metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: results
results: []
results
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0462
- Accuracy: 0.565
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: 4
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 15
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6966 | 0.12 | 30 | 1.6482 | 0.205 |
| 1.6111 | 0.24 | 60 | 1.5500 | 0.312 |
| 1.5634 | 0.36 | 90 | 1.4253 | 0.391 |
| 1.4389 | 0.48 | 120 | 1.2866 | 0.429 |
| 1.3507 | 0.6 | 150 | 1.2292 | 0.466 |
| 1.3072 | 0.72 | 180 | 1.2251 | 0.435 |
| 1.2346 | 0.84 | 210 | 1.3498 | 0.412 |
| 1.3884 | 0.96 | 240 | 1.1693 | 0.515 |
| 1.0748 | 1.08 | 270 | 1.2255 | 0.474 |
| 1.02 | 1.2 | 300 | 1.2691 | 0.475 |
| 1.0354 | 1.32 | 330 | 1.1937 | 0.48 |
| 1.0622 | 1.44 | 360 | 1.1304 | 0.512 |
| 1.0289 | 1.56 | 390 | 1.2823 | 0.465 |
| 1.1433 | 1.6800 | 420 | 1.0603 | 0.527 |
| 1.0125 | 1.8 | 450 | 1.0753 | 0.522 |
| 0.8716 | 1.92 | 480 | 1.0901 | 0.532 |
| 0.8761 | 2.04 | 510 | 1.0462 | 0.565 |
| 0.6857 | 2.16 | 540 | 1.0626 | 0.555 |
| 0.7674 | 2.2800 | 570 | 1.0799 | 0.545 |
| 0.6676 | 2.4 | 600 | 1.0843 | 0.546 |
| 0.6254 | 2.52 | 630 | 1.1148 | 0.551 |
| 0.6813 | 2.64 | 660 | 1.1227 | 0.553 |
| 0.7043 | 2.76 | 690 | 1.1267 | 0.558 |
| 0.4643 | 2.88 | 720 | 1.1227 | 0.551 |
| 0.6665 | 3.0 | 750 | 1.1222 | 0.557 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1