metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: albert_model__25_1
results: []
albert_model__25_1
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: 0.4995
- Accuracy: 0.7833
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 355 | 0.5751 | 0.7424 |
| 0.6685 | 2.0 | 710 | 0.4995 | 0.7833 |
| 0.4105 | 3.0 | 1065 | 0.5366 | 0.7826 |
| 0.4105 | 4.0 | 1420 | 0.6784 | 0.7784 |
| 0.2443 | 5.0 | 1775 | 0.7940 | 0.7812 |
| 0.1393 | 6.0 | 2130 | 0.9600 | 0.7826 |
| 0.1393 | 7.0 | 2485 | 1.0671 | 0.7763 |
| 0.0921 | 8.0 | 2840 | 1.1389 | 0.7812 |
| 0.0456 | 9.0 | 3195 | 1.2180 | 0.7826 |
| 0.0297 | 10.0 | 3550 | 1.2229 | 0.7791 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1