source-role-model

alex2awesome/source-role-model

source-role-model is a machine learning model from alex2awesome. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

13% of all-time downloads

All-time downloads

Public

Repo size

10 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin501 MB · 100%

At a glance

Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Jul 11, 2023
Updated: Jul 11, 2023
SHA: ae8d4245

Model card

From the Hugging Face model README

source-role-model

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

Loss: 2.5543
F1: 0.5814

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
train_batch_size: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	0.12	100	1.0000	0.3391
No log	0.25	200	0.8371	0.5055
No log	0.37	300	0.8684	0.5019
No log	0.49	400	0.8668	0.5208
0.9644	0.62	500	0.8473	0.5422
0.9644	0.74	600	0.8852	0.4956
0.9644	0.86	700	0.8368	0.5124
0.9644	0.99	800	0.7913	0.5848
0.9644	1.11	900	1.0570	0.4950
0.8375	1.23	1000	0.9402	0.5280
0.8375	1.35	1100	0.8023	0.5084
0.8375	1.48	1200	0.9299	0.4807
0.8375	1.6	1300	0.9661	0.5194
0.8375	1.72	1400	0.8014	0.6016
0.8149	1.85	1500	0.8608	0.6105
0.8149	1.97	1600	0.9195	0.5741
0.8149	2.09	1700	1.2378	0.5964
0.8149	2.22	1800	1.0415	0.5902
0.8149	2.34	1900	1.0499	0.5526
0.6932	2.46	2000	1.0600	0.5832
0.6932	2.59	2100	0.9368	0.6074
0.6932	2.71	2200	1.0872	0.6270
0.6932	2.83	2300	1.0912	0.5707
0.6932	2.96	2400	0.8815	0.5602
0.6214	3.08	2500	1.1650	0.5993
0.6214	3.2	2600	1.4485	0.5821
0.6214	3.33	2700	1.5382	0.5775
0.6214	3.45	2800	1.3999	0.5696
0.6214	3.57	2900	1.3702	0.6114
0.5686	3.69	3000	1.3840	0.5635
0.5686	3.82	3100	1.3547	0.5403
0.5686	3.94	3200	1.0283	0.5723
0.5686	4.06	3300	1.3593	0.6242
0.5686	4.19	3400	1.5985	0.6004
0.4807	4.31	3500	1.5351	0.6177
0.4807	4.43	3600	1.4109	0.5779
0.4807	4.56	3700	1.6972	0.5637
0.4807	4.68	3800	1.5336	0.6047
0.4807	4.8	3900	1.7811	0.5909
0.4387	4.93	4000	1.5862	0.5869
0.4387	5.05	4100	1.7106	0.5637
0.4387	5.17	4200	1.5251	0.5624
0.4387	5.3	4300	1.5519	0.5944
0.4387	5.42	4400	1.7315	0.5908
0.3219	5.54	4500	1.7588	0.6015
0.3219	5.67	4600	1.9277	0.5635
0.3219	5.79	4700	1.7663	0.5891
0.3219	5.91	4800	1.8401	0.5917
0.3219	6.03	4900	2.0516	0.5845
0.2311	6.16	5000	2.0510	0.6166
0.2311	6.28	5100	2.1673	0.5732
0.2311	6.4	5200	2.0931	0.5819
0.2311	6.53	5300	2.2803	0.5961
0.2311	6.65	5400	1.9985	0.6010
0.1669	6.77	5500	2.1742	0.5664
0.1669	6.9	5600	2.1021	0.5732
0.1669	7.02	5700	2.2043	0.5641
0.1669	7.14	5800	2.2018	0.5837
0.1669	7.27	5900	2.3575	0.5721
0.1698	7.39	6000	2.4663	0.5662
0.1698	7.51	6100	2.2658	0.5851
0.1698	7.64	6200	2.1585	0.5676
0.1698	7.76	6300	2.1755	0.5774
0.1698	7.88	6400	2.2680	0.5696
0.1378	8.0	6500	2.3505	0.5615
0.1378	8.13	6600	2.2773	0.5705
0.1378	8.25	6700	2.3112	0.5662
0.1378	8.37	6800	2.4572	0.5679
0.1378	8.5	6900	2.4642	0.5766
0.0756	8.62	7000	2.4643	0.5885
0.0756	8.74	7100	2.5096	0.5779
0.0756	8.87	7200	2.4261	0.5789
0.0756	8.99	7300	2.3973	0.5757
0.0756	9.11	7400	2.4137	0.5906
0.0842	9.24	7500	2.4577	0.5844
0.0842	9.36	7600	2.5034	0.5840
0.0842	9.48	7700	2.5176	0.5810
0.0842	9.61	7800	2.5240	0.5852
0.0842	9.73	7900	2.5141	0.5824
0.0634	9.85	8000	2.5482	0.5814
0.0634	9.98	8100	2.5543	0.5814

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3

Library: transformers
Type: roberta
License: mit
Created: Jul 11, 2023
Updated: Jul 11, 2023