metadata
base_model: meta-llama/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: dpo-llama3-8b-sample-rules
results: []
dpo-llama3-8b-sample-rules
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1877
- Rewards/chosen: 0.0468
- Rewards/rejected: -1.6718
- Rewards/accuracies: 1.0
- Rewards/margins: 1.7186
- Logps/rejected: -533.8027
- Logps/chosen: -205.1740
- Logits/rejected: -1.4124
- Logits/chosen: -1.2468
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: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_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
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4235 | 0.4444 | 50 | 0.3831 | 0.1873 | -0.5971 | 1.0 | 0.7844 | -426.3294 | -191.1236 | -1.4109 | -1.2728 |
| 0.1946 | 0.8889 | 100 | 0.1877 | 0.0468 | -1.6718 | 1.0 | 1.7186 | -533.8027 | -205.1740 | -1.4124 | -1.2468 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1