metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: N_bert_imdb_padding80model
    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: 0.93712

N_bert_imdb_padding80model

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

Loss: 0.6996
Accuracy: 0.9371

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
0.2198	1.0	1563	0.2296	0.9239
0.1582	2.0	3126	0.2158	0.9298
0.0896	3.0	4689	0.3067	0.9335
0.0635	4.0	6252	0.3594	0.9304
0.0344	5.0	7815	0.3923	0.9299
0.0315	6.0	9378	0.4625	0.9343
0.0196	7.0	10941	0.4629	0.9338
0.0205	8.0	12504	0.5247	0.9252
0.0161	9.0	14067	0.4549	0.9326
0.0105	10.0	15630	0.4703	0.9323
0.0049	11.0	17193	0.6050	0.9286
0.0088	12.0	18756	0.5788	0.9353
0.0043	13.0	20319	0.5495	0.9348
0.0062	14.0	21882	0.6886	0.9307
0.0019	15.0	23445	0.6479	0.9348
0.0035	16.0	25008	0.6449	0.9360
0.0008	17.0	26571	0.7024	0.9349
0.0003	18.0	28134	0.7011	0.9370
0.001	19.0	29697	0.6921	0.9372
0.0	20.0	31260	0.6996	0.9371

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3