PedroSampaio's picture
End of training
e99d9d4
{
"best_metric": 0.9991625528913963,
"best_model_checkpoint": "vit-base-patch16-224-in21k-fruits-360-16-7/checkpoint-4231",
"epoch": 6.995036634365398,
"eval_steps": 500,
"global_step": 7399,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 6.756756756756758e-07,
"loss": 4.7408,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 1.3513513513513515e-06,
"loss": 4.7357,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 2.0270270270270273e-06,
"loss": 4.7311,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 2.702702702702703e-06,
"loss": 4.7236,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 3.3783783783783788e-06,
"loss": 4.7226,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 4.0540540540540545e-06,
"loss": 4.7061,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 4.72972972972973e-06,
"loss": 4.688,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 5.405405405405406e-06,
"loss": 4.6835,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 6.081081081081082e-06,
"loss": 4.6623,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 6.7567567567567575e-06,
"loss": 4.6482,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 7.432432432432433e-06,
"loss": 4.6329,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 8.108108108108109e-06,
"loss": 4.6103,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 8.783783783783785e-06,
"loss": 4.5847,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 9.45945945945946e-06,
"loss": 4.5388,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 1.0135135135135136e-05,
"loss": 4.5186,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 1.0810810810810812e-05,
"loss": 4.4828,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 1.1486486486486488e-05,
"loss": 4.4418,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 1.2162162162162164e-05,
"loss": 4.4053,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 1.2837837837837838e-05,
"loss": 4.3534,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 1.3513513513513515e-05,
"loss": 4.3042,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 1.4189189189189189e-05,
"loss": 4.2399,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 1.4864864864864867e-05,
"loss": 4.2144,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 1.554054054054054e-05,
"loss": 4.1902,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 1.6216216216216218e-05,
"loss": 4.1009,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 1.6891891891891892e-05,
"loss": 4.0529,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 1.756756756756757e-05,
"loss": 4.0103,
"step": 260
},
{
"epoch": 0.26,
"learning_rate": 1.8243243243243244e-05,
"loss": 3.9411,
"step": 270
},
{
"epoch": 0.26,
"learning_rate": 1.891891891891892e-05,
"loss": 3.9155,
"step": 280
},
{
"epoch": 0.27,
"learning_rate": 1.9594594594594595e-05,
"loss": 3.7913,
"step": 290
},
{
"epoch": 0.28,
"learning_rate": 2.0270270270270273e-05,
"loss": 3.775,
"step": 300
},
{
"epoch": 0.29,
"learning_rate": 2.0945945945945947e-05,
"loss": 3.7204,
"step": 310
},
{
"epoch": 0.3,
"learning_rate": 2.1621621621621624e-05,
"loss": 3.6663,
"step": 320
},
{
"epoch": 0.31,
"learning_rate": 2.2297297297297298e-05,
"loss": 3.6078,
"step": 330
},
{
"epoch": 0.32,
"learning_rate": 2.2972972972972976e-05,
"loss": 3.5168,
"step": 340
},
{
"epoch": 0.33,
"learning_rate": 2.364864864864865e-05,
"loss": 3.4668,
"step": 350
},
{
"epoch": 0.34,
"learning_rate": 2.4324324324324327e-05,
"loss": 3.369,
"step": 360
},
{
"epoch": 0.35,
"learning_rate": 2.5e-05,
"loss": 3.3425,
"step": 370
},
{
"epoch": 0.36,
"learning_rate": 2.5675675675675675e-05,
"loss": 3.2829,
"step": 380
},
{
"epoch": 0.37,
"learning_rate": 2.635135135135135e-05,
"loss": 3.2168,
"step": 390
},
{
"epoch": 0.38,
"learning_rate": 2.702702702702703e-05,
"loss": 3.1507,
"step": 400
},
{
"epoch": 0.39,
"learning_rate": 2.7702702702702704e-05,
"loss": 3.13,
"step": 410
},
{
"epoch": 0.4,
"learning_rate": 2.8378378378378378e-05,
"loss": 3.0482,
"step": 420
},
{
"epoch": 0.41,
"learning_rate": 2.9054054054054052e-05,
"loss": 2.9662,
"step": 430
},
{
"epoch": 0.42,
"learning_rate": 2.9729729729729733e-05,
"loss": 2.8872,
"step": 440
},
{
"epoch": 0.43,
"learning_rate": 3.0405405405405407e-05,
"loss": 2.8515,
"step": 450
},
{
"epoch": 0.43,
"learning_rate": 3.108108108108108e-05,
"loss": 2.8076,
"step": 460
},
{
"epoch": 0.44,
"learning_rate": 3.175675675675676e-05,
"loss": 2.7156,
"step": 470
},
{
"epoch": 0.45,
"learning_rate": 3.2432432432432436e-05,
"loss": 2.6701,
"step": 480
},
{
"epoch": 0.46,
"learning_rate": 3.310810810810811e-05,
"loss": 2.6437,
"step": 490
},
{
"epoch": 0.47,
"learning_rate": 3.3783783783783784e-05,
"loss": 2.5387,
"step": 500
},
{
"epoch": 0.48,
"learning_rate": 3.445945945945946e-05,
"loss": 2.4826,
"step": 510
},
{
"epoch": 0.49,
"learning_rate": 3.513513513513514e-05,
"loss": 2.4394,
"step": 520
},
{
"epoch": 0.5,
"learning_rate": 3.581081081081081e-05,
"loss": 2.4068,
"step": 530
},
{
"epoch": 0.51,
"learning_rate": 3.648648648648649e-05,
"loss": 2.3375,
"step": 540
},
{
"epoch": 0.52,
"learning_rate": 3.7162162162162165e-05,
"loss": 2.2659,
"step": 550
},
{
"epoch": 0.53,
"learning_rate": 3.783783783783784e-05,
"loss": 2.2681,
"step": 560
},
{
"epoch": 0.54,
"learning_rate": 3.851351351351351e-05,
"loss": 2.1877,
"step": 570
},
{
"epoch": 0.55,
"learning_rate": 3.918918918918919e-05,
"loss": 2.175,
"step": 580
},
{
"epoch": 0.56,
"learning_rate": 3.986486486486487e-05,
"loss": 2.0828,
"step": 590
},
{
"epoch": 0.57,
"learning_rate": 4.0540540540540545e-05,
"loss": 2.0032,
"step": 600
},
{
"epoch": 0.58,
"learning_rate": 4.1216216216216216e-05,
"loss": 1.9624,
"step": 610
},
{
"epoch": 0.59,
"learning_rate": 4.189189189189189e-05,
"loss": 1.9754,
"step": 620
},
{
"epoch": 0.6,
"learning_rate": 4.256756756756757e-05,
"loss": 1.9027,
"step": 630
},
{
"epoch": 0.61,
"learning_rate": 4.324324324324325e-05,
"loss": 1.8227,
"step": 640
},
{
"epoch": 0.61,
"learning_rate": 4.391891891891892e-05,
"loss": 1.7568,
"step": 650
},
{
"epoch": 0.62,
"learning_rate": 4.4594594594594596e-05,
"loss": 1.7081,
"step": 660
},
{
"epoch": 0.63,
"learning_rate": 4.5270270270270274e-05,
"loss": 1.6812,
"step": 670
},
{
"epoch": 0.64,
"learning_rate": 4.594594594594595e-05,
"loss": 1.5847,
"step": 680
},
{
"epoch": 0.65,
"learning_rate": 4.662162162162162e-05,
"loss": 1.5732,
"step": 690
},
{
"epoch": 0.66,
"learning_rate": 4.72972972972973e-05,
"loss": 1.525,
"step": 700
},
{
"epoch": 0.67,
"learning_rate": 4.797297297297298e-05,
"loss": 1.4475,
"step": 710
},
{
"epoch": 0.68,
"learning_rate": 4.8648648648648654e-05,
"loss": 1.4424,
"step": 720
},
{
"epoch": 0.69,
"learning_rate": 4.9324324324324325e-05,
"loss": 1.3733,
"step": 730
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 1.3017,
"step": 740
},
{
"epoch": 0.71,
"learning_rate": 4.992491365069831e-05,
"loss": 1.3203,
"step": 750
},
{
"epoch": 0.72,
"learning_rate": 4.984982730139661e-05,
"loss": 1.2573,
"step": 760
},
{
"epoch": 0.73,
"learning_rate": 4.977474095209491e-05,
"loss": 1.2189,
"step": 770
},
{
"epoch": 0.74,
"learning_rate": 4.9699654602793215e-05,
"loss": 1.1907,
"step": 780
},
{
"epoch": 0.75,
"learning_rate": 4.9624568253491515e-05,
"loss": 1.0897,
"step": 790
},
{
"epoch": 0.76,
"learning_rate": 4.954948190418982e-05,
"loss": 1.0683,
"step": 800
},
{
"epoch": 0.77,
"learning_rate": 4.947439555488813e-05,
"loss": 1.0816,
"step": 810
},
{
"epoch": 0.78,
"learning_rate": 4.939930920558643e-05,
"loss": 1.0097,
"step": 820
},
{
"epoch": 0.78,
"learning_rate": 4.932422285628473e-05,
"loss": 0.9751,
"step": 830
},
{
"epoch": 0.79,
"learning_rate": 4.9249136506983033e-05,
"loss": 0.9478,
"step": 840
},
{
"epoch": 0.8,
"learning_rate": 4.917405015768133e-05,
"loss": 0.9171,
"step": 850
},
{
"epoch": 0.81,
"learning_rate": 4.909896380837964e-05,
"loss": 0.8877,
"step": 860
},
{
"epoch": 0.82,
"learning_rate": 4.9023877459077946e-05,
"loss": 0.8512,
"step": 870
},
{
"epoch": 0.83,
"learning_rate": 4.8948791109776246e-05,
"loss": 0.8163,
"step": 880
},
{
"epoch": 0.84,
"learning_rate": 4.8873704760474546e-05,
"loss": 0.7922,
"step": 890
},
{
"epoch": 0.85,
"learning_rate": 4.879861841117285e-05,
"loss": 0.7531,
"step": 900
},
{
"epoch": 0.86,
"learning_rate": 4.872353206187115e-05,
"loss": 0.7509,
"step": 910
},
{
"epoch": 0.87,
"learning_rate": 4.864844571256946e-05,
"loss": 0.6975,
"step": 920
},
{
"epoch": 0.88,
"learning_rate": 4.8573359363267765e-05,
"loss": 0.6904,
"step": 930
},
{
"epoch": 0.89,
"learning_rate": 4.8498273013966065e-05,
"loss": 0.64,
"step": 940
},
{
"epoch": 0.9,
"learning_rate": 4.8423186664664364e-05,
"loss": 0.6395,
"step": 950
},
{
"epoch": 0.91,
"learning_rate": 4.834810031536267e-05,
"loss": 0.6603,
"step": 960
},
{
"epoch": 0.92,
"learning_rate": 4.827301396606097e-05,
"loss": 0.6032,
"step": 970
},
{
"epoch": 0.93,
"learning_rate": 4.819792761675928e-05,
"loss": 0.5898,
"step": 980
},
{
"epoch": 0.94,
"learning_rate": 4.8122841267457583e-05,
"loss": 0.5707,
"step": 990
},
{
"epoch": 0.95,
"learning_rate": 4.8047754918155876e-05,
"loss": 0.555,
"step": 1000
},
{
"epoch": 0.95,
"learning_rate": 4.797266856885418e-05,
"loss": 0.5239,
"step": 1010
},
{
"epoch": 0.96,
"learning_rate": 4.789758221955249e-05,
"loss": 0.5193,
"step": 1020
},
{
"epoch": 0.97,
"learning_rate": 4.782249587025079e-05,
"loss": 0.4723,
"step": 1030
},
{
"epoch": 0.98,
"learning_rate": 4.7747409520949096e-05,
"loss": 0.4888,
"step": 1040
},
{
"epoch": 0.99,
"learning_rate": 4.7672323171647395e-05,
"loss": 0.4608,
"step": 1050
},
{
"epoch": 1.0,
"eval_accuracy": 0.9983251057827927,
"eval_loss": 0.41809961199760437,
"eval_runtime": 123.358,
"eval_samples_per_second": 183.92,
"eval_steps_per_second": 11.495,
"step": 1057
},
{
"epoch": 1.0,
"learning_rate": 4.7597236822345695e-05,
"loss": 0.4578,
"step": 1060
},
{
"epoch": 1.01,
"learning_rate": 4.7522150473044e-05,
"loss": 0.453,
"step": 1070
},
{
"epoch": 1.02,
"learning_rate": 4.744706412374231e-05,
"loss": 0.4272,
"step": 1080
},
{
"epoch": 1.03,
"learning_rate": 4.737197777444061e-05,
"loss": 0.4221,
"step": 1090
},
{
"epoch": 1.04,
"learning_rate": 4.7296891425138914e-05,
"loss": 0.3859,
"step": 1100
},
{
"epoch": 1.05,
"learning_rate": 4.7221805075837214e-05,
"loss": 0.3549,
"step": 1110
},
{
"epoch": 1.06,
"learning_rate": 4.7146718726535514e-05,
"loss": 0.3656,
"step": 1120
},
{
"epoch": 1.07,
"learning_rate": 4.707163237723382e-05,
"loss": 0.3614,
"step": 1130
},
{
"epoch": 1.08,
"learning_rate": 4.699654602793213e-05,
"loss": 0.3592,
"step": 1140
},
{
"epoch": 1.09,
"learning_rate": 4.6921459678630426e-05,
"loss": 0.3374,
"step": 1150
},
{
"epoch": 1.1,
"learning_rate": 4.684637332932873e-05,
"loss": 0.3392,
"step": 1160
},
{
"epoch": 1.11,
"learning_rate": 4.677128698002703e-05,
"loss": 0.3172,
"step": 1170
},
{
"epoch": 1.12,
"learning_rate": 4.669620063072533e-05,
"loss": 0.2892,
"step": 1180
},
{
"epoch": 1.13,
"learning_rate": 4.662111428142364e-05,
"loss": 0.3023,
"step": 1190
},
{
"epoch": 1.13,
"learning_rate": 4.6546027932121945e-05,
"loss": 0.3214,
"step": 1200
},
{
"epoch": 1.14,
"learning_rate": 4.6470941582820245e-05,
"loss": 0.2754,
"step": 1210
},
{
"epoch": 1.15,
"learning_rate": 4.639585523351855e-05,
"loss": 0.2921,
"step": 1220
},
{
"epoch": 1.16,
"learning_rate": 4.632076888421685e-05,
"loss": 0.2655,
"step": 1230
},
{
"epoch": 1.17,
"learning_rate": 4.624568253491515e-05,
"loss": 0.2539,
"step": 1240
},
{
"epoch": 1.18,
"learning_rate": 4.617059618561346e-05,
"loss": 0.2815,
"step": 1250
},
{
"epoch": 1.19,
"learning_rate": 4.6095509836311764e-05,
"loss": 0.2576,
"step": 1260
},
{
"epoch": 1.2,
"learning_rate": 4.6020423487010064e-05,
"loss": 0.2371,
"step": 1270
},
{
"epoch": 1.21,
"learning_rate": 4.594533713770836e-05,
"loss": 0.2363,
"step": 1280
},
{
"epoch": 1.22,
"learning_rate": 4.587025078840667e-05,
"loss": 0.2267,
"step": 1290
},
{
"epoch": 1.23,
"learning_rate": 4.579516443910497e-05,
"loss": 0.2229,
"step": 1300
},
{
"epoch": 1.24,
"learning_rate": 4.5720078089803276e-05,
"loss": 0.2253,
"step": 1310
},
{
"epoch": 1.25,
"learning_rate": 4.564499174050158e-05,
"loss": 0.2202,
"step": 1320
},
{
"epoch": 1.26,
"learning_rate": 4.556990539119988e-05,
"loss": 0.213,
"step": 1330
},
{
"epoch": 1.27,
"learning_rate": 4.549481904189818e-05,
"loss": 0.2154,
"step": 1340
},
{
"epoch": 1.28,
"learning_rate": 4.541973269259649e-05,
"loss": 0.232,
"step": 1350
},
{
"epoch": 1.29,
"learning_rate": 4.534464634329479e-05,
"loss": 0.1958,
"step": 1360
},
{
"epoch": 1.3,
"learning_rate": 4.5269559993993095e-05,
"loss": 0.1925,
"step": 1370
},
{
"epoch": 1.3,
"learning_rate": 4.51944736446914e-05,
"loss": 0.1843,
"step": 1380
},
{
"epoch": 1.31,
"learning_rate": 4.51193872953897e-05,
"loss": 0.2023,
"step": 1390
},
{
"epoch": 1.32,
"learning_rate": 4.5044300946088e-05,
"loss": 0.1824,
"step": 1400
},
{
"epoch": 1.33,
"learning_rate": 4.496921459678631e-05,
"loss": 0.192,
"step": 1410
},
{
"epoch": 1.34,
"learning_rate": 4.489412824748461e-05,
"loss": 0.1866,
"step": 1420
},
{
"epoch": 1.35,
"learning_rate": 4.481904189818291e-05,
"loss": 0.1911,
"step": 1430
},
{
"epoch": 1.36,
"learning_rate": 4.474395554888122e-05,
"loss": 0.1852,
"step": 1440
},
{
"epoch": 1.37,
"learning_rate": 4.466886919957951e-05,
"loss": 0.161,
"step": 1450
},
{
"epoch": 1.38,
"learning_rate": 4.459378285027782e-05,
"loss": 0.1599,
"step": 1460
},
{
"epoch": 1.39,
"learning_rate": 4.4518696500976126e-05,
"loss": 0.1633,
"step": 1470
},
{
"epoch": 1.4,
"learning_rate": 4.4443610151674425e-05,
"loss": 0.1602,
"step": 1480
},
{
"epoch": 1.41,
"learning_rate": 4.436852380237273e-05,
"loss": 0.1611,
"step": 1490
},
{
"epoch": 1.42,
"learning_rate": 4.429343745307103e-05,
"loss": 0.1495,
"step": 1500
},
{
"epoch": 1.43,
"learning_rate": 4.421835110376933e-05,
"loss": 0.1431,
"step": 1510
},
{
"epoch": 1.44,
"learning_rate": 4.414326475446764e-05,
"loss": 0.1508,
"step": 1520
},
{
"epoch": 1.45,
"learning_rate": 4.4068178405165944e-05,
"loss": 0.1491,
"step": 1530
},
{
"epoch": 1.46,
"learning_rate": 4.3993092055864244e-05,
"loss": 0.1412,
"step": 1540
},
{
"epoch": 1.47,
"learning_rate": 4.391800570656255e-05,
"loss": 0.1368,
"step": 1550
},
{
"epoch": 1.47,
"learning_rate": 4.384291935726085e-05,
"loss": 0.1417,
"step": 1560
},
{
"epoch": 1.48,
"learning_rate": 4.376783300795915e-05,
"loss": 0.1306,
"step": 1570
},
{
"epoch": 1.49,
"learning_rate": 4.3692746658657457e-05,
"loss": 0.1228,
"step": 1580
},
{
"epoch": 1.5,
"learning_rate": 4.361766030935576e-05,
"loss": 0.1382,
"step": 1590
},
{
"epoch": 1.51,
"learning_rate": 4.354257396005406e-05,
"loss": 0.1432,
"step": 1600
},
{
"epoch": 1.52,
"learning_rate": 4.346748761075237e-05,
"loss": 0.1276,
"step": 1610
},
{
"epoch": 1.53,
"learning_rate": 4.339240126145067e-05,
"loss": 0.1163,
"step": 1620
},
{
"epoch": 1.54,
"learning_rate": 4.331731491214897e-05,
"loss": 0.1262,
"step": 1630
},
{
"epoch": 1.55,
"learning_rate": 4.3242228562847275e-05,
"loss": 0.12,
"step": 1640
},
{
"epoch": 1.56,
"learning_rate": 4.316714221354558e-05,
"loss": 0.1478,
"step": 1650
},
{
"epoch": 1.57,
"learning_rate": 4.309205586424388e-05,
"loss": 0.1056,
"step": 1660
},
{
"epoch": 1.58,
"learning_rate": 4.301696951494219e-05,
"loss": 0.134,
"step": 1670
},
{
"epoch": 1.59,
"learning_rate": 4.294188316564049e-05,
"loss": 0.1122,
"step": 1680
},
{
"epoch": 1.6,
"learning_rate": 4.286679681633879e-05,
"loss": 0.1254,
"step": 1690
},
{
"epoch": 1.61,
"learning_rate": 4.2791710467037094e-05,
"loss": 0.1112,
"step": 1700
},
{
"epoch": 1.62,
"learning_rate": 4.27166241177354e-05,
"loss": 0.108,
"step": 1710
},
{
"epoch": 1.63,
"learning_rate": 4.26415377684337e-05,
"loss": 0.1002,
"step": 1720
},
{
"epoch": 1.64,
"learning_rate": 4.2566451419132e-05,
"loss": 0.1158,
"step": 1730
},
{
"epoch": 1.65,
"learning_rate": 4.2491365069830306e-05,
"loss": 0.1181,
"step": 1740
},
{
"epoch": 1.65,
"learning_rate": 4.2416278720528606e-05,
"loss": 0.0943,
"step": 1750
},
{
"epoch": 1.66,
"learning_rate": 4.234119237122691e-05,
"loss": 0.0977,
"step": 1760
},
{
"epoch": 1.67,
"learning_rate": 4.226610602192522e-05,
"loss": 0.1236,
"step": 1770
},
{
"epoch": 1.68,
"learning_rate": 4.219101967262352e-05,
"loss": 0.1342,
"step": 1780
},
{
"epoch": 1.69,
"learning_rate": 4.211593332332182e-05,
"loss": 0.1318,
"step": 1790
},
{
"epoch": 1.7,
"learning_rate": 4.2040846974020125e-05,
"loss": 0.1069,
"step": 1800
},
{
"epoch": 1.71,
"learning_rate": 4.196576062471843e-05,
"loss": 0.0979,
"step": 1810
},
{
"epoch": 1.72,
"learning_rate": 4.189067427541673e-05,
"loss": 0.0872,
"step": 1820
},
{
"epoch": 1.73,
"learning_rate": 4.181558792611504e-05,
"loss": 0.0968,
"step": 1830
},
{
"epoch": 1.74,
"learning_rate": 4.174050157681334e-05,
"loss": 0.0945,
"step": 1840
},
{
"epoch": 1.75,
"learning_rate": 4.166541522751164e-05,
"loss": 0.1174,
"step": 1850
},
{
"epoch": 1.76,
"learning_rate": 4.1590328878209944e-05,
"loss": 0.1135,
"step": 1860
},
{
"epoch": 1.77,
"learning_rate": 4.151524252890825e-05,
"loss": 0.1158,
"step": 1870
},
{
"epoch": 1.78,
"learning_rate": 4.144015617960655e-05,
"loss": 0.115,
"step": 1880
},
{
"epoch": 1.79,
"learning_rate": 4.1365069830304856e-05,
"loss": 0.1124,
"step": 1890
},
{
"epoch": 1.8,
"learning_rate": 4.1289983481003156e-05,
"loss": 0.1119,
"step": 1900
},
{
"epoch": 1.81,
"learning_rate": 4.1214897131701456e-05,
"loss": 0.0801,
"step": 1910
},
{
"epoch": 1.82,
"learning_rate": 4.113981078239976e-05,
"loss": 0.0824,
"step": 1920
},
{
"epoch": 1.82,
"learning_rate": 4.106472443309807e-05,
"loss": 0.0924,
"step": 1930
},
{
"epoch": 1.83,
"learning_rate": 4.098963808379637e-05,
"loss": 0.0934,
"step": 1940
},
{
"epoch": 1.84,
"learning_rate": 4.0914551734494675e-05,
"loss": 0.1003,
"step": 1950
},
{
"epoch": 1.85,
"learning_rate": 4.0839465385192975e-05,
"loss": 0.0803,
"step": 1960
},
{
"epoch": 1.86,
"learning_rate": 4.0764379035891274e-05,
"loss": 0.0659,
"step": 1970
},
{
"epoch": 1.87,
"learning_rate": 4.068929268658958e-05,
"loss": 0.0803,
"step": 1980
},
{
"epoch": 1.88,
"learning_rate": 4.061420633728789e-05,
"loss": 0.0761,
"step": 1990
},
{
"epoch": 1.89,
"learning_rate": 4.053911998798619e-05,
"loss": 0.0856,
"step": 2000
},
{
"epoch": 1.9,
"learning_rate": 4.046403363868449e-05,
"loss": 0.0807,
"step": 2010
},
{
"epoch": 1.91,
"learning_rate": 4.038894728938279e-05,
"loss": 0.0761,
"step": 2020
},
{
"epoch": 1.92,
"learning_rate": 4.031386094008109e-05,
"loss": 0.0922,
"step": 2030
},
{
"epoch": 1.93,
"learning_rate": 4.02387745907794e-05,
"loss": 0.0703,
"step": 2040
},
{
"epoch": 1.94,
"learning_rate": 4.0163688241477706e-05,
"loss": 0.0738,
"step": 2050
},
{
"epoch": 1.95,
"learning_rate": 4.0088601892176006e-05,
"loss": 0.0817,
"step": 2060
},
{
"epoch": 1.96,
"learning_rate": 4.0013515542874305e-05,
"loss": 0.0709,
"step": 2070
},
{
"epoch": 1.97,
"learning_rate": 3.993842919357261e-05,
"loss": 0.0646,
"step": 2080
},
{
"epoch": 1.98,
"learning_rate": 3.986334284427091e-05,
"loss": 0.0754,
"step": 2090
},
{
"epoch": 1.99,
"learning_rate": 3.978825649496922e-05,
"loss": 0.0705,
"step": 2100
},
{
"epoch": 1.99,
"learning_rate": 3.9713170145667525e-05,
"loss": 0.0699,
"step": 2110
},
{
"epoch": 2.0,
"eval_accuracy": 0.995283850493653,
"eval_loss": 0.06486628204584122,
"eval_runtime": 123.5071,
"eval_samples_per_second": 183.698,
"eval_steps_per_second": 11.481,
"step": 2115
},
{
"epoch": 2.0,
"learning_rate": 3.9638083796365824e-05,
"loss": 0.0801,
"step": 2120
},
{
"epoch": 2.01,
"learning_rate": 3.9562997447064124e-05,
"loss": 0.0714,
"step": 2130
},
{
"epoch": 2.02,
"learning_rate": 3.948791109776243e-05,
"loss": 0.074,
"step": 2140
},
{
"epoch": 2.03,
"learning_rate": 3.941282474846073e-05,
"loss": 0.0726,
"step": 2150
},
{
"epoch": 2.04,
"learning_rate": 3.933773839915904e-05,
"loss": 0.0702,
"step": 2160
},
{
"epoch": 2.05,
"learning_rate": 3.926265204985734e-05,
"loss": 0.0709,
"step": 2170
},
{
"epoch": 2.06,
"learning_rate": 3.918756570055564e-05,
"loss": 0.0766,
"step": 2180
},
{
"epoch": 2.07,
"learning_rate": 3.911247935125394e-05,
"loss": 0.0757,
"step": 2190
},
{
"epoch": 2.08,
"learning_rate": 3.903739300195225e-05,
"loss": 0.062,
"step": 2200
},
{
"epoch": 2.09,
"learning_rate": 3.896230665265055e-05,
"loss": 0.0695,
"step": 2210
},
{
"epoch": 2.1,
"learning_rate": 3.8887220303348855e-05,
"loss": 0.0558,
"step": 2220
},
{
"epoch": 2.11,
"learning_rate": 3.8812133954047155e-05,
"loss": 0.059,
"step": 2230
},
{
"epoch": 2.12,
"learning_rate": 3.8737047604745455e-05,
"loss": 0.0605,
"step": 2240
},
{
"epoch": 2.13,
"learning_rate": 3.866196125544376e-05,
"loss": 0.0444,
"step": 2250
},
{
"epoch": 2.14,
"learning_rate": 3.858687490614207e-05,
"loss": 0.0516,
"step": 2260
},
{
"epoch": 2.15,
"learning_rate": 3.851178855684037e-05,
"loss": 0.0572,
"step": 2270
},
{
"epoch": 2.16,
"learning_rate": 3.8436702207538674e-05,
"loss": 0.0653,
"step": 2280
},
{
"epoch": 2.16,
"learning_rate": 3.8361615858236974e-05,
"loss": 0.0905,
"step": 2290
},
{
"epoch": 2.17,
"learning_rate": 3.8286529508935273e-05,
"loss": 0.0704,
"step": 2300
},
{
"epoch": 2.18,
"learning_rate": 3.821144315963358e-05,
"loss": 0.0565,
"step": 2310
},
{
"epoch": 2.19,
"learning_rate": 3.8136356810331886e-05,
"loss": 0.0587,
"step": 2320
},
{
"epoch": 2.2,
"learning_rate": 3.8061270461030186e-05,
"loss": 0.0622,
"step": 2330
},
{
"epoch": 2.21,
"learning_rate": 3.798618411172849e-05,
"loss": 0.0567,
"step": 2340
},
{
"epoch": 2.22,
"learning_rate": 3.791109776242679e-05,
"loss": 0.0488,
"step": 2350
},
{
"epoch": 2.23,
"learning_rate": 3.783601141312509e-05,
"loss": 0.0595,
"step": 2360
},
{
"epoch": 2.24,
"learning_rate": 3.77609250638234e-05,
"loss": 0.0643,
"step": 2370
},
{
"epoch": 2.25,
"learning_rate": 3.7685838714521705e-05,
"loss": 0.0538,
"step": 2380
},
{
"epoch": 2.26,
"learning_rate": 3.7610752365220005e-05,
"loss": 0.0407,
"step": 2390
},
{
"epoch": 2.27,
"learning_rate": 3.753566601591831e-05,
"loss": 0.0427,
"step": 2400
},
{
"epoch": 2.28,
"learning_rate": 3.746057966661661e-05,
"loss": 0.0493,
"step": 2410
},
{
"epoch": 2.29,
"learning_rate": 3.738549331731491e-05,
"loss": 0.0678,
"step": 2420
},
{
"epoch": 2.3,
"learning_rate": 3.731040696801322e-05,
"loss": 0.0567,
"step": 2430
},
{
"epoch": 2.31,
"learning_rate": 3.7235320618711524e-05,
"loss": 0.0559,
"step": 2440
},
{
"epoch": 2.32,
"learning_rate": 3.7160234269409823e-05,
"loss": 0.0381,
"step": 2450
},
{
"epoch": 2.33,
"learning_rate": 3.708514792010812e-05,
"loss": 0.0371,
"step": 2460
},
{
"epoch": 2.34,
"learning_rate": 3.701006157080643e-05,
"loss": 0.0367,
"step": 2470
},
{
"epoch": 2.34,
"learning_rate": 3.693497522150473e-05,
"loss": 0.0415,
"step": 2480
},
{
"epoch": 2.35,
"learning_rate": 3.6859888872203036e-05,
"loss": 0.0636,
"step": 2490
},
{
"epoch": 2.36,
"learning_rate": 3.678480252290134e-05,
"loss": 0.0519,
"step": 2500
},
{
"epoch": 2.37,
"learning_rate": 3.670971617359964e-05,
"loss": 0.0487,
"step": 2510
},
{
"epoch": 2.38,
"learning_rate": 3.663462982429794e-05,
"loss": 0.0421,
"step": 2520
},
{
"epoch": 2.39,
"learning_rate": 3.655954347499625e-05,
"loss": 0.0546,
"step": 2530
},
{
"epoch": 2.4,
"learning_rate": 3.648445712569455e-05,
"loss": 0.0461,
"step": 2540
},
{
"epoch": 2.41,
"learning_rate": 3.6409370776392855e-05,
"loss": 0.0533,
"step": 2550
},
{
"epoch": 2.42,
"learning_rate": 3.633428442709116e-05,
"loss": 0.0446,
"step": 2560
},
{
"epoch": 2.43,
"learning_rate": 3.625919807778946e-05,
"loss": 0.0611,
"step": 2570
},
{
"epoch": 2.44,
"learning_rate": 3.618411172848776e-05,
"loss": 0.0399,
"step": 2580
},
{
"epoch": 2.45,
"learning_rate": 3.610902537918607e-05,
"loss": 0.041,
"step": 2590
},
{
"epoch": 2.46,
"learning_rate": 3.603393902988437e-05,
"loss": 0.0601,
"step": 2600
},
{
"epoch": 2.47,
"learning_rate": 3.595885268058267e-05,
"loss": 0.0536,
"step": 2610
},
{
"epoch": 2.48,
"learning_rate": 3.588376633128098e-05,
"loss": 0.0419,
"step": 2620
},
{
"epoch": 2.49,
"learning_rate": 3.580867998197928e-05,
"loss": 0.0454,
"step": 2630
},
{
"epoch": 2.5,
"learning_rate": 3.573359363267758e-05,
"loss": 0.0379,
"step": 2640
},
{
"epoch": 2.51,
"learning_rate": 3.5658507283375886e-05,
"loss": 0.041,
"step": 2650
},
{
"epoch": 2.51,
"learning_rate": 3.5583420934074185e-05,
"loss": 0.037,
"step": 2660
},
{
"epoch": 2.52,
"learning_rate": 3.550833458477249e-05,
"loss": 0.04,
"step": 2670
},
{
"epoch": 2.53,
"learning_rate": 3.54332482354708e-05,
"loss": 0.0351,
"step": 2680
},
{
"epoch": 2.54,
"learning_rate": 3.535816188616909e-05,
"loss": 0.0321,
"step": 2690
},
{
"epoch": 2.55,
"learning_rate": 3.52830755368674e-05,
"loss": 0.0404,
"step": 2700
},
{
"epoch": 2.56,
"learning_rate": 3.5207989187565704e-05,
"loss": 0.0401,
"step": 2710
},
{
"epoch": 2.57,
"learning_rate": 3.5132902838264004e-05,
"loss": 0.0375,
"step": 2720
},
{
"epoch": 2.58,
"learning_rate": 3.505781648896231e-05,
"loss": 0.0449,
"step": 2730
},
{
"epoch": 2.59,
"learning_rate": 3.498273013966061e-05,
"loss": 0.0354,
"step": 2740
},
{
"epoch": 2.6,
"learning_rate": 3.490764379035891e-05,
"loss": 0.036,
"step": 2750
},
{
"epoch": 2.61,
"learning_rate": 3.4832557441057216e-05,
"loss": 0.0359,
"step": 2760
},
{
"epoch": 2.62,
"learning_rate": 3.475747109175552e-05,
"loss": 0.0467,
"step": 2770
},
{
"epoch": 2.63,
"learning_rate": 3.468238474245382e-05,
"loss": 0.0572,
"step": 2780
},
{
"epoch": 2.64,
"learning_rate": 3.460729839315213e-05,
"loss": 0.0499,
"step": 2790
},
{
"epoch": 2.65,
"learning_rate": 3.453221204385043e-05,
"loss": 0.0354,
"step": 2800
},
{
"epoch": 2.66,
"learning_rate": 3.445712569454873e-05,
"loss": 0.0341,
"step": 2810
},
{
"epoch": 2.67,
"learning_rate": 3.4382039345247035e-05,
"loss": 0.0455,
"step": 2820
},
{
"epoch": 2.68,
"learning_rate": 3.430695299594534e-05,
"loss": 0.0335,
"step": 2830
},
{
"epoch": 2.68,
"learning_rate": 3.423186664664364e-05,
"loss": 0.0358,
"step": 2840
},
{
"epoch": 2.69,
"learning_rate": 3.415678029734195e-05,
"loss": 0.0406,
"step": 2850
},
{
"epoch": 2.7,
"learning_rate": 3.408169394804025e-05,
"loss": 0.0297,
"step": 2860
},
{
"epoch": 2.71,
"learning_rate": 3.400660759873855e-05,
"loss": 0.0391,
"step": 2870
},
{
"epoch": 2.72,
"learning_rate": 3.3931521249436854e-05,
"loss": 0.0432,
"step": 2880
},
{
"epoch": 2.73,
"learning_rate": 3.385643490013516e-05,
"loss": 0.0415,
"step": 2890
},
{
"epoch": 2.74,
"learning_rate": 3.378134855083346e-05,
"loss": 0.0393,
"step": 2900
},
{
"epoch": 2.75,
"learning_rate": 3.3706262201531766e-05,
"loss": 0.0409,
"step": 2910
},
{
"epoch": 2.76,
"learning_rate": 3.3631175852230066e-05,
"loss": 0.0494,
"step": 2920
},
{
"epoch": 2.77,
"learning_rate": 3.3556089502928366e-05,
"loss": 0.0407,
"step": 2930
},
{
"epoch": 2.78,
"learning_rate": 3.348100315362667e-05,
"loss": 0.0341,
"step": 2940
},
{
"epoch": 2.79,
"learning_rate": 3.340591680432498e-05,
"loss": 0.0269,
"step": 2950
},
{
"epoch": 2.8,
"learning_rate": 3.333083045502328e-05,
"loss": 0.0355,
"step": 2960
},
{
"epoch": 2.81,
"learning_rate": 3.325574410572158e-05,
"loss": 0.0294,
"step": 2970
},
{
"epoch": 2.82,
"learning_rate": 3.3180657756419885e-05,
"loss": 0.0357,
"step": 2980
},
{
"epoch": 2.83,
"learning_rate": 3.3105571407118184e-05,
"loss": 0.0333,
"step": 2990
},
{
"epoch": 2.84,
"learning_rate": 3.303048505781649e-05,
"loss": 0.0304,
"step": 3000
},
{
"epoch": 2.85,
"learning_rate": 3.29553987085148e-05,
"loss": 0.0351,
"step": 3010
},
{
"epoch": 2.86,
"learning_rate": 3.28803123592131e-05,
"loss": 0.0246,
"step": 3020
},
{
"epoch": 2.86,
"learning_rate": 3.28052260099114e-05,
"loss": 0.0223,
"step": 3030
},
{
"epoch": 2.87,
"learning_rate": 3.27301396606097e-05,
"loss": 0.0316,
"step": 3040
},
{
"epoch": 2.88,
"learning_rate": 3.2655053311308e-05,
"loss": 0.0331,
"step": 3050
},
{
"epoch": 2.89,
"learning_rate": 3.257996696200631e-05,
"loss": 0.0308,
"step": 3060
},
{
"epoch": 2.9,
"learning_rate": 3.2504880612704616e-05,
"loss": 0.0391,
"step": 3070
},
{
"epoch": 2.91,
"learning_rate": 3.2429794263402916e-05,
"loss": 0.0238,
"step": 3080
},
{
"epoch": 2.92,
"learning_rate": 3.2354707914101215e-05,
"loss": 0.0226,
"step": 3090
},
{
"epoch": 2.93,
"learning_rate": 3.227962156479952e-05,
"loss": 0.0716,
"step": 3100
},
{
"epoch": 2.94,
"learning_rate": 3.220453521549782e-05,
"loss": 0.0468,
"step": 3110
},
{
"epoch": 2.95,
"learning_rate": 3.212944886619613e-05,
"loss": 0.0271,
"step": 3120
},
{
"epoch": 2.96,
"learning_rate": 3.2054362516894435e-05,
"loss": 0.037,
"step": 3130
},
{
"epoch": 2.97,
"learning_rate": 3.1979276167592734e-05,
"loss": 0.0459,
"step": 3140
},
{
"epoch": 2.98,
"learning_rate": 3.1904189818291034e-05,
"loss": 0.0281,
"step": 3150
},
{
"epoch": 2.99,
"learning_rate": 3.182910346898934e-05,
"loss": 0.0269,
"step": 3160
},
{
"epoch": 3.0,
"learning_rate": 3.175401711968764e-05,
"loss": 0.0313,
"step": 3170
},
{
"epoch": 3.0,
"eval_accuracy": 0.998589562764457,
"eval_loss": 0.024297082796692848,
"eval_runtime": 122.6446,
"eval_samples_per_second": 184.99,
"eval_steps_per_second": 11.562,
"step": 3173
},
{
"epoch": 3.01,
"learning_rate": 3.167893077038595e-05,
"loss": 0.0345,
"step": 3180
},
{
"epoch": 3.02,
"learning_rate": 3.1603844421084247e-05,
"loss": 0.031,
"step": 3190
},
{
"epoch": 3.03,
"learning_rate": 3.1528758071782546e-05,
"loss": 0.0319,
"step": 3200
},
{
"epoch": 3.03,
"learning_rate": 3.145367172248085e-05,
"loss": 0.036,
"step": 3210
},
{
"epoch": 3.04,
"learning_rate": 3.137858537317916e-05,
"loss": 0.0263,
"step": 3220
},
{
"epoch": 3.05,
"learning_rate": 3.130349902387746e-05,
"loss": 0.0291,
"step": 3230
},
{
"epoch": 3.06,
"learning_rate": 3.1228412674575765e-05,
"loss": 0.0321,
"step": 3240
},
{
"epoch": 3.07,
"learning_rate": 3.1153326325274065e-05,
"loss": 0.025,
"step": 3250
},
{
"epoch": 3.08,
"learning_rate": 3.1078239975972365e-05,
"loss": 0.0396,
"step": 3260
},
{
"epoch": 3.09,
"learning_rate": 3.100315362667067e-05,
"loss": 0.024,
"step": 3270
},
{
"epoch": 3.1,
"learning_rate": 3.092806727736898e-05,
"loss": 0.0319,
"step": 3280
},
{
"epoch": 3.11,
"learning_rate": 3.085298092806728e-05,
"loss": 0.0539,
"step": 3290
},
{
"epoch": 3.12,
"learning_rate": 3.0777894578765584e-05,
"loss": 0.0317,
"step": 3300
},
{
"epoch": 3.13,
"learning_rate": 3.0702808229463884e-05,
"loss": 0.0315,
"step": 3310
},
{
"epoch": 3.14,
"learning_rate": 3.0627721880162184e-05,
"loss": 0.0243,
"step": 3320
},
{
"epoch": 3.15,
"learning_rate": 3.055263553086049e-05,
"loss": 0.021,
"step": 3330
},
{
"epoch": 3.16,
"learning_rate": 3.0477549181558797e-05,
"loss": 0.0171,
"step": 3340
},
{
"epoch": 3.17,
"learning_rate": 3.0402462832257096e-05,
"loss": 0.0419,
"step": 3350
},
{
"epoch": 3.18,
"learning_rate": 3.03273764829554e-05,
"loss": 0.0461,
"step": 3360
},
{
"epoch": 3.19,
"learning_rate": 3.0252290133653706e-05,
"loss": 0.0351,
"step": 3370
},
{
"epoch": 3.2,
"learning_rate": 3.0177203784352006e-05,
"loss": 0.0409,
"step": 3380
},
{
"epoch": 3.2,
"learning_rate": 3.010211743505031e-05,
"loss": 0.0277,
"step": 3390
},
{
"epoch": 3.21,
"learning_rate": 3.0027031085748615e-05,
"loss": 0.0168,
"step": 3400
},
{
"epoch": 3.22,
"learning_rate": 2.995194473644691e-05,
"loss": 0.0215,
"step": 3410
},
{
"epoch": 3.23,
"learning_rate": 2.9876858387145218e-05,
"loss": 0.0445,
"step": 3420
},
{
"epoch": 3.24,
"learning_rate": 2.980177203784352e-05,
"loss": 0.0374,
"step": 3430
},
{
"epoch": 3.25,
"learning_rate": 2.972668568854182e-05,
"loss": 0.0345,
"step": 3440
},
{
"epoch": 3.26,
"learning_rate": 2.9651599339240127e-05,
"loss": 0.0264,
"step": 3450
},
{
"epoch": 3.27,
"learning_rate": 2.957651298993843e-05,
"loss": 0.0383,
"step": 3460
},
{
"epoch": 3.28,
"learning_rate": 2.950142664063673e-05,
"loss": 0.052,
"step": 3470
},
{
"epoch": 3.29,
"learning_rate": 2.9426340291335037e-05,
"loss": 0.0414,
"step": 3480
},
{
"epoch": 3.3,
"learning_rate": 2.935125394203334e-05,
"loss": 0.0275,
"step": 3490
},
{
"epoch": 3.31,
"learning_rate": 2.927616759273164e-05,
"loss": 0.0403,
"step": 3500
},
{
"epoch": 3.32,
"learning_rate": 2.9201081243429946e-05,
"loss": 0.0223,
"step": 3510
},
{
"epoch": 3.33,
"learning_rate": 2.912599489412825e-05,
"loss": 0.0418,
"step": 3520
},
{
"epoch": 3.34,
"learning_rate": 2.905090854482655e-05,
"loss": 0.0676,
"step": 3530
},
{
"epoch": 3.35,
"learning_rate": 2.8975822195524855e-05,
"loss": 0.0757,
"step": 3540
},
{
"epoch": 3.36,
"learning_rate": 2.890073584622316e-05,
"loss": 0.0323,
"step": 3550
},
{
"epoch": 3.37,
"learning_rate": 2.8825649496921458e-05,
"loss": 0.0269,
"step": 3560
},
{
"epoch": 3.38,
"learning_rate": 2.8750563147619765e-05,
"loss": 0.0454,
"step": 3570
},
{
"epoch": 3.38,
"learning_rate": 2.8675476798318068e-05,
"loss": 0.0333,
"step": 3580
},
{
"epoch": 3.39,
"learning_rate": 2.8600390449016367e-05,
"loss": 0.0284,
"step": 3590
},
{
"epoch": 3.4,
"learning_rate": 2.8525304099714674e-05,
"loss": 0.0358,
"step": 3600
},
{
"epoch": 3.41,
"learning_rate": 2.8450217750412977e-05,
"loss": 0.0338,
"step": 3610
},
{
"epoch": 3.42,
"learning_rate": 2.8375131401111277e-05,
"loss": 0.0196,
"step": 3620
},
{
"epoch": 3.43,
"learning_rate": 2.8300045051809583e-05,
"loss": 0.0389,
"step": 3630
},
{
"epoch": 3.44,
"learning_rate": 2.8224958702507886e-05,
"loss": 0.0368,
"step": 3640
},
{
"epoch": 3.45,
"learning_rate": 2.8149872353206186e-05,
"loss": 0.0294,
"step": 3650
},
{
"epoch": 3.46,
"learning_rate": 2.807478600390449e-05,
"loss": 0.0409,
"step": 3660
},
{
"epoch": 3.47,
"learning_rate": 2.7999699654602796e-05,
"loss": 0.0205,
"step": 3670
},
{
"epoch": 3.48,
"learning_rate": 2.7924613305301095e-05,
"loss": 0.0258,
"step": 3680
},
{
"epoch": 3.49,
"learning_rate": 2.78495269559994e-05,
"loss": 0.0199,
"step": 3690
},
{
"epoch": 3.5,
"learning_rate": 2.7774440606697705e-05,
"loss": 0.0149,
"step": 3700
},
{
"epoch": 3.51,
"learning_rate": 2.7699354257396005e-05,
"loss": 0.0158,
"step": 3710
},
{
"epoch": 3.52,
"learning_rate": 2.7624267908094308e-05,
"loss": 0.0189,
"step": 3720
},
{
"epoch": 3.53,
"learning_rate": 2.7549181558792614e-05,
"loss": 0.0151,
"step": 3730
},
{
"epoch": 3.54,
"learning_rate": 2.7474095209490914e-05,
"loss": 0.0241,
"step": 3740
},
{
"epoch": 3.55,
"learning_rate": 2.7399008860189217e-05,
"loss": 0.0268,
"step": 3750
},
{
"epoch": 3.55,
"learning_rate": 2.7323922510887524e-05,
"loss": 0.0387,
"step": 3760
},
{
"epoch": 3.56,
"learning_rate": 2.7248836161585823e-05,
"loss": 0.05,
"step": 3770
},
{
"epoch": 3.57,
"learning_rate": 2.7173749812284126e-05,
"loss": 0.0218,
"step": 3780
},
{
"epoch": 3.58,
"learning_rate": 2.7098663462982433e-05,
"loss": 0.0194,
"step": 3790
},
{
"epoch": 3.59,
"learning_rate": 2.7023577113680733e-05,
"loss": 0.0135,
"step": 3800
},
{
"epoch": 3.6,
"learning_rate": 2.6948490764379036e-05,
"loss": 0.0285,
"step": 3810
},
{
"epoch": 3.61,
"learning_rate": 2.6873404415077342e-05,
"loss": 0.0343,
"step": 3820
},
{
"epoch": 3.62,
"learning_rate": 2.6798318065775642e-05,
"loss": 0.0136,
"step": 3830
},
{
"epoch": 3.63,
"learning_rate": 2.6723231716473945e-05,
"loss": 0.0316,
"step": 3840
},
{
"epoch": 3.64,
"learning_rate": 2.664814536717225e-05,
"loss": 0.0159,
"step": 3850
},
{
"epoch": 3.65,
"learning_rate": 2.657305901787055e-05,
"loss": 0.0206,
"step": 3860
},
{
"epoch": 3.66,
"learning_rate": 2.6497972668568854e-05,
"loss": 0.0161,
"step": 3870
},
{
"epoch": 3.67,
"learning_rate": 2.642288631926716e-05,
"loss": 0.0133,
"step": 3880
},
{
"epoch": 3.68,
"learning_rate": 2.6347799969965464e-05,
"loss": 0.034,
"step": 3890
},
{
"epoch": 3.69,
"learning_rate": 2.6272713620663764e-05,
"loss": 0.0277,
"step": 3900
},
{
"epoch": 3.7,
"learning_rate": 2.619762727136207e-05,
"loss": 0.0198,
"step": 3910
},
{
"epoch": 3.71,
"learning_rate": 2.6122540922060373e-05,
"loss": 0.0128,
"step": 3920
},
{
"epoch": 3.72,
"learning_rate": 2.6047454572758673e-05,
"loss": 0.026,
"step": 3930
},
{
"epoch": 3.72,
"learning_rate": 2.5972368223456976e-05,
"loss": 0.0215,
"step": 3940
},
{
"epoch": 3.73,
"learning_rate": 2.5897281874155283e-05,
"loss": 0.0433,
"step": 3950
},
{
"epoch": 3.74,
"learning_rate": 2.5822195524853582e-05,
"loss": 0.0186,
"step": 3960
},
{
"epoch": 3.75,
"learning_rate": 2.5747109175551885e-05,
"loss": 0.0282,
"step": 3970
},
{
"epoch": 3.76,
"learning_rate": 2.5672022826250192e-05,
"loss": 0.0184,
"step": 3980
},
{
"epoch": 3.77,
"learning_rate": 2.559693647694849e-05,
"loss": 0.0201,
"step": 3990
},
{
"epoch": 3.78,
"learning_rate": 2.5521850127646795e-05,
"loss": 0.0327,
"step": 4000
},
{
"epoch": 3.79,
"learning_rate": 2.54467637783451e-05,
"loss": 0.0389,
"step": 4010
},
{
"epoch": 3.8,
"learning_rate": 2.53716774290434e-05,
"loss": 0.0295,
"step": 4020
},
{
"epoch": 3.81,
"learning_rate": 2.5296591079741704e-05,
"loss": 0.0125,
"step": 4030
},
{
"epoch": 3.82,
"learning_rate": 2.522150473044001e-05,
"loss": 0.0153,
"step": 4040
},
{
"epoch": 3.83,
"learning_rate": 2.514641838113831e-05,
"loss": 0.03,
"step": 4050
},
{
"epoch": 3.84,
"learning_rate": 2.5071332031836613e-05,
"loss": 0.0197,
"step": 4060
},
{
"epoch": 3.85,
"learning_rate": 2.4996245682534917e-05,
"loss": 0.014,
"step": 4070
},
{
"epoch": 3.86,
"learning_rate": 2.492115933323322e-05,
"loss": 0.0272,
"step": 4080
},
{
"epoch": 3.87,
"learning_rate": 2.4846072983931523e-05,
"loss": 0.0121,
"step": 4090
},
{
"epoch": 3.88,
"learning_rate": 2.4770986634629826e-05,
"loss": 0.0156,
"step": 4100
},
{
"epoch": 3.89,
"learning_rate": 2.469590028532813e-05,
"loss": 0.0402,
"step": 4110
},
{
"epoch": 3.9,
"learning_rate": 2.4620813936026432e-05,
"loss": 0.0117,
"step": 4120
},
{
"epoch": 3.9,
"learning_rate": 2.4545727586724735e-05,
"loss": 0.021,
"step": 4130
},
{
"epoch": 3.91,
"learning_rate": 2.4470641237423035e-05,
"loss": 0.0251,
"step": 4140
},
{
"epoch": 3.92,
"learning_rate": 2.439555488812134e-05,
"loss": 0.0145,
"step": 4150
},
{
"epoch": 3.93,
"learning_rate": 2.4320468538819644e-05,
"loss": 0.0186,
"step": 4160
},
{
"epoch": 3.94,
"learning_rate": 2.4245382189517944e-05,
"loss": 0.0153,
"step": 4170
},
{
"epoch": 3.95,
"learning_rate": 2.417029584021625e-05,
"loss": 0.0236,
"step": 4180
},
{
"epoch": 3.96,
"learning_rate": 2.4095209490914554e-05,
"loss": 0.0125,
"step": 4190
},
{
"epoch": 3.97,
"learning_rate": 2.4020123141612854e-05,
"loss": 0.0206,
"step": 4200
},
{
"epoch": 3.98,
"learning_rate": 2.394503679231116e-05,
"loss": 0.0244,
"step": 4210
},
{
"epoch": 3.99,
"learning_rate": 2.3869950443009463e-05,
"loss": 0.0125,
"step": 4220
},
{
"epoch": 4.0,
"learning_rate": 2.3794864093707763e-05,
"loss": 0.0143,
"step": 4230
},
{
"epoch": 4.0,
"eval_accuracy": 0.9991625528913963,
"eval_loss": 0.013120466843247414,
"eval_runtime": 128.2581,
"eval_samples_per_second": 176.893,
"eval_steps_per_second": 11.056,
"step": 4231
},
{
"epoch": 4.01,
"learning_rate": 2.371977774440607e-05,
"loss": 0.0196,
"step": 4240
},
{
"epoch": 4.02,
"learning_rate": 2.3644691395104372e-05,
"loss": 0.0145,
"step": 4250
},
{
"epoch": 4.03,
"learning_rate": 2.3569605045802672e-05,
"loss": 0.0221,
"step": 4260
},
{
"epoch": 4.04,
"learning_rate": 2.349451869650098e-05,
"loss": 0.0318,
"step": 4270
},
{
"epoch": 4.05,
"learning_rate": 2.341943234719928e-05,
"loss": 0.0227,
"step": 4280
},
{
"epoch": 4.06,
"learning_rate": 2.334434599789758e-05,
"loss": 0.0309,
"step": 4290
},
{
"epoch": 4.07,
"learning_rate": 2.3269259648595888e-05,
"loss": 0.0184,
"step": 4300
},
{
"epoch": 4.07,
"learning_rate": 2.3194173299294188e-05,
"loss": 0.0351,
"step": 4310
},
{
"epoch": 4.08,
"learning_rate": 2.311908694999249e-05,
"loss": 0.023,
"step": 4320
},
{
"epoch": 4.09,
"learning_rate": 2.3044000600690797e-05,
"loss": 0.0134,
"step": 4330
},
{
"epoch": 4.1,
"learning_rate": 2.2968914251389097e-05,
"loss": 0.0326,
"step": 4340
},
{
"epoch": 4.11,
"learning_rate": 2.28938279020874e-05,
"loss": 0.0189,
"step": 4350
},
{
"epoch": 4.12,
"learning_rate": 2.2818741552785707e-05,
"loss": 0.0109,
"step": 4360
},
{
"epoch": 4.13,
"learning_rate": 2.2743655203484006e-05,
"loss": 0.0117,
"step": 4370
},
{
"epoch": 4.14,
"learning_rate": 2.266856885418231e-05,
"loss": 0.017,
"step": 4380
},
{
"epoch": 4.15,
"learning_rate": 2.2593482504880616e-05,
"loss": 0.0118,
"step": 4390
},
{
"epoch": 4.16,
"learning_rate": 2.2518396155578916e-05,
"loss": 0.0097,
"step": 4400
},
{
"epoch": 4.17,
"learning_rate": 2.2443309806277222e-05,
"loss": 0.0391,
"step": 4410
},
{
"epoch": 4.18,
"learning_rate": 2.2368223456975522e-05,
"loss": 0.0091,
"step": 4420
},
{
"epoch": 4.19,
"learning_rate": 2.2293137107673825e-05,
"loss": 0.0227,
"step": 4430
},
{
"epoch": 4.2,
"learning_rate": 2.221805075837213e-05,
"loss": 0.0219,
"step": 4440
},
{
"epoch": 4.21,
"learning_rate": 2.214296440907043e-05,
"loss": 0.028,
"step": 4450
},
{
"epoch": 4.22,
"learning_rate": 2.2067878059768734e-05,
"loss": 0.0225,
"step": 4460
},
{
"epoch": 4.23,
"learning_rate": 2.199279171046704e-05,
"loss": 0.0101,
"step": 4470
},
{
"epoch": 4.24,
"learning_rate": 2.191770536116534e-05,
"loss": 0.0232,
"step": 4480
},
{
"epoch": 4.24,
"learning_rate": 2.1842619011863644e-05,
"loss": 0.0191,
"step": 4490
},
{
"epoch": 4.25,
"learning_rate": 2.176753266256195e-05,
"loss": 0.0251,
"step": 4500
},
{
"epoch": 4.26,
"learning_rate": 2.169244631326025e-05,
"loss": 0.0285,
"step": 4510
},
{
"epoch": 4.27,
"learning_rate": 2.1617359963958553e-05,
"loss": 0.0314,
"step": 4520
},
{
"epoch": 4.28,
"learning_rate": 2.1542273614656856e-05,
"loss": 0.0174,
"step": 4530
},
{
"epoch": 4.29,
"learning_rate": 2.146718726535516e-05,
"loss": 0.0122,
"step": 4540
},
{
"epoch": 4.3,
"learning_rate": 2.1392100916053462e-05,
"loss": 0.0287,
"step": 4550
},
{
"epoch": 4.31,
"learning_rate": 2.1317014566751765e-05,
"loss": 0.0163,
"step": 4560
},
{
"epoch": 4.32,
"learning_rate": 2.124192821745007e-05,
"loss": 0.0226,
"step": 4570
},
{
"epoch": 4.33,
"learning_rate": 2.116684186814837e-05,
"loss": 0.0114,
"step": 4580
},
{
"epoch": 4.34,
"learning_rate": 2.1091755518846675e-05,
"loss": 0.013,
"step": 4590
},
{
"epoch": 4.35,
"learning_rate": 2.1016669169544978e-05,
"loss": 0.0325,
"step": 4600
},
{
"epoch": 4.36,
"learning_rate": 2.094158282024328e-05,
"loss": 0.0131,
"step": 4610
},
{
"epoch": 4.37,
"learning_rate": 2.0866496470941584e-05,
"loss": 0.0146,
"step": 4620
},
{
"epoch": 4.38,
"learning_rate": 2.0791410121639887e-05,
"loss": 0.0134,
"step": 4630
},
{
"epoch": 4.39,
"learning_rate": 2.071632377233819e-05,
"loss": 0.0153,
"step": 4640
},
{
"epoch": 4.4,
"learning_rate": 2.0641237423036493e-05,
"loss": 0.0232,
"step": 4650
},
{
"epoch": 4.41,
"learning_rate": 2.0566151073734796e-05,
"loss": 0.0266,
"step": 4660
},
{
"epoch": 4.42,
"learning_rate": 2.04910647244331e-05,
"loss": 0.0097,
"step": 4670
},
{
"epoch": 4.42,
"learning_rate": 2.0415978375131403e-05,
"loss": 0.0279,
"step": 4680
},
{
"epoch": 4.43,
"learning_rate": 2.0340892025829706e-05,
"loss": 0.0248,
"step": 4690
},
{
"epoch": 4.44,
"learning_rate": 2.026580567652801e-05,
"loss": 0.0241,
"step": 4700
},
{
"epoch": 4.45,
"learning_rate": 2.0190719327226312e-05,
"loss": 0.0145,
"step": 4710
},
{
"epoch": 4.46,
"learning_rate": 2.0115632977924615e-05,
"loss": 0.0097,
"step": 4720
},
{
"epoch": 4.47,
"learning_rate": 2.0040546628622918e-05,
"loss": 0.0175,
"step": 4730
},
{
"epoch": 4.48,
"learning_rate": 1.996546027932122e-05,
"loss": 0.0295,
"step": 4740
},
{
"epoch": 4.49,
"learning_rate": 1.9890373930019524e-05,
"loss": 0.0195,
"step": 4750
},
{
"epoch": 4.5,
"learning_rate": 1.9815287580717824e-05,
"loss": 0.0195,
"step": 4760
},
{
"epoch": 4.51,
"learning_rate": 1.974020123141613e-05,
"loss": 0.0082,
"step": 4770
},
{
"epoch": 4.52,
"learning_rate": 1.9665114882114434e-05,
"loss": 0.0264,
"step": 4780
},
{
"epoch": 4.53,
"learning_rate": 1.9590028532812733e-05,
"loss": 0.0142,
"step": 4790
},
{
"epoch": 4.54,
"learning_rate": 1.951494218351104e-05,
"loss": 0.0163,
"step": 4800
},
{
"epoch": 4.55,
"learning_rate": 1.9439855834209343e-05,
"loss": 0.008,
"step": 4810
},
{
"epoch": 4.56,
"learning_rate": 1.9364769484907643e-05,
"loss": 0.0158,
"step": 4820
},
{
"epoch": 4.57,
"learning_rate": 1.928968313560595e-05,
"loss": 0.0177,
"step": 4830
},
{
"epoch": 4.58,
"learning_rate": 1.9214596786304252e-05,
"loss": 0.0174,
"step": 4840
},
{
"epoch": 4.59,
"learning_rate": 1.9139510437002552e-05,
"loss": 0.0134,
"step": 4850
},
{
"epoch": 4.59,
"learning_rate": 1.906442408770086e-05,
"loss": 0.0367,
"step": 4860
},
{
"epoch": 4.6,
"learning_rate": 1.898933773839916e-05,
"loss": 0.0077,
"step": 4870
},
{
"epoch": 4.61,
"learning_rate": 1.891425138909746e-05,
"loss": 0.0121,
"step": 4880
},
{
"epoch": 4.62,
"learning_rate": 1.8839165039795768e-05,
"loss": 0.011,
"step": 4890
},
{
"epoch": 4.63,
"learning_rate": 1.8764078690494068e-05,
"loss": 0.0071,
"step": 4900
},
{
"epoch": 4.64,
"learning_rate": 1.868899234119237e-05,
"loss": 0.0072,
"step": 4910
},
{
"epoch": 4.65,
"learning_rate": 1.8613905991890677e-05,
"loss": 0.008,
"step": 4920
},
{
"epoch": 4.66,
"learning_rate": 1.8538819642588977e-05,
"loss": 0.0183,
"step": 4930
},
{
"epoch": 4.67,
"learning_rate": 1.846373329328728e-05,
"loss": 0.0115,
"step": 4940
},
{
"epoch": 4.68,
"learning_rate": 1.8388646943985587e-05,
"loss": 0.0154,
"step": 4950
},
{
"epoch": 4.69,
"learning_rate": 1.8313560594683886e-05,
"loss": 0.0086,
"step": 4960
},
{
"epoch": 4.7,
"learning_rate": 1.823847424538219e-05,
"loss": 0.0073,
"step": 4970
},
{
"epoch": 4.71,
"learning_rate": 1.8163387896080496e-05,
"loss": 0.0081,
"step": 4980
},
{
"epoch": 4.72,
"learning_rate": 1.8088301546778796e-05,
"loss": 0.0227,
"step": 4990
},
{
"epoch": 4.73,
"learning_rate": 1.80132151974771e-05,
"loss": 0.0108,
"step": 5000
},
{
"epoch": 4.74,
"learning_rate": 1.7938128848175402e-05,
"loss": 0.0131,
"step": 5010
},
{
"epoch": 4.75,
"learning_rate": 1.7863042498873705e-05,
"loss": 0.0099,
"step": 5020
},
{
"epoch": 4.76,
"learning_rate": 1.7787956149572008e-05,
"loss": 0.0146,
"step": 5030
},
{
"epoch": 4.76,
"learning_rate": 1.771286980027031e-05,
"loss": 0.0125,
"step": 5040
},
{
"epoch": 4.77,
"learning_rate": 1.7637783450968614e-05,
"loss": 0.0098,
"step": 5050
},
{
"epoch": 4.78,
"learning_rate": 1.7562697101666917e-05,
"loss": 0.0123,
"step": 5060
},
{
"epoch": 4.79,
"learning_rate": 1.748761075236522e-05,
"loss": 0.0129,
"step": 5070
},
{
"epoch": 4.8,
"learning_rate": 1.7412524403063524e-05,
"loss": 0.0215,
"step": 5080
},
{
"epoch": 4.81,
"learning_rate": 1.7337438053761827e-05,
"loss": 0.0076,
"step": 5090
},
{
"epoch": 4.82,
"learning_rate": 1.726235170446013e-05,
"loss": 0.0067,
"step": 5100
},
{
"epoch": 4.83,
"learning_rate": 1.7187265355158433e-05,
"loss": 0.0089,
"step": 5110
},
{
"epoch": 4.84,
"learning_rate": 1.7112179005856736e-05,
"loss": 0.0194,
"step": 5120
},
{
"epoch": 4.85,
"learning_rate": 1.703709265655504e-05,
"loss": 0.0317,
"step": 5130
},
{
"epoch": 4.86,
"learning_rate": 1.6962006307253342e-05,
"loss": 0.0076,
"step": 5140
},
{
"epoch": 4.87,
"learning_rate": 1.6886919957951645e-05,
"loss": 0.0129,
"step": 5150
},
{
"epoch": 4.88,
"learning_rate": 1.681183360864995e-05,
"loss": 0.0133,
"step": 5160
},
{
"epoch": 4.89,
"learning_rate": 1.673674725934825e-05,
"loss": 0.0106,
"step": 5170
},
{
"epoch": 4.9,
"learning_rate": 1.6661660910046555e-05,
"loss": 0.0155,
"step": 5180
},
{
"epoch": 4.91,
"learning_rate": 1.6586574560744858e-05,
"loss": 0.0102,
"step": 5190
},
{
"epoch": 4.92,
"learning_rate": 1.651148821144316e-05,
"loss": 0.0162,
"step": 5200
},
{
"epoch": 4.93,
"learning_rate": 1.6436401862141464e-05,
"loss": 0.0091,
"step": 5210
},
{
"epoch": 4.94,
"learning_rate": 1.6361315512839767e-05,
"loss": 0.0164,
"step": 5220
},
{
"epoch": 4.94,
"learning_rate": 1.628622916353807e-05,
"loss": 0.0071,
"step": 5230
},
{
"epoch": 4.95,
"learning_rate": 1.621114281423637e-05,
"loss": 0.0153,
"step": 5240
},
{
"epoch": 4.96,
"learning_rate": 1.6136056464934676e-05,
"loss": 0.028,
"step": 5250
},
{
"epoch": 4.97,
"learning_rate": 1.606097011563298e-05,
"loss": 0.0075,
"step": 5260
},
{
"epoch": 4.98,
"learning_rate": 1.598588376633128e-05,
"loss": 0.0122,
"step": 5270
},
{
"epoch": 4.99,
"learning_rate": 1.5910797417029586e-05,
"loss": 0.0121,
"step": 5280
},
{
"epoch": 5.0,
"eval_accuracy": 0.998898095909732,
"eval_loss": 0.010311879217624664,
"eval_runtime": 126.6828,
"eval_samples_per_second": 179.093,
"eval_steps_per_second": 11.193,
"step": 5288
},
{
"epoch": 5.0,
"learning_rate": 1.583571106772789e-05,
"loss": 0.006,
"step": 5290
},
{
"epoch": 5.01,
"learning_rate": 1.576062471842619e-05,
"loss": 0.0125,
"step": 5300
},
{
"epoch": 5.02,
"learning_rate": 1.5685538369124495e-05,
"loss": 0.018,
"step": 5310
},
{
"epoch": 5.03,
"learning_rate": 1.5610452019822798e-05,
"loss": 0.0102,
"step": 5320
},
{
"epoch": 5.04,
"learning_rate": 1.5535365670521098e-05,
"loss": 0.0098,
"step": 5330
},
{
"epoch": 5.05,
"learning_rate": 1.5460279321219404e-05,
"loss": 0.0072,
"step": 5340
},
{
"epoch": 5.06,
"learning_rate": 1.5385192971917707e-05,
"loss": 0.012,
"step": 5350
},
{
"epoch": 5.07,
"learning_rate": 1.5310106622616007e-05,
"loss": 0.0146,
"step": 5360
},
{
"epoch": 5.08,
"learning_rate": 1.5235020273314312e-05,
"loss": 0.0071,
"step": 5370
},
{
"epoch": 5.09,
"learning_rate": 1.5159933924012615e-05,
"loss": 0.0121,
"step": 5380
},
{
"epoch": 5.1,
"learning_rate": 1.5084847574710916e-05,
"loss": 0.011,
"step": 5390
},
{
"epoch": 5.11,
"learning_rate": 1.5009761225409221e-05,
"loss": 0.0142,
"step": 5400
},
{
"epoch": 5.11,
"learning_rate": 1.4934674876107524e-05,
"loss": 0.0107,
"step": 5410
},
{
"epoch": 5.12,
"learning_rate": 1.4859588526805826e-05,
"loss": 0.0145,
"step": 5420
},
{
"epoch": 5.13,
"learning_rate": 1.478450217750413e-05,
"loss": 0.0122,
"step": 5430
},
{
"epoch": 5.14,
"learning_rate": 1.4709415828202434e-05,
"loss": 0.0087,
"step": 5440
},
{
"epoch": 5.15,
"learning_rate": 1.4634329478900738e-05,
"loss": 0.0095,
"step": 5450
},
{
"epoch": 5.16,
"learning_rate": 1.455924312959904e-05,
"loss": 0.0066,
"step": 5460
},
{
"epoch": 5.17,
"learning_rate": 1.4484156780297343e-05,
"loss": 0.0185,
"step": 5470
},
{
"epoch": 5.18,
"learning_rate": 1.4409070430995648e-05,
"loss": 0.0177,
"step": 5480
},
{
"epoch": 5.19,
"learning_rate": 1.433398408169395e-05,
"loss": 0.0079,
"step": 5490
},
{
"epoch": 5.2,
"learning_rate": 1.425889773239225e-05,
"loss": 0.0122,
"step": 5500
},
{
"epoch": 5.21,
"learning_rate": 1.4183811383090555e-05,
"loss": 0.0121,
"step": 5510
},
{
"epoch": 5.22,
"learning_rate": 1.4108725033788858e-05,
"loss": 0.0077,
"step": 5520
},
{
"epoch": 5.23,
"learning_rate": 1.403363868448716e-05,
"loss": 0.0082,
"step": 5530
},
{
"epoch": 5.24,
"learning_rate": 1.3958552335185465e-05,
"loss": 0.0237,
"step": 5540
},
{
"epoch": 5.25,
"learning_rate": 1.3883465985883768e-05,
"loss": 0.0093,
"step": 5550
},
{
"epoch": 5.26,
"learning_rate": 1.380837963658207e-05,
"loss": 0.0191,
"step": 5560
},
{
"epoch": 5.27,
"learning_rate": 1.3733293287280374e-05,
"loss": 0.0162,
"step": 5570
},
{
"epoch": 5.28,
"learning_rate": 1.3658206937978677e-05,
"loss": 0.0099,
"step": 5580
},
{
"epoch": 5.28,
"learning_rate": 1.3583120588676979e-05,
"loss": 0.0127,
"step": 5590
},
{
"epoch": 5.29,
"learning_rate": 1.3508034239375283e-05,
"loss": 0.0155,
"step": 5600
},
{
"epoch": 5.3,
"learning_rate": 1.3432947890073585e-05,
"loss": 0.0117,
"step": 5610
},
{
"epoch": 5.31,
"learning_rate": 1.3357861540771888e-05,
"loss": 0.0173,
"step": 5620
},
{
"epoch": 5.32,
"learning_rate": 1.3282775191470193e-05,
"loss": 0.0186,
"step": 5630
},
{
"epoch": 5.33,
"learning_rate": 1.3207688842168494e-05,
"loss": 0.0068,
"step": 5640
},
{
"epoch": 5.34,
"learning_rate": 1.3132602492866797e-05,
"loss": 0.021,
"step": 5650
},
{
"epoch": 5.35,
"learning_rate": 1.3057516143565102e-05,
"loss": 0.0286,
"step": 5660
},
{
"epoch": 5.36,
"learning_rate": 1.2982429794263403e-05,
"loss": 0.0058,
"step": 5670
},
{
"epoch": 5.37,
"learning_rate": 1.2907343444961707e-05,
"loss": 0.0132,
"step": 5680
},
{
"epoch": 5.38,
"learning_rate": 1.2832257095660011e-05,
"loss": 0.0056,
"step": 5690
},
{
"epoch": 5.39,
"learning_rate": 1.2757170746358313e-05,
"loss": 0.0055,
"step": 5700
},
{
"epoch": 5.4,
"learning_rate": 1.2682084397056616e-05,
"loss": 0.0053,
"step": 5710
},
{
"epoch": 5.41,
"learning_rate": 1.260699804775492e-05,
"loss": 0.0058,
"step": 5720
},
{
"epoch": 5.42,
"learning_rate": 1.2531911698453222e-05,
"loss": 0.0056,
"step": 5730
},
{
"epoch": 5.43,
"learning_rate": 1.2456825349151525e-05,
"loss": 0.0186,
"step": 5740
},
{
"epoch": 5.44,
"learning_rate": 1.2381738999849828e-05,
"loss": 0.0227,
"step": 5750
},
{
"epoch": 5.45,
"learning_rate": 1.2306652650548131e-05,
"loss": 0.0076,
"step": 5760
},
{
"epoch": 5.45,
"learning_rate": 1.2231566301246434e-05,
"loss": 0.0054,
"step": 5770
},
{
"epoch": 5.46,
"learning_rate": 1.2156479951944736e-05,
"loss": 0.015,
"step": 5780
},
{
"epoch": 5.47,
"learning_rate": 1.208139360264304e-05,
"loss": 0.0186,
"step": 5790
},
{
"epoch": 5.48,
"learning_rate": 1.2006307253341344e-05,
"loss": 0.0077,
"step": 5800
},
{
"epoch": 5.49,
"learning_rate": 1.1931220904039645e-05,
"loss": 0.0165,
"step": 5810
},
{
"epoch": 5.5,
"learning_rate": 1.185613455473795e-05,
"loss": 0.005,
"step": 5820
},
{
"epoch": 5.51,
"learning_rate": 1.1781048205436253e-05,
"loss": 0.0069,
"step": 5830
},
{
"epoch": 5.52,
"learning_rate": 1.1705961856134555e-05,
"loss": 0.0142,
"step": 5840
},
{
"epoch": 5.53,
"learning_rate": 1.1630875506832858e-05,
"loss": 0.0148,
"step": 5850
},
{
"epoch": 5.54,
"learning_rate": 1.1555789157531162e-05,
"loss": 0.0147,
"step": 5860
},
{
"epoch": 5.55,
"learning_rate": 1.1480702808229464e-05,
"loss": 0.0056,
"step": 5870
},
{
"epoch": 5.56,
"learning_rate": 1.1405616458927767e-05,
"loss": 0.0142,
"step": 5880
},
{
"epoch": 5.57,
"learning_rate": 1.1330530109626072e-05,
"loss": 0.0051,
"step": 5890
},
{
"epoch": 5.58,
"learning_rate": 1.1255443760324373e-05,
"loss": 0.0112,
"step": 5900
},
{
"epoch": 5.59,
"learning_rate": 1.1180357411022676e-05,
"loss": 0.016,
"step": 5910
},
{
"epoch": 5.6,
"learning_rate": 1.110527106172098e-05,
"loss": 0.0143,
"step": 5920
},
{
"epoch": 5.61,
"learning_rate": 1.1030184712419282e-05,
"loss": 0.0052,
"step": 5930
},
{
"epoch": 5.62,
"learning_rate": 1.0955098363117586e-05,
"loss": 0.0068,
"step": 5940
},
{
"epoch": 5.63,
"learning_rate": 1.0880012013815889e-05,
"loss": 0.0159,
"step": 5950
},
{
"epoch": 5.63,
"learning_rate": 1.0804925664514192e-05,
"loss": 0.0054,
"step": 5960
},
{
"epoch": 5.64,
"learning_rate": 1.0729839315212495e-05,
"loss": 0.0065,
"step": 5970
},
{
"epoch": 5.65,
"learning_rate": 1.0654752965910798e-05,
"loss": 0.0062,
"step": 5980
},
{
"epoch": 5.66,
"learning_rate": 1.0579666616609101e-05,
"loss": 0.0058,
"step": 5990
},
{
"epoch": 5.67,
"learning_rate": 1.0504580267307404e-05,
"loss": 0.0132,
"step": 6000
},
{
"epoch": 5.68,
"learning_rate": 1.0429493918005707e-05,
"loss": 0.01,
"step": 6010
},
{
"epoch": 5.69,
"learning_rate": 1.0354407568704009e-05,
"loss": 0.0067,
"step": 6020
},
{
"epoch": 5.7,
"learning_rate": 1.0279321219402314e-05,
"loss": 0.0269,
"step": 6030
},
{
"epoch": 5.71,
"learning_rate": 1.0204234870100617e-05,
"loss": 0.0066,
"step": 6040
},
{
"epoch": 5.72,
"learning_rate": 1.0129148520798918e-05,
"loss": 0.0052,
"step": 6050
},
{
"epoch": 5.73,
"learning_rate": 1.0054062171497223e-05,
"loss": 0.0069,
"step": 6060
},
{
"epoch": 5.74,
"learning_rate": 9.978975822195526e-06,
"loss": 0.0155,
"step": 6070
},
{
"epoch": 5.75,
"learning_rate": 9.903889472893827e-06,
"loss": 0.0055,
"step": 6080
},
{
"epoch": 5.76,
"learning_rate": 9.82880312359213e-06,
"loss": 0.0058,
"step": 6090
},
{
"epoch": 5.77,
"learning_rate": 9.753716774290435e-06,
"loss": 0.0306,
"step": 6100
},
{
"epoch": 5.78,
"learning_rate": 9.678630424988737e-06,
"loss": 0.0062,
"step": 6110
},
{
"epoch": 5.79,
"learning_rate": 9.60354407568704e-06,
"loss": 0.0103,
"step": 6120
},
{
"epoch": 5.8,
"learning_rate": 9.528457726385345e-06,
"loss": 0.0053,
"step": 6130
},
{
"epoch": 5.8,
"learning_rate": 9.453371377083646e-06,
"loss": 0.0069,
"step": 6140
},
{
"epoch": 5.81,
"learning_rate": 9.378285027781949e-06,
"loss": 0.005,
"step": 6150
},
{
"epoch": 5.82,
"learning_rate": 9.303198678480252e-06,
"loss": 0.0087,
"step": 6160
},
{
"epoch": 5.83,
"learning_rate": 9.228112329178555e-06,
"loss": 0.0045,
"step": 6170
},
{
"epoch": 5.84,
"learning_rate": 9.153025979876858e-06,
"loss": 0.0236,
"step": 6180
},
{
"epoch": 5.85,
"learning_rate": 9.077939630575162e-06,
"loss": 0.0051,
"step": 6190
},
{
"epoch": 5.86,
"learning_rate": 9.002853281273465e-06,
"loss": 0.0101,
"step": 6200
},
{
"epoch": 5.87,
"learning_rate": 8.927766931971768e-06,
"loss": 0.0052,
"step": 6210
},
{
"epoch": 5.88,
"learning_rate": 8.852680582670071e-06,
"loss": 0.0288,
"step": 6220
},
{
"epoch": 5.89,
"learning_rate": 8.777594233368374e-06,
"loss": 0.0048,
"step": 6230
},
{
"epoch": 5.9,
"learning_rate": 8.702507884066677e-06,
"loss": 0.0058,
"step": 6240
},
{
"epoch": 5.91,
"learning_rate": 8.62742153476498e-06,
"loss": 0.0054,
"step": 6250
},
{
"epoch": 5.92,
"learning_rate": 8.552335185463283e-06,
"loss": 0.0151,
"step": 6260
},
{
"epoch": 5.93,
"learning_rate": 8.477248836161586e-06,
"loss": 0.0046,
"step": 6270
},
{
"epoch": 5.94,
"learning_rate": 8.40216248685989e-06,
"loss": 0.0109,
"step": 6280
},
{
"epoch": 5.95,
"learning_rate": 8.327076137558193e-06,
"loss": 0.0072,
"step": 6290
},
{
"epoch": 5.96,
"learning_rate": 8.251989788256496e-06,
"loss": 0.0108,
"step": 6300
},
{
"epoch": 5.97,
"learning_rate": 8.176903438954799e-06,
"loss": 0.0157,
"step": 6310
},
{
"epoch": 5.97,
"learning_rate": 8.101817089653102e-06,
"loss": 0.0126,
"step": 6320
},
{
"epoch": 5.98,
"learning_rate": 8.026730740351403e-06,
"loss": 0.0044,
"step": 6330
},
{
"epoch": 5.99,
"learning_rate": 7.951644391049708e-06,
"loss": 0.009,
"step": 6340
},
{
"epoch": 6.0,
"eval_accuracy": 0.9987658674188998,
"eval_loss": 0.00954383984208107,
"eval_runtime": 122.3644,
"eval_samples_per_second": 185.413,
"eval_steps_per_second": 11.588,
"step": 6346
},
{
"epoch": 6.0,
"learning_rate": 7.876558041748011e-06,
"loss": 0.006,
"step": 6350
},
{
"epoch": 6.01,
"learning_rate": 7.801471692446313e-06,
"loss": 0.0147,
"step": 6360
},
{
"epoch": 6.02,
"learning_rate": 7.726385343144617e-06,
"loss": 0.0148,
"step": 6370
},
{
"epoch": 6.03,
"learning_rate": 7.65129899384292e-06,
"loss": 0.0072,
"step": 6380
},
{
"epoch": 6.04,
"learning_rate": 7.576212644541222e-06,
"loss": 0.0154,
"step": 6390
},
{
"epoch": 6.05,
"learning_rate": 7.501126295239526e-06,
"loss": 0.0129,
"step": 6400
},
{
"epoch": 6.06,
"learning_rate": 7.426039945937829e-06,
"loss": 0.0061,
"step": 6410
},
{
"epoch": 6.07,
"learning_rate": 7.350953596636131e-06,
"loss": 0.0045,
"step": 6420
},
{
"epoch": 6.08,
"learning_rate": 7.275867247334435e-06,
"loss": 0.0052,
"step": 6430
},
{
"epoch": 6.09,
"learning_rate": 7.200780898032738e-06,
"loss": 0.0268,
"step": 6440
},
{
"epoch": 6.1,
"learning_rate": 7.125694548731041e-06,
"loss": 0.0141,
"step": 6450
},
{
"epoch": 6.11,
"learning_rate": 7.050608199429344e-06,
"loss": 0.0113,
"step": 6460
},
{
"epoch": 6.12,
"learning_rate": 6.975521850127648e-06,
"loss": 0.0046,
"step": 6470
},
{
"epoch": 6.13,
"learning_rate": 6.90043550082595e-06,
"loss": 0.0042,
"step": 6480
},
{
"epoch": 6.14,
"learning_rate": 6.825349151524253e-06,
"loss": 0.0151,
"step": 6490
},
{
"epoch": 6.15,
"learning_rate": 6.750262802222557e-06,
"loss": 0.0076,
"step": 6500
},
{
"epoch": 6.15,
"learning_rate": 6.675176452920858e-06,
"loss": 0.0093,
"step": 6510
},
{
"epoch": 6.16,
"learning_rate": 6.600090103619162e-06,
"loss": 0.0044,
"step": 6520
},
{
"epoch": 6.17,
"learning_rate": 6.5250037543174655e-06,
"loss": 0.0085,
"step": 6530
},
{
"epoch": 6.18,
"learning_rate": 6.449917405015768e-06,
"loss": 0.0045,
"step": 6540
},
{
"epoch": 6.19,
"learning_rate": 6.374831055714072e-06,
"loss": 0.013,
"step": 6550
},
{
"epoch": 6.2,
"learning_rate": 6.299744706412375e-06,
"loss": 0.007,
"step": 6560
},
{
"epoch": 6.21,
"learning_rate": 6.224658357110678e-06,
"loss": 0.0044,
"step": 6570
},
{
"epoch": 6.22,
"learning_rate": 6.14957200780898e-06,
"loss": 0.0042,
"step": 6580
},
{
"epoch": 6.23,
"learning_rate": 6.074485658507283e-06,
"loss": 0.0061,
"step": 6590
},
{
"epoch": 6.24,
"learning_rate": 5.999399309205587e-06,
"loss": 0.0044,
"step": 6600
},
{
"epoch": 6.25,
"learning_rate": 5.9243129599038895e-06,
"loss": 0.0207,
"step": 6610
},
{
"epoch": 6.26,
"learning_rate": 5.8492266106021934e-06,
"loss": 0.0096,
"step": 6620
},
{
"epoch": 6.27,
"learning_rate": 5.774140261300496e-06,
"loss": 0.0047,
"step": 6630
},
{
"epoch": 6.28,
"learning_rate": 5.699053911998799e-06,
"loss": 0.005,
"step": 6640
},
{
"epoch": 6.29,
"learning_rate": 5.623967562697102e-06,
"loss": 0.0042,
"step": 6650
},
{
"epoch": 6.3,
"learning_rate": 5.548881213395405e-06,
"loss": 0.0049,
"step": 6660
},
{
"epoch": 6.31,
"learning_rate": 5.473794864093708e-06,
"loss": 0.0163,
"step": 6670
},
{
"epoch": 6.32,
"learning_rate": 5.398708514792011e-06,
"loss": 0.0114,
"step": 6680
},
{
"epoch": 6.32,
"learning_rate": 5.323622165490314e-06,
"loss": 0.0091,
"step": 6690
},
{
"epoch": 6.33,
"learning_rate": 5.248535816188617e-06,
"loss": 0.0067,
"step": 6700
},
{
"epoch": 6.34,
"learning_rate": 5.1734494668869205e-06,
"loss": 0.0068,
"step": 6710
},
{
"epoch": 6.35,
"learning_rate": 5.098363117585224e-06,
"loss": 0.004,
"step": 6720
},
{
"epoch": 6.36,
"learning_rate": 5.023276768283526e-06,
"loss": 0.0045,
"step": 6730
},
{
"epoch": 6.37,
"learning_rate": 4.94819041898183e-06,
"loss": 0.0089,
"step": 6740
},
{
"epoch": 6.38,
"learning_rate": 4.873104069680132e-06,
"loss": 0.0074,
"step": 6750
},
{
"epoch": 6.39,
"learning_rate": 4.798017720378435e-06,
"loss": 0.0138,
"step": 6760
},
{
"epoch": 6.4,
"learning_rate": 4.722931371076738e-06,
"loss": 0.0066,
"step": 6770
},
{
"epoch": 6.41,
"learning_rate": 4.6478450217750414e-06,
"loss": 0.0056,
"step": 6780
},
{
"epoch": 6.42,
"learning_rate": 4.5727586724733445e-06,
"loss": 0.0069,
"step": 6790
},
{
"epoch": 6.43,
"learning_rate": 4.497672323171648e-06,
"loss": 0.0047,
"step": 6800
},
{
"epoch": 6.44,
"learning_rate": 4.422585973869951e-06,
"loss": 0.0038,
"step": 6810
},
{
"epoch": 6.45,
"learning_rate": 4.347499624568253e-06,
"loss": 0.0095,
"step": 6820
},
{
"epoch": 6.46,
"learning_rate": 4.272413275266557e-06,
"loss": 0.0041,
"step": 6830
},
{
"epoch": 6.47,
"learning_rate": 4.19732692596486e-06,
"loss": 0.0049,
"step": 6840
},
{
"epoch": 6.48,
"learning_rate": 4.122240576663162e-06,
"loss": 0.0039,
"step": 6850
},
{
"epoch": 6.49,
"learning_rate": 4.047154227361466e-06,
"loss": 0.0091,
"step": 6860
},
{
"epoch": 6.49,
"learning_rate": 3.9720678780597685e-06,
"loss": 0.0085,
"step": 6870
},
{
"epoch": 6.5,
"learning_rate": 3.8969815287580725e-06,
"loss": 0.004,
"step": 6880
},
{
"epoch": 6.51,
"learning_rate": 3.821895179456375e-06,
"loss": 0.0059,
"step": 6890
},
{
"epoch": 6.52,
"learning_rate": 3.746808830154678e-06,
"loss": 0.0048,
"step": 6900
},
{
"epoch": 6.53,
"learning_rate": 3.6717224808529814e-06,
"loss": 0.0039,
"step": 6910
},
{
"epoch": 6.54,
"learning_rate": 3.596636131551284e-06,
"loss": 0.0041,
"step": 6920
},
{
"epoch": 6.55,
"learning_rate": 3.521549782249587e-06,
"loss": 0.0062,
"step": 6930
},
{
"epoch": 6.56,
"learning_rate": 3.4464634329478907e-06,
"loss": 0.0085,
"step": 6940
},
{
"epoch": 6.57,
"learning_rate": 3.3713770836461934e-06,
"loss": 0.0039,
"step": 6950
},
{
"epoch": 6.58,
"learning_rate": 3.296290734344496e-06,
"loss": 0.0136,
"step": 6960
},
{
"epoch": 6.59,
"learning_rate": 3.2212043850427996e-06,
"loss": 0.0123,
"step": 6970
},
{
"epoch": 6.6,
"learning_rate": 3.1461180357411023e-06,
"loss": 0.0041,
"step": 6980
},
{
"epoch": 6.61,
"learning_rate": 3.0710316864394054e-06,
"loss": 0.0064,
"step": 6990
},
{
"epoch": 6.62,
"learning_rate": 2.9959453371377085e-06,
"loss": 0.004,
"step": 7000
},
{
"epoch": 6.63,
"learning_rate": 2.9208589878360116e-06,
"loss": 0.0042,
"step": 7010
},
{
"epoch": 6.64,
"learning_rate": 2.8457726385343147e-06,
"loss": 0.005,
"step": 7020
},
{
"epoch": 6.65,
"learning_rate": 2.7706862892326174e-06,
"loss": 0.0038,
"step": 7030
},
{
"epoch": 6.66,
"learning_rate": 2.6955999399309205e-06,
"loss": 0.0114,
"step": 7040
},
{
"epoch": 6.67,
"learning_rate": 2.6205135906292236e-06,
"loss": 0.0038,
"step": 7050
},
{
"epoch": 6.67,
"learning_rate": 2.545427241327527e-06,
"loss": 0.0152,
"step": 7060
},
{
"epoch": 6.68,
"learning_rate": 2.47034089202583e-06,
"loss": 0.0039,
"step": 7070
},
{
"epoch": 6.69,
"learning_rate": 2.395254542724133e-06,
"loss": 0.0195,
"step": 7080
},
{
"epoch": 6.7,
"learning_rate": 2.320168193422436e-06,
"loss": 0.0081,
"step": 7090
},
{
"epoch": 6.71,
"learning_rate": 2.2450818441207387e-06,
"loss": 0.0075,
"step": 7100
},
{
"epoch": 6.72,
"learning_rate": 2.169995494819042e-06,
"loss": 0.0055,
"step": 7110
},
{
"epoch": 6.73,
"learning_rate": 2.0949091455173454e-06,
"loss": 0.0041,
"step": 7120
},
{
"epoch": 6.74,
"learning_rate": 2.019822796215648e-06,
"loss": 0.004,
"step": 7130
},
{
"epoch": 6.75,
"learning_rate": 1.944736446913951e-06,
"loss": 0.0038,
"step": 7140
},
{
"epoch": 6.76,
"learning_rate": 1.8696500976122543e-06,
"loss": 0.0119,
"step": 7150
},
{
"epoch": 6.77,
"learning_rate": 1.7945637483105572e-06,
"loss": 0.0068,
"step": 7160
},
{
"epoch": 6.78,
"learning_rate": 1.7194773990088603e-06,
"loss": 0.0062,
"step": 7170
},
{
"epoch": 6.79,
"learning_rate": 1.6443910497071634e-06,
"loss": 0.0042,
"step": 7180
},
{
"epoch": 6.8,
"learning_rate": 1.5693047004054665e-06,
"loss": 0.0073,
"step": 7190
},
{
"epoch": 6.81,
"learning_rate": 1.4942183511037694e-06,
"loss": 0.0038,
"step": 7200
},
{
"epoch": 6.82,
"learning_rate": 1.4191320018020725e-06,
"loss": 0.0049,
"step": 7210
},
{
"epoch": 6.83,
"learning_rate": 1.3440456525003754e-06,
"loss": 0.0101,
"step": 7220
},
{
"epoch": 6.84,
"learning_rate": 1.2689593031986787e-06,
"loss": 0.0117,
"step": 7230
},
{
"epoch": 6.84,
"learning_rate": 1.1938729538969816e-06,
"loss": 0.0042,
"step": 7240
},
{
"epoch": 6.85,
"learning_rate": 1.1187866045952845e-06,
"loss": 0.0155,
"step": 7250
},
{
"epoch": 6.86,
"learning_rate": 1.0437002552935878e-06,
"loss": 0.0049,
"step": 7260
},
{
"epoch": 6.87,
"learning_rate": 9.686139059918907e-07,
"loss": 0.0038,
"step": 7270
},
{
"epoch": 6.88,
"learning_rate": 8.935275566901939e-07,
"loss": 0.0075,
"step": 7280
},
{
"epoch": 6.89,
"learning_rate": 8.184412073884968e-07,
"loss": 0.0113,
"step": 7290
},
{
"epoch": 6.9,
"learning_rate": 7.433548580867999e-07,
"loss": 0.0039,
"step": 7300
},
{
"epoch": 6.91,
"learning_rate": 6.682685087851029e-07,
"loss": 0.0037,
"step": 7310
},
{
"epoch": 6.92,
"learning_rate": 5.931821594834059e-07,
"loss": 0.0075,
"step": 7320
},
{
"epoch": 6.93,
"learning_rate": 5.18095810181709e-07,
"loss": 0.0038,
"step": 7330
},
{
"epoch": 6.94,
"learning_rate": 4.4300946088001206e-07,
"loss": 0.0067,
"step": 7340
},
{
"epoch": 6.95,
"learning_rate": 3.6792311157831506e-07,
"loss": 0.0092,
"step": 7350
},
{
"epoch": 6.96,
"learning_rate": 2.928367622766181e-07,
"loss": 0.0039,
"step": 7360
},
{
"epoch": 6.97,
"learning_rate": 2.1775041297492117e-07,
"loss": 0.004,
"step": 7370
},
{
"epoch": 6.98,
"learning_rate": 1.4266406367322422e-07,
"loss": 0.0078,
"step": 7380
},
{
"epoch": 6.99,
"learning_rate": 6.757771437152727e-08,
"loss": 0.0037,
"step": 7390
},
{
"epoch": 7.0,
"eval_accuracy": 0.998898095909732,
"eval_loss": 0.008991311304271221,
"eval_runtime": 128.5597,
"eval_samples_per_second": 176.478,
"eval_steps_per_second": 11.03,
"step": 7399
},
{
"epoch": 7.0,
"step": 7399,
"total_flos": 3.6728960862956544e+19,
"train_loss": 0.39934727716508756,
"train_runtime": 6686.2358,
"train_samples_per_second": 70.866,
"train_steps_per_second": 1.107
}
],
"logging_steps": 10,
"max_steps": 7399,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 3.6728960862956544e+19,
"trial_name": null,
"trial_params": null
}