Gokulapriyan's picture
End of training
5f5f320
raw
history blame
25.3 kB
{
"best_metric": 0.9557870124349027,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1983",
"epoch": 2.9988666414809217,
"global_step": 1983,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 2.512562814070352e-06,
"loss": 1.3842,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 5.025125628140704e-06,
"loss": 1.3045,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 7.537688442211055e-06,
"loss": 1.1787,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 1.0050251256281408e-05,
"loss": 1.02,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 1.2562814070351759e-05,
"loss": 0.9295,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 1.507537688442211e-05,
"loss": 0.837,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 1.7587939698492464e-05,
"loss": 0.8061,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 2.0100502512562815e-05,
"loss": 0.8085,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 2.2613065326633167e-05,
"loss": 0.7833,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 2.5125628140703518e-05,
"loss": 0.7737,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 2.763819095477387e-05,
"loss": 0.7031,
"step": 110
},
{
"epoch": 0.18,
"learning_rate": 3.015075376884422e-05,
"loss": 0.7153,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 3.2663316582914576e-05,
"loss": 0.7036,
"step": 130
},
{
"epoch": 0.21,
"learning_rate": 3.517587939698493e-05,
"loss": 0.7027,
"step": 140
},
{
"epoch": 0.23,
"learning_rate": 3.768844221105528e-05,
"loss": 0.7046,
"step": 150
},
{
"epoch": 0.24,
"learning_rate": 4.020100502512563e-05,
"loss": 0.6977,
"step": 160
},
{
"epoch": 0.26,
"learning_rate": 4.271356783919598e-05,
"loss": 0.6629,
"step": 170
},
{
"epoch": 0.27,
"learning_rate": 4.522613065326633e-05,
"loss": 0.7026,
"step": 180
},
{
"epoch": 0.29,
"learning_rate": 4.7738693467336685e-05,
"loss": 0.6673,
"step": 190
},
{
"epoch": 0.3,
"learning_rate": 4.997197309417041e-05,
"loss": 0.6554,
"step": 200
},
{
"epoch": 0.32,
"learning_rate": 4.969170403587444e-05,
"loss": 0.6548,
"step": 210
},
{
"epoch": 0.33,
"learning_rate": 4.941143497757848e-05,
"loss": 0.6225,
"step": 220
},
{
"epoch": 0.35,
"learning_rate": 4.913116591928251e-05,
"loss": 0.6582,
"step": 230
},
{
"epoch": 0.36,
"learning_rate": 4.885089686098655e-05,
"loss": 0.6132,
"step": 240
},
{
"epoch": 0.38,
"learning_rate": 4.857062780269058e-05,
"loss": 0.583,
"step": 250
},
{
"epoch": 0.39,
"learning_rate": 4.829035874439462e-05,
"loss": 0.6279,
"step": 260
},
{
"epoch": 0.41,
"learning_rate": 4.801008968609866e-05,
"loss": 0.6178,
"step": 270
},
{
"epoch": 0.42,
"learning_rate": 4.7729820627802694e-05,
"loss": 0.5601,
"step": 280
},
{
"epoch": 0.44,
"learning_rate": 4.744955156950673e-05,
"loss": 0.5939,
"step": 290
},
{
"epoch": 0.45,
"learning_rate": 4.7169282511210764e-05,
"loss": 0.6023,
"step": 300
},
{
"epoch": 0.47,
"learning_rate": 4.68890134529148e-05,
"loss": 0.5932,
"step": 310
},
{
"epoch": 0.48,
"learning_rate": 4.6608744394618834e-05,
"loss": 0.5353,
"step": 320
},
{
"epoch": 0.5,
"learning_rate": 4.6328475336322875e-05,
"loss": 0.5472,
"step": 330
},
{
"epoch": 0.51,
"learning_rate": 4.6048206278026903e-05,
"loss": 0.5445,
"step": 340
},
{
"epoch": 0.53,
"learning_rate": 4.5767937219730945e-05,
"loss": 0.5398,
"step": 350
},
{
"epoch": 0.54,
"learning_rate": 4.548766816143498e-05,
"loss": 0.5054,
"step": 360
},
{
"epoch": 0.56,
"learning_rate": 4.5207399103139015e-05,
"loss": 0.5082,
"step": 370
},
{
"epoch": 0.57,
"learning_rate": 4.492713004484305e-05,
"loss": 0.5801,
"step": 380
},
{
"epoch": 0.59,
"learning_rate": 4.464686098654709e-05,
"loss": 0.548,
"step": 390
},
{
"epoch": 0.6,
"learning_rate": 4.436659192825112e-05,
"loss": 0.5703,
"step": 400
},
{
"epoch": 0.62,
"learning_rate": 4.408632286995516e-05,
"loss": 0.507,
"step": 410
},
{
"epoch": 0.63,
"learning_rate": 4.380605381165919e-05,
"loss": 0.505,
"step": 420
},
{
"epoch": 0.65,
"learning_rate": 4.352578475336323e-05,
"loss": 0.4939,
"step": 430
},
{
"epoch": 0.66,
"learning_rate": 4.3245515695067267e-05,
"loss": 0.4916,
"step": 440
},
{
"epoch": 0.68,
"learning_rate": 4.29652466367713e-05,
"loss": 0.4722,
"step": 450
},
{
"epoch": 0.7,
"learning_rate": 4.2684977578475336e-05,
"loss": 0.4934,
"step": 460
},
{
"epoch": 0.71,
"learning_rate": 4.240470852017938e-05,
"loss": 0.4524,
"step": 470
},
{
"epoch": 0.73,
"learning_rate": 4.2124439461883406e-05,
"loss": 0.483,
"step": 480
},
{
"epoch": 0.74,
"learning_rate": 4.184417040358745e-05,
"loss": 0.4941,
"step": 490
},
{
"epoch": 0.76,
"learning_rate": 4.156390134529148e-05,
"loss": 0.4584,
"step": 500
},
{
"epoch": 0.77,
"learning_rate": 4.128363228699552e-05,
"loss": 0.4782,
"step": 510
},
{
"epoch": 0.79,
"learning_rate": 4.100336322869955e-05,
"loss": 0.4642,
"step": 520
},
{
"epoch": 0.8,
"learning_rate": 4.0723094170403595e-05,
"loss": 0.4527,
"step": 530
},
{
"epoch": 0.82,
"learning_rate": 4.044282511210762e-05,
"loss": 0.4402,
"step": 540
},
{
"epoch": 0.83,
"learning_rate": 4.0162556053811665e-05,
"loss": 0.4271,
"step": 550
},
{
"epoch": 0.85,
"learning_rate": 3.98822869955157e-05,
"loss": 0.4439,
"step": 560
},
{
"epoch": 0.86,
"learning_rate": 3.9602017937219735e-05,
"loss": 0.455,
"step": 570
},
{
"epoch": 0.88,
"learning_rate": 3.932174887892377e-05,
"loss": 0.4369,
"step": 580
},
{
"epoch": 0.89,
"learning_rate": 3.9041479820627804e-05,
"loss": 0.4563,
"step": 590
},
{
"epoch": 0.91,
"learning_rate": 3.876121076233184e-05,
"loss": 0.4441,
"step": 600
},
{
"epoch": 0.92,
"learning_rate": 3.8480941704035874e-05,
"loss": 0.4234,
"step": 610
},
{
"epoch": 0.94,
"learning_rate": 3.820067264573991e-05,
"loss": 0.4257,
"step": 620
},
{
"epoch": 0.95,
"learning_rate": 3.792040358744395e-05,
"loss": 0.3985,
"step": 630
},
{
"epoch": 0.97,
"learning_rate": 3.7640134529147986e-05,
"loss": 0.3935,
"step": 640
},
{
"epoch": 0.98,
"learning_rate": 3.735986547085202e-05,
"loss": 0.4099,
"step": 650
},
{
"epoch": 1.0,
"learning_rate": 3.7079596412556056e-05,
"loss": 0.4052,
"step": 660
},
{
"epoch": 1.0,
"eval_accuracy": 0.8906366245084494,
"eval_loss": 0.2878882884979248,
"eval_runtime": 123.5087,
"eval_samples_per_second": 76.181,
"eval_steps_per_second": 2.388,
"step": 661
},
{
"epoch": 1.01,
"learning_rate": 3.679932735426009e-05,
"loss": 0.4176,
"step": 670
},
{
"epoch": 1.03,
"learning_rate": 3.6519058295964126e-05,
"loss": 0.3807,
"step": 680
},
{
"epoch": 1.04,
"learning_rate": 3.623878923766816e-05,
"loss": 0.3781,
"step": 690
},
{
"epoch": 1.06,
"learning_rate": 3.59585201793722e-05,
"loss": 0.4276,
"step": 700
},
{
"epoch": 1.07,
"learning_rate": 3.567825112107623e-05,
"loss": 0.4053,
"step": 710
},
{
"epoch": 1.09,
"learning_rate": 3.539798206278027e-05,
"loss": 0.3546,
"step": 720
},
{
"epoch": 1.1,
"learning_rate": 3.51177130044843e-05,
"loss": 0.3792,
"step": 730
},
{
"epoch": 1.12,
"learning_rate": 3.483744394618834e-05,
"loss": 0.3942,
"step": 740
},
{
"epoch": 1.13,
"learning_rate": 3.455717488789238e-05,
"loss": 0.409,
"step": 750
},
{
"epoch": 1.15,
"learning_rate": 3.427690582959641e-05,
"loss": 0.359,
"step": 760
},
{
"epoch": 1.16,
"learning_rate": 3.399663677130045e-05,
"loss": 0.4147,
"step": 770
},
{
"epoch": 1.18,
"learning_rate": 3.371636771300449e-05,
"loss": 0.3849,
"step": 780
},
{
"epoch": 1.19,
"learning_rate": 3.343609865470852e-05,
"loss": 0.3619,
"step": 790
},
{
"epoch": 1.21,
"learning_rate": 3.315582959641256e-05,
"loss": 0.3841,
"step": 800
},
{
"epoch": 1.23,
"learning_rate": 3.2875560538116594e-05,
"loss": 0.3437,
"step": 810
},
{
"epoch": 1.24,
"learning_rate": 3.259529147982063e-05,
"loss": 0.3413,
"step": 820
},
{
"epoch": 1.26,
"learning_rate": 3.2315022421524664e-05,
"loss": 0.3605,
"step": 830
},
{
"epoch": 1.27,
"learning_rate": 3.2034753363228705e-05,
"loss": 0.3406,
"step": 840
},
{
"epoch": 1.29,
"learning_rate": 3.1754484304932734e-05,
"loss": 0.376,
"step": 850
},
{
"epoch": 1.3,
"learning_rate": 3.1474215246636775e-05,
"loss": 0.329,
"step": 860
},
{
"epoch": 1.32,
"learning_rate": 3.119394618834081e-05,
"loss": 0.3673,
"step": 870
},
{
"epoch": 1.33,
"learning_rate": 3.0913677130044845e-05,
"loss": 0.3527,
"step": 880
},
{
"epoch": 1.35,
"learning_rate": 3.063340807174888e-05,
"loss": 0.3198,
"step": 890
},
{
"epoch": 1.36,
"learning_rate": 3.0353139013452915e-05,
"loss": 0.3233,
"step": 900
},
{
"epoch": 1.38,
"learning_rate": 3.007286995515695e-05,
"loss": 0.3703,
"step": 910
},
{
"epoch": 1.39,
"learning_rate": 2.979260089686099e-05,
"loss": 0.3353,
"step": 920
},
{
"epoch": 1.41,
"learning_rate": 2.951233183856502e-05,
"loss": 0.3367,
"step": 930
},
{
"epoch": 1.42,
"learning_rate": 2.923206278026906e-05,
"loss": 0.3346,
"step": 940
},
{
"epoch": 1.44,
"learning_rate": 2.8951793721973097e-05,
"loss": 0.3155,
"step": 950
},
{
"epoch": 1.45,
"learning_rate": 2.867152466367713e-05,
"loss": 0.3248,
"step": 960
},
{
"epoch": 1.47,
"learning_rate": 2.8391255605381167e-05,
"loss": 0.3529,
"step": 970
},
{
"epoch": 1.48,
"learning_rate": 2.8110986547085205e-05,
"loss": 0.3273,
"step": 980
},
{
"epoch": 1.5,
"learning_rate": 2.7830717488789237e-05,
"loss": 0.3517,
"step": 990
},
{
"epoch": 1.51,
"learning_rate": 2.7550448430493275e-05,
"loss": 0.3532,
"step": 1000
},
{
"epoch": 1.53,
"learning_rate": 2.7270179372197313e-05,
"loss": 0.3549,
"step": 1010
},
{
"epoch": 1.54,
"learning_rate": 2.6989910313901345e-05,
"loss": 0.3091,
"step": 1020
},
{
"epoch": 1.56,
"learning_rate": 2.6709641255605383e-05,
"loss": 0.3171,
"step": 1030
},
{
"epoch": 1.57,
"learning_rate": 2.642937219730942e-05,
"loss": 0.3219,
"step": 1040
},
{
"epoch": 1.59,
"learning_rate": 2.6149103139013453e-05,
"loss": 0.3309,
"step": 1050
},
{
"epoch": 1.6,
"learning_rate": 2.586883408071749e-05,
"loss": 0.3166,
"step": 1060
},
{
"epoch": 1.62,
"learning_rate": 2.5588565022421523e-05,
"loss": 0.298,
"step": 1070
},
{
"epoch": 1.63,
"learning_rate": 2.530829596412556e-05,
"loss": 0.3025,
"step": 1080
},
{
"epoch": 1.65,
"learning_rate": 2.50280269058296e-05,
"loss": 0.3075,
"step": 1090
},
{
"epoch": 1.66,
"learning_rate": 2.4747757847533635e-05,
"loss": 0.3047,
"step": 1100
},
{
"epoch": 1.68,
"learning_rate": 2.446748878923767e-05,
"loss": 0.3483,
"step": 1110
},
{
"epoch": 1.69,
"learning_rate": 2.4187219730941705e-05,
"loss": 0.288,
"step": 1120
},
{
"epoch": 1.71,
"learning_rate": 2.3906950672645743e-05,
"loss": 0.3153,
"step": 1130
},
{
"epoch": 1.72,
"learning_rate": 2.3626681614349778e-05,
"loss": 0.3133,
"step": 1140
},
{
"epoch": 1.74,
"learning_rate": 2.3346412556053813e-05,
"loss": 0.314,
"step": 1150
},
{
"epoch": 1.75,
"learning_rate": 2.306614349775785e-05,
"loss": 0.2799,
"step": 1160
},
{
"epoch": 1.77,
"learning_rate": 2.2785874439461886e-05,
"loss": 0.2767,
"step": 1170
},
{
"epoch": 1.78,
"learning_rate": 2.250560538116592e-05,
"loss": 0.3038,
"step": 1180
},
{
"epoch": 1.8,
"learning_rate": 2.2225336322869956e-05,
"loss": 0.2795,
"step": 1190
},
{
"epoch": 1.81,
"learning_rate": 2.1945067264573994e-05,
"loss": 0.3159,
"step": 1200
},
{
"epoch": 1.83,
"learning_rate": 2.166479820627803e-05,
"loss": 0.3275,
"step": 1210
},
{
"epoch": 1.84,
"learning_rate": 2.1384529147982064e-05,
"loss": 0.2889,
"step": 1220
},
{
"epoch": 1.86,
"learning_rate": 2.11042600896861e-05,
"loss": 0.2949,
"step": 1230
},
{
"epoch": 1.87,
"learning_rate": 2.0823991031390138e-05,
"loss": 0.3073,
"step": 1240
},
{
"epoch": 1.89,
"learning_rate": 2.0543721973094173e-05,
"loss": 0.285,
"step": 1250
},
{
"epoch": 1.91,
"learning_rate": 2.0263452914798208e-05,
"loss": 0.3138,
"step": 1260
},
{
"epoch": 1.92,
"learning_rate": 1.9983183856502243e-05,
"loss": 0.2894,
"step": 1270
},
{
"epoch": 1.94,
"learning_rate": 1.9702914798206277e-05,
"loss": 0.2711,
"step": 1280
},
{
"epoch": 1.95,
"learning_rate": 1.9422645739910312e-05,
"loss": 0.289,
"step": 1290
},
{
"epoch": 1.97,
"learning_rate": 1.914237668161435e-05,
"loss": 0.2621,
"step": 1300
},
{
"epoch": 1.98,
"learning_rate": 1.8862107623318386e-05,
"loss": 0.2872,
"step": 1310
},
{
"epoch": 2.0,
"learning_rate": 1.858183856502242e-05,
"loss": 0.3079,
"step": 1320
},
{
"epoch": 2.0,
"eval_accuracy": 0.936762674035498,
"eval_loss": 0.15844394266605377,
"eval_runtime": 121.8002,
"eval_samples_per_second": 77.249,
"eval_steps_per_second": 2.422,
"step": 1322
},
{
"epoch": 2.01,
"learning_rate": 1.8301569506726456e-05,
"loss": 0.3002,
"step": 1330
},
{
"epoch": 2.03,
"learning_rate": 1.8021300448430494e-05,
"loss": 0.2138,
"step": 1340
},
{
"epoch": 2.04,
"learning_rate": 1.774103139013453e-05,
"loss": 0.29,
"step": 1350
},
{
"epoch": 2.06,
"learning_rate": 1.7460762331838564e-05,
"loss": 0.2843,
"step": 1360
},
{
"epoch": 2.07,
"learning_rate": 1.7180493273542602e-05,
"loss": 0.275,
"step": 1370
},
{
"epoch": 2.09,
"learning_rate": 1.6900224215246637e-05,
"loss": 0.2545,
"step": 1380
},
{
"epoch": 2.1,
"learning_rate": 1.6619955156950672e-05,
"loss": 0.262,
"step": 1390
},
{
"epoch": 2.12,
"learning_rate": 1.633968609865471e-05,
"loss": 0.2746,
"step": 1400
},
{
"epoch": 2.13,
"learning_rate": 1.6059417040358745e-05,
"loss": 0.2595,
"step": 1410
},
{
"epoch": 2.15,
"learning_rate": 1.577914798206278e-05,
"loss": 0.2648,
"step": 1420
},
{
"epoch": 2.16,
"learning_rate": 1.5498878923766815e-05,
"loss": 0.2705,
"step": 1430
},
{
"epoch": 2.18,
"learning_rate": 1.5218609865470854e-05,
"loss": 0.2653,
"step": 1440
},
{
"epoch": 2.19,
"learning_rate": 1.4938340807174889e-05,
"loss": 0.2706,
"step": 1450
},
{
"epoch": 2.21,
"learning_rate": 1.4658071748878924e-05,
"loss": 0.2658,
"step": 1460
},
{
"epoch": 2.22,
"learning_rate": 1.4377802690582962e-05,
"loss": 0.277,
"step": 1470
},
{
"epoch": 2.24,
"learning_rate": 1.4097533632286997e-05,
"loss": 0.2391,
"step": 1480
},
{
"epoch": 2.25,
"learning_rate": 1.3817264573991032e-05,
"loss": 0.2576,
"step": 1490
},
{
"epoch": 2.27,
"learning_rate": 1.3536995515695067e-05,
"loss": 0.278,
"step": 1500
},
{
"epoch": 2.28,
"learning_rate": 1.3256726457399105e-05,
"loss": 0.2247,
"step": 1510
},
{
"epoch": 2.3,
"learning_rate": 1.297645739910314e-05,
"loss": 0.2638,
"step": 1520
},
{
"epoch": 2.31,
"learning_rate": 1.2696188340807175e-05,
"loss": 0.2399,
"step": 1530
},
{
"epoch": 2.33,
"learning_rate": 1.2415919282511212e-05,
"loss": 0.2306,
"step": 1540
},
{
"epoch": 2.34,
"learning_rate": 1.2135650224215247e-05,
"loss": 0.263,
"step": 1550
},
{
"epoch": 2.36,
"learning_rate": 1.1855381165919283e-05,
"loss": 0.2624,
"step": 1560
},
{
"epoch": 2.37,
"learning_rate": 1.1575112107623318e-05,
"loss": 0.2533,
"step": 1570
},
{
"epoch": 2.39,
"learning_rate": 1.1294843049327355e-05,
"loss": 0.2431,
"step": 1580
},
{
"epoch": 2.4,
"learning_rate": 1.101457399103139e-05,
"loss": 0.252,
"step": 1590
},
{
"epoch": 2.42,
"learning_rate": 1.0734304932735427e-05,
"loss": 0.2275,
"step": 1600
},
{
"epoch": 2.44,
"learning_rate": 1.0454035874439462e-05,
"loss": 0.2553,
"step": 1610
},
{
"epoch": 2.45,
"learning_rate": 1.0173766816143498e-05,
"loss": 0.2388,
"step": 1620
},
{
"epoch": 2.47,
"learning_rate": 9.893497757847533e-06,
"loss": 0.2367,
"step": 1630
},
{
"epoch": 2.48,
"learning_rate": 9.61322869955157e-06,
"loss": 0.2495,
"step": 1640
},
{
"epoch": 2.5,
"learning_rate": 9.332959641255606e-06,
"loss": 0.2574,
"step": 1650
},
{
"epoch": 2.51,
"learning_rate": 9.052690582959641e-06,
"loss": 0.2425,
"step": 1660
},
{
"epoch": 2.53,
"learning_rate": 8.772421524663678e-06,
"loss": 0.2636,
"step": 1670
},
{
"epoch": 2.54,
"learning_rate": 8.492152466367713e-06,
"loss": 0.23,
"step": 1680
},
{
"epoch": 2.56,
"learning_rate": 8.21188340807175e-06,
"loss": 0.253,
"step": 1690
},
{
"epoch": 2.57,
"learning_rate": 7.931614349775786e-06,
"loss": 0.2397,
"step": 1700
},
{
"epoch": 2.59,
"learning_rate": 7.651345291479821e-06,
"loss": 0.2319,
"step": 1710
},
{
"epoch": 2.6,
"learning_rate": 7.371076233183857e-06,
"loss": 0.217,
"step": 1720
},
{
"epoch": 2.62,
"learning_rate": 7.090807174887892e-06,
"loss": 0.275,
"step": 1730
},
{
"epoch": 2.63,
"learning_rate": 6.810538116591929e-06,
"loss": 0.2507,
"step": 1740
},
{
"epoch": 2.65,
"learning_rate": 6.530269058295964e-06,
"loss": 0.2409,
"step": 1750
},
{
"epoch": 2.66,
"learning_rate": 6.25e-06,
"loss": 0.2405,
"step": 1760
},
{
"epoch": 2.68,
"learning_rate": 5.969730941704036e-06,
"loss": 0.2353,
"step": 1770
},
{
"epoch": 2.69,
"learning_rate": 5.689461883408072e-06,
"loss": 0.2283,
"step": 1780
},
{
"epoch": 2.71,
"learning_rate": 5.409192825112108e-06,
"loss": 0.2595,
"step": 1790
},
{
"epoch": 2.72,
"learning_rate": 5.128923766816144e-06,
"loss": 0.2345,
"step": 1800
},
{
"epoch": 2.74,
"learning_rate": 4.848654708520179e-06,
"loss": 0.2261,
"step": 1810
},
{
"epoch": 2.75,
"learning_rate": 4.568385650224215e-06,
"loss": 0.233,
"step": 1820
},
{
"epoch": 2.77,
"learning_rate": 4.288116591928251e-06,
"loss": 0.2184,
"step": 1830
},
{
"epoch": 2.78,
"learning_rate": 4.007847533632287e-06,
"loss": 0.247,
"step": 1840
},
{
"epoch": 2.8,
"learning_rate": 3.7275784753363225e-06,
"loss": 0.2328,
"step": 1850
},
{
"epoch": 2.81,
"learning_rate": 3.447309417040359e-06,
"loss": 0.2115,
"step": 1860
},
{
"epoch": 2.83,
"learning_rate": 3.167040358744395e-06,
"loss": 0.2455,
"step": 1870
},
{
"epoch": 2.84,
"learning_rate": 2.886771300448431e-06,
"loss": 0.2406,
"step": 1880
},
{
"epoch": 2.86,
"learning_rate": 2.606502242152466e-06,
"loss": 0.2438,
"step": 1890
},
{
"epoch": 2.87,
"learning_rate": 2.3262331838565024e-06,
"loss": 0.2534,
"step": 1900
},
{
"epoch": 2.89,
"learning_rate": 2.045964125560538e-06,
"loss": 0.2053,
"step": 1910
},
{
"epoch": 2.9,
"learning_rate": 1.765695067264574e-06,
"loss": 0.241,
"step": 1920
},
{
"epoch": 2.92,
"learning_rate": 1.4854260089686098e-06,
"loss": 0.2144,
"step": 1930
},
{
"epoch": 2.93,
"learning_rate": 1.2051569506726458e-06,
"loss": 0.2587,
"step": 1940
},
{
"epoch": 2.95,
"learning_rate": 9.248878923766817e-07,
"loss": 0.2551,
"step": 1950
},
{
"epoch": 2.96,
"learning_rate": 6.446188340807175e-07,
"loss": 0.2279,
"step": 1960
},
{
"epoch": 2.98,
"learning_rate": 3.643497757847534e-07,
"loss": 0.2128,
"step": 1970
},
{
"epoch": 2.99,
"learning_rate": 8.408071748878925e-08,
"loss": 0.2444,
"step": 1980
},
{
"epoch": 3.0,
"eval_accuracy": 0.9557870124349027,
"eval_loss": 0.12056268006563187,
"eval_runtime": 124.8088,
"eval_samples_per_second": 75.387,
"eval_steps_per_second": 2.364,
"step": 1983
},
{
"epoch": 3.0,
"step": 1983,
"total_flos": 6.312630587402281e+18,
"train_loss": 0.39632425417036826,
"train_runtime": 5574.9078,
"train_samples_per_second": 45.565,
"train_steps_per_second": 0.356
}
],
"max_steps": 1983,
"num_train_epochs": 3,
"total_flos": 6.312630587402281e+18,
"trial_name": null,
"trial_params": null
}