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:a927ad1e1d61d2d8e4ae2b2143121279f192e97672cfc2ab4cc436ce92075147
+size 3554214752

runs/Jan02_21-09-48_notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944/events.out.tfevents.1735823908.notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944.3125.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2658f97544025de781c195f16ec662a01ab2b158bde85032ef2e8c1a32f808f
+size 40676

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 +1,785 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 478,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02092050209205021,
+      "grad_norm": 1.8475663661956787,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": 0.3203125,
+      "logits/rejected": 0.400390625,
+      "logps/chosen": -1.34375,
+      "logps/rejected": -1.4140625,
+      "loss": 0.7551,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -1.34375,
+      "rewards/margins": 0.07421875,
+      "rewards/rejected": -1.4140625,
+      "step": 10
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 1.5401519536972046,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 0.310546875,
+      "logits/rejected": 0.34765625,
+      "logps/chosen": -1.34375,
+      "logps/rejected": -1.4453125,
+      "loss": 0.7511,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -1.34375,
+      "rewards/margins": 0.09521484375,
+      "rewards/rejected": -1.4453125,
+      "step": 20
+    },
+    {
+      "epoch": 0.06276150627615062,
+      "grad_norm": 0.9768715500831604,
+      "learning_rate": 9.995691082675907e-07,
+      "logits/chosen": 0.427734375,
+      "logits/rejected": 0.4609375,
+      "logps/chosen": -1.3125,
+      "logps/rejected": -1.5234375,
+      "loss": 0.7174,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5687500238418579,
+      "rewards/chosen": -1.3125,
+      "rewards/margins": 0.21484375,
+      "rewards/rejected": -1.5234375,
+      "step": 30
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 1.1228318214416504,
+      "learning_rate": 9.969385700404345e-07,
+      "logits/chosen": 0.296875,
+      "logits/rejected": 0.357421875,
+      "logps/chosen": -1.2734375,
+      "logps/rejected": -1.40625,
+      "loss": 0.7385,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.534375011920929,
+      "rewards/chosen": -1.2734375,
+      "rewards/margins": 0.13671875,
+      "rewards/rejected": -1.40625,
+      "step": 40
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "grad_norm": 1.303710699081421,
+      "learning_rate": 9.91929453572245e-07,
+      "logits/chosen": 0.302734375,
+      "logits/rejected": 0.42578125,
+      "logps/chosen": -1.078125,
+      "logps/rejected": -1.359375,
+      "loss": 0.7204,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5843750238418579,
+      "rewards/chosen": -1.078125,
+      "rewards/margins": 0.28125,
+      "rewards/rejected": -1.359375,
+      "step": 50
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 1.6195344924926758,
+      "learning_rate": 9.845657348152955e-07,
+      "logits/chosen": 0.30078125,
+      "logits/rejected": 0.376953125,
+      "logps/chosen": -1.171875,
+      "logps/rejected": -1.34375,
+      "loss": 0.7488,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.171875,
+      "rewards/margins": 0.169921875,
+      "rewards/rejected": -1.34375,
+      "step": 60
+    },
+    {
+      "epoch": 0.14644351464435146,
+      "grad_norm": 0.9580543041229248,
+      "learning_rate": 9.748826599393632e-07,
+      "logits/chosen": 0.1787109375,
+      "logits/rejected": 0.25,
+      "logps/chosen": -1.078125,
+      "logps/rejected": -1.3984375,
+      "loss": 0.6996,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -1.078125,
+      "rewards/margins": 0.314453125,
+      "rewards/rejected": -1.3984375,
+      "step": 70
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 1.0547847747802734,
+      "learning_rate": 9.629265766272291e-07,
+      "logits/chosen": 0.271484375,
+      "logits/rejected": 0.380859375,
+      "logps/chosen": -1.125,
+      "logps/rejected": -1.328125,
+      "loss": 0.7164,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -1.125,
+      "rewards/margins": 0.2001953125,
+      "rewards/rejected": -1.328125,
+      "step": 80
+    },
+    {
+      "epoch": 0.18828451882845187,
+      "grad_norm": 1.3746100664138794,
+      "learning_rate": 9.487547122331964e-07,
+      "logits/chosen": 0.259765625,
+      "logits/rejected": 0.369140625,
+      "logps/chosen": -1.140625,
+      "logps/rejected": -1.3515625,
+      "loss": 0.72,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.565625011920929,
+      "rewards/chosen": -1.140625,
+      "rewards/margins": 0.212890625,
+      "rewards/rejected": -1.3515625,
+      "step": 90
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 1.3906371593475342,
+      "learning_rate": 9.324348998664548e-07,
+      "logits/chosen": 0.3125,
+      "logits/rejected": 0.396484375,
+      "logps/chosen": -1.1328125,
+      "logps/rejected": -1.359375,
+      "loss": 0.7105,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.590624988079071,
+      "rewards/chosen": -1.1328125,
+      "rewards/margins": 0.2236328125,
+      "rewards/rejected": -1.359375,
+      "step": 100
+    },
+    {
+      "epoch": 0.2301255230125523,
+      "grad_norm": 1.1979008913040161,
+      "learning_rate": 9.140452537103941e-07,
+      "logits/chosen": 0.310546875,
+      "logits/rejected": 0.380859375,
+      "logps/chosen": -1.15625,
+      "logps/rejected": -1.3046875,
+      "loss": 0.7282,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.15625,
+      "rewards/margins": 0.150390625,
+      "rewards/rejected": -1.3046875,
+      "step": 110
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 1.7712326049804688,
+      "learning_rate": 8.936737951319275e-07,
+      "logits/chosen": 0.287109375,
+      "logits/rejected": 0.40234375,
+      "logps/chosen": -1.109375,
+      "logps/rejected": -1.375,
+      "loss": 0.7061,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": -1.109375,
+      "rewards/margins": 0.267578125,
+      "rewards/rejected": -1.375,
+      "step": 120
+    },
+    {
+      "epoch": 0.2719665271966527,
+      "grad_norm": 1.0993026494979858,
+      "learning_rate": 8.714180313704489e-07,
+      "logits/chosen": 0.310546875,
+      "logits/rejected": 0.43359375,
+      "logps/chosen": -1.171875,
+      "logps/rejected": -1.4609375,
+      "loss": 0.7141,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": -1.171875,
+      "rewards/margins": 0.2890625,
+      "rewards/rejected": -1.4609375,
+      "step": 130
+    },
+    {
+      "epoch": 0.2928870292887029,
+      "grad_norm": 1.2873952388763428,
+      "learning_rate": 8.473844888230064e-07,
+      "logits/chosen": 0.388671875,
+      "logits/rejected": 0.484375,
+      "logps/chosen": -1.2109375,
+      "logps/rejected": -1.3984375,
+      "loss": 0.7206,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.2109375,
+      "rewards/margins": 0.1865234375,
+      "rewards/rejected": -1.3984375,
+      "step": 140
+    },
+    {
+      "epoch": 0.3138075313807531,
+      "grad_norm": 1.2388606071472168,
+      "learning_rate": 8.216882031596096e-07,
+      "logits/chosen": 0.416015625,
+      "logits/rejected": 0.47265625,
+      "logps/chosen": -1.1640625,
+      "logps/rejected": -1.4765625,
+      "loss": 0.7093,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5843750238418579,
+      "rewards/chosen": -1.1640625,
+      "rewards/margins": 0.306640625,
+      "rewards/rejected": -1.4765625,
+      "step": 150
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 1.259517788887024,
+      "learning_rate": 7.944521687092142e-07,
+      "logits/chosen": 0.41796875,
+      "logits/rejected": 0.546875,
+      "logps/chosen": -1.1484375,
+      "logps/rejected": -1.3828125,
+      "loss": 0.7045,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.1484375,
+      "rewards/margins": 0.2314453125,
+      "rewards/rejected": -1.3828125,
+      "step": 160
+    },
+    {
+      "epoch": 0.35564853556485354,
+      "grad_norm": 1.333101749420166,
+      "learning_rate": 7.658067497518772e-07,
+      "logits/chosen": 0.34375,
+      "logits/rejected": 0.462890625,
+      "logps/chosen": -1.15625,
+      "logps/rejected": -1.4375,
+      "loss": 0.7071,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": -1.15625,
+      "rewards/margins": 0.279296875,
+      "rewards/rejected": -1.4375,
+      "step": 170
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "grad_norm": 1.4813274145126343,
+      "learning_rate": 7.358890565349105e-07,
+      "logits/chosen": 0.39453125,
+      "logits/rejected": 0.46484375,
+      "logps/chosen": -1.1875,
+      "logps/rejected": -1.4921875,
+      "loss": 0.7057,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5687500238418579,
+      "rewards/chosen": -1.1875,
+      "rewards/margins": 0.302734375,
+      "rewards/rejected": -1.4921875,
+      "step": 180
+    },
+    {
+      "epoch": 0.39748953974895396,
+      "grad_norm": 2.0108981132507324,
+      "learning_rate": 7.048422889997115e-07,
+      "logits/chosen": 0.287109375,
+      "logits/rejected": 0.392578125,
+      "logps/chosen": -1.2265625,
+      "logps/rejected": -1.59375,
+      "loss": 0.6979,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -1.2265625,
+      "rewards/margins": 0.369140625,
+      "rewards/rejected": -1.59375,
+      "step": 190
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 1.4848254919052124,
+      "learning_rate": 6.72815051360494e-07,
+      "logits/chosen": 0.384765625,
+      "logits/rejected": 0.5,
+      "logps/chosen": -1.1796875,
+      "logps/rejected": -1.4765625,
+      "loss": 0.6763,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -1.1796875,
+      "rewards/margins": 0.29296875,
+      "rewards/rejected": -1.4765625,
+      "step": 200
+    },
+    {
+      "epoch": 0.4393305439330544,
+      "grad_norm": 1.0059075355529785,
+      "learning_rate": 6.399606408156687e-07,
+      "logits/chosen": 0.41015625,
+      "logits/rejected": 0.466796875,
+      "logps/chosen": -1.2265625,
+      "logps/rejected": -1.5078125,
+      "loss": 0.6888,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": -1.2265625,
+      "rewards/margins": 0.28125,
+      "rewards/rejected": -1.5078125,
+      "step": 210
+    },
+    {
+      "epoch": 0.4602510460251046,
+      "grad_norm": 1.5360616445541382,
+      "learning_rate": 6.064363137964225e-07,
+      "logits/chosen": 0.435546875,
+      "logits/rejected": 0.53515625,
+      "logps/chosen": -1.203125,
+      "logps/rejected": -1.5546875,
+      "loss": 0.6654,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.203125,
+      "rewards/margins": 0.345703125,
+      "rewards/rejected": -1.5546875,
+      "step": 220
+    },
+    {
+      "epoch": 0.4811715481171548,
+      "grad_norm": 5.390141487121582,
+      "learning_rate": 5.724025332645793e-07,
+      "logits/chosen": 0.458984375,
+      "logits/rejected": 0.53515625,
+      "logps/chosen": -1.28125,
+      "logps/rejected": -1.4921875,
+      "loss": 0.6899,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -1.28125,
+      "rewards/margins": 0.216796875,
+      "rewards/rejected": -1.4921875,
+      "step": 230
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 1.5487908124923706,
+      "learning_rate": 5.380222006625179e-07,
+      "logits/chosen": 0.38671875,
+      "logits/rejected": 0.515625,
+      "logps/chosen": -1.234375,
+      "logps/rejected": -1.6484375,
+      "loss": 0.6761,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -1.234375,
+      "rewards/margins": 0.4140625,
+      "rewards/rejected": -1.6484375,
+      "step": 240
+    },
+    {
+      "epoch": 0.5230125523012552,
+      "grad_norm": 1.3993537425994873,
+      "learning_rate": 5.034598761913916e-07,
+      "logits/chosen": 0.38671875,
+      "logits/rejected": 0.52734375,
+      "logps/chosen": -1.2578125,
+      "logps/rejected": -1.625,
+      "loss": 0.677,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -1.2578125,
+      "rewards/margins": 0.373046875,
+      "rewards/rejected": -1.625,
+      "step": 250
+    },
+    {
+      "epoch": 0.5439330543933054,
+      "grad_norm": 1.6489665508270264,
+      "learning_rate": 4.688809911497609e-07,
+      "logits/chosen": 0.4140625,
+      "logits/rejected": 0.5625,
+      "logps/chosen": -1.2890625,
+      "logps/rejected": -1.671875,
+      "loss": 0.6837,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -1.2890625,
+      "rewards/margins": 0.3828125,
+      "rewards/rejected": -1.671875,
+      "step": 260
+    },
+    {
+      "epoch": 0.5648535564853556,
+      "grad_norm": 1.4435418844223022,
+      "learning_rate": 4.344510561027498e-07,
+      "logits/chosen": 0.388671875,
+      "logits/rejected": 0.4921875,
+      "logps/chosen": -1.3203125,
+      "logps/rejected": -1.703125,
+      "loss": 0.6721,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.3203125,
+      "rewards/margins": 0.38671875,
+      "rewards/rejected": -1.703125,
+      "step": 270
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 1.013711929321289,
+      "learning_rate": 4.003348686717949e-07,
+      "logits/chosen": 0.439453125,
+      "logits/rejected": 0.5625,
+      "logps/chosen": -1.296875,
+      "logps/rejected": -1.6484375,
+      "loss": 0.6779,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.628125011920929,
+      "rewards/chosen": -1.296875,
+      "rewards/margins": 0.35546875,
+      "rewards/rejected": -1.6484375,
+      "step": 280
+    },
+    {
+      "epoch": 0.606694560669456,
+      "grad_norm": 1.2121633291244507,
+      "learning_rate": 3.666957247368757e-07,
+      "logits/chosen": 0.3984375,
+      "logits/rejected": 0.5703125,
+      "logps/chosen": -1.2890625,
+      "logps/rejected": -1.65625,
+      "loss": 0.6906,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -1.2890625,
+      "rewards/margins": 0.365234375,
+      "rewards/rejected": -1.65625,
+      "step": 290
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 1.591893196105957,
+      "learning_rate": 3.3369463682677234e-07,
+      "logits/chosen": 0.3984375,
+      "logits/rejected": 0.55078125,
+      "logps/chosen": -1.3671875,
+      "logps/rejected": -1.6796875,
+      "loss": 0.6659,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.628125011920929,
+      "rewards/chosen": -1.3671875,
+      "rewards/margins": 0.3125,
+      "rewards/rejected": -1.6796875,
+      "step": 300
+    },
+    {
+      "epoch": 0.6485355648535565,
+      "grad_norm": 1.368701696395874,
+      "learning_rate": 3.014895634385014e-07,
+      "logits/chosen": 0.431640625,
+      "logits/rejected": 0.54296875,
+      "logps/chosen": -1.3671875,
+      "logps/rejected": -1.734375,
+      "loss": 0.6656,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -1.3671875,
+      "rewards/margins": 0.3671875,
+      "rewards/rejected": -1.734375,
+      "step": 310
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 1.4159173965454102,
+      "learning_rate": 2.7023465297476424e-07,
+      "logits/chosen": 0.462890625,
+      "logits/rejected": 0.6171875,
+      "logps/chosen": -1.390625,
+      "logps/rejected": -1.75,
+      "loss": 0.6505,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -1.390625,
+      "rewards/margins": 0.361328125,
+      "rewards/rejected": -1.75,
+      "step": 320
+    },
+    {
+      "epoch": 0.6903765690376569,
+      "grad_norm": 1.2280809879302979,
+      "learning_rate": 2.4007950591826913e-07,
+      "logits/chosen": 0.42578125,
+      "logits/rejected": 0.53515625,
+      "logps/chosen": -1.3203125,
+      "logps/rejected": -1.7421875,
+      "loss": 0.6651,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.3203125,
+      "rewards/margins": 0.419921875,
+      "rewards/rejected": -1.7421875,
+      "step": 330
+    },
+    {
+      "epoch": 0.7112970711297071,
+      "grad_norm": 1.3542604446411133,
+      "learning_rate": 2.1116845877450805e-07,
+      "logits/chosen": 0.4765625,
+      "logits/rejected": 0.61328125,
+      "logps/chosen": -1.359375,
+      "logps/rejected": -1.7578125,
+      "loss": 0.667,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -1.359375,
+      "rewards/margins": 0.400390625,
+      "rewards/rejected": -1.7578125,
+      "step": 340
+    },
+    {
+      "epoch": 0.7322175732217573,
+      "grad_norm": 1.5316176414489746,
+      "learning_rate": 1.8363989321036577e-07,
+      "logits/chosen": 0.330078125,
+      "logits/rejected": 0.49609375,
+      "logps/chosen": -1.4140625,
+      "logps/rejected": -1.7109375,
+      "loss": 0.6679,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -1.4140625,
+      "rewards/margins": 0.294921875,
+      "rewards/rejected": -1.7109375,
+      "step": 350
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 1.7469818592071533,
+      "learning_rate": 1.5762557369534708e-07,
+      "logits/chosen": 0.48046875,
+      "logits/rejected": 0.58203125,
+      "logps/chosen": -1.421875,
+      "logps/rejected": -1.75,
+      "loss": 0.6766,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6031249761581421,
+      "rewards/chosen": -1.421875,
+      "rewards/margins": 0.33203125,
+      "rewards/rejected": -1.75,
+      "step": 360
+    },
+    {
+      "epoch": 0.7740585774058577,
+      "grad_norm": 1.427762746810913,
+      "learning_rate": 1.332500168157748e-07,
+      "logits/chosen": 0.41015625,
+      "logits/rejected": 0.5234375,
+      "logps/chosen": -1.3671875,
+      "logps/rejected": -1.7890625,
+      "loss": 0.668,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.628125011920929,
+      "rewards/chosen": -1.3671875,
+      "rewards/margins": 0.421875,
+      "rewards/rejected": -1.7890625,
+      "step": 370
+    },
+    {
+      "epoch": 0.7949790794979079,
+      "grad_norm": 1.8916194438934326,
+      "learning_rate": 1.1062989528071681e-07,
+      "logits/chosen": 0.462890625,
+      "logits/rejected": 0.51171875,
+      "logps/chosen": -1.3671875,
+      "logps/rejected": -1.8125,
+      "loss": 0.6799,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -1.3671875,
+      "rewards/margins": 0.447265625,
+      "rewards/rejected": -1.8125,
+      "step": 380
+    },
+    {
+      "epoch": 0.8158995815899581,
+      "grad_norm": 2.0285046100616455,
+      "learning_rate": 8.987347947234192e-08,
+      "logits/chosen": 0.478515625,
+      "logits/rejected": 0.625,
+      "logps/chosen": -1.375,
+      "logps/rejected": -1.859375,
+      "loss": 0.6716,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -1.375,
+      "rewards/margins": 0.482421875,
+      "rewards/rejected": -1.859375,
+      "step": 390
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 1.5867072343826294,
+      "learning_rate": 7.108011921370727e-08,
+      "logits/chosen": 0.44140625,
+      "logits/rejected": 0.58984375,
+      "logps/chosen": -1.453125,
+      "logps/rejected": -1.8203125,
+      "loss": 0.6794,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -1.453125,
+      "rewards/margins": 0.36328125,
+      "rewards/rejected": -1.8203125,
+      "step": 400
+    },
+    {
+      "epoch": 0.8577405857740585,
+      "grad_norm": 1.4711084365844727,
+      "learning_rate": 5.433976823447262e-08,
+      "logits/chosen": 0.5,
+      "logits/rejected": 0.60546875,
+      "logps/chosen": -1.421875,
+      "logps/rejected": -1.8515625,
+      "loss": 0.6766,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": -1.421875,
+      "rewards/margins": 0.4296875,
+      "rewards/rejected": -1.8515625,
+      "step": 410
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "grad_norm": 1.7933145761489868,
+      "learning_rate": 3.973255361067346e-08,
+      "logits/chosen": 0.333984375,
+      "logits/rejected": 0.470703125,
+      "logps/chosen": -1.4765625,
+      "logps/rejected": -1.7578125,
+      "loss": 0.6645,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -1.4765625,
+      "rewards/margins": 0.28125,
+      "rewards/rejected": -1.7578125,
+      "step": 420
+    },
+    {
+      "epoch": 0.899581589958159,
+      "grad_norm": 1.1009119749069214,
+      "learning_rate": 2.732839223940914e-08,
+      "logits/chosen": 0.34375,
+      "logits/rejected": 0.455078125,
+      "logps/chosen": -1.4375,
+      "logps/rejected": -1.8359375,
+      "loss": 0.6838,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -1.4375,
+      "rewards/margins": 0.400390625,
+      "rewards/rejected": -1.8359375,
+      "step": 430
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 3.219727039337158,
+      "learning_rate": 1.7186656184179473e-08,
+      "logits/chosen": 0.40625,
+      "logits/rejected": 0.515625,
+      "logps/chosen": -1.34375,
+      "logps/rejected": -1.7421875,
+      "loss": 0.7008,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -1.34375,
+      "rewards/margins": 0.39453125,
+      "rewards/rejected": -1.7421875,
+      "step": 440
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 1.8418503999710083,
+      "learning_rate": 9.355888492680153e-09,
+      "logits/chosen": 0.435546875,
+      "logits/rejected": 0.56640625,
+      "logps/chosen": -1.4375,
+      "logps/rejected": -1.828125,
+      "loss": 0.6758,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -1.4375,
+      "rewards/margins": 0.396484375,
+      "rewards/rejected": -1.828125,
+      "step": 450
+    },
+    {
+      "epoch": 0.9623430962343096,
+      "grad_norm": 1.1154942512512207,
+      "learning_rate": 3.873570847285012e-09,
+      "logits/chosen": 0.396484375,
+      "logits/rejected": 0.5390625,
+      "logps/chosen": -1.4140625,
+      "logps/rejected": -1.890625,
+      "loss": 0.6633,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -1.4140625,
+      "rewards/margins": 0.474609375,
+      "rewards/rejected": -1.890625,
+      "step": 460
+    },
+    {
+      "epoch": 0.9832635983263598,
+      "grad_norm": 1.7730712890625,
+      "learning_rate": 7.65944160348142e-10,
+      "logits/chosen": 0.41796875,
+      "logits/rejected": 0.58203125,
+      "logps/chosen": -1.4296875,
+      "logps/rejected": -1.796875,
+      "loss": 0.6715,
+      "nll_loss": 0.0,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -1.4296875,
+      "rewards/margins": 0.36328125,
+      "rewards/rejected": -1.796875,
+      "step": 470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 478,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc465cfdfdd7e999ceff13fbf7fe904d8a50dd7dcbf7f0285cad43e3bc613e85
+size 7032