|
--- |
|
base_model: roberta-large |
|
library_name: peft |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ft-roberta-large-on-bionlp2004-lora |
|
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. --> |
|
|
|
# ft-roberta-large-on-bionlp2004-lora |
|
|
|
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the cdcvd/ejpfepj dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0886 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 13 | 0.2459 | |
|
| No log | 2.0 | 26 | 0.1373 | |
|
| No log | 3.0 | 39 | 0.1105 | |
|
| No log | 4.0 | 52 | 0.1414 | |
|
| No log | 5.0 | 65 | 0.1707 | |
|
| No log | 6.0 | 78 | 0.1172 | |
|
| No log | 7.0 | 91 | 0.3309 | |
|
| No log | 8.0 | 104 | 0.5585 | |
|
| No log | 9.0 | 117 | 0.5192 | |
|
| No log | 10.0 | 130 | 0.5445 | |
|
| No log | 11.0 | 143 | 0.6039 | |
|
| No log | 12.0 | 156 | 0.5424 | |
|
| No log | 13.0 | 169 | 0.5210 | |
|
| No log | 14.0 | 182 | 0.5190 | |
|
| No log | 15.0 | 195 | 0.5433 | |
|
| No log | 16.0 | 208 | 0.5199 | |
|
| No log | 17.0 | 221 | 0.5309 | |
|
| No log | 18.0 | 234 | 0.5507 | |
|
| No log | 19.0 | 247 | 0.5427 | |
|
| No log | 20.0 | 260 | 0.5223 | |
|
| No log | 21.0 | 273 | 0.5194 | |
|
| No log | 22.0 | 286 | 0.5216 | |
|
| No log | 23.0 | 299 | 0.5248 | |
|
| No log | 24.0 | 312 | 0.5192 | |
|
| No log | 25.0 | 325 | 0.5409 | |
|
| No log | 26.0 | 338 | 0.5223 | |
|
| No log | 27.0 | 351 | 0.5719 | |
|
| No log | 28.0 | 364 | 0.5307 | |
|
| No log | 29.0 | 377 | 0.5576 | |
|
| No log | 30.0 | 390 | 0.5272 | |
|
| No log | 31.0 | 403 | 0.5193 | |
|
| No log | 32.0 | 416 | 0.5489 | |
|
| No log | 33.0 | 429 | 0.5215 | |
|
| No log | 34.0 | 442 | 0.5359 | |
|
| No log | 35.0 | 455 | 0.5728 | |
|
| No log | 36.0 | 468 | 0.5560 | |
|
| No log | 37.0 | 481 | 0.5765 | |
|
| No log | 38.0 | 494 | 0.5562 | |
|
| 0.4913 | 39.0 | 507 | 0.6608 | |
|
| 0.4913 | 40.0 | 520 | 0.7299 | |
|
| 0.4913 | 41.0 | 533 | 0.5850 | |
|
| 0.4913 | 42.0 | 546 | 0.7992 | |
|
| 0.4913 | 43.0 | 559 | 0.7670 | |
|
| 0.4913 | 44.0 | 572 | 0.9654 | |
|
| 0.4913 | 45.0 | 585 | 1.0347 | |
|
| 0.4913 | 46.0 | 598 | 0.9568 | |
|
| 0.4913 | 47.0 | 611 | 1.0205 | |
|
| 0.4913 | 48.0 | 624 | 1.0679 | |
|
| 0.4913 | 49.0 | 637 | 1.1054 | |
|
| 0.4913 | 50.0 | 650 | 1.0886 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.2 |
