metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert_prof_single_v3_128_below_100
results: []
bert_prof_single_v3_128_below_100
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6341
- Accuracy: 0.8500
- F1: 0.8455
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: 1.6289314429698796e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7676 | 1.0 | 7505 | 0.7432 | 0.8097 | 0.7967 |
| 0.579 | 2.0 | 15010 | 0.6401 | 0.8404 | 0.8343 |
| 0.4389 | 3.0 | 22515 | 0.6213 | 0.8482 | 0.8430 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1