metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8221
- Accuracy: 0.8578
- F1: 0.9007
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0601 | 0.2174 | 50 | 1.0957 | 0.8137 | 0.8774 |
| 0.1259 | 0.4348 | 100 | 0.7100 | 0.8284 | 0.8864 |
| 0.0279 | 0.6522 | 150 | 0.6962 | 0.8456 | 0.8885 |
| 0.0589 | 0.8696 | 200 | 0.6800 | 0.8603 | 0.9019 |
| 0.0544 | 1.0870 | 250 | 0.8519 | 0.8284 | 0.8818 |
| 0.0383 | 1.3043 | 300 | 0.7663 | 0.8578 | 0.8968 |
| 0.0126 | 1.5217 | 350 | 0.8467 | 0.8505 | 0.8920 |
| 0.0077 | 1.7391 | 400 | 0.8421 | 0.8578 | 0.8993 |
| 0.0874 | 1.9565 | 450 | 0.7528 | 0.8578 | 0.8961 |
| 0.0005 | 2.1739 | 500 | 0.8270 | 0.8652 | 0.9050 |
| 0.0009 | 2.3913 | 550 | 0.8435 | 0.8554 | 0.8981 |
| 0.0387 | 2.6087 | 600 | 0.8534 | 0.8652 | 0.9053 |
| 0.0495 | 2.8261 | 650 | 0.8221 | 0.8578 | 0.9007 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2