<!-- 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. -->
BERTovoSENTNEG4
This model is a fine-tuned version of Tanor/BERTicovoSENTNEG4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0675
- F1: 0.5778
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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 32
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 53 | 0.0491 | 0.0800 |
| No log | 2.0 | 106 | 0.0487 | 0.5294 |
| No log | 3.0 | 159 | 0.0517 | 0.5714 |
| No log | 4.0 | 212 | 0.0585 | 0.5366 |
| No log | 5.0 | 265 | 0.0675 | 0.5778 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3
