Modelpublic

fftristan/finetuned-endpoints_classif_test_2-4_14_1259

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes6downloads

Model Card

finetuned-endpointsclassiftest2-414_1259

This model is a fine-tuned version of ProsusAI/finbert on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.1479
—F1: 0.9533
—Accuracy: 0.9545
—Precision: 0.9593
—Recall: 0.9545

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
—trainbatchsize: 10
—evalbatchsize: 10
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 12
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy	Precision	Recall
1.8576	1.0	19	1.7069	0.2234	0.3864	0.1585	0.3864
1.4072	2.0	38	1.3519	0.4570	0.5227	0.4489	0.5227
1.0111	3.0	57	0.9178	0.7552	0.7955	0.7300	0.7955
0.6001	4.0	76	0.5478	0.7958	0.8409	0.7684	0.8409
0.3433	5.0	95	0.4193	0.8220	0.8409	0.8864	0.8409
0.1889	6.0	114	0.3115	0.8435	0.8636	0.9048	0.8636
0.1132	7.0	133	0.2479	0.9533	0.9545	0.9593	0.9545
0.071	8.0	152	0.1863	0.9531	0.9545	0.9601	0.9545
0.0437	9.0	171	0.1709	0.9533	0.9545	0.9593	0.9545
0.0324	10.0	190	0.1559	0.9533	0.9545	0.9593	0.9545
0.0233	11.0	209	0.1514	0.9533	0.9545	0.9593	0.9545
0.021	12.0	228	0.1479	0.9533	0.9545	0.9593	0.9545

Framework versions

—Transformers 4.28.0
—Pytorch 2.0.0+cu118
—Datasets 2.11.0
—Tokenizers 0.13.3