<!-- 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. -->
finetuning-sentiment-model-1
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-bne on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1023
- Accuracy: 0.6423
- F1: 0.5470
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 16 | 1.2357 | 0.4328 | 0.1510 |
| No log | 2.0 | 32 | 1.0922 | 0.6008 | 0.3431 |
| No log | 3.0 | 48 | 0.9682 | 0.6166 | 0.3607 |
| No log | 4.0 | 64 | 0.9349 | 0.6522 | 0.4815 |
| No log | 5.0 | 80 | 0.9244 | 0.6542 | 0.5471 |
| No log | 6.0 | 96 | 0.9796 | 0.6581 | 0.5386 |
| No log | 7.0 | 112 | 1.0155 | 0.6522 | 0.5626 |
| No log | 8.0 | 128 | 1.0731 | 0.6265 | 0.5428 |
| No log | 9.0 | 144 | 1.1026 | 0.6324 | 0.5418 |
| No log | 10.0 | 160 | 1.1023 | 0.6423 | 0.5470 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
