Modelpublic

RyuExcalibur/bart-large-mnli-aitools-8n-p

sourceHugging Facemitupdated 4y agoView on Hugging Face

0likes7downloads

Model Card

bart-large-mnli-aitools-8n-p

This model is a fine-tuned version of facebook/bart-large-mnli on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.3997
—Precision: 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
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision
No log	0.07	50	0.5082	0.0
No log	0.14	100	0.5312	0.0
No log	0.21	150	0.3020	0.7895
No log	0.27	200	0.3802	0.8667
No log	0.34	250	0.3721	0.9231
No log	0.41	300	0.3692	0.8
No log	0.48	350	0.4657	1.0
No log	0.55	400	0.5192	0.75
No log	0.62	450	0.4348	0.8667
0.3718	0.68	500	0.3369	0.8421
0.3718	0.75	550	0.3150	0.8889
0.3718	0.82	600	0.2712	1.0
0.3718	0.89	650	0.2900	0.85
0.3718	0.96	700	0.2895	0.9375
0.3718	1.03	750	0.2578	0.7826
0.3718	1.09	800	0.3731	0.9412
0.3718	1.16	850	0.1916	0.8571
0.3718	1.23	900	0.1980	0.85
0.3718	1.3	950	0.3446	0.9412
0.2003	1.37	1000	0.3997	0.9375
0.2003	1.44	1050	0.3500	0.85
0.2003	1.5	1100	0.2820	0.7917
0.2003	1.57	1150	0.3192	0.8947

Framework versions

—Transformers 4.26.1
—Pytorch 1.13.1+cu116
—Datasets 2.9.0
—Tokenizers 0.13.2