Upload folder using huggingface_hub

.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 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c0906527c4b2624263a5b31936a52b7977bbf10dc6b7354513159a8fb82fed
+size 2384234968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1ece1d465a9063a116e45fbb9753b649732412ced72734536e04a1915552af
+size 4768663315

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84d11a42c3eeaffdda5adade6b15f4b8d722e929b1856863f9bf6f820dd0250
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f91292b84a994cd254423d23215df10da8aa2ef02d5bf7bbb7aa4b2050cd26
+size 1465

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": "<|endoftext|>",
+    "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6413136438793545,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.045612634699811846,
+      "grad_norm": 59.46120071411133,
+      "learning_rate": 6.409090909090908e-07,
+      "logits/chosen": -1.3211605548858643,
+      "logits/rejected": -1.3492553234100342,
+      "logps/chosen": -169.80906677246094,
+      "logps/rejected": -200.97677612304688,
+      "loss": 0.6812,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -0.0059404876083135605,
+      "rewards/margins": 0.025952553376555443,
+      "rewards/rejected": -0.031893040984869,
+      "step": 50
+    },
+    {
+      "epoch": 0.09122526939962369,
+      "grad_norm": 86.95048522949219,
+      "learning_rate": 1.3227272727272727e-06,
+      "logits/chosen": -1.411544919013977,
+      "logits/rejected": -1.4442178010940552,
+      "logps/chosen": -178.4121551513672,
+      "logps/rejected": -219.94424438476562,
+      "loss": 0.5771,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.29405269026756287,
+      "rewards/margins": 0.4449906647205353,
+      "rewards/rejected": -0.7390434145927429,
+      "step": 100
+    },
+    {
+      "epoch": 0.13683790409943555,
+      "grad_norm": 64.74836730957031,
+      "learning_rate": 1.9909090909090913e-06,
+      "logits/chosen": -1.485386610031128,
+      "logits/rejected": -1.5248019695281982,
+      "logps/chosen": -175.85545349121094,
+      "logps/rejected": -215.98086547851562,
+      "loss": 0.4865,
+      "rewards/accuracies": 0.7524999976158142,
+      "rewards/chosen": -0.47845691442489624,
+      "rewards/margins": 1.005491852760315,
+      "rewards/rejected": -1.483948826789856,
+      "step": 150
+    },
+    {
+      "epoch": 0.18245053879924739,
+      "grad_norm": 48.148223876953125,
+      "learning_rate": 2.6727272727272727e-06,
+      "logits/chosen": -1.6364929676055908,
+      "logits/rejected": -1.6319957971572876,
+      "logps/chosen": -179.0496063232422,
+      "logps/rejected": -229.71234130859375,
+      "loss": 0.4315,
+      "rewards/accuracies": 0.7674999833106995,
+      "rewards/chosen": -0.8819997906684875,
+      "rewards/margins": 1.617713212966919,
+      "rewards/rejected": -2.499713182449341,
+      "step": 200
+    },
+    {
+      "epoch": 0.22806317349905925,
+      "grad_norm": 90.83224487304688,
+      "learning_rate": 2.9987134348280704e-06,
+      "logits/chosen": -1.5377447605133057,
+      "logits/rejected": -1.5789711475372314,
+      "logps/chosen": -189.28240966796875,
+      "logps/rejected": -241.5106964111328,
+      "loss": 0.4431,
+      "rewards/accuracies": 0.7674999833106995,
+      "rewards/chosen": -1.1264184713363647,
+      "rewards/margins": 1.8479437828063965,
+      "rewards/rejected": -2.9743621349334717,
+      "step": 250
+    },
+    {
+      "epoch": 0.2736758081988711,
+      "grad_norm": 54.77507781982422,
+      "learning_rate": 2.9890189525113655e-06,
+      "logits/chosen": -1.6410760879516602,
+      "logits/rejected": -1.5978457927703857,
+      "logps/chosen": -178.2059326171875,
+      "logps/rejected": -239.80654907226562,
+      "loss": 0.4138,
+      "rewards/accuracies": 0.7987499833106995,
+      "rewards/chosen": -1.0319082736968994,
+      "rewards/margins": 2.2714104652404785,
+      "rewards/rejected": -3.303318500518799,
+      "step": 300
+    },
+    {
+      "epoch": 0.3192884428986829,
+      "grad_norm": 40.69072723388672,
+      "learning_rate": 2.9698817631509474e-06,
+      "logits/chosen": -1.7185229063034058,
+      "logits/rejected": -1.751165509223938,
+      "logps/chosen": -190.39962768554688,
+      "logps/rejected": -247.27247619628906,
+      "loss": 0.385,
+      "rewards/accuracies": 0.8112499713897705,
+      "rewards/chosen": -1.313816785812378,
+      "rewards/margins": 2.4288673400878906,
+      "rewards/rejected": -3.7426836490631104,
+      "step": 350
+    },
+    {
+      "epoch": 0.36490107759849477,
+      "grad_norm": 51.27244567871094,
+      "learning_rate": 2.9414232264329826e-06,
+      "logits/chosen": -1.6467254161834717,
+      "logits/rejected": -1.6478239297866821,
+      "logps/chosen": -179.54312133789062,
+      "logps/rejected": -231.5401153564453,
+      "loss": 0.431,
+      "rewards/accuracies": 0.7837499976158142,
+      "rewards/chosen": -1.276109218597412,
+      "rewards/margins": 2.3179662227630615,
+      "rewards/rejected": -3.5940752029418945,
+      "step": 400
+    },
+    {
+      "epoch": 0.41051371229830663,
+      "grad_norm": 70.65045928955078,
+      "learning_rate": 2.9038238139523195e-06,
+      "logits/chosen": -1.649796724319458,
+      "logits/rejected": -1.6734592914581299,
+      "logps/chosen": -178.8260955810547,
+      "logps/rejected": -234.79722595214844,
+      "loss": 0.3768,
+      "rewards/accuracies": 0.8149999976158142,
+      "rewards/chosen": -1.090864896774292,
+      "rewards/margins": 2.503946304321289,
+      "rewards/rejected": -3.59481143951416,
+      "step": 450
+    },
+    {
+      "epoch": 0.4561263469981185,
+      "grad_norm": 53.61136245727539,
+      "learning_rate": 2.857321964740558e-06,
+      "logits/chosen": -1.5642222166061401,
+      "logits/rejected": -1.5648502111434937,
+      "logps/chosen": -191.90611267089844,
+      "logps/rejected": -252.19386291503906,
+      "loss": 0.3945,
+      "rewards/accuracies": 0.7962499856948853,
+      "rewards/chosen": -1.3972392082214355,
+      "rewards/margins": 2.93603515625,
+      "rewards/rejected": -4.3332743644714355,
+      "step": 500
+    },
+    {
+      "epoch": 0.5017389816979303,
+      "grad_norm": 51.6324577331543,
+      "learning_rate": 2.802212573189981e-06,
+      "logits/chosen": -1.6049363613128662,
+      "logits/rejected": -1.6026443243026733,
+      "logps/chosen": -187.35401916503906,
+      "logps/rejected": -257.5898742675781,
+      "loss": 0.331,
+      "rewards/accuracies": 0.8287500143051147,
+      "rewards/chosen": -1.2774113416671753,
+      "rewards/margins": 3.223512649536133,
+      "rewards/rejected": -4.500924110412598,
+      "step": 550
+    },
+    {
+      "epoch": 0.5473516163977422,
+      "grad_norm": 40.728816986083984,
+      "learning_rate": 2.738845118962275e-06,
+      "logits/chosen": -1.6046830415725708,
+      "logits/rejected": -1.5583266019821167,
+      "logps/chosen": -197.91168212890625,
+      "logps/rejected": -263.0049743652344,
+      "loss": 0.3482,
+      "rewards/accuracies": 0.8224999904632568,
+      "rewards/chosen": -1.6200157403945923,
+      "rewards/margins": 3.3425958156585693,
+      "rewards/rejected": -4.962611198425293,
+      "step": 600
+    },
+    {
+      "epoch": 0.592964251097554,
+      "grad_norm": 45.273345947265625,
+      "learning_rate": 2.6676214507413463e-06,
+      "logits/chosen": -1.6240191459655762,
+      "logits/rejected": -1.611716866493225,
+      "logps/chosen": -194.59600830078125,
+      "logps/rejected": -265.8725891113281,
+      "loss": 0.3288,
+      "rewards/accuracies": 0.8412500023841858,
+      "rewards/chosen": -1.3388230800628662,
+      "rewards/margins": 3.5074219703674316,
+      "rewards/rejected": -4.846245288848877,
+      "step": 650
+    },
+    {
+      "epoch": 0.6385768857973658,
+      "grad_norm": 34.892608642578125,
+      "learning_rate": 2.5889932378846963e-06,
+      "logits/chosen": -1.7866308689117432,
+      "logits/rejected": -1.7742173671722412,
+      "logps/chosen": -184.9108428955078,
+      "logps/rejected": -247.7977294921875,
+      "loss": 0.3715,
+      "rewards/accuracies": 0.8149999976158142,
+      "rewards/chosen": -1.4488279819488525,
+      "rewards/margins": 3.0412204265594482,
+      "rewards/rejected": -4.490048408508301,
+      "step": 700
+    },
+    {
+      "epoch": 0.6841895204971777,
+      "grad_norm": 55.344505310058594,
+      "learning_rate": 2.5052340273394205e-06,
+      "logits/chosen": -1.826340675354004,
+      "logits/rejected": -1.8333815336227417,
+      "logps/chosen": -184.3016357421875,
+      "logps/rejected": -246.4990692138672,
+      "loss": 0.3508,
+      "rewards/accuracies": 0.8274999856948853,
+      "rewards/chosen": -1.5381311178207397,
+      "rewards/margins": 3.2081944942474365,
+      "rewards/rejected": -4.746325492858887,
+      "step": 750
+    },
+    {
+      "epoch": 0.7298021551969895,
+      "grad_norm": 16.396432876586914,
+      "learning_rate": 2.4134580840681784e-06,
+      "logits/chosen": -1.8897172212600708,
+      "logits/rejected": -1.9127064943313599,
+      "logps/chosen": -206.5291748046875,
+      "logps/rejected": -274.1864318847656,
+      "loss": 0.3101,
+      "rewards/accuracies": 0.8550000190734863,
+      "rewards/chosen": -2.1525042057037354,
+      "rewards/margins": 3.880983591079712,
+      "rewards/rejected": -6.033487319946289,
+      "step": 800
+    },
+    {
+      "epoch": 0.7754147898968015,
+      "grad_norm": 37.60529327392578,
+      "learning_rate": 2.3158893890861404e-06,
+      "logits/chosen": -1.7926125526428223,
+      "logits/rejected": -1.7985824346542358,
+      "logps/chosen": -196.04129028320312,
+      "logps/rejected": -259.4538269042969,
+      "loss": 0.3114,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -2.2751173973083496,
+      "rewards/margins": 3.9349923133850098,
+      "rewards/rejected": -6.210109710693359,
+      "step": 850
+    },
+    {
+      "epoch": 0.8210274245966133,
+      "grad_norm": 38.6811408996582,
+      "learning_rate": 2.213146680389758e-06,
+      "logits/chosen": -1.8608883619308472,
+      "logits/rejected": -1.8560402393341064,
+      "logps/chosen": -196.21221923828125,
+      "logps/rejected": -274.54345703125,
+      "loss": 0.3121,
+      "rewards/accuracies": 0.8450000286102295,
+      "rewards/chosen": -2.3408617973327637,
+      "rewards/margins": 4.028858184814453,
+      "rewards/rejected": -6.369719982147217,
+      "step": 900
+    },
+    {
+      "epoch": 0.8666400592964251,
+      "grad_norm": 67.59371948242188,
+      "learning_rate": 2.1058815073078422e-06,
+      "logits/chosen": -1.945671558380127,
+      "logits/rejected": -1.9288123846054077,
+      "logps/chosen": -197.5050811767578,
+      "logps/rejected": -271.6333312988281,
+      "loss": 0.2909,
+      "rewards/accuracies": 0.8537499904632568,
+      "rewards/chosen": -1.4789001941680908,
+      "rewards/margins": 4.0447797775268555,
+      "rewards/rejected": -5.523679256439209,
+      "step": 950
+    },
+    {
+      "epoch": 0.912252693996237,
+      "grad_norm": 28.43963050842285,
+      "learning_rate": 1.99477409866065e-06,
+      "logits/chosen": -1.9384291172027588,
+      "logits/rejected": -1.9162278175354004,
+      "logps/chosen": -200.1200408935547,
+      "logps/rejected": -264.21453857421875,
+      "loss": 0.3136,
+      "rewards/accuracies": 0.8462499976158142,
+      "rewards/chosen": -1.7790579795837402,
+      "rewards/margins": 3.894080400466919,
+      "rewards/rejected": -5.673138618469238,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9578653286960488,
+      "grad_norm": 49.5960807800293,
+      "learning_rate": 1.8805290490461682e-06,
+      "logits/chosen": -1.9607409238815308,
+      "logits/rejected": -1.9329227209091187,
+      "logps/chosen": -190.69606018066406,
+      "logps/rejected": -262.543212890625,
+      "loss": 0.2701,
+      "rewards/accuracies": 0.8799999952316284,
+      "rewards/chosen": -1.4124534130096436,
+      "rewards/margins": 3.9889495372772217,
+      "rewards/rejected": -5.401403427124023,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0027367580819888,
+      "grad_norm": 8.592507362365723,
+      "learning_rate": 1.763870850609299e-06,
+      "logits/chosen": -2.1728835105895996,
+      "logits/rejected": -2.0995230674743652,
+      "logps/chosen": -191.92657470703125,
+      "logps/rejected": -273.9614562988281,
+      "loss": 0.2427,
+      "rewards/accuracies": 0.8856416940689087,
+      "rewards/chosen": -1.5243728160858154,
+      "rewards/margins": 4.81222677230835,
+      "rewards/rejected": -6.336598873138428,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0483493927818006,
+      "grad_norm": 15.577631950378418,
+      "learning_rate": 1.6455392986294975e-06,
+      "logits/chosen": -2.4582772254943848,
+      "logits/rejected": -2.3846638202667236,
+      "logps/chosen": -189.32957458496094,
+      "logps/rejected": -283.9933166503906,
+      "loss": 0.063,
+      "rewards/accuracies": 0.9825000166893005,
+      "rewards/chosen": -1.279435634613037,
+      "rewards/margins": 6.347279071807861,
+      "rewards/rejected": -7.626713752746582,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0939620274816124,
+      "grad_norm": 43.521793365478516,
+      "learning_rate": 1.5262848000626241e-06,
+      "logits/chosen": -3.1720001697540283,
+      "logits/rejected": -3.0936548709869385,
+      "logps/chosen": -191.5170440673828,
+      "logps/rejected": -302.63201904296875,
+      "loss": 0.0713,
+      "rewards/accuracies": 0.9800000190734863,
+      "rewards/chosen": -1.885518193244934,
+      "rewards/margins": 7.22011661529541,
+      "rewards/rejected": -9.105633735656738,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1395746621814242,
+      "grad_norm": 24.051679611206055,
+      "learning_rate": 1.4068636147881868e-06,
+      "logits/chosen": -3.590402126312256,
+      "logits/rejected": -3.4608168601989746,
+      "logps/chosen": -199.92221069335938,
+      "logps/rejected": -318.69219970703125,
+      "loss": 0.05,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -2.2472312450408936,
+      "rewards/margins": 8.160175323486328,
+      "rewards/rejected": -10.407405853271484,
+      "step": 1250
+    },
+    {
+      "epoch": 1.185187296881236,
+      "grad_norm": 9.708622932434082,
+      "learning_rate": 1.288033059739901e-06,
+      "logits/chosen": -3.806685209274292,
+      "logits/rejected": -3.6277265548706055,
+      "logps/chosen": -205.2801971435547,
+      "logps/rejected": -317.83807373046875,
+      "loss": 0.063,
+      "rewards/accuracies": 0.9825000166893005,
+      "rewards/chosen": -2.7129626274108887,
+      "rewards/margins": 8.290043830871582,
+      "rewards/rejected": -11.003006935119629,
+      "step": 1300
+    },
+    {
+      "epoch": 1.230799931581048,
+      "grad_norm": 2.236952781677246,
+      "learning_rate": 1.170546706332872e-06,
+      "logits/chosen": -3.8718817234039307,
+      "logits/rejected": -3.7462046146392822,
+      "logps/chosen": -209.9652862548828,
+      "logps/rejected": -328.6727600097656,
+      "loss": 0.0501,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -3.4696946144104004,
+      "rewards/margins": 8.770748138427734,
+      "rewards/rejected": -12.240442276000977,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2764125662808599,
+      "grad_norm": 1.4985854625701904,
+      "learning_rate": 1.0551496016432202e-06,
+      "logits/chosen": -4.127021312713623,
+      "logits/rejected": -3.9822707176208496,
+      "logps/chosen": -216.8661651611328,
+      "logps/rejected": -341.8252258300781,
+      "loss": 0.0577,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -3.4729561805725098,
+      "rewards/margins": 8.868853569030762,
+      "rewards/rejected": -12.34181022644043,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3220252009806717,
+      "grad_norm": 37.12932205200195,
+      "learning_rate": 9.425735436453361e-07,
+      "logits/chosen": -4.2538580894470215,
+      "logits/rejected": -4.086177825927734,
+      "logps/chosen": -206.88836669921875,
+      "logps/rejected": -324.8296813964844,
+      "loss": 0.0603,
+      "rewards/accuracies": 0.9775000214576721,
+      "rewards/chosen": -3.3129966259002686,
+      "rewards/margins": 8.81570053100586,
+      "rewards/rejected": -12.128695487976074,
+      "step": 1450
+    },
+    {
+      "epoch": 1.3676378356804835,
+      "grad_norm": 19.34769630432129,
+      "learning_rate": 8.356741060752298e-07,
+      "logits/chosen": -4.326617240905762,
+      "logits/rejected": -4.108016490936279,
+      "logps/chosen": -211.08132934570312,
+      "logps/rejected": -342.179443359375,
+      "loss": 0.0639,
+      "rewards/accuracies": 0.9787499904632568,
+      "rewards/chosen": -3.5119857788085938,
+      "rewards/margins": 9.29565715789795,
+      "rewards/rejected": -12.807641983032227,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4132504703802953,
+      "grad_norm": 3.8228871822357178,
+      "learning_rate": 7.307683094676016e-07,
+      "logits/chosen": -4.324881076812744,
+      "logits/rejected": -4.193660259246826,
+      "logps/chosen": -209.66769409179688,
+      "logps/rejected": -341.2529296875,
+      "loss": 0.0562,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -3.7620954513549805,
+      "rewards/margins": 9.563469886779785,
+      "rewards/rejected": -13.32556438446045,
+      "step": 1550
+    },
+    {
+      "epoch": 1.4588631050801073,
+      "grad_norm": 10.610180854797363,
+      "learning_rate": 6.30740643853663e-07,
+      "logits/chosen": -4.231253623962402,
+      "logits/rejected": -4.145637512207031,
+      "logps/chosen": -206.0325927734375,
+      "logps/rejected": -329.6341857910156,
+      "loss": 0.0599,
+      "rewards/accuracies": 0.9775000214576721,
+      "rewards/chosen": -3.3670105934143066,
+      "rewards/margins": 9.107893943786621,
+      "rewards/rejected": -12.474905014038086,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5044757397799189,
+      "grad_norm": 3.419102191925049,
+      "learning_rate": 5.362254409462939e-07,
+      "logits/chosen": -4.283145904541016,
+      "logits/rejected": -4.177493095397949,
+      "logps/chosen": -207.3034210205078,
+      "logps/rejected": -323.41595458984375,
+      "loss": 0.0611,
+      "rewards/accuracies": 0.9737499952316284,
+      "rewards/chosen": -3.4872689247131348,
+      "rewards/margins": 8.951678276062012,
+      "rewards/rejected": -12.438947677612305,
+      "step": 1650
+    },
+    {
+      "epoch": 1.550088374479731,
+      "grad_norm": 9.434532165527344,
+      "learning_rate": 4.478220748305115e-07,
+      "logits/chosen": -4.194823265075684,
+      "logits/rejected": -4.0666184425354,
+      "logps/chosen": -206.98306274414062,
+      "logps/rejected": -332.0705871582031,
+      "loss": 0.0626,
+      "rewards/accuracies": 0.9800000190734863,
+      "rewards/chosen": -3.25546932220459,
+      "rewards/margins": 9.118634223937988,
+      "rewards/rejected": -12.374103546142578,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5957010091795427,
+      "grad_norm": 25.252395629882812,
+      "learning_rate": 3.6609116099512447e-07,
+      "logits/chosen": -4.359646320343018,
+      "logits/rejected": -4.207290172576904,
+      "logps/chosen": -213.02706909179688,
+      "logps/rejected": -331.1492919921875,
+      "loss": 0.0584,
+      "rewards/accuracies": 0.9787499904632568,
+      "rewards/chosen": -3.5253746509552,
+      "rewards/margins": 9.35997200012207,
+      "rewards/rejected": -12.885346412658691,
+      "step": 1750
+    },
+    {
+      "epoch": 1.6413136438793545,
+      "grad_norm": 3.1381542682647705,
+      "learning_rate": 2.915510011544664e-07,
+      "logits/chosen": -4.435996055603027,
+      "logits/rejected": -4.291849136352539,
+      "logps/chosen": -211.94927978515625,
+      "logps/rejected": -346.5935974121094,
+      "loss": 0.0417,
+      "rewards/accuracies": 0.9850000143051147,
+      "rewards/chosen": -3.7163028717041016,
+      "rewards/margins": 9.784122467041016,
+      "rewards/rejected": -13.5004243850708,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdc17851ff3ea21e6d6a9096173770699ec390ffb756097275a3c3f068c3e3c
+size 6545