working
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: 0.1224
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: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 15
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9283 | 0.99 | 42 | 0.6680 |
| 0.4333 | 1.98 | 84 | 0.3164 |
| 0.2286 | 3.0 | 127 | 0.2224 |
| 0.1812 | 3.99 | 169 | 0.1807 |
| 0.1508 | 5.0 | 212 | 0.1540 |
| 0.1373 | 5.99 | 254 | 0.1396 |
| 0.1261 | 6.98 | 296 | 0.1307 |
| 0.1157 | 8.0 | 339 | 0.1257 |
| 0.1128 | 8.99 | 381 | 0.1235 |
| 0.1097 | 9.91 | 420 | 0.1224 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for Surabhi-K1/phi2_20_epoch
Base model
microsoft/phi-2