|
--- |
|
license: mit |
|
base_model: microsoft/phi-2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: V0424MADP5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# V0424MADP5 |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1480 |
|
|
|
## 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: 0.0003 |
|
- 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: 80 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 8.3847 | 0.09 | 10 | 2.9270 | |
|
| 4.8632 | 0.18 | 20 | 2.1131 | |
|
| 1.8758 | 0.27 | 30 | 0.8698 | |
|
| 0.3611 | 0.36 | 40 | 0.3136 | |
|
| 0.173 | 0.45 | 50 | 0.1911 | |
|
| 0.1662 | 0.54 | 60 | 0.1774 | |
|
| 0.1615 | 0.63 | 70 | 0.1630 | |
|
| 0.1598 | 0.73 | 80 | 0.1656 | |
|
| 0.1612 | 0.82 | 90 | 0.1598 | |
|
| 0.1547 | 0.91 | 100 | 0.1515 | |
|
| 0.1574 | 1.0 | 110 | 0.1517 | |
|
| 0.1576 | 1.09 | 120 | 0.1557 | |
|
| 0.1616 | 1.18 | 130 | 0.1728 | |
|
| 0.1587 | 1.27 | 140 | 0.1538 | |
|
| 0.156 | 1.36 | 150 | 0.1534 | |
|
| 0.1545 | 1.45 | 160 | 0.1487 | |
|
| 0.1552 | 1.54 | 170 | 0.1612 | |
|
| 0.1578 | 1.63 | 180 | 0.1528 | |
|
| 0.1587 | 1.72 | 190 | 0.1691 | |
|
| 0.1567 | 1.81 | 200 | 0.1491 | |
|
| 0.1619 | 1.9 | 210 | 0.1497 | |
|
| 0.1546 | 1.99 | 220 | 0.1508 | |
|
| 0.1564 | 2.08 | 230 | 0.1497 | |
|
| 0.1481 | 2.18 | 240 | 0.1481 | |
|
| 0.1491 | 2.27 | 250 | 0.1512 | |
|
| 0.1511 | 2.36 | 260 | 0.1504 | |
|
| 0.1519 | 2.45 | 270 | 0.1494 | |
|
| 0.1464 | 2.54 | 280 | 0.1493 | |
|
| 0.148 | 2.63 | 290 | 0.1488 | |
|
| 0.1499 | 2.72 | 300 | 0.1487 | |
|
| 0.1487 | 2.81 | 310 | 0.1480 | |
|
| 0.1484 | 2.9 | 320 | 0.1479 | |
|
| 0.15 | 2.99 | 330 | 0.1480 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.14.1 |
|
|
