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: 1.6251
- Rewards/chosen: -0.0217
- Rewards/rejected: -0.0319
- Rewards/accuracies: 0.5079
- Rewards/margins: 0.0102
- Logps/rejected: -37.5964
- Logps/chosen: -34.0889
- Logits/rejected: -2.2264
- Logits/chosen: -2.2312
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
1.4583 | 0.26 | 100 | 1.6162 | 0.0017 | -0.0028 | 0.5245 | 0.0045 | -37.5236 | -34.0303 | -2.2308 | -2.2357 |
1.279 | 0.52 | 200 | 1.6100 | -0.0192 | -0.0303 | 0.5257 | 0.0111 | -37.5923 | -34.0825 | -2.2311 | -2.2359 |
1.0043 | 0.78 | 300 | 1.5962 | -0.0200 | -0.0335 | 0.5166 | 0.0135 | -37.6004 | -34.0845 | -2.2263 | -2.2312 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1