PlantDiseaseClassifier-Resnet50 / trainer_state.json
SanketJadhav's picture
End of training
99518a4
{
"best_metric": 0.9641475073981334,
"best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-1098",
"epoch": 4.997724169321803,
"global_step": 2745,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0,
"loss": 0.3223,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 0.0,
"loss": 0.3467,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 0.0,
"loss": 0.2952,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 0.0,
"loss": 0.3184,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 0.0,
"loss": 0.3607,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 0.0,
"loss": 0.2938,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 0.0,
"loss": 0.3201,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 0.0,
"loss": 0.307,
"step": 80
},
{
"epoch": 0.16,
"learning_rate": 0.0,
"loss": 0.3133,
"step": 90
},
{
"epoch": 0.18,
"learning_rate": 0.0,
"loss": 0.295,
"step": 100
},
{
"epoch": 0.2,
"learning_rate": 0.0,
"loss": 0.3321,
"step": 110
},
{
"epoch": 0.22,
"learning_rate": 0.0,
"loss": 0.3218,
"step": 120
},
{
"epoch": 0.24,
"learning_rate": 0.0,
"loss": 0.3313,
"step": 130
},
{
"epoch": 0.25,
"learning_rate": 0.0,
"loss": 0.3518,
"step": 140
},
{
"epoch": 0.27,
"learning_rate": 0.0,
"loss": 0.319,
"step": 150
},
{
"epoch": 0.29,
"learning_rate": 0.0,
"loss": 0.318,
"step": 160
},
{
"epoch": 0.31,
"learning_rate": 0.0,
"loss": 0.3051,
"step": 170
},
{
"epoch": 0.33,
"learning_rate": 0.0,
"loss": 0.304,
"step": 180
},
{
"epoch": 0.35,
"learning_rate": 0.0,
"loss": 0.3102,
"step": 190
},
{
"epoch": 0.36,
"learning_rate": 0.0,
"loss": 0.2951,
"step": 200
},
{
"epoch": 0.38,
"learning_rate": 0.0,
"loss": 0.3074,
"step": 210
},
{
"epoch": 0.4,
"learning_rate": 0.0,
"loss": 0.3245,
"step": 220
},
{
"epoch": 0.42,
"learning_rate": 0.0,
"loss": 0.3138,
"step": 230
},
{
"epoch": 0.44,
"learning_rate": 0.0,
"loss": 0.3479,
"step": 240
},
{
"epoch": 0.46,
"learning_rate": 0.0,
"loss": 0.344,
"step": 250
},
{
"epoch": 0.47,
"learning_rate": 0.0,
"loss": 0.3239,
"step": 260
},
{
"epoch": 0.49,
"learning_rate": 0.0,
"loss": 0.3223,
"step": 270
},
{
"epoch": 0.51,
"learning_rate": 0.0,
"loss": 0.3292,
"step": 280
},
{
"epoch": 0.53,
"learning_rate": 0.0,
"loss": 0.2866,
"step": 290
},
{
"epoch": 0.55,
"learning_rate": 0.0,
"loss": 0.3019,
"step": 300
},
{
"epoch": 0.56,
"learning_rate": 0.0,
"loss": 0.3334,
"step": 310
},
{
"epoch": 0.58,
"learning_rate": 0.0,
"loss": 0.2834,
"step": 320
},
{
"epoch": 0.6,
"learning_rate": 0.0,
"loss": 0.3198,
"step": 330
},
{
"epoch": 0.62,
"learning_rate": 0.0,
"loss": 0.3173,
"step": 340
},
{
"epoch": 0.64,
"learning_rate": 0.0,
"loss": 0.3495,
"step": 350
},
{
"epoch": 0.66,
"learning_rate": 0.0,
"loss": 0.3267,
"step": 360
},
{
"epoch": 0.67,
"learning_rate": 0.0,
"loss": 0.3229,
"step": 370
},
{
"epoch": 0.69,
"learning_rate": 0.0,
"loss": 0.3154,
"step": 380
},
{
"epoch": 0.71,
"learning_rate": 0.0,
"loss": 0.2958,
"step": 390
},
{
"epoch": 0.73,
"learning_rate": 0.0,
"loss": 0.3068,
"step": 400
},
{
"epoch": 0.75,
"learning_rate": 0.0,
"loss": 0.3443,
"step": 410
},
{
"epoch": 0.76,
"learning_rate": 0.0,
"loss": 0.3371,
"step": 420
},
{
"epoch": 0.78,
"learning_rate": 0.0,
"loss": 0.3311,
"step": 430
},
{
"epoch": 0.8,
"learning_rate": 0.0,
"loss": 0.3345,
"step": 440
},
{
"epoch": 0.82,
"learning_rate": 0.0,
"loss": 0.2798,
"step": 450
},
{
"epoch": 0.84,
"learning_rate": 0.0,
"loss": 0.2834,
"step": 460
},
{
"epoch": 0.86,
"learning_rate": 0.0,
"loss": 0.3295,
"step": 470
},
{
"epoch": 0.87,
"learning_rate": 0.0,
"loss": 0.3176,
"step": 480
},
{
"epoch": 0.89,
"learning_rate": 0.0,
"loss": 0.281,
"step": 490
},
{
"epoch": 0.91,
"learning_rate": 0.0,
"loss": 0.3066,
"step": 500
},
{
"epoch": 0.93,
"learning_rate": 0.0,
"loss": 0.2898,
"step": 510
},
{
"epoch": 0.95,
"learning_rate": 0.0,
"loss": 0.307,
"step": 520
},
{
"epoch": 0.96,
"learning_rate": 0.0,
"loss": 0.3126,
"step": 530
},
{
"epoch": 0.98,
"learning_rate": 0.0,
"loss": 0.2976,
"step": 540
},
{
"epoch": 1.0,
"eval_accuracy": 0.9635784202139768,
"eval_loss": 0.1450216919183731,
"eval_runtime": 111.4659,
"eval_samples_per_second": 157.645,
"eval_steps_per_second": 4.934,
"step": 549
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.3563,
"step": 550
},
{
"epoch": 1.02,
"learning_rate": 0.0,
"loss": 0.3112,
"step": 560
},
{
"epoch": 1.04,
"learning_rate": 0.0,
"loss": 0.3078,
"step": 570
},
{
"epoch": 1.06,
"learning_rate": 0.0,
"loss": 0.2967,
"step": 580
},
{
"epoch": 1.07,
"learning_rate": 0.0,
"loss": 0.2955,
"step": 590
},
{
"epoch": 1.09,
"learning_rate": 0.0,
"loss": 0.3216,
"step": 600
},
{
"epoch": 1.11,
"learning_rate": 0.0,
"loss": 0.3227,
"step": 610
},
{
"epoch": 1.13,
"learning_rate": 0.0,
"loss": 0.3164,
"step": 620
},
{
"epoch": 1.15,
"learning_rate": 0.0,
"loss": 0.3181,
"step": 630
},
{
"epoch": 1.17,
"learning_rate": 0.0,
"loss": 0.2877,
"step": 640
},
{
"epoch": 1.18,
"learning_rate": 0.0,
"loss": 0.2977,
"step": 650
},
{
"epoch": 1.2,
"learning_rate": 0.0,
"loss": 0.3257,
"step": 660
},
{
"epoch": 1.22,
"learning_rate": 0.0,
"loss": 0.3415,
"step": 670
},
{
"epoch": 1.24,
"learning_rate": 0.0,
"loss": 0.3257,
"step": 680
},
{
"epoch": 1.26,
"learning_rate": 0.0,
"loss": 0.3145,
"step": 690
},
{
"epoch": 1.27,
"learning_rate": 0.0,
"loss": 0.3626,
"step": 700
},
{
"epoch": 1.29,
"learning_rate": 0.0,
"loss": 0.3251,
"step": 710
},
{
"epoch": 1.31,
"learning_rate": 0.0,
"loss": 0.3272,
"step": 720
},
{
"epoch": 1.33,
"learning_rate": 0.0,
"loss": 0.315,
"step": 730
},
{
"epoch": 1.35,
"learning_rate": 0.0,
"loss": 0.318,
"step": 740
},
{
"epoch": 1.37,
"learning_rate": 0.0,
"loss": 0.3067,
"step": 750
},
{
"epoch": 1.38,
"learning_rate": 0.0,
"loss": 0.2829,
"step": 760
},
{
"epoch": 1.4,
"learning_rate": 0.0,
"loss": 0.2894,
"step": 770
},
{
"epoch": 1.42,
"learning_rate": 0.0,
"loss": 0.3045,
"step": 780
},
{
"epoch": 1.44,
"learning_rate": 0.0,
"loss": 0.3003,
"step": 790
},
{
"epoch": 1.46,
"learning_rate": 0.0,
"loss": 0.2724,
"step": 800
},
{
"epoch": 1.47,
"learning_rate": 0.0,
"loss": 0.2818,
"step": 810
},
{
"epoch": 1.49,
"learning_rate": 0.0,
"loss": 0.2925,
"step": 820
},
{
"epoch": 1.51,
"learning_rate": 0.0,
"loss": 0.3095,
"step": 830
},
{
"epoch": 1.53,
"learning_rate": 0.0,
"loss": 0.3079,
"step": 840
},
{
"epoch": 1.55,
"learning_rate": 0.0,
"loss": 0.3226,
"step": 850
},
{
"epoch": 1.57,
"learning_rate": 0.0,
"loss": 0.3346,
"step": 860
},
{
"epoch": 1.58,
"learning_rate": 0.0,
"loss": 0.3343,
"step": 870
},
{
"epoch": 1.6,
"learning_rate": 0.0,
"loss": 0.2956,
"step": 880
},
{
"epoch": 1.62,
"learning_rate": 0.0,
"loss": 0.3006,
"step": 890
},
{
"epoch": 1.64,
"learning_rate": 0.0,
"loss": 0.3165,
"step": 900
},
{
"epoch": 1.66,
"learning_rate": 0.0,
"loss": 0.3185,
"step": 910
},
{
"epoch": 1.68,
"learning_rate": 0.0,
"loss": 0.2932,
"step": 920
},
{
"epoch": 1.69,
"learning_rate": 0.0,
"loss": 0.3233,
"step": 930
},
{
"epoch": 1.71,
"learning_rate": 0.0,
"loss": 0.2804,
"step": 940
},
{
"epoch": 1.73,
"learning_rate": 0.0,
"loss": 0.3244,
"step": 950
},
{
"epoch": 1.75,
"learning_rate": 0.0,
"loss": 0.3166,
"step": 960
},
{
"epoch": 1.77,
"learning_rate": 0.0,
"loss": 0.2889,
"step": 970
},
{
"epoch": 1.78,
"learning_rate": 0.0,
"loss": 0.3084,
"step": 980
},
{
"epoch": 1.8,
"learning_rate": 0.0,
"loss": 0.3083,
"step": 990
},
{
"epoch": 1.82,
"learning_rate": 0.0,
"loss": 0.3597,
"step": 1000
},
{
"epoch": 1.84,
"learning_rate": 0.0,
"loss": 0.3192,
"step": 1010
},
{
"epoch": 1.86,
"learning_rate": 0.0,
"loss": 0.3044,
"step": 1020
},
{
"epoch": 1.88,
"learning_rate": 0.0,
"loss": 0.3149,
"step": 1030
},
{
"epoch": 1.89,
"learning_rate": 0.0,
"loss": 0.3192,
"step": 1040
},
{
"epoch": 1.91,
"learning_rate": 0.0,
"loss": 0.2853,
"step": 1050
},
{
"epoch": 1.93,
"learning_rate": 0.0,
"loss": 0.3255,
"step": 1060
},
{
"epoch": 1.95,
"learning_rate": 0.0,
"loss": 0.3079,
"step": 1070
},
{
"epoch": 1.97,
"learning_rate": 0.0,
"loss": 0.2867,
"step": 1080
},
{
"epoch": 1.98,
"learning_rate": 0.0,
"loss": 0.3388,
"step": 1090
},
{
"epoch": 2.0,
"eval_accuracy": 0.9641475073981334,
"eval_loss": 0.1382417380809784,
"eval_runtime": 112.0412,
"eval_samples_per_second": 156.835,
"eval_steps_per_second": 4.909,
"step": 1098
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 0.3561,
"step": 1100
},
{
"epoch": 2.02,
"learning_rate": 0.0,
"loss": 0.296,
"step": 1110
},
{
"epoch": 2.04,
"learning_rate": 0.0,
"loss": 0.2846,
"step": 1120
},
{
"epoch": 2.06,
"learning_rate": 0.0,
"loss": 0.3364,
"step": 1130
},
{
"epoch": 2.08,
"learning_rate": 0.0,
"loss": 0.3638,
"step": 1140
},
{
"epoch": 2.09,
"learning_rate": 0.0,
"loss": 0.3259,
"step": 1150
},
{
"epoch": 2.11,
"learning_rate": 0.0,
"loss": 0.316,
"step": 1160
},
{
"epoch": 2.13,
"learning_rate": 0.0,
"loss": 0.3298,
"step": 1170
},
{
"epoch": 2.15,
"learning_rate": 0.0,
"loss": 0.3135,
"step": 1180
},
{
"epoch": 2.17,
"learning_rate": 0.0,
"loss": 0.3031,
"step": 1190
},
{
"epoch": 2.18,
"learning_rate": 0.0,
"loss": 0.2982,
"step": 1200
},
{
"epoch": 2.2,
"learning_rate": 0.0,
"loss": 0.3074,
"step": 1210
},
{
"epoch": 2.22,
"learning_rate": 0.0,
"loss": 0.3465,
"step": 1220
},
{
"epoch": 2.24,
"learning_rate": 0.0,
"loss": 0.3148,
"step": 1230
},
{
"epoch": 2.26,
"learning_rate": 0.0,
"loss": 0.3406,
"step": 1240
},
{
"epoch": 2.28,
"learning_rate": 0.0,
"loss": 0.2878,
"step": 1250
},
{
"epoch": 2.29,
"learning_rate": 0.0,
"loss": 0.3026,
"step": 1260
},
{
"epoch": 2.31,
"learning_rate": 0.0,
"loss": 0.3189,
"step": 1270
},
{
"epoch": 2.33,
"learning_rate": 0.0,
"loss": 0.312,
"step": 1280
},
{
"epoch": 2.35,
"learning_rate": 0.0,
"loss": 0.3393,
"step": 1290
},
{
"epoch": 2.37,
"learning_rate": 0.0,
"loss": 0.3389,
"step": 1300
},
{
"epoch": 2.39,
"learning_rate": 0.0,
"loss": 0.3073,
"step": 1310
},
{
"epoch": 2.4,
"learning_rate": 0.0,
"loss": 0.3525,
"step": 1320
},
{
"epoch": 2.42,
"learning_rate": 0.0,
"loss": 0.2958,
"step": 1330
},
{
"epoch": 2.44,
"learning_rate": 0.0,
"loss": 0.2998,
"step": 1340
},
{
"epoch": 2.46,
"learning_rate": 0.0,
"loss": 0.2992,
"step": 1350
},
{
"epoch": 2.48,
"learning_rate": 0.0,
"loss": 0.314,
"step": 1360
},
{
"epoch": 2.49,
"learning_rate": 0.0,
"loss": 0.3128,
"step": 1370
},
{
"epoch": 2.51,
"learning_rate": 0.0,
"loss": 0.3074,
"step": 1380
},
{
"epoch": 2.53,
"learning_rate": 0.0,
"loss": 0.3189,
"step": 1390
},
{
"epoch": 2.55,
"learning_rate": 0.0,
"loss": 0.3284,
"step": 1400
},
{
"epoch": 2.57,
"learning_rate": 0.0,
"loss": 0.3278,
"step": 1410
},
{
"epoch": 2.59,
"learning_rate": 0.0,
"loss": 0.2897,
"step": 1420
},
{
"epoch": 2.6,
"learning_rate": 0.0,
"loss": 0.3472,
"step": 1430
},
{
"epoch": 2.62,
"learning_rate": 0.0,
"loss": 0.3571,
"step": 1440
},
{
"epoch": 2.64,
"learning_rate": 0.0,
"loss": 0.3078,
"step": 1450
},
{
"epoch": 2.66,
"learning_rate": 0.0,
"loss": 0.3512,
"step": 1460
},
{
"epoch": 2.68,
"learning_rate": 0.0,
"loss": 0.3017,
"step": 1470
},
{
"epoch": 2.69,
"learning_rate": 0.0,
"loss": 0.302,
"step": 1480
},
{
"epoch": 2.71,
"learning_rate": 0.0,
"loss": 0.3281,
"step": 1490
},
{
"epoch": 2.73,
"learning_rate": 0.0,
"loss": 0.3511,
"step": 1500
},
{
"epoch": 2.75,
"learning_rate": 0.0,
"loss": 0.3088,
"step": 1510
},
{
"epoch": 2.77,
"learning_rate": 0.0,
"loss": 0.2802,
"step": 1520
},
{
"epoch": 2.79,
"learning_rate": 0.0,
"loss": 0.304,
"step": 1530
},
{
"epoch": 2.8,
"learning_rate": 0.0,
"loss": 0.3119,
"step": 1540
},
{
"epoch": 2.82,
"learning_rate": 0.0,
"loss": 0.3194,
"step": 1550
},
{
"epoch": 2.84,
"learning_rate": 0.0,
"loss": 0.3028,
"step": 1560
},
{
"epoch": 2.86,
"learning_rate": 0.0,
"loss": 0.2849,
"step": 1570
},
{
"epoch": 2.88,
"learning_rate": 0.0,
"loss": 0.2897,
"step": 1580
},
{
"epoch": 2.89,
"learning_rate": 0.0,
"loss": 0.309,
"step": 1590
},
{
"epoch": 2.91,
"learning_rate": 0.0,
"loss": 0.3223,
"step": 1600
},
{
"epoch": 2.93,
"learning_rate": 0.0,
"loss": 0.3157,
"step": 1610
},
{
"epoch": 2.95,
"learning_rate": 0.0,
"loss": 0.3112,
"step": 1620
},
{
"epoch": 2.97,
"learning_rate": 0.0,
"loss": 0.2911,
"step": 1630
},
{
"epoch": 2.99,
"learning_rate": 0.0,
"loss": 0.361,
"step": 1640
},
{
"epoch": 3.0,
"eval_accuracy": 0.9631800591850671,
"eval_loss": 0.14322593808174133,
"eval_runtime": 112.3273,
"eval_samples_per_second": 156.436,
"eval_steps_per_second": 4.896,
"step": 1647
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.3124,
"step": 1650
},
{
"epoch": 3.02,
"learning_rate": 0.0,
"loss": 0.3007,
"step": 1660
},
{
"epoch": 3.04,
"learning_rate": 0.0,
"loss": 0.3119,
"step": 1670
},
{
"epoch": 3.06,
"learning_rate": 0.0,
"loss": 0.2744,
"step": 1680
},
{
"epoch": 3.08,
"learning_rate": 0.0,
"loss": 0.3164,
"step": 1690
},
{
"epoch": 3.1,
"learning_rate": 0.0,
"loss": 0.336,
"step": 1700
},
{
"epoch": 3.11,
"learning_rate": 0.0,
"loss": 0.3423,
"step": 1710
},
{
"epoch": 3.13,
"learning_rate": 0.0,
"loss": 0.347,
"step": 1720
},
{
"epoch": 3.15,
"learning_rate": 0.0,
"loss": 0.3064,
"step": 1730
},
{
"epoch": 3.17,
"learning_rate": 0.0,
"loss": 0.3241,
"step": 1740
},
{
"epoch": 3.19,
"learning_rate": 0.0,
"loss": 0.3381,
"step": 1750
},
{
"epoch": 3.2,
"learning_rate": 0.0,
"loss": 0.2719,
"step": 1760
},
{
"epoch": 3.22,
"learning_rate": 0.0,
"loss": 0.3141,
"step": 1770
},
{
"epoch": 3.24,
"learning_rate": 0.0,
"loss": 0.3369,
"step": 1780
},
{
"epoch": 3.26,
"learning_rate": 0.0,
"loss": 0.2892,
"step": 1790
},
{
"epoch": 3.28,
"learning_rate": 0.0,
"loss": 0.3228,
"step": 1800
},
{
"epoch": 3.3,
"learning_rate": 0.0,
"loss": 0.3339,
"step": 1810
},
{
"epoch": 3.31,
"learning_rate": 0.0,
"loss": 0.2774,
"step": 1820
},
{
"epoch": 3.33,
"learning_rate": 0.0,
"loss": 0.3103,
"step": 1830
},
{
"epoch": 3.35,
"learning_rate": 0.0,
"loss": 0.2864,
"step": 1840
},
{
"epoch": 3.37,
"learning_rate": 0.0,
"loss": 0.3264,
"step": 1850
},
{
"epoch": 3.39,
"learning_rate": 0.0,
"loss": 0.3145,
"step": 1860
},
{
"epoch": 3.4,
"learning_rate": 0.0,
"loss": 0.3559,
"step": 1870
},
{
"epoch": 3.42,
"learning_rate": 0.0,
"loss": 0.3365,
"step": 1880
},
{
"epoch": 3.44,
"learning_rate": 0.0,
"loss": 0.2965,
"step": 1890
},
{
"epoch": 3.46,
"learning_rate": 0.0,
"loss": 0.3412,
"step": 1900
},
{
"epoch": 3.48,
"learning_rate": 0.0,
"loss": 0.3237,
"step": 1910
},
{
"epoch": 3.5,
"learning_rate": 0.0,
"loss": 0.3052,
"step": 1920
},
{
"epoch": 3.51,
"learning_rate": 0.0,
"loss": 0.296,
"step": 1930
},
{
"epoch": 3.53,
"learning_rate": 0.0,
"loss": 0.3165,
"step": 1940
},
{
"epoch": 3.55,
"learning_rate": 0.0,
"loss": 0.3097,
"step": 1950
},
{
"epoch": 3.57,
"learning_rate": 0.0,
"loss": 0.3141,
"step": 1960
},
{
"epoch": 3.59,
"learning_rate": 0.0,
"loss": 0.3165,
"step": 1970
},
{
"epoch": 3.6,
"learning_rate": 0.0,
"loss": 0.3504,
"step": 1980
},
{
"epoch": 3.62,
"learning_rate": 0.0,
"loss": 0.3353,
"step": 1990
},
{
"epoch": 3.64,
"learning_rate": 0.0,
"loss": 0.3096,
"step": 2000
},
{
"epoch": 3.66,
"learning_rate": 0.0,
"loss": 0.3167,
"step": 2010
},
{
"epoch": 3.68,
"learning_rate": 0.0,
"loss": 0.2839,
"step": 2020
},
{
"epoch": 3.7,
"learning_rate": 0.0,
"loss": 0.2972,
"step": 2030
},
{
"epoch": 3.71,
"learning_rate": 0.0,
"loss": 0.3193,
"step": 2040
},
{
"epoch": 3.73,
"learning_rate": 0.0,
"loss": 0.2793,
"step": 2050
},
{
"epoch": 3.75,
"learning_rate": 0.0,
"loss": 0.3599,
"step": 2060
},
{
"epoch": 3.77,
"learning_rate": 0.0,
"loss": 0.3134,
"step": 2070
},
{
"epoch": 3.79,
"learning_rate": 0.0,
"loss": 0.3017,
"step": 2080
},
{
"epoch": 3.81,
"learning_rate": 0.0,
"loss": 0.3107,
"step": 2090
},
{
"epoch": 3.82,
"learning_rate": 0.0,
"loss": 0.3402,
"step": 2100
},
{
"epoch": 3.84,
"learning_rate": 0.0,
"loss": 0.3046,
"step": 2110
},
{
"epoch": 3.86,
"learning_rate": 0.0,
"loss": 0.3675,
"step": 2120
},
{
"epoch": 3.88,
"learning_rate": 0.0,
"loss": 0.3236,
"step": 2130
},
{
"epoch": 3.9,
"learning_rate": 0.0,
"loss": 0.2909,
"step": 2140
},
{
"epoch": 3.91,
"learning_rate": 0.0,
"loss": 0.3472,
"step": 2150
},
{
"epoch": 3.93,
"learning_rate": 0.0,
"loss": 0.2666,
"step": 2160
},
{
"epoch": 3.95,
"learning_rate": 0.0,
"loss": 0.3138,
"step": 2170
},
{
"epoch": 3.97,
"learning_rate": 0.0,
"loss": 0.3314,
"step": 2180
},
{
"epoch": 3.99,
"learning_rate": 0.0,
"loss": 0.3163,
"step": 2190
},
{
"epoch": 4.0,
"eval_accuracy": 0.9639767812428864,
"eval_loss": 0.14118124544620514,
"eval_runtime": 112.337,
"eval_samples_per_second": 156.422,
"eval_steps_per_second": 4.896,
"step": 2197
},
{
"epoch": 4.01,
"learning_rate": 0.0,
"loss": 0.2996,
"step": 2200
},
{
"epoch": 4.02,
"learning_rate": 0.0,
"loss": 0.3324,
"step": 2210
},
{
"epoch": 4.04,
"learning_rate": 0.0,
"loss": 0.2756,
"step": 2220
},
{
"epoch": 4.06,
"learning_rate": 0.0,
"loss": 0.2944,
"step": 2230
},
{
"epoch": 4.08,
"learning_rate": 0.0,
"loss": 0.3082,
"step": 2240
},
{
"epoch": 4.1,
"learning_rate": 0.0,
"loss": 0.3241,
"step": 2250
},
{
"epoch": 4.11,
"learning_rate": 0.0,
"loss": 0.3301,
"step": 2260
},
{
"epoch": 4.13,
"learning_rate": 0.0,
"loss": 0.283,
"step": 2270
},
{
"epoch": 4.15,
"learning_rate": 0.0,
"loss": 0.3029,
"step": 2280
},
{
"epoch": 4.17,
"learning_rate": 0.0,
"loss": 0.3299,
"step": 2290
},
{
"epoch": 4.19,
"learning_rate": 0.0,
"loss": 0.3163,
"step": 2300
},
{
"epoch": 4.21,
"learning_rate": 0.0,
"loss": 0.2886,
"step": 2310
},
{
"epoch": 4.22,
"learning_rate": 0.0,
"loss": 0.2912,
"step": 2320
},
{
"epoch": 4.24,
"learning_rate": 0.0,
"loss": 0.3443,
"step": 2330
},
{
"epoch": 4.26,
"learning_rate": 0.0,
"loss": 0.3066,
"step": 2340
},
{
"epoch": 4.28,
"learning_rate": 0.0,
"loss": 0.3289,
"step": 2350
},
{
"epoch": 4.3,
"learning_rate": 0.0,
"loss": 0.3178,
"step": 2360
},
{
"epoch": 4.31,
"learning_rate": 0.0,
"loss": 0.3248,
"step": 2370
},
{
"epoch": 4.33,
"learning_rate": 0.0,
"loss": 0.3366,
"step": 2380
},
{
"epoch": 4.35,
"learning_rate": 0.0,
"loss": 0.3215,
"step": 2390
},
{
"epoch": 4.37,
"learning_rate": 0.0,
"loss": 0.2989,
"step": 2400
},
{
"epoch": 4.39,
"learning_rate": 0.0,
"loss": 0.3011,
"step": 2410
},
{
"epoch": 4.41,
"learning_rate": 0.0,
"loss": 0.3113,
"step": 2420
},
{
"epoch": 4.42,
"learning_rate": 0.0,
"loss": 0.3419,
"step": 2430
},
{
"epoch": 4.44,
"learning_rate": 0.0,
"loss": 0.3369,
"step": 2440
},
{
"epoch": 4.46,
"learning_rate": 0.0,
"loss": 0.3148,
"step": 2450
},
{
"epoch": 4.48,
"learning_rate": 0.0,
"loss": 0.3224,
"step": 2460
},
{
"epoch": 4.5,
"learning_rate": 0.0,
"loss": 0.2957,
"step": 2470
},
{
"epoch": 4.52,
"learning_rate": 0.0,
"loss": 0.2852,
"step": 2480
},
{
"epoch": 4.53,
"learning_rate": 0.0,
"loss": 0.3099,
"step": 2490
},
{
"epoch": 4.55,
"learning_rate": 0.0,
"loss": 0.3152,
"step": 2500
},
{
"epoch": 4.57,
"learning_rate": 0.0,
"loss": 0.328,
"step": 2510
},
{
"epoch": 4.59,
"learning_rate": 0.0,
"loss": 0.3273,
"step": 2520
},
{
"epoch": 4.61,
"learning_rate": 0.0,
"loss": 0.3105,
"step": 2530
},
{
"epoch": 4.62,
"learning_rate": 0.0,
"loss": 0.2704,
"step": 2540
},
{
"epoch": 4.64,
"learning_rate": 0.0,
"loss": 0.3113,
"step": 2550
},
{
"epoch": 4.66,
"learning_rate": 0.0,
"loss": 0.291,
"step": 2560
},
{
"epoch": 4.68,
"learning_rate": 0.0,
"loss": 0.3214,
"step": 2570
},
{
"epoch": 4.7,
"learning_rate": 0.0,
"loss": 0.3307,
"step": 2580
},
{
"epoch": 4.72,
"learning_rate": 0.0,
"loss": 0.2952,
"step": 2590
},
{
"epoch": 4.73,
"learning_rate": 0.0,
"loss": 0.3218,
"step": 2600
},
{
"epoch": 4.75,
"learning_rate": 0.0,
"loss": 0.2881,
"step": 2610
},
{
"epoch": 4.77,
"learning_rate": 0.0,
"loss": 0.2984,
"step": 2620
},
{
"epoch": 4.79,
"learning_rate": 0.0,
"loss": 0.3318,
"step": 2630
},
{
"epoch": 4.81,
"learning_rate": 0.0,
"loss": 0.3192,
"step": 2640
},
{
"epoch": 4.82,
"learning_rate": 0.0,
"loss": 0.2928,
"step": 2650
},
{
"epoch": 4.84,
"learning_rate": 0.0,
"loss": 0.3178,
"step": 2660
},
{
"epoch": 4.86,
"learning_rate": 0.0,
"loss": 0.3158,
"step": 2670
},
{
"epoch": 4.88,
"learning_rate": 0.0,
"loss": 0.3225,
"step": 2680
},
{
"epoch": 4.9,
"learning_rate": 0.0,
"loss": 0.3287,
"step": 2690
},
{
"epoch": 4.92,
"learning_rate": 0.0,
"loss": 0.2937,
"step": 2700
},
{
"epoch": 4.93,
"learning_rate": 0.0,
"loss": 0.2998,
"step": 2710
},
{
"epoch": 4.95,
"learning_rate": 0.0,
"loss": 0.3084,
"step": 2720
},
{
"epoch": 4.97,
"learning_rate": 0.0,
"loss": 0.3264,
"step": 2730
},
{
"epoch": 4.99,
"learning_rate": 0.0,
"loss": 0.3103,
"step": 2740
},
{
"epoch": 5.0,
"eval_accuracy": 0.9639198725244708,
"eval_loss": 0.13910169899463654,
"eval_runtime": 112.3738,
"eval_samples_per_second": 156.371,
"eval_steps_per_second": 4.894,
"step": 2745
},
{
"epoch": 5.0,
"step": 2745,
"total_flos": 7.485957524358513e+18,
"train_loss": 0.31472766021561754,
"train_runtime": 5227.0581,
"train_samples_per_second": 67.241,
"train_steps_per_second": 0.525
}
],
"max_steps": 2745,
"num_train_epochs": 5,
"total_flos": 7.485957524358513e+18,
"trial_name": null,
"trial_params": null
}