wav2vec2-base-ft-keyword-spotting / trainer_state.json
antonjaragon's picture
End of training
7de6d75
{
"best_metric": 0.9832303618711385,
"best_model_checkpoint": "wav2vec2-base-ft-keyword-spotting/checkpoint-1597",
"epoch": 4.996869129618034,
"eval_steps": 500,
"global_step": 1995,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1.5e-06,
"loss": 2.4941,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 3e-06,
"loss": 2.4759,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 4.5e-06,
"loss": 2.4215,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 6e-06,
"loss": 2.3219,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 7.5e-06,
"loss": 2.1799,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 9e-06,
"loss": 2.0087,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 1.05e-05,
"loss": 1.8646,
"step": 70
},
{
"epoch": 0.2,
"learning_rate": 1.2e-05,
"loss": 1.7391,
"step": 80
},
{
"epoch": 0.23,
"learning_rate": 1.3500000000000001e-05,
"loss": 1.6466,
"step": 90
},
{
"epoch": 0.25,
"learning_rate": 1.5e-05,
"loss": 1.6398,
"step": 100
},
{
"epoch": 0.28,
"learning_rate": 1.65e-05,
"loss": 1.519,
"step": 110
},
{
"epoch": 0.3,
"learning_rate": 1.8e-05,
"loss": 1.5813,
"step": 120
},
{
"epoch": 0.33,
"learning_rate": 1.95e-05,
"loss": 1.4891,
"step": 130
},
{
"epoch": 0.35,
"learning_rate": 2.1e-05,
"loss": 1.5947,
"step": 140
},
{
"epoch": 0.38,
"learning_rate": 2.25e-05,
"loss": 1.542,
"step": 150
},
{
"epoch": 0.4,
"learning_rate": 2.4e-05,
"loss": 1.4833,
"step": 160
},
{
"epoch": 0.43,
"learning_rate": 2.55e-05,
"loss": 1.431,
"step": 170
},
{
"epoch": 0.45,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.353,
"step": 180
},
{
"epoch": 0.48,
"learning_rate": 2.8499999999999998e-05,
"loss": 1.265,
"step": 190
},
{
"epoch": 0.5,
"learning_rate": 3e-05,
"loss": 1.2248,
"step": 200
},
{
"epoch": 0.53,
"learning_rate": 2.9832869080779945e-05,
"loss": 1.0998,
"step": 210
},
{
"epoch": 0.55,
"learning_rate": 2.9665738161559886e-05,
"loss": 1.1259,
"step": 220
},
{
"epoch": 0.58,
"learning_rate": 2.9498607242339834e-05,
"loss": 1.0713,
"step": 230
},
{
"epoch": 0.6,
"learning_rate": 2.933147632311978e-05,
"loss": 1.0161,
"step": 240
},
{
"epoch": 0.63,
"learning_rate": 2.916434540389972e-05,
"loss": 0.9614,
"step": 250
},
{
"epoch": 0.65,
"learning_rate": 2.8997214484679665e-05,
"loss": 0.8767,
"step": 260
},
{
"epoch": 0.68,
"learning_rate": 2.8830083565459613e-05,
"loss": 0.8643,
"step": 270
},
{
"epoch": 0.7,
"learning_rate": 2.8662952646239554e-05,
"loss": 0.8183,
"step": 280
},
{
"epoch": 0.73,
"learning_rate": 2.84958217270195e-05,
"loss": 0.7784,
"step": 290
},
{
"epoch": 0.75,
"learning_rate": 2.8328690807799443e-05,
"loss": 0.6894,
"step": 300
},
{
"epoch": 0.78,
"learning_rate": 2.8161559888579388e-05,
"loss": 0.6612,
"step": 310
},
{
"epoch": 0.8,
"learning_rate": 2.7994428969359332e-05,
"loss": 0.6353,
"step": 320
},
{
"epoch": 0.83,
"learning_rate": 2.7827298050139277e-05,
"loss": 0.6632,
"step": 330
},
{
"epoch": 0.85,
"learning_rate": 2.7660167130919218e-05,
"loss": 0.5824,
"step": 340
},
{
"epoch": 0.88,
"learning_rate": 2.7493036211699166e-05,
"loss": 0.5914,
"step": 350
},
{
"epoch": 0.9,
"learning_rate": 2.732590529247911e-05,
"loss": 0.5481,
"step": 360
},
{
"epoch": 0.93,
"learning_rate": 2.7158774373259055e-05,
"loss": 0.5055,
"step": 370
},
{
"epoch": 0.95,
"learning_rate": 2.6991643454038996e-05,
"loss": 0.5035,
"step": 380
},
{
"epoch": 0.98,
"learning_rate": 2.6824512534818944e-05,
"loss": 0.4547,
"step": 390
},
{
"epoch": 1.0,
"eval_accuracy": 0.9710208884966166,
"eval_loss": 0.33722183108329773,
"eval_runtime": 13.726,
"eval_samples_per_second": 495.265,
"eval_steps_per_second": 15.518,
"step": 399
},
{
"epoch": 1.0,
"learning_rate": 2.665738161559889e-05,
"loss": 0.4363,
"step": 400
},
{
"epoch": 1.03,
"learning_rate": 2.649025069637883e-05,
"loss": 0.4134,
"step": 410
},
{
"epoch": 1.05,
"learning_rate": 2.6323119777158774e-05,
"loss": 0.4144,
"step": 420
},
{
"epoch": 1.08,
"learning_rate": 2.6155988857938722e-05,
"loss": 0.4239,
"step": 430
},
{
"epoch": 1.1,
"learning_rate": 2.5988857938718663e-05,
"loss": 0.3925,
"step": 440
},
{
"epoch": 1.13,
"learning_rate": 2.5821727019498608e-05,
"loss": 0.3468,
"step": 450
},
{
"epoch": 1.15,
"learning_rate": 2.5654596100278553e-05,
"loss": 0.3417,
"step": 460
},
{
"epoch": 1.18,
"learning_rate": 2.5487465181058497e-05,
"loss": 0.3667,
"step": 470
},
{
"epoch": 1.2,
"learning_rate": 2.532033426183844e-05,
"loss": 0.361,
"step": 480
},
{
"epoch": 1.23,
"learning_rate": 2.5153203342618386e-05,
"loss": 0.3563,
"step": 490
},
{
"epoch": 1.25,
"learning_rate": 2.4986072423398327e-05,
"loss": 0.3567,
"step": 500
},
{
"epoch": 1.28,
"learning_rate": 2.4818941504178275e-05,
"loss": 0.336,
"step": 510
},
{
"epoch": 1.3,
"learning_rate": 2.465181058495822e-05,
"loss": 0.3095,
"step": 520
},
{
"epoch": 1.33,
"learning_rate": 2.448467966573816e-05,
"loss": 0.3213,
"step": 530
},
{
"epoch": 1.35,
"learning_rate": 2.4317548746518106e-05,
"loss": 0.281,
"step": 540
},
{
"epoch": 1.38,
"learning_rate": 2.415041782729805e-05,
"loss": 0.2936,
"step": 550
},
{
"epoch": 1.4,
"learning_rate": 2.3983286908077995e-05,
"loss": 0.2731,
"step": 560
},
{
"epoch": 1.43,
"learning_rate": 2.381615598885794e-05,
"loss": 0.255,
"step": 570
},
{
"epoch": 1.45,
"learning_rate": 2.3649025069637884e-05,
"loss": 0.2892,
"step": 580
},
{
"epoch": 1.48,
"learning_rate": 2.3481894150417825e-05,
"loss": 0.258,
"step": 590
},
{
"epoch": 1.5,
"learning_rate": 2.3314763231197773e-05,
"loss": 0.2621,
"step": 600
},
{
"epoch": 1.53,
"learning_rate": 2.3147632311977718e-05,
"loss": 0.2533,
"step": 610
},
{
"epoch": 1.55,
"learning_rate": 2.298050139275766e-05,
"loss": 0.2595,
"step": 620
},
{
"epoch": 1.58,
"learning_rate": 2.2813370473537603e-05,
"loss": 0.2685,
"step": 630
},
{
"epoch": 1.6,
"learning_rate": 2.264623955431755e-05,
"loss": 0.2603,
"step": 640
},
{
"epoch": 1.63,
"learning_rate": 2.2479108635097492e-05,
"loss": 0.286,
"step": 650
},
{
"epoch": 1.65,
"learning_rate": 2.2311977715877437e-05,
"loss": 0.2588,
"step": 660
},
{
"epoch": 1.68,
"learning_rate": 2.214484679665738e-05,
"loss": 0.2327,
"step": 670
},
{
"epoch": 1.7,
"learning_rate": 2.1977715877437326e-05,
"loss": 0.2604,
"step": 680
},
{
"epoch": 1.73,
"learning_rate": 2.181058495821727e-05,
"loss": 0.2328,
"step": 690
},
{
"epoch": 1.75,
"learning_rate": 2.1643454038997215e-05,
"loss": 0.2207,
"step": 700
},
{
"epoch": 1.78,
"learning_rate": 2.147632311977716e-05,
"loss": 0.2125,
"step": 710
},
{
"epoch": 1.8,
"learning_rate": 2.1309192200557104e-05,
"loss": 0.2212,
"step": 720
},
{
"epoch": 1.83,
"learning_rate": 2.114206128133705e-05,
"loss": 0.1926,
"step": 730
},
{
"epoch": 1.85,
"learning_rate": 2.0974930362116993e-05,
"loss": 0.2338,
"step": 740
},
{
"epoch": 1.88,
"learning_rate": 2.0807799442896935e-05,
"loss": 0.2278,
"step": 750
},
{
"epoch": 1.9,
"learning_rate": 2.0640668523676883e-05,
"loss": 0.2128,
"step": 760
},
{
"epoch": 1.93,
"learning_rate": 2.0473537604456827e-05,
"loss": 0.2214,
"step": 770
},
{
"epoch": 1.95,
"learning_rate": 2.0306406685236768e-05,
"loss": 0.199,
"step": 780
},
{
"epoch": 1.98,
"learning_rate": 2.0139275766016713e-05,
"loss": 0.2625,
"step": 790
},
{
"epoch": 2.0,
"eval_accuracy": 0.9779346866725508,
"eval_loss": 0.11822522431612015,
"eval_runtime": 13.9175,
"eval_samples_per_second": 488.448,
"eval_steps_per_second": 15.304,
"step": 798
},
{
"epoch": 2.0,
"learning_rate": 1.997214484679666e-05,
"loss": 0.1903,
"step": 800
},
{
"epoch": 2.03,
"learning_rate": 1.9805013927576602e-05,
"loss": 0.1891,
"step": 810
},
{
"epoch": 2.05,
"learning_rate": 1.9637883008356546e-05,
"loss": 0.2066,
"step": 820
},
{
"epoch": 2.08,
"learning_rate": 1.947075208913649e-05,
"loss": 0.1839,
"step": 830
},
{
"epoch": 2.1,
"learning_rate": 1.9303621169916436e-05,
"loss": 0.1799,
"step": 840
},
{
"epoch": 2.13,
"learning_rate": 1.9153203342618386e-05,
"loss": 0.2192,
"step": 850
},
{
"epoch": 2.15,
"learning_rate": 1.898607242339833e-05,
"loss": 0.2021,
"step": 860
},
{
"epoch": 2.18,
"learning_rate": 1.8818941504178272e-05,
"loss": 0.2315,
"step": 870
},
{
"epoch": 2.2,
"learning_rate": 1.8651810584958216e-05,
"loss": 0.2357,
"step": 880
},
{
"epoch": 2.23,
"learning_rate": 1.8484679665738164e-05,
"loss": 0.1723,
"step": 890
},
{
"epoch": 2.25,
"learning_rate": 1.8317548746518105e-05,
"loss": 0.2169,
"step": 900
},
{
"epoch": 2.28,
"learning_rate": 1.815041782729805e-05,
"loss": 0.1875,
"step": 910
},
{
"epoch": 2.3,
"learning_rate": 1.7983286908077995e-05,
"loss": 0.1807,
"step": 920
},
{
"epoch": 2.33,
"learning_rate": 1.781615598885794e-05,
"loss": 0.1777,
"step": 930
},
{
"epoch": 2.35,
"learning_rate": 1.7649025069637884e-05,
"loss": 0.187,
"step": 940
},
{
"epoch": 2.38,
"learning_rate": 1.7481894150417828e-05,
"loss": 0.1855,
"step": 950
},
{
"epoch": 2.4,
"learning_rate": 1.731476323119777e-05,
"loss": 0.1486,
"step": 960
},
{
"epoch": 2.43,
"learning_rate": 1.7147632311977717e-05,
"loss": 0.1879,
"step": 970
},
{
"epoch": 2.45,
"learning_rate": 1.6980501392757662e-05,
"loss": 0.1662,
"step": 980
},
{
"epoch": 2.48,
"learning_rate": 1.6813370473537606e-05,
"loss": 0.1908,
"step": 990
},
{
"epoch": 2.5,
"learning_rate": 1.6646239554317548e-05,
"loss": 0.1785,
"step": 1000
},
{
"epoch": 2.53,
"learning_rate": 1.6479108635097496e-05,
"loss": 0.1643,
"step": 1010
},
{
"epoch": 2.55,
"learning_rate": 1.631197771587744e-05,
"loss": 0.1606,
"step": 1020
},
{
"epoch": 2.58,
"learning_rate": 1.614484679665738e-05,
"loss": 0.1504,
"step": 1030
},
{
"epoch": 2.6,
"learning_rate": 1.5977715877437326e-05,
"loss": 0.1806,
"step": 1040
},
{
"epoch": 2.63,
"learning_rate": 1.581058495821727e-05,
"loss": 0.1574,
"step": 1050
},
{
"epoch": 2.65,
"learning_rate": 1.5643454038997215e-05,
"loss": 0.1769,
"step": 1060
},
{
"epoch": 2.68,
"learning_rate": 1.547632311977716e-05,
"loss": 0.1853,
"step": 1070
},
{
"epoch": 2.71,
"learning_rate": 1.5309192200557104e-05,
"loss": 0.1916,
"step": 1080
},
{
"epoch": 2.73,
"learning_rate": 1.5142061281337047e-05,
"loss": 0.1796,
"step": 1090
},
{
"epoch": 2.76,
"learning_rate": 1.4974930362116992e-05,
"loss": 0.172,
"step": 1100
},
{
"epoch": 2.78,
"learning_rate": 1.4807799442896936e-05,
"loss": 0.1934,
"step": 1110
},
{
"epoch": 2.81,
"learning_rate": 1.464066852367688e-05,
"loss": 0.1946,
"step": 1120
},
{
"epoch": 2.83,
"learning_rate": 1.4473537604456825e-05,
"loss": 0.159,
"step": 1130
},
{
"epoch": 2.86,
"learning_rate": 1.4306406685236768e-05,
"loss": 0.1769,
"step": 1140
},
{
"epoch": 2.88,
"learning_rate": 1.4139275766016714e-05,
"loss": 0.1501,
"step": 1150
},
{
"epoch": 2.91,
"learning_rate": 1.3972144846796657e-05,
"loss": 0.1731,
"step": 1160
},
{
"epoch": 2.93,
"learning_rate": 1.3805013927576602e-05,
"loss": 0.1645,
"step": 1170
},
{
"epoch": 2.96,
"learning_rate": 1.3637883008356546e-05,
"loss": 0.1756,
"step": 1180
},
{
"epoch": 2.98,
"learning_rate": 1.3470752089136491e-05,
"loss": 0.1575,
"step": 1190
},
{
"epoch": 3.0,
"eval_accuracy": 0.978670197116799,
"eval_loss": 0.09626787155866623,
"eval_runtime": 13.6857,
"eval_samples_per_second": 496.721,
"eval_steps_per_second": 15.564,
"step": 1197
},
{
"epoch": 3.01,
"learning_rate": 1.3303621169916434e-05,
"loss": 0.1462,
"step": 1200
},
{
"epoch": 3.03,
"learning_rate": 1.313649025069638e-05,
"loss": 0.1298,
"step": 1210
},
{
"epoch": 3.06,
"learning_rate": 1.2969359331476323e-05,
"loss": 0.1755,
"step": 1220
},
{
"epoch": 3.08,
"learning_rate": 1.2802228412256267e-05,
"loss": 0.1677,
"step": 1230
},
{
"epoch": 3.11,
"learning_rate": 1.2635097493036212e-05,
"loss": 0.1487,
"step": 1240
},
{
"epoch": 3.13,
"learning_rate": 1.2467966573816157e-05,
"loss": 0.1359,
"step": 1250
},
{
"epoch": 3.16,
"learning_rate": 1.2300835654596101e-05,
"loss": 0.1499,
"step": 1260
},
{
"epoch": 3.18,
"learning_rate": 1.2133704735376046e-05,
"loss": 0.1593,
"step": 1270
},
{
"epoch": 3.21,
"learning_rate": 1.1966573816155989e-05,
"loss": 0.1632,
"step": 1280
},
{
"epoch": 3.23,
"learning_rate": 1.1799442896935935e-05,
"loss": 0.1769,
"step": 1290
},
{
"epoch": 3.26,
"learning_rate": 1.1632311977715878e-05,
"loss": 0.159,
"step": 1300
},
{
"epoch": 3.28,
"learning_rate": 1.1465181058495822e-05,
"loss": 0.1489,
"step": 1310
},
{
"epoch": 3.31,
"learning_rate": 1.1298050139275767e-05,
"loss": 0.1684,
"step": 1320
},
{
"epoch": 3.33,
"learning_rate": 1.1130919220055711e-05,
"loss": 0.1515,
"step": 1330
},
{
"epoch": 3.36,
"learning_rate": 1.0963788300835654e-05,
"loss": 0.1421,
"step": 1340
},
{
"epoch": 3.38,
"learning_rate": 1.0796657381615599e-05,
"loss": 0.143,
"step": 1350
},
{
"epoch": 3.41,
"learning_rate": 1.0629526462395543e-05,
"loss": 0.1674,
"step": 1360
},
{
"epoch": 3.43,
"learning_rate": 1.0462395543175486e-05,
"loss": 0.1255,
"step": 1370
},
{
"epoch": 3.46,
"learning_rate": 1.0295264623955432e-05,
"loss": 0.1431,
"step": 1380
},
{
"epoch": 3.48,
"learning_rate": 1.0128133704735375e-05,
"loss": 0.1066,
"step": 1390
},
{
"epoch": 3.51,
"learning_rate": 9.961002785515322e-06,
"loss": 0.1471,
"step": 1400
},
{
"epoch": 3.53,
"learning_rate": 9.793871866295264e-06,
"loss": 0.1384,
"step": 1410
},
{
"epoch": 3.56,
"learning_rate": 9.626740947075209e-06,
"loss": 0.1366,
"step": 1420
},
{
"epoch": 3.58,
"learning_rate": 9.459610027855154e-06,
"loss": 0.1433,
"step": 1430
},
{
"epoch": 3.61,
"learning_rate": 9.292479108635098e-06,
"loss": 0.1387,
"step": 1440
},
{
"epoch": 3.63,
"learning_rate": 9.125348189415041e-06,
"loss": 0.1336,
"step": 1450
},
{
"epoch": 3.66,
"learning_rate": 8.958217270194987e-06,
"loss": 0.1277,
"step": 1460
},
{
"epoch": 3.68,
"learning_rate": 8.79108635097493e-06,
"loss": 0.1762,
"step": 1470
},
{
"epoch": 3.71,
"learning_rate": 8.623955431754875e-06,
"loss": 0.1493,
"step": 1480
},
{
"epoch": 3.73,
"learning_rate": 8.45682451253482e-06,
"loss": 0.1595,
"step": 1490
},
{
"epoch": 3.76,
"learning_rate": 8.289693593314764e-06,
"loss": 0.154,
"step": 1500
},
{
"epoch": 3.78,
"learning_rate": 8.122562674094707e-06,
"loss": 0.1023,
"step": 1510
},
{
"epoch": 3.81,
"learning_rate": 7.955431754874653e-06,
"loss": 0.1103,
"step": 1520
},
{
"epoch": 3.83,
"learning_rate": 7.788300835654596e-06,
"loss": 0.1822,
"step": 1530
},
{
"epoch": 3.86,
"learning_rate": 7.621169916434541e-06,
"loss": 0.1238,
"step": 1540
},
{
"epoch": 3.88,
"learning_rate": 7.454038997214485e-06,
"loss": 0.1626,
"step": 1550
},
{
"epoch": 3.91,
"learning_rate": 7.2869080779944286e-06,
"loss": 0.1534,
"step": 1560
},
{
"epoch": 3.93,
"learning_rate": 7.119777158774373e-06,
"loss": 0.1365,
"step": 1570
},
{
"epoch": 3.96,
"learning_rate": 6.952646239554318e-06,
"loss": 0.1453,
"step": 1580
},
{
"epoch": 3.98,
"learning_rate": 6.785515320334261e-06,
"loss": 0.1314,
"step": 1590
},
{
"epoch": 4.0,
"eval_accuracy": 0.9832303618711385,
"eval_loss": 0.0826701819896698,
"eval_runtime": 14.003,
"eval_samples_per_second": 485.468,
"eval_steps_per_second": 15.211,
"step": 1597
},
{
"epoch": 4.01,
"learning_rate": 6.618384401114206e-06,
"loss": 0.154,
"step": 1600
},
{
"epoch": 4.03,
"learning_rate": 6.4512534818941505e-06,
"loss": 0.1425,
"step": 1610
},
{
"epoch": 4.06,
"learning_rate": 6.284122562674095e-06,
"loss": 0.1525,
"step": 1620
},
{
"epoch": 4.08,
"learning_rate": 6.116991643454039e-06,
"loss": 0.1148,
"step": 1630
},
{
"epoch": 4.11,
"learning_rate": 5.949860724233983e-06,
"loss": 0.1506,
"step": 1640
},
{
"epoch": 4.13,
"learning_rate": 5.782729805013928e-06,
"loss": 0.1339,
"step": 1650
},
{
"epoch": 4.16,
"learning_rate": 5.615598885793872e-06,
"loss": 0.1111,
"step": 1660
},
{
"epoch": 4.18,
"learning_rate": 5.448467966573816e-06,
"loss": 0.1158,
"step": 1670
},
{
"epoch": 4.21,
"learning_rate": 5.281337047353761e-06,
"loss": 0.1257,
"step": 1680
},
{
"epoch": 4.23,
"learning_rate": 5.114206128133705e-06,
"loss": 0.1553,
"step": 1690
},
{
"epoch": 4.26,
"learning_rate": 4.947075208913649e-06,
"loss": 0.1289,
"step": 1700
},
{
"epoch": 4.28,
"learning_rate": 4.7799442896935936e-06,
"loss": 0.1269,
"step": 1710
},
{
"epoch": 4.31,
"learning_rate": 4.612813370473538e-06,
"loss": 0.1514,
"step": 1720
},
{
"epoch": 4.33,
"learning_rate": 4.445682451253482e-06,
"loss": 0.1262,
"step": 1730
},
{
"epoch": 4.36,
"learning_rate": 4.278551532033426e-06,
"loss": 0.1363,
"step": 1740
},
{
"epoch": 4.38,
"learning_rate": 4.111420612813371e-06,
"loss": 0.1131,
"step": 1750
},
{
"epoch": 4.41,
"learning_rate": 3.944289693593315e-06,
"loss": 0.116,
"step": 1760
},
{
"epoch": 4.43,
"learning_rate": 3.7771587743732592e-06,
"loss": 0.1216,
"step": 1770
},
{
"epoch": 4.46,
"learning_rate": 3.6100278551532034e-06,
"loss": 0.1246,
"step": 1780
},
{
"epoch": 4.48,
"learning_rate": 3.4428969359331475e-06,
"loss": 0.1313,
"step": 1790
},
{
"epoch": 4.51,
"learning_rate": 3.275766016713092e-06,
"loss": 0.136,
"step": 1800
},
{
"epoch": 4.53,
"learning_rate": 3.108635097493036e-06,
"loss": 0.1494,
"step": 1810
},
{
"epoch": 4.56,
"learning_rate": 2.9415041782729803e-06,
"loss": 0.1381,
"step": 1820
},
{
"epoch": 4.58,
"learning_rate": 2.774373259052925e-06,
"loss": 0.1621,
"step": 1830
},
{
"epoch": 4.61,
"learning_rate": 2.607242339832869e-06,
"loss": 0.1307,
"step": 1840
},
{
"epoch": 4.63,
"learning_rate": 2.4401114206128136e-06,
"loss": 0.1164,
"step": 1850
},
{
"epoch": 4.66,
"learning_rate": 2.2729805013927577e-06,
"loss": 0.128,
"step": 1860
},
{
"epoch": 4.68,
"learning_rate": 2.1058495821727023e-06,
"loss": 0.1226,
"step": 1870
},
{
"epoch": 4.71,
"learning_rate": 1.9387186629526464e-06,
"loss": 0.1234,
"step": 1880
},
{
"epoch": 4.73,
"learning_rate": 1.7715877437325906e-06,
"loss": 0.1666,
"step": 1890
},
{
"epoch": 4.76,
"learning_rate": 1.604456824512535e-06,
"loss": 0.1072,
"step": 1900
},
{
"epoch": 4.78,
"learning_rate": 1.437325905292479e-06,
"loss": 0.1151,
"step": 1910
},
{
"epoch": 4.81,
"learning_rate": 1.2701949860724234e-06,
"loss": 0.1556,
"step": 1920
},
{
"epoch": 4.83,
"learning_rate": 1.1030640668523677e-06,
"loss": 0.1222,
"step": 1930
},
{
"epoch": 4.86,
"learning_rate": 9.35933147632312e-07,
"loss": 0.1251,
"step": 1940
},
{
"epoch": 4.88,
"learning_rate": 7.688022284122563e-07,
"loss": 0.1262,
"step": 1950
},
{
"epoch": 4.91,
"learning_rate": 6.016713091922006e-07,
"loss": 0.1096,
"step": 1960
},
{
"epoch": 4.93,
"learning_rate": 4.3454038997214486e-07,
"loss": 0.1115,
"step": 1970
},
{
"epoch": 4.96,
"learning_rate": 2.6740947075208915e-07,
"loss": 0.1065,
"step": 1980
},
{
"epoch": 4.98,
"learning_rate": 1.0027855153203343e-07,
"loss": 0.1307,
"step": 1990
},
{
"epoch": 5.0,
"eval_accuracy": 0.9830832597822889,
"eval_loss": 0.07888180762529373,
"eval_runtime": 13.938,
"eval_samples_per_second": 487.73,
"eval_steps_per_second": 15.282,
"step": 1995
},
{
"epoch": 5.0,
"step": 1995,
"total_flos": 2.3180194781952e+18,
"train_loss": 0.39961676239071037,
"train_runtime": 1167.3183,
"train_samples_per_second": 218.852,
"train_steps_per_second": 1.709
}
],
"logging_steps": 10,
"max_steps": 1995,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 2.3180194781952e+18,
"trial_name": null,
"trial_params": null
}