Upload via huggingface_hub API

.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

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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b149011ebfc57d3e2280587babf04492b814c3fedcd65b2ac89d70e7851dd1
+size 3087467144

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d63211297d7747b4c83e36f10e8b179242bdb91e7c6fabd66e0dbf807cda853
+size 3136849858

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60afd58a1678a9dd9d2925035a51899be4c0cbfbb4194cb5d5d0649d4106309
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9247523a2a09e2300eda233d249b37d104af98f3bfd334c48fdfa496dd543bfb
+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": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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": 1024,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1233 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03968647683301915,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 221.46875,
+      "epoch": 0.0003968647683301915,
+      "grad_norm": 0.1240234375,
+      "kl": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.875,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 0.875,
+      "step": 1
+    },
+    {
+      "completion_length": 181.71875,
+      "epoch": 0.000793729536660383,
+      "grad_norm": 0.00052642822265625,
+      "kl": 0.00021356809156714007,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.125,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.125,
+      "step": 2
+    },
+    {
+      "completion_length": 279.875,
+      "epoch": 0.0011905943049905744,
+      "grad_norm": 0.380859375,
+      "kl": 0.0001963738031918183,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.40625,
+      "reward_std": 0.13466878235340118,
+      "rewards/correctness_reward_func": 1.40625,
+      "step": 3
+    },
+    {
+      "completion_length": 231.625,
+      "epoch": 0.001587459073320766,
+      "grad_norm": 0.068359375,
+      "kl": 0.00031982854125089943,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 4
+    },
+    {
+      "completion_length": 271.140625,
+      "epoch": 0.0019843238416509573,
+      "grad_norm": 0.00013446807861328125,
+      "kl": 0.00010319267312297598,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 2.0,
+      "step": 5
+    },
+    {
+      "completion_length": 294.65625,
+      "epoch": 0.0023811886099811487,
+      "grad_norm": 0.04248046875,
+      "kl": 0.0001881300595414359,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.34375,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.34375,
+      "step": 6
+    },
+    {
+      "completion_length": 279.25,
+      "epoch": 0.0027780533783113405,
+      "grad_norm": 0.000713348388671875,
+      "kl": 0.0002071384915325325,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.125,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.125,
+      "step": 7
+    },
+    {
+      "completion_length": 287.125,
+      "epoch": 0.003174918146641532,
+      "grad_norm": 0.0003032684326171875,
+      "kl": 0.0001682171678112354,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 2.0,
+      "step": 8
+    },
+    {
+      "completion_length": 259.0625,
+      "epoch": 0.0035717829149717233,
+      "grad_norm": 0.1591796875,
+      "kl": 0.0002609610164654441,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.34375,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.34375,
+      "step": 9
+    },
+    {
+      "completion_length": 380.171875,
+      "epoch": 0.003968647683301915,
+      "grad_norm": 0.0654296875,
+      "kl": 0.0002176924463128671,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.34375,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.34375,
+      "step": 10
+    },
+    {
+      "completion_length": 489.640625,
+      "epoch": 0.004365512451632106,
+      "grad_norm": 0.032958984375,
+      "kl": 0.00015466208969883155,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.21875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.21875,
+      "step": 11
+    },
+    {
+      "completion_length": 332.609375,
+      "epoch": 0.0047623772199622974,
+      "grad_norm": 0.056640625,
+      "kl": 0.00017187761113746092,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.90625,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.90625,
+      "step": 12
+    },
+    {
+      "completion_length": 366.828125,
+      "epoch": 0.00515924198829249,
+      "grad_norm": 0.00021648406982421875,
+      "kl": 0.00014664832269772887,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.75,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.75,
+      "step": 13
+    },
+    {
+      "completion_length": 232.5,
+      "epoch": 0.005556106756622681,
+      "grad_norm": 0.0005340576171875,
+      "kl": 0.000275460712146014,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 2.0,
+      "step": 14
+    },
+    {
+      "completion_length": 294.359375,
+      "epoch": 0.0059529715249528724,
+      "grad_norm": 0.087890625,
+      "kl": 0.00027155900897923857,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 1.0,
+      "step": 15
+    },
+    {
+      "completion_length": 384.578125,
+      "epoch": 0.006349836293283064,
+      "grad_norm": 0.0634765625,
+      "kl": 0.00022811047529103234,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.13466878235340118,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 16
+    },
+    {
+      "completion_length": 334.09375,
+      "epoch": 0.006746701061613255,
+      "grad_norm": 0.057861328125,
+      "kl": 0.00027415682779974304,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 17
+    },
+    {
+      "completion_length": 375.921875,
+      "epoch": 0.007143565829943447,
+      "grad_norm": 0.08642578125,
+      "kl": 0.0001596472029632423,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.78125,
+      "reward_std": 0.13466878235340118,
+      "rewards/correctness_reward_func": 1.78125,
+      "step": 18
+    },
+    {
+      "completion_length": 345.203125,
+      "epoch": 0.007540430598273638,
+      "grad_norm": 0.000461578369140625,
+      "kl": 0.00024132111502694897,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 2.0,
+      "step": 19
+    },
+    {
+      "completion_length": 418.296875,
+      "epoch": 0.00793729536660383,
+      "grad_norm": 0.251953125,
+      "kl": 0.0002591940647107549,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0625,
+      "reward_std": 0.25,
+      "rewards/correctness_reward_func": 1.0625,
+      "step": 20
+    },
+    {
+      "completion_length": 441.0,
+      "epoch": 0.00833416013493402,
+      "grad_norm": 0.240234375,
+      "kl": 0.00021814405772602186,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.25,
+      "reward_std": 0.3221687823534012,
+      "rewards/correctness_reward_func": 1.25,
+      "step": 21
+    },
+    {
+      "completion_length": 349.15625,
+      "epoch": 0.008731024903264212,
+      "grad_norm": 0.0947265625,
+      "kl": 0.00023298784799408168,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.4375,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.4375,
+      "step": 22
+    },
+    {
+      "completion_length": 375.90625,
+      "epoch": 0.009127889671594403,
+      "grad_norm": 0.064453125,
+      "kl": 0.0001741187043080572,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.375,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 1.375,
+      "step": 23
+    },
+    {
+      "completion_length": 383.203125,
+      "epoch": 0.009524754439924595,
+      "grad_norm": 0.0732421875,
+      "kl": 0.00014529807594954036,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.9375,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.9375,
+      "step": 24
+    },
+    {
+      "completion_length": 334.6875,
+      "epoch": 0.009921619208254788,
+      "grad_norm": 0.06005859375,
+      "kl": 0.00016799916193122044,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.9375,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.9375,
+      "step": 25
+    },
+    {
+      "completion_length": 405.140625,
+      "epoch": 0.01031848397658498,
+      "grad_norm": 0.0245361328125,
+      "kl": 0.00020157176550128497,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 26
+    },
+    {
+      "completion_length": 374.28125,
+      "epoch": 0.01071534874491517,
+      "grad_norm": 0.1796875,
+      "kl": 0.00029869095305912197,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.9375,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 0.9375,
+      "step": 27
+    },
+    {
+      "completion_length": 426.484375,
+      "epoch": 0.011112213513245362,
+      "grad_norm": 0.43359375,
+      "kl": 0.0002508295456209453,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.9375,
+      "reward_std": 0.4471687823534012,
+      "rewards/correctness_reward_func": 0.9375,
+      "step": 28
+    },
+    {
+      "completion_length": 432.21875,
+      "epoch": 0.011509078281575554,
+      "grad_norm": 0.2578125,
+      "kl": 0.00018439985433360562,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.03125,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.03125,
+      "step": 29
+    },
+    {
+      "completion_length": 610.609375,
+      "epoch": 0.011905943049905745,
+      "grad_norm": 0.162109375,
+      "kl": 9.109115489991382e-05,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.40625,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 0.40625,
+      "step": 30
+    },
+    {
+      "completion_length": 411.140625,
+      "epoch": 0.012302807818235936,
+      "grad_norm": 0.12890625,
+      "kl": 0.00014656526946055237,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.8125,
+      "reward_std": 0.32216876745224,
+      "rewards/correctness_reward_func": 0.8125,
+      "step": 31
+    },
+    {
+      "completion_length": 371.359375,
+      "epoch": 0.012699672586566128,
+      "grad_norm": 0.053955078125,
+      "kl": 0.0001413824884366477,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.71875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.71875,
+      "step": 32
+    },
+    {
+      "completion_length": 360.6875,
+      "epoch": 0.013096537354896319,
+      "grad_norm": 0.09375,
+      "kl": 0.00014583250776922796,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.96875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.96875,
+      "step": 33
+    },
+    {
+      "completion_length": 256.140625,
+      "epoch": 0.01349340212322651,
+      "grad_norm": 0.0003681182861328125,
+      "kl": 0.00021255770843708888,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.875,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.875,
+      "step": 34
+    },
+    {
+      "completion_length": 298.71875,
+      "epoch": 0.013890266891556702,
+      "grad_norm": 0.05712890625,
+      "kl": 0.00023778366448823363,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.84375,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.84375,
+      "step": 35
+    },
+    {
+      "completion_length": 397.203125,
+      "epoch": 0.014287131659886893,
+      "grad_norm": 0.0693359375,
+      "kl": 0.0001875234411272686,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.96875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 0.96875,
+      "step": 36
+    },
+    {
+      "completion_length": 476.59375,
+      "epoch": 0.014683996428217085,
+      "grad_norm": 0.1982421875,
+      "kl": 0.0002962429862236604,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.15625,
+      "reward_std": 0.45683756470680237,
+      "rewards/correctness_reward_func": 1.15625,
+      "step": 37
+    },
+    {
+      "completion_length": 380.046875,
+      "epoch": 0.015080861196547276,
+      "grad_norm": 0.2177734375,
+      "kl": 0.00021642427236656658,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.25,
+      "reward_std": 0.3221687823534012,
+      "rewards/correctness_reward_func": 1.25,
+      "step": 38
+    },
+    {
+      "completion_length": 319.671875,
+      "epoch": 0.015477725964877467,
+      "grad_norm": 0.1787109375,
+      "kl": 0.0002720155207498465,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 1.0,
+      "step": 39
+    },
+    {
+      "completion_length": 527.625,
+      "epoch": 0.01587459073320766,
+      "grad_norm": 0.11474609375,
+      "kl": 0.0001258815245819278,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.625,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 0.625,
+      "step": 40
+    },
+    {
+      "completion_length": 326.09375,
+      "epoch": 0.01627145550153785,
+      "grad_norm": 0.0634765625,
+      "kl": 0.00018829756663762964,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.78125,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.78125,
+      "step": 41
+    },
+    {
+      "completion_length": 362.1875,
+      "epoch": 0.01666832026986804,
+      "grad_norm": 0.042724609375,
+      "kl": 0.00019165025150869042,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.71875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.71875,
+      "step": 42
+    },
+    {
+      "completion_length": 297.5625,
+      "epoch": 0.017065185038198233,
+      "grad_norm": 0.000431060791015625,
+      "kl": 0.00027088051137980074,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 2.0,
+      "step": 43
+    },
+    {
+      "completion_length": 361.09375,
+      "epoch": 0.017462049806528424,
+      "grad_norm": 0.0712890625,
+      "kl": 0.00019505245654727332,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.96875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.96875,
+      "step": 44
+    },
+    {
+      "completion_length": 349.140625,
+      "epoch": 0.017858914574858616,
+      "grad_norm": 0.08984375,
+      "kl": 0.000281722481304314,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.0,
+      "step": 45
+    },
+    {
+      "completion_length": 454.375,
+      "epoch": 0.018255779343188807,
+      "grad_norm": 0.203125,
+      "kl": 0.0002504781477910001,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.15625,
+      "reward_std": 0.33183756470680237,
+      "rewards/correctness_reward_func": 1.15625,
+      "step": 46
+    },
+    {
+      "completion_length": 417.984375,
+      "epoch": 0.018652644111519,
+      "grad_norm": 0.57421875,
+      "kl": 0.0007036441420495976,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.96875,
+      "reward_std": 0.33183756470680237,
+      "rewards/correctness_reward_func": 0.96875,
+      "step": 47
+    },
+    {
+      "completion_length": 403.5625,
+      "epoch": 0.01904950887984919,
+      "grad_norm": 0.2109375,
+      "kl": 0.00022189919036463834,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.28125,
+      "reward_std": 0.2596687823534012,
+      "rewards/correctness_reward_func": 1.28125,
+      "step": 48
+    },
+    {
+      "completion_length": 578.09375,
+      "epoch": 0.019446373648179385,
+      "grad_norm": 0.193359375,
+      "kl": 0.00016415365462307818,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.3221687823534012,
+      "rewards/correctness_reward_func": 0.5,
+      "step": 49
+    },
+    {
+      "completion_length": 388.46875,
+      "epoch": 0.019843238416509576,
+      "grad_norm": 0.2041015625,
+      "kl": 0.00029624684611917473,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.625,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 0.625,
+      "step": 50
+    },
+    {
+      "completion_length": 393.546875,
+      "epoch": 0.020240103184839767,
+      "grad_norm": 0.06201171875,
+      "kl": 0.000217016367969336,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.4375,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.4375,
+      "step": 51
+    },
+    {
+      "completion_length": 483.203125,
+      "epoch": 0.02063696795316996,
+      "grad_norm": 0.12109375,
+      "kl": 0.00021450840722536668,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.46875,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.46875,
+      "step": 52
+    },
+    {
+      "completion_length": 333.375,
+      "epoch": 0.02103383272150015,
+      "grad_norm": 0.0003528594970703125,
+      "kl": 0.0002801330847432837,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.625,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.625,
+      "step": 53
+    },
+    {
+      "completion_length": 327.609375,
+      "epoch": 0.02143069748983034,
+      "grad_norm": 0.05908203125,
+      "kl": 0.0002553274571255315,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.5625,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.5625,
+      "step": 54
+    },
+    {
+      "completion_length": 313.484375,
+      "epoch": 0.021827562258160533,
+      "grad_norm": 0.05126953125,
+      "kl": 0.00040918682134361006,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.4375,
+      "reward_std": 0.07216878235340118,
+      "rewards/correctness_reward_func": 1.4375,
+      "step": 55
+    },
+    {
+      "completion_length": 587.828125,
+      "epoch": 0.022224427026490724,
+      "grad_norm": 0.2421875,
+      "kl": 0.00024972553364932537,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.59375,
+      "reward_std": 0.5290063470602036,
+      "rewards/correctness_reward_func": 0.59375,
+      "step": 56
+    },
+    {
+      "completion_length": 397.625,
+      "epoch": 0.022621291794820916,
+      "grad_norm": 0.1962890625,
+      "kl": 0.0003616545727709308,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.125,
+      "reward_std": 0.26933756470680237,
+      "rewards/correctness_reward_func": 1.125,
+      "step": 57
+    },
+    {
+      "completion_length": 493.171875,
+      "epoch": 0.023018156563151107,
+      "grad_norm": 0.146484375,
+      "kl": 0.00021447856852319092,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.1875,
+      "reward_std": 0.34150634706020355,
+      "rewards/correctness_reward_func": 1.1875,
+      "step": 58
+    },
+    {
+      "completion_length": 505.140625,
+      "epoch": 0.0234150213314813,
+      "grad_norm": 0.173828125,
+      "kl": 0.00036706905302708037,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.6875,
+      "reward_std": 0.3221687823534012,
+      "rewards/correctness_reward_func": 0.6875,
+      "step": 59
+    },
+    {
+      "completion_length": 565.90625,
+      "epoch": 0.02381188609981149,
+      "grad_norm": 0.10107421875,
+      "kl": 0.0002694212962524034,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 0.5,
+      "step": 60
+    },
+    {
+      "completion_length": 554.953125,
+      "epoch": 0.02420875086814168,
+      "grad_norm": 0.0400390625,
+      "kl": 0.00021707677660742775,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.28125,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 0.28125,
+      "step": 61
+    },
+    {
+      "completion_length": 297.0625,
+      "epoch": 0.024605615636471873,
+      "grad_norm": 0.0004024505615234375,
+      "kl": 0.000280580159596866,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.5,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.5,
+      "step": 62
+    },
+    {
+      "completion_length": 412.125,
+      "epoch": 0.025002480404802064,
+      "grad_norm": 0.08984375,
+      "kl": 0.0002535973835620098,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.90625,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.90625,
+      "step": 63
+    },
+    {
+      "completion_length": 416.046875,
+      "epoch": 0.025399345173132255,
+      "grad_norm": 0.087890625,
+      "kl": 0.00024055263565969653,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.71875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.71875,
+      "step": 64
+    },
+    {
+      "completion_length": 267.140625,
+      "epoch": 0.025796209941462447,
+      "grad_norm": 0.000850677490234375,
+      "kl": 0.0006130204565124586,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.75,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.75,
+      "step": 65
+    },
+    {
+      "completion_length": 402.5625,
+      "epoch": 0.026193074709792638,
+      "grad_norm": 0.0986328125,
+      "kl": 0.0002838912623701617,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.3125,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 1.3125,
+      "step": 66
+    },
+    {
+      "completion_length": 466.6875,
+      "epoch": 0.02658993947812283,
+      "grad_norm": 0.08349609375,
+      "kl": 0.0002692481575650163,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0,
+      "reward_std": 0.25,
+      "rewards/correctness_reward_func": 1.0,
+      "step": 67
+    },
+    {
+      "completion_length": 445.171875,
+      "epoch": 0.02698680424645302,
+      "grad_norm": 0.177734375,
+      "kl": 0.0005885176433366723,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.28125,
+      "reward_std": 0.3125,
+      "rewards/correctness_reward_func": 1.28125,
+      "step": 68
+    },
+    {
+      "completion_length": 530.484375,
+      "epoch": 0.027383669014783212,
+      "grad_norm": 0.1162109375,
+      "kl": 0.0002777522022370249,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.9375,
+      "reward_std": 0.25,
+      "rewards/correctness_reward_func": 0.9375,
+      "step": 69
+    },
+    {
+      "completion_length": 360.640625,
+      "epoch": 0.027780533783113404,
+      "grad_norm": 0.1171875,
+      "kl": 0.000590253112022765,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.6875,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.6875,
+      "step": 70
+    },
+    {
+      "completion_length": 481.71875,
+      "epoch": 0.028177398551443595,
+      "grad_norm": 0.061767578125,
+      "kl": 0.0002587015369499568,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.71875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 0.71875,
+      "step": 71
+    },
+    {
+      "completion_length": 539.5,
+      "epoch": 0.028574263319773786,
+      "grad_norm": 0.11767578125,
+      "kl": 0.00022344068929669447,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.125,
+      "reward_std": 0.39433756470680237,
+      "rewards/correctness_reward_func": 1.125,
+      "step": 72
+    },
+    {
+      "completion_length": 331.703125,
+      "epoch": 0.028971128088103978,
+      "grad_norm": 0.000308990478515625,
+      "kl": 0.0002874392084777355,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.75,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.75,
+      "step": 73
+    },
+    {
+      "completion_length": 439.34375,
+      "epoch": 0.02936799285643417,
+      "grad_norm": 0.07177734375,
+      "kl": 0.00026139178953599185,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.5625,
+      "reward_std": 0.125,
+      "rewards/correctness_reward_func": 1.5625,
+      "step": 74
+    },
+    {
+      "completion_length": 448.328125,
+      "epoch": 0.02976485762476436,
+      "grad_norm": 0.1455078125,
+      "kl": 0.00037807323678862303,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.625,
+      "reward_std": 0.26933756470680237,
+      "rewards/correctness_reward_func": 1.625,
+      "step": 75
+    },
+    {
+      "completion_length": 271.0625,
+      "epoch": 0.030161722393094552,
+      "grad_norm": 0.000728607177734375,
+      "kl": 0.0005262854028842412,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.875,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.875,
+      "step": 76
+    },
+    {
+      "completion_length": 348.4375,
+      "epoch": 0.030558587161424743,
+      "grad_norm": 0.11279296875,
+      "kl": 0.0004181276017334312,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.71875,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.71875,
+      "step": 77
+    },
+    {
+      "completion_length": 526.40625,
+      "epoch": 0.030955451929754935,
+      "grad_norm": 0.1318359375,
+      "kl": 0.0003622628501034342,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.5625,
+      "reward_std": 0.41367512941360474,
+      "rewards/correctness_reward_func": 0.5625,
+      "step": 78
+    },
+    {
+      "completion_length": 308.1875,
+      "epoch": 0.03135231669808513,
+      "grad_norm": 0.171875,
+      "kl": 0.00046880038280505687,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.46875,
+      "reward_std": 0.13466878235340118,
+      "rewards/correctness_reward_func": 1.46875,
+      "step": 79
+    },
+    {
+      "completion_length": 473.03125,
+      "epoch": 0.03174918146641532,
+      "grad_norm": 0.279296875,
+      "kl": 0.0005240375467110425,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.0625,
+      "reward_std": 0.5721687823534012,
+      "rewards/correctness_reward_func": 1.0625,
+      "step": 80
+    },
+    {
+      "completion_length": 415.5,
+      "epoch": 0.03214604623474551,
+      "grad_norm": 0.1865234375,
+      "kl": 0.000653728457109537,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.25,
+      "reward_std": 0.4471687823534012,
+      "rewards/correctness_reward_func": 1.25,
+      "step": 81
+    },
+    {
+      "completion_length": 438.625,
+      "epoch": 0.0325429110030757,
+      "grad_norm": 0.11572265625,
+      "kl": 0.0006323889683699235,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.21875,
+      "reward_std": 0.33183756470680237,
+      "rewards/correctness_reward_func": 1.21875,
+      "step": 82
+    },
+    {
+      "completion_length": 600.796875,
+      "epoch": 0.032939775771405895,
+      "grad_norm": 0.19921875,
+      "kl": 0.00043308708700351417,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.375,
+      "reward_std": 0.25,
+      "rewards/correctness_reward_func": 0.375,
+      "step": 83
+    },
+    {
+      "completion_length": 414.65625,
+      "epoch": 0.03333664053973608,
+      "grad_norm": 0.080078125,
+      "kl": 0.0003923129916074686,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.34375,
+      "reward_std": 0.2596687823534012,
+      "rewards/correctness_reward_func": 1.34375,
+      "step": 84
+    },
+    {
+      "completion_length": 409.6875,
+      "epoch": 0.03373350530806628,
+      "grad_norm": 0.17578125,
+      "kl": 0.0005655539498548023,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.625,
+      "reward_std": 0.3221687823534012,
+      "rewards/correctness_reward_func": 1.625,
+      "step": 85
+    },
+    {
+      "completion_length": 388.9375,
+      "epoch": 0.034130370076396466,
+      "grad_norm": 0.07666015625,
+      "kl": 0.00030672067805426195,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.4375,
+      "reward_std": 0.07216878235340118,
+      "rewards/correctness_reward_func": 1.4375,
+      "step": 86
+    },
+    {
+      "completion_length": 377.5625,
+      "epoch": 0.03452723484472666,
+      "grad_norm": 0.00054931640625,
+      "kl": 0.0005226589782978408,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.875,
+      "reward_std": 0.0,
+      "rewards/correctness_reward_func": 1.875,
+      "step": 87
+    },
+    {
+      "completion_length": 403.59375,
+      "epoch": 0.03492409961305685,
+      "grad_norm": 0.09521484375,
+      "kl": 0.0003179389132128563,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.25,
+      "reward_std": 0.14433756470680237,
+      "rewards/correctness_reward_func": 1.25,
+      "step": 88
+    },
+    {
+      "completion_length": 433.5,
+      "epoch": 0.03532096438138704,
+      "grad_norm": 0.1513671875,
+      "kl": 0.0005926354933762923,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.46875,
+      "reward_std": 0.0625,
+      "rewards/correctness_reward_func": 1.46875,
+      "step": 89
+    },
+    {
+      "completion_length": 581.0625,
+      "epoch": 0.03571782914971723,
+      "grad_norm": 0.18359375,
+      "kl": 0.00041846034582704306,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.84375,
+      "reward_std": 0.3846687823534012,
+      "rewards/correctness_reward_func": 0.84375,
+      "step": 90
+    },
+    {
+      "completion_length": 545.015625,
+      "epoch": 0.036114693918047426,
+      "grad_norm": 0.236328125,
+      "kl": 0.0004266584510332905,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.96875,
+      "reward_std": 0.5096687823534012,
+      "rewards/correctness_reward_func": 0.96875,
+      "step": 91
+    },
+    {
+      "completion_length": 454.59375,
+      "epoch": 0.036511558686377614,
+      "grad_norm": 0.16015625,
+      "kl": 0.00039287004256038927,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.96875,
+      "reward_std": 0.3846687823534012,
+      "rewards/correctness_reward_func": 0.96875,
+      "step": 92
+    },
+    {
+      "completion_length": 450.28125,
+      "epoch": 0.03690842345470781,
+      "grad_norm": 0.1318359375,
+      "kl": 0.0003956604123231955,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.25,
+      "reward_std": 0.25,
+      "rewards/correctness_reward_func": 1.25,
+      "step": 93
+    },
+    {
+      "completion_length": 606.96875,
+      "epoch": 0.037305288223038,
+      "grad_norm": 0.1650390625,
+      "kl": 0.00025138623459497467,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.3125,
+      "reward_std": 0.39433756470680237,
+      "rewards/correctness_reward_func": 0.3125,
+      "step": 94
+    },
+    {
+      "completion_length": 486.15625,
+      "epoch": 0.03770215299136819,
+      "grad_norm": 0.1552734375,
+      "kl": 0.00036627210283768363,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 0.8125,
+      "reward_std": 0.19716878235340118,
+      "rewards/correctness_reward_func": 0.8125,
+      "step": 95
+    },
+    {
+      "completion_length": 442.8125,
+      "epoch": 0.03809901775969838,
+      "grad_norm": 0.09521484375,
+      "kl": 0.0002713065696298145,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.59375,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.59375,
+      "step": 96
+    },
+    {
+      "completion_length": 511.015625,
+      "epoch": 0.038495882528028574,
+      "grad_norm": 0.10205078125,
+      "kl": 0.0002741093012446072,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.3125,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 97
+    },
+    {
+      "completion_length": 510.390625,
+      "epoch": 0.03889274729635877,
+      "grad_norm": 0.09814453125,
+      "kl": 0.00027243237127549946,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.8125,
+      "reward_std": 0.26933756470680237,
+      "rewards/correctness_reward_func": 1.8125,
+      "step": 98
+    },
+    {
+      "completion_length": 354.9375,
+      "epoch": 0.03928961206468896,
+      "grad_norm": 0.0927734375,
+      "kl": 0.0004462298093130812,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.65625,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.65625,
+      "step": 99
+    },
+    {
+      "completion_length": 450.296875,
+      "epoch": 0.03968647683301915,
+      "grad_norm": 0.06298828125,
+      "kl": 0.0003486628302198369,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "reward": 1.53125,
+      "reward_std": 0.1875,
+      "rewards/correctness_reward_func": 1.53125,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 503800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 200,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea622c19cd765facbf5103407e0d8a4b7c647d0bebac70a63158366afff885e
+size 5880