my-finetuned-emotion-distilbert

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

my-finetuned-emotion-distilbert

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

• Loss: 0.4044

• Accuracy: 0.8360

• F1: 0.8351

• Precision: 0.8350

• Recall: 0.8360

• Classification Report: precision recall f1-score support

  Class 0 0.84 0.87 0.86 87 Class 1 0.85 0.87 0.86 268 Class 2 0.80 0.75 0.77 151

  accuracy 0.84 506 macro avg 0.83 0.83 0.83 506 weighted avg 0.84 0.84 0.84 506

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

 Class 0       0.83      0.78      0.80        87
 Class 1       0.80      0.89      0.84       268
 Class 2       0.76      0.64      0.70       151

accuracy                           0.80       506

macro avg 0.80 0.77 0.78 506 weighted avg 0.79 0.80 0.79 506 | | 0.4627 | 2.0 | 144 | 0.4044 | 0.8360 | 0.8351 | 0.8350 | 0.8360 | precision recall f1-score support

 Class 0       0.84      0.87      0.86        87
 Class 1       0.85      0.87      0.86       268
 Class 2       0.80      0.75      0.77       151

accuracy                           0.84       506

macro avg 0.83 0.83 0.83 506 weighted avg 0.84 0.84 0.84 506 |

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.2
• Datasets 2.20.0
• Tokenizers 0.19.1