metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: distilbert_imdb_padding30model
    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: 0.93324

distilbert_imdb_padding30model

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: 0.7240
Accuracy: 0.9332

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
0.2379	1.0	1563	0.2408	0.9134
0.1715	2.0	3126	0.2436	0.928
0.1026	3.0	4689	0.2785	0.9294
0.061	4.0	6252	0.3530	0.9286
0.0454	5.0	7815	0.4828	0.9204
0.0378	6.0	9378	0.4618	0.9289
0.0234	7.0	10941	0.4958	0.9269
0.0239	8.0	12504	0.5093	0.9275
0.0196	9.0	14067	0.4641	0.9294
0.0135	10.0	15630	0.6116	0.9277
0.0128	11.0	17193	0.6289	0.9278
0.012	12.0	18756	0.6210	0.9299
0.0087	13.0	20319	0.6698	0.93
0.0063	14.0	21882	0.6935	0.927
0.0045	15.0	23445	0.6642	0.9286
0.0034	16.0	25008	0.6603	0.9318
0.0009	17.0	26571	0.6836	0.9332
0.0011	18.0	28134	0.7181	0.9316
0.0004	19.0	29697	0.7155	0.9329
0.0004	20.0	31260	0.7240	0.9332

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3