metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: base-vanilla-target-imdb
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: 0.9604
- name: F1
type: f1
value: 0.9798000408079984
base-vanilla-target-imdb
This model is a fine-tuned version of google/bert_uncased_L-12_H-768_A-12 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1564
- Accuracy: 0.9604
- F1: 0.9798
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: 32
- eval_batch_size: 32
- 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 |
---|---|---|---|---|---|
0.2549 | 0.64 | 500 | 0.2049 | 0.9234 | 0.9602 |
0.1771 | 1.28 | 1000 | 0.0750 | 0.9763 | 0.9880 |
0.1271 | 1.92 | 1500 | 0.0871 | 0.9707 | 0.9851 |
0.0755 | 2.56 | 2000 | 0.3361 | 0.9235 | 0.9602 |
0.0631 | 3.2 | 2500 | 0.1564 | 0.9604 | 0.9798 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2