metadata

license: mit
base_model: microsoft/MiniLM-L12-H384-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: minilm-imdb
    results:
      - task:
          name: text-classification
          type: text-classification
        dataset:
          name: imdb
          type: imdb
          config: default
          split: train
          args: default
        metrics:
          - name: accuracy
            type: accuracy
            value: 0.92288
          - name: f1
            type: f1
            value: 0.922831
datasets:
  - imdb
language:
  - en
pipeline_tag: text-classification

minilm-imdb

This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.2403
Accuracy: 0.9229
F1: 0.9228

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: 4
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.1511	1.0	293	0.2212	0.9234	0.9229
0.1047	2.0	586	0.2211	0.9230	0.9217
0.1008	3.0	879	0.2403	0.9229	0.9228

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.0
Tokenizers 0.15.0