iab_classification-finetuned-mnli-finetuned-mnli

This model is a fine-tuned version of mfreihaut/iab_classification-finetuned-mnli-finetuned-mnli on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8711

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	250	1.5956
0.9361	2.0	500	0.0409
0.9361	3.0	750	2.9853
0.7634	4.0	1000	0.1317
0.7634	5.0	1250	0.4056
0.611	6.0	1500	1.8038
0.611	7.0	1750	0.6305
0.5627	8.0	2000	0.6923
0.5627	9.0	2250	3.7410
0.9863	10.0	2500	2.1912
0.9863	11.0	2750	1.5405
1.0197	12.0	3000	1.9271
1.0197	13.0	3250	1.1741
0.5186	14.0	3500	1.1864
0.5186	15.0	3750	0.7945
0.4042	16.0	4000	1.0645
0.4042	17.0	4250	1.8826
0.3637	18.0	4500	0.3234
0.3637	19.0	4750	0.2641
0.3464	20.0	5000	0.8596
0.3464	21.0	5250	0.5601
0.2449	22.0	5500	0.4543
0.2449	23.0	5750	1.1986
0.2595	24.0	6000	0.3642
0.2595	25.0	6250	1.3606
0.298	26.0	6500	0.8154
0.298	27.0	6750	1.1105
0.1815	28.0	7000	0.7443
0.1815	29.0	7250	0.2616
0.165	30.0	7500	0.5318
0.165	31.0	7750	0.7608
0.1435	32.0	8000	0.9647
0.1435	33.0	8250	1.3749
0.1516	34.0	8500	0.7167
0.1516	35.0	8750	0.5426
0.1359	36.0	9000	0.7225
0.1359	37.0	9250	0.5453
0.1266	38.0	9500	0.4825
0.1266	39.0	9750	0.7271
0.1153	40.0	10000	0.9044
0.1153	41.0	10250	1.0363
0.1175	42.0	10500	0.7987
0.1175	43.0	10750	0.7596
0.1089	44.0	11000	0.8637
0.1089	45.0	11250	0.8327
0.1092	46.0	11500	0.7161
0.1092	47.0	11750	0.7768
0.1068	48.0	12000	0.9059
0.1068	49.0	12250	0.8829
0.1045	50.0	12500	0.8711

Framework versions

• Transformers 4.22.1
• Pytorch 1.10.0
• Datasets 2.5.1
• Tokenizers 0.12.1