metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: roberta-base-Roberta-Model
results: []
roberta-base-Roberta-Model
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7971
- F1: 0.6393
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: 8
- eval_batch_size: 8
- 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 | F1 |
|---|---|---|---|---|
| 0.8536 | 0.5 | 500 | 0.8421 | 0.6256 |
| 0.8287 | 1.0 | 1000 | 0.8261 | 0.6295 |
| 0.8274 | 1.5 | 1500 | 0.8228 | 0.6296 |
| 0.8716 | 2.01 | 2000 | 0.9578 | 0.3234 |
| 0.9525 | 2.51 | 2500 | 0.9556 | 0.3222 |
| 0.9656 | 3.01 | 3000 | 0.9501 | 0.3222 |
| 0.8652 | 3.51 | 3500 | 0.8374 | 0.6319 |
| 0.831 | 4.01 | 4000 | 0.8575 | 0.6163 |
| 0.8292 | 4.51 | 4500 | 0.8372 | 0.6290 |
| 0.794 | 5.02 | 5000 | 0.8374 | 0.6268 |
| 0.8711 | 5.52 | 5500 | 0.9145 | 0.5923 |
| 0.823 | 6.02 | 6000 | 0.8496 | 0.6233 |
| 0.8323 | 6.52 | 6500 | 0.8339 | 0.6243 |
| 0.8009 | 7.02 | 7000 | 0.8403 | 0.6248 |
| 0.8038 | 7.52 | 7500 | 0.8402 | 0.6243 |
| 0.7961 | 8.02 | 8000 | 0.8370 | 0.6305 |
| 0.793 | 8.53 | 8500 | 0.8203 | 0.6353 |
| 0.7915 | 9.03 | 9000 | 0.8192 | 0.6306 |
| 0.763 | 9.53 | 9500 | 0.7971 | 0.6393 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3