metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-classifier
results: []
distilbert-base-uncased-classifier
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3636
- Accuracy: 0.8929
- F1: 0.8102
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0 | 0 | 0.7504 | 0.2894 | 0.4489 |
| No log | 1.0 | 313 | 0.3280 | 0.8697 | 0.7384 |
| 0.3445 | 2.0 | 626 | 0.2999 | 0.8857 | 0.7960 |
| 0.3445 | 3.0 | 939 | 0.3678 | 0.8657 | 0.7846 |
| 0.2115 | 4.0 | 1252 | 0.3471 | 0.8881 | 0.8056 |
| 0.1359 | 5.0 | 1565 | 0.3636 | 0.8929 | 0.8102 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2