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

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-8B
+- dpo
+- lora
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/autodl-tmp/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec75f89391f00aef4218bd56822a6d7ee53ab5a3501e1d75214a60009f3a3d62
+size 174655536

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
+}

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 %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf16d339405c4a15ebada27d07bc6d549b6bd41e28819064605c1c48ab32d6c
+size 349601867

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4dbc429b944185e04cecdf1df51cd653fbca1e7456ae9a0b42532c7619b74d2
+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": "<|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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 32.68030548095703,
+      "learning_rate": 8.000000000000001e-06,
+      "logits/chosen": -1.6396703720092773,
+      "logits/rejected": -4.051800727844238,
+      "logps/chosen": -991.9453125,
+      "logps/rejected": -804.3565673828125,
+      "loss": 0.6639,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 0.03835174813866615,
+      "rewards/margins": 0.06670190393924713,
+      "rewards/rejected": -0.028350140899419785,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 15.304901123046875,
+      "learning_rate": 1.8e-05,
+      "logits/chosen": -1.3240370750427246,
+      "logits/rejected": -3.8731656074523926,
+      "logps/chosen": -1051.1619873046875,
+      "logps/rejected": -844.4005126953125,
+      "loss": 0.4827,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.36078932881355286,
+      "rewards/margins": 0.5343167185783386,
+      "rewards/rejected": -0.17352741956710815,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7237646579742432,
+      "learning_rate": 2.8000000000000003e-05,
+      "logits/chosen": -1.3096798658370972,
+      "logits/rejected": -3.6570611000061035,
+      "logps/chosen": -1035.888427734375,
+      "logps/rejected": -842.5685424804688,
+      "loss": 0.0832,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.0725021362304688,
+      "rewards/margins": 3.071218729019165,
+      "rewards/rejected": -0.9987167119979858,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.0076161520555615425,
+      "learning_rate": 3.8e-05,
+      "logits/chosen": -0.8284958004951477,
+      "logits/rejected": -2.9240927696228027,
+      "logps/chosen": -870.0358276367188,
+      "logps/rejected": -1002.2626953125,
+      "loss": 0.0019,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.352972507476807,
+      "rewards/margins": 8.709424018859863,
+      "rewards/rejected": -3.3564505577087402,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.004960057325661182,
+      "learning_rate": 4.8e-05,
+      "logits/chosen": -0.6791419982910156,
+      "logits/rejected": NaN,
+      "logps/chosen": -874.9759521484375,
+      "logps/rejected": -876.6950073242188,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 10.639605522155762,
+      "rewards/margins": 17.804119110107422,
+      "rewards/rejected": -7.164514064788818,
+      "step": 25
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3971771295473445e-07,
+      "learning_rate": 4.999125183044924e-05,
+      "logits/chosen": -0.34096163511276245,
+      "logits/rejected": NaN,
+      "logps/chosen": -939.2772216796875,
+      "logps/rejected": -893.369140625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 14.58117961883545,
+      "rewards/margins": 25.044315338134766,
+      "rewards/rejected": -10.463134765625,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.2492258338880902e-09,
+      "learning_rate": 4.9955722884434114e-05,
+      "logits/chosen": -0.140629380941391,
+      "logits/rejected": -1.5191800594329834,
+      "logps/chosen": -808.206298828125,
+      "logps/rejected": -1101.503662109375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 15.305819511413574,
+      "rewards/margins": 30.041492462158203,
+      "rewards/rejected": -14.735674858093262,
+      "step": 35
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.451875288528754e-08,
+      "learning_rate": 4.98929052218411e-05,
+      "logits/chosen": -0.08291908353567123,
+      "logits/rejected": -1.5926605463027954,
+      "logps/chosen": -799.0426025390625,
+      "logps/rejected": -941.26025390625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 16.93221664428711,
+      "rewards/margins": 32.224510192871094,
+      "rewards/rejected": -15.292287826538086,
+      "step": 40
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.276909547686671e-11,
+      "learning_rate": 4.980286753286195e-05,
+      "logits/chosen": -0.07936549186706543,
+      "logits/rejected": -1.6235363483428955,
+      "logps/chosen": -739.1414794921875,
+      "logps/rejected": -916.921875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.33672523498535,
+      "rewards/margins": 34.177513122558594,
+      "rewards/rejected": -15.840789794921875,
+      "step": 45
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.576159755633526e-11,
+      "learning_rate": 4.968570827238764e-05,
+      "logits/chosen": -0.01292533241212368,
+      "logits/rejected": -1.3671391010284424,
+      "logps/chosen": -804.4974365234375,
+      "logps/rejected": -1069.5924072265625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.07866668701172,
+      "rewards/margins": 38.214569091796875,
+      "rewards/rejected": -20.13589859008789,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.919030007077279e-12,
+      "learning_rate": 4.95415555523494e-05,
+      "logits/chosen": 0.1709265410900116,
+      "logits/rejected": -1.2384920120239258,
+      "logps/chosen": -947.8603515625,
+      "logps/rejected": -1064.900146484375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.031835556030273,
+      "rewards/margins": 38.730384826660156,
+      "rewards/rejected": -19.698551177978516,
+      "step": 55
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.758817560128307e-10,
+      "learning_rate": 4.937056700163015e-05,
+      "logits/chosen": 0.06906407326459885,
+      "logits/rejected": -1.3715310096740723,
+      "logps/chosen": -822.6943359375,
+      "logps/rejected": -1030.0531005859375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.58559799194336,
+      "rewards/margins": 39.85332107543945,
+      "rewards/rejected": -20.267719268798828,
+      "step": 60
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.939841546820287e-14,
+      "learning_rate": 4.917292959369968e-05,
+      "logits/chosen": 0.12646104395389557,
+      "logits/rejected": -1.2485965490341187,
+      "logps/chosen": -848.3450927734375,
+      "logps/rejected": -1009.3894653320312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.458877563476562,
+      "rewards/margins": 38.36582946777344,
+      "rewards/rejected": -19.906951904296875,
+      "step": 65
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.7889120164134056e-09,
+      "learning_rate": 4.8948859442161874e-05,
+      "logits/chosen": -0.05368973687291145,
+      "logits/rejected": -1.1779694557189941,
+      "logps/chosen": -843.9136962890625,
+      "logps/rejected": -1093.84765625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.823673248291016,
+      "rewards/margins": 40.01471710205078,
+      "rewards/rejected": -21.1910457611084,
+      "step": 70
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.912129630321114e-13,
+      "learning_rate": 4.8698601564437675e-05,
+      "logits/chosen": 0.21445438265800476,
+      "logits/rejected": -1.3090651035308838,
+      "logps/chosen": -829.6139526367188,
+      "logps/rejected": -967.4557495117188,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.882862091064453,
+      "rewards/margins": 38.040679931640625,
+      "rewards/rejected": -19.157821655273438,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.708504026669329e-14,
+      "learning_rate": 4.842242961384211e-05,
+      "logits/chosen": 0.24517253041267395,
+      "logits/rejected": -1.157088041305542,
+      "logps/chosen": -695.1763305664062,
+      "logps/rejected": -1113.8963623046875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.196081161499023,
+      "rewards/margins": 39.54194259643555,
+      "rewards/rejected": -21.34585952758789,
+      "step": 80
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.941465566128412e-14,
+      "learning_rate": 4.812064558034847e-05,
+      "logits/chosen": 0.2809743285179138,
+      "logits/rejected": NaN,
+      "logps/chosen": -787.4198608398438,
+      "logps/rejected": -980.9554443359375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.84877586364746,
+      "rewards/margins": 38.223331451416016,
+      "rewards/rejected": -20.374557495117188,
+      "step": 85
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.4191766171837168e-12,
+      "learning_rate": 4.779357946036661e-05,
+      "logits/chosen": 0.09962861239910126,
+      "logits/rejected": NaN,
+      "logps/chosen": -801.5222778320312,
+      "logps/rejected": -1071.500732421875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.405176162719727,
+      "rewards/margins": 38.406497955322266,
+      "rewards/rejected": -21.00132179260254,
+      "step": 90
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.459133756684608e-11,
+      "learning_rate": 4.7441588895896805e-05,
+      "logits/chosen": 0.2806223928928375,
+      "logits/rejected": -1.0863935947418213,
+      "logps/chosen": -767.6072998046875,
+      "logps/rejected": -1064.6678466796875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.554723739624023,
+      "rewards/margins": 37.88628387451172,
+      "rewards/rejected": -19.33156394958496,
+      "step": 95
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.7513205783584868e-13,
+      "learning_rate": 4.7065058783453424e-05,
+      "logits/chosen": 0.056603264063596725,
+      "logits/rejected": -1.2640782594680786,
+      "logps/chosen": -806.6994018554688,
+      "logps/rejected": -1040.3111572265625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.12691879272461,
+      "rewards/margins": 39.593467712402344,
+      "rewards/rejected": -20.466548919677734,
+      "step": 100
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.6995760354632239e-09,
+      "learning_rate": 4.666440085318626e-05,
+      "logits/chosen": 0.10824018716812134,
+      "logits/rejected": NaN,
+      "logps/chosen": -879.4221801757812,
+      "logps/rejected": -935.998046875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.599552154541016,
+      "rewards/margins": 38.348724365234375,
+      "rewards/rejected": -19.74917221069336,
+      "step": 105
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.936039411594038e-09,
+      "learning_rate": 4.6240053218659674e-05,
+      "logits/chosen": 0.13882726430892944,
+      "logits/rejected": NaN,
+      "logps/chosen": -952.7330932617188,
+      "logps/rejected": -1139.3414306640625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.053531646728516,
+      "rewards/margins": 39.75517272949219,
+      "rewards/rejected": -20.701641082763672,
+      "step": 110
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.191885337791803e-10,
+      "learning_rate": 4.579247989778179e-05,
+      "logits/chosen": -0.0359259769320488,
+      "logits/rejected": NaN,
+      "logps/chosen": -923.9146728515625,
+      "logps/rejected": -1042.310302734375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 20.208402633666992,
+      "rewards/margins": 40.31129455566406,
+      "rewards/rejected": -20.102888107299805,
+      "step": 115
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.4515948122337252e-12,
+      "learning_rate": 4.532217030540781e-05,
+      "logits/chosen": 0.15440431237220764,
+      "logits/rejected": -1.2660012245178223,
+      "logps/chosen": -851.1140747070312,
+      "logps/rejected": -1047.481201171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.158273696899414,
+      "rewards/margins": 40.312068939208984,
+      "rewards/rejected": -21.153797149658203,
+      "step": 120
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5757608759492392e-11,
+      "learning_rate": 4.4829638718171954e-05,
+      "logits/chosen": 0.3456230163574219,
+      "logits/rejected": -1.1057803630828857,
+      "logps/chosen": -893.2120361328125,
+      "logps/rejected": -1084.09228515625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.828678131103516,
+      "rewards/margins": 38.39183807373047,
+      "rewards/rejected": -20.563154220581055,
+      "step": 125
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.1954889349671408e-13,
+      "learning_rate": 4.4315423712133595e-05,
+      "logits/chosen": -0.05226398631930351,
+      "logits/rejected": -1.1536673307418823,
+      "logps/chosen": -912.1346435546875,
+      "logps/rejected": -1105.4722900390625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.78438377380371,
+      "rewards/margins": 39.1011962890625,
+      "rewards/rejected": -20.316814422607422,
+      "step": 130
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.803347819660631e-12,
+      "learning_rate": 4.3780087573852213e-05,
+      "logits/chosen": -0.027118748053908348,
+      "logits/rejected": NaN,
+      "logps/chosen": -879.7356567382812,
+      "logps/rejected": -1004.5798950195312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.120731353759766,
+      "rewards/margins": 39.363121032714844,
+      "rewards/rejected": -20.242389678955078,
+      "step": 135
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.3039590507932814e-10,
+      "learning_rate": 4.3224215685535294e-05,
+      "logits/chosen": 0.14910843968391418,
+      "logits/rejected": -1.2413218021392822,
+      "logps/chosen": -663.5389404296875,
+      "logps/rejected": -1058.497314453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.181045532226562,
+      "rewards/margins": 37.49201202392578,
+      "rewards/rejected": -20.310962677001953,
+      "step": 140
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.77260845300043e-07,
+      "learning_rate": 4.2648415884931476e-05,
+      "logits/chosen": 0.055362772196531296,
+      "logits/rejected": -1.4401803016662598,
+      "logps/chosen": -692.7725830078125,
+      "logps/rejected": -937.9246215820312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.841815948486328,
+      "rewards/margins": 36.7285041809082,
+      "rewards/rejected": -18.886686325073242,
+      "step": 145
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.572725065702583e-15,
+      "learning_rate": 4.205331780066892e-05,
+      "logits/chosen": 0.10420503467321396,
+      "logits/rejected": -1.265973687171936,
+      "logps/chosen": -759.1443481445312,
+      "logps/rejected": -1018.9404296875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.249958038330078,
+      "rewards/margins": 38.52296447753906,
+      "rewards/rejected": -20.273006439208984,
+      "step": 150
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0893125811095583e-11,
+      "learning_rate": 4.143957216376561e-05,
+      "logits/chosen": 0.39625436067581177,
+      "logits/rejected": NaN,
+      "logps/chosen": -825.2239990234375,
+      "logps/rejected": -1143.4208984375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.700899124145508,
+      "rewards/margins": 38.6351432800293,
+      "rewards/rejected": -20.934249877929688,
+      "step": 155
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.4590178782091243e-07,
+      "learning_rate": 4.0807850096064605e-05,
+      "logits/chosen": -0.03116157092154026,
+      "logits/rejected": NaN,
+      "logps/chosen": -857.17431640625,
+      "logps/rejected": -1014.2100830078125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.429927825927734,
+      "rewards/margins": 40.577064514160156,
+      "rewards/rejected": -21.14713478088379,
+      "step": 160
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.329039514696433e-10,
+      "learning_rate": 4.0158842376372064e-05,
+      "logits/chosen": 0.09649789333343506,
+      "logits/rejected": -1.1944949626922607,
+      "logps/chosen": -899.2138671875,
+      "logps/rejected": -1035.7169189453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.823169708251953,
+      "rewards/margins": 39.15609359741211,
+      "rewards/rejected": -20.33292579650879,
+      "step": 165
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.8029356613501477e-11,
+      "learning_rate": 3.949325868510083e-05,
+      "logits/chosen": 0.20623020827770233,
+      "logits/rejected": -1.129809856414795,
+      "logps/chosen": -864.5255126953125,
+      "logps/rejected": -1091.5992431640625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.275066375732422,
+      "rewards/margins": 37.25093460083008,
+      "rewards/rejected": -19.975866317749023,
+      "step": 170
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.3411516825801457e-13,
+      "learning_rate": 3.8811826828245334e-05,
+      "logits/chosen": 0.14641737937927246,
+      "logits/rejected": -1.1825670003890991,
+      "logps/chosen": -762.6082153320312,
+      "logps/rejected": -1034.0648193359375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.018020629882812,
+      "rewards/margins": 38.99062728881836,
+      "rewards/rejected": -19.972606658935547,
+      "step": 175
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.0999298627017923e-14,
+      "learning_rate": 3.8115291941536345e-05,
+      "logits/chosen": 0.10354921966791153,
+      "logits/rejected": -1.275838017463684,
+      "logps/chosen": -829.5315551757812,
+      "logps/rejected": -1124.622314453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.930105209350586,
+      "rewards/margins": 41.81705093383789,
+      "rewards/rejected": -22.886947631835938,
+      "step": 180
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.645327750253057e-12,
+      "learning_rate": 3.7404415675646054e-05,
+      "logits/chosen": 0.031611260026693344,
+      "logits/rejected": -1.3882781267166138,
+      "logps/chosen": -694.6297607421875,
+      "logps/rejected": -1017.4817504882812,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.6253662109375,
+      "rewards/margins": 39.39641189575195,
+      "rewards/rejected": -19.77104377746582,
+      "step": 185
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 6.707449873299964e-11,
+      "learning_rate": 3.667997536333424e-05,
+      "logits/chosen": 0.24062354862689972,
+      "logits/rejected": NaN,
+      "logps/chosen": -938.1993408203125,
+      "logps/rejected": -1000.3816528320312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.56690216064453,
+      "rewards/margins": 38.47909927368164,
+      "rewards/rejected": -18.912195205688477,
+      "step": 190
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 8.01747113143847e-09,
+      "learning_rate": 3.5942763169446295e-05,
+      "logits/chosen": 0.24746160209178925,
+      "logits/rejected": -1.2341853380203247,
+      "logps/chosen": -773.4998779296875,
+      "logps/rejected": -1065.763916015625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 16.8951416015625,
+      "rewards/margins": 37.755271911621094,
+      "rewards/rejected": -20.86013412475586,
+      "step": 195
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.772403471355659e-11,
+      "learning_rate": 3.519358522469259e-05,
+      "logits/chosen": -0.09942921251058578,
+      "logits/rejected": NaN,
+      "logps/chosen": -756.4301147460938,
+      "logps/rejected": -936.4187622070312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 20.048839569091797,
+      "rewards/margins": 39.792686462402344,
+      "rewards/rejected": -19.743852615356445,
+      "step": 200
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.032920859955766e-09,
+      "learning_rate": 3.4433260744156396e-05,
+      "logits/chosen": 0.1056319922208786,
+      "logits/rejected": -1.3145227432250977,
+      "logps/chosen": -784.6891479492188,
+      "logps/rejected": -1036.238525390625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 19.342937469482422,
+      "rewards/margins": 40.68000030517578,
+      "rewards/rejected": -21.337064743041992,
+      "step": 205
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.7231743526812124e-09,
+      "learning_rate": 3.3662621131494204e-05,
+      "logits/chosen": 0.12614893913269043,
+      "logits/rejected": -1.2963688373565674,
+      "logps/chosen": -781.6393432617188,
+      "logps/rejected": -1004.7862548828125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.965452194213867,
+      "rewards/margins": 37.53193664550781,
+      "rewards/rejected": -19.566486358642578,
+      "step": 210
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.9980299492970985e-11,
+      "learning_rate": 3.2882509069808044e-05,
+      "logits/chosen": 0.17609557509422302,
+      "logits/rejected": -1.2237725257873535,
+      "logps/chosen": -860.0303955078125,
+      "logps/rejected": -1028.668701171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 20.395902633666992,
+      "rewards/margins": 41.38351058959961,
+      "rewards/rejected": -20.987613677978516,
+      "step": 215
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.3077050613908336e-15,
+      "learning_rate": 3.2093777600183875e-05,
+      "logits/chosen": 0.19297495484352112,
+      "logits/rejected": -1.239027738571167,
+      "logps/chosen": -742.4468994140625,
+      "logps/rejected": -979.86572265625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.114458084106445,
+      "rewards/margins": 37.93598556518555,
+      "rewards/rejected": -19.821529388427734,
+      "step": 220
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 7.659513578950339e-10,
+      "learning_rate": 3.129728918890371e-05,
+      "logits/chosen": 0.04276902601122856,
+      "logits/rejected": -1.2328051328659058,
+      "logps/chosen": -925.1580200195312,
+      "logps/rejected": -1018.6541748046875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.087682723999023,
+      "rewards/margins": 37.770076751708984,
+      "rewards/rejected": -19.68239402770996,
+      "step": 225
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3605957249751555e-08,
+      "learning_rate": 3.0493914784351328e-05,
+      "logits/chosen": 0.1790432333946228,
+      "logits/rejected": -1.4544163942337036,
+      "logps/chosen": -825.8486328125,
+      "logps/rejected": -938.1361083984375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.809961318969727,
+      "rewards/margins": 38.43498611450195,
+      "rewards/rejected": -19.62502670288086,
+      "step": 230
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.6664260249488194e-11,
+      "learning_rate": 2.9684532864643122e-05,
+      "logits/chosen": 0.2744317650794983,
+      "logits/rejected": NaN,
+      "logps/chosen": -817.6921997070312,
+      "logps/rejected": -1043.99462890625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 16.49943733215332,
+      "rewards/margins": 37.538238525390625,
+      "rewards/rejected": -21.038799285888672,
+      "step": 235
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0462511662156365e-13,
+      "learning_rate": 2.8870028477025042e-05,
+      "logits/chosen": 0.19406965374946594,
+      "logits/rejected": NaN,
+      "logps/chosen": -763.9988403320312,
+      "logps/rejected": -1111.3155517578125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 17.56269073486328,
+      "rewards/margins": 39.26129913330078,
+      "rewards/rejected": -21.698612213134766,
+      "step": 240
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.816194281280332e-07,
+      "learning_rate": 2.8051292270086503e-05,
+      "logits/chosen": 0.19585652649402618,
+      "logits/rejected": -1.20717453956604,
+      "logps/chosen": -778.9284057617188,
+      "logps/rejected": -1086.0411376953125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.085580825805664,
+      "rewards/margins": 37.675872802734375,
+      "rewards/rejected": -19.590295791625977,
+      "step": 245
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.960840691206389e-11,
+      "learning_rate": 2.722921951984927e-05,
+      "logits/chosen": 0.255943238735199,
+      "logits/rejected": NaN,
+      "logps/chosen": -806.9491577148438,
+      "logps/rejected": -977.7510986328125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 18.35710906982422,
+      "rewards/margins": 37.92182540893555,
+      "rewards/rejected": -19.56471824645996,
+      "step": 250
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "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:bb8b306741be853f5f48efdf849cfbf6233d3aa2a3f4e839e61080b373b518f8
+size 6737