upload

.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 +1,30 @@
+{
+  "_name_or_path": "models/Qwen2.5-1.5B-ultrachat200k",
+  "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": 131072,
+  "max_window_layers": 28,
+  "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": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b40d0ab4920a56132143586d57d177f26c72f8d5eaae38a6ef93aaddcf67d50
+size 3554214752

runs/Jan01_14-26-05_notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944/events.out.tfevents.1735712799.notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944.18510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2616a7bf3420083e9c0438b8e39571747600b4eba9a0b8f76e22012770a5335
+size 38659

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 +1,207 @@
+{
+  "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 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 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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,738 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984301412872841,
+  "eval_steps": 500,
+  "global_step": 477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020931449502878074,
+      "grad_norm": 0.24787747859954834,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -0.294921875,
+      "logits/rejected": -0.2490234375,
+      "logps/chosen": -314.0,
+      "logps/rejected": -290.0,
+      "loss": 0.241,
+      "rewards/accuracies": 0.2593750059604645,
+      "rewards/chosen": -0.000606536865234375,
+      "rewards/margins": 5.888938903808594e-05,
+      "rewards/rejected": -0.000667572021484375,
+      "step": 10
+    },
+    {
+      "epoch": 0.04186289900575615,
+      "grad_norm": 0.22992154955863953,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": -0.275390625,
+      "logits/rejected": -0.265625,
+      "logps/chosen": -300.0,
+      "logps/rejected": -280.0,
+      "loss": 0.2396,
+      "rewards/accuracies": 0.3187499940395355,
+      "rewards/chosen": -0.000583648681640625,
+      "rewards/margins": -0.000942230224609375,
+      "rewards/rejected": 0.0003604888916015625,
+      "step": 20
+    },
+    {
+      "epoch": 0.06279434850863422,
+      "grad_norm": 0.23145779967308044,
+      "learning_rate": 9.995672040508656e-07,
+      "logits/chosen": -0.2578125,
+      "logits/rejected": -0.2041015625,
+      "logps/chosen": -302.0,
+      "logps/rejected": -278.0,
+      "loss": 0.2347,
+      "rewards/accuracies": 0.43437498807907104,
+      "rewards/chosen": -0.0014495849609375,
+      "rewards/margins": 0.0023651123046875,
+      "rewards/rejected": -0.003814697265625,
+      "step": 30
+    },
+    {
+      "epoch": 0.0837257980115123,
+      "grad_norm": 0.2316477745771408,
+      "learning_rate": 9.969250527610354e-07,
+      "logits/chosen": -0.30078125,
+      "logits/rejected": -0.35546875,
+      "logps/chosen": -342.0,
+      "logps/rejected": -288.0,
+      "loss": 0.2388,
+      "rewards/accuracies": 0.5531250238418579,
+      "rewards/chosen": 0.0027923583984375,
+      "rewards/margins": 0.0098876953125,
+      "rewards/rejected": -0.007110595703125,
+      "step": 40
+    },
+    {
+      "epoch": 0.10465724751439037,
+      "grad_norm": 0.23977532982826233,
+      "learning_rate": 9.918938793897e-07,
+      "logits/chosen": -0.306640625,
+      "logits/rejected": -0.267578125,
+      "logps/chosen": -334.0,
+      "logps/rejected": -282.0,
+      "loss": 0.2374,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": 0.00921630859375,
+      "rewards/margins": 0.01953125,
+      "rewards/rejected": -0.0103759765625,
+      "step": 50
+    },
+    {
+      "epoch": 0.12558869701726844,
+      "grad_norm": 0.22875246405601501,
+      "learning_rate": 9.844978718585855e-07,
+      "logits/chosen": -0.28515625,
+      "logits/rejected": -0.24609375,
+      "logps/chosen": -312.0,
+      "logps/rejected": -276.0,
+      "loss": 0.2258,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.01043701171875,
+      "rewards/margins": 0.02685546875,
+      "rewards/rejected": -0.0164794921875,
+      "step": 60
+    },
+    {
+      "epoch": 0.14652014652014653,
+      "grad_norm": 0.2097596377134323,
+      "learning_rate": 9.747725872908607e-07,
+      "logits/chosen": -0.35546875,
+      "logits/rejected": -0.2314453125,
+      "logps/chosen": -318.0,
+      "logps/rejected": -286.0,
+      "loss": 0.2224,
+      "rewards/accuracies": 0.621874988079071,
+      "rewards/chosen": 0.005340576171875,
+      "rewards/margins": 0.031982421875,
+      "rewards/rejected": -0.0267333984375,
+      "step": 70
+    },
+    {
+      "epoch": 0.1674515960230246,
+      "grad_norm": 0.260216623544693,
+      "learning_rate": 9.627647810663406e-07,
+      "logits/chosen": -0.365234375,
+      "logits/rejected": -0.328125,
+      "logps/chosen": -306.0,
+      "logps/rejected": -288.0,
+      "loss": 0.2262,
+      "rewards/accuracies": 0.6031249761581421,
+      "rewards/chosen": -0.01116943359375,
+      "rewards/margins": 0.03173828125,
+      "rewards/rejected": -0.04296875,
+      "step": 80
+    },
+    {
+      "epoch": 0.18838304552590268,
+      "grad_norm": 0.26707494258880615,
+      "learning_rate": 9.48532182039832e-07,
+      "logits/chosen": -0.318359375,
+      "logits/rejected": -0.328125,
+      "logps/chosen": -322.0,
+      "logps/rejected": -300.0,
+      "loss": 0.2271,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.0208740234375,
+      "rewards/margins": 0.045654296875,
+      "rewards/rejected": -0.06640625,
+      "step": 90
+    },
+    {
+      "epoch": 0.20931449502878074,
+      "grad_norm": 0.2734158933162689,
+      "learning_rate": 9.321432150032882e-07,
+      "logits/chosen": -0.39453125,
+      "logits/rejected": -0.2890625,
+      "logps/chosen": -302.0,
+      "logps/rejected": -276.0,
+      "loss": 0.2226,
+      "rewards/accuracies": 0.653124988079071,
+      "rewards/chosen": -0.01153564453125,
+      "rewards/margins": 0.06494140625,
+      "rewards/rejected": -0.07666015625,
+      "step": 100
+    },
+    {
+      "epoch": 0.2302459445316588,
+      "grad_norm": 0.21252916753292084,
+      "learning_rate": 9.13676671726063e-07,
+      "logits/chosen": -0.53515625,
+      "logits/rejected": -0.466796875,
+      "logps/chosen": -306.0,
+      "logps/rejected": -298.0,
+      "loss": 0.2129,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -0.0234375,
+      "rewards/margins": 0.08056640625,
+      "rewards/rejected": -0.103515625,
+      "step": 110
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 0.22458691895008087,
+      "learning_rate": 8.932213321547768e-07,
+      "logits/chosen": -0.48046875,
+      "logits/rejected": -0.42578125,
+      "logps/chosen": -348.0,
+      "logps/rejected": -304.0,
+      "loss": 0.2124,
+      "rewards/accuracies": 0.659375011920929,
+      "rewards/chosen": -0.041015625,
+      "rewards/margins": 0.09423828125,
+      "rewards/rejected": -0.1357421875,
+      "step": 120
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.24381956458091736,
+      "learning_rate": 8.708755375939161e-07,
+      "logits/chosen": -0.578125,
+      "logits/rejected": -0.435546875,
+      "logps/chosen": -340.0,
+      "logps/rejected": -332.0,
+      "loss": 0.1961,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.045166015625,
+      "rewards/margins": 0.11474609375,
+      "rewards/rejected": -0.16015625,
+      "step": 130
+    },
+    {
+      "epoch": 0.29304029304029305,
+      "grad_norm": 0.21222463250160217,
+      "learning_rate": 8.467467179191492e-07,
+      "logits/chosen": -0.56640625,
+      "logits/rejected": -0.5078125,
+      "logps/chosen": -314.0,
+      "logps/rejected": -290.0,
+      "loss": 0.1913,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.1064453125,
+      "rewards/margins": 0.119140625,
+      "rewards/rejected": -0.2255859375,
+      "step": 140
+    },
+    {
+      "epoch": 0.3139717425431711,
+      "grad_norm": 0.2219766229391098,
+      "learning_rate": 8.209508750963328e-07,
+      "logits/chosen": -0.58984375,
+      "logits/rejected": -0.46875,
+      "logps/chosen": -318.0,
+      "logps/rejected": -310.0,
+      "loss": 0.1809,
+      "rewards/accuracies": 0.6156250238418579,
+      "rewards/chosen": -0.15234375,
+      "rewards/margins": 0.09912109375,
+      "rewards/rejected": -0.251953125,
+      "step": 150
+    },
+    {
+      "epoch": 0.3349031920460492,
+      "grad_norm": 0.24187949299812317,
+      "learning_rate": 7.936120254892471e-07,
+      "logits/chosen": -0.6015625,
+      "logits/rejected": -0.6171875,
+      "logps/chosen": -356.0,
+      "logps/rejected": -302.0,
+      "loss": 0.181,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.1611328125,
+      "rewards/margins": 0.1748046875,
+      "rewards/rejected": -0.3359375,
+      "step": 160
+    },
+    {
+      "epoch": 0.35583464154892724,
+      "grad_norm": 0.2268301099538803,
+      "learning_rate": 7.648616036372286e-07,
+      "logits/chosen": -0.69921875,
+      "logits/rejected": -0.65625,
+      "logps/chosen": -334.0,
+      "logps/rejected": -316.0,
+      "loss": 0.171,
+      "rewards/accuracies": 0.653124988079071,
+      "rewards/chosen": -0.1669921875,
+      "rewards/margins": 0.1484375,
+      "rewards/rejected": -0.314453125,
+      "step": 170
+    },
+    {
+      "epoch": 0.37676609105180536,
+      "grad_norm": 0.205755814909935,
+      "learning_rate": 7.348378303691029e-07,
+      "logits/chosen": -0.6953125,
+      "logits/rejected": -0.6796875,
+      "logps/chosen": -358.0,
+      "logps/rejected": -316.0,
+      "loss": 0.1631,
+      "rewards/accuracies": 0.5843750238418579,
+      "rewards/chosen": -0.228515625,
+      "rewards/margins": 0.130859375,
+      "rewards/rejected": -0.359375,
+      "step": 180
+    },
+    {
+      "epoch": 0.3976975405546834,
+      "grad_norm": 0.27961233258247375,
+      "learning_rate": 7.036850482912839e-07,
+      "logits/chosen": -0.734375,
+      "logits/rejected": -0.6171875,
+      "logps/chosen": -326.0,
+      "logps/rejected": -318.0,
+      "loss": 0.1595,
+      "rewards/accuracies": 0.653124988079071,
+      "rewards/chosen": -0.2373046875,
+      "rewards/margins": 0.169921875,
+      "rewards/rejected": -0.40625,
+      "step": 190
+    },
+    {
+      "epoch": 0.4186289900575615,
+      "grad_norm": 0.24265378713607788,
+      "learning_rate": 6.715530278447479e-07,
+      "logits/chosen": -0.76953125,
+      "logits/rejected": -0.75390625,
+      "logps/chosen": -324.0,
+      "logps/rejected": -302.0,
+      "loss": 0.1523,
+      "rewards/accuracies": 0.6781250238418579,
+      "rewards/chosen": -0.28515625,
+      "rewards/margins": 0.13671875,
+      "rewards/rejected": -0.421875,
+      "step": 200
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 0.28898414969444275,
+      "learning_rate": 6.385962472670953e-07,
+      "logits/chosen": -0.80078125,
+      "logits/rejected": -0.765625,
+      "logps/chosen": -344.0,
+      "logps/rejected": -328.0,
+      "loss": 0.1488,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.23828125,
+      "rewards/margins": 0.22265625,
+      "rewards/rejected": -0.4609375,
+      "step": 210
+    },
+    {
+      "epoch": 0.4604918890633176,
+      "grad_norm": 0.22757989168167114,
+      "learning_rate": 6.049731499213605e-07,
+      "logits/chosen": -0.8828125,
+      "logits/rejected": -0.84765625,
+      "logps/chosen": -358.0,
+      "logps/rejected": -324.0,
+      "loss": 0.1542,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.267578125,
+      "rewards/margins": 0.2080078125,
+      "rewards/rejected": -0.474609375,
+      "step": 220
+    },
+    {
+      "epoch": 0.48142333856619574,
+      "grad_norm": 0.23223264515399933,
+      "learning_rate": 5.708453825620412e-07,
+      "logits/chosen": -0.85546875,
+      "logits/rejected": -0.8203125,
+      "logps/chosen": -362.0,
+      "logps/rejected": -354.0,
+      "loss": 0.1487,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.30859375,
+      "rewards/margins": 0.2294921875,
+      "rewards/rejected": -0.5390625,
+      "step": 230
+    },
+    {
+      "epoch": 0.5023547880690737,
+      "grad_norm": 0.20395652949810028,
+      "learning_rate": 5.36377018200472e-07,
+      "logits/chosen": -0.86328125,
+      "logits/rejected": -0.8203125,
+      "logps/chosen": -358.0,
+      "logps/rejected": -336.0,
+      "loss": 0.1488,
+      "rewards/accuracies": 0.6468750238418579,
+      "rewards/chosen": -0.322265625,
+      "rewards/margins": 0.1943359375,
+      "rewards/rejected": -0.515625,
+      "step": 240
+    },
+    {
+      "epoch": 0.5232862375719518,
+      "grad_norm": 0.2625373899936676,
+      "learning_rate": 5.017337673056971e-07,
+      "logits/chosen": -0.9296875,
+      "logits/rejected": -0.8203125,
+      "logps/chosen": -326.0,
+      "logps/rejected": -328.0,
+      "loss": 0.1493,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -0.28515625,
+      "rewards/margins": 0.1787109375,
+      "rewards/rejected": -0.46484375,
+      "step": 250
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.21191805601119995,
+      "learning_rate": 4.6708218113308835e-07,
+      "logits/chosen": -0.92578125,
+      "logits/rejected": -0.8828125,
+      "logps/chosen": -374.0,
+      "logps/rejected": -352.0,
+      "loss": 0.143,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.2578125,
+      "rewards/margins": 0.251953125,
+      "rewards/rejected": -0.51171875,
+      "step": 260
+    },
+    {
+      "epoch": 0.565149136577708,
+      "grad_norm": 0.2124152034521103,
+      "learning_rate": 4.325888510107856e-07,
+      "logits/chosen": -1.0234375,
+      "logits/rejected": -0.95703125,
+      "logps/chosen": -336.0,
+      "logps/rejected": -330.0,
+      "loss": 0.1302,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.267578125,
+      "rewards/margins": 0.22265625,
+      "rewards/rejected": -0.490234375,
+      "step": 270
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "grad_norm": 0.20444093644618988,
+      "learning_rate": 3.9841960743348594e-07,
+      "logits/chosen": -0.984375,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -360.0,
+      "logps/rejected": -350.0,
+      "loss": 0.1426,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -0.298828125,
+      "rewards/margins": 0.2177734375,
+      "rewards/rejected": -0.515625,
+      "step": 280
+    },
+    {
+      "epoch": 0.6070120355834642,
+      "grad_norm": 0.19832541048526764,
+      "learning_rate": 3.647387228140232e-07,
+      "logits/chosen": -1.015625,
+      "logits/rejected": -0.8984375,
+      "logps/chosen": -340.0,
+      "logps/rejected": -318.0,
+      "loss": 0.1374,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": -0.263671875,
+      "rewards/margins": 0.251953125,
+      "rewards/rejected": -0.515625,
+      "step": 290
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "grad_norm": 0.3114321231842041,
+      "learning_rate": 3.317081217255969e-07,
+      "logits/chosen": -0.98046875,
+      "logits/rejected": -0.88671875,
+      "logps/chosen": -366.0,
+      "logps/rejected": -350.0,
+      "loss": 0.1419,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": -0.322265625,
+      "rewards/margins": 0.2197265625,
+      "rewards/rejected": -0.54296875,
+      "step": 300
+    },
+    {
+      "epoch": 0.6488749345892203,
+      "grad_norm": 0.2070474773645401,
+      "learning_rate": 2.994866024315009e-07,
+      "logits/chosen": -1.0,
+      "logits/rejected": -0.921875,
+      "logps/chosen": -344.0,
+      "logps/rejected": -368.0,
+      "loss": 0.1384,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.294921875,
+      "rewards/margins": 0.2373046875,
+      "rewards/rejected": -0.53125,
+      "step": 310
+    },
+    {
+      "epoch": 0.6698063840920984,
+      "grad_norm": 0.22273701429367065,
+      "learning_rate": 2.682290734449314e-07,
+      "logits/chosen": -1.046875,
+      "logits/rejected": -0.92578125,
+      "logps/chosen": -340.0,
+      "logps/rejected": -350.0,
+      "loss": 0.1346,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.2890625,
+      "rewards/margins": 0.259765625,
+      "rewards/rejected": -0.546875,
+      "step": 320
+    },
+    {
+      "epoch": 0.6907378335949764,
+      "grad_norm": 0.21851293742656708,
+      "learning_rate": 2.3808580878919941e-07,
+      "logits/chosen": -0.94921875,
+      "logits/rejected": -0.859375,
+      "logps/chosen": -342.0,
+      "logps/rejected": -338.0,
+      "loss": 0.138,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.3203125,
+      "rewards/margins": 0.232421875,
+      "rewards/rejected": -0.55078125,
+      "step": 330
+    },
+    {
+      "epoch": 0.7116692830978545,
+      "grad_norm": 0.21169716119766235,
+      "learning_rate": 2.0920172553876285e-07,
+      "logits/chosen": -0.97265625,
+      "logits/rejected": -0.91015625,
+      "logps/chosen": -336.0,
+      "logps/rejected": -334.0,
+      "loss": 0.1417,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.298828125,
+      "rewards/margins": 0.27734375,
+      "rewards/rejected": -0.57421875,
+      "step": 340
+    },
+    {
+      "epoch": 0.7326007326007326,
+      "grad_norm": 0.19472256302833557,
+      "learning_rate": 1.8171568711438512e-07,
+      "logits/chosen": -1.0390625,
+      "logits/rejected": -0.88671875,
+      "logps/chosen": -334.0,
+      "logps/rejected": -330.0,
+      "loss": 0.1372,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.30078125,
+      "rewards/margins": 0.1943359375,
+      "rewards/rejected": -0.49609375,
+      "step": 350
+    },
+    {
+      "epoch": 0.7535321821036107,
+      "grad_norm": 0.23481227457523346,
+      "learning_rate": 1.5575983568189998e-07,
+      "logits/chosen": -0.953125,
+      "logits/rejected": -0.98828125,
+      "logps/chosen": -322.0,
+      "logps/rejected": -324.0,
+      "loss": 0.1345,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -0.330078125,
+      "rewards/margins": 0.208984375,
+      "rewards/rejected": -0.5390625,
+      "step": 360
+    },
+    {
+      "epoch": 0.7744636316064888,
+      "grad_norm": 0.20973995327949524,
+      "learning_rate": 1.3145895686415353e-07,
+      "logits/chosen": -0.92578125,
+      "logits/rejected": -0.9375,
+      "logps/chosen": -372.0,
+      "logps/rejected": -332.0,
+      "loss": 0.1378,
+      "rewards/accuracies": 0.628125011920929,
+      "rewards/chosen": -0.33203125,
+      "rewards/margins": 0.1865234375,
+      "rewards/rejected": -0.515625,
+      "step": 370
+    },
+    {
+      "epoch": 0.7953950811093669,
+      "grad_norm": 0.18481357395648956,
+      "learning_rate": 1.0892987982033757e-07,
+      "logits/chosen": -0.92578125,
+      "logits/rejected": -0.92578125,
+      "logps/chosen": -354.0,
+      "logps/rejected": -356.0,
+      "loss": 0.1338,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": -0.3125,
+      "rewards/margins": 0.2392578125,
+      "rewards/rejected": -0.55078125,
+      "step": 380
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.22186759114265442,
+      "learning_rate": 8.828091557690287e-08,
+      "logits/chosen": -0.90234375,
+      "logits/rejected": -0.875,
+      "logps/chosen": -346.0,
+      "logps/rejected": -328.0,
+      "loss": 0.1304,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.330078125,
+      "rewards/margins": 0.2177734375,
+      "rewards/rejected": -0.546875,
+      "step": 390
+    },
+    {
+      "epoch": 0.837257980115123,
+      "grad_norm": 0.2037443071603775,
+      "learning_rate": 6.961133631033511e-08,
+      "logits/chosen": -0.9296875,
+      "logits/rejected": -0.89453125,
+      "logps/chosen": -352.0,
+      "logps/rejected": -370.0,
+      "loss": 0.134,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": -0.333984375,
+      "rewards/margins": 0.240234375,
+      "rewards/rejected": -0.57421875,
+      "step": 400
+    },
+    {
+      "epoch": 0.858189429618001,
+      "grad_norm": 0.22719213366508484,
+      "learning_rate": 5.301089808520048e-08,
+      "logits/chosen": -0.98046875,
+      "logits/rejected": -0.8984375,
+      "logps/chosen": -354.0,
+      "logps/rejected": -338.0,
+      "loss": 0.1353,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.314453125,
+      "rewards/margins": 0.259765625,
+      "rewards/rejected": -0.57421875,
+      "step": 410
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.20336544513702393,
+      "learning_rate": 3.855940934195145e-08,
+      "logits/chosen": -0.984375,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -350.0,
+      "logps/rejected": -338.0,
+      "loss": 0.133,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.294921875,
+      "rewards/margins": 0.263671875,
+      "rewards/rejected": -0.55859375,
+      "step": 420
+    },
+    {
+      "epoch": 0.9000523286237572,
+      "grad_norm": 0.2312639355659485,
+      "learning_rate": 2.6326347209032817e-08,
+      "logits/chosen": -0.890625,
+      "logits/rejected": -0.875,
+      "logps/chosen": -354.0,
+      "logps/rejected": -358.0,
+      "loss": 0.1337,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.328125,
+      "rewards/margins": 0.2451171875,
+      "rewards/rejected": -0.57421875,
+      "step": 430
+    },
+    {
+      "epoch": 0.9209837781266352,
+      "grad_norm": 0.21316397190093994,
+      "learning_rate": 1.63705234839131e-08,
+      "logits/chosen": -0.96484375,
+      "logits/rejected": -0.95703125,
+      "logps/chosen": -346.0,
+      "logps/rejected": -322.0,
+      "loss": 0.1381,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -0.333984375,
+      "rewards/margins": 0.234375,
+      "rewards/rejected": -0.56640625,
+      "step": 440
+    },
+    {
+      "epoch": 0.9419152276295133,
+      "grad_norm": 0.18119490146636963,
+      "learning_rate": 8.739801888871468e-09,
+      "logits/chosen": -0.98828125,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -364.0,
+      "logps/rejected": -342.0,
+      "loss": 0.1327,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.25,
+      "rewards/margins": 0.279296875,
+      "rewards/rejected": -0.52734375,
+      "step": 450
+    },
+    {
+      "epoch": 0.9628466771323915,
+      "grad_norm": 0.21448834240436554,
+      "learning_rate": 3.47086796086582e-09,
+      "logits/chosen": -1.03125,
+      "logits/rejected": -0.984375,
+      "logps/chosen": -334.0,
+      "logps/rejected": -330.0,
+      "loss": 0.1264,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": -0.3046875,
+      "rewards/margins": 0.271484375,
+      "rewards/rejected": -0.57421875,
+      "step": 460
+    },
+    {
+      "epoch": 0.9837781266352695,
+      "grad_norm": 0.20449356734752655,
+      "learning_rate": 5.89052681761626e-10,
+      "logits/chosen": -0.96484375,
+      "logits/rejected": -0.87109375,
+      "logps/chosen": -364.0,
+      "logps/rejected": -356.0,
+      "loss": 0.1367,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.3125,
+      "rewards/margins": 0.240234375,
+      "rewards/rejected": -0.5546875,
+      "step": 470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 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 sha256:38c0461a91737044430afbb4a7f3c236b5421ede367eb2b8033902f52041e7f3
+size 7608