metadata
license: apache-2.0
base_model: ibaucells/RoBERTa-ca-CaWikiTC
tags:
- generated_from_trainer
model-index:
- name: test6_balanced
results: []
test6_balanced
This model is a fine-tuned version of ibaucells/RoBERTa-ca-CaWikiTC on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6982
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: 5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8358 | 1.0 | 63 | 2.8655 |
| 2.8469 | 2.0 | 126 | 2.8447 |
| 2.7935 | 3.0 | 189 | 2.8533 |
| 2.8191 | 4.0 | 252 | 2.8142 |
| 2.6885 | 5.0 | 315 | 2.8259 |
| 2.5876 | 6.0 | 378 | 2.6759 |
| 2.5032 | 7.0 | 441 | 2.6097 |
| 2.3133 | 8.0 | 504 | 2.5192 |
| 2.1289 | 9.0 | 567 | 2.5403 |
| 1.9344 | 10.0 | 630 | 2.4371 |
| 1.6321 | 11.0 | 693 | 2.2946 |
| 1.4731 | 12.0 | 756 | 2.1326 |
| 1.2114 | 13.0 | 819 | 2.0522 |
| 1.1537 | 14.0 | 882 | 2.1146 |
| 1.022 | 15.0 | 945 | 1.9946 |
| 0.8745 | 16.0 | 1008 | 1.8565 |
| 0.5796 | 17.0 | 1071 | 1.7965 |
| 0.5599 | 18.0 | 1134 | 1.7063 |
| 0.4366 | 19.0 | 1197 | 1.9333 |
| 0.3558 | 20.0 | 1260 | 1.8851 |
| 0.3272 | 21.0 | 1323 | 1.8570 |
| 0.2594 | 22.0 | 1386 | 1.8596 |
| 0.2432 | 23.0 | 1449 | 1.9433 |
| 0.2298 | 24.0 | 1512 | 1.9467 |
| 0.266 | 25.0 | 1575 | 1.9150 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2