Upload checkpoint 10

.gitattributes

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

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0003879352148191252,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 7995.9375,
+      "epoch": 3.879352148191252e-05,
+      "grad_norm": 6.90427827835083,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": -0.0,
+      "reward": 1.4031733199954033,
+      "reward_std": 0.4605106054805219,
+      "rewards/correctness_reward_func": 1.2900390625,
+      "rewards/soft_format_reward_func": 0.034375000395812094,
+      "rewards/strict_format_reward_func": 0.056250000139698386,
+      "rewards/thinkcount_reward_func": 0.022509375237859786,
+      "step": 1
+    },
+    {
+      "completion_length": 8088.5,
+      "epoch": 7.758704296382504e-05,
+      "grad_norm": 3.891556739807129,
+      "kl": 0.0,
+      "learning_rate": 1.939487975174554e-09,
+      "loss": 0.0,
+      "reward": 0.6285155983641744,
+      "reward_std": 0.5935920812189579,
+      "rewards/correctness_reward_func": 0.556640625,
+      "rewards/soft_format_reward_func": 0.012500000069849193,
+      "rewards/strict_format_reward_func": 0.01875000004656613,
+      "rewards/thinkcount_reward_func": 0.04062500037252903,
+      "step": 2
+    },
+    {
+      "completion_length": 8096.0,
+      "epoch": 0.00011638056444573757,
+      "grad_norm": 4.713188648223877,
+      "kl": 0.0024320849624928087,
+      "learning_rate": 3.878975950349108e-09,
+      "loss": 0.0001,
+      "reward": 0.36123043298721313,
+      "reward_std": 0.6821078089997172,
+      "rewards/correctness_reward_func": 0.27685546875,
+      "rewards/soft_format_reward_func": 0.020312500069849193,
+      "rewards/strict_format_reward_func": 0.028125000186264515,
+      "rewards/thinkcount_reward_func": 0.03593750111758709,
+      "step": 3
+    },
+    {
+      "completion_length": 8115.5,
+      "epoch": 0.0001551740859276501,
+      "grad_norm": 10.833508491516113,
+      "kl": 0.006935258745215833,
+      "learning_rate": 5.818463925523662e-09,
+      "loss": 0.0003,
+      "reward": 0.47499995585530996,
+      "reward_std": 0.5724418228492141,
+      "rewards/correctness_reward_func": 0.3984375,
+      "rewards/soft_format_reward_func": 0.017187500139698386,
+      "rewards/strict_format_reward_func": 0.018750000512227416,
+      "rewards/thinkcount_reward_func": 0.040625001303851604,
+      "step": 4
+    },
+    {
+      "completion_length": 8079.5,
+      "epoch": 0.0001939676074095626,
+      "grad_norm": 6.034649848937988,
+      "kl": 0.006615209276787937,
+      "learning_rate": 7.757951900698217e-09,
+      "loss": 0.0003,
+      "reward": 0.7902882173657417,
+      "reward_std": 1.0456753224134445,
+      "rewards/correctness_reward_func": 0.69775390625,
+      "rewards/soft_format_reward_func": 0.020312500651925802,
+      "rewards/strict_format_reward_func": 0.034375000512227416,
+      "rewards/thinkcount_reward_func": 0.03784687537699938,
+      "step": 5
+    },
+    {
+      "completion_length": 8104.5,
+      "epoch": 0.00023276112889147513,
+      "grad_norm": 9.310425758361816,
+      "kl": 0.09857439913321286,
+      "learning_rate": 9.69743987587277e-09,
+      "loss": 0.0039,
+      "reward": 0.287792949937284,
+      "reward_std": 0.3186251698061824,
+      "rewards/correctness_reward_func": 0.20654296875,
+      "rewards/soft_format_reward_func": 0.01718750037252903,
+      "rewards/strict_format_reward_func": 0.028125000651925802,
+      "rewards/thinkcount_reward_func": 0.0359375006519258,
+      "step": 6
+    },
+    {
+      "completion_length": 8110.25,
+      "epoch": 0.00027155465037338765,
+      "grad_norm": 7.819715976715088,
+      "kl": 0.006849915022030473,
+      "learning_rate": 1.1636927851047324e-08,
+      "loss": 0.0003,
+      "reward": 1.4021483808755875,
+      "reward_std": 1.0534077435731888,
+      "rewards/correctness_reward_func": 1.2880859375,
+      "rewards/soft_format_reward_func": 0.04218750027939677,
+      "rewards/strict_format_reward_func": 0.0437500006519258,
+      "rewards/thinkcount_reward_func": 0.028125000651925802,
+      "step": 7
+    },
+    {
+      "completion_length": 8072.25,
+      "epoch": 0.0003103481718553002,
+      "grad_norm": 6.4098968505859375,
+      "kl": 0.012619216577149928,
+      "learning_rate": 1.3576415826221879e-08,
+      "loss": 0.0005,
+      "reward": 0.13281249441206455,
+      "reward_std": 0.21568109560757875,
+      "rewards/correctness_reward_func": 0.0703125,
+      "rewards/soft_format_reward_func": 0.007812500116415322,
+      "rewards/strict_format_reward_func": 0.00937500037252903,
+      "rewards/thinkcount_reward_func": 0.045312500558793545,
+      "step": 8
+    },
+    {
+      "completion_length": 8094.75,
+      "epoch": 0.0003491416933372127,
+      "grad_norm": 3.926931142807007,
+      "kl": 0.0073505338514223695,
+      "learning_rate": 1.5515903801396434e-08,
+      "loss": 0.0003,
+      "reward": 0.6381835415959358,
+      "reward_std": 0.8727416917681694,
+      "rewards/correctness_reward_func": 0.55224609375,
+      "rewards/soft_format_reward_func": 0.020312500651925802,
+      "rewards/strict_format_reward_func": 0.03125000116415322,
+      "rewards/thinkcount_reward_func": 0.03437500074505806,
+      "step": 9
+    },
+    {
+      "completion_length": 8081.0,
+      "epoch": 0.0003879352148191252,
+      "grad_norm": 2.6511805057525635,
+      "kl": 0.007916834903880954,
+      "learning_rate": 1.7455391776570988e-08,
+      "loss": 0.0003,
+      "reward": 0.5579859064891934,
+      "reward_std": 0.7801620215177536,
+      "rewards/correctness_reward_func": 0.4755859375,
+      "rewards/soft_format_reward_func": 0.014062500093132257,
+      "rewards/strict_format_reward_func": 0.025000000139698386,
+      "rewards/thinkcount_reward_func": 0.04333750158548355,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

README.md

@@ -0,0 +1,27 @@
+---
+base_model: InfiniAILab/OpenR1-Qwen-3B-SFT-Instruct
+library_name: peft
+---
+# T2 3B Instruct (Step 10 Checkpoint)
+
+> [!NOTE]
+> Training in progress...
+
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Progress Bar</title>
+</head>
+<body>
+<div style="width: 100%; background-color: #e0e0e0; border-radius: 25px; overflow: hidden; margin: 20px 0;">
+  <div style="height: 30px; width: 0.04%; background-color: #44965a; text-align: center; line-height: 30px; color: white; border-radius: 25px 0 0 25px;">
+    <!-- 0.0% -->
+  </div>
+</div>
+<p style="font-family: Arial, sans-serif; font-size: 16px;">Progress: 10 out of 25777 steps</p>
+</body>
+</html>
+
+## Training Loss
+![Training Loss Chart](loss.png)

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "InfiniAILab/OpenR1-Qwen-3B-SFT-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d83062a82d491d0f48ec510f8224e88dbfbe5621c538d7857e4753fad12c801
+size 479005064

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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2d52c72c4c306dff5538d09fedd4487ae3fa558b32e2d9927f63b3401593fd
+size 243802484

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d71c8564ddac81c1d70660c7694a5b1590b4c14e08413434402e84b9c8e363
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2624cb76ad34a6b4f502605cf2b828909c0b62d6684c3baaf5d5cca99e3aa341
+size 1064

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|vision_pad|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e71213db910f5cafa86d35091f37393dcc344b1bbc34091d1b3eed4cca01d5
+size 11422064

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0003879352148191252,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 7995.9375,
+      "epoch": 3.879352148191252e-05,
+      "grad_norm": 6.90427827835083,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": -0.0,
+      "reward": 1.4031733199954033,
+      "reward_std": 0.4605106054805219,
+      "rewards/correctness_reward_func": 1.2900390625,
+      "rewards/soft_format_reward_func": 0.034375000395812094,
+      "rewards/strict_format_reward_func": 0.056250000139698386,
+      "rewards/thinkcount_reward_func": 0.022509375237859786,
+      "step": 1
+    },
+    {
+      "completion_length": 8088.5,
+      "epoch": 7.758704296382504e-05,
+      "grad_norm": 3.891556739807129,
+      "kl": 0.0,
+      "learning_rate": 1.939487975174554e-09,
+      "loss": 0.0,
+      "reward": 0.6285155983641744,
+      "reward_std": 0.5935920812189579,
+      "rewards/correctness_reward_func": 0.556640625,
+      "rewards/soft_format_reward_func": 0.012500000069849193,
+      "rewards/strict_format_reward_func": 0.01875000004656613,
+      "rewards/thinkcount_reward_func": 0.04062500037252903,
+      "step": 2
+    },
+    {
+      "completion_length": 8096.0,
+      "epoch": 0.00011638056444573757,
+      "grad_norm": 4.713188648223877,
+      "kl": 0.0024320849624928087,
+      "learning_rate": 3.878975950349108e-09,
+      "loss": 0.0001,
+      "reward": 0.36123043298721313,
+      "reward_std": 0.6821078089997172,
+      "rewards/correctness_reward_func": 0.27685546875,
+      "rewards/soft_format_reward_func": 0.020312500069849193,
+      "rewards/strict_format_reward_func": 0.028125000186264515,
+      "rewards/thinkcount_reward_func": 0.03593750111758709,
+      "step": 3
+    },
+    {
+      "completion_length": 8115.5,
+      "epoch": 0.0001551740859276501,
+      "grad_norm": 10.833508491516113,
+      "kl": 0.006935258745215833,
+      "learning_rate": 5.818463925523662e-09,
+      "loss": 0.0003,
+      "reward": 0.47499995585530996,
+      "reward_std": 0.5724418228492141,
+      "rewards/correctness_reward_func": 0.3984375,
+      "rewards/soft_format_reward_func": 0.017187500139698386,
+      "rewards/strict_format_reward_func": 0.018750000512227416,
+      "rewards/thinkcount_reward_func": 0.040625001303851604,
+      "step": 4
+    },
+    {
+      "completion_length": 8079.5,
+      "epoch": 0.0001939676074095626,
+      "grad_norm": 6.034649848937988,
+      "kl": 0.006615209276787937,
+      "learning_rate": 7.757951900698217e-09,
+      "loss": 0.0003,
+      "reward": 0.7902882173657417,
+      "reward_std": 1.0456753224134445,
+      "rewards/correctness_reward_func": 0.69775390625,
+      "rewards/soft_format_reward_func": 0.020312500651925802,
+      "rewards/strict_format_reward_func": 0.034375000512227416,
+      "rewards/thinkcount_reward_func": 0.03784687537699938,
+      "step": 5
+    },
+    {
+      "completion_length": 8104.5,
+      "epoch": 0.00023276112889147513,
+      "grad_norm": 9.310425758361816,
+      "kl": 0.09857439913321286,
+      "learning_rate": 9.69743987587277e-09,
+      "loss": 0.0039,
+      "reward": 0.287792949937284,
+      "reward_std": 0.3186251698061824,
+      "rewards/correctness_reward_func": 0.20654296875,
+      "rewards/soft_format_reward_func": 0.01718750037252903,
+      "rewards/strict_format_reward_func": 0.028125000651925802,
+      "rewards/thinkcount_reward_func": 0.0359375006519258,
+      "step": 6
+    },
+    {
+      "completion_length": 8110.25,
+      "epoch": 0.00027155465037338765,
+      "grad_norm": 7.819715976715088,
+      "kl": 0.006849915022030473,
+      "learning_rate": 1.1636927851047324e-08,
+      "loss": 0.0003,
+      "reward": 1.4021483808755875,
+      "reward_std": 1.0534077435731888,
+      "rewards/correctness_reward_func": 1.2880859375,
+      "rewards/soft_format_reward_func": 0.04218750027939677,
+      "rewards/strict_format_reward_func": 0.0437500006519258,
+      "rewards/thinkcount_reward_func": 0.028125000651925802,
+      "step": 7
+    },
+    {
+      "completion_length": 8072.25,
+      "epoch": 0.0003103481718553002,
+      "grad_norm": 6.4098968505859375,
+      "kl": 0.012619216577149928,
+      "learning_rate": 1.3576415826221879e-08,
+      "loss": 0.0005,
+      "reward": 0.13281249441206455,
+      "reward_std": 0.21568109560757875,
+      "rewards/correctness_reward_func": 0.0703125,
+      "rewards/soft_format_reward_func": 0.007812500116415322,
+      "rewards/strict_format_reward_func": 0.00937500037252903,
+      "rewards/thinkcount_reward_func": 0.045312500558793545,
+      "step": 8
+    },
+    {
+      "completion_length": 8094.75,
+      "epoch": 0.0003491416933372127,
+      "grad_norm": 3.926931142807007,
+      "kl": 0.0073505338514223695,
+      "learning_rate": 1.5515903801396434e-08,
+      "loss": 0.0003,
+      "reward": 0.6381835415959358,
+      "reward_std": 0.8727416917681694,
+      "rewards/correctness_reward_func": 0.55224609375,
+      "rewards/soft_format_reward_func": 0.020312500651925802,
+      "rewards/strict_format_reward_func": 0.03125000116415322,
+      "rewards/thinkcount_reward_func": 0.03437500074505806,
+      "step": 9
+    },
+    {
+      "completion_length": 8081.0,
+      "epoch": 0.0003879352148191252,
+      "grad_norm": 2.6511805057525635,
+      "kl": 0.007916834903880954,
+      "learning_rate": 1.7455391776570988e-08,
+      "loss": 0.0003,
+      "reward": 0.5579859064891934,
+      "reward_std": 0.7801620215177536,
+      "rewards/correctness_reward_func": 0.4755859375,
+      "rewards/soft_format_reward_func": 0.014062500093132257,
+      "rewards/strict_format_reward_func": 0.025000000139698386,
+      "rewards/thinkcount_reward_func": 0.04333750158548355,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c439ee5f2ed27e7b4cb118a8c1ad35d1e17e87f6cc183f5ab6553236f1a38c3
+size 5752