metadata
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: NbAiLab/nb-gpt-j-6B-v2
datasets:
- hugodk-sch/aftonposten_title_prefs
model-index:
- name: aftonposten-6b-align-scan
results: []
aftonposten-6b-align-scan
This model is a fine-tuned version of data/ap-gpt-j-6b-sft-qlora-04-08 on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6926
- Rewards/chosen: -0.0279
- Rewards/rejected: -0.0401
- Rewards/accuracies: 0.5212
- Rewards/margins: 0.0122
- Logps/rejected: -37.5969
- Logps/chosen: -34.0903
- Logits/rejected: -2.2228
- Logits/chosen: -2.2276
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6634 | 0.26 | 100 | 0.6931 | 0.0028 | -0.0041 | 0.5216 | 0.0069 | -37.5249 | -34.0290 | -2.2276 | -2.2324 |
| 0.6329 | 0.52 | 200 | 0.6905 | -0.0127 | -0.0275 | 0.5274 | 0.0148 | -37.5716 | -34.0600 | -2.2255 | -2.2304 |
| 0.5742 | 0.78 | 300 | 0.6920 | -0.0273 | -0.0406 | 0.5278 | 0.0133 | -37.5978 | -34.0891 | -2.2231 | -2.2279 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1