selfbiorag-7b-wo-kqa_golden-iter-dpo-step2
This model is a fine-tuned version of Minbyul/selfbiorag-7b-wo-kqa_golden-iter-sft-step1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.4028
- Rewards/chosen: -1.3389
- Rewards/rejected: -4.1640
- Rewards/accuracies: 0.7344
- Rewards/margins: 2.8251
- Logps/rejected: -858.1113
- Logps/chosen: -368.7221
- Logits/rejected: -0.8026
- Logits/chosen: -1.0600
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.139 | 0.62 | 100 | 0.3923 | -1.1034 | -3.4359 | 0.7422 | 2.3325 | -785.2989 | -345.1770 | -0.8936 | -1.1380 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2