metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: medium-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: 0.9064
- name: F1
type: f1
value: 0.9509022240872849
medium-mlm-imdb-target-imdb
This model is a fine-tuned version of muhtasham/medium-mlm-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3883
- Accuracy: 0.9064
- F1: 0.9509
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 |
|---|---|---|---|---|---|
| 0.2923 | 0.64 | 500 | 0.1860 | 0.9310 | 0.9642 |
| 0.2049 | 1.28 | 1000 | 0.0830 | 0.9708 | 0.9852 |
| 0.1569 | 1.92 | 1500 | 0.1258 | 0.9547 | 0.9768 |
| 0.1067 | 2.56 | 2000 | 0.5306 | 0.8643 | 0.9272 |
| 0.0837 | 3.2 | 2500 | 0.3883 | 0.9064 | 0.9509 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2