metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: N_distilbert_imdb_padding0model
    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: 0.93296

N_distilbert_imdb_padding0model

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: 0.7323
Accuracy: 0.9330

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
0.2341	1.0	1563	0.2381	0.9157
0.1705	2.0	3126	0.2390	0.9244
0.1026	3.0	4689	0.2963	0.9316
0.0606	4.0	6252	0.3241	0.9300
0.0449	5.0	7815	0.4178	0.9278
0.032	6.0	9378	0.4681	0.9274
0.0261	7.0	10941	0.4475	0.9303
0.0193	8.0	12504	0.5411	0.9272
0.0222	9.0	14067	0.5159	0.9279
0.018	10.0	15630	0.5166	0.9302
0.009	11.0	17193	0.6404	0.9222
0.0055	12.0	18756	0.5728	0.9298
0.0065	13.0	20319	0.5887	0.9311
0.0023	14.0	21882	0.6744	0.9314
0.0039	15.0	23445	0.6904	0.9309
0.0011	16.0	25008	0.7160	0.9334
0.0017	17.0	26571	0.7068	0.9325
0.0	18.0	28134	0.7238	0.9314
0.0005	19.0	29697	0.7341	0.9331
0.0003	20.0	31260	0.7323	0.9330

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3