my-lora-sum

benitoals/my-lora-sum

my-lora-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

40% of all-time downloads

All-time downloads

Public

Repo size

20.9 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json16.4 MB · 78%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 11, 2025
Updated: Mar 11, 2025
SHA: f6d85d3c

Base models

google/mt5-small

Model card

From the Hugging Face model README

my-lora-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: 5.3452
Rouge1: 2.9750
Rouge2: 0.0640
Rougel: 2.8027
Rougelsum: 2.8035

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
23.6472	0.0160	5	11.7512	0.4881	0.0353	0.4380	0.4362
21.3789	0.0319	10	11.7109	0.4912	0.0353	0.4526	0.4486
19.719	0.0479	15	11.6279	0.5005	0.0432	0.4531	0.4477
22.2901	0.0639	20	11.6000	0.4946	0.0319	0.4410	0.4381
19.6455	0.0799	25	11.5404	0.5263	0.0530	0.4856	0.4833
19.892	0.0958	30	11.5011	0.5202	0.0396	0.4798	0.4716
19.8908	0.1118	35	11.4428	0.5431	0.0429	0.5013	0.4933
21.5179	0.1278	40	11.4066	0.5156	0.0405	0.4717	0.4682
21.7581	0.1438	45	11.3629	0.5416	0.0325	0.4834	0.4787
20.9988	0.1597	50	11.2869	0.5288	0.0270	0.4752	0.4743
21.3311	0.1757	55	11.2290	0.5260	0.0223	0.4642	0.4629
23.6669	0.1917	60	11.1785	0.4932	0.0188	0.4345	0.4307
18.2309	0.2077	65	11.1129	0.4645	0.0193	0.4156	0.4170
20.9785	0.2236	70	11.0331	0.5031	0.0238	0.4532	0.4530
16.4643	0.2396	75	10.9403	0.4414	0.0177	0.3945	0.3899
16.8242	0.2556	80	10.8374	0.4631	0.0177	0.4165	0.4110
23.1133	0.2716	85	10.7508	0.5054	0.0253	0.4434	0.4380
21.1076	0.2875	90	10.6718	0.4766	0.0178	0.4129	0.4101
17.6879	0.3035	95	10.5684	0.5166	0.0212	0.4634	0.4573
19.3182	0.3195	100	10.4315	0.5774	0.0217	0.5121	0.5070
18.6413	0.3355	105	10.2988	0.5325	0.0257	0.4803	0.4803
19.9276	0.3514	110	10.1745	0.5529	0.0348	0.4877	0.4841
17.9226	0.3674	115	10.0297	0.5852	0.0432	0.5075	0.5039
15.9707	0.3834	120	9.8977	0.5779	0.0403	0.5015	0.4992
16.5054	0.3994	125	9.7266	0.5685	0.0416	0.5011	0.4963
14.6994	0.4153	130	9.5595	0.6368	0.0506	0.5492	0.5447
15.9555	0.4313	135	9.3894	0.6401	0.0438	0.5520	0.5465
14.876	0.4473	140	9.2403	0.6910	0.0467	0.5961	0.5929
17.3615	0.4633	145	9.0976	0.7497	0.0499	0.6499	0.6448
15.8582	0.4792	150	8.9385	0.7409	0.0383	0.6427	0.6398
14.4111	0.4952	155	8.7924	0.7075	0.0457	0.6404	0.6366
13.9827	0.5112	160	8.6373	0.6750	0.0446	0.6211	0.6173
17.1081	0.5272	165	8.5070	0.7013	0.0547	0.6479	0.6420
14.2012	0.5431	170	8.3725	0.7220	0.0544	0.6553	0.6525
13.5024	0.5591	175	8.2316	0.7125	0.0324	0.6540	0.6495
13.2137	0.5751	180	8.1178	0.7591	0.0626	0.6776	0.6720
12.6791	0.5911	185	8.0139	0.7564	0.0302	0.6845	0.6840
13.4419	0.6070	190	7.9119	0.7047	0.0277	0.6559	0.6484
13.469	0.6230	195	7.8019	0.7849	0.0268	0.7215	0.7189
12.8491	0.6390	200	7.6875	0.8839	0.0264	0.8145	0.8153
12.8009	0.6550	205	7.5978	0.9797	0.0375	0.8922	0.8930
13.0495	0.6709	210	7.5245	1.0712	0.0504	0.9587	0.9579
12.3307	0.6869	215	7.4464	1.0918	0.0523	1.0047	0.9994
11.1893	0.7029	220	7.3770	1.1632	0.0695	1.0571	1.0527
12.0019	0.7188	225	7.3174	1.1872	0.0522	1.0827	1.0821
10.5739	0.7348	230	7.2509	1.1771	0.0665	1.0618	1.0630
10.7484	0.7508	235	7.1847	1.3403	0.0782	1.1967	1.1933
11.0539	0.7668	240	7.1230	1.4099	0.1009	1.2615	1.2612
10.6808	0.7827	245	7.0601	1.5268	0.0882	1.3528	1.3506
10.0456	0.7987	250	7.0148	1.4664	0.0789	1.3207	1.3142
9.7895	0.8147	255	6.9850	1.6529	0.0969	1.4578	1.4445
9.3146	0.8307	260	6.9547	1.7461	0.0943	1.5750	1.5566
9.8935	0.8466	265	6.9348	1.9384	0.1090	1.7219	1.7093
9.3272	0.8626	270	6.9348	1.8664	0.1143	1.6837	1.6758
9.4551	0.8786	275	6.9497	2.1360	0.1578	1.9404	1.9297
8.7474	0.8946	280	6.9095	2.1561	0.1494	1.9453	1.9398
8.8361	0.9105	285	6.8680	2.1476	0.1304	1.9360	1.9314
10.3327	0.9265	290	6.8129	2.2233	0.1330	1.9752	1.9732
9.6949	0.9425	295	6.7423	2.2698	0.1491	2.0114	2.0057
9.2422	0.9585	300	6.6728	2.2544	0.1332	2.0282	2.0281
9.1457	0.9744	305	6.5924	2.1699	0.1038	1.9641	1.9592
8.4371	0.9904	310	6.5061	2.2267	0.1423	2.0247	2.0174
8.8187	1.0064	315	6.4224	2.3070	0.1251	2.1206	2.1144
8.6228	1.0224	320	6.3316	2.3591	0.1070	2.1583	2.1714
7.9446	1.0383	325	6.2488	2.3552	0.1209	2.1538	2.1659
7.9126	1.0543	330	6.1856	2.3870	0.1292	2.1680	2.1668
8.0568	1.0703	335	6.1166	2.5029	0.1254	2.2559	2.2636
7.5392	1.0863	340	6.0326	2.4650	0.1265	2.2809	2.2768
8.2361	1.1022	345	5.9569	2.4594	0.1041	2.2155	2.2160
7.7452	1.1182	350	5.8964	2.4663	0.0998	2.2324	2.2333
7.6389	1.1342	355	5.8526	2.4997	0.1063	2.2902	2.2822
7.6098	1.1502	360	5.8106	2.6162	0.1157	2.3610	2.3596
7.8916	1.1661	365	5.7841	2.5536	0.0968	2.3276	2.3290
7.5782	1.1821	370	5.7585	2.5692	0.1032	2.3456	2.3406
7.3974	1.1981	375	5.7402	2.5963	0.1286	2.3806	2.3711
7.0614	1.2141	380	5.7159	2.6104	0.0990	2.3693	2.3758
7.2043	1.2300	385	5.6968	2.6200	0.0934	2.3816	2.3891
6.996	1.2460	390	5.6787	2.5952	0.0641	2.4221	2.4286
8.2705	1.2620	395	5.6632	2.6169	0.0403	2.4257	2.4329
7.1852	1.2780	400	5.6461	2.5815	0.0522	2.4163	2.4257
7.1047	1.2939	405	5.6273	2.5892	0.0486	2.4551	2.4584
7.0063	1.3099	410	5.6064	2.5683	0.0327	2.4328	2.4334
6.8297	1.3259	415	5.5840	2.5684	0.0425	2.4205	2.4136
6.7474	1.3419	420	5.5610	2.5945	0.0279	2.4552	2.4478
7.0426	1.3578	425	5.5415	2.5908	0.0120	2.4275	2.4241
6.6945	1.3738	430	5.5259	2.5609	0.0086	2.4019	2.4040
6.8208	1.3898	435	5.5160	2.6132	0.0086	2.4673	2.4634
6.6174	1.4058	440	5.5070	2.6443	0.0187	2.4737	2.4660
6.7205	1.4217	445	5.4988	2.6701	0.0236	2.5099	2.4985
6.6941	1.4377	450	5.4915	2.6858	0.0236	2.5133	2.5047
6.5988	1.4537	455	5.4851	2.6766	0.0349	2.5185	2.5128
6.4683	1.4696	460	5.4767	2.6661	0.0347	2.4922	2.4918
6.7409	1.4856	465	5.4675	2.6519	0.0347	2.5065	2.5077
6.9734	1.5016	470	5.4599	2.6663	0.0431	2.5285	2.5313
6.7049	1.5176	475	5.4536	2.6913	0.0428	2.5617	2.5574
7.1744	1.5335	480	5.4483	2.7426	0.0469	2.5896	2.5873
6.6163	1.5495	485	5.4434	2.7223	0.0428	2.5761	2.5782
6.6025	1.5655	490	5.4381	2.6981	0.0379	2.5405	2.5406
6.4328	1.5815	495	5.4326	2.6555	0.0321	2.5019	2.4957
6.5182	1.5974	500	5.4278	2.7413	0.0445	2.5816	2.5765
6.6248	1.6134	505	5.4226	2.7559	0.0384	2.5907	2.5833
6.4422	1.6294	510	5.4180	2.8097	0.0384	2.6591	2.6516
6.3315	1.6454	515	5.4139	2.8195	0.0345	2.6772	2.6692
6.3602	1.6613	520	5.4077	2.8024	0.0435	2.6610	2.6544
6.3096	1.6773	525	5.4016	2.8611	0.0558	2.7244	2.7161
6.4627	1.6933	530	5.3956	2.8914	0.0558	2.7576	2.7547
7.0027	1.7093	535	5.3912	2.9207	0.0601	2.7619	2.7592
6.6364	1.7252	540	5.3880	2.9260	0.0601	2.7612	2.7558
6.3329	1.7412	545	5.3835	2.9258	0.0631	2.7616	2.7580
6.3528	1.7572	550	5.3783	2.9378	0.0631	2.7630	2.7573
6.3083	1.7732	555	5.3731	2.9500	0.0631	2.7680	2.7632
6.3824	1.7891	560	5.3686	2.9599	0.0681	2.7896	2.7882
6.2145	1.8051	565	5.3646	2.9371	0.0644	2.7612	2.7619
6.5271	1.8211	570	5.3605	2.9350	0.0647	2.7695	2.7717
6.5508	1.8371	575	5.3568	2.9277	0.0524	2.7676	2.7682
6.4093	1.8530	580	5.3551	2.9401	0.0524	2.7711	2.7727
6.5111	1.8690	585	5.3532	2.9682	0.0641	2.7947	2.7934
6.459	1.8850	590	5.3513	2.9682	0.0641	2.7946	2.7933
6.3278	1.9010	595	5.3497	2.9685	0.0641	2.7994	2.7970
6.7423	1.9169	600	5.3486	2.9733	0.0641	2.7993	2.7969
6.5692	1.9329	605	5.3476	2.9732	0.0641	2.8092	2.8055
6.3758	1.9489	610	5.3467	2.9784	0.0640	2.8074	2.8060
6.4735	1.9649	615	5.3460	2.9749	0.0640	2.8028	2.8034
6.2938	1.9808	620	5.3455	2.9749	0.0640	2.8027	2.8033
6.2542	1.9968	625	5.3452	2.9750	0.0640	2.8027	2.8035

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