metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert_Pfinal_2e-5_16_10
results: []
bert_Pfinal_2e-5_16_10
This model is a fine-tuned version of fredymad/bert_Pfinal_2e-5_16_2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6295
- F1: 0.7355
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 | F1 |
|---|---|---|---|---|
| 0.101 | 1.0 | 669 | 0.3000 | 0.7169 |
| 0.1282 | 2.0 | 1338 | 0.2993 | 0.7361 |
| 0.0548 | 3.0 | 2007 | 0.3924 | 0.7308 |
| 0.0278 | 4.0 | 2676 | 0.4989 | 0.7221 |
| 0.0229 | 5.0 | 3345 | 0.6089 | 0.6940 |
| 0.0168 | 6.0 | 4014 | 0.5561 | 0.7361 |
| 0.0082 | 7.0 | 4683 | 0.6112 | 0.7297 |
| 0.008 | 8.0 | 5352 | 0.6101 | 0.7343 |
| 0.0052 | 9.0 | 6021 | 0.6253 | 0.7400 |
| 0.003 | 10.0 | 6690 | 0.6295 | 0.7355 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3