metadata
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-sft-outB
results: []
phi-sft-outB
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: 0.9402
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9855 | 0.01 | 1 | 1.1349 |
| 1.3387 | 0.2 | 18 | 1.1270 |
| 1.1906 | 0.4 | 36 | 1.0901 |
| 0.8854 | 0.6 | 54 | 1.0535 |
| 1.1896 | 0.8 | 72 | 1.0300 |
| 0.9865 | 1.0 | 90 | 1.0094 |
| 1.1497 | 1.2 | 108 | 0.9901 |
| 1.1192 | 1.4 | 126 | 0.9769 |
| 0.8953 | 1.6 | 144 | 0.9651 |
| 1.0513 | 1.81 | 162 | 0.9565 |
| 0.9776 | 2.01 | 180 | 0.9512 |
| 1.087 | 2.21 | 198 | 0.9473 |
| 1.1714 | 2.41 | 216 | 0.9443 |
| 0.8238 | 2.61 | 234 | 0.9423 |
| 1.0734 | 2.81 | 252 | 0.9413 |
| 0.8108 | 3.01 | 270 | 0.9406 |
| 1.0202 | 3.21 | 288 | 0.9403 |
| 1.134 | 3.41 | 306 | 0.9402 |
| 0.8043 | 3.61 | 324 | 0.9401 |
| 1.0807 | 3.81 | 342 | 0.9402 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0