metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: mini-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: 0.87528
- name: F1
type: f1
value: 0.9334925984386332
mini-vanilla-target-imdb
This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4773
- Accuracy: 0.8753
- F1: 0.9335
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 |
|---|---|---|---|---|---|
| 0.4272 | 0.64 | 500 | 0.2066 | 0.92 | 0.9583 |
| 0.299 | 1.28 | 1000 | 0.2608 | 0.8906 | 0.9422 |
| 0.2533 | 1.92 | 1500 | 0.1706 | 0.9337 | 0.9657 |
| 0.2126 | 2.56 | 2000 | 0.3601 | 0.8576 | 0.9233 |
| 0.1913 | 3.2 | 2500 | 0.3955 | 0.8594 | 0.9244 |
| 0.1541 | 3.84 | 3000 | 0.1432 | 0.9484 | 0.9735 |
| 0.1432 | 4.48 | 3500 | 0.2027 | 0.9346 | 0.9662 |
| 0.1256 | 5.12 | 4000 | 0.3797 | 0.8898 | 0.9417 |
| 0.1026 | 5.75 | 4500 | 0.4773 | 0.8753 | 0.9335 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2