|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: roberta-base-mnli_MULTI |
|
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. --> |
|
|
|
# roberta-base-mnli_MULTI |
|
|
|
This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7607 |
|
- Acc: 0.8310 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Acc | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.4798 | 0.17 | 2000 | 0.4810 | 0.8211 | |
|
| 0.4494 | 0.33 | 4000 | 0.4606 | 0.8268 | |
|
| 0.431 | 0.5 | 6000 | 0.4623 | 0.8301 | |
|
| 0.4371 | 0.67 | 8000 | 0.4437 | 0.8297 | |
|
| 0.4297 | 0.83 | 10000 | 0.4548 | 0.8313 | |
|
| 0.4214 | 1.0 | 12000 | 0.4566 | 0.8337 | |
|
| 0.3123 | 1.17 | 14000 | 0.4893 | 0.8323 | |
|
| 0.3158 | 1.33 | 16000 | 0.4861 | 0.8342 | |
|
| 0.324 | 1.5 | 18000 | 0.4812 | 0.8308 | |
|
| 0.3161 | 1.66 | 20000 | 0.4630 | 0.8365 | |
|
| 0.32 | 1.83 | 22000 | 0.4630 | 0.8366 | |
|
| 0.3195 | 2.0 | 24000 | 0.4681 | 0.8355 | |
|
| 0.2274 | 2.16 | 26000 | 0.5347 | 0.8407 | |
|
| 0.2311 | 2.33 | 28000 | 0.5650 | 0.8310 | |
|
| 0.2293 | 2.5 | 30000 | 0.5408 | 0.8355 | |
|
| 0.2296 | 2.66 | 32000 | 0.5207 | 0.8374 | |
|
| 0.2274 | 2.83 | 34000 | 0.5696 | 0.8353 | |
|
| 0.23 | 3.0 | 36000 | 0.5332 | 0.8366 | |
|
| 0.1686 | 3.16 | 38000 | 0.6275 | 0.8343 | |
|
| 0.1632 | 3.33 | 40000 | 0.6457 | 0.8349 | |
|
| 0.1686 | 3.5 | 42000 | 0.5965 | 0.8338 | |
|
| 0.1634 | 3.66 | 44000 | 0.6272 | 0.8342 | |
|
| 0.1656 | 3.83 | 46000 | 0.6541 | 0.8312 | |
|
| 0.162 | 4.0 | 48000 | 0.6408 | 0.8317 | |
|
| 0.1288 | 4.16 | 50000 | 0.7237 | 0.8349 | |
|
| 0.1275 | 4.33 | 52000 | 0.7558 | 0.8295 | |
|
| 0.1291 | 4.5 | 54000 | 0.7730 | 0.8306 | |
|
| 0.1261 | 4.66 | 56000 | 0.7524 | 0.8300 | |
|
| 0.1272 | 4.83 | 58000 | 0.7572 | 0.8317 | |
|
| 0.1242 | 4.99 | 60000 | 0.7607 | 0.8310 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.12.1 |
|
|
