my-lora-local-combined-sum

benitoals/my-lora-local-combined-sum

my-lora-local-combined-sum is a machine learning model from benitoals. 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 peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

31% of all-time downloads

All-time downloads

Public

Repo size

21.1 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json16.4 MB · 77%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 11, 2025
Updated: Mar 11, 2025
SHA: 0aafad23

Base models

google/mt5-small

Model card

From the Hugging Face model README

my-lora-local-combined-sum

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.3239
Rouge1: 3.1309
Rouge2: 0.1383
Rougel: 2.9320
Rougelsum: 2.9324

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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
23.652	0.0160	5	11.7543	0.5335	0.0402	0.4991	0.4949
21.4941	0.0319	10	11.7207	0.5200	0.0374	0.4762	0.4711
19.422	0.0479	15	11.6789	0.6095	0.0500	0.5583	0.5571
22.1389	0.0639	20	11.6402	0.6042	0.0481	0.5449	0.5407
20.0441	0.0799	25	11.5933	0.6250	0.0374	0.5482	0.5459
19.8832	0.0958	30	11.5414	0.6758	0.0517	0.5900	0.5834
19.6299	0.1118	35	11.4640	0.6860	0.0464	0.6029	0.6038
21.9358	0.1278	40	11.4154	0.6940	0.0536	0.6154	0.6163
22.2149	0.1438	45	11.3558	0.6759	0.0489	0.6079	0.6052
21.5263	0.1597	50	11.2812	0.6470	0.0584	0.5696	0.5700
20.7417	0.1757	55	11.2026	0.6474	0.0542	0.5906	0.5867
23.6982	0.1917	60	11.1133	0.5920	0.0661	0.5417	0.5435
17.6926	0.2077	65	11.0459	0.6807	0.0713	0.6018	0.5990
21.006	0.2236	70	10.9396	0.5966	0.0472	0.5545	0.5506
16.5991	0.2396	75	10.8254	0.6446	0.0594	0.5795	0.5795
16.2146	0.2556	80	10.7155	0.6542	0.0608	0.5892	0.5876
22.3505	0.2716	85	10.6118	0.6909	0.0519	0.6129	0.6082
21.3726	0.2875	90	10.4817	0.6439	0.0595	0.5608	0.5584
16.7014	0.3035	95	10.3467	0.6685	0.0720	0.5853	0.5847
18.2504	0.3195	100	10.2216	0.7344	0.0705	0.6395	0.6370
17.9526	0.3355	105	10.1161	0.7135	0.0850	0.6213	0.6190
19.2727	0.3514	110	10.0225	0.6474	0.0965	0.5498	0.5467
17.3108	0.3674	115	9.8542	0.6541	0.0800	0.5539	0.5547
14.8073	0.3834	120	9.7522	0.6335	0.0599	0.5548	0.5489
16.2244	0.3994	125	9.6181	0.7317	0.0618	0.6425	0.6337
14.5446	0.4153	130	9.5206	0.7480	0.0618	0.6331	0.6282
15.6145	0.4313	135	9.4280	0.7840	0.0915	0.6683	0.6591
14.5598	0.4473	140	9.3180	0.7976	0.0747	0.6857	0.6803
16.626	0.4633	145	9.1933	0.7144	0.0680	0.6037	0.6026
15.2717	0.4792	150	9.0056	0.6882	0.0764	0.5920	0.5917
13.4159	0.4952	155	8.8481	0.7891	0.0724	0.6943	0.6895
14.1487	0.5112	160	8.6840	0.8197	0.0542	0.7087	0.7051
16.2853	0.5272	165	8.5537	0.8577	0.0479	0.7464	0.7425
13.7284	0.5431	170	8.4408	0.8904	0.0404	0.8066	0.8058
13.035	0.5591	175	8.3316	0.9318	0.0634	0.8208	0.8100
12.7887	0.5751	180	8.2053	1.0418	0.0625	0.9095	0.9066
12.2665	0.5911	185	8.0928	1.0168	0.0567	0.8907	0.8891
12.7005	0.6070	190	7.9882	1.1973	0.0850	1.0934	1.0860
12.7293	0.6230	195	7.8489	1.2476	0.0833	1.1583	1.1515
12.1713	0.6390	200	7.6980	1.6482	0.1230	1.4793	1.4661
11.501	0.6550	205	7.5613	1.6241	0.1111	1.4590	1.4586
11.6457	0.6709	210	7.4689	1.8776	0.1296	1.6991	1.6871
11.7026	0.6869	215	7.3935	1.9311	0.1224	1.7739	1.7714
10.5877	0.7029	220	7.3031	2.1049	0.1427	1.8897	1.8797
10.9339	0.7188	225	7.2184	2.2620	0.1604	2.0377	2.0331
9.8031	0.7348	230	7.1438	2.3388	0.1500	2.1312	2.1271
10.2145	0.7508	235	7.0725	2.4207	0.1572	2.1943	2.1750
10.0909	0.7668	240	7.0029	2.4045	0.1427	2.1776	2.1770
9.8222	0.7827	245	6.9333	2.3929	0.1324	2.1964	2.1889
9.0728	0.7987	250	6.8557	2.4630	0.1364	2.2430	2.2337
9.308	0.8147	255	6.7682	2.5453	0.1473	2.3249	2.3172
9.0191	0.8307	260	6.6723	2.6619	0.1206	2.4392	2.4277
9.2552	0.8466	265	6.5731	2.5866	0.1098	2.3381	2.3322
8.7318	0.8626	270	6.4862	2.5568	0.1112	2.3082	2.3006
8.9958	0.8786	275	6.4084	2.5543	0.1102	2.3193	2.3160
8.2857	0.8946	280	6.3348	2.5717	0.1146	2.3284	2.3330
8.3112	0.9105	285	6.2517	2.7736	0.1357	2.5063	2.5098
8.8349	0.9265	290	6.1757	2.7153	0.1111	2.4674	2.4641
8.6952	0.9425	295	6.1052	2.7401	0.1081	2.5038	2.5073
8.5782	0.9585	300	6.0515	2.7391	0.1211	2.5241	2.5096
8.6426	0.9744	305	6.0058	2.7657	0.1443	2.5530	2.5519
8.1808	0.9904	310	5.9701	2.7706	0.1457	2.5485	2.5441
8.3015	1.0064	315	5.9410	2.7316	0.1531	2.5080	2.5072
8.3451	1.0224	320	5.9180	2.6415	0.1317	2.4510	2.4458
7.873	1.0383	325	5.8935	2.6211	0.1097	2.4057	2.4020
7.8035	1.0543	330	5.8663	2.5718	0.0779	2.3788	2.3755
7.4984	1.0703	335	5.8367	2.4868	0.0582	2.3166	2.3104
7.3556	1.0863	340	5.8020	2.4792	0.0550	2.3044	2.2916
8.0786	1.1022	345	5.7732	2.4080	0.0420	2.2622	2.2553
7.5338	1.1182	350	5.7436	2.4495	0.0461	2.2676	2.2592
7.5628	1.1342	355	5.7189	2.5874	0.0641	2.3737	2.3701
7.4467	1.1502	360	5.6907	2.5347	0.0413	2.3525	2.3482
7.6056	1.1661	365	5.6671	2.5697	0.0448	2.3524	2.3528
7.463	1.1821	370	5.6491	2.6025	0.0448	2.3822	2.3773
7.1363	1.1981	375	5.6348	2.5469	0.0357	2.3393	2.3311
7.0927	1.2141	380	5.6140	2.5685	0.0589	2.3623	2.3654
7.0816	1.2300	385	5.5978	2.6166	0.0589	2.4159	2.4212
6.8517	1.2460	390	5.5818	2.6452	0.0499	2.4727	2.4786
8.0498	1.2620	395	5.5675	2.7419	0.0512	2.5631	2.5606
7.0932	1.2780	400	5.5517	2.6195	0.0476	2.4942	2.4895
6.8587	1.2939	405	5.5344	2.5747	0.0391	2.4363	2.4312
6.9344	1.3099	410	5.5205	2.6110	0.0351	2.4583	2.4549
6.7229	1.3259	415	5.5108	2.6736	0.0334	2.5078	2.5052
6.6704	1.3419	420	5.5011	2.6529	0.0289	2.4826	2.4746
6.6762	1.3578	425	5.4873	2.6323	0.0289	2.4645	2.4530
6.6617	1.3738	430	5.4773	2.6210	0.0211	2.4641	2.4561
6.783	1.3898	435	5.4706	2.6646	0.0226	2.4979	2.4957
6.54	1.4058	440	5.4643	2.6527	0.0170	2.4945	2.4867
6.5901	1.4217	445	5.4572	2.6805	0.0170	2.5278	2.5214
6.6093	1.4377	450	5.4519	2.6769	0.0234	2.5196	2.5075
6.5077	1.4537	455	5.4466	2.6851	0.0274	2.5514	2.5439
6.3797	1.4696	460	5.4402	2.6756	0.0270	2.5497	2.5380
6.64	1.4856	465	5.4353	2.7025	0.0423	2.5647	2.5530
6.9645	1.5016	470	5.4311	2.7576	0.0257	2.6191	2.6132
6.6399	1.5176	475	5.4263	2.7655	0.0217	2.6279	2.6225
7.1064	1.5335	480	5.4224	2.7561	0.0217	2.6194	2.6118
6.5318	1.5495	485	5.4186	2.7226	0.0217	2.5902	2.5744
6.6985	1.5655	490	5.4142	2.7083	0.0217	2.5735	2.5629
6.3787	1.5815	495	5.4100	2.7172	0.0217	2.5852	2.5765
6.4844	1.5974	500	5.4051	2.7730	0.0217	2.6503	2.6442
6.5958	1.6134	505	5.4002	2.8511	0.0384	2.7220	2.7149
6.4135	1.6294	510	5.3951	2.8595	0.0409	2.7355	2.7261
6.3097	1.6454	515	5.3896	2.8092	0.0462	2.6927	2.6906
6.3015	1.6613	520	5.3836	2.8498	0.0579	2.7391	2.7357
6.2501	1.6773	525	5.3776	2.8643	0.0612	2.7585	2.7506
6.4105	1.6933	530	5.3714	2.8698	0.0612	2.7576	2.7500
6.9844	1.7093	535	5.3667	2.9023	0.0698	2.7706	2.7640
6.5541	1.7252	540	5.3623	2.9349	0.0733	2.8098	2.8037
6.2722	1.7412	545	5.3579	2.9333	0.0675	2.8005	2.7961
6.3432	1.7572	550	5.3531	3.0079	0.0698	2.8572	2.8527
6.392	1.7732	555	5.3490	3.0083	0.0728	2.8491	2.8482
6.4564	1.7891	560	5.3457	2.9957	0.0699	2.8449	2.8436
6.1712	1.8051	565	5.3425	3.0035	0.0698	2.8504	2.8484
6.4905	1.8211	570	5.3386	3.0050	0.0741	2.8525	2.8527
6.483	1.8371	575	5.3353	3.0098	0.0848	2.8661	2.8604
6.4069	1.8530	580	5.3333	3.0188	0.0817	2.8816	2.8737
6.3736	1.8690	585	5.3318	3.0172	0.0817	2.8718	2.8651
6.3639	1.8850	590	5.3299	3.0201	0.0847	2.8755	2.8717
6.214	1.9010	595	5.3282	3.0291	0.0847	2.8898	2.8852
6.537	1.9169	600	5.3270	3.0432	0.0847	2.9011	2.8966
6.4734	1.9329	605	5.3260	3.0428	0.0908	2.8934	2.8907
6.298	1.9489	610	5.3251	3.0780	0.1251	2.9044	2.9019
6.4594	1.9649	615	5.3245	3.1170	0.1383	2.9269	2.9250
6.2875	1.9808	620	5.3241	3.1276	0.1383	2.9320	2.9324
6.1948	1.9968	625	5.3239	3.1309	0.1383	2.9320	2.9324

Framework versions

PEFT 0.14.0
Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0

Library: peft
License: apache-2.0
Created: Mar 11, 2025
Updated: Mar 11, 2025