metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: tiny-mlm-imdb-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: 0.88952
- name: F1
type: f1
value: 0.9415301240526694
tiny-mlm-imdb-target-imdb
This model is a fine-tuned version of muhtasham/tiny-mlm-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.2699
- Accuracy: 0.8895
- F1: 0.9415
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 |
---|---|---|---|---|---|
0.5432 | 0.64 | 500 | 0.3567 | 0.8578 | 0.9235 |
0.366 | 1.28 | 1000 | 0.3687 | 0.8414 | 0.9138 |
0.32 | 1.92 | 1500 | 0.2648 | 0.8922 | 0.9430 |
0.2868 | 2.56 | 2000 | 0.3868 | 0.8314 | 0.9079 |
0.2671 | 3.2 | 2500 | 0.3092 | 0.8774 | 0.9347 |
0.248 | 3.84 | 3000 | 0.2699 | 0.8895 | 0.9415 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2