metadata
library_name: transformers
license: mit
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: fine_tuned_phi1_5
results: []
fine_tuned_phi1_5
This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3498
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
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9275 | 4 | 5.3873 |
| No log | 1.9275 | 8 | 5.1770 |
| 6.4196 | 2.9275 | 12 | 4.5702 |
| 6.4196 | 3.9275 | 16 | 3.1211 |
| 4.6448 | 4.9275 | 20 | 2.0151 |
| 4.6448 | 5.9275 | 24 | 0.5937 |
| 4.6448 | 6.9275 | 28 | 0.4527 |
| 0.9737 | 7.9275 | 32 | 0.4155 |
| 0.9737 | 8.9275 | 36 | 0.3759 |
| 0.4308 | 9.9275 | 40 | 0.3498 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0