Upload task output abc123

.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 +1,28 @@
+{
+  "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": 32768,
+  "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": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+202,0.00023559275723528117

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b316ceca0fd69a88ca78e6263ebb4eed5c0bc75c3b1d2a7b77cb662432a40310
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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        {{- '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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,666 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9852216748768474,
+  "eval_steps": 500,
+  "global_step": 202,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 109.0,
+      "learning_rate": 2.52589e-06,
+      "logits/chosen": 0.05971701070666313,
+      "logits/rejected": -0.009489008225500584,
+      "logps/chosen": -715.102294921875,
+      "logps/rejected": -992.0411376953125,
+      "loss": 0.6912,
+      "rewards/accuracies": 0.3333333432674408,
+      "rewards/chosen": -0.0028032560367137194,
+      "rewards/margins": 0.006950830575078726,
+      "rewards/rejected": -0.009754086844623089,
+      "step": 5
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 75.0,
+      "learning_rate": 5.6832524999999995e-06,
+      "logits/chosen": 0.04588876664638519,
+      "logits/rejected": 0.003985819406807423,
+      "logps/chosen": -671.5519409179688,
+      "logps/rejected": -1003.0562744140625,
+      "loss": 0.5469,
+      "rewards/accuracies": 0.9083333015441895,
+      "rewards/chosen": 0.09333531558513641,
+      "rewards/margins": 0.3377665579319,
+      "rewards/rejected": -0.24443121254444122,
+      "step": 10
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 29.125,
+      "learning_rate": 8.840615e-06,
+      "logits/chosen": -0.02368784323334694,
+      "logits/rejected": 0.04294583946466446,
+      "logps/chosen": -677.3331909179688,
+      "logps/rejected": -989.4844970703125,
+      "loss": 0.2525,
+      "rewards/accuracies": 0.98333340883255,
+      "rewards/chosen": 0.3687068819999695,
+      "rewards/margins": 1.4707039594650269,
+      "rewards/rejected": -1.101996898651123,
+      "step": 15
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 3.703125,
+      "learning_rate": 1.19979775e-05,
+      "logits/chosen": 0.008908278308808804,
+      "logits/rejected": 0.017966633662581444,
+      "logps/chosen": -703.7459716796875,
+      "logps/rejected": -1041.655029296875,
+      "loss": 0.0458,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.7780574560165405,
+      "rewards/margins": 4.076639652252197,
+      "rewards/rejected": -3.298582077026367,
+      "step": 20
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 12.0,
+      "learning_rate": 1.5155340000000002e-05,
+      "logits/chosen": -0.024580026045441628,
+      "logits/rejected": 0.03568558394908905,
+      "logps/chosen": -717.9066162109375,
+      "logps/rejected": -1072.755126953125,
+      "loss": 0.016,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.2561551332473755,
+      "rewards/margins": 7.924638271331787,
+      "rewards/rejected": -6.668482780456543,
+      "step": 25
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 1.8312702500000002e-05,
+      "logits/chosen": 0.021068373695015907,
+      "logits/rejected": -0.008218185044825077,
+      "logps/chosen": -672.0543212890625,
+      "logps/rejected": -1118.3712158203125,
+      "loss": 0.0009,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.809730887413025,
+      "rewards/margins": 12.14515495300293,
+      "rewards/rejected": -10.335424423217773,
+      "step": 30
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 7.1875,
+      "learning_rate": 2.1470065e-05,
+      "logits/chosen": 0.0051301405765116215,
+      "logits/rejected": -0.02955557033419609,
+      "logps/chosen": -665.8123779296875,
+      "logps/rejected": -1053.738037109375,
+      "loss": 0.0086,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.6763460636138916,
+      "rewards/margins": 13.757688522338867,
+      "rewards/rejected": -12.081342697143555,
+      "step": 35
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 4.1875,
+      "learning_rate": 2.2092428004483083e-05,
+      "logits/chosen": 0.07094338536262512,
+      "logits/rejected": 0.05427859351038933,
+      "logps/chosen": -715.7424926757812,
+      "logps/rejected": -1175.1407470703125,
+      "loss": 0.002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.44687819480896,
+      "rewards/margins": 15.842519760131836,
+      "rewards/rejected": -13.39564037322998,
+      "step": 40
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 0.00194549560546875,
+      "learning_rate": 2.205545499586072e-05,
+      "logits/chosen": -0.023238930851221085,
+      "logits/rejected": -0.05826393887400627,
+      "logps/chosen": -682.96142578125,
+      "logps/rejected": -1163.7904052734375,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.871985912322998,
+      "rewards/margins": 16.598369598388672,
+      "rewards/rejected": -13.7263822555542,
+      "step": 45
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.5390625,
+      "learning_rate": 2.1990176011484834e-05,
+      "logits/chosen": 0.07197682559490204,
+      "logits/rejected": -0.03699414059519768,
+      "logps/chosen": -663.2843627929688,
+      "logps/rejected": -1101.3746337890625,
+      "loss": 0.0012,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.7080256938934326,
+      "rewards/margins": 16.22707176208496,
+      "rewards/rejected": -13.519048690795898,
+      "step": 50
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 1.1484375,
+      "learning_rate": 2.1896815242896443e-05,
+      "logits/chosen": -0.07335661351680756,
+      "logits/rejected": -0.07419757544994354,
+      "logps/chosen": -613.652099609375,
+      "logps/rejected": -1092.04052734375,
+      "loss": 0.0016,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.8754172325134277,
+      "rewards/margins": 16.448772430419922,
+      "rewards/rejected": -13.573356628417969,
+      "step": 55
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.00213623046875,
+      "learning_rate": 2.1775693324596527e-05,
+      "logits/chosen": -0.03252274543046951,
+      "logits/rejected": -0.03407047688961029,
+      "logps/chosen": -665.9483642578125,
+      "logps/rejected": -1142.9947509765625,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2369766235351562,
+      "rewards/margins": 17.267452239990234,
+      "rewards/rejected": -14.030476570129395,
+      "step": 60
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 0.00213623046875,
+      "learning_rate": 2.1627226232871688e-05,
+      "logits/chosen": -0.02839934267103672,
+      "logits/rejected": -0.16694848239421844,
+      "logps/chosen": -728.3703002929688,
+      "logps/rejected": -1130.7135009765625,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.4549667835235596,
+      "rewards/margins": 17.37836265563965,
+      "rewards/rejected": -13.9233980178833,
+      "step": 65
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 2.1451923857181784e-05,
+      "logits/chosen": -0.0006940827006474137,
+      "logits/rejected": -0.10031332820653915,
+      "logps/chosen": -674.8314819335938,
+      "logps/rejected": -1093.62890625,
+      "loss": 0.0007,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.454847812652588,
+      "rewards/margins": 16.464736938476562,
+      "rewards/rejected": -13.0098876953125,
+      "step": 70
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.27734375,
+      "learning_rate": 2.12503882490159e-05,
+      "logits/chosen": -0.08651714771986008,
+      "logits/rejected": -0.1013587936758995,
+      "logps/chosen": -670.3421020507812,
+      "logps/rejected": -1148.192626953125,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3947932720184326,
+      "rewards/margins": 16.52945899963379,
+      "rewards/rejected": -13.134666442871094,
+      "step": 75
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.2890625,
+      "learning_rate": 2.1023311554230692e-05,
+      "logits/chosen": 0.04961782321333885,
+      "logits/rejected": -0.06455739587545395,
+      "logps/chosen": -684.1675415039062,
+      "logps/rejected": -1145.384033203125,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.4156594276428223,
+      "rewards/margins": 16.826187133789062,
+      "rewards/rejected": -13.410530090332031,
+      "step": 80
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 2.0771473635972312e-05,
+      "logits/chosen": -0.07051565498113632,
+      "logits/rejected": -0.06034456938505173,
+      "logps/chosen": -641.9849853515625,
+      "logps/rejected": -1189.5823974609375,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3825697898864746,
+      "rewards/margins": 16.967540740966797,
+      "rewards/rejected": -13.584970474243164,
+      "step": 85
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.0495739396345457e-05,
+      "logits/chosen": -0.08308638632297516,
+      "logits/rejected": -0.15096285939216614,
+      "logps/chosen": -629.1686401367188,
+      "logps/rejected": -1102.910888671875,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.448202133178711,
+      "rewards/margins": 17.18029022216797,
+      "rewards/rejected": -13.732088088989258,
+      "step": 90
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 2.01970558060281e-05,
+      "logits/chosen": -0.025356780737638474,
+      "logits/rejected": -0.04741012677550316,
+      "logps/chosen": -725.537353515625,
+      "logps/rejected": -1180.159912109375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.787024974822998,
+      "rewards/margins": 17.374534606933594,
+      "rewards/rejected": -13.587509155273438,
+      "step": 95
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 1.9876448652033145e-05,
+      "logits/chosen": -0.12176716327667236,
+      "logits/rejected": -0.1069510206580162,
+      "logps/chosen": -615.0023193359375,
+      "logps/rejected": -1111.8590087890625,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.566725492477417,
+      "rewards/margins": 16.64693832397461,
+      "rewards/rejected": -13.080212593078613,
+      "step": 100
+    },
+    {
+      "epoch": 0.9950738916256158,
+      "eval_logits/chosen": -0.10971267521381378,
+      "eval_logits/rejected": -0.11195576936006546,
+      "eval_logps/chosen": -621.429443359375,
+      "eval_logps/rejected": -1077.3065185546875,
+      "eval_loss": 0.00026110102771781385,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.707453727722168,
+      "eval_rewards/margins": 16.420101165771484,
+      "eval_rewards/rejected": -12.71264934539795,
+      "eval_runtime": 16.3811,
+      "eval_samples_per_second": 12.209,
+      "eval_steps_per_second": 12.209,
+      "step": 101
+    },
+    {
+      "epoch": 1.0295566502463054,
+      "grad_norm": 0.00640869140625,
+      "learning_rate": 1.9535019014786414e-05,
+      "logits/chosen": -0.061172205954790115,
+      "logits/rejected": -0.10132347047328949,
+      "logps/chosen": -672.3265380859375,
+      "logps/rejected": -1173.51171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.708890199661255,
+      "rewards/margins": 17.31882667541504,
+      "rewards/rejected": -13.60993766784668,
+      "step": 105
+    },
+    {
+      "epoch": 1.0788177339901477,
+      "grad_norm": 0.001983642578125,
+      "learning_rate": 1.9173939486619933e-05,
+      "logits/chosen": -0.05034123733639717,
+      "logits/rejected": -0.10526905208826065,
+      "logps/chosen": -647.2199096679688,
+      "logps/rejected": -1188.275634765625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.165084362030029,
+      "rewards/margins": 17.745838165283203,
+      "rewards/rejected": -13.5807523727417,
+      "step": 110
+    },
+    {
+      "epoch": 1.1280788177339902,
+      "grad_norm": 0.0123291015625,
+      "learning_rate": 1.8794450144667584e-05,
+      "logits/chosen": -0.037617627531290054,
+      "logits/rejected": -0.12743313610553741,
+      "logps/chosen": -771.9480590820312,
+      "logps/rejected": -1097.7689208984375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.783888339996338,
+      "rewards/margins": 18.24011993408203,
+      "rewards/rejected": -13.456230163574219,
+      "step": 115
+    },
+    {
+      "epoch": 1.1773399014778325,
+      "grad_norm": 0.000865936279296875,
+      "learning_rate": 1.839785429199364e-05,
+      "logits/chosen": -0.00499363336712122,
+      "logits/rejected": -0.14917989075183868,
+      "logps/chosen": -711.33447265625,
+      "logps/rejected": -1193.215576171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.206370830535889,
+      "rewards/margins": 18.47035026550293,
+      "rewards/rejected": -14.263978958129883,
+      "step": 120
+    },
+    {
+      "epoch": 1.2266009852216748,
+      "grad_norm": 0.004608154296875,
+      "learning_rate": 1.7985513981580707e-05,
+      "logits/chosen": -0.07984370738267899,
+      "logits/rejected": -0.14964917302131653,
+      "logps/chosen": -656.4620361328125,
+      "logps/rejected": -1094.466064453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.7183139324188232,
+      "rewards/margins": 17.3912353515625,
+      "rewards/rejected": -13.67292308807373,
+      "step": 125
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.01708984375,
+      "learning_rate": 1.7558845338549242e-05,
+      "logits/chosen": -0.07335531711578369,
+      "logits/rejected": -0.25236526131629944,
+      "logps/chosen": -668.4403076171875,
+      "logps/rejected": -1086.022216796875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.3127336502075195,
+      "rewards/margins": 17.868593215942383,
+      "rewards/rejected": -13.555859565734863,
+      "step": 130
+    },
+    {
+      "epoch": 1.3251231527093597,
+      "grad_norm": 0.003265380859375,
+      "learning_rate": 1.711931369667393e-05,
+      "logits/chosen": -0.10842283070087433,
+      "logits/rejected": -0.20305411517620087,
+      "logps/chosen": -665.7677001953125,
+      "logps/rejected": -1082.3480224609375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.790182590484619,
+      "rewards/margins": 17.2746639251709,
+      "rewards/rejected": -13.484481811523438,
+      "step": 135
+    },
+    {
+      "epoch": 1.374384236453202,
+      "grad_norm": 0.004364013671875,
+      "learning_rate": 1.666842856589978e-05,
+      "logits/chosen": -0.10986592620611191,
+      "logits/rejected": -0.11519701778888702,
+      "logps/chosen": -634.3655395507812,
+      "logps/rejected": -1161.351806640625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.9017367362976074,
+      "rewards/margins": 17.374921798706055,
+      "rewards/rejected": -13.473180770874023,
+      "step": 140
+    },
+    {
+      "epoch": 1.4236453201970443,
+      "grad_norm": 0.000965118408203125,
+      "learning_rate": 1.6207738448141366e-05,
+      "logits/chosen": -0.07416743785142899,
+      "logits/rejected": -0.16824878752231598,
+      "logps/chosen": -629.0369262695312,
+      "logps/rejected": -1140.7796630859375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.62548828125,
+      "rewards/margins": 17.625173568725586,
+      "rewards/rejected": -13.999687194824219,
+      "step": 145
+    },
+    {
+      "epoch": 1.4729064039408866,
+      "grad_norm": 0.0030364990234375,
+      "learning_rate": 1.573882551916961e-05,
+      "logits/chosen": -0.12653779983520508,
+      "logits/rejected": -0.12018134444952011,
+      "logps/chosen": -682.4252319335938,
+      "logps/rejected": -1164.7567138671875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.8734822273254395,
+      "rewards/margins": 17.484914779663086,
+      "rewards/rejected": -13.611432075500488,
+      "step": 150
+    },
+    {
+      "epoch": 1.522167487684729,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 1.5263300194850375e-05,
+      "logits/chosen": -0.13870279490947723,
+      "logits/rejected": -0.17405085265636444,
+      "logps/chosen": -562.0906372070312,
+      "logps/rejected": -1064.6165771484375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.8661842346191406,
+      "rewards/margins": 16.854862213134766,
+      "rewards/rejected": -12.988679885864258,
+      "step": 155
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.0101318359375,
+      "learning_rate": 1.478279560039646e-05,
+      "logits/chosen": 0.00353141943924129,
+      "logits/rejected": -0.052297573536634445,
+      "logps/chosen": -631.2164916992188,
+      "logps/rejected": -1117.577392578125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.469149112701416,
+      "rewards/margins": 16.642498016357422,
+      "rewards/rejected": -13.17335033416748,
+      "step": 160
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.003143310546875,
+      "learning_rate": 1.429896196162745e-05,
+      "logits/chosen": -0.0989263653755188,
+      "logits/rejected": -0.08890175819396973,
+      "logps/chosen": -593.7097778320312,
+      "logps/rejected": -1195.1968994140625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.126656532287598,
+      "rewards/margins": 17.980117797851562,
+      "rewards/rejected": -13.853459358215332,
+      "step": 165
+    },
+    {
+      "epoch": 1.6699507389162562,
+      "grad_norm": 0.0030975341796875,
+      "learning_rate": 1.3813460937500001e-05,
+      "logits/chosen": -0.020123030990362167,
+      "logits/rejected": -0.1141321063041687,
+      "logps/chosen": -704.115478515625,
+      "logps/rejected": -1211.7939453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.987809419631958,
+      "rewards/margins": 18.1489315032959,
+      "rewards/rejected": -14.161120414733887,
+      "step": 170
+    },
+    {
+      "epoch": 1.7192118226600985,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 1.332795991337255e-05,
+      "logits/chosen": -0.07781299948692322,
+      "logits/rejected": -0.1914922446012497,
+      "logps/chosen": -714.4182739257812,
+      "logps/rejected": -1111.824951171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.549325942993164,
+      "rewards/margins": 18.17251205444336,
+      "rewards/rejected": -13.623186111450195,
+      "step": 175
+    },
+    {
+      "epoch": 1.7684729064039408,
+      "grad_norm": 0.0003814697265625,
+      "learning_rate": 1.2844126274603544e-05,
+      "logits/chosen": -0.04165253788232803,
+      "logits/rejected": -0.11223433166742325,
+      "logps/chosen": -728.790771484375,
+      "logps/rejected": -1157.66552734375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.202837944030762,
+      "rewards/margins": 17.818559646606445,
+      "rewards/rejected": -13.615720748901367,
+      "step": 180
+    },
+    {
+      "epoch": 1.8177339901477834,
+      "grad_norm": 0.005523681640625,
+      "learning_rate": 1.2363621680149627e-05,
+      "logits/chosen": 0.018531261011958122,
+      "logits/rejected": -0.08929164707660675,
+      "logps/chosen": -655.3833618164062,
+      "logps/rejected": -1119.193115234375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.5976531505584717,
+      "rewards/margins": 17.0244197845459,
+      "rewards/rejected": -13.426763534545898,
+      "step": 185
+    },
+    {
+      "epoch": 1.8669950738916257,
+      "grad_norm": 0.00177764892578125,
+      "learning_rate": 1.1888096355830394e-05,
+      "logits/chosen": -0.008384434506297112,
+      "logits/rejected": -0.078025683760643,
+      "logps/chosen": -641.1484985351562,
+      "logps/rejected": -1152.9144287109375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.942249298095703,
+      "rewards/margins": 17.213258743286133,
+      "rewards/rejected": -13.271008491516113,
+      "step": 190
+    },
+    {
+      "epoch": 1.916256157635468,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 1.1419183426858638e-05,
+      "logits/chosen": -0.11397171020507812,
+      "logits/rejected": -0.14867517352104187,
+      "logps/chosen": -606.4990844726562,
+      "logps/rejected": -1104.8248291015625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.0419487953186035,
+      "rewards/margins": 17.517881393432617,
+      "rewards/rejected": -13.475932121276855,
+      "step": 195
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 1.0958493309100225e-05,
+      "logits/chosen": -0.04851642996072769,
+      "logits/rejected": -0.09745767712593079,
+      "logps/chosen": -662.3472900390625,
+      "logps/rejected": -1182.0906982421875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.098772048950195,
+      "rewards/margins": 18.182476043701172,
+      "rewards/rejected": -14.083703994750977,
+      "step": 200
+    },
+    {
+      "epoch": 1.9852216748768474,
+      "eval_logits/chosen": -0.11506563425064087,
+      "eval_logits/rejected": -0.11980016529560089,
+      "eval_logps/chosen": -620.9696655273438,
+      "eval_logps/rejected": -1077.2542724609375,
+      "eval_loss": 0.00023559275723528117,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.7534308433532715,
+      "eval_rewards/margins": 16.460861206054688,
+      "eval_rewards/rejected": -12.70743179321289,
+      "eval_runtime": 17.0739,
+      "eval_samples_per_second": 11.714,
+      "eval_steps_per_second": 11.714,
+      "step": 202
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 303,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "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": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca5fc5ec268283fdc7c45c09fa4a36b3a361610f08042358654cebbf1cb9274
+size 6392