distilbert-base-uncased-finetuned-emotion

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

• Loss: 0.2992
• Accuracy: 0.9375
• F1: 0.9374
• Precision: 0.9374
• Recall: 0.9375

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6371	1.0	250	0.2255	0.926	0.9266	0.9287	0.926
0.1899	2.0	500	0.1751	0.9335	0.9329	0.9346	0.9335
0.1311	3.0	750	0.1518	0.9345	0.9351	0.9372	0.9345
0.1032	4.0	1000	0.1564	0.938	0.9388	0.9412	0.938
0.0845	5.0	1250	0.1562	0.934	0.9341	0.9355	0.934
0.0689	6.0	1500	0.1656	0.939	0.9389	0.9390	0.939
0.0588	7.0	1750	0.1860	0.937	0.9359	0.9370	0.937
0.042	8.0	2000	0.1991	0.9345	0.9348	0.9355	0.9345
0.034	9.0	2250	0.2233	0.937	0.9369	0.9374	0.937
0.0289	10.0	2500	0.2471	0.934	0.9345	0.9355	0.934
0.0218	11.0	2750	0.2548	0.9335	0.9341	0.9355	0.9335
0.0191	12.0	3000	0.2716	0.938	0.9378	0.9380	0.938
0.0167	13.0	3250	0.2668	0.933	0.9331	0.9334	0.933
0.0145	14.0	3500	0.2862	0.9335	0.9338	0.9346	0.9335
0.015	15.0	3750	0.2794	0.939	0.9392	0.9398	0.939
0.01	16.0	4000	0.2879	0.935	0.9350	0.9350	0.935
0.0092	17.0	4250	0.2939	0.9355	0.9355	0.9356	0.9355
0.0092	18.0	4500	0.2980	0.936	0.9361	0.9365	0.936
0.0075	19.0	4750	0.2978	0.9365	0.9364	0.9365	0.9365
0.0081	20.0	5000	0.2992	0.9375	0.9374	0.9374	0.9375

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1