metadata
license: apache-2.0
base_model: BSC-TeMU/roberta-base-bne
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-base-bne-finetuned-multi-sentiment-finetuned-multi-sentiment
results: []
roberta-base-bne-finetuned-multi-sentiment-finetuned-multi-sentiment
This model is a fine-tuned version of BSC-TeMU/roberta-base-bne on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0249
- Accuracy: 0.6451
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.5534 | 1.0 | 115 | 0.7764 | 0.6512 |
| 0.3479 | 2.0 | 230 | 0.9324 | 0.6512 |
| 0.0922 | 3.0 | 345 | 1.2452 | 0.6574 |
| 0.0218 | 4.0 | 460 | 1.7006 | 0.6512 |
| 0.001 | 5.0 | 575 | 1.7949 | 0.6512 |
| 0.0007 | 6.0 | 690 | 1.8798 | 0.6605 |
| 0.0006 | 7.0 | 805 | 1.9510 | 0.6451 |
| 0.0005 | 8.0 | 920 | 1.9926 | 0.6451 |
| 0.0004 | 9.0 | 1035 | 2.0169 | 0.6451 |
| 0.0004 | 10.0 | 1150 | 2.0249 | 0.6451 |
Framework versions
- Transformers 4.40.2
- Pytorch 1.13.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1