mt5-base-b16-e16-t126k-jupyter

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: 0.1645
• Rouge1: 69.0491
• Rouge2: 62.3577
• Rougel: 68.9223
• Rougelsum: 68.9293
• Gen Len: 19.1285

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4664	0.1269	1000	0.3503	58.6102	49.1959	58.3363	58.338	19.2724
0.4085	0.2538	2000	0.2657	64.9195	55.7744	64.6518	64.6597	19.0740
0.332	0.3808	3000	0.2551	67.2391	58.6115	67.0285	67.0369	19.1507
0.2964	0.5077	4000	0.2240	59.4787	51.7894	59.3096	59.3014	18.8110
0.2776	0.6346	5000	0.2101	48.75	41.3868	48.5559	48.5627	17.7630
0.2596	0.7615	6000	0.2014	64.9022	56.7611	64.7122	64.7321	19.1331
0.2497	0.8884	7000	0.1960	57.5409	50.5573	57.3506	57.3713	19.2094
0.2279	1.0154	8000	0.1953	65.7851	58.3685	65.6045	65.6017	19.1360
0.1745	1.1423	9000	0.1945	69.9367	62.548	69.7904	69.7943	19.2043
0.1762	1.2692	10000	0.1836	64.1157	56.773	63.9375	63.9338	18.8669
0.1692	1.3961	11000	0.1802	68.431	61.0582	68.2591	68.2677	19.2098
0.1678	1.5230	12000	0.1816	67.5347	60.4008	67.3811	67.385	19.2364
0.1691	1.6500	13000	0.1754	65.9637	58.9869	65.8222	65.8294	19.1470
0.1656	1.7769	14000	0.1716	55.9545	49.1856	55.7837	55.7761	18.9288
0.1623	1.9038	15000	0.1668	65.4847	58.5782	65.3217	65.3235	19.2038
0.1469	2.0307	16000	0.1714	65.3287	58.5385	65.1742	65.1803	19.0559
0.1133	2.1576	17000	0.1721	66.502	59.67	66.3759	66.3848	19.0530
0.114	2.2846	18000	0.1787	66.0224	59.2078	65.8882	65.8981	19.1717
0.114	2.4115	19000	0.1725	60.8491	54.101	60.696	60.6942	18.9738
0.1185	2.5384	20000	0.1691	57.2166	50.3259	57.0389	57.0385	18.5442
0.1165	2.6653	21000	0.1677	68.1682	61.5828	68.0211	68.0217	19.2470
0.1173	2.7922	22000	0.1674	69.019	62.4579	68.9009	68.8989	19.1336
0.1156	2.9192	23000	0.1645	69.0491	62.3577	68.9223	68.9293	19.1285
0.1026	3.0461	24000	0.1725	68.3381	61.8488	68.2171	68.2209	18.9749
0.0805	3.1730	25000	0.1746	69.2018	62.7444	69.0733	69.0814	19.1173
0.0813	3.2999	26000	0.1786	68.0695	61.5598	67.9424	67.9475	19.1217
0.0821	3.4268	27000	0.1729	71.4822	65.1469	71.3625	71.3711	19.1623
0.0836	3.5538	28000	0.1787	69.384	62.875	69.2804	69.2795	19.1467
0.0868	3.6807	29000	0.1707	69.9597	63.5038	69.8371	69.8369	19.2096
0.086	3.8076	30000	0.1712	64.6143	58.195	64.4892	64.4989	18.9053
0.085	3.9345	31000	0.1734	64.0262	57.7604	63.8999	63.8955	18.8091
0.0722	4.0614	32000	0.1815	64.4249	58.0731	64.3094	64.3093	18.8705
0.0577	4.1883	33000	0.1827	68.8388	62.3576	68.7079	68.7167	19.1096
0.06	4.3153	34000	0.1829	68.9629	62.5964	68.8241	68.8355	19.1820
0.0628	4.4422	35000	0.1841	67.0498	60.5408	66.8984	66.9192	19.0666
0.0636	4.5691	36000	0.1846	70.3454	63.9895	70.2318	70.2356	19.1360
0.0648	4.6960	37000	0.1783	69.7467	63.4059	69.6243	69.6299	19.1450
0.0642	4.8229	38000	0.1791	68.374	61.7525	68.2523	68.2543	19.0701
0.0659	4.9499	39000	0.1818	68.5635	62.1515	68.4405	68.4462	19.1936
0.0526	5.0768	40000	0.1974	71.1718	64.9477	71.0566	71.0651	19.1645
0.0444	5.2037	41000	0.1865	69.6394	63.2955	69.521	69.5322	19.1499
0.0449	5.3306	42000	0.1904	70.1591	63.6933	70.0387	70.0529	19.1812
0.0457	5.4575	43000	0.1912	71.1048	64.8898	70.9968	71.0021	19.1706
0.0489	5.5845	44000	0.1910	70.9571	64.6543	70.8418	70.846	19.1642
0.0477	5.7114	45000	0.1995	71.1174	64.8599	71.0092	71.0157	19.1676
0.0499	5.8383	46000	0.1883	67.9455	61.5466	67.8268	67.8291	19.0710
0.0489	5.9652	47000	0.1943	69.2924	62.8611	69.1755	69.1852	19.1791
0.0362	6.0921	48000	0.2003	69.6819	63.4608	69.5671	69.5726	19.1258
0.0334	6.2191	49000	0.1999	70.229	63.9271	70.1131	70.1184	19.2295
0.0339	6.3460	50000	0.2004	69.5581	63.2151	69.4493	69.4556	19.2695
0.0357	6.4729	51000	0.2045	69.9536	63.6877	69.827	69.8373	19.1732
0.0362	6.5998	52000	0.2005	68.0243	61.7015	67.9114	67.9188	19.0782
0.0371	6.7267	53000	0.2027	68.7199	62.41	68.6001	68.611	19.1258
0.0376	6.8537	54000	0.2018	66.4473	60.0452	66.3113	66.3162	19.0988
0.0378	6.9806	55000	0.2056	68.6484	62.3742	68.5344	68.5377	19.1435
0.0266	7.1075	56000	0.2195	67.8788	61.538	67.7618	67.7651	19.1034
0.0243	7.2344	57000	0.2179	67.1296	60.7251	67.0162	67.0143	19.0743
0.0264	7.3613	58000	0.2173	66.7227	60.5002	66.6089	66.6165	19.1236
0.0272	7.4883	59000	0.2102	71.1275	65.0313	71.0101	71.0243	19.1706
0.0274	7.6152	60000	0.2163	70.459	64.334	70.3602	70.3636	19.1725
0.0288	7.7421	61000	0.2036	67.5839	61.1639	67.4641	67.4691	19.0064
0.0272	7.8690	62000	0.2085	68.9624	62.7038	68.8432	68.8504	19.1775
0.0291	7.9959	63000	0.2091	67.1602	60.7383	67.0253	67.0379	19.1666
0.0192	8.1229	64000	0.2261	70.048	63.9186	69.9255	69.9291	19.1684
0.0194	8.2498	65000	0.2299	69.2928	63.116	69.1601	69.1736	19.1384
0.0198	8.3767	66000	0.2269	67.6192	61.2499	67.4866	67.492	19.2088
0.0198	8.5036	67000	0.2255	69.7527	63.6416	69.6346	69.6453	19.2061
0.021	8.6305	68000	0.2188	68.2419	62.0352	68.1225	68.1289	19.1070
0.0212	8.7575	69000	0.2180	64.683	58.6031	64.5447	64.5551	18.8629
0.021	8.8844	70000	0.2237	64.7196	58.4031	64.5935	64.6065	18.9414
0.0207	9.0113	71000	0.2286	70.1433	64.1181	70.0359	70.0399	19.1467
0.0144	9.1382	72000	0.2381	67.8838	61.7006	67.7642	67.7786	19.1517
0.0144	9.2651	73000	0.2325	70.1472	64.1045	70.0423	70.0431	19.1717
0.015	9.3921	74000	0.2360	71.3244	65.4014	71.2154	71.2262	19.1433
0.0149	9.5190	75000	0.2410	71.2676	65.3896	71.1525	71.1656	19.1706
0.016	9.6459	76000	0.2351	72.1784	66.3816	72.0702	72.0816	19.1549
0.015	9.7728	77000	0.2380	72.3992	66.5645	72.292	72.3048	19.1705
0.016	9.8997	78000	0.2341	71.0815	65.205	70.986	70.9874	19.1701
0.0144	10.0267	79000	0.2461	70.1223	64.1529	70.0051	70.0088	19.1602
0.0109	10.1536	80000	0.2413	68.6412	62.6327	68.5089	68.5152	19.1642
0.0109	10.2805	81000	0.2531	69.2718	63.1213	69.1523	69.1603	19.1552
0.0113	10.4074	82000	0.2509	69.3696	63.2617	69.2464	69.2622	19.1938
0.0113	10.5343	83000	0.2437	69.2457	63.178	69.1322	69.145	19.1876
0.0109	10.6613	84000	0.2579	69.9983	63.9436	69.8858	69.893	19.1903
0.0114	10.7882	85000	0.2522	68.8232	62.5196	68.7168	68.7286	19.1273
0.0115	10.9151	86000	0.2498	67.6943	61.5001	67.5733	67.5787	19.1484
0.0099	11.0420	87000	0.2649	68.5861	62.4139	68.4787	68.4842	19.1288
0.0078	11.1689	88000	0.2610	67.6684	61.4378	67.5605	67.5663	19.1644
0.008	11.2958	89000	0.2627	69.2172	63.0948	69.1101	69.1167	19.2093
0.0078	11.4228	90000	0.2670	67.9655	61.7532	67.8555	67.8537	19.1457
0.0081	11.5497	91000	0.2627	68.6292	62.4361	68.51	68.5225	19.2017
0.0081	11.6766	92000	0.2675	67.5707	61.4739	67.4536	67.4645	19.1873
0.0081	11.8035	93000	0.2661	67.8674	61.695	67.74	67.7535	19.1516
0.0084	11.9304	94000	0.2678	66.7531	60.6613	66.6401	66.6481	19.1218
0.0071	12.0574	95000	0.2767	67.5904	61.4704	67.4677	67.4743	19.1178
0.0063	12.1843	96000	0.2754	66.3677	60.2218	66.2238	66.2309	19.0790
0.0056	12.3112	97000	0.2846	68.9713	62.9631	68.8408	68.8516	19.1473
0.0057	12.4381	98000	0.2899	69.3481	63.4716	69.2312	69.2378	19.1224
0.0058	12.5650	99000	0.2749	68.866	62.9244	68.7422	68.7552	19.1194
0.0058	12.6920	100000	0.2880	66.9218	60.7514	66.8013	66.8022	19.0786
0.0058	12.8189	101000	0.2912	68.2067	62.1356	68.0816	68.0936	19.1021
0.0058	12.9458	102000	0.2832	66.3243	60.1518	66.1979	66.1978	19.0439
0.0048	13.0727	103000	0.3017	66.5581	60.3887	66.4172	66.4245	19.0610
0.0043	13.1996	104000	0.2920	68.1021	61.953	67.9814	67.9924	19.1312
0.0041	13.3266	105000	0.2969	67.1438	60.934	67.0129	67.0261	19.1098
0.0042	13.4535	106000	0.2998	66.0186	59.8272	65.8811	65.8871	19.0740
0.0043	13.5804	107000	0.2962	66.1395	59.9014	66.0011	66.0105	19.0626
0.0039	13.7073	108000	0.3029	67.6976	61.543	67.5765	67.5771	19.1092
0.004	13.8342	109000	0.3041	68.7212	62.6213	68.6135	68.6104	19.1106
0.0039	13.9612	110000	0.3091	68.164	62.0282	68.0419	68.0521	19.1198
0.0032	14.0881	111000	0.3152	67.4907	61.2721	67.364	67.3715	19.0937
0.0029	14.2150	112000	0.3180	67.2118	61.0255	67.0818	67.0911	19.1074
0.0027	14.3419	113000	0.3256	66.6723	60.4405	66.5353	66.5474	19.0571
0.003	14.4688	114000	0.3196	67.9842	61.7442	67.8502	67.8586	19.1207
0.0028	14.5958	115000	0.3280	68.1337	61.9552	67.9942	68.0032	19.1020
0.0029	14.7227	116000	0.3264	66.8958	60.6476	66.7586	66.7686	19.0682
0.0029	14.8496	117000	0.3232	67.7823	61.5145	67.6528	67.6575	19.1225
0.0031	14.9765	118000	0.3230	67.9894	61.7854	67.8634	67.872	19.1056
0.0025	15.1034	119000	0.3280	68.0723	61.87	67.951	67.9591	19.1074
0.0022	15.2304	120000	0.3352	67.3952	61.2142	67.2731	67.2772	19.0851
0.0024	15.3573	121000	0.3319	67.2694	61.0931	67.1442	67.1523	19.0729
0.002	15.4842	122000	0.3348	67.6768	61.5274	67.5549	67.5622	19.0860
0.0022	15.6111	123000	0.3350	67.8076	61.6275	67.6806	67.687	19.0935
0.0021	15.7380	124000	0.3351	67.8397	61.6565	67.7097	67.7203	19.1006
0.002	15.8650	125000	0.3353	67.8209	61.6651	67.6884	67.6941	19.0988
0.0021	15.9919	126000	0.3358	67.7802	61.6191	67.6505	67.6599	19.0989

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1