doplhin-mistral-dpo-ultrafeedback-binarized-preferences-sigmoid
This model is a fine-tuned version of cognitivecomputations/dolphin-2.1-mistral-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6025
- Rewards/chosen: -7.8168
- Rewards/rejected: -14.5388
- Rewards/accuracies: 0.8310
- Rewards/margins: 6.7220
- Logps/rejected: -469.4976
- Logps/chosen: -438.1190
- Logits/rejected: -2.1911
- Logits/chosen: -2.3064
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0466 | 0.25 | 700 | 0.8185 | -6.6407 | -9.8742 | 0.7464 | 3.2335 | -422.8520 | -426.3579 | -2.3161 | -2.4530 |
| 0.7039 | 0.51 | 1400 | 0.7051 | -6.5305 | -12.5351 | 0.8085 | 6.0046 | -449.4607 | -425.2558 | -2.1415 | -2.2554 |
| 0.9519 | 0.76 | 2100 | 0.6025 | -7.8168 | -14.5388 | 0.8310 | 6.7220 | -469.4976 | -438.1190 | -2.1911 | -2.3064 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for DrishtiSharma/dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-sigmoid
Base model
cognitivecomputations/dolphin-2.1-mistral-7b