metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - ag_news
metrics:
  - accuracy
model-index:
  - name: N_distilbert_agnews_padding30model
    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: 0.9431578947368421

N_distilbert_agnews_padding30model

This model is a fine-tuned version of distilbert-base-uncased on the ag_news dataset. It achieves the following results on the evaluation set:

Loss: 0.6563
Accuracy: 0.9432

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
0.1786	1.0	7500	0.1921	0.9395
0.1379	2.0	15000	0.1926	0.9447
0.1163	3.0	22500	0.2237	0.9443
0.0863	4.0	30000	0.2627	0.9432
0.0551	5.0	37500	0.3291	0.9412
0.0422	6.0	45000	0.3613	0.9464
0.0356	7.0	52500	0.4004	0.9405
0.0319	8.0	60000	0.4574	0.9388
0.0229	9.0	67500	0.4549	0.9404
0.0173	10.0	75000	0.4684	0.9420
0.0173	11.0	82500	0.4891	0.9405
0.0097	12.0	90000	0.5301	0.9418
0.0088	13.0	97500	0.5361	0.9409
0.0061	14.0	105000	0.5930	0.9433
0.0031	15.0	112500	0.5658	0.9438
0.0037	16.0	120000	0.6000	0.9420
0.0023	17.0	127500	0.6230	0.9420
0.0003	18.0	135000	0.6184	0.9441
0.0003	19.0	142500	0.6488	0.9426
0.0007	20.0	150000	0.6563	0.9432

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3