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: 0.6726
- Rewards/chosen: -0.0859
- Rewards/rejected: -0.1885
- Rewards/accuracies: 0.5627
- Rewards/margins: 0.1027
- Logps/rejected: -35.0124
- Logps/chosen: -31.4256
- Logits/rejected: -2.8174
- Logits/chosen: -2.8199
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6371 | 0.26 | 100 | 0.6738 | 0.0094 | -0.0765 | 0.6013 | 0.0860 | -34.8257 | -31.2667 | -2.8093 | -2.8120 |
| 0.5701 | 0.52 | 200 | 0.6704 | -0.0753 | -0.1790 | 0.5777 | 0.1037 | -34.9964 | -31.4080 | -2.8197 | -2.8224 |
| 0.5462 | 0.78 | 300 | 0.6756 | -0.0773 | -0.1729 | 0.5569 | 0.0956 | -34.9863 | -31.4113 | -2.8175 | -2.8199 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1