metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_model
results: []
test_model
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9938
- Accuracy: 0.76
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6263 | 0.62 | 100 | 0.5941 | 0.7394 |
| 0.5263 | 1.24 | 200 | 0.5814 | 0.7578 |
| 0.4177 | 1.86 | 300 | 0.6013 | 0.7530 |
| 0.2901 | 2.48 | 400 | 0.7275 | 0.7402 |
| 0.2377 | 3.11 | 500 | 0.7853 | 0.7433 |
| 0.1313 | 3.73 | 600 | 0.8747 | 0.7394 |
| 0.1043 | 4.35 | 700 | 0.9510 | 0.7464 |
| 0.0714 | 4.97 | 800 | 0.9938 | 0.7473 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.13.3