metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: albert_model_02
results: []
albert_model_02
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: 0.6010
- Accuracy: 0.7406
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 310 | 0.6197 | 0.7203 |
| 0.6587 | 2.0 | 620 | 0.6010 | 0.7406 |
| 0.6587 | 3.0 | 930 | 0.6613 | 0.7345 |
| 0.3804 | 4.0 | 1240 | 0.7342 | 0.7467 |
| 0.2432 | 5.0 | 1550 | 0.7571 | 0.7476 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2