metadata
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: NbAiLab/nb-gpt-j-6B-v2
datasets:
- hugodk-sch/aftonposten_title_prefs
model-index:
- name: aftonposten-6b-align-scan
results: []
aftonposten-6b-align-scan
This model is a fine-tuned version of data/ap-gpt-j-6b-sft-qlora-04-08 on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set:
- Loss: 0.5753
- Rewards/chosen: 0.0012
- Rewards/rejected: 0.0139
- Rewards/accuracies: 0.4576
- Rewards/margins: -0.0127
- Logps/rejected: -37.4968
- Logps/chosen: -34.0329
- Logits/rejected: -2.2389
- Logits/chosen: -2.2438
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-07
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5589 | 0.26 | 100 | 0.5107 | 0.0178 | 0.0027 | 0.5573 | 0.0151 | -37.5127 | -34.0091 | -2.2393 | -2.2442 |
| 0.522 | 0.52 | 200 | 0.5423 | 0.0040 | 0.0035 | 0.4689 | 0.0005 | -37.5116 | -34.0288 | -2.2385 | -2.2433 |
| 0.4616 | 0.78 | 300 | 0.5652 | 0.0047 | 0.0129 | 0.4809 | -0.0083 | -37.4981 | -34.0279 | -2.2391 | -2.2439 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1