|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: tiiuae/falcon-7b |
|
model-index: |
|
- name: working |
|
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. --> |
|
|
|
# working |
|
|
|
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6524 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.4729 | 0.95 | 5 | 2.1690 | |
|
| 2.3701 | 1.9 | 10 | 2.0002 | |
|
| 2.1498 | 2.86 | 15 | 1.8282 | |
|
| 1.5589 | 4.0 | 21 | 1.6084 | |
|
| 1.7043 | 4.95 | 26 | 1.4217 | |
|
| 1.315 | 5.9 | 31 | 1.2678 | |
|
| 1.1273 | 6.86 | 36 | 1.1439 | |
|
| 0.7666 | 8.0 | 42 | 1.0079 | |
|
| 0.762 | 8.95 | 47 | 0.9406 | |
|
| 0.6241 | 9.9 | 52 | 0.8969 | |
|
| 0.5211 | 10.86 | 57 | 0.8128 | |
|
| 0.3836 | 12.0 | 63 | 0.7788 | |
|
| 0.396 | 12.95 | 68 | 0.7358 | |
|
| 0.3255 | 13.9 | 73 | 0.7152 | |
|
| 0.2863 | 14.86 | 78 | 0.6880 | |
|
| 0.2405 | 16.0 | 84 | 0.6383 | |
|
| 0.2471 | 16.95 | 89 | 0.6414 | |
|
| 0.2214 | 17.9 | 94 | 0.6250 | |
|
| 0.2074 | 18.86 | 99 | 0.6280 | |
|
| 0.1682 | 20.0 | 105 | 0.6317 | |
|
| 0.1984 | 20.95 | 110 | 0.6157 | |
|
| 0.1817 | 21.9 | 115 | 0.6330 | |
|
| 0.1723 | 22.86 | 120 | 0.6154 | |
|
| 0.1393 | 24.0 | 126 | 0.6111 | |
|
| 0.1615 | 24.95 | 131 | 0.6330 | |
|
| 0.177 | 25.9 | 136 | 0.6185 | |
|
| 0.1462 | 26.86 | 141 | 0.6225 | |
|
| 0.1204 | 28.0 | 147 | 0.6225 | |
|
| 0.1494 | 28.95 | 152 | 0.6336 | |
|
| 0.1463 | 29.9 | 157 | 0.6345 | |
|
| 0.1507 | 30.86 | 162 | 0.6250 | |
|
| 0.1163 | 32.0 | 168 | 0.6178 | |
|
| 0.1556 | 32.95 | 173 | 0.6377 | |
|
| 0.1465 | 33.9 | 178 | 0.6392 | |
|
| 0.1391 | 34.86 | 183 | 0.6459 | |
|
| 0.113 | 36.0 | 189 | 0.6572 | |
|
| 0.1386 | 36.95 | 194 | 0.6436 | |
|
| 0.1497 | 37.9 | 199 | 0.6284 | |
|
| 0.1567 | 38.86 | 204 | 0.6434 | |
|
| 0.1097 | 40.0 | 210 | 0.6492 | |
|
| 0.1276 | 40.95 | 215 | 0.6451 | |
|
| 0.1423 | 41.9 | 220 | 0.6395 | |
|
| 0.126 | 42.86 | 225 | 0.6457 | |
|
| 0.1064 | 44.0 | 231 | 0.6517 | |
|
| 0.131 | 44.95 | 236 | 0.6525 | |
|
| 0.1224 | 45.9 | 241 | 0.6517 | |
|
| 0.1399 | 46.86 | 246 | 0.6521 | |
|
| 0.0991 | 47.62 | 250 | 0.6524 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
