metadata

base_model: choidf/finetuning-sentiment-model-bert-base-25000-samples
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
  - f1
model-index:
  - name: finetuning-sentiment-model-bert-base-25000-samples
    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: 0.9308
          - name: F1
            type: f1
            value: 0.9325009754194303

finetuning-sentiment-model-bert-base-25000-samples

This model is a fine-tuned version of choidf/finetuning-sentiment-model-bert-base-25000-samples on the imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.5129
Accuracy: 0.9308
F1: 0.9325

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0535	1.0	1407	0.4188	0.9224	0.9222
0.0324	2.0	2814	0.4382	0.928	0.9288
0.0201	3.0	4221	0.4542	0.928	0.9308
0.0202	4.0	5628	0.4747	0.9296	0.9321
0.0057	5.0	7035	0.5129	0.9308	0.9325

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1