metadata

license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: N_roberta_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: 0.95048

N_roberta_imdb_padding30model

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

Loss: 0.4323
Accuracy: 0.9505

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
0.2137	1.0	1563	0.2731	0.9326
0.1664	2.0	3126	0.1977	0.9475
0.1079	3.0	4689	0.2742	0.9441
0.0728	4.0	6252	0.2245	0.9474
0.0479	5.0	7815	0.2897	0.9496
0.0405	6.0	9378	0.3329	0.9473
0.0428	7.0	10941	0.3308	0.9452
0.0285	8.0	12504	0.3586	0.9468
0.0242	9.0	14067	0.3599	0.9459
0.0193	10.0	15630	0.3755	0.9444
0.0133	11.0	17193	0.3994	0.9445
0.0178	12.0	18756	0.3940	0.9486
0.0081	13.0	20319	0.4090	0.9479
0.0064	14.0	21882	0.4170	0.9500
0.004	15.0	23445	0.4484	0.9434
0.0031	16.0	25008	0.4368	0.9484
0.0043	17.0	26571	0.4170	0.9496
0.0053	18.0	28134	0.4129	0.9501
0.0026	19.0	29697	0.4325	0.9498
0.0029	20.0	31260	0.4323	0.9505

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3