V0410MPTEST
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1698
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: 0.003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 20
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3082 | 0.18 | 20 | 0.1512 |
| 0.3851 | 0.36 | 40 | 0.1436 |
| 1.3893 | 0.54 | 60 | 2.9457 |
| 2.275 | 0.73 | 80 | 2.0088 |
| 1.2688 | 0.91 | 100 | 0.5535 |
| 0.3937 | 1.09 | 120 | 0.3250 |
| 0.2655 | 1.27 | 140 | 0.2408 |
| 0.2169 | 1.45 | 160 | 0.1967 |
| 0.1912 | 1.63 | 180 | 0.1814 |
| 0.1784 | 1.81 | 200 | 0.1738 |
| 0.1757 | 1.99 | 220 | 0.1698 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for Litzy619/V0410MPTEST
Base model
microsoft/phi-2