metadata
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: norallm/normistral-7b-warm
model-index:
- name: ap-normistral-7b-align-scan
results: []
ap-normistral-7b-align-scan
This model is a fine-tuned version of norallm/normistral-7b-warm on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.6485
- Rewards/chosen: 0.0015
- Rewards/rejected: -0.0116
- Rewards/accuracies: 0.5390
- Rewards/margins: 0.0131
- Logps/rejected: -36.0246
- Logps/chosen: -32.4356
- Logits/rejected: 98.9867
- Logits/chosen: 99.0023
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 6.7218 | 0.26 | 100 | 7.5705 | -0.0028 | -0.0151 | 0.5083 | 0.0123 | -36.0421 | -32.4573 | 98.6549 | 98.6709 |
| 6.2997 | 0.52 | 200 | 7.1457 | -0.0201 | -0.0563 | 0.5403 | 0.0361 | -36.2478 | -32.5438 | 98.9065 | 98.9208 |
| 6.0651 | 0.78 | 300 | 7.6485 | 0.0015 | -0.0116 | 0.5390 | 0.0131 | -36.0246 | -32.4356 | 98.9867 | 99.0023 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1