pegasus-samsum

drsis/pegasus-samsum

pegasus-samsum is a machine learning model from drsis. 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

2% of all-time downloads

All-time downloads

419

Public

Repo size

4.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin2.3 GB · 100%

At a glance

Library: transformers
Model type: pegasus
Access: Public
Created: Apr 25, 2022
Updated: Apr 25, 2022
SHA: 1db79d3c

Datasets

samsum

Model card

From the Hugging Face model README

pegasus-samsum

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 1.4251

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
3.1284	0.01	10	2.5960
3.122	0.02	20	2.5579
3.0196	0.03	30	2.4983
2.9803	0.04	40	2.4197
2.8471	0.05	50	2.3258
2.7692	0.07	60	2.2438
2.682	0.08	70	2.1608
2.3648	0.09	80	2.0838
2.5696	0.1	90	2.0222
2.3403	0.11	100	1.9713
2.2036	0.12	110	1.9199
2.1998	0.13	120	1.8750
2.3006	0.14	130	1.8382
2.1182	0.15	140	1.8050
2.1493	0.16	150	1.7748
2.0437	0.17	160	1.7494
1.9236	0.18	170	1.7289
2.0114	0.2	180	1.7106
1.9939	0.21	190	1.6906
1.928	0.22	200	1.6737
1.9444	0.23	210	1.6603
1.9071	0.24	220	1.6485
1.8314	0.25	230	1.6369
1.8085	0.26	240	1.6277
1.7493	0.27	250	1.6203
1.8539	0.28	260	1.6089
1.7048	0.29	270	1.5999
1.7486	0.3	280	1.5921
1.795	0.31	290	1.5842
1.6613	0.33	300	1.5815
1.8163	0.34	310	1.5732
1.6133	0.35	320	1.5621
1.8	0.36	330	1.5542
1.7159	0.37	340	1.5506
1.8081	0.38	350	1.5483
1.7365	0.39	360	1.5451
1.7334	0.4	370	1.5405
1.7329	0.41	380	1.5334
1.6923	0.42	390	1.5259
1.6868	0.43	400	1.5227
1.7033	0.45	410	1.5163
1.6805	0.46	420	1.5144
1.6056	0.47	430	1.5126
1.7317	0.48	440	1.5086
1.6303	0.49	450	1.5015
1.7136	0.5	460	1.4943
1.534	0.51	470	1.4910
1.6682	0.52	480	1.4917
1.6234	0.53	490	1.4885
1.7103	0.54	500	1.4857
1.7673	0.55	510	1.4800
1.6631	0.56	520	1.4776
1.7073	0.58	530	1.4745
1.6843	0.59	540	1.4698
1.6849	0.6	550	1.4679
1.6054	0.61	560	1.4642
1.6073	0.62	570	1.4629
1.5896	0.63	580	1.4591
1.608	0.64	590	1.4580
1.58	0.65	600	1.4548
1.5722	0.66	610	1.4548
1.5529	0.67	620	1.4542
1.5948	0.68	630	1.4518
1.5869	0.7	640	1.4489
1.577	0.71	650	1.4488
1.6517	0.72	660	1.4477
1.5955	0.73	670	1.4436
1.5678	0.74	680	1.4402
1.6743	0.75	690	1.4384
1.5791	0.76	700	1.4374
1.6397	0.77	710	1.4380
1.5637	0.78	720	1.4363
1.5849	0.79	730	1.4356
1.5815	0.8	740	1.4350
1.5797	0.81	750	1.4362
1.5551	0.83	760	1.4354
1.5486	0.84	770	1.4341
1.5756	0.85	780	1.4320
1.5326	0.86	790	1.4300
1.6198	0.87	800	1.4290
1.5947	0.88	810	1.4288
1.6326	0.89	820	1.4291
1.6231	0.9	830	1.4288
1.597	0.91	840	1.4281
1.5781	0.92	850	1.4273
1.6835	0.93	860	1.4260
1.5373	0.94	870	1.4257
1.5458	0.96	880	1.4252
1.4953	0.97	890	1.4252
1.5299	0.98	900	1.4252
1.5853	0.99	910	1.4251
1.5723	1.0	920	1.4251

Framework versions

Transformers 4.18.0
Pytorch 1.11.0
Datasets 1.18.4
Tokenizers 0.12.1

Library: transformers
Type: pegasus
Created: Apr 25, 2022
Updated: Apr 25, 2022