distilbert-emotion-analysis-v1

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

haidwg/distilbert-emotion-analysis-v1

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

• Train Loss: 0.0510
• Validation Loss: 0.1881
• Train Accuracy: 0.9395
• Train 0 Precision: 0.9674
• Train 0 Recall: 0.9709
• Train 0 F1: 0.9691
• Train 1 Precision: 0.9611
• Train 1 Recall: 0.9474
• Train 1 F1: 0.9542
• Train 2 Precision: 0.8396
• Train 2 Recall: 0.8820
• Train 2 F1: 0.8603
• Train 3 Precision: 0.9734
• Train 3 Recall: 0.9309
• Train 3 F1: 0.9517
• Train 4 Precision: 0.8894
• Train 4 Recall: 0.9104
• Train 4 F1: 0.8998
• Train 5 Precision: 0.8276
• Train 5 Recall: 0.8889
• Train 5 F1: 0.8571
• Train Macro avg Precision: 0.9097
• Train Macro avg Recall: 0.9218
• Train Macro avg F1: 0.9154
• Train Weighted avg Precision: 0.9407
• Train Weighted avg Recall: 0.9395
• Train Weighted avg F1: 0.9399
• Epoch: 4

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': np.float32(2e-05), 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Framework versions

• Transformers 4.53.2
• TensorFlow 2.18.0
• Datasets 4.0.0
• Tokenizers 0.21.2