---
library_name: transformers
license: apache-2.0
base_model: zera09/long_t5_4
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: dpo_t5_2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# dpo_t5_2

This model is a fine-tuned version of [zera09/long_t5_4](https://huggingface.co/zera09/long_t5_4) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.3486
- eval_runtime: 189.2688
- eval_samples_per_second: 8.454
- eval_steps_per_second: 1.057
- eval_rewards/chosen: 0.4122
- eval_rewards/rejected: -0.7810
- eval_rewards/accuracies: 0.8781
- eval_rewards/margins: 1.1932
- eval_logps/rejected: -6.7047
- eval_logps/chosen: -26.4297
- eval_logits/rejected: -19.0942
- eval_logits/chosen: -18.7712
- epoch: 2.3
- step: 460

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1000

### Framework versions

- Transformers 4.45.2
- Pytorch 2.2.1
- Datasets 3.0.1
- Tokenizers 0.20.1