metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
  - f1
model-index:
  - name: finetuned-self_mlm_mini
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: imdb
          type: imdb
          config: plain_text
          split: train
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8224
          - name: F1
            type: f1
            value: 0.9025460930640913

finetuned-self_mlm_mini

This model is a fine-tuned version of muhtasham/bert-tiny-mlm-finetuned-imdb on the imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.6150
Accuracy: 0.8224
F1: 0.9025

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: 3e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.4426	2.55	500	0.4673	0.7928	0.8844
0.2845	5.1	1000	0.3099	0.8697	0.9303
0.2282	7.65	1500	0.3432	0.8589	0.9241
0.1819	10.2	2000	0.2702	0.8998	0.9472
0.1461	12.76	2500	0.4852	0.8344	0.9097
0.111	15.31	3000	0.6807	0.7950	0.8858
0.0883	17.86	3500	0.6150	0.8224	0.9025

Framework versions

Transformers 4.25.1
Pytorch 1.12.1+cu113
Datasets 2.7.1
Tokenizers 0.13.2