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: 0.7295
- Rewards/chosen: -0.1029
- Rewards/rejected: -0.1921
- Rewards/accuracies: 0.5507
- Rewards/margins: 0.0893
- Logps/rejected: -36.2867
- Logps/chosen: -32.6146
- Logits/rejected: 98.5914
- Logits/chosen: 98.6142
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6845 | 0.26 | 100 | 0.7399 | 0.0002 | -0.0442 | 0.5245 | 0.0444 | -36.0401 | -32.4428 | 98.7048 | 98.7141 |
| 0.6115 | 0.52 | 200 | 0.7253 | -0.1275 | -0.2129 | 0.5303 | 0.0854 | -36.3214 | -32.6557 | 98.6043 | 98.6285 |
| 0.5545 | 0.78 | 300 | 0.7249 | -0.1096 | -0.2129 | 0.5282 | 0.1033 | -36.3214 | -32.6259 | 98.6240 | 98.6482 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1