The model is trained on a dataset to classify emotions. Users can utilize the model to classify sentences such as "I feel so much joy" or "I feel sad today".

Intended uses & limitations

Ejoy using it and report back please

Training and evaluation data

The model's been trained on around 10000 sentences expressing different emotions such as sadness, joy, trust, etc.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.4836	1.0	144	0.3200	0.9932	0.9932
0.1483	2.0	288	0.0362	0.9994	0.9994
0.04	3.0	432	0.0193	0.9988	0.9988
0.0246	4.0	576	0.0134	0.9988	0.9988
0.0195	5.0	720	0.0121	0.9994	0.9994

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

JIHussain/distilbert-base-uncased-finetuned-emotions

distilbert-base-uncased-finetuned-emotions

Model description