unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

andreaschandra/unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad is a machine learning model from andreaschandra. 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.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

490

Public

Repo size

6.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin892 MB · 100%

At a glance

Library: transformers
Model type: t5
Access: Public
Created: Nov 16, 2022
Updated: Nov 20, 2022
SHA: 6cadc45b

Model card

From the Hugging Face model README

unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

This model is a fine-tuned version of allenai/unifiedqa-v2-t5-base-1363200 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2574

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.7378	0.05	73	1.1837
0.6984	0.1	146	0.8918
0.4511	0.15	219	0.8342
0.4696	0.2	292	0.7642
0.295	0.25	365	0.7996
0.266	0.3	438	0.7773
0.2372	0.35	511	0.8592
0.2881	0.39	584	0.8440
0.2578	0.44	657	0.8306
0.2733	0.49	730	0.8228
0.2073	0.54	803	0.8419
0.2683	0.59	876	0.8241
0.2693	0.64	949	0.8573
0.355	0.69	1022	0.8204
0.2246	0.74	1095	0.8530
0.2468	0.79	1168	0.8410
0.3102	0.84	1241	0.8035
0.2115	0.89	1314	0.8262
0.1855	0.94	1387	0.8560
0.1772	0.99	1460	0.8747
0.1509	1.04	1533	0.9132
0.1871	1.09	1606	0.8920
0.1624	1.14	1679	0.9085
0.1404	1.18	1752	0.9460
0.1639	1.23	1825	0.9812
0.0983	1.28	1898	0.9790
0.1395	1.33	1971	0.9843
0.1439	1.38	2044	0.9877
0.1397	1.43	2117	1.0338
0.1095	1.48	2190	1.0589
0.1228	1.53	2263	1.0498
0.1246	1.58	2336	1.0923
0.1438	1.63	2409	1.0995
0.1305	1.68	2482	1.0867
0.1077	1.73	2555	1.1013
0.2104	1.78	2628	1.0765
0.1633	1.83	2701	1.0796
0.1658	1.88	2774	1.0314
0.1358	1.92	2847	0.9823
0.1571	1.97	2920	0.9826
0.1127	2.02	2993	1.0324
0.0927	2.07	3066	1.0679
0.0549	2.12	3139	1.1069
0.0683	2.17	3212	1.1624
0.0677	2.22	3285	1.1174
0.0615	2.27	3358	1.1431
0.0881	2.32	3431	1.1721
0.0807	2.37	3504	1.1885
0.0955	2.42	3577	1.1991
0.0779	2.47	3650	1.1999
0.11	2.52	3723	1.1774
0.0852	2.57	3796	1.2095
0.0616	2.62	3869	1.1824
0.072	2.67	3942	1.2397
0.1055	2.71	4015	1.2181
0.0806	2.76	4088	1.2159
0.0684	2.81	4161	1.1864
0.0869	2.86	4234	1.1816
0.1023	2.91	4307	1.1717
0.0583	2.96	4380	1.1477
0.0684	3.01	4453	1.1662
0.0319	3.06	4526	1.2174
0.0609	3.11	4599	1.1947
0.0435	3.16	4672	1.1821
0.0417	3.21	4745	1.1964
0.0502	3.26	4818	1.2140
0.0844	3.31	4891	1.2028
0.0692	3.36	4964	1.2215
0.0366	3.41	5037	1.2136
0.0615	3.46	5110	1.2224
0.0656	3.5	5183	1.2468
0.0469	3.55	5256	1.2554
0.0475	3.6	5329	1.2804
0.0998	3.65	5402	1.2035
0.0505	3.7	5475	1.2095
0.0459	3.75	5548	1.2064
0.0256	3.8	5621	1.2164
0.0831	3.85	5694	1.2154
0.0397	3.9	5767	1.2126
0.0449	3.95	5840	1.2174
0.0322	4.0	5913	1.2288
0.059	4.05	5986	1.2274
0.0382	4.1	6059	1.2228
0.0202	4.15	6132	1.2177
0.0328	4.2	6205	1.2305
0.0407	4.24	6278	1.2342
0.0356	4.29	6351	1.2448
0.0414	4.34	6424	1.2537
0.0448	4.39	6497	1.2540
0.0545	4.44	6570	1.2552
0.0492	4.49	6643	1.2570
0.0293	4.54	6716	1.2594
0.0498	4.59	6789	1.2562
0.0349	4.64	6862	1.2567
0.0497	4.69	6935	1.2550
0.0194	4.74	7008	1.2605
0.0255	4.79	7081	1.2590
0.0212	4.84	7154	1.2571
0.0231	4.89	7227	1.2583
0.0399	4.94	7300	1.2580
0.0719	4.99	7373	1.2574

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.7.0
Tokenizers 0.13.2

Library: transformers
Type: t5
Created: Nov 16, 2022
Updated: Nov 20, 2022