metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-baseB_10epoch
results: []
roberta-baseB_10epoch
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1305
- Accuracy: 0.8379
- Precision: 0.0983
- Recall: 0.0258
- F1: 0.0355
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: 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 217 | 0.1250 | 0.8571 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 434 | 0.1276 | 0.8571 | 0.0 | 0.0 | 0.0 |
| 0.1727 | 3.0 | 651 | 0.1281 | 0.8571 | 0.0 | 0.0 | 0.0 |
| 0.1727 | 4.0 | 868 | 0.1275 | 0.8571 | 0.0 | 0.0 | 0.0 |
| 0.1577 | 5.0 | 1085 | 0.1296 | 0.8571 | 0.0 | 0.0 | 0.0 |
| 0.1577 | 6.0 | 1302 | 0.1265 | 0.8571 | 0.0 | 0.0 | 0.0 |
| 0.1533 | 7.0 | 1519 | 0.1329 | 0.8529 | 0.0 | 0.0 | 0.0 |
| 0.1533 | 8.0 | 1736 | 0.1268 | 0.8486 | 0.0604 | 0.0037 | 0.0070 |
| 0.1533 | 9.0 | 1953 | 0.1292 | 0.8414 | 0.0789 | 0.0148 | 0.0221 |
| 0.1432 | 10.0 | 2170 | 0.1305 | 0.8379 | 0.0983 | 0.0258 | 0.0355 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1