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 sha256:30692ceb235c4429caf85385bb5458694b351ae55100bbfb3f50a74566d5f9f1
+size 2384234968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd62ddddee6c23a6650a91d1b2d97b6552130af70cc0c03b742eeb84fd96ec01
+size 4768663315

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dc60940088350df2476daec612777256353a222718d12ad1d77c0a8edad709
+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 +1,469 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1493,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.033489618218352314,
+      "grad_norm": 90.51985931396484,
+      "learning_rate": 4.835900870730074e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -179.42369079589844,
+      "logps/rejected": -227.34011840820312,
+      "loss": 0.6272,
+      "rewards/accuracies": 0.4987500011920929,
+      "rewards/chosen": -0.41917884349823,
+      "rewards/margins": 0.4206826388835907,
+      "rewards/rejected": -0.8398614525794983,
+      "step": 50
+    },
+    {
+      "epoch": 0.06697923643670463,
+      "grad_norm": 122.67408752441406,
+      "learning_rate": 4.668452779638312e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -189.38446044921875,
+      "logps/rejected": -243.21636962890625,
+      "loss": 0.6008,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.9909499287605286,
+      "rewards/margins": 0.8664093613624573,
+      "rewards/rejected": -1.8573591709136963,
+      "step": 100
+    },
+    {
+      "epoch": 0.10046885465505694,
+      "grad_norm": 69.09490203857422,
+      "learning_rate": 4.501004688546551e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -172.51051330566406,
+      "logps/rejected": -237.64398193359375,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.5912500023841858,
+      "rewards/chosen": -0.773537814617157,
+      "rewards/margins": 1.0922305583953857,
+      "rewards/rejected": -1.8657684326171875,
+      "step": 150
+    },
+    {
+      "epoch": 0.13395847287340926,
+      "grad_norm": 92.90730285644531,
+      "learning_rate": 4.333556597454789e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -185.27850341796875,
+      "logps/rejected": -240.15431213378906,
+      "loss": 0.5958,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": -0.8680741190910339,
+      "rewards/margins": 1.0129902362823486,
+      "rewards/rejected": -1.8810642957687378,
+      "step": 200
+    },
+    {
+      "epoch": 0.16744809109176156,
+      "grad_norm": 41.30106735229492,
+      "learning_rate": 4.166108506363028e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -185.0808563232422,
+      "logps/rejected": -243.77664184570312,
+      "loss": 0.5232,
+      "rewards/accuracies": 0.5950000286102295,
+      "rewards/chosen": -0.6241927742958069,
+      "rewards/margins": 1.5013166666030884,
+      "rewards/rejected": -2.125509262084961,
+      "step": 250
+    },
+    {
+      "epoch": 0.20093770931011387,
+      "grad_norm": 88.7403793334961,
+      "learning_rate": 3.998660415271266e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -184.0787353515625,
+      "logps/rejected": -243.6924285888672,
+      "loss": 0.5419,
+      "rewards/accuracies": 0.5950000286102295,
+      "rewards/chosen": -0.8100302219390869,
+      "rewards/margins": 1.521090030670166,
+      "rewards/rejected": -2.331120491027832,
+      "step": 300
+    },
+    {
+      "epoch": 0.23442732752846618,
+      "grad_norm": 70.95861053466797,
+      "learning_rate": 3.831212324179505e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": -1.532848834991455,
+      "logps/chosen": -182.43124389648438,
+      "logps/rejected": -248.5233917236328,
+      "loss": 0.5533,
+      "rewards/accuracies": 0.5824999809265137,
+      "rewards/chosen": -1.069503903388977,
+      "rewards/margins": 1.6424156427383423,
+      "rewards/rejected": -2.7119195461273193,
+      "step": 350
+    },
+    {
+      "epoch": 0.2679169457468185,
+      "grad_norm": 71.3283462524414,
+      "learning_rate": 3.663764233087743e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -180.90724182128906,
+      "logps/rejected": -253.06655883789062,
+      "loss": 0.5131,
+      "rewards/accuracies": 0.6449999809265137,
+      "rewards/chosen": -0.9932506084442139,
+      "rewards/margins": 2.001958131790161,
+      "rewards/rejected": -2.995208740234375,
+      "step": 400
+    },
+    {
+      "epoch": 0.3014065639651708,
+      "grad_norm": 52.41379928588867,
+      "learning_rate": 3.496316141995982e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -187.8169708251953,
+      "logps/rejected": -250.7092742919922,
+      "loss": 0.574,
+      "rewards/accuracies": 0.6087499856948853,
+      "rewards/chosen": -0.9525413513183594,
+      "rewards/margins": 1.8562077283859253,
+      "rewards/rejected": -2.808749198913574,
+      "step": 450
+    },
+    {
+      "epoch": 0.33489618218352313,
+      "grad_norm": 86.05554962158203,
+      "learning_rate": 3.32886805090422e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -184.93011474609375,
+      "logps/rejected": -245.39427185058594,
+      "loss": 0.545,
+      "rewards/accuracies": 0.6200000047683716,
+      "rewards/chosen": -0.9822418093681335,
+      "rewards/margins": 1.7062770128250122,
+      "rewards/rejected": -2.68851900100708,
+      "step": 500
+    },
+    {
+      "epoch": 0.3683858004018754,
+      "grad_norm": 24.4642391204834,
+      "learning_rate": 3.1614199598124583e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -177.97482299804688,
+      "logps/rejected": -253.92169189453125,
+      "loss": 0.5249,
+      "rewards/accuracies": 0.6150000095367432,
+      "rewards/chosen": -0.7585690021514893,
+      "rewards/margins": 2.060235023498535,
+      "rewards/rejected": -2.8188037872314453,
+      "step": 550
+    },
+    {
+      "epoch": 0.40187541862022774,
+      "grad_norm": 28.010169982910156,
+      "learning_rate": 2.993971868720697e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -187.2054443359375,
+      "logps/rejected": -262.4362487792969,
+      "loss": 0.531,
+      "rewards/accuracies": 0.6212499737739563,
+      "rewards/chosen": -1.0288543701171875,
+      "rewards/margins": 2.0049030780792236,
+      "rewards/rejected": -3.033757209777832,
+      "step": 600
+    },
+    {
+      "epoch": 0.43536503683858,
+      "grad_norm": 88.00039672851562,
+      "learning_rate": 2.8265237776289352e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -199.0946044921875,
+      "logps/rejected": -257.4405212402344,
+      "loss": 0.506,
+      "rewards/accuracies": 0.6175000071525574,
+      "rewards/chosen": -0.9385867118835449,
+      "rewards/margins": 1.9474469423294067,
+      "rewards/rejected": -2.8860340118408203,
+      "step": 650
+    },
+    {
+      "epoch": 0.46885465505693236,
+      "grad_norm": 76.95013427734375,
+      "learning_rate": 2.6590756865371737e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -188.61651611328125,
+      "logps/rejected": -255.59820556640625,
+      "loss": 0.4841,
+      "rewards/accuracies": 0.6287500262260437,
+      "rewards/chosen": -0.9187755584716797,
+      "rewards/margins": 2.190307378768921,
+      "rewards/rejected": -3.1090831756591797,
+      "step": 700
+    },
+    {
+      "epoch": 0.5023442732752846,
+      "grad_norm": 37.079219818115234,
+      "learning_rate": 2.491627595445412e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -182.82937622070312,
+      "logps/rejected": -253.3831787109375,
+      "loss": 0.5061,
+      "rewards/accuracies": 0.6324999928474426,
+      "rewards/chosen": -0.8986356854438782,
+      "rewards/margins": 2.1806037425994873,
+      "rewards/rejected": -3.0792391300201416,
+      "step": 750
+    },
+    {
+      "epoch": 0.535833891493637,
+      "grad_norm": 31.89027976989746,
+      "learning_rate": 2.3241795043536505e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -172.42593383789062,
+      "logps/rejected": -251.63729858398438,
+      "loss": 0.4358,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.7772516012191772,
+      "rewards/margins": 2.509305953979492,
+      "rewards/rejected": -3.286557674407959,
+      "step": 800
+    },
+    {
+      "epoch": 0.5693235097119893,
+      "grad_norm": 49.636253356933594,
+      "learning_rate": 2.156731413261889e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -177.4981231689453,
+      "logps/rejected": -252.06234741210938,
+      "loss": 0.4752,
+      "rewards/accuracies": 0.6262500286102295,
+      "rewards/chosen": -0.8873915672302246,
+      "rewards/margins": 2.302338123321533,
+      "rewards/rejected": -3.1897289752960205,
+      "step": 850
+    },
+    {
+      "epoch": 0.6028131279303416,
+      "grad_norm": 42.22234344482422,
+      "learning_rate": 1.9892833221701274e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -185.84585571289062,
+      "logps/rejected": -251.1869354248047,
+      "loss": 0.5284,
+      "rewards/accuracies": 0.6200000047683716,
+      "rewards/chosen": -0.9590955972671509,
+      "rewards/margins": 2.267340660095215,
+      "rewards/rejected": -3.2264363765716553,
+      "step": 900
+    },
+    {
+      "epoch": 0.6363027461486939,
+      "grad_norm": 60.56090545654297,
+      "learning_rate": 1.8218352310783657e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -182.73912048339844,
+      "logps/rejected": -245.673828125,
+      "loss": 0.4587,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.6209310293197632,
+      "rewards/margins": 2.47007155418396,
+      "rewards/rejected": -3.0910024642944336,
+      "step": 950
+    },
+    {
+      "epoch": 0.6697923643670463,
+      "grad_norm": 47.82743453979492,
+      "learning_rate": 1.6543871399866043e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -170.28599548339844,
+      "logps/rejected": -247.58837890625,
+      "loss": 0.4471,
+      "rewards/accuracies": 0.6424999833106995,
+      "rewards/chosen": -0.5806804895401001,
+      "rewards/margins": 2.4890031814575195,
+      "rewards/rejected": -3.06968355178833,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7032819825853985,
+      "grad_norm": 33.236053466796875,
+      "learning_rate": 1.4869390488948425e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -173.26913452148438,
+      "logps/rejected": -257.9516906738281,
+      "loss": 0.4204,
+      "rewards/accuracies": 0.6825000047683716,
+      "rewards/chosen": -0.4792047142982483,
+      "rewards/margins": 2.651007890701294,
+      "rewards/rejected": -3.1302123069763184,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7367716008037508,
+      "grad_norm": 39.73881530761719,
+      "learning_rate": 1.3194909578030812e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -161.0741424560547,
+      "logps/rejected": -243.2300262451172,
+      "loss": 0.4058,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.5020321607589722,
+      "rewards/margins": 2.7466940879821777,
+      "rewards/rejected": -3.2487261295318604,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7702612190221031,
+      "grad_norm": 37.8878173828125,
+      "learning_rate": 1.1520428667113196e-06,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -177.0689697265625,
+      "logps/rejected": -248.60035705566406,
+      "loss": 0.4246,
+      "rewards/accuracies": 0.6575000286102295,
+      "rewards/chosen": -0.6515741944313049,
+      "rewards/margins": 2.5524582862854004,
+      "rewards/rejected": -3.2040326595306396,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8037508372404555,
+      "grad_norm": 54.17752456665039,
+      "learning_rate": 9.84594775619558e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -184.8086395263672,
+      "logps/rejected": -270.40771484375,
+      "loss": 0.4499,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.5556185841560364,
+      "rewards/margins": 2.5394182205200195,
+      "rewards/rejected": -3.0950369834899902,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8372404554588078,
+      "grad_norm": 37.586639404296875,
+      "learning_rate": 8.171466845277964e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -182.44801330566406,
+      "logps/rejected": -255.1699676513672,
+      "loss": 0.4307,
+      "rewards/accuracies": 0.6537500023841858,
+      "rewards/chosen": -0.6889155507087708,
+      "rewards/margins": 2.603567123413086,
+      "rewards/rejected": -3.292482852935791,
+      "step": 1250
+    },
+    {
+      "epoch": 0.87073007367716,
+      "grad_norm": 52.10836410522461,
+      "learning_rate": 6.496985934360349e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -179.65557861328125,
+      "logps/rejected": -245.46560668945312,
+      "loss": 0.4125,
+      "rewards/accuracies": 0.6637499928474426,
+      "rewards/chosen": -0.5343858003616333,
+      "rewards/margins": 2.6487746238708496,
+      "rewards/rejected": -3.1831603050231934,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9042196918955124,
+      "grad_norm": 30.635120391845703,
+      "learning_rate": 4.822505023442733e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -175.81723022460938,
+      "logps/rejected": -254.23828125,
+      "loss": 0.4304,
+      "rewards/accuracies": 0.6524999737739563,
+      "rewards/chosen": -0.5225290060043335,
+      "rewards/margins": 2.57625675201416,
+      "rewards/rejected": -3.098785638809204,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9377093101138647,
+      "grad_norm": 49.38210678100586,
+      "learning_rate": 3.1480241125251174e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -177.96661376953125,
+      "logps/rejected": -240.63694763183594,
+      "loss": 0.4411,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.4394516050815582,
+      "rewards/margins": 2.5781943798065186,
+      "rewards/rejected": -3.017645835876465,
+      "step": 1400
+    },
+    {
+      "epoch": 0.971198928332217,
+      "grad_norm": 57.8912467956543,
+      "learning_rate": 1.4735432016075018e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": NaN,
+      "logps/chosen": -176.60218811035156,
+      "logps/rejected": -250.90786743164062,
+      "loss": 0.4317,
+      "rewards/accuracies": 0.6474999785423279,
+      "rewards/chosen": -0.514062225818634,
+      "rewards/margins": 2.4711577892303467,
+      "rewards/rejected": -2.985220432281494,
+      "step": 1450
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1493,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83253cf573c71383f710bb1441ffc24338aa5407acd305912e4964de7e52bda0
+size 6545