|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: predict-perception-bertino-cause-none |
|
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. --> |
|
|
|
# predict-perception-bertino-cause-none |
|
|
|
This model is a fine-tuned version of [indigo-ai/BERTino](https://huggingface.co/indigo-ai/BERTino) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1988 |
|
- R2: 0.4467 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 20 |
|
- eval_batch_size: 8 |
|
- seed: 1996 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 47 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | R2 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.56 | 1.0 | 14 | 0.3460 | 0.0372 | |
|
| 0.3752 | 2.0 | 28 | 0.3082 | 0.1423 | |
|
| 0.147 | 3.0 | 42 | 0.2299 | 0.3603 | |
|
| 0.0961 | 4.0 | 56 | 0.3254 | 0.0944 | |
|
| 0.0859 | 5.0 | 70 | 0.2650 | 0.2625 | |
|
| 0.0735 | 6.0 | 84 | 0.2430 | 0.3237 | |
|
| 0.042 | 7.0 | 98 | 0.2567 | 0.2856 | |
|
| 0.0328 | 8.0 | 112 | 0.2092 | 0.4180 | |
|
| 0.028 | 9.0 | 126 | 0.2262 | 0.3706 | |
|
| 0.0237 | 10.0 | 140 | 0.2170 | 0.3960 | |
|
| 0.0235 | 11.0 | 154 | 0.2137 | 0.4054 | |
|
| 0.0195 | 12.0 | 168 | 0.2009 | 0.4409 | |
|
| 0.0217 | 13.0 | 182 | 0.2001 | 0.4431 | |
|
| 0.0176 | 14.0 | 196 | 0.2123 | 0.4091 | |
|
| 0.0226 | 15.0 | 210 | 0.2076 | 0.4224 | |
|
| 0.019 | 16.0 | 224 | 0.1920 | 0.4657 | |
|
| 0.0122 | 17.0 | 238 | 0.2301 | 0.3598 | |
|
| 0.0121 | 18.0 | 252 | 0.2092 | 0.4178 | |
|
| 0.0112 | 19.0 | 266 | 0.2038 | 0.4329 | |
|
| 0.0081 | 20.0 | 280 | 0.2008 | 0.4411 | |
|
| 0.0079 | 21.0 | 294 | 0.1930 | 0.4631 | |
|
| 0.0083 | 22.0 | 308 | 0.2076 | 0.4222 | |
|
| 0.0061 | 23.0 | 322 | 0.2036 | 0.4334 | |
|
| 0.0057 | 24.0 | 336 | 0.1986 | 0.4472 | |
|
| 0.0059 | 25.0 | 350 | 0.2079 | 0.4215 | |
|
| 0.0082 | 26.0 | 364 | 0.2125 | 0.4087 | |
|
| 0.0093 | 27.0 | 378 | 0.2096 | 0.4168 | |
|
| 0.0061 | 28.0 | 392 | 0.2129 | 0.4076 | |
|
| 0.005 | 29.0 | 406 | 0.2054 | 0.4284 | |
|
| 0.0058 | 30.0 | 420 | 0.2024 | 0.4368 | |
|
| 0.006 | 31.0 | 434 | 0.1999 | 0.4437 | |
|
| 0.0047 | 32.0 | 448 | 0.1917 | 0.4666 | |
|
| 0.0046 | 33.0 | 462 | 0.2000 | 0.4435 | |
|
| 0.005 | 34.0 | 476 | 0.2003 | 0.4425 | |
|
| 0.0041 | 35.0 | 490 | 0.2057 | 0.4276 | |
|
| 0.0037 | 36.0 | 504 | 0.1985 | 0.4476 | |
|
| 0.0049 | 37.0 | 518 | 0.2029 | 0.4353 | |
|
| 0.0031 | 38.0 | 532 | 0.1963 | 0.4539 | |
|
| 0.0031 | 39.0 | 546 | 0.1957 | 0.4554 | |
|
| 0.0031 | 40.0 | 560 | 0.1962 | 0.4540 | |
|
| 0.0029 | 41.0 | 574 | 0.2000 | 0.4433 | |
|
| 0.0028 | 42.0 | 588 | 0.1986 | 0.4473 | |
|
| 0.0035 | 43.0 | 602 | 0.1972 | 0.4514 | |
|
| 0.0029 | 44.0 | 616 | 0.1984 | 0.4479 | |
|
| 0.0036 | 45.0 | 630 | 0.2005 | 0.4422 | |
|
| 0.0033 | 46.0 | 644 | 0.1994 | 0.4452 | |
|
| 0.0029 | 47.0 | 658 | 0.1988 | 0.4467 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 1.10.2+cu113 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.11.0 |
|
|
