metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- ag_news
metrics:
- accuracy
model-index:
- name: N_bert_agnews_padding60model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: ag_news
type: ag_news
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9477631578947369
N_bert_agnews_padding60model
This model is a fine-tuned version of bert-base-uncased on the ag_news dataset. It achieves the following results on the evaluation set:
- Loss: 0.5465
- Accuracy: 0.9478
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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1768 | 1.0 | 7500 | 0.1912 | 0.9447 |
0.1428 | 2.0 | 15000 | 0.2136 | 0.9397 |
0.1172 | 3.0 | 22500 | 0.2275 | 0.9418 |
0.08 | 4.0 | 30000 | 0.2665 | 0.9446 |
0.0564 | 5.0 | 37500 | 0.3084 | 0.9462 |
0.0368 | 6.0 | 45000 | 0.3503 | 0.9442 |
0.0381 | 7.0 | 52500 | 0.3898 | 0.9418 |
0.0279 | 8.0 | 60000 | 0.4233 | 0.9418 |
0.0177 | 9.0 | 67500 | 0.4515 | 0.9436 |
0.012 | 10.0 | 75000 | 0.4573 | 0.9451 |
0.0186 | 11.0 | 82500 | 0.4427 | 0.9455 |
0.0124 | 12.0 | 90000 | 0.4840 | 0.9424 |
0.0074 | 13.0 | 97500 | 0.4665 | 0.9459 |
0.0077 | 14.0 | 105000 | 0.5069 | 0.9461 |
0.0031 | 15.0 | 112500 | 0.5102 | 0.9443 |
0.0028 | 16.0 | 120000 | 0.5251 | 0.9466 |
0.0021 | 17.0 | 127500 | 0.5325 | 0.9464 |
0.0024 | 18.0 | 135000 | 0.5260 | 0.9483 |
0.0004 | 19.0 | 142500 | 0.5443 | 0.9472 |
0.0011 | 20.0 | 150000 | 0.5465 | 0.9478 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3