|
--- |
|
license: mit |
|
base_model: microsoft/phi-2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: V0424HMA12 |
|
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. --> |
|
|
|
# V0424HMA12 |
|
|
|
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: 0.1319 |
|
|
|
## 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: 100 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.5164 | 0.09 | 10 | 0.1470 | |
|
| 0.1523 | 0.18 | 20 | 0.1190 | |
|
| 0.1124 | 0.27 | 30 | 0.0974 | |
|
| 0.1056 | 0.36 | 40 | 0.0875 | |
|
| 0.0798 | 0.45 | 50 | 0.0797 | |
|
| 0.0884 | 0.54 | 60 | 0.0825 | |
|
| 0.0851 | 0.63 | 70 | 0.0749 | |
|
| 0.084 | 0.73 | 80 | 0.1080 | |
|
| 0.1024 | 0.82 | 90 | 0.0820 | |
|
| 0.342 | 0.91 | 100 | 0.1022 | |
|
| 0.1777 | 1.0 | 110 | 0.1201 | |
|
| 1.1335 | 1.09 | 120 | 10.0693 | |
|
| 3.546 | 1.18 | 130 | 0.4678 | |
|
| 0.5922 | 1.27 | 140 | 0.2032 | |
|
| 0.293 | 1.36 | 150 | 0.1823 | |
|
| 0.175 | 1.45 | 160 | 0.1510 | |
|
| 0.1651 | 1.54 | 170 | 0.1670 | |
|
| 0.1582 | 1.63 | 180 | 0.1542 | |
|
| 0.1492 | 1.72 | 190 | 0.1420 | |
|
| 0.1409 | 1.81 | 200 | 0.1404 | |
|
| 0.1462 | 1.9 | 210 | 0.1417 | |
|
| 0.1428 | 1.99 | 220 | 0.1407 | |
|
| 0.1498 | 2.08 | 230 | 0.1731 | |
|
| 0.1461 | 2.18 | 240 | 0.1394 | |
|
| 0.1378 | 2.27 | 250 | 0.1333 | |
|
| 0.1357 | 2.36 | 260 | 0.1321 | |
|
| 0.1294 | 2.45 | 270 | 0.1322 | |
|
| 0.1339 | 2.54 | 280 | 0.1312 | |
|
| 0.131 | 2.63 | 290 | 0.1330 | |
|
| 0.132 | 2.72 | 300 | 0.1361 | |
|
| 0.1369 | 2.81 | 310 | 0.1319 | |
|
| 0.1348 | 2.9 | 320 | 0.1317 | |
|
| 0.1309 | 2.99 | 330 | 0.1319 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.14.1 |
|
|
