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: 0.6762
- Rewards/chosen: -0.0561
- Rewards/rejected: -0.0991
- Rewards/accuracies: 0.5889
- Rewards/margins: 0.0431
- Logps/rejected: -36.9578
- Logps/chosen: -33.0039
- Logits/rejected: 97.9360
- Logits/chosen: 97.9657
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6795 | 0.26 | 100 | 0.6967 | 0.0004 | 0.0027 | 0.4846 | -0.0023 | -35.9393 | -32.4388 | 98.7026 | 98.7111 |
| 0.6355 | 0.52 | 200 | 0.6793 | -0.0461 | -0.0803 | 0.5835 | 0.0342 | -36.7700 | -32.9042 | 98.1082 | 98.1292 |
| 0.6306 | 0.78 | 300 | 0.6733 | -0.0561 | -0.1040 | 0.6121 | 0.0480 | -37.0066 | -33.0038 | 97.9574 | 97.9847 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1