Upload folder using huggingface_hub

dpo-training/README.md

@@ -0,0 +1,70 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: transformers
+model_name: output_v3
+tags:
+- generated_from_trainer
+- trl
+- unsloth
+- dpo
+licence: license
+---
+
+# Model Card for output_v3
+
+This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mohammed164ayman-vrtualize/huggingface/runs/q95rw9dh) 
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.21.0
+- Transformers: 4.55.2
+- Pytorch: 2.8.0+cu126
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

dpo-training/checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.17.0

dpo-training/checkpoint-500/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo-training/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c16eb388e1b21a7c1899e7a86fb4c98abe5560d4d8703ba3dd1294164cb1a7
+size 872476000

dpo-training/checkpoint-500/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

dpo-training/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4e43f92431bcd8804833b5b62b1a9ed080ee1e43ef76598568dd5add03c848
+size 1745216102

dpo-training/checkpoint-500/reference/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo-training/checkpoint-500/reference/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efaaf996bb35adda1d46fb82561a955d2480a46caa0bf95bd5582ce2fd24214c
+size 604040264

dpo-training/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

dpo-training/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06b74f2bed676cd448ce55fafa3eb80c6e8bf4ec9faa8e1bba55139dc9154dd
+size 1465

dpo-training/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

dpo-training/checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

dpo-training/checkpoint-500/trainer_state.json

@@ -0,0 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4630541871921183,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 203.1785888671875,
+      "learning_rate": 9.852216748768472e-07,
+      "logits/chosen": -2.98828125,
+      "logits/rejected": -2.985156297683716,
+      "logps/chosen": -690.875,
+      "logps/rejected": -472.0,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.11501464992761612,
+      "rewards/margins": 0.1190643310546875,
+      "rewards/rejected": -0.004062652587890625,
+      "step": 10
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 183.48594665527344,
+      "learning_rate": 9.688013136288999e-07,
+      "logits/chosen": -2.9632811546325684,
+      "logits/rejected": -2.9994139671325684,
+      "logps/chosen": -623.5499877929688,
+      "logps/rejected": -358.7749938964844,
+      "loss": 0.5256,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.569934070110321,
+      "rewards/margins": 0.41779786348342896,
+      "rewards/rejected": 0.15219727158546448,
+      "step": 20
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 177.51573181152344,
+      "learning_rate": 9.523809523809522e-07,
+      "logits/chosen": -2.962109327316284,
+      "logits/rejected": -2.997851610183716,
+      "logps/chosen": -673.3250122070312,
+      "logps/rejected": -418.51251220703125,
+      "loss": 0.3765,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.367431640625,
+      "rewards/margins": 0.95556640625,
+      "rewards/rejected": 0.411865234375,
+      "step": 30
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 116.17716217041016,
+      "learning_rate": 9.359605911330048e-07,
+      "logits/chosen": -2.9925780296325684,
+      "logits/rejected": -2.9916014671325684,
+      "logps/chosen": -607.4500122070312,
+      "logps/rejected": -430.25,
+      "loss": 0.2823,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7712891101837158,
+      "rewards/margins": 1.2548828125,
+      "rewards/rejected": 0.5162353515625,
+      "step": 40
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 77.2922134399414,
+      "learning_rate": 9.195402298850574e-07,
+      "logits/chosen": -2.985546827316284,
+      "logits/rejected": -3.000781297683716,
+      "logps/chosen": -630.8499755859375,
+      "logps/rejected": -426.5249938964844,
+      "loss": 0.2678,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.05859375,
+      "rewards/margins": 1.4564940929412842,
+      "rewards/rejected": 0.6025635004043579,
+      "step": 50
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 58.28313064575195,
+      "learning_rate": 9.0311986863711e-07,
+      "logits/chosen": -2.9937500953674316,
+      "logits/rejected": -3.0072264671325684,
+      "logps/chosen": -628.125,
+      "logps/rejected": -483.5249938964844,
+      "loss": 0.2115,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.308789014816284,
+      "rewards/margins": 1.748046875,
+      "rewards/rejected": 0.56072998046875,
+      "step": 60
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 103.42900085449219,
+      "learning_rate": 8.866995073891625e-07,
+      "logits/chosen": -2.976367235183716,
+      "logits/rejected": -2.9605469703674316,
+      "logps/chosen": -559.3499755859375,
+      "logps/rejected": -378.125,
+      "loss": 0.1628,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.4417967796325684,
+      "rewards/margins": 2.049023389816284,
+      "rewards/rejected": 0.39243775606155396,
+      "step": 70
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 101.71812438964844,
+      "learning_rate": 8.702791461412151e-07,
+      "logits/chosen": -2.9664063453674316,
+      "logits/rejected": -3.003710985183716,
+      "logps/chosen": -625.6500244140625,
+      "logps/rejected": -388.6499938964844,
+      "loss": 0.143,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.1548829078674316,
+      "rewards/margins": 2.657421827316284,
+      "rewards/rejected": 0.49718016386032104,
+      "step": 80
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 28.862045288085938,
+      "learning_rate": 8.538587848932676e-07,
+      "logits/chosen": -2.985156297683716,
+      "logits/rejected": -2.994140625,
+      "logps/chosen": -611.2999877929688,
+      "logps/rejected": -465.0,
+      "loss": 0.1131,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.06591796875,
+      "rewards/margins": 2.7118163108825684,
+      "rewards/rejected": 0.3544158935546875,
+      "step": 90
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 20.341941833496094,
+      "learning_rate": 8.374384236453202e-07,
+      "logits/chosen": -2.994335889816284,
+      "logits/rejected": -2.9779295921325684,
+      "logps/chosen": -465.8374938964844,
+      "logps/rejected": -401.6875,
+      "loss": 0.1633,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.720996141433716,
+      "rewards/margins": 2.49609375,
+      "rewards/rejected": 0.22498169541358948,
+      "step": 100
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 4.284467697143555,
+      "learning_rate": 8.210180623973727e-07,
+      "logits/chosen": -2.952343702316284,
+      "logits/rejected": -2.974414110183716,
+      "logps/chosen": -587.5999755859375,
+      "logps/rejected": -450.95001220703125,
+      "loss": 0.0498,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.9847655296325684,
+      "rewards/margins": 3.97265625,
+      "rewards/rejected": 0.01254882849752903,
+      "step": 110
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 12.270442962646484,
+      "learning_rate": 8.045977011494253e-07,
+      "logits/chosen": -2.975390672683716,
+      "logits/rejected": -2.988085985183716,
+      "logps/chosen": -662.7750244140625,
+      "logps/rejected": -446.6499938964844,
+      "loss": 0.0609,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.9697265625,
+      "rewards/margins": 4.036913871765137,
+      "rewards/rejected": -0.06724242866039276,
+      "step": 120
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 67.37637329101562,
+      "learning_rate": 7.881773399014779e-07,
+      "logits/chosen": -2.967578172683716,
+      "logits/rejected": -2.986132860183716,
+      "logps/chosen": -573.1500244140625,
+      "logps/rejected": -439.29998779296875,
+      "loss": 0.1303,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.8240723609924316,
+      "rewards/margins": 3.335742235183716,
+      "rewards/rejected": -0.511059582233429,
+      "step": 130
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 8.81290054321289,
+      "learning_rate": 7.717569786535302e-07,
+      "logits/chosen": -3.0111327171325684,
+      "logits/rejected": -2.962695360183716,
+      "logps/chosen": -530.0,
+      "logps/rejected": -394.0249938964844,
+      "loss": 0.0831,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.523144483566284,
+      "rewards/margins": 4.159960746765137,
+      "rewards/rejected": -0.6378753781318665,
+      "step": 140
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.581110417842865,
+      "learning_rate": 7.553366174055828e-07,
+      "logits/chosen": -2.9365234375,
+      "logits/rejected": -2.972851514816284,
+      "logps/chosen": -658.2999877929688,
+      "logps/rejected": -472.45001220703125,
+      "loss": 0.0689,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.7357420921325684,
+      "rewards/margins": 4.794140815734863,
+      "rewards/rejected": -1.0580871105194092,
+      "step": 150
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 4.293052673339844,
+      "learning_rate": 7.389162561576354e-07,
+      "logits/chosen": -2.955273389816284,
+      "logits/rejected": -2.958203077316284,
+      "logps/chosen": -604.75,
+      "logps/rejected": -414.45001220703125,
+      "loss": 0.1006,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.843554735183716,
+      "rewards/margins": 4.778710842132568,
+      "rewards/rejected": -0.9347168207168579,
+      "step": 160
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 24.498516082763672,
+      "learning_rate": 7.22495894909688e-07,
+      "logits/chosen": -2.912890672683716,
+      "logits/rejected": -2.9447264671325684,
+      "logps/chosen": -444.0,
+      "logps/rejected": -369.875,
+      "loss": 0.0323,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.6924805641174316,
+      "rewards/margins": 4.558398246765137,
+      "rewards/rejected": -1.8652222156524658,
+      "step": 170
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.2468932420015335,
+      "learning_rate": 7.060755336617405e-07,
+      "logits/chosen": -2.987499952316284,
+      "logits/rejected": -2.9697265625,
+      "logps/chosen": -534.7874755859375,
+      "logps/rejected": -407.95001220703125,
+      "loss": 0.0441,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.237597703933716,
+      "rewards/margins": 5.033593654632568,
+      "rewards/rejected": -1.7952880859375,
+      "step": 180
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 1.9548287391662598,
+      "learning_rate": 6.896551724137931e-07,
+      "logits/chosen": -2.916796922683716,
+      "logits/rejected": -2.970898389816284,
+      "logps/chosen": -485.07501220703125,
+      "logps/rejected": -406.3999938964844,
+      "loss": 0.0642,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.289843797683716,
+      "rewards/margins": 5.383984565734863,
+      "rewards/rejected": -2.09442138671875,
+      "step": 190
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 59.31279373168945,
+      "learning_rate": 6.732348111658456e-07,
+      "logits/chosen": -2.9380860328674316,
+      "logits/rejected": -2.986328125,
+      "logps/chosen": -613.0499877929688,
+      "logps/rejected": -481.875,
+      "loss": 0.0267,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.551562547683716,
+      "rewards/margins": 5.289258003234863,
+      "rewards/rejected": -1.737390160560608,
+      "step": 200
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 32.091800689697266,
+      "learning_rate": 6.568144499178982e-07,
+      "logits/chosen": -2.9224610328674316,
+      "logits/rejected": -2.927539110183716,
+      "logps/chosen": -489.625,
+      "logps/rejected": -415.125,
+      "loss": 0.0108,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.927929639816284,
+      "rewards/margins": 6.529296875,
+      "rewards/rejected": -2.6015625,
+      "step": 210
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.8448113203048706,
+      "learning_rate": 6.403940886699507e-07,
+      "logits/chosen": -2.9287109375,
+      "logits/rejected": -2.9339842796325684,
+      "logps/chosen": -632.0250244140625,
+      "logps/rejected": -485.5,
+      "loss": 0.0078,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.085351467132568,
+      "rewards/margins": 7.605078220367432,
+      "rewards/rejected": -2.5193848609924316,
+      "step": 220
+    },
+    {
+      "epoch": 1.1330049261083743,
+      "grad_norm": 0.14300227165222168,
+      "learning_rate": 6.239737274220033e-07,
+      "logits/chosen": -2.9417967796325684,
+      "logits/rejected": -2.9359374046325684,
+      "logps/chosen": -614.9749755859375,
+      "logps/rejected": -458.8500061035156,
+      "loss": 0.0014,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.646582126617432,
+      "rewards/margins": 7.631640434265137,
+      "rewards/rejected": -2.9849610328674316,
+      "step": 230
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.5171189904212952,
+      "learning_rate": 6.075533661740558e-07,
+      "logits/chosen": -2.9417967796325684,
+      "logits/rejected": -2.9496092796325684,
+      "logps/chosen": -513.7999877929688,
+      "logps/rejected": -413.51251220703125,
+      "loss": 0.003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.515625,
+      "rewards/margins": 7.489843845367432,
+      "rewards/rejected": -2.9735350608825684,
+      "step": 240
+    },
+    {
+      "epoch": 1.2315270935960592,
+      "grad_norm": 3.326808214187622,
+      "learning_rate": 5.911330049261084e-07,
+      "logits/chosen": -2.9404296875,
+      "logits/rejected": -2.9400391578674316,
+      "logps/chosen": -574.5750122070312,
+      "logps/rejected": -494.2749938964844,
+      "loss": 0.0062,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.180273532867432,
+      "rewards/margins": 7.197656154632568,
+      "rewards/rejected": -3.016406297683716,
+      "step": 250
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 30.087703704833984,
+      "learning_rate": 5.747126436781608e-07,
+      "logits/chosen": -2.9283204078674316,
+      "logits/rejected": -2.9000000953674316,
+      "logps/chosen": -520.1749877929688,
+      "logps/rejected": -373.1000061035156,
+      "loss": 0.0887,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 4.016308784484863,
+      "rewards/margins": 7.095117092132568,
+      "rewards/rejected": -3.0791993141174316,
+      "step": 260
+    },
+    {
+      "epoch": 1.3300492610837438,
+      "grad_norm": 0.6066940426826477,
+      "learning_rate": 5.582922824302134e-07,
+      "logits/chosen": -2.915820360183716,
+      "logits/rejected": -2.9224610328674316,
+      "logps/chosen": -600.5250244140625,
+      "logps/rejected": -442.45001220703125,
+      "loss": 0.0085,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.91845703125,
+      "rewards/margins": 7.68359375,
+      "rewards/rejected": -2.7652344703674316,
+      "step": 270
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.05844691023230553,
+      "learning_rate": 5.41871921182266e-07,
+      "logits/chosen": -2.8941407203674316,
+      "logits/rejected": -2.9164061546325684,
+      "logps/chosen": -664.7000122070312,
+      "logps/rejected": -476.04998779296875,
+      "loss": 0.0087,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.80078125,
+      "rewards/margins": 6.916796684265137,
+      "rewards/rejected": -2.115429639816284,
+      "step": 280
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 29.84724235534668,
+      "learning_rate": 5.254515599343186e-07,
+      "logits/chosen": -2.8882813453674316,
+      "logits/rejected": -2.8968749046325684,
+      "logps/chosen": -525.5999755859375,
+      "logps/rejected": -392.95001220703125,
+      "loss": 0.024,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.382080078125,
+      "rewards/margins": 7.035742282867432,
+      "rewards/rejected": -2.6546630859375,
+      "step": 290
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 1.2890305519104004,
+      "learning_rate": 5.090311986863711e-07,
+      "logits/chosen": -2.9185547828674316,
+      "logits/rejected": -2.9320311546325684,
+      "logps/chosen": -584.3250122070312,
+      "logps/rejected": -475.3999938964844,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.585351467132568,
+      "rewards/margins": 7.463281154632568,
+      "rewards/rejected": -2.878124952316284,
+      "step": 300
+    },
+    {
+      "epoch": 1.5270935960591134,
+      "grad_norm": 0.15950246155261993,
+      "learning_rate": 4.926108374384236e-07,
+      "logits/chosen": -2.887500047683716,
+      "logits/rejected": -2.9169921875,
+      "logps/chosen": -533.3250122070312,
+      "logps/rejected": -446.0249938964844,
+      "loss": 0.0034,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.676367282867432,
+      "rewards/margins": 7.962109565734863,
+      "rewards/rejected": -3.284960985183716,
+      "step": 310
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 10.223557472229004,
+      "learning_rate": 4.761904761904761e-07,
+      "logits/chosen": -2.9205079078674316,
+      "logits/rejected": -2.9291014671325684,
+      "logps/chosen": -584.9375,
+      "logps/rejected": -426.32501220703125,
+      "loss": 0.004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.026074409484863,
+      "rewards/margins": 7.832421779632568,
+      "rewards/rejected": -2.806640625,
+      "step": 320
+    },
+    {
+      "epoch": 1.625615763546798,
+      "grad_norm": 0.08788923174142838,
+      "learning_rate": 4.597701149425287e-07,
+      "logits/chosen": -2.908007860183716,
+      "logits/rejected": -2.918164014816284,
+      "logps/chosen": -652.9874877929688,
+      "logps/rejected": -506.75,
+      "loss": 0.0199,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.5665283203125,
+      "rewards/margins": 8.3828125,
+      "rewards/rejected": -2.816699266433716,
+      "step": 330
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.5178083181381226,
+      "learning_rate": 4.4334975369458127e-07,
+      "logits/chosen": -2.916015625,
+      "logits/rejected": -2.9380860328674316,
+      "logps/chosen": -552.1500244140625,
+      "logps/rejected": -440.32501220703125,
+      "loss": 0.0023,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.864062309265137,
+      "rewards/margins": 8.216015815734863,
+      "rewards/rejected": -3.3515625,
+      "step": 340
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.028590844944119453,
+      "learning_rate": 4.269293924466338e-07,
+      "logits/chosen": -2.9164061546325684,
+      "logits/rejected": -2.9242186546325684,
+      "logps/chosen": -634.1749877929688,
+      "logps/rejected": -474.2250061035156,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.277929782867432,
+      "rewards/margins": 8.540624618530273,
+      "rewards/rejected": -3.262988328933716,
+      "step": 350
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 43.381683349609375,
+      "learning_rate": 4.1050903119868637e-07,
+      "logits/chosen": -2.9091796875,
+      "logits/rejected": -2.888671875,
+      "logps/chosen": -520.0999755859375,
+      "logps/rejected": -430.54998779296875,
+      "loss": 0.0155,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.227148532867432,
+      "rewards/margins": 7.447656154632568,
+      "rewards/rejected": -3.2217774391174316,
+      "step": 360
+    },
+    {
+      "epoch": 1.8226600985221675,
+      "grad_norm": 15.941888809204102,
+      "learning_rate": 3.9408866995073894e-07,
+      "logits/chosen": -2.902148485183716,
+      "logits/rejected": -2.928515672683716,
+      "logps/chosen": -604.2249755859375,
+      "logps/rejected": -547.5,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.381640434265137,
+      "rewards/margins": 8.069140434265137,
+      "rewards/rejected": -3.687939405441284,
+      "step": 370
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 4.674588680267334,
+      "learning_rate": 3.776683087027914e-07,
+      "logits/chosen": -2.9037108421325684,
+      "logits/rejected": -2.879687547683716,
+      "logps/chosen": -474.6000061035156,
+      "logps/rejected": -391.76251220703125,
+      "loss": 0.0022,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.585546970367432,
+      "rewards/margins": 8.424219131469727,
+      "rewards/rejected": -3.837695360183716,
+      "step": 380
+    },
+    {
+      "epoch": 1.9211822660098523,
+      "grad_norm": 0.05743112042546272,
+      "learning_rate": 3.61247947454844e-07,
+      "logits/chosen": -2.8984375,
+      "logits/rejected": -2.889843702316284,
+      "logps/chosen": -501.17498779296875,
+      "logps/rejected": -456.5375061035156,
+      "loss": 0.0013,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.5552735328674316,
+      "rewards/margins": 8.082422256469727,
+      "rewards/rejected": -4.527148246765137,
+      "step": 390
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 1.0344998836517334,
+      "learning_rate": 3.4482758620689656e-07,
+      "logits/chosen": -2.870312452316284,
+      "logits/rejected": -2.902539014816284,
+      "logps/chosen": -677.1500244140625,
+      "logps/rejected": -541.2750244140625,
+      "loss": 0.0014,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.013574123382568,
+      "rewards/margins": 8.578516006469727,
+      "rewards/rejected": -3.563671827316284,
+      "step": 400
+    },
+    {
+      "epoch": 2.019704433497537,
+      "grad_norm": 0.010985920205712318,
+      "learning_rate": 3.284072249589491e-07,
+      "logits/chosen": -2.8814454078674316,
+      "logits/rejected": -2.8861327171325684,
+      "logps/chosen": -626.9000244140625,
+      "logps/rejected": -477.8500061035156,
+      "loss": 0.0018,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.729150295257568,
+      "rewards/margins": 8.932812690734863,
+      "rewards/rejected": -4.202734470367432,
+      "step": 410
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.1741197407245636,
+      "learning_rate": 3.1198686371100166e-07,
+      "logits/chosen": -2.901562452316284,
+      "logits/rejected": -2.862499952316284,
+      "logps/chosen": -532.375,
+      "logps/rejected": -427.9375,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.255273342132568,
+      "rewards/margins": 8.537500381469727,
+      "rewards/rejected": -4.283593654632568,
+      "step": 420
+    },
+    {
+      "epoch": 2.1182266009852215,
+      "grad_norm": 0.1754264533519745,
+      "learning_rate": 2.955665024630542e-07,
+      "logits/chosen": -2.9078125953674316,
+      "logits/rejected": -2.862499952316284,
+      "logps/chosen": -651.0250244140625,
+      "logps/rejected": -490.2749938964844,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.1142578125,
+      "rewards/margins": 8.8984375,
+      "rewards/rejected": -3.78515625,
+      "step": 430
+    },
+    {
+      "epoch": 2.167487684729064,
+      "grad_norm": 0.08032465726137161,
+      "learning_rate": 2.791461412151067e-07,
+      "logits/chosen": -2.803906202316284,
+      "logits/rejected": -2.845703125,
+      "logps/chosen": -545.1749877929688,
+      "logps/rejected": -481.25,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.478662014007568,
+      "rewards/margins": 9.135937690734863,
+      "rewards/rejected": -4.656054496765137,
+      "step": 440
+    },
+    {
+      "epoch": 2.2167487684729066,
+      "grad_norm": 2.0722830295562744,
+      "learning_rate": 2.627257799671593e-07,
+      "logits/chosen": -2.904296875,
+      "logits/rejected": -2.914257764816284,
+      "logps/chosen": -572.5999755859375,
+      "logps/rejected": -413.7250061035156,
+      "loss": 0.004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.226953029632568,
+      "rewards/margins": 8.386327743530273,
+      "rewards/rejected": -4.160058498382568,
+      "step": 450
+    },
+    {
+      "epoch": 2.2660098522167487,
+      "grad_norm": 4.566242694854736,
+      "learning_rate": 2.463054187192118e-07,
+      "logits/chosen": -2.8623046875,
+      "logits/rejected": -2.8636717796325684,
+      "logps/chosen": -614.2249755859375,
+      "logps/rejected": -475.67498779296875,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.31640625,
+      "rewards/margins": 9.180859565734863,
+      "rewards/rejected": -3.8641600608825684,
+      "step": 460
+    },
+    {
+      "epoch": 2.315270935960591,
+      "grad_norm": 0.5854314565658569,
+      "learning_rate": 2.2988505747126435e-07,
+      "logits/chosen": -2.878124952316284,
+      "logits/rejected": -2.874804735183716,
+      "logps/chosen": -593.5999755859375,
+      "logps/rejected": -473.2250061035156,
+      "loss": 0.0012,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.661718845367432,
+      "rewards/margins": 9.364453315734863,
+      "rewards/rejected": -3.7030272483825684,
+      "step": 470
+    },
+    {
+      "epoch": 2.3645320197044333,
+      "grad_norm": 0.001913163810968399,
+      "learning_rate": 2.134646962233169e-07,
+      "logits/chosen": -2.888867139816284,
+      "logits/rejected": -2.907421827316284,
+      "logps/chosen": -611.1500244140625,
+      "logps/rejected": -485.3500061035156,
+      "loss": 0.0017,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.228613376617432,
+      "rewards/margins": 8.978515625,
+      "rewards/rejected": -3.7503905296325684,
+      "step": 480
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.8092690110206604,
+      "learning_rate": 1.9704433497536947e-07,
+      "logits/chosen": -2.863085985183716,
+      "logits/rejected": -2.887890577316284,
+      "logps/chosen": -421.54998779296875,
+      "logps/rejected": -368.42498779296875,
+      "loss": 0.0076,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.868457078933716,
+      "rewards/margins": 8.104687690734863,
+      "rewards/rejected": -4.236718654632568,
+      "step": 490
+    },
+    {
+      "epoch": 2.4630541871921183,
+      "grad_norm": 31.578500747680664,
+      "learning_rate": 1.80623973727422e-07,
+      "logits/chosen": -2.8681640625,
+      "logits/rejected": -2.8470702171325684,
+      "logps/chosen": -434.07501220703125,
+      "logps/rejected": -409.2749938964844,
+      "loss": 0.0114,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.9619140625,
+      "rewards/margins": 7.552343845367432,
+      "rewards/rejected": -4.591406345367432,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 609,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

dpo-training/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d8ccd263f4895ca2bf34af708a7343c52ae03679473ca28aa1232d5d17a7bd
+size 6737

dpo-training/checkpoint-609/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.17.0

dpo-training/checkpoint-609/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo-training/checkpoint-609/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00059792c1bec532af18992354af15edcc79a0ffa1fd69c18eacad091ec82682
+size 872476000

dpo-training/checkpoint-609/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

dpo-training/checkpoint-609/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db34051a522e32f6d69b144e055a861c4a498e088238fe031e60511cd2aa1925
+size 1745216102

dpo-training/checkpoint-609/reference/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo-training/checkpoint-609/reference/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efaaf996bb35adda1d46fb82561a955d2480a46caa0bf95bd5582ce2fd24214c
+size 604040264

dpo-training/checkpoint-609/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

dpo-training/checkpoint-609/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85180873e554797c40a91f5d03b53633deb4d0b3576699d3ec1a2519aa9ff6a
+size 1465

dpo-training/checkpoint-609/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

dpo-training/checkpoint-609/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

dpo-training/checkpoint-609/trainer_state.json

@@ -0,0 +1,934 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 609,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 203.1785888671875,
+      "learning_rate": 9.852216748768472e-07,
+      "logits/chosen": -2.98828125,
+      "logits/rejected": -2.985156297683716,
+      "logps/chosen": -690.875,
+      "logps/rejected": -472.0,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.11501464992761612,
+      "rewards/margins": 0.1190643310546875,
+      "rewards/rejected": -0.004062652587890625,
+      "step": 10
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 183.48594665527344,
+      "learning_rate": 9.688013136288999e-07,
+      "logits/chosen": -2.9632811546325684,
+      "logits/rejected": -2.9994139671325684,
+      "logps/chosen": -623.5499877929688,
+      "logps/rejected": -358.7749938964844,
+      "loss": 0.5256,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.569934070110321,
+      "rewards/margins": 0.41779786348342896,
+      "rewards/rejected": 0.15219727158546448,
+      "step": 20
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 177.51573181152344,
+      "learning_rate": 9.523809523809522e-07,
+      "logits/chosen": -2.962109327316284,
+      "logits/rejected": -2.997851610183716,
+      "logps/chosen": -673.3250122070312,
+      "logps/rejected": -418.51251220703125,
+      "loss": 0.3765,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.367431640625,
+      "rewards/margins": 0.95556640625,
+      "rewards/rejected": 0.411865234375,
+      "step": 30
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 116.17716217041016,
+      "learning_rate": 9.359605911330048e-07,
+      "logits/chosen": -2.9925780296325684,
+      "logits/rejected": -2.9916014671325684,
+      "logps/chosen": -607.4500122070312,
+      "logps/rejected": -430.25,
+      "loss": 0.2823,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7712891101837158,
+      "rewards/margins": 1.2548828125,
+      "rewards/rejected": 0.5162353515625,
+      "step": 40
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 77.2922134399414,
+      "learning_rate": 9.195402298850574e-07,
+      "logits/chosen": -2.985546827316284,
+      "logits/rejected": -3.000781297683716,
+      "logps/chosen": -630.8499755859375,
+      "logps/rejected": -426.5249938964844,
+      "loss": 0.2678,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.05859375,
+      "rewards/margins": 1.4564940929412842,
+      "rewards/rejected": 0.6025635004043579,
+      "step": 50
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 58.28313064575195,
+      "learning_rate": 9.0311986863711e-07,
+      "logits/chosen": -2.9937500953674316,
+      "logits/rejected": -3.0072264671325684,
+      "logps/chosen": -628.125,
+      "logps/rejected": -483.5249938964844,
+      "loss": 0.2115,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.308789014816284,
+      "rewards/margins": 1.748046875,
+      "rewards/rejected": 0.56072998046875,
+      "step": 60
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 103.42900085449219,
+      "learning_rate": 8.866995073891625e-07,
+      "logits/chosen": -2.976367235183716,
+      "logits/rejected": -2.9605469703674316,
+      "logps/chosen": -559.3499755859375,
+      "logps/rejected": -378.125,
+      "loss": 0.1628,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.4417967796325684,
+      "rewards/margins": 2.049023389816284,
+      "rewards/rejected": 0.39243775606155396,
+      "step": 70
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 101.71812438964844,
+      "learning_rate": 8.702791461412151e-07,
+      "logits/chosen": -2.9664063453674316,
+      "logits/rejected": -3.003710985183716,
+      "logps/chosen": -625.6500244140625,
+      "logps/rejected": -388.6499938964844,
+      "loss": 0.143,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.1548829078674316,
+      "rewards/margins": 2.657421827316284,
+      "rewards/rejected": 0.49718016386032104,
+      "step": 80
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 28.862045288085938,
+      "learning_rate": 8.538587848932676e-07,
+      "logits/chosen": -2.985156297683716,
+      "logits/rejected": -2.994140625,
+      "logps/chosen": -611.2999877929688,
+      "logps/rejected": -465.0,
+      "loss": 0.1131,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.06591796875,
+      "rewards/margins": 2.7118163108825684,
+      "rewards/rejected": 0.3544158935546875,
+      "step": 90
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 20.341941833496094,
+      "learning_rate": 8.374384236453202e-07,
+      "logits/chosen": -2.994335889816284,
+      "logits/rejected": -2.9779295921325684,
+      "logps/chosen": -465.8374938964844,
+      "logps/rejected": -401.6875,
+      "loss": 0.1633,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.720996141433716,
+      "rewards/margins": 2.49609375,
+      "rewards/rejected": 0.22498169541358948,
+      "step": 100
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 4.284467697143555,
+      "learning_rate": 8.210180623973727e-07,
+      "logits/chosen": -2.952343702316284,
+      "logits/rejected": -2.974414110183716,
+      "logps/chosen": -587.5999755859375,
+      "logps/rejected": -450.95001220703125,
+      "loss": 0.0498,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.9847655296325684,
+      "rewards/margins": 3.97265625,
+      "rewards/rejected": 0.01254882849752903,
+      "step": 110
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 12.270442962646484,
+      "learning_rate": 8.045977011494253e-07,
+      "logits/chosen": -2.975390672683716,
+      "logits/rejected": -2.988085985183716,
+      "logps/chosen": -662.7750244140625,
+      "logps/rejected": -446.6499938964844,
+      "loss": 0.0609,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.9697265625,
+      "rewards/margins": 4.036913871765137,
+      "rewards/rejected": -0.06724242866039276,
+      "step": 120
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 67.37637329101562,
+      "learning_rate": 7.881773399014779e-07,
+      "logits/chosen": -2.967578172683716,
+      "logits/rejected": -2.986132860183716,
+      "logps/chosen": -573.1500244140625,
+      "logps/rejected": -439.29998779296875,
+      "loss": 0.1303,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.8240723609924316,
+      "rewards/margins": 3.335742235183716,
+      "rewards/rejected": -0.511059582233429,
+      "step": 130
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 8.81290054321289,
+      "learning_rate": 7.717569786535302e-07,
+      "logits/chosen": -3.0111327171325684,
+      "logits/rejected": -2.962695360183716,
+      "logps/chosen": -530.0,
+      "logps/rejected": -394.0249938964844,
+      "loss": 0.0831,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.523144483566284,
+      "rewards/margins": 4.159960746765137,
+      "rewards/rejected": -0.6378753781318665,
+      "step": 140
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.581110417842865,
+      "learning_rate": 7.553366174055828e-07,
+      "logits/chosen": -2.9365234375,
+      "logits/rejected": -2.972851514816284,
+      "logps/chosen": -658.2999877929688,
+      "logps/rejected": -472.45001220703125,
+      "loss": 0.0689,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.7357420921325684,
+      "rewards/margins": 4.794140815734863,
+      "rewards/rejected": -1.0580871105194092,
+      "step": 150
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 4.293052673339844,
+      "learning_rate": 7.389162561576354e-07,
+      "logits/chosen": -2.955273389816284,
+      "logits/rejected": -2.958203077316284,
+      "logps/chosen": -604.75,
+      "logps/rejected": -414.45001220703125,
+      "loss": 0.1006,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.843554735183716,
+      "rewards/margins": 4.778710842132568,
+      "rewards/rejected": -0.9347168207168579,
+      "step": 160
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 24.498516082763672,
+      "learning_rate": 7.22495894909688e-07,
+      "logits/chosen": -2.912890672683716,
+      "logits/rejected": -2.9447264671325684,
+      "logps/chosen": -444.0,
+      "logps/rejected": -369.875,
+      "loss": 0.0323,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.6924805641174316,
+      "rewards/margins": 4.558398246765137,
+      "rewards/rejected": -1.8652222156524658,
+      "step": 170
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.2468932420015335,
+      "learning_rate": 7.060755336617405e-07,
+      "logits/chosen": -2.987499952316284,
+      "logits/rejected": -2.9697265625,
+      "logps/chosen": -534.7874755859375,
+      "logps/rejected": -407.95001220703125,
+      "loss": 0.0441,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.237597703933716,
+      "rewards/margins": 5.033593654632568,
+      "rewards/rejected": -1.7952880859375,
+      "step": 180
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 1.9548287391662598,
+      "learning_rate": 6.896551724137931e-07,
+      "logits/chosen": -2.916796922683716,
+      "logits/rejected": -2.970898389816284,
+      "logps/chosen": -485.07501220703125,
+      "logps/rejected": -406.3999938964844,
+      "loss": 0.0642,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.289843797683716,
+      "rewards/margins": 5.383984565734863,
+      "rewards/rejected": -2.09442138671875,
+      "step": 190
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 59.31279373168945,
+      "learning_rate": 6.732348111658456e-07,
+      "logits/chosen": -2.9380860328674316,
+      "logits/rejected": -2.986328125,
+      "logps/chosen": -613.0499877929688,
+      "logps/rejected": -481.875,
+      "loss": 0.0267,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.551562547683716,
+      "rewards/margins": 5.289258003234863,
+      "rewards/rejected": -1.737390160560608,
+      "step": 200
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 32.091800689697266,
+      "learning_rate": 6.568144499178982e-07,
+      "logits/chosen": -2.9224610328674316,
+      "logits/rejected": -2.927539110183716,
+      "logps/chosen": -489.625,
+      "logps/rejected": -415.125,
+      "loss": 0.0108,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.927929639816284,
+      "rewards/margins": 6.529296875,
+      "rewards/rejected": -2.6015625,
+      "step": 210
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.8448113203048706,
+      "learning_rate": 6.403940886699507e-07,
+      "logits/chosen": -2.9287109375,
+      "logits/rejected": -2.9339842796325684,
+      "logps/chosen": -632.0250244140625,
+      "logps/rejected": -485.5,
+      "loss": 0.0078,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.085351467132568,
+      "rewards/margins": 7.605078220367432,
+      "rewards/rejected": -2.5193848609924316,
+      "step": 220
+    },
+    {
+      "epoch": 1.1330049261083743,
+      "grad_norm": 0.14300227165222168,
+      "learning_rate": 6.239737274220033e-07,
+      "logits/chosen": -2.9417967796325684,
+      "logits/rejected": -2.9359374046325684,
+      "logps/chosen": -614.9749755859375,
+      "logps/rejected": -458.8500061035156,
+      "loss": 0.0014,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.646582126617432,
+      "rewards/margins": 7.631640434265137,
+      "rewards/rejected": -2.9849610328674316,
+      "step": 230
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.5171189904212952,
+      "learning_rate": 6.075533661740558e-07,
+      "logits/chosen": -2.9417967796325684,
+      "logits/rejected": -2.9496092796325684,
+      "logps/chosen": -513.7999877929688,
+      "logps/rejected": -413.51251220703125,
+      "loss": 0.003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.515625,
+      "rewards/margins": 7.489843845367432,
+      "rewards/rejected": -2.9735350608825684,
+      "step": 240
+    },
+    {
+      "epoch": 1.2315270935960592,
+      "grad_norm": 3.326808214187622,
+      "learning_rate": 5.911330049261084e-07,
+      "logits/chosen": -2.9404296875,
+      "logits/rejected": -2.9400391578674316,
+      "logps/chosen": -574.5750122070312,
+      "logps/rejected": -494.2749938964844,
+      "loss": 0.0062,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.180273532867432,
+      "rewards/margins": 7.197656154632568,
+      "rewards/rejected": -3.016406297683716,
+      "step": 250
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 30.087703704833984,
+      "learning_rate": 5.747126436781608e-07,
+      "logits/chosen": -2.9283204078674316,
+      "logits/rejected": -2.9000000953674316,
+      "logps/chosen": -520.1749877929688,
+      "logps/rejected": -373.1000061035156,
+      "loss": 0.0887,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 4.016308784484863,
+      "rewards/margins": 7.095117092132568,
+      "rewards/rejected": -3.0791993141174316,
+      "step": 260
+    },
+    {
+      "epoch": 1.3300492610837438,
+      "grad_norm": 0.6066940426826477,
+      "learning_rate": 5.582922824302134e-07,
+      "logits/chosen": -2.915820360183716,
+      "logits/rejected": -2.9224610328674316,
+      "logps/chosen": -600.5250244140625,
+      "logps/rejected": -442.45001220703125,
+      "loss": 0.0085,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.91845703125,
+      "rewards/margins": 7.68359375,
+      "rewards/rejected": -2.7652344703674316,
+      "step": 270
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.05844691023230553,
+      "learning_rate": 5.41871921182266e-07,
+      "logits/chosen": -2.8941407203674316,
+      "logits/rejected": -2.9164061546325684,
+      "logps/chosen": -664.7000122070312,
+      "logps/rejected": -476.04998779296875,
+      "loss": 0.0087,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.80078125,
+      "rewards/margins": 6.916796684265137,
+      "rewards/rejected": -2.115429639816284,
+      "step": 280
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 29.84724235534668,
+      "learning_rate": 5.254515599343186e-07,
+      "logits/chosen": -2.8882813453674316,
+      "logits/rejected": -2.8968749046325684,
+      "logps/chosen": -525.5999755859375,
+      "logps/rejected": -392.95001220703125,
+      "loss": 0.024,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.382080078125,
+      "rewards/margins": 7.035742282867432,
+      "rewards/rejected": -2.6546630859375,
+      "step": 290
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 1.2890305519104004,
+      "learning_rate": 5.090311986863711e-07,
+      "logits/chosen": -2.9185547828674316,
+      "logits/rejected": -2.9320311546325684,
+      "logps/chosen": -584.3250122070312,
+      "logps/rejected": -475.3999938964844,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.585351467132568,
+      "rewards/margins": 7.463281154632568,
+      "rewards/rejected": -2.878124952316284,
+      "step": 300
+    },
+    {
+      "epoch": 1.5270935960591134,
+      "grad_norm": 0.15950246155261993,
+      "learning_rate": 4.926108374384236e-07,
+      "logits/chosen": -2.887500047683716,
+      "logits/rejected": -2.9169921875,
+      "logps/chosen": -533.3250122070312,
+      "logps/rejected": -446.0249938964844,
+      "loss": 0.0034,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.676367282867432,
+      "rewards/margins": 7.962109565734863,
+      "rewards/rejected": -3.284960985183716,
+      "step": 310
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 10.223557472229004,
+      "learning_rate": 4.761904761904761e-07,
+      "logits/chosen": -2.9205079078674316,
+      "logits/rejected": -2.9291014671325684,
+      "logps/chosen": -584.9375,
+      "logps/rejected": -426.32501220703125,
+      "loss": 0.004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.026074409484863,
+      "rewards/margins": 7.832421779632568,
+      "rewards/rejected": -2.806640625,
+      "step": 320
+    },
+    {
+      "epoch": 1.625615763546798,
+      "grad_norm": 0.08788923174142838,
+      "learning_rate": 4.597701149425287e-07,
+      "logits/chosen": -2.908007860183716,
+      "logits/rejected": -2.918164014816284,
+      "logps/chosen": -652.9874877929688,
+      "logps/rejected": -506.75,
+      "loss": 0.0199,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.5665283203125,
+      "rewards/margins": 8.3828125,
+      "rewards/rejected": -2.816699266433716,
+      "step": 330
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.5178083181381226,
+      "learning_rate": 4.4334975369458127e-07,
+      "logits/chosen": -2.916015625,
+      "logits/rejected": -2.9380860328674316,
+      "logps/chosen": -552.1500244140625,
+      "logps/rejected": -440.32501220703125,
+      "loss": 0.0023,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.864062309265137,
+      "rewards/margins": 8.216015815734863,
+      "rewards/rejected": -3.3515625,
+      "step": 340
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.028590844944119453,
+      "learning_rate": 4.269293924466338e-07,
+      "logits/chosen": -2.9164061546325684,
+      "logits/rejected": -2.9242186546325684,
+      "logps/chosen": -634.1749877929688,
+      "logps/rejected": -474.2250061035156,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.277929782867432,
+      "rewards/margins": 8.540624618530273,
+      "rewards/rejected": -3.262988328933716,
+      "step": 350
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 43.381683349609375,
+      "learning_rate": 4.1050903119868637e-07,
+      "logits/chosen": -2.9091796875,
+      "logits/rejected": -2.888671875,
+      "logps/chosen": -520.0999755859375,
+      "logps/rejected": -430.54998779296875,
+      "loss": 0.0155,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.227148532867432,
+      "rewards/margins": 7.447656154632568,
+      "rewards/rejected": -3.2217774391174316,
+      "step": 360
+    },
+    {
+      "epoch": 1.8226600985221675,
+      "grad_norm": 15.941888809204102,
+      "learning_rate": 3.9408866995073894e-07,
+      "logits/chosen": -2.902148485183716,
+      "logits/rejected": -2.928515672683716,
+      "logps/chosen": -604.2249755859375,
+      "logps/rejected": -547.5,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.381640434265137,
+      "rewards/margins": 8.069140434265137,
+      "rewards/rejected": -3.687939405441284,
+      "step": 370
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 4.674588680267334,
+      "learning_rate": 3.776683087027914e-07,
+      "logits/chosen": -2.9037108421325684,
+      "logits/rejected": -2.879687547683716,
+      "logps/chosen": -474.6000061035156,
+      "logps/rejected": -391.76251220703125,
+      "loss": 0.0022,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.585546970367432,
+      "rewards/margins": 8.424219131469727,
+      "rewards/rejected": -3.837695360183716,
+      "step": 380
+    },
+    {
+      "epoch": 1.9211822660098523,
+      "grad_norm": 0.05743112042546272,
+      "learning_rate": 3.61247947454844e-07,
+      "logits/chosen": -2.8984375,
+      "logits/rejected": -2.889843702316284,
+      "logps/chosen": -501.17498779296875,
+      "logps/rejected": -456.5375061035156,
+      "loss": 0.0013,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.5552735328674316,
+      "rewards/margins": 8.082422256469727,
+      "rewards/rejected": -4.527148246765137,
+      "step": 390
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 1.0344998836517334,
+      "learning_rate": 3.4482758620689656e-07,
+      "logits/chosen": -2.870312452316284,
+      "logits/rejected": -2.902539014816284,
+      "logps/chosen": -677.1500244140625,
+      "logps/rejected": -541.2750244140625,
+      "loss": 0.0014,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.013574123382568,
+      "rewards/margins": 8.578516006469727,
+      "rewards/rejected": -3.563671827316284,
+      "step": 400
+    },
+    {
+      "epoch": 2.019704433497537,
+      "grad_norm": 0.010985920205712318,
+      "learning_rate": 3.284072249589491e-07,
+      "logits/chosen": -2.8814454078674316,
+      "logits/rejected": -2.8861327171325684,
+      "logps/chosen": -626.9000244140625,
+      "logps/rejected": -477.8500061035156,
+      "loss": 0.0018,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.729150295257568,
+      "rewards/margins": 8.932812690734863,
+      "rewards/rejected": -4.202734470367432,
+      "step": 410
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.1741197407245636,
+      "learning_rate": 3.1198686371100166e-07,
+      "logits/chosen": -2.901562452316284,
+      "logits/rejected": -2.862499952316284,
+      "logps/chosen": -532.375,
+      "logps/rejected": -427.9375,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.255273342132568,
+      "rewards/margins": 8.537500381469727,
+      "rewards/rejected": -4.283593654632568,
+      "step": 420
+    },
+    {
+      "epoch": 2.1182266009852215,
+      "grad_norm": 0.1754264533519745,
+      "learning_rate": 2.955665024630542e-07,
+      "logits/chosen": -2.9078125953674316,
+      "logits/rejected": -2.862499952316284,
+      "logps/chosen": -651.0250244140625,
+      "logps/rejected": -490.2749938964844,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.1142578125,
+      "rewards/margins": 8.8984375,
+      "rewards/rejected": -3.78515625,
+      "step": 430
+    },
+    {
+      "epoch": 2.167487684729064,
+      "grad_norm": 0.08032465726137161,
+      "learning_rate": 2.791461412151067e-07,
+      "logits/chosen": -2.803906202316284,
+      "logits/rejected": -2.845703125,
+      "logps/chosen": -545.1749877929688,
+      "logps/rejected": -481.25,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.478662014007568,
+      "rewards/margins": 9.135937690734863,
+      "rewards/rejected": -4.656054496765137,
+      "step": 440
+    },
+    {
+      "epoch": 2.2167487684729066,
+      "grad_norm": 2.0722830295562744,
+      "learning_rate": 2.627257799671593e-07,
+      "logits/chosen": -2.904296875,
+      "logits/rejected": -2.914257764816284,
+      "logps/chosen": -572.5999755859375,
+      "logps/rejected": -413.7250061035156,
+      "loss": 0.004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.226953029632568,
+      "rewards/margins": 8.386327743530273,
+      "rewards/rejected": -4.160058498382568,
+      "step": 450
+    },
+    {
+      "epoch": 2.2660098522167487,
+      "grad_norm": 4.566242694854736,
+      "learning_rate": 2.463054187192118e-07,
+      "logits/chosen": -2.8623046875,
+      "logits/rejected": -2.8636717796325684,
+      "logps/chosen": -614.2249755859375,
+      "logps/rejected": -475.67498779296875,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.31640625,
+      "rewards/margins": 9.180859565734863,
+      "rewards/rejected": -3.8641600608825684,
+      "step": 460
+    },
+    {
+      "epoch": 2.315270935960591,
+      "grad_norm": 0.5854314565658569,
+      "learning_rate": 2.2988505747126435e-07,
+      "logits/chosen": -2.878124952316284,
+      "logits/rejected": -2.874804735183716,
+      "logps/chosen": -593.5999755859375,
+      "logps/rejected": -473.2250061035156,
+      "loss": 0.0012,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.661718845367432,
+      "rewards/margins": 9.364453315734863,
+      "rewards/rejected": -3.7030272483825684,
+      "step": 470
+    },
+    {
+      "epoch": 2.3645320197044333,
+      "grad_norm": 0.001913163810968399,
+      "learning_rate": 2.134646962233169e-07,
+      "logits/chosen": -2.888867139816284,
+      "logits/rejected": -2.907421827316284,
+      "logps/chosen": -611.1500244140625,
+      "logps/rejected": -485.3500061035156,
+      "loss": 0.0017,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.228613376617432,
+      "rewards/margins": 8.978515625,
+      "rewards/rejected": -3.7503905296325684,
+      "step": 480
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.8092690110206604,
+      "learning_rate": 1.9704433497536947e-07,
+      "logits/chosen": -2.863085985183716,
+      "logits/rejected": -2.887890577316284,
+      "logps/chosen": -421.54998779296875,
+      "logps/rejected": -368.42498779296875,
+      "loss": 0.0076,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.868457078933716,
+      "rewards/margins": 8.104687690734863,
+      "rewards/rejected": -4.236718654632568,
+      "step": 490
+    },
+    {
+      "epoch": 2.4630541871921183,
+      "grad_norm": 31.578500747680664,
+      "learning_rate": 1.80623973727422e-07,
+      "logits/chosen": -2.8681640625,
+      "logits/rejected": -2.8470702171325684,
+      "logps/chosen": -434.07501220703125,
+      "logps/rejected": -409.2749938964844,
+      "loss": 0.0114,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.9619140625,
+      "rewards/margins": 7.552343845367432,
+      "rewards/rejected": -4.591406345367432,
+      "step": 500
+    },
+    {
+      "epoch": 2.512315270935961,
+      "grad_norm": 0.12709029018878937,
+      "learning_rate": 1.6420361247947454e-07,
+      "logits/chosen": -2.8716797828674316,
+      "logits/rejected": -2.8921875953674316,
+      "logps/chosen": -566.5374755859375,
+      "logps/rejected": -468.07501220703125,
+      "loss": 0.0009,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.087988376617432,
+      "rewards/margins": 8.895312309265137,
+      "rewards/rejected": -3.8065428733825684,
+      "step": 510
+    },
+    {
+      "epoch": 2.561576354679803,
+      "grad_norm": 0.08383513987064362,
+      "learning_rate": 1.477832512315271e-07,
+      "logits/chosen": -2.8541016578674316,
+      "logits/rejected": -2.841992139816284,
+      "logps/chosen": -579.4000244140625,
+      "logps/rejected": -496.8500061035156,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.802636623382568,
+      "rewards/margins": 9.590624809265137,
+      "rewards/rejected": -4.790429592132568,
+      "step": 520
+    },
+    {
+      "epoch": 2.6108374384236455,
+      "grad_norm": 0.10007257014513016,
+      "learning_rate": 1.3136288998357964e-07,
+      "logits/chosen": -2.883984327316284,
+      "logits/rejected": -2.877148389816284,
+      "logps/chosen": -652.9500122070312,
+      "logps/rejected": -519.3250122070312,
+      "loss": 0.0202,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.237500190734863,
+      "rewards/margins": 8.44140625,
+      "rewards/rejected": -3.2041993141174316,
+      "step": 530
+    },
+    {
+      "epoch": 2.6600985221674875,
+      "grad_norm": 0.21863970160484314,
+      "learning_rate": 1.1494252873563217e-07,
+      "logits/chosen": -2.8646483421325684,
+      "logits/rejected": -2.8714842796325684,
+      "logps/chosen": -560.5625,
+      "logps/rejected": -465.92498779296875,
+      "loss": 0.0009,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.9794921875,
+      "rewards/margins": 9.121874809265137,
+      "rewards/rejected": -4.142480373382568,
+      "step": 540
+    },
+    {
+      "epoch": 2.70935960591133,
+      "grad_norm": 0.020649878308176994,
+      "learning_rate": 9.852216748768474e-08,
+      "logits/chosen": -2.8617186546325684,
+      "logits/rejected": -2.8804688453674316,
+      "logps/chosen": -668.9000244140625,
+      "logps/rejected": -507.04998779296875,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 5.8662109375,
+      "rewards/margins": 10.056249618530273,
+      "rewards/rejected": -4.189453125,
+      "step": 550
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.1907971054315567,
+      "learning_rate": 8.210180623973727e-08,
+      "logits/chosen": -2.873242139816284,
+      "logits/rejected": -2.8773436546325684,
+      "logps/chosen": -551.2999877929688,
+      "logps/rejected": -438.54998779296875,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.8486328125,
+      "rewards/margins": 8.854296684265137,
+      "rewards/rejected": -4.006054878234863,
+      "step": 560
+    },
+    {
+      "epoch": 2.8078817733990147,
+      "grad_norm": 0.001020336989313364,
+      "learning_rate": 6.568144499178982e-08,
+      "logits/chosen": -2.8656249046325684,
+      "logits/rejected": -2.8804688453674316,
+      "logps/chosen": -559.75,
+      "logps/rejected": -494.3500061035156,
+      "loss": 0.0009,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.337597846984863,
+      "rewards/margins": 9.077343940734863,
+      "rewards/rejected": -4.740038871765137,
+      "step": 570
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.16810493171215057,
+      "learning_rate": 4.926108374384237e-08,
+      "logits/chosen": -2.8501954078674316,
+      "logits/rejected": -2.8726563453674316,
+      "logps/chosen": -542.2750244140625,
+      "logps/rejected": -444.92498779296875,
+      "loss": 0.0011,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.039453029632568,
+      "rewards/margins": 8.626172065734863,
+      "rewards/rejected": -4.58740234375,
+      "step": 580
+    },
+    {
+      "epoch": 2.9064039408866993,
+      "grad_norm": 0.06971245259046555,
+      "learning_rate": 3.284072249589491e-08,
+      "logits/chosen": -2.8759765625,
+      "logits/rejected": -2.8857421875,
+      "logps/chosen": -585.5,
+      "logps/rejected": -495.32501220703125,
+      "loss": 0.0012,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.425024509429932,
+      "rewards/margins": 8.797656059265137,
+      "rewards/rejected": -4.372851371765137,
+      "step": 590
+    },
+    {
+      "epoch": 2.955665024630542,
+      "grad_norm": 0.04007822275161743,
+      "learning_rate": 1.6420361247947455e-08,
+      "logits/chosen": -2.8910155296325684,
+      "logits/rejected": -2.863085985183716,
+      "logps/chosen": -561.7999877929688,
+      "logps/rejected": -413.48748779296875,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.448876857757568,
+      "rewards/margins": 8.94921875,
+      "rewards/rejected": -4.5009765625,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 609,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

dpo-training/checkpoint-609/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d8ccd263f4895ca2bf34af708a7343c52ae03679473ca28aa1232d5d17a7bd
+size 6737

dpo-training/runs/Aug21_07-36-02_9313b65d545c/events.out.tfevents.1755761772.9313b65d545c.38351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c72ca443d1202db15bae73e939c0fb3be58792a85ccf45a14a49975a06d61f7
+size 6391

dpo-training/runs/Aug21_07-48-22_9313b65d545c/events.out.tfevents.1755762511.9313b65d545c.40851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e0cdbd77f4c2a9dba5c10a259bd8b6fedb5ce7979870a3fa547f585281e348
+size 6399

dpo-training/runs/Aug21_07-54-14_9313b65d545c/events.out.tfevents.1755762860.9313b65d545c.40851.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247eff6258d60284c5fda931eae8213e3dc51d8bd81ad63a55e448c8fe4d1873
+size 4184

dpo-training/runs/Aug21_07-58-51_9313b65d545c/events.out.tfevents.1755763176.9313b65d545c.44283.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95db520ac50327e8bedbf6730201887a295d0bc1f87930fec081791deb193ce
+size 6391

dpo-training/runs/Aug21_08-04-17_9313b65d545c/events.out.tfevents.1755763467.9313b65d545c.45997.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe9c037f54fe11057a745f629846428ca11fb90b243bb63078608e6f4d23d2f
+size 7067

dpo-training/runs/Aug21_08-11-41_9313b65d545c/events.out.tfevents.1755763912.9313b65d545c.47766.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb9eba0014fb00c8b6f8b28408802c6436f84af976c60029f48ad7bdff221e8
+size 47881