metadata
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: alignment-handbook/zephyr-7b-sft-full
model-index:
- name: nash_ave_pi_with_golden_iter_1
results: []
nash_ave_pi_with_golden_iter_1
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6285
- Rewards/chosen: -0.1151
- Rewards/rejected: -0.2881
- Rewards/accuracies: 0.6880
- Rewards/margins: 0.1730
- Logps/rejected: -286.3282
- Logps/chosen: -295.5510
- Logits/rejected: -2.5398
- Logits/chosen: -2.6242
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6297 | 0.64 | 100 | 0.6285 | -0.1151 | -0.2881 | 0.6880 | 0.1730 | -286.3282 | -295.5510 | -2.5398 | -2.6242 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2