phi3-mini
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.9347
- Rewards/chosen: -0.1857
- Rewards/rejected: -0.1976
- Rewards/accuracies: 0.5
- Rewards/margins: 0.0119
- Logps/rejected: -1.9760
- Logps/chosen: -1.8571
- Logits/rejected: 1.1450
- Logits/chosen: 0.9812
- Nll Loss: 4.8526
- Log Odds Ratio: -0.8211
- Log Odds Chosen: 0.1482
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: 8e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- 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 | Nll Loss | Log Odds Ratio | Log Odds Chosen |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
3.6683 | 0.2020 | 25 | 4.9347 | -0.1857 | -0.1976 | 0.5 | 0.0119 | -1.9760 | -1.8571 | 1.1450 | 0.9812 | 4.8526 | -0.8211 | 0.1482 |
3.8133 | 0.4040 | 50 | 4.9347 | -0.1857 | -0.1976 | 0.5 | 0.0119 | -1.9760 | -1.8571 | 1.1450 | 0.9812 | 4.8526 | -0.8211 | 0.1482 |
5.3188 | 0.6061 | 75 | 4.9347 | -0.1857 | -0.1976 | 0.5 | 0.0119 | -1.9760 | -1.8571 | 1.1450 | 0.9812 | 4.8526 | -0.8211 | 0.1482 |
3.3559 | 0.8081 | 100 | 4.9347 | -0.1857 | -0.1976 | 0.5 | 0.0119 | -1.9760 | -1.8571 | 1.1450 | 0.9812 | 4.8526 | -0.8211 | 0.1482 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0