Modelpublic

Davidozito/fewshot-CDW-CE-250-samples

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes5downloads

Model Card

fewshot-CDW-CE-250-samples

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

—Loss: 1.1342
—Accuracy: 0.52
—F1 Macro: 0.4567
—F1 Weighted: 0.4859
—Precision Macro: 0.4891
—Recall Macro: 0.4833

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: 1e-05
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.1
—num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Recall Macro
1.1607	0.2414	7	1.1334	0.48	0.4406	0.4664	0.48	0.45
1.198	0.4828	14	1.1342	0.52	0.4567	0.4859	0.4891	0.4833
1.0988	0.7241	21	1.1320	0.48	0.4405	0.4777	0.4678	0.4400
1.0673	0.9655	28	1.1304	0.48	0.4405	0.4777	0.4678	0.4400
1.2669	1.2069	35	1.1282	0.48	0.4405	0.4777	0.4678	0.4400
1.0031	1.4483	42	1.1274	0.48	0.4405	0.4777	0.4678	0.4400
1.264	1.6897	49	1.1288	0.48	0.4405	0.4777	0.4678	0.4400
1.0977	1.9310	56	1.1292	0.48	0.4405	0.4777	0.4678	0.4400
1.2181	2.1724	63	1.1300	0.48	0.4405	0.4777	0.4678	0.4400
1.1506	2.4138	70	1.1310	0.48	0.4405	0.4777	0.4678	0.4400
1.0379	2.6552	77	1.1300	0.48	0.4405	0.4777	0.4678	0.4400
1.1612	2.8966	84	1.1277	0.48	0.4405	0.4777	0.4678	0.4400
1.1059	3.1379	91	1.1273	0.48	0.4405	0.4777	0.4678	0.4400
1.1636	3.3793	98	1.1267	0.48	0.4405	0.4777	0.4678	0.4400
1.0985	3.6207	105	1.1266	0.48	0.4405	0.4777	0.4678	0.4400
1.0929	3.8621	112	1.1267	0.48	0.4405	0.4777	0.4678	0.4400
0.9983	4.1034	119	1.1266	0.48	0.4405	0.4777	0.4678	0.4400
1.1553	4.3448	126	1.1266	0.48	0.4405	0.4777	0.4678	0.4400
1.2561	4.5862	133	1.1270	0.48	0.4405	0.4777	0.4678	0.4400
1.0976	4.8276	140	1.1271	0.48	0.4405	0.4777	0.4678	0.4400

Framework versions

—Transformers 4.52.4
—Pytorch 2.7.1
—Datasets 3.6.0
—Tokenizers 0.21.1