my-lora

benitoals/my-lora

my-lora 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

20% of all-time downloads

All-time downloads

Public

Repo size

21.3 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: fd664475

Base models

google/mt5-small

Model card

From the Hugging Face model README

my-lora

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: 4.4558
Rouge1: 6.9916
Rouge2: 0.6816
Rougel: 5.7118
Rougelsum: 5.7018

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
23.6756	0.0160	5	11.7300	0.4936	0.0298	0.4390	0.4355
21.3163	0.0319	10	11.6817	0.5950	0.0303	0.5441	0.5398
19.4831	0.0479	15	11.6197	0.5874	0.0422	0.5365	0.5379
22.1207	0.0639	20	11.5248	0.5548	0.0413	0.5229	0.5198
19.8132	0.0799	25	11.4054	0.5510	0.0240	0.5010	0.4974
20.1565	0.0958	30	11.3720	0.6226	0.0216	0.5805	0.5763
19.7845	0.1118	35	11.3636	0.6424	0.0370	0.5877	0.5833
21.83	0.1278	40	11.3292	0.6306	0.0416	0.5777	0.5757
22.8683	0.1438	45	11.2816	0.6071	0.0340	0.5619	0.5612
21.5372	0.1597	50	11.2166	0.6361	0.0311	0.5761	0.5722
20.4096	0.1757	55	11.1637	0.6519	0.0339	0.5762	0.5752
23.4684	0.1917	60	11.1275	0.6089	0.0326	0.5266	0.5304
18.1937	0.2077	65	11.0679	0.6298	0.0284	0.5691	0.5679
20.9906	0.2236	70	11.0010	0.6016	0.0294	0.5618	0.5626
16.9343	0.2396	75	10.9141	0.6042	0.0341	0.5629	0.5605
16.213	0.2556	80	10.8014	0.5869	0.0341	0.5468	0.5422
23.0994	0.2716	85	10.6858	0.6965	0.0399	0.6411	0.6366
21.3159	0.2875	90	10.5525	0.7669	0.0560	0.6992	0.6939
17.8493	0.3035	95	10.4093	0.7420	0.0527	0.6913	0.6831
18.3706	0.3195	100	10.2754	0.7243	0.0332	0.6716	0.6648
18.2941	0.3355	105	10.1246	0.7495	0.0387	0.6865	0.6772
19.6502	0.3514	110	9.9765	0.7874	0.0579	0.7173	0.7144
17.7381	0.3674	115	9.8496	0.7391	0.0366	0.6777	0.6765
15.6761	0.3834	120	9.7321	0.8022	0.0563	0.7337	0.7291
16.2067	0.3994	125	9.6046	0.7913	0.0531	0.7319	0.7289
13.8577	0.4153	130	9.4678	0.8529	0.0571	0.7788	0.7763
15.4965	0.4313	135	9.3599	0.8251	0.0542	0.7540	0.7478
14.362	0.4473	140	9.2515	0.8661	0.0632	0.7880	0.7862
17.1324	0.4633	145	9.0933	0.8565	0.0416	0.8081	0.8043
15.5484	0.4792	150	8.9389	0.8524	0.0501	0.7688	0.7655
13.7671	0.4952	155	8.7882	0.9513	0.0701	0.8614	0.8538
14.2473	0.5112	160	8.6085	0.9936	0.0760	0.8882	0.8819
16.2646	0.5272	165	8.4261	1.0280	0.0825	0.9123	0.9112
14.422	0.5431	170	8.2682	0.9989	0.0732	0.9057	0.9046
12.8457	0.5591	175	8.1451	1.1030	0.0744	0.9912	0.9920
13.1231	0.5751	180	8.0125	1.2091	0.0769	1.0877	1.0854
12.4348	0.5911	185	7.8906	1.2220	0.0873	1.1092	1.1044
12.7066	0.6070	190	7.7846	1.2845	0.0905	1.1493	1.1445
12.6802	0.6230	195	7.6824	1.2024	0.0764	1.0739	1.0730
12.6226	0.6390	200	7.5869	1.2994	0.1020	1.1752	1.1781
11.7003	0.6550	205	7.4930	1.3573	0.0789	1.2515	1.2518
11.7344	0.6709	210	7.4188	1.3916	0.0922	1.2819	1.2819
11.7628	0.6869	215	7.3503	1.4452	0.0918	1.3172	1.3105
10.2049	0.7029	220	7.2817	1.6040	0.0990	1.4637	1.4567
10.803	0.7188	225	7.2149	1.8393	0.1138	1.6247	1.6199
10.014	0.7348	230	7.1472	1.9519	0.1254	1.7554	1.7515
10.6801	0.7508	235	7.0828	2.1037	0.1414	1.8470	1.8434
10.0471	0.7668	240	7.0481	2.0665	0.1527	1.7971	1.7958
9.7399	0.7827	245	7.0096	2.0347	0.1374	1.7735	1.7707
9.1483	0.7987	250	6.9719	2.1064	0.0887	1.8688	1.8726
8.8226	0.8147	255	6.9016	2.3382	0.1402	2.0657	2.0607
8.6236	0.8307	260	6.8058	2.2605	0.1258	2.0048	1.9982
8.8137	0.8466	265	6.7130	2.4050	0.1255	2.1567	2.1508
8.4192	0.8626	270	6.6078	2.4312	0.0998	2.2026	2.1954
8.3304	0.8786	275	6.4693	2.5363	0.1506	2.3432	2.3501
8.0673	0.8946	280	6.3136	2.5803	0.1364	2.3812	2.3723
7.8489	0.9105	285	6.1742	2.5226	0.1223	2.3425	2.3377
8.9521	0.9265	290	6.0328	2.5598	0.1001	2.3583	2.3461
7.6618	0.9425	295	5.8830	2.7390	0.1270	2.5325	2.5231
7.6692	0.9585	300	5.7741	2.7669	0.0933	2.5127	2.5096
7.9787	0.9744	305	5.7020	2.7929	0.0678	2.5641	2.5689
7.577	0.9904	310	5.6454	2.7002	0.0625	2.4869	2.4944
7.7221	1.0064	315	5.6025	2.7943	0.0410	2.5835	2.5853
7.3943	1.0224	320	5.5779	2.8294	0.0574	2.6103	2.6068
7.2515	1.0383	325	5.5558	2.6871	0.0391	2.5212	2.5114
7.13	1.0543	330	5.5428	2.7466	0.0538	2.5637	2.5593
6.7682	1.0703	335	5.5243	2.5682	0.0561	2.4248	2.4171
6.6841	1.0863	340	5.5019	2.5695	0.0390	2.4028	2.3910
7.061	1.1022	345	5.4904	2.6353	0.0232	2.4626	2.4600
6.8416	1.1182	350	5.4781	2.7188	0.0364	2.5442	2.5418
6.833	1.1342	355	5.4651	2.7963	0.0946	2.6191	2.6053
6.6498	1.1502	360	5.4439	2.7616	0.0794	2.5699	2.5632
6.5082	1.1661	365	5.4256	2.8136	0.0643	2.6238	2.6181
6.7253	1.1821	370	5.4129	2.8281	0.0564	2.6235	2.6203
6.3954	1.1981	375	5.3968	2.9543	0.0471	2.7386	2.7316
6.381	1.2141	380	5.3664	3.0891	0.1198	2.8635	2.8481
6.2691	1.2300	385	5.3405	3.1817	0.0991	2.9678	2.9600
6.3465	1.2460	390	5.3137	3.2596	0.0955	3.0371	3.0193
7.5564	1.2620	395	5.2915	3.4445	0.1965	3.2355	3.2178
6.297	1.2780	400	5.2659	3.3451	0.1735	3.1460	3.1341
6.0585	1.2939	405	5.2356	3.5268	0.1811	3.2960	3.2930
6.146	1.3099	410	5.2035	3.5298	0.2186	3.3129	3.3068
5.8611	1.3259	415	5.1748	3.5515	0.2134	3.3375	3.3356
6.1246	1.3419	420	5.1458	3.5293	0.1791	3.3109	3.3109
5.941	1.3578	425	5.1199	3.6252	0.1844	3.3822	3.3820
5.9336	1.3738	430	5.0968	3.7394	0.2487	3.4850	3.4839
6.0573	1.3898	435	5.0772	3.8920	0.2854	3.5845	3.5833
5.8787	1.4058	440	5.0583	3.9947	0.3167	3.7099	3.7060
5.742	1.4217	445	5.0390	4.2624	0.3612	3.9232	3.9237
5.9164	1.4377	450	5.0187	4.5394	0.3685	4.1808	4.1667
5.8206	1.4537	455	4.9996	4.7519	0.4171	4.3353	4.3228
5.7587	1.4696	460	4.9800	4.8192	0.4494	4.4227	4.4091
5.782	1.4856	465	4.9617	4.8078	0.4496	4.3912	4.3769
6.0275	1.5016	470	4.9466	4.8523	0.5041	4.4154	4.3983
5.9688	1.5176	475	4.9314	4.8285	0.4628	4.4055	4.3831
6.2916	1.5335	480	4.9161	4.8893	0.4697	4.4384	4.4320
5.8275	1.5495	485	4.9018	4.8905	0.4666	4.4296	4.4204
5.7246	1.5655	490	4.8863	4.8774	0.4725	4.4002	4.3823
5.6779	1.5815	495	4.8671	4.7665	0.4170	4.2980	4.2936
5.6032	1.5974	500	4.8466	4.9297	0.4819	4.4265	4.4229
5.8246	1.6134	505	4.8283	5.0824	0.4941	4.4664	4.4746
5.6855	1.6294	510	4.8129	5.0445	0.5022	4.4670	4.4665
5.4763	1.6454	515	4.7979	5.1488	0.4781	4.5613	4.5503
5.5418	1.6613	520	4.7839	5.3006	0.4677	4.7011	4.6898
5.489	1.6773	525	4.7723	5.3246	0.4893	4.7215	4.7127
5.6303	1.6933	530	4.7623	5.5604	0.5124	4.8999	4.8991
6.2405	1.7093	535	4.7547	5.5092	0.4656	4.8064	4.7866
5.8127	1.7252	540	4.7469	5.5956	0.5156	4.8723	4.8640
5.5919	1.7412	545	4.7389	5.6788	0.5618	4.9519	4.9475
5.574	1.7572	550	4.7309	5.7099	0.5667	5.0054	4.9991
5.415	1.7732	555	4.7239	5.6398	0.5503	4.8735	4.8653
5.5172	1.7891	560	4.7158	5.5743	0.4962	4.8134	4.7998
5.3554	1.8051	565	4.7086	5.6326	0.5413	4.7946	4.7893
5.632	1.8211	570	4.6997	5.6395	0.5585	4.8162	4.8135
5.6441	1.8371	575	4.6913	5.6594	0.5934	4.8383	4.8440
5.6121	1.8530	580	4.6848	5.7094	0.6287	4.8887	4.8955
5.6247	1.8690	585	4.6811	5.7092	0.5953	4.8865	4.8931
5.5127	1.8850	590	4.6774	5.7369	0.6294	4.9060	4.9123
5.3986	1.9010	595	4.6725	5.8236	0.6239	5.0256	5.0308
5.3653	1.9169	600	4.6657	5.8826	0.6295	5.0282	5.0357
5.5225	1.9329	605	4.6599	5.8561	0.6483	5.0548	5.0661
5.4748	1.9489	610	4.6542	5.8777	0.6013	5.0208	5.0236
5.4552	1.9649	615	4.6488	5.8850	0.6102	4.9776	4.9827
5.4006	1.9808	620	4.6435	5.8263	0.5668	4.9280	4.9319
5.2525	1.9968	625	4.6374	5.8090	0.5567	4.8903	4.8934
5.3651	2.0128	630	4.6327	5.8141	0.5850	4.8955	4.9018
5.3102	2.0288	635	4.6288	5.7891	0.6054	4.9275	4.9390
5.4252	2.0447	640	4.6243	5.7595	0.5903	4.9053	4.9143
5.623	2.0607	645	4.6207	5.8272	0.5991	4.9243	4.9271
5.9216	2.0767	650	4.6182	5.7977	0.5746	4.8630	4.8650
5.2885	2.0927	655	4.6160	5.8832	0.6089	4.9655	4.9590
5.4478	2.1086	660	4.6143	6.1030	0.6493	5.1520	5.1469
5.4389	2.1246	665	4.6138	6.2193	0.6379	5.2267	5.2330
5.3506	2.1406	670	4.6115	6.2155	0.6610	5.2507	5.2505
5.2738	2.1565	675	4.6067	6.4144	0.6590	5.3567	5.3562
5.2637	2.1725	680	4.6028	6.6140	0.6895	5.5451	5.5404
5.4674	2.1885	685	4.5991	6.6112	0.6680	5.5371	5.5289
5.4239	2.2045	690	4.5962	6.6814	0.6930	5.6114	5.6027
5.5427	2.2204	695	4.5940	6.6225	0.6488	5.5083	5.5054
5.33	2.2364	700	4.5913	6.5749	0.6924	5.4796	5.4663
5.326	2.2524	705	4.5876	6.5141	0.6854	5.4379	5.4275
5.1821	2.2684	710	4.5827	6.5709	0.7154	5.4791	5.4750
5.3379	2.2843	715	4.5779	6.6474	0.7288	5.5817	5.5757
5.5842	2.3003	720	4.5742	6.6228	0.6962	5.5504	5.5346
5.3523	2.3163	725	4.5706	6.6456	0.7115	5.5543	5.5382
5.3367	2.3323	730	4.5668	6.6447	0.7167	5.5495	5.5403
5.3159	2.3482	735	4.5639	6.6856	0.7344	5.6046	5.5874
5.2955	2.3642	740	4.5617	6.6819	0.7438	5.6109	5.5915
5.3509	2.3802	745	4.5588	6.6925	0.7367	5.6635	5.6420
5.4309	2.3962	750	4.5564	6.6572	0.7239	5.6270	5.6078
5.3232	2.4121	755	4.5549	6.6658	0.7242	5.6407	5.6248
5.3663	2.4281	760	4.5545	6.6939	0.7227	5.6980	5.6823
5.2839	2.4441	765	4.5528	6.6417	0.7172	5.6179	5.6046
5.1068	2.4601	770	4.5507	6.6977	0.7300	5.6509	5.6364
5.2285	2.4760	775	4.5483	6.6988	0.7397	5.6623	5.6474
5.3325	2.4920	780	4.5455	6.6992	0.7395	5.6787	5.6597
5.2692	2.5080	785	4.5423	6.7269	0.7354	5.6832	5.6717
5.2416	2.5240	790	4.5402	6.6987	0.7277	5.6825	5.6674
5.2668	2.5399	795	4.5380	6.7267	0.7257	5.7369	5.7216
5.3415	2.5559	800	4.5363	6.7654	0.7323	5.7682	5.7448
5.2675	2.5719	805	4.5346	6.9076	0.7348	5.8630	5.8460
5.1813	2.5879	810	4.5333	6.9111	0.7139	5.8215	5.8088
5.3719	2.6038	815	4.5319	6.9676	0.7501	5.8938	5.8751
5.2826	2.6198	820	4.5296	6.9759	0.7424	5.9081	5.8935
5.2366	2.6358	825	4.5281	6.9508	0.7371	5.8471	5.8354
5.1769	2.6518	830	4.5276	6.9875	0.7161	5.8823	5.8731
5.2484	2.6677	835	4.5270	6.9863	0.7222	5.8866	5.8754
5.2323	2.6837	840	4.5263	6.9414	0.6963	5.8284	5.8195
5.1327	2.6997	845	4.5240	6.9841	0.6984	5.8296	5.8195
5.138	2.7157	850	4.5209	7.0102	0.7134	5.8757	5.8637
5.1938	2.7316	855	4.5168	6.9719	0.7021	5.8537	5.8429
5.1618	2.7476	860	4.5136	6.8674	0.6884	5.7749	5.7624
5.1931	2.7636	865	4.5116	6.8026	0.6750	5.7132	5.7083
5.0372	2.7796	870	4.5097	6.7480	0.6611	5.6958	5.6879
5.2144	2.7955	875	4.5084	6.7780	0.6605	5.7056	5.6933
5.3514	2.8115	880	4.5070	6.7706	0.6476	5.7317	5.7224
5.3267	2.8275	885	4.5049	6.7649	0.6556	5.7269	5.7248
5.2012	2.8435	890	4.5025	6.7671	0.6727	5.7185	5.7078
5.231	2.8594	895	4.5000	6.7752	0.6605	5.7131	5.7062
5.5058	2.8754	900	4.4982	6.8061	0.6414	5.7308	5.7243
5.1725	2.8914	905	4.4971	6.7574	0.6312	5.6988	5.6969
5.1605	2.9073	910	4.4953	6.7771	0.6541	5.7257	5.7234
5.205	2.9233	915	4.4932	6.7896	0.6608	5.7603	5.7574
5.3089	2.9393	920	4.4916	6.7881	0.6504	5.7507	5.7542
5.2994	2.9553	925	4.4903	6.7905	0.6427	5.7104	5.7157
5.0648	2.9712	930	4.4885	6.7691	0.6338	5.7117	5.7143
5.1906	2.9872	935	4.4870	6.7841	0.6414	5.7250	5.7231
5.2381	3.0032	940	4.4852	6.8148	0.6582	5.7312	5.7279
5.2319	3.0192	945	4.4837	6.8141	0.6613	5.7176	5.7204
5.1976	3.0351	950	4.4823	6.7903	0.6651	5.6967	5.6950
5.0499	3.0511	955	4.4804	6.8182	0.6681	5.7180	5.7155
5.2995	3.0671	960	4.4784	6.8703	0.6622	5.7614	5.7628
5.1794	3.0831	965	4.4767	6.8704	0.6576	5.7600	5.7633
5.0923	3.0990	970	4.4757	6.8784	0.6412	5.7703	5.7741
5.1729	3.1150	975	4.4747	6.9144	0.6403	5.8102	5.8064
5.1864	3.1310	980	4.4742	6.9348	0.6531	5.8079	5.8027
5.2251	3.1470	985	4.4737	6.9469	0.6869	5.8021	5.8002
5.1631	3.1629	990	4.4733	6.9770	0.6909	5.8255	5.8155
5.2361	3.1789	995	4.4732	6.9978	0.7205	5.8385	5.8312
5.2153	3.1949	1000	4.4727	7.0194	0.7462	5.8473	5.8427
4.949	3.2109	1005	4.4724	7.0442	0.7346	5.8631	5.8543
5.0817	3.2268	1010	4.4721	7.0183	0.7229	5.8697	5.8590
5.0898	3.2428	1015	4.4716	7.0135	0.7131	5.8406	5.8362
5.1289	3.2588	1020	4.4715	6.9679	0.7175	5.8269	5.8193
5.2497	3.2748	1025	4.4708	6.9824	0.7243	5.8302	5.8229
5.2646	3.2907	1030	4.4700	6.9954	0.7178	5.8304	5.8193
5.2577	3.3067	1035	4.4689	6.9859	0.7132	5.8183	5.8091
5.0303	3.3227	1040	4.4675	6.9681	0.7205	5.7512	5.7422
5.0681	3.3387	1045	4.4662	6.9814	0.7321	5.7606	5.7567
5.1703	3.3546	1050	4.4648	6.9691	0.7201	5.7592	5.7554
5.1361	3.3706	1055	4.4635	6.9370	0.7088	5.7440	5.7445
5.2493	3.3866	1060	4.4625	6.9814	0.7020	5.7481	5.7480
5.2599	3.4026	1065	4.4615	6.9617	0.7029	5.7426	5.7407
5.6987	3.4185	1070	4.4608	6.9748	0.7117	5.7502	5.7481
5.1897	3.4345	1075	4.4606	6.9616	0.7094	5.7620	5.7587
5.1351	3.4505	1080	4.4608	6.9574	0.7200	5.7551	5.7568
5.1565	3.4665	1085	4.4612	6.9928	0.7335	5.7861	5.7773
5.0921	3.4824	1090	4.4611	6.9979	0.7437	5.7963	5.7911
5.2995	3.4984	1095	4.4613	6.9737	0.7398	5.7852	5.7807
5.2095	3.5144	1100	4.4610	6.9365	0.7029	5.7513	5.7477
4.9812	3.5304	1105	4.4608	6.9247	0.7040	5.7530	5.7444
5.0206	3.5463	1110	4.4604	6.9237	0.7161	5.7440	5.7371
5.1183	3.5623	1115	4.4602	6.9120	0.7013	5.7443	5.7361
5.1914	3.5783	1120	4.4603	6.9370	0.7057	5.7433	5.7367
4.9982	3.5942	1125	4.4603	6.9551	0.7008	5.7582	5.7546
5.0126	3.6102	1130	4.4604	6.9574	0.6951	5.7389	5.7325
5.1075	3.6262	1135	4.4603	6.9903	0.7045	5.7472	5.7432
5.1985	3.6422	1140	4.4601	6.9734	0.6858	5.7350	5.7301
5.3398	3.6581	1145	4.4600	6.9579	0.6883	5.7210	5.7124
5.1475	3.6741	1150	4.4596	6.9668	0.6785	5.7307	5.7186
5.016	3.6901	1155	4.4594	6.9717	0.6789	5.7341	5.7186
5.2785	3.7061	1160	4.4592	7.0314	0.6962	5.7750	5.7639
5.295	3.7220	1165	4.4589	7.0075	0.6895	5.7655	5.7547
5.1939	3.7380	1170	4.4587	7.0287	0.6944	5.7671	5.7590
5.2976	3.7540	1175	4.4585	7.0327	0.6917	5.7685	5.7589
4.9886	3.7700	1180	4.4581	7.0105	0.6844	5.7469	5.7372
5.2187	3.7859	1185	4.4577	6.9933	0.6810	5.7267	5.7187
5.3142	3.8019	1190	4.4573	7.0135	0.6810	5.7426	5.7333
5.1089	3.8179	1195	4.4572	7.0202	0.6810	5.7430	5.7323
5.2423	3.8339	1200	4.4569	7.0209	0.6810	5.7376	5.7267
5.1709	3.8498	1205	4.4566	7.0130	0.6810	5.7197	5.7088
5.2386	3.8658	1210	4.4564	7.0002	0.6753	5.7134	5.7056
5.0235	3.8818	1215	4.4562	6.9875	0.6753	5.7133	5.7057
5.1144	3.8978	1220	4.4561	6.9713	0.6816	5.6947	5.6868
5.1089	3.9137	1225	4.4560	6.9713	0.6816	5.6947	5.6868
5.1123	3.9297	1230	4.4559	6.9656	0.6816	5.6991	5.6932
4.9316	3.9457	1235	4.4559	6.9584	0.6673	5.6909	5.6877
5.1495	3.9617	1240	4.4558	6.9390	0.6673	5.6744	5.6706
5.169	3.9776	1245	4.4558	6.9656	0.6816	5.6991	5.6932
5.3732	3.9936	1250	4.4558	6.9916	0.6816	5.7118	5.7018

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