base-lora-hf

benitoals/base-lora-hf

base-lora-hf 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

19% of all-time downloads

All-time downloads

Public

Repo size

22.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json16.4 MB · 72%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 17, 2025
Updated: Mar 17, 2025
SHA: 4c07f8f4

Base models

google/mt5-base

Model card

From the Hugging Face model README

base-lora-hf

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

Loss: 4.9672
Rouge1: 5.3819
Rouge2: 0.5196
Rougel: 4.7713
Rougelsum: 4.7866

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
19.9845	0.0251	5	20.2996	0.9748	0.2022	0.9325	0.9418
21.4138	0.0503	10	20.5804	0.9695	0.2108	0.9242	0.9322
22.1251	0.0754	15	20.5377	0.9484	0.2108	0.9059	0.9121
21.3367	0.1005	20	20.3529	0.9310	0.1873	0.8883	0.8910
21.8064	0.1256	25	20.1915	0.9299	0.1873	0.8920	0.8878
22.1628	0.1508	30	19.8701	0.9189	0.1867	0.8760	0.8783
19.1129	0.1759	35	19.4976	0.9189	0.1867	0.8760	0.8783
22.7727	0.2010	40	19.3954	0.8863	0.1693	0.8449	0.8450
19.4877	0.2261	45	19.3051	0.8695	0.1693	0.8311	0.8350
22.7237	0.2513	50	19.0373	0.9211	0.1867	0.8840	0.8873
20.0259	0.2764	55	18.8301	0.9075	0.1867	0.8753	0.8772
20.0452	0.3015	60	18.6446	0.9345	0.1867	0.8992	0.9021
19.9441	0.3266	65	18.5094	0.9493	0.1867	0.9210	0.9190
20.6445	0.3518	70	17.7888	0.9241	0.1867	0.8851	0.8835
20.2272	0.3769	75	17.7626	0.8845	0.1867	0.8603	0.8597
19.4512	0.4020	80	17.4225	0.8690	0.1693	0.8451	0.8463
18.6298	0.4271	85	17.2512	0.8690	0.1693	0.8451	0.8463
19.8135	0.4523	90	16.9832	0.8717	0.1693	0.8470	0.8476
18.1969	0.4774	95	16.5094	0.8603	0.1693	0.8375	0.8378
18.2965	0.5025	100	16.2330	0.8725	0.1693	0.8469	0.8480
17.7528	0.5276	105	15.9999	0.9351	0.2016	0.8999	0.9103
18.5468	0.5528	110	15.8200	0.9093	0.2005	0.8722	0.8864
18.5202	0.5779	115	15.2716	0.9639	0.2307	0.9213	0.9236
18.4827	0.6030	120	15.0205	1.0231	0.2307	0.9861	0.9923
18.4432	0.6281	125	14.2666	1.0696	0.2412	1.0329	1.0385
15.5714	0.6533	130	13.8502	1.0922	0.2793	1.0538	1.0591
16.6447	0.6784	135	13.3299	1.1199	0.2929	1.0721	1.0778
16.5493	0.7035	140	13.1941	1.2006	0.2819	1.1359	1.1420
16.5007	0.7286	145	13.0195	1.1336	0.2819	1.0792	1.0843
15.3121	0.7538	150	12.5816	1.0646	0.2355	1.0290	1.0348
15.9766	0.7789	155	12.2410	1.1067	0.2355	1.0669	1.0773
14.5082	0.8040	160	11.9994	1.1207	0.2355	1.0817	1.0943
14.812	0.8291	165	11.5947	1.0905	0.2344	1.0519	1.0659
15.0269	0.8543	170	11.3428	1.0979	0.2357	1.0521	1.0671
14.4106	0.8794	175	11.1049	1.1636	0.2357	1.1055	1.1181
14.1319	0.9045	180	10.7609	1.2215	0.2248	1.1438	1.1535
13.8952	0.9296	185	10.5520	1.2630	0.2248	1.1831	1.1883
12.7063	0.9548	190	10.4312	1.3229	0.2378	1.2448	1.2592
13.4554	0.9799	195	10.2339	1.3215	0.2384	1.2514	1.2582
14.6064	1.0050	200	9.9984	1.3350	0.2384	1.2627	1.2693
12.8018	1.0302	205	9.7809	1.3170	0.2350	1.2483	1.2603
12.6067	1.0553	210	9.5817	1.4603	0.2350	1.3532	1.3609
12.7822	1.0804	215	9.4338	1.5522	0.2447	1.4238	1.4276
12.596	1.1055	220	9.3207	1.5781	0.2436	1.4383	1.4388
11.9216	1.1307	225	9.1564	1.6240	0.2417	1.4953	1.4960
12.0841	1.1558	230	9.0333	1.7191	0.2437	1.5857	1.5886
11.5676	1.1809	235	8.9293	1.6431	0.2437	1.5272	1.5248
11.4117	1.2060	240	8.7542	1.6855	0.2447	1.5391	1.5390
11.1348	1.2312	245	8.5618	1.8631	0.2640	1.7019	1.7125
11.2796	1.2563	250	8.3880	1.8559	0.2379	1.7178	1.7262
10.7728	1.2814	255	8.2453	2.0466	0.2500	1.8301	1.8343
10.7193	1.3065	260	8.0746	2.0877	0.2297	1.8682	1.8809
10.3078	1.3317	265	7.9463	2.1213	0.2118	1.8659	1.8702
9.4906	1.3568	270	7.8111	2.2115	0.1872	1.9316	1.9337
9.7248	1.3819	275	7.7112	2.3184	0.1621	2.0219	2.0422
9.12	1.4070	280	7.6426	2.3553	0.1770	2.0438	2.0638
9.9925	1.4322	285	7.5105	2.2216	0.1630	1.9617	1.9819
9.2764	1.4573	290	7.4422	2.2106	0.1344	2.0391	2.0359
9.0597	1.4824	295	7.3792	2.1439	0.1053	2.0053	1.9983
8.5065	1.5075	300	7.3106	2.0833	0.1089	1.8708	1.8755
8.992	1.5327	305	7.2412	2.0063	0.1084	1.8417	1.8540
8.6069	1.5578	310	7.1944	1.9500	0.1077	1.7940	1.8023
9.0201	1.5829	315	7.1420	2.0260	0.0967	1.8499	1.8535
8.8578	1.6080	320	7.0990	2.1266	0.0860	1.9794	1.9809
8.8284	1.6332	325	7.0596	2.0635	0.0982	1.9106	1.9164
8.3734	1.6583	330	7.0340	1.9703	0.0852	1.8102	1.8107
8.6248	1.6834	335	6.9965	1.8375	0.0843	1.7519	1.7559
8.3218	1.7085	340	6.9770	1.8187	0.0720	1.7496	1.7501
8.3853	1.7337	345	6.9528	1.7610	0.0598	1.6486	1.6470
8.4904	1.7588	350	6.9318	1.6401	0.0486	1.5289	1.5242
8.2582	1.7839	355	6.9122	1.6295	0.0493	1.5232	1.5156
8.5878	1.8090	360	6.8823	1.6154	0.0258	1.5108	1.5050
7.7663	1.8342	365	6.8499	1.5827	0.0258	1.5094	1.5009
8.2	1.8593	370	6.8237	1.6436	0.0258	1.5411	1.5388
7.5589	1.8844	375	6.8067	1.6364	0.0258	1.5458	1.5432
8.1803	1.9095	380	6.7845	1.5375	0.0124	1.4493	1.4461
7.7374	1.9347	385	6.7645	1.5121	0.0124	1.4347	1.4303
7.8814	1.9598	390	6.7452	1.5152	0.0124	1.4376	1.4363
7.6648	1.9849	395	6.7257	1.5162	0.0124	1.4428	1.4339
7.6132	2.0101	400	6.7029	1.5577	0.0124	1.4781	1.4777
7.864	2.0352	405	6.6846	1.6281	0.0124	1.5464	1.5479
7.5629	2.0603	410	6.6705	1.6544	0.0124	1.5745	1.5703
7.6238	2.0854	415	6.6598	1.6077	0.0124	1.5295	1.5295
7.4898	2.1106	420	6.6395	1.6862	0.0124	1.6088	1.6062
7.8069	2.1357	425	6.6117	1.7010	0.0124	1.6381	1.6358
7.4597	2.1608	430	6.5884	1.7218	0.0124	1.6599	1.6582
7.3898	2.1859	435	6.5677	1.7601	0.0124	1.7094	1.7086
7.3911	2.2111	440	6.5463	1.8674	0.0124	1.8057	1.7979
7.1733	2.2362	445	6.5197	1.8953	0.0124	1.8350	1.8341
7.1887	2.2613	450	6.4986	1.9404	0.0124	1.8864	1.8842
7.0774	2.2864	455	6.4825	2.0663	0.0124	2.0050	2.0030
7.2954	2.3116	460	6.4684	2.1557	0.0124	2.0807	2.0742
7.0925	2.3367	465	6.4529	2.2422	0.0124	2.1712	2.1695
7.1943	2.3618	470	6.4348	2.3632	0.0124	2.2752	2.2679
7.0861	2.3869	475	6.4134	2.4368	0.0124	2.3484	2.3430
7.18	2.4121	480	6.3854	2.5631	0.0124	2.4796	2.4720
7.2415	2.4372	485	6.3554	2.6147	0.0124	2.5171	2.5113
7.0627	2.4623	490	6.3225	2.7857	0.0124	2.6762	2.6708
7.2473	2.4874	495	6.2878	2.8660	0.0	2.7604	2.7589
7.1432	2.5126	500	6.2584	3.0089	0.0	2.8942	2.9031
6.8786	2.5377	505	6.2204	3.0677	0.0	2.9803	2.9827
7.2605	2.5628	510	6.1884	3.1637	0.0	3.0661	3.0713
6.8372	2.5879	515	6.1583	3.2234	0.0	3.1330	3.1292
6.9582	2.6131	520	6.1281	3.4104	0.0	3.2578	3.2674
6.834	2.6382	525	6.0949	3.5180	0.0137	3.3648	3.3729
7.065	2.6633	530	6.0598	3.5609	0.0137	3.4115	3.4148
6.8041	2.6884	535	6.0301	3.6212	0.0263	3.4610	3.4601
7.0177	2.7136	540	6.0045	3.6462	0.0263	3.4834	3.4829
6.7565	2.7387	545	5.9789	3.6683	0.0263	3.5033	3.5079
6.6908	2.7638	550	5.9469	3.6961	0.0263	3.5384	3.5331
6.6701	2.7889	555	5.9122	3.8271	0.0398	3.6780	3.6719
6.703	2.8141	560	5.8798	3.9789	0.0399	3.8203	3.8054
6.7734	2.8392	565	5.8518	4.0644	0.0533	3.9002	3.9022
6.8523	2.8643	570	5.8196	4.0991	0.0653	3.9677	3.9648
6.477	2.8894	575	5.7907	4.1666	0.0914	4.0340	4.0302
6.8284	2.9146	580	5.7659	4.1567	0.0914	4.0088	4.0067
6.8174	2.9397	585	5.7360	4.2228	0.0914	4.0340	4.0372
6.7112	2.9648	590	5.7117	4.2814	0.0915	4.0661	4.0639
6.5568	2.9899	595	5.6804	4.3052	0.1413	4.0651	4.0724
6.4933	3.0151	600	5.6472	4.3145	0.1273	4.0867	4.0873
6.3	3.0402	605	5.5958	4.2657	0.1510	4.0182	4.0272
6.5645	3.0653	610	5.5545	4.2810	0.1695	4.0035	3.9989
6.5585	3.0905	615	5.5188	4.3714	0.1699	4.1262	4.1184
6.5803	3.1156	620	5.4954	4.3159	0.1574	4.0346	4.0352
6.3667	3.1407	625	5.4669	4.4380	0.1829	4.1416	4.1304
6.4128	3.1658	630	5.4418	4.4830	0.1828	4.1453	4.1436
6.2	3.1910	635	5.4183	4.5121	0.1953	4.1746	4.1750
6.2363	3.2161	640	5.3853	4.6840	0.2092	4.3241	4.3157
6.3394	3.2412	645	5.3572	4.6549	0.1969	4.3112	4.3093
6.3711	3.2663	650	5.3348	4.8189	0.2395	4.4461	4.4309
6.3356	3.2915	655	5.3154	4.7549	0.2282	4.3740	4.3551
6.2359	3.3166	660	5.2990	4.7922	0.2556	4.3994	4.3842
6.1759	3.3417	665	5.2830	4.9007	0.2765	4.4718	4.4659
6.5212	3.3668	670	5.2652	4.8672	0.2772	4.4498	4.4419
6.3572	3.3920	675	5.2523	4.8740	0.2921	4.4736	4.4664
6.142	3.4171	680	5.2297	4.8456	0.3048	4.4642	4.4639
6.2698	3.4422	685	5.2075	4.9942	0.3382	4.5893	4.5796
6.1898	3.4673	690	5.1786	5.0596	0.3377	4.6012	4.6013
6.1935	3.4925	695	5.1579	5.1421	0.3352	4.6368	4.6311
6.0207	3.5176	700	5.1373	5.1597	0.3198	4.6450	4.6314
6.2054	3.5427	705	5.1142	5.3065	0.3589	4.7477	4.7568
6.0647	3.5678	710	5.0953	5.3270	0.4192	4.7751	4.7847
6.2467	3.5930	715	5.0779	5.3485	0.4558	4.7980	4.8109
6.2021	3.6181	720	5.0642	5.3178	0.4558	4.7720	4.7920
6.1525	3.6432	725	5.0512	5.2626	0.4670	4.7375	4.7532
5.9856	3.6683	730	5.0375	5.3317	0.4597	4.7651	4.7658
6.3415	3.6935	735	5.0281	5.2917	0.4597	4.7487	4.7482
5.9981	3.7186	740	5.0204	5.2751	0.4597	4.7114	4.7088
6.1648	3.7437	745	5.0091	5.2866	0.4597	4.7184	4.7199
6.1724	3.7688	750	5.0011	5.3533	0.4597	4.7817	4.7842
6.0231	3.7940	755	4.9939	5.3533	0.4597	4.7817	4.7842
5.9608	3.8191	760	4.9870	5.4313	0.4952	4.8477	4.8522
6.1358	3.8442	765	4.9817	5.4523	0.5043	4.8543	4.8664
6.061	3.8693	770	4.9765	5.5196	0.5196	4.8860	4.8956
6.2685	3.8945	775	4.9726	5.4864	0.5196	4.8490	4.8594
6.0714	3.9196	780	4.9702	5.4314	0.5196	4.8078	4.8230
6.1423	3.9447	785	4.9686	5.3819	0.5196	4.7713	4.7866
5.931	3.9698	790	4.9676	5.4160	0.5196	4.8078	4.8230
6.148	3.9950	795	4.9672	5.3819	0.5196	4.7713	4.7866

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 17, 2025
Updated: Mar 17, 2025