life2lang-pt

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0482

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
22.1588	0.0078	50	19.2749
18.4364	0.0157	100	14.3397
11.7105	0.0235	150	4.3493
4.0853	0.0313	200	3.2481
3.1862	0.0392	250	2.5404
2.6147	0.0470	300	2.0131
2.1487	0.0548	350	1.8028
1.8747	0.0627	400	1.6388
1.64	0.0705	450	1.3478
1.4195	0.0783	500	1.2805
1.3282	0.0862	550	1.2760
1.2827	0.0940	600	1.2517
1.2636	0.1018	650	1.2455
1.2392	0.1097	700	1.2260
1.2323	0.1175	750	1.2223
1.2063	0.1253	800	1.2105
1.206	0.1332	850	1.2048
1.1913	0.1410	900	1.2007
1.1932	0.1488	950	1.1919
1.1795	0.1567	1000	1.1870
1.1716	0.1645	1050	1.1852
1.1745	0.1723	1100	1.1754
1.1641	0.1802	1150	1.1689
1.1497	0.1880	1200	1.1679
1.1526	0.1958	1250	1.1639
1.1494	0.2037	1300	1.1641
1.1527	0.2115	1350	1.1549
1.1327	0.2193	1400	1.1553
1.1262	0.2272	1450	1.1590
1.1299	0.2350	1500	1.1570
1.1255	0.2428	1550	1.1492
1.1257	0.2507	1600	1.1535
1.1174	0.2585	1650	1.1481
1.119	0.2663	1700	1.1283
1.1114	0.2742	1750	1.1421
1.1032	0.2820	1800	1.1262
1.1089	0.2898	1850	1.1282
1.1017	0.2977	1900	1.1130
1.1007	0.3055	1950	1.1164
1.0949	0.3133	2000	1.1174
1.0946	0.3212	2050	1.1306
1.0927	0.3290	2100	1.1103
1.0912	0.3368	2150	1.1406
1.0878	0.3447	2200	1.1136
1.0825	0.3525	2250	1.1036
1.0835	0.3603	2300	1.1054
1.0783	0.3682	2350	1.1127
1.0783	0.3760	2400	1.1087
1.0736	0.3838	2450	1.1034
1.0739	0.3917	2500	1.0999
1.0679	0.3995	2550	1.0904
1.0712	0.4073	2600	1.0927
1.063	0.4151	2650	1.0933
1.0689	0.4230	2700	1.0902
1.0659	0.4308	2750	1.0965
1.0616	0.4386	2800	1.0908
1.0635	0.4465	2850	1.0840
1.0614	0.4543	2900	1.0853
1.0632	0.4621	2950	1.0967
1.0585	0.4700	3000	1.0868
1.0494	0.4778	3050	1.0878
1.0548	0.4856	3100	1.0833
1.0495	0.4935	3150	1.0726
1.0565	0.5013	3200	1.0805
1.0446	0.5091	3250	1.0685
1.053	0.5170	3300	1.0700
1.0509	0.5248	3350	1.0794
1.0491	0.5326	3400	1.0678
1.0477	0.5405	3450	1.0679
1.0461	0.5483	3500	1.0716
1.0407	0.5561	3550	1.0737
1.0425	0.5640	3600	1.0628
1.0354	0.5718	3650	1.0670
1.0402	0.5796	3700	1.0671
1.0376	0.5875	3750	1.0685
1.0379	0.5953	3800	1.0673
1.0328	0.6031	3850	1.0579
1.0354	0.6110	3900	1.0622
1.0313	0.6188	3950	1.0621
1.0363	0.6266	4000	1.0590
1.0362	0.6345	4050	1.0653
1.0333	0.6423	4100	1.0593
1.0285	0.6501	4150	1.0578
1.0309	0.6580	4200	1.0581
1.0305	0.6658	4250	1.0561
1.026	0.6736	4300	1.0569
1.0315	0.6815	4350	1.0585
1.0317	0.6893	4400	1.0522
1.0348	0.6971	4450	1.0574
1.0293	0.7050	4500	1.0545
1.0283	0.7128	4550	1.0524
1.0274	0.7206	4600	1.0544
1.026	0.7285	4650	1.0525
1.0258	0.7363	4700	1.0541
1.0268	0.7441	4750	1.0580
1.0244	0.7520	4800	1.0484
1.0271	0.7598	4850	1.0508
1.0279	0.7676	4900	1.0508
1.0265	0.7755	4950	1.0478
1.0264	0.7833	5000	1.0520
1.0203	0.7911	5050	1.0496
1.026	0.7990	5100	1.0473
1.0227	0.8068	5150	1.0494
1.0227	0.8146	5200	1.0497
1.0228	0.8225	5250	1.0513
1.022	0.8303	5300	1.0521
1.022	0.8381	5350	1.0502
1.0259	0.8460	5400	1.0489
1.021	0.8538	5450	1.0504
1.0244	0.8616	5500	1.0475
1.025	0.8695	5550	1.0490
1.0197	0.8773	5600	1.0513
1.0224	0.8851	5650	1.0477
1.0189	0.8930	5700	1.0490
1.0227	0.9008	5750	1.0490
1.0182	0.9086	5800	1.0487
1.0201	0.9165	5850	1.0480
1.0239	0.9243	5900	1.0495
1.0182	0.9321	5950	1.0489
1.0224	0.9400	6000	1.0485
1.0251	0.9478	6050	1.0478
1.0223	0.9556	6100	1.0488
1.0232	0.9635	6150	1.0481
1.0217	0.9713	6200	1.0482
1.0194	0.9791	6250	1.0483
1.0208	0.9870	6300	1.0481
1.0219	0.9948	6350	1.0482