metadata
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: NorLLM-AI/NorMistral-7B
datasets:
- hugodk-sch/aftonposten_title_prefs
model-index:
- name: norllm-ai-normistral-7b-align-scan
results: []
norllm-ai-normistral-7b-align-scan
This model is a fine-tuned version of data/norllm-ai-normistral-7b-sft-qlora on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set:
- Loss: 0.9567
- Rewards/chosen: -0.0809
- Rewards/rejected: -0.1243
- Rewards/accuracies: 0.6213
- Rewards/margins: 0.0434
- Logps/rejected: -35.9413
- Logps/chosen: -32.0916
- Logits/rejected: -2.8370
- Logits/chosen: -2.8394
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.9581 | 0.26 | 100 | 0.9819 | 0.0013 | -0.0170 | 0.5955 | 0.0182 | -34.8678 | -31.2699 | -2.8027 | -2.8053 |
| 0.8824 | 0.52 | 200 | 0.9602 | -0.0546 | -0.0945 | 0.6092 | 0.0399 | -35.6429 | -31.8280 | -2.8288 | -2.8315 |
| 0.8245 | 0.78 | 300 | 0.9559 | -0.0753 | -0.1195 | 0.6005 | 0.0441 | -35.8927 | -32.0356 | -2.8365 | -2.8392 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1