metadata
library_name: peft
tags:
- trl
- dpo
- DPO
- WeniGPT
- generated_from_trainer
base_model: Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged
model-index:
- name: WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO
results: []
WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO
This model is a fine-tuned version of Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0520
- Rewards/chosen: 2.3217
- Rewards/rejected: -1.5051
- Rewards/accuracies: 1.0
- Rewards/margins: 3.8268
- Logps/rejected: -167.9981
- Logps/chosen: -107.6077
- Logits/rejected: -1.7717
- Logits/chosen: -1.7573
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 180
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.3976 | 0.9677 | 30 | 0.3186 | 0.8373 | -0.0381 | 1.0 | 0.8754 | -160.6632 | -115.0300 | -1.7561 | -1.7413 |
| 0.1934 | 1.9355 | 60 | 0.1752 | 1.6472 | -0.5496 | 1.0 | 2.1968 | -163.2207 | -110.9804 | -1.7603 | -1.7456 |
| 0.1058 | 2.9032 | 90 | 0.1096 | 1.9881 | -0.7856 | 1.0 | 2.7737 | -164.4007 | -109.2759 | -1.7637 | -1.7491 |
| 0.0527 | 3.8710 | 120 | 0.0787 | 2.1758 | -1.0246 | 1.0 | 3.2004 | -165.5957 | -108.3371 | -1.7676 | -1.7532 |
| 0.0526 | 4.8387 | 150 | 0.0577 | 2.2762 | -1.3610 | 1.0 | 3.6373 | -167.2778 | -107.8351 | -1.7693 | -1.7549 |
| 0.0529 | 5.8065 | 180 | 0.0520 | 2.3217 | -1.5051 | 1.0 | 3.8268 | -167.9981 | -107.6077 | -1.7717 | -1.7573 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.19.1