clasificador-imdb

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

• Loss: 0.6040
• Accuracy: 0.875

Model description

This model was fine-tuned for binary text classification, specifically sentiment analysys of movie reviews. The goal of the model is to classify input into two categories:

• 0 = Negative sentiment
• 1 = Postitive sentiment

The base architecture used is ModernBERT-base, which was adapted through supervised fine-tuning on a subset of the IMDB dataset.

Intended uses & limitations

This model can be used for:

• Sentiment analysys of moviw reviews
• Binary opinion classification (positive vs negative)
• Educational purposes and NLP experimentation

Limitations:

• The model was trained on movie reviews, so performance may decrease on other domains.
• Only a reduced subest of the dataset was used for training.
• The model only predicts two classes (positive or negative), without neutral sentiment.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	100	0.6079	0.845
No log	2.0	200	0.4541	0.875
No log	3.0	300	0.6040	0.875

Framework versions

• Transformers 5.8.1
• Pytorch 2.10.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2