metadata
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: norallm/normistral-7b-warm
datasets:
- hugodk-sch/aftonposten_title_prefs
model-index:
- name: ap-normistral-7b-align-scan
results: []
ap-normistral-7b-align-scan
This model is a fine-tuned version of data/ap-normistral-7b-sft-qlora on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set:
- Loss: 0.4850
- Rewards/chosen: 0.1654
- Rewards/rejected: 0.0857
- Rewards/accuracies: 0.5399
- Rewards/margins: 0.0797
- Logps/rejected: -35.8594
- Logps/chosen: -32.2364
- Logits/rejected: 98.4059
- Logits/chosen: 98.4070
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4705 | 0.26 | 100 | 0.4947 | 0.1342 | 0.1226 | 0.4896 | 0.0116 | -35.8133 | -32.2754 | 98.6750 | 98.6871 |
| 0.3097 | 0.52 | 200 | 0.4910 | 0.1604 | 0.1008 | 0.5482 | 0.0596 | -35.8405 | -32.2427 | 98.4702 | 98.4771 |
| 0.3066 | 0.78 | 300 | 0.4855 | 0.1659 | 0.0986 | 0.5282 | 0.0673 | -35.8433 | -32.2358 | 98.4267 | 98.4293 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1