+    "records": 120,
+    "valid_records": 120,
+    "mean_score": 0.5833333333333334,
+    "max@4": 0.7666666666666667,
+    "score_methods": {
+      "math_paper_react_cli_exact_fallback": 112,
+      "math_paper_react_cli_missing_final_answer": 8
+    },
+    "by_sample": {
+      "0": {
+        "count": 30,
+        "mean_score": 0.6666666666666666
+      },
+      "1": {
+        "count": 30,
+        "mean_score": 0.5666666666666667
+      },
+      "2": {
+        "count": 30,
+        "mean_score": 0.5333333333333333
+      },
+      "3": {
+        "count": 30,
+        "mean_score": 0.5666666666666667
+      }
+    },
+    "docvqa_diagnostics": null,
+    "dataset": "aime2026",
+    "kind": "math",
+    "data": "/data/external/wangzk_team/chenrs/project/es/Dynamic-Agent/data/trace2skill/math_reasoning/aime_2026.jsonl",
+    "items": 30,
+    "samples": 4,
+    "expected_records": 120,
+    "enable_thinking": false,
+    "mode": "paper_react_cli",
+    "math_max_turns": 50,
+    "docvqa_max_turns": null,
+    "sampling": {
+      "temperature": 1.0,
+      "top_p": 1.0,
+      "top_k": 40,
+      "min_p": 0.0,
+      "presence_penalty": 2.0,
+      "repetition_penalty": 1.0
+    }
+  }
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</think>": 248069,
+  "</tool_call>": 248059,
+  "</tool_response>": 248067,
+  "<think>": 248068,
+  "<tool_call>": 248058,
+  "<tool_response>": 248066,
+  "<tts_pad>": 248072,
+  "<tts_text_bos>": 248073,
+  "<tts_text_bos_single>": 248075,
+  "<tts_text_eod>": 248074,
+  "<|audio_end|>": 248071,
+  "<|audio_pad|>": 248076,
+  "<|audio_start|>": 248070,
+  "<|box_end|>": 248050,
+  "<|box_start|>": 248049,
+  "<|endoftext|>": 248044,
+  "<|file_sep|>": 248065,
+  "<|fim_middle|>": 248061,
+  "<|fim_pad|>": 248063,
+  "<|fim_prefix|>": 248060,
+  "<|fim_suffix|>": 248062,
+  "<|im_end|>": 248046,
+  "<|im_start|>": 248045,
+  "<|image_pad|>": 248056,
+  "<|object_ref_end|>": 248048,
+  "<|object_ref_start|>": 248047,
+  "<|quad_end|>": 248052,
+  "<|quad_start|>": 248051,
+  "<|repo_name|>": 248064,
+  "<|video_pad|>": 248057,
+  "<|vision_end|>": 248054,
+  "<|vision_pad|>": 248055,
+  "<|vision_start|>": 248053
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3NextForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31
+  ],
+  "model_type": "qwen3_next",
+  "moe_intermediate_size": 512,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 0,
+  "num_experts_per_tok": 0,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 248044,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 248320
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248046,
+  "pad_token_id": 248044,
+  "transformers_version": "4.57.1"
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7e0070c83e436a160e16806df9621354c88da3d5e9e879465a2ff555bc3349
+size 4948083944

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ce424bb17412d50a446b2085d0b1ed37dc64d7e252e575a9531a7935b744ce
+size 4997765600

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055f625132996f5ee4882d8c68dd592b299c27f84f09935e58f84b7454e16e21
+size 4997765672

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4271e856225bf2bc8850839f37c18c592440fd7e6f11b6346168c8fbcf4ed463
+size 4422230088

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/model.safetensors.index.json

@@ -0,0 +1,387 @@
+{
+  "metadata": {
+    "total_parameters": 4841450496,
+    "total_size": 19365801984
+  },
+  "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.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.in_proj_ba.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.in_proj_qkvz.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.linear_attn.out_proj.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.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.in_proj_ba.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.in_proj_qkvz.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.linear_attn.out_proj.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.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.linear_attn.out_proj.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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.linear_attn.out_proj.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.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.linear_attn.out_proj.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.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.linear_attn.out_proj.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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.linear_attn.out_proj.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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.in_proj_ba.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.in_proj_qkvz.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.linear_attn.out_proj.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.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.linear_attn.out_proj.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.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.linear_attn.out_proj.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.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.linear_attn.out_proj.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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.linear_attn.out_proj.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.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.linear_attn.out_proj.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.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.in_proj_ba.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.in_proj_qkvz.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.linear_attn.out_proj.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.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.in_proj_ba.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.in_proj_qkvz.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.in_proj_ba.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.in_proj_qkvz.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.in_proj_ba.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.in_proj_qkvz.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.in_proj_ba.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.in_proj_qkvz.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.linear_attn.out_proj.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.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.in_proj_ba.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.in_proj_qkvz.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.linear_attn.out_proj.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.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.in_proj_ba.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.in_proj_qkvz.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.linear_attn.out_proj.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.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "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|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<|image_pad|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

models/qwen35-4b-math-grpo-dapo400-e15-seed1-step20/tokenizer_config.json

@@ -0,0 +1,312 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "fix_mistral_regex": true,
+  "image_token": "<|image_pad|>",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_001.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955c08cc00e5598ab9692cef1c8b6f4db1f1d400af24e26fb17777a4572647cb
+size 3843434

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_002.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87cbc593cea2e944490459cc0e2b9e0b4ec88089d6850f7d2f842bfd2718a39
+size 4260850

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_003.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c77791f84aa7732ec9fdc8ecba7bef1a47e9e47d4a09dd7a2573c821bdafdee
+size 4418909

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_004.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69bb46acd028a1d10ae499a63dd41d7a48d907366e89e8854a59b0e8044d572
+size 3970785

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_005.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d702c8107e3946e5e627d7ed56190eecdff87ce023e7044d3658a1eb55e6928
+size 4040933

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_006.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bad48b1a5cb48559e1a3f190336a253b7604f3a092e3a68bde4ca3fe773b44
+size 3976607

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_007.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6504f58dc820119325f06934564051157f5d0280678a33aa8d75bb4944650f
+size 3242492

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_008.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd7c9f1d48de177226940f7a86868fc504c8628dff797b068ddbfe33dcf2422
+size 2609765

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_009.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b0bcba68e3a4f70d8c0a7b40c20ad1f381611f8abe117fbe4cb2d5f9c22379
+size 3224594

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_010.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2ea212a251f75efe8d57b402de799ef4c6ce3d7a9df9e7780fcd1b47a42aeb
+size 3441083

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_011.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f6d32e2fb6dba67ef90bf44a65958519aa2e1db9d3fbd8165f2bd3d4421d4
+size 2951789

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_012.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772f59a7c9c48d6e41c882f85fd8c72dd7cfc93d0ff7b7d51d6fd1dfab4888a2
+size 2670339

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_013.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f8fcd83a099c257c2c896bebf92c47b3fd556803b1becf9490e20f4daceea3
+size 2910514

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_014.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6a1f7869c8ec68daad6aa739194cfe955334ba6ab5f8cc9cd95f75dd1c1074
+size 3822793

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_015.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27159f1398f1801400bf4431f420c0d6eb8ad48886fd919d7290cc26cb2aef8a
+size 3160563

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_016.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0684753db35f1b828546eb78c667a849970487d6d84b007d948174672c8c53dc
+size 3218567

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_017.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1538d9b8a1f209ddbfb4a7c9910935e672026ac047bd956ca7fafc38b1157f2b
+size 3353710

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_018.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e216aba9ae5f0533a4d955ba3ace5e516e2e8de6d5821e5aa16bdd15ca7524d0
+size 3288659

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_019.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e48512ff368b3f151476448cff40541b2bc4c99f931c0197e1f9a93c1098f7
+size 2957332

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/train/step_020.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6ce18cee96323cadc44ab116e0541649f14c07e6b408002e9e9743e5072ac6
+size 2791164

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/validation/step_000.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439d8a3019712c9251d1db137d730c10ba004528f52903a946cb06064de99284
+size 2594365

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/validation/step_005.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca2940343172ead0d3fc57a28d11d2075d9c02850bced2babb2ee18f1042b59
+size 2159335

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/validation/step_010.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05bce35b9b3c7115ec6e5d8b8540acc8b56103d930707edf4435845acc75911
+size 1970109

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/validation/step_015.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e394176c62f5372aee13503a55f8b5f0f5aeaec5145b2b1099eb704e3d17799
+size 1981579

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/exports/attempt2_step001_020/validation/step_020.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c3c4e0a3d45d45462543f93cc6807155f5223cc4ababa34a175c81b72a0308
+size 1908123

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/1.attempt02.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955c08cc00e5598ab9692cef1c8b6f4db1f1d400af24e26fb17777a4572647cb
+size 3843434

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/1.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4155eef1a9d100f18b6d4c503e662d397e5e3abfb2264c459e596582c50aa7b6
+size 3834556

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/10.attempt02.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2ea212a251f75efe8d57b402de799ef4c6ce3d7a9df9e7780fcd1b47a42aeb
+size 3441083

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/10.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80032c05398540296ac885f9cb516421347b6c0ae68768385b53012fb283dca1
+size 3623043

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/11.attempt02.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f6d32e2fb6dba67ef90bf44a65958519aa2e1db9d3fbd8165f2bd3d4421d4
+size 2951789

trajectories/qwen35-4b-math-grpo-dapo400-e15-seed1/raw/train_raw/11.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25265297f37db9a16105032ce85d6a6bda3ad37973f1d91ab2a086f1dedeb4f7
+size 3409767