finetuned_bert_sentiment_classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9785
• Accuracy: 0.78

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	68	0.6297	0.73
No log	2.0	136	0.9044	0.73
No log	3.0	204	1.2008	0.78
No log	4.0	272	1.4143	0.75
No log	5.0	340	1.4934	0.76
No log	6.0	408	1.5581	0.765
No log	7.0	476	1.6158	0.78
0.1371	8.0	544	1.6786	0.785
0.1371	9.0	612	1.7112	0.78
0.1371	10.0	680	1.7416	0.78
0.1371	11.0	748	1.7667	0.78
0.1371	12.0	816	1.7937	0.78
0.1371	13.0	884	1.8139	0.78
0.1371	14.0	952	1.8347	0.78
0.0002	15.0	1020	1.8531	0.785
0.0002	16.0	1088	1.8645	0.78
0.0002	17.0	1156	1.8798	0.78
0.0002	18.0	1224	1.8964	0.78
0.0002	19.0	1292	1.9097	0.78
0.0002	20.0	1360	1.9206	0.78
0.0002	21.0	1428	1.9310	0.78
0.0002	22.0	1496	1.9410	0.78
0.0001	23.0	1564	1.9494	0.78
0.0001	24.0	1632	1.9566	0.78
0.0001	25.0	1700	1.9628	0.78
0.0001	26.0	1768	1.9681	0.78
0.0001	27.0	1836	1.9730	0.78
0.0001	28.0	1904	1.9761	0.78
0.0001	29.0	1972	1.9779	0.78
0.0	30.0	2040	1.9785	0.78

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0