phi-1_5-finetuned-model-instruction
This model is a fine-tuned version of microsoft/phi-1_5 on an unknown dataset.
It achieves the following results on the evaluation set:
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: 0.0004
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 2.1228 |
0.81 |
250 |
2.1649 |
| 2.0486 |
1.62 |
500 |
2.1162 |
| 1.9924 |
2.44 |
750 |
2.0775 |
| 1.9132 |
3.25 |
1000 |
2.0590 |
| 1.8639 |
4.06 |
1250 |
2.0433 |
| 1.8384 |
4.87 |
1500 |
2.0478 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
