This model is a fine-tuned version of answerdotai/ModernBERT-base on stanfordnlp/imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.3102
Accuracy: 0.938

Model description

This model is a fine-tuned version of ModernBERT, trained to text-classification with english texts.

Intended uses & limitations

This model is intended to classify texts according to their polarity (0, 1) in tasks of sentiment analysis.

Training and evaluation data

'train_loss': 1.7447739664713542

'test_loss': 0.3102864921092987

'test_accuracy': 0.938

Metrics

Informe de clasificación global y detallado de las predicciones hechas por el modelo en función de las clases.

                        precision    recall  f1-score   support
          
                   neg       0.95      0.93      0.94       512
                   pos       0.93      0.95      0.94       488
          
              accuracy                           0.94      1000
             macro avg       0.94      0.94      0.94      1000
          weighted avg       0.94      0.94      0.94      1000

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	50	0.676211	0.90
No log	2.0	100	0.730392	0.90
No log	3.0	150	0.766377	0.905

Framework versions

Transformers 5.3.0
Pytorch 2.10.0+cu128
Datasets 4.7.0
Tokenizers 0.22.2

Jeanievas/clasificador-imdb

clasificador-imdb