Modelpublic

legal900428/distilroberta-base-finetuned-5-improve

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes16downloads

Model Card

distilroberta-base-finetuned-5-improve

This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.0000

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: 8
—evalbatchsize: 8
—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
No log	0.13	100	1.3123
No log	0.25	200	0.1606
No log	0.38	300	0.0307
No log	0.5	400	0.0100
1.1473	0.63	500	0.0059
1.1473	0.75	600	0.0039
1.1473	0.88	700	0.0042
1.1473	1.01	800	0.0016
1.1473	1.13	900	0.0019
0.0193	1.26	1000	0.0017
0.0193	1.38	1100	0.0006
0.0193	1.51	1200	0.0010
0.0193	1.64	1300	0.0008
0.0193	1.76	1400	0.0004
0.0077	1.89	1500	0.0003
0.0077	2.01	1600	0.0005
0.0077	2.14	1700	0.0003
0.0077	2.26	1800	0.0001
0.0077	2.39	1900	0.0002
0.0049	2.52	2000	0.0004
0.0049	2.64	2100	0.0003
0.0049	2.77	2200	0.0003
0.0049	2.89	2300	0.0004
0.0049	3.02	2400	0.0002
0.0034	3.14	2500	0.0002
0.0034	3.27	2600	0.0003
0.0034	3.4	2700	0.0001
0.0034	3.52	2800	0.0001
0.0034	3.65	2900	0.0003
0.0025	3.77	3000	0.0003
0.0025	3.9	3100	0.0002
0.0025	4.03	3200	0.0002
0.0025	4.15	3300	0.0002
0.0025	4.28	3400	0.0003
0.0024	4.4	3500	0.0003
0.0024	4.53	3600	0.0002
0.0024	4.65	3700	0.0002
0.0024	4.78	3800	0.0000
0.0024	4.91	3900	0.0000

Framework versions

—Transformers 4.38.2
—Pytorch 2.1.2+cu118
—Datasets 2.18.0
—Tokenizers 0.15.2