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

Train Loss	Validation Loss	Train Accuracy	Train 0 Precision	Train 0 Recall	Train 0 F1	Train 1 Precision	Train 1 Recall	Train 1 F1	Train 2 Precision	Train 2 Recall	Train 2 F1	Train 3 Precision	Train 3 Recall	Train 3 F1	Train 4 Precision	Train 4 Recall	Train 4 F1	Train 5 Precision	Train 5 Recall	Train 5 F1	Train Macro avg Precision	Train Macro avg Recall	Train Macro avg F1	Train Weighted avg Precision	Train Weighted avg Recall	Train Weighted avg F1	Epoch
0.0974	0.1514	0.936	0.9705	0.9582	0.9643	0.9560	0.9574	0.9567	0.8579	0.8820	0.8698	0.9648	0.8982	0.9303	0.8375	0.9481	0.8894	0.9041	0.8148	0.8571	0.9152	0.9098	0.9113	0.9378	0.936	0.9363	0
0.0834	0.1639	0.932	0.9653	0.9618	0.9636	0.9609	0.9432	0.9520	0.8177	0.8820	0.8486	0.9689	0.9055	0.9361	0.8375	0.9481	0.8894	0.8889	0.7901	0.8366	0.9065	0.9051	0.9044	0.9345	0.932	0.9325	1
0.0687	0.1951	0.933	0.9520	0.9727	0.9622	0.9530	0.9503	0.9516	0.8470	0.8708	0.8587	0.9798	0.88	0.9272	0.8609	0.9340	0.8959	0.8816	0.8272	0.8535	0.9124	0.9058	0.9082	0.9343	0.933	0.9330	2
0.0569	0.1914	0.939	0.9554	0.9727	0.9640	0.9662	0.9347	0.9502	0.8232	0.9157	0.8670	0.9664	0.9418	0.9540	0.8959	0.9340	0.9145	0.9028	0.8025	0.8497	0.9183	0.9169	0.9166	0.9405	0.939	0.9392	3
0.0510	0.1881	0.9395	0.9674	0.9709	0.9691	0.9611	0.9474	0.9542	0.8396	0.8820	0.8603	0.9734	0.9309	0.9517	0.8894	0.9104	0.8998	0.8276	0.8889	0.8571	0.9097	0.9218	0.9154	0.9407	0.9395	0.9399	4

Framework versions

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