metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: distilbert_imdb_padding100model
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: imdb
          type: imdb
          config: plain_text
          split: test
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9298

distilbert_imdb_padding100model

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

Loss: 0.7577
Accuracy: 0.9298

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
0.24	1.0	1563	0.2377	0.9178
0.1837	2.0	3126	0.2434	0.926
0.1183	3.0	4689	0.3062	0.9256
0.0725	4.0	6252	0.3338	0.9271
0.0455	5.0	7815	0.4833	0.9156
0.0436	6.0	9378	0.4745	0.9260
0.0257	7.0	10941	0.4971	0.9254
0.0235	8.0	12504	0.5366	0.9226
0.0219	9.0	14067	0.5533	0.9244
0.0219	10.0	15630	0.5323	0.9267
0.0122	11.0	17193	0.7565	0.9170
0.012	12.0	18756	0.6422	0.9261
0.0068	13.0	20319	0.6996	0.9265
0.0055	14.0	21882	0.7342	0.9269
0.0135	15.0	23445	0.7324	0.9252
0.0053	16.0	25008	0.6880	0.9288
0.001	17.0	26571	0.7319	0.9289
0.0015	18.0	28134	0.7300	0.9287
0.0016	19.0	29697	0.7450	0.9294
0.0001	20.0	31260	0.7577	0.9298

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3