初始化项目，由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-ipo-avg-beta0p01-s42
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,25 @@
+---
+library_name: transformers
+base_model: Qwen/Qwen3-8B
+tags:
+- ronpo
+- mnpo
+- qwen3
+- preference-optimization
+---
+
+# qwen3-8b-ipo-avg-beta0p01-s42
+
+Research checkpoint for the RONPO AAAI revision experiments.
+
+- Method: IPO-avg beta=0.01
+- Base model: `Qwen/Qwen3-8B` with non-thinking generation protocol
+- Seed: 42
+- Local source at upload time: `/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/train/ipo_avg_beta0p01_s42_nhn-b200-q3-seq-07101430-ipo`
+- Uploaded at UTC: 2026-07-11T03:10:12Z
+- Run status metadata: `not found`
+
+Qwen3-8B IPO baseline on the averaged three-reward oracle.
+
+Intended use: reproducibility and evaluation for the RONPO paper. This
+checkpoint is not intended as a production assistant.

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 2490.3512815710615,
+    "train_runtime": 3284.6395,
+    "train_samples": 18644,
+    "train_samples_per_second": 5.676,
+    "train_steps_per_second": 0.044
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

config.yaml

@@ -0,0 +1,53 @@
+model_name_or_path: /NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218
+torch_dtype: null
+attn_implementation: eager
+dataset_mixer:
+  /NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/precomputed/avg_oracle: 1.0
+dataset_splits:
+  - train
+  - test
+preprocessing_num_workers: 12
+bf16: true
+loss_type: ipo
+dpo_beta: 0.01
+simpo_beta: 2.5
+simpo_gamma: 1.0
+eta: 0.0075
+ratio: 0.3333
+max_history_t: 1
+history_weights: [1.0]
+beta: 10
+learning_rate: 5.0e-7
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+optim: adamw_torch
+weight_decay: 0.0
+seed: 42
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+num_train_epochs: 1
+
+per_device_train_batch_size: 1
+per_device_eval_batch_size: 1
+max_length: 2048
+max_prompt_length: 1800
+do_eval: true
+eval_strategy: "steps"
+eval_steps: 500
+logging_steps: 10
+log_level: info
+generate_during_eval: false
+metric_for_best_model: eval_loss
+load_best_model_at_end: false
+save_strategy: "steps"
+save_steps: 1000
+save_total_limit: 1
+save_only_model: true
+save_safetensors: true
+push_to_hub: false
+report_to:
+  - wandb
+output_dir: /NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/train/ipo_avg_beta0p01_s42_nhn-b200-q3-seq-07101430-ipo
+run_name: rev-q3-ipo-b0p01-s42-nhn-b200-q3-seq-07101430-ipo

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.13.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f920002de84073c192a44d179183154a1601e73b7b62b70b2531da96330900af
+size 16381517208

run_status.json

@@ -0,0 +1,15 @@
+{
+  "method": "ipo",
+  "loss_type": "ipo",
+  "seed": 42,
+  "beta": 0.01,
+  "backbone": "Qwen/Qwen3-8B",
+  "status": "completed",
+  "returncode": 0,
+  "completed_at": "2026-07-11T03:08:02Z",
+  "dataset": "/NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/precomputed/avg_oracle",
+  "output_dir": "/NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/train/ipo_avg_beta0p01_s42_nhn-b200-q3-seq-07101430-ipo",
+  "config": "/NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/train/ipo_avg_beta0p01_s42_nhn-b200-q3-seq-07101430-ipo/config.yaml",
+  "train_metrics_exists": true,
+  "trainer_state_exists": true
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 2490.3512815710615,
+    "train_runtime": 3284.6395,
+    "train_samples": 18644,
+    "train_samples_per_second": 5.676,
+    "train_steps_per_second": 0.044
+}

trainer_state.json

@@ -0,0 +1,269 @@
+{
+  "best_global_step": 146,
+  "best_metric": 2487.621826171875,
+  "best_model_checkpoint": "/NHNHOME/WORKSPACE/26msit001_A/mnpo/revision_qwen3_8b/full_iter1/train/ipo_avg_beta0p01_s42_nhn-b200-q3-seq-07101430-ipo/checkpoint-146",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 146,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06864006864006864,
+      "grad_norm": 10027.114290420466,
+      "learning_rate": 3e-07,
+      "logits/chosen": -0.8125,
+      "logits/rejected": -0.8203125,
+      "logps/chosen": -16.0,
+      "logps/rejected": -15.9375,
+      "loss": 2489.71826171875,
+      "rewards/accuracies": 0.518750011920929,
+      "rewards/chosen": -153.37606811523438,
+      "rewards/margins": 1.1065444946289062,
+      "rewards/rejected": -154.48260498046875,
+      "step": 10
+    },
+    {
+      "epoch": 0.13728013728013727,
+      "grad_norm": 8819.949018899022,
+      "learning_rate": 4.988506452457066e-07,
+      "logits/chosen": -0.8828125,
+      "logits/rejected": -0.85546875,
+      "logps/chosen": -15.8125,
+      "logps/rejected": -15.875,
+      "loss": 2487.34423828125,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -153.25982666015625,
+      "rewards/margins": 1.295501708984375,
+      "rewards/rejected": -154.55532836914062,
+      "step": 20
+    },
+    {
+      "epoch": 0.2059202059202059,
+      "grad_norm": 8211.073831209287,
+      "learning_rate": 4.860414659112948e-07,
+      "logits/chosen": -0.76953125,
+      "logits/rejected": -0.77734375,
+      "logps/chosen": -16.0,
+      "logps/rejected": -15.9375,
+      "loss": 2502.94287109375,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -154.95367431640625,
+      "rewards/margins": -0.227020263671875,
+      "rewards/rejected": -154.72665405273438,
+      "step": 30
+    },
+    {
+      "epoch": 0.27456027456027454,
+      "grad_norm": 8719.803872679653,
+      "learning_rate": 4.597220474379125e-07,
+      "logits/chosen": -0.76171875,
+      "logits/rejected": -0.7734375,
+      "logps/chosen": -16.0,
+      "logps/rejected": -15.9375,
+      "loss": 2498.837158203125,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -154.68797302246094,
+      "rewards/margins": 0.18853759765625,
+      "rewards/rejected": -154.87649536132812,
+      "step": 40
+    },
+    {
+      "epoch": 0.3432003432003432,
+      "grad_norm": 9152.672087584928,
+      "learning_rate": 4.2139882699413613e-07,
+      "logits/chosen": -0.765625,
+      "logits/rejected": -0.74609375,
+      "logps/chosen": -16.0,
+      "logps/rejected": -16.0,
+      "loss": 2489.340087890625,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -154.12176513671875,
+      "rewards/margins": 1.1353836059570312,
+      "rewards/rejected": -155.2571563720703,
+      "step": 50
+    },
+    {
+      "epoch": 0.4118404118404118,
+      "grad_norm": 14845.378062289448,
+      "learning_rate": 3.7326529999303633e-07,
+      "logits/chosen": -0.73046875,
+      "logits/rejected": -0.734375,
+      "logps/chosen": -16.0,
+      "logps/rejected": -15.9375,
+      "loss": 2498.56591796875,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -155.47003173828125,
+      "rewards/margins": 0.18729400634765625,
+      "rewards/rejected": -155.65731811523438,
+      "step": 60
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "grad_norm": 10089.737237780628,
+      "learning_rate": 3.1807647161082797e-07,
+      "logits/chosen": -0.72265625,
+      "logits/rejected": -0.69140625,
+      "logps/chosen": -15.9375,
+      "logps/rejected": -15.9375,
+      "loss": 2490.2265625,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": -154.46917724609375,
+      "rewards/margins": 1.055145263671875,
+      "rewards/rejected": -155.52432250976562,
+      "step": 70
+    },
+    {
+      "epoch": 0.5491205491205491,
+      "grad_norm": 13080.69256033714,
+      "learning_rate": 2.5899116932879534e-07,
+      "logits/chosen": -0.7109375,
+      "logits/rejected": -0.71875,
+      "logps/chosen": -16.0,
+      "logps/rejected": -16.0,
+      "loss": 2498.123046875,
+      "rewards/accuracies": 0.48124998807907104,
+      "rewards/chosen": -155.04067993164062,
+      "rewards/margins": 0.243621826171875,
+      "rewards/rejected": -155.2843017578125,
+      "step": 80
+    },
+    {
+      "epoch": 0.6177606177606177,
+      "grad_norm": 10488.56173199215,
+      "learning_rate": 1.993912420112756e-07,
+      "logits/chosen": -0.7265625,
+      "logits/rejected": -0.7109375,
+      "logps/chosen": -15.875,
+      "logps/rejected": -15.875,
+      "loss": 2492.578369140625,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -153.39874267578125,
+      "rewards/margins": 0.793731689453125,
+      "rewards/rejected": -154.19247436523438,
+      "step": 90
+    },
+    {
+      "epoch": 0.6864006864006864,
+      "grad_norm": 12700.337502115342,
+      "learning_rate": 1.426879939713322e-07,
+      "logits/chosen": -0.69140625,
+      "logits/rejected": -0.6875,
+      "logps/chosen": -15.875,
+      "logps/rejected": -15.875,
+      "loss": 2490.487060546875,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -153.31903076171875,
+      "rewards/margins": 1.01458740234375,
+      "rewards/rejected": -154.33360290527344,
+      "step": 100
+    },
+    {
+      "epoch": 0.7550407550407551,
+      "grad_norm": 9077.531663523849,
+      "learning_rate": 9.212693310317479e-08,
+      "logits/chosen": -0.69140625,
+      "logits/rejected": -0.69140625,
+      "logps/chosen": -16.0,
+      "logps/rejected": -16.0,
+      "loss": 2487.44677734375,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -154.6409912109375,
+      "rewards/margins": 1.328338623046875,
+      "rewards/rejected": -155.96932983398438,
+      "step": 110
+    },
+    {
+      "epoch": 0.8236808236808236,
+      "grad_norm": 8718.070043453483,
+      "learning_rate": 5.060200865767605e-08,
+      "logits/chosen": -0.625,
+      "logits/rejected": -0.62890625,
+      "logps/chosen": -16.0,
+      "logps/rejected": -16.125,
+      "loss": 2481.56396484375,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -153.7762451171875,
+      "rewards/margins": 1.955291748046875,
+      "rewards/rejected": -155.73153686523438,
+      "step": 120
+    },
+    {
+      "epoch": 0.8923208923208923,
+      "grad_norm": 11737.493049054548,
+      "learning_rate": 2.0489971081290193e-08,
+      "logits/chosen": -0.66015625,
+      "logits/rejected": -0.66015625,
+      "logps/chosen": -15.9375,
+      "logps/rejected": -15.9375,
+      "loss": 2495.81494140625,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -154.38516235351562,
+      "rewards/margins": 0.4686431884765625,
+      "rewards/rejected": -154.8538055419922,
+      "step": 130
+    },
+    {
+      "epoch": 0.960960960960961,
+      "grad_norm": 9402.719273365525,
+      "learning_rate": 3.5143346177878565e-09,
+      "logits/chosen": -0.640625,
+      "logits/rejected": -0.62890625,
+      "logps/chosen": -15.9375,
+      "logps/rejected": -16.0,
+      "loss": 2483.26611328125,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -154.122314453125,
+      "rewards/margins": 1.7264404296875,
+      "rewards/rejected": -155.8487548828125,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -0.65234375,
+      "eval_logits/rejected": -0.625,
+      "eval_logps/chosen": -15.9375,
+      "eval_logps/rejected": -16.0,
+      "eval_loss": 2487.621826171875,
+      "eval_rewards/accuracies": 0.5526315569877625,
+      "eval_rewards/chosen": -154.9027862548828,
+      "eval_rewards/margins": 1.2624943256378174,
+      "eval_rewards/rejected": -156.165283203125,
+      "eval_runtime": 69.2925,
+      "eval_samples_per_second": 8.717,
+      "eval_steps_per_second": 1.097,
+      "step": 146
+    },
+    {
+      "epoch": 1.0,
+      "step": 146,
+      "total_flos": 0.0,
+      "train_loss": 2490.3512815710615,
+      "train_runtime": 3284.6395,
+      "train_samples_per_second": 5.676,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 146,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096ce8a681d0524d243f91b47ce7c5438fabe6ce829262b46c0eecd08477eb93
+size 8401