vit-base-cifar10 / trainer_state.json
simlaharma's picture
End of training
b5c013c
raw
history blame contribute delete
No virus
83.3 kB
{
"best_metric": 2.328753709793091,
"best_model_checkpoint": "./cifar10_hbfp2,64/checkpoint-1328",
"epoch": 9.999623635679338,
"global_step": 6640,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.992469879518072e-05,
"loss": 2.303,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 4.984939759036145e-05,
"loss": 2.3059,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 4.9774096385542175e-05,
"loss": 2.308,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 4.9698795180722894e-05,
"loss": 2.3078,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 4.962349397590362e-05,
"loss": 2.3086,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 4.954819277108434e-05,
"loss": 2.3078,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 4.947289156626506e-05,
"loss": 2.3041,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 4.9397590361445786e-05,
"loss": 2.3138,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 4.932228915662651e-05,
"loss": 2.3229,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 4.924698795180723e-05,
"loss": 2.308,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 4.917168674698795e-05,
"loss": 2.3083,
"step": 110
},
{
"epoch": 0.18,
"learning_rate": 4.909638554216868e-05,
"loss": 2.311,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 4.90210843373494e-05,
"loss": 2.3162,
"step": 130
},
{
"epoch": 0.21,
"learning_rate": 4.8945783132530124e-05,
"loss": 2.3042,
"step": 140
},
{
"epoch": 0.23,
"learning_rate": 4.887048192771085e-05,
"loss": 2.3084,
"step": 150
},
{
"epoch": 0.24,
"learning_rate": 4.879518072289157e-05,
"loss": 2.3077,
"step": 160
},
{
"epoch": 0.26,
"learning_rate": 4.871987951807229e-05,
"loss": 2.3108,
"step": 170
},
{
"epoch": 0.27,
"learning_rate": 4.8644578313253016e-05,
"loss": 2.3062,
"step": 180
},
{
"epoch": 0.29,
"learning_rate": 4.8569277108433736e-05,
"loss": 2.3112,
"step": 190
},
{
"epoch": 0.3,
"learning_rate": 4.8493975903614455e-05,
"loss": 2.318,
"step": 200
},
{
"epoch": 0.32,
"learning_rate": 4.841867469879519e-05,
"loss": 2.319,
"step": 210
},
{
"epoch": 0.33,
"learning_rate": 4.834337349397591e-05,
"loss": 2.3082,
"step": 220
},
{
"epoch": 0.35,
"learning_rate": 4.826807228915663e-05,
"loss": 2.3207,
"step": 230
},
{
"epoch": 0.36,
"learning_rate": 4.8192771084337354e-05,
"loss": 2.3087,
"step": 240
},
{
"epoch": 0.38,
"learning_rate": 4.8117469879518074e-05,
"loss": 2.3204,
"step": 250
},
{
"epoch": 0.39,
"learning_rate": 4.804216867469879e-05,
"loss": 2.3026,
"step": 260
},
{
"epoch": 0.41,
"learning_rate": 4.796686746987952e-05,
"loss": 2.3105,
"step": 270
},
{
"epoch": 0.42,
"learning_rate": 4.7891566265060246e-05,
"loss": 2.3089,
"step": 280
},
{
"epoch": 0.44,
"learning_rate": 4.7816265060240965e-05,
"loss": 2.3197,
"step": 290
},
{
"epoch": 0.45,
"learning_rate": 4.774096385542169e-05,
"loss": 2.3203,
"step": 300
},
{
"epoch": 0.47,
"learning_rate": 4.766566265060241e-05,
"loss": 2.3131,
"step": 310
},
{
"epoch": 0.48,
"learning_rate": 4.759036144578313e-05,
"loss": 2.3141,
"step": 320
},
{
"epoch": 0.5,
"learning_rate": 4.751506024096386e-05,
"loss": 2.3076,
"step": 330
},
{
"epoch": 0.51,
"learning_rate": 4.7439759036144584e-05,
"loss": 2.3162,
"step": 340
},
{
"epoch": 0.53,
"learning_rate": 4.73644578313253e-05,
"loss": 2.3079,
"step": 350
},
{
"epoch": 0.54,
"learning_rate": 4.728915662650602e-05,
"loss": 2.301,
"step": 360
},
{
"epoch": 0.56,
"learning_rate": 4.721385542168675e-05,
"loss": 2.3247,
"step": 370
},
{
"epoch": 0.57,
"learning_rate": 4.713855421686747e-05,
"loss": 2.319,
"step": 380
},
{
"epoch": 0.59,
"learning_rate": 4.7063253012048195e-05,
"loss": 2.3075,
"step": 390
},
{
"epoch": 0.6,
"learning_rate": 4.698795180722892e-05,
"loss": 2.3267,
"step": 400
},
{
"epoch": 0.62,
"learning_rate": 4.691265060240964e-05,
"loss": 2.3128,
"step": 410
},
{
"epoch": 0.63,
"learning_rate": 4.683734939759036e-05,
"loss": 2.3059,
"step": 420
},
{
"epoch": 0.65,
"learning_rate": 4.676204819277109e-05,
"loss": 2.3161,
"step": 430
},
{
"epoch": 0.66,
"learning_rate": 4.668674698795181e-05,
"loss": 2.3169,
"step": 440
},
{
"epoch": 0.68,
"learning_rate": 4.661144578313253e-05,
"loss": 2.3265,
"step": 450
},
{
"epoch": 0.69,
"learning_rate": 4.653614457831326e-05,
"loss": 2.3258,
"step": 460
},
{
"epoch": 0.71,
"learning_rate": 4.646084337349398e-05,
"loss": 2.3263,
"step": 470
},
{
"epoch": 0.72,
"learning_rate": 4.63855421686747e-05,
"loss": 2.3256,
"step": 480
},
{
"epoch": 0.74,
"learning_rate": 4.6310240963855425e-05,
"loss": 2.3216,
"step": 490
},
{
"epoch": 0.75,
"learning_rate": 4.6234939759036145e-05,
"loss": 2.3122,
"step": 500
},
{
"epoch": 0.77,
"learning_rate": 4.615963855421687e-05,
"loss": 2.327,
"step": 510
},
{
"epoch": 0.78,
"learning_rate": 4.608433734939759e-05,
"loss": 2.3187,
"step": 520
},
{
"epoch": 0.8,
"learning_rate": 4.600903614457832e-05,
"loss": 2.312,
"step": 530
},
{
"epoch": 0.81,
"learning_rate": 4.5933734939759037e-05,
"loss": 2.3274,
"step": 540
},
{
"epoch": 0.83,
"learning_rate": 4.585843373493976e-05,
"loss": 2.3279,
"step": 550
},
{
"epoch": 0.84,
"learning_rate": 4.578313253012048e-05,
"loss": 2.3307,
"step": 560
},
{
"epoch": 0.86,
"learning_rate": 4.570783132530121e-05,
"loss": 2.324,
"step": 570
},
{
"epoch": 0.87,
"learning_rate": 4.563253012048193e-05,
"loss": 2.3216,
"step": 580
},
{
"epoch": 0.89,
"learning_rate": 4.5557228915662655e-05,
"loss": 2.3184,
"step": 590
},
{
"epoch": 0.9,
"learning_rate": 4.5481927710843374e-05,
"loss": 2.3159,
"step": 600
},
{
"epoch": 0.92,
"learning_rate": 4.5406626506024094e-05,
"loss": 2.3238,
"step": 610
},
{
"epoch": 0.93,
"learning_rate": 4.533132530120482e-05,
"loss": 2.3233,
"step": 620
},
{
"epoch": 0.95,
"learning_rate": 4.525602409638555e-05,
"loss": 2.3299,
"step": 630
},
{
"epoch": 0.96,
"learning_rate": 4.5180722891566266e-05,
"loss": 2.3401,
"step": 640
},
{
"epoch": 0.98,
"learning_rate": 4.510542168674699e-05,
"loss": 2.3291,
"step": 650
},
{
"epoch": 0.99,
"learning_rate": 4.503012048192771e-05,
"loss": 2.3324,
"step": 660
},
{
"epoch": 1.0,
"eval_accuracy": 0.09666666666666666,
"eval_loss": 2.3351855278015137,
"eval_runtime": 90.5384,
"eval_samples_per_second": 82.838,
"eval_steps_per_second": 5.18,
"step": 664
},
{
"epoch": 1.01,
"learning_rate": 4.495481927710843e-05,
"loss": 2.3837,
"step": 670
},
{
"epoch": 1.02,
"learning_rate": 4.487951807228916e-05,
"loss": 2.326,
"step": 680
},
{
"epoch": 1.04,
"learning_rate": 4.4804216867469885e-05,
"loss": 2.3356,
"step": 690
},
{
"epoch": 1.05,
"learning_rate": 4.4728915662650604e-05,
"loss": 2.3464,
"step": 700
},
{
"epoch": 1.07,
"learning_rate": 4.465361445783133e-05,
"loss": 2.3346,
"step": 710
},
{
"epoch": 1.08,
"learning_rate": 4.457831325301205e-05,
"loss": 2.3325,
"step": 720
},
{
"epoch": 1.1,
"learning_rate": 4.450301204819277e-05,
"loss": 2.3444,
"step": 730
},
{
"epoch": 1.11,
"learning_rate": 4.4427710843373496e-05,
"loss": 2.3249,
"step": 740
},
{
"epoch": 1.13,
"learning_rate": 4.435240963855422e-05,
"loss": 2.3472,
"step": 750
},
{
"epoch": 1.14,
"learning_rate": 4.427710843373494e-05,
"loss": 2.3406,
"step": 760
},
{
"epoch": 1.16,
"learning_rate": 4.420180722891566e-05,
"loss": 2.3482,
"step": 770
},
{
"epoch": 1.17,
"learning_rate": 4.412650602409639e-05,
"loss": 2.3323,
"step": 780
},
{
"epoch": 1.19,
"learning_rate": 4.405120481927711e-05,
"loss": 2.3407,
"step": 790
},
{
"epoch": 1.2,
"learning_rate": 4.3975903614457834e-05,
"loss": 2.3466,
"step": 800
},
{
"epoch": 1.22,
"learning_rate": 4.390060240963856e-05,
"loss": 2.3505,
"step": 810
},
{
"epoch": 1.23,
"learning_rate": 4.382530120481928e-05,
"loss": 2.3289,
"step": 820
},
{
"epoch": 1.25,
"learning_rate": 4.375e-05,
"loss": 2.3513,
"step": 830
},
{
"epoch": 1.26,
"learning_rate": 4.3674698795180726e-05,
"loss": 2.3546,
"step": 840
},
{
"epoch": 1.28,
"learning_rate": 4.3599397590361446e-05,
"loss": 2.3134,
"step": 850
},
{
"epoch": 1.3,
"learning_rate": 4.352409638554217e-05,
"loss": 2.3286,
"step": 860
},
{
"epoch": 1.31,
"learning_rate": 4.34487951807229e-05,
"loss": 2.3346,
"step": 870
},
{
"epoch": 1.33,
"learning_rate": 4.337349397590362e-05,
"loss": 2.3357,
"step": 880
},
{
"epoch": 1.34,
"learning_rate": 4.329819277108434e-05,
"loss": 2.3316,
"step": 890
},
{
"epoch": 1.36,
"learning_rate": 4.3222891566265064e-05,
"loss": 2.3363,
"step": 900
},
{
"epoch": 1.37,
"learning_rate": 4.3147590361445783e-05,
"loss": 2.3385,
"step": 910
},
{
"epoch": 1.39,
"learning_rate": 4.307228915662651e-05,
"loss": 2.354,
"step": 920
},
{
"epoch": 1.4,
"learning_rate": 4.299698795180723e-05,
"loss": 2.3349,
"step": 930
},
{
"epoch": 1.42,
"learning_rate": 4.2921686746987956e-05,
"loss": 2.3247,
"step": 940
},
{
"epoch": 1.43,
"learning_rate": 4.2846385542168675e-05,
"loss": 2.3473,
"step": 950
},
{
"epoch": 1.45,
"learning_rate": 4.27710843373494e-05,
"loss": 2.339,
"step": 960
},
{
"epoch": 1.46,
"learning_rate": 4.269578313253012e-05,
"loss": 2.3523,
"step": 970
},
{
"epoch": 1.48,
"learning_rate": 4.262048192771085e-05,
"loss": 2.3478,
"step": 980
},
{
"epoch": 1.49,
"learning_rate": 4.254518072289157e-05,
"loss": 2.3442,
"step": 990
},
{
"epoch": 1.51,
"learning_rate": 4.2469879518072294e-05,
"loss": 2.3359,
"step": 1000
},
{
"epoch": 1.52,
"learning_rate": 4.239457831325301e-05,
"loss": 2.3298,
"step": 1010
},
{
"epoch": 1.54,
"learning_rate": 4.231927710843373e-05,
"loss": 2.3438,
"step": 1020
},
{
"epoch": 1.55,
"learning_rate": 4.224397590361446e-05,
"loss": 2.3356,
"step": 1030
},
{
"epoch": 1.57,
"learning_rate": 4.2168674698795186e-05,
"loss": 2.3476,
"step": 1040
},
{
"epoch": 1.58,
"learning_rate": 4.2093373493975905e-05,
"loss": 2.3233,
"step": 1050
},
{
"epoch": 1.6,
"learning_rate": 4.201807228915663e-05,
"loss": 2.319,
"step": 1060
},
{
"epoch": 1.61,
"learning_rate": 4.194277108433735e-05,
"loss": 2.334,
"step": 1070
},
{
"epoch": 1.63,
"learning_rate": 4.186746987951807e-05,
"loss": 2.3372,
"step": 1080
},
{
"epoch": 1.64,
"learning_rate": 4.17921686746988e-05,
"loss": 2.3215,
"step": 1090
},
{
"epoch": 1.66,
"learning_rate": 4.1716867469879523e-05,
"loss": 2.3351,
"step": 1100
},
{
"epoch": 1.67,
"learning_rate": 4.164156626506024e-05,
"loss": 2.3215,
"step": 1110
},
{
"epoch": 1.69,
"learning_rate": 4.156626506024097e-05,
"loss": 2.3382,
"step": 1120
},
{
"epoch": 1.7,
"learning_rate": 4.149096385542169e-05,
"loss": 2.3395,
"step": 1130
},
{
"epoch": 1.72,
"learning_rate": 4.141566265060241e-05,
"loss": 2.331,
"step": 1140
},
{
"epoch": 1.73,
"learning_rate": 4.1340361445783135e-05,
"loss": 2.3181,
"step": 1150
},
{
"epoch": 1.75,
"learning_rate": 4.126506024096386e-05,
"loss": 2.3452,
"step": 1160
},
{
"epoch": 1.76,
"learning_rate": 4.118975903614458e-05,
"loss": 2.3292,
"step": 1170
},
{
"epoch": 1.78,
"learning_rate": 4.11144578313253e-05,
"loss": 2.3285,
"step": 1180
},
{
"epoch": 1.79,
"learning_rate": 4.103915662650603e-05,
"loss": 2.3236,
"step": 1190
},
{
"epoch": 1.81,
"learning_rate": 4.0963855421686746e-05,
"loss": 2.3347,
"step": 1200
},
{
"epoch": 1.82,
"learning_rate": 4.088855421686747e-05,
"loss": 2.3231,
"step": 1210
},
{
"epoch": 1.84,
"learning_rate": 4.08132530120482e-05,
"loss": 2.3289,
"step": 1220
},
{
"epoch": 1.85,
"learning_rate": 4.073795180722892e-05,
"loss": 2.3383,
"step": 1230
},
{
"epoch": 1.87,
"learning_rate": 4.066265060240964e-05,
"loss": 2.3344,
"step": 1240
},
{
"epoch": 1.88,
"learning_rate": 4.0587349397590365e-05,
"loss": 2.3504,
"step": 1250
},
{
"epoch": 1.9,
"learning_rate": 4.0512048192771084e-05,
"loss": 2.3235,
"step": 1260
},
{
"epoch": 1.91,
"learning_rate": 4.0436746987951804e-05,
"loss": 2.3281,
"step": 1270
},
{
"epoch": 1.93,
"learning_rate": 4.036144578313254e-05,
"loss": 2.3367,
"step": 1280
},
{
"epoch": 1.94,
"learning_rate": 4.028614457831326e-05,
"loss": 2.3364,
"step": 1290
},
{
"epoch": 1.96,
"learning_rate": 4.0210843373493976e-05,
"loss": 2.3225,
"step": 1300
},
{
"epoch": 1.97,
"learning_rate": 4.01355421686747e-05,
"loss": 2.3343,
"step": 1310
},
{
"epoch": 1.99,
"learning_rate": 4.006024096385542e-05,
"loss": 2.3489,
"step": 1320
},
{
"epoch": 2.0,
"eval_accuracy": 0.10493333333333334,
"eval_loss": 2.328753709793091,
"eval_runtime": 88.1948,
"eval_samples_per_second": 85.039,
"eval_steps_per_second": 5.318,
"step": 1328
},
{
"epoch": 2.0,
"learning_rate": 3.998493975903614e-05,
"loss": 2.3911,
"step": 1330
},
{
"epoch": 2.02,
"learning_rate": 3.9909638554216875e-05,
"loss": 2.336,
"step": 1340
},
{
"epoch": 2.03,
"learning_rate": 3.9834337349397595e-05,
"loss": 2.3294,
"step": 1350
},
{
"epoch": 2.05,
"learning_rate": 3.9759036144578314e-05,
"loss": 2.3399,
"step": 1360
},
{
"epoch": 2.06,
"learning_rate": 3.968373493975904e-05,
"loss": 2.3437,
"step": 1370
},
{
"epoch": 2.08,
"learning_rate": 3.960843373493976e-05,
"loss": 2.3291,
"step": 1380
},
{
"epoch": 2.09,
"learning_rate": 3.953313253012048e-05,
"loss": 2.3548,
"step": 1390
},
{
"epoch": 2.11,
"learning_rate": 3.9457831325301206e-05,
"loss": 2.317,
"step": 1400
},
{
"epoch": 2.12,
"learning_rate": 3.938253012048193e-05,
"loss": 2.3428,
"step": 1410
},
{
"epoch": 2.14,
"learning_rate": 3.930722891566265e-05,
"loss": 2.3414,
"step": 1420
},
{
"epoch": 2.15,
"learning_rate": 3.923192771084337e-05,
"loss": 2.3572,
"step": 1430
},
{
"epoch": 2.17,
"learning_rate": 3.91566265060241e-05,
"loss": 2.3479,
"step": 1440
},
{
"epoch": 2.18,
"learning_rate": 3.908132530120482e-05,
"loss": 2.3257,
"step": 1450
},
{
"epoch": 2.2,
"learning_rate": 3.9006024096385544e-05,
"loss": 2.324,
"step": 1460
},
{
"epoch": 2.21,
"learning_rate": 3.893072289156627e-05,
"loss": 2.3178,
"step": 1470
},
{
"epoch": 2.23,
"learning_rate": 3.885542168674699e-05,
"loss": 2.3505,
"step": 1480
},
{
"epoch": 2.24,
"learning_rate": 3.878012048192771e-05,
"loss": 2.3403,
"step": 1490
},
{
"epoch": 2.26,
"learning_rate": 3.8704819277108436e-05,
"loss": 2.3233,
"step": 1500
},
{
"epoch": 2.27,
"learning_rate": 3.8629518072289155e-05,
"loss": 2.3791,
"step": 1510
},
{
"epoch": 2.29,
"learning_rate": 3.855421686746988e-05,
"loss": 2.3549,
"step": 1520
},
{
"epoch": 2.3,
"learning_rate": 3.847891566265061e-05,
"loss": 2.3709,
"step": 1530
},
{
"epoch": 2.32,
"learning_rate": 3.840361445783133e-05,
"loss": 2.3481,
"step": 1540
},
{
"epoch": 2.33,
"learning_rate": 3.832831325301205e-05,
"loss": 2.3613,
"step": 1550
},
{
"epoch": 2.35,
"learning_rate": 3.8253012048192774e-05,
"loss": 2.3564,
"step": 1560
},
{
"epoch": 2.36,
"learning_rate": 3.817771084337349e-05,
"loss": 2.3781,
"step": 1570
},
{
"epoch": 2.38,
"learning_rate": 3.810240963855422e-05,
"loss": 2.3624,
"step": 1580
},
{
"epoch": 2.39,
"learning_rate": 3.802710843373494e-05,
"loss": 2.3582,
"step": 1590
},
{
"epoch": 2.41,
"learning_rate": 3.7951807228915666e-05,
"loss": 2.342,
"step": 1600
},
{
"epoch": 2.42,
"learning_rate": 3.7876506024096385e-05,
"loss": 2.3774,
"step": 1610
},
{
"epoch": 2.44,
"learning_rate": 3.780120481927711e-05,
"loss": 2.341,
"step": 1620
},
{
"epoch": 2.45,
"learning_rate": 3.772590361445783e-05,
"loss": 2.3589,
"step": 1630
},
{
"epoch": 2.47,
"learning_rate": 3.765060240963856e-05,
"loss": 2.334,
"step": 1640
},
{
"epoch": 2.48,
"learning_rate": 3.757530120481928e-05,
"loss": 2.3761,
"step": 1650
},
{
"epoch": 2.5,
"learning_rate": 3.7500000000000003e-05,
"loss": 2.3596,
"step": 1660
},
{
"epoch": 2.51,
"learning_rate": 3.742469879518072e-05,
"loss": 2.4082,
"step": 1670
},
{
"epoch": 2.53,
"learning_rate": 3.734939759036144e-05,
"loss": 2.3813,
"step": 1680
},
{
"epoch": 2.54,
"learning_rate": 3.7274096385542176e-05,
"loss": 2.3404,
"step": 1690
},
{
"epoch": 2.56,
"learning_rate": 3.7198795180722895e-05,
"loss": 2.3859,
"step": 1700
},
{
"epoch": 2.58,
"learning_rate": 3.7123493975903615e-05,
"loss": 2.4133,
"step": 1710
},
{
"epoch": 2.59,
"learning_rate": 3.704819277108434e-05,
"loss": 2.4011,
"step": 1720
},
{
"epoch": 2.61,
"learning_rate": 3.697289156626506e-05,
"loss": 2.4124,
"step": 1730
},
{
"epoch": 2.62,
"learning_rate": 3.689759036144578e-05,
"loss": 2.4081,
"step": 1740
},
{
"epoch": 2.64,
"learning_rate": 3.6822289156626514e-05,
"loss": 2.4022,
"step": 1750
},
{
"epoch": 2.65,
"learning_rate": 3.674698795180723e-05,
"loss": 2.4333,
"step": 1760
},
{
"epoch": 2.67,
"learning_rate": 3.667168674698795e-05,
"loss": 2.4422,
"step": 1770
},
{
"epoch": 2.68,
"learning_rate": 3.659638554216868e-05,
"loss": 2.4196,
"step": 1780
},
{
"epoch": 2.7,
"learning_rate": 3.65210843373494e-05,
"loss": 2.3988,
"step": 1790
},
{
"epoch": 2.71,
"learning_rate": 3.644578313253012e-05,
"loss": 2.4066,
"step": 1800
},
{
"epoch": 2.73,
"learning_rate": 3.6370481927710845e-05,
"loss": 2.3854,
"step": 1810
},
{
"epoch": 2.74,
"learning_rate": 3.629518072289157e-05,
"loss": 2.4092,
"step": 1820
},
{
"epoch": 2.76,
"learning_rate": 3.621987951807229e-05,
"loss": 2.4533,
"step": 1830
},
{
"epoch": 2.77,
"learning_rate": 3.614457831325301e-05,
"loss": 2.4181,
"step": 1840
},
{
"epoch": 2.79,
"learning_rate": 3.606927710843374e-05,
"loss": 2.4229,
"step": 1850
},
{
"epoch": 2.8,
"learning_rate": 3.5993975903614456e-05,
"loss": 2.4473,
"step": 1860
},
{
"epoch": 2.82,
"learning_rate": 3.591867469879518e-05,
"loss": 2.4258,
"step": 1870
},
{
"epoch": 2.83,
"learning_rate": 3.584337349397591e-05,
"loss": 2.4076,
"step": 1880
},
{
"epoch": 2.85,
"learning_rate": 3.576807228915663e-05,
"loss": 2.4527,
"step": 1890
},
{
"epoch": 2.86,
"learning_rate": 3.569277108433735e-05,
"loss": 2.4653,
"step": 1900
},
{
"epoch": 2.88,
"learning_rate": 3.5617469879518075e-05,
"loss": 2.4161,
"step": 1910
},
{
"epoch": 2.89,
"learning_rate": 3.5542168674698794e-05,
"loss": 2.4817,
"step": 1920
},
{
"epoch": 2.91,
"learning_rate": 3.546686746987952e-05,
"loss": 2.4586,
"step": 1930
},
{
"epoch": 2.92,
"learning_rate": 3.539156626506025e-05,
"loss": 2.4455,
"step": 1940
},
{
"epoch": 2.94,
"learning_rate": 3.5316265060240967e-05,
"loss": 2.4666,
"step": 1950
},
{
"epoch": 2.95,
"learning_rate": 3.5240963855421686e-05,
"loss": 2.4678,
"step": 1960
},
{
"epoch": 2.97,
"learning_rate": 3.516566265060241e-05,
"loss": 2.5005,
"step": 1970
},
{
"epoch": 2.98,
"learning_rate": 3.509036144578313e-05,
"loss": 2.4819,
"step": 1980
},
{
"epoch": 3.0,
"learning_rate": 3.501506024096386e-05,
"loss": 2.4899,
"step": 1990
},
{
"epoch": 3.0,
"eval_accuracy": 0.09893333333333333,
"eval_loss": 2.447309970855713,
"eval_runtime": 87.9258,
"eval_samples_per_second": 85.299,
"eval_steps_per_second": 5.334,
"step": 1992
},
{
"epoch": 3.01,
"learning_rate": 3.4939759036144585e-05,
"loss": 2.4848,
"step": 2000
},
{
"epoch": 3.03,
"learning_rate": 3.4864457831325304e-05,
"loss": 2.5148,
"step": 2010
},
{
"epoch": 3.04,
"learning_rate": 3.4789156626506024e-05,
"loss": 2.4835,
"step": 2020
},
{
"epoch": 3.06,
"learning_rate": 3.471385542168675e-05,
"loss": 2.5572,
"step": 2030
},
{
"epoch": 3.07,
"learning_rate": 3.463855421686747e-05,
"loss": 2.5478,
"step": 2040
},
{
"epoch": 3.09,
"learning_rate": 3.4563253012048196e-05,
"loss": 2.5037,
"step": 2050
},
{
"epoch": 3.1,
"learning_rate": 3.4487951807228916e-05,
"loss": 2.5438,
"step": 2060
},
{
"epoch": 3.12,
"learning_rate": 3.441265060240964e-05,
"loss": 2.5037,
"step": 2070
},
{
"epoch": 3.13,
"learning_rate": 3.433734939759036e-05,
"loss": 2.5474,
"step": 2080
},
{
"epoch": 3.15,
"learning_rate": 3.426204819277108e-05,
"loss": 2.5127,
"step": 2090
},
{
"epoch": 3.16,
"learning_rate": 3.418674698795181e-05,
"loss": 2.4961,
"step": 2100
},
{
"epoch": 3.18,
"learning_rate": 3.4111445783132534e-05,
"loss": 2.526,
"step": 2110
},
{
"epoch": 3.19,
"learning_rate": 3.4036144578313254e-05,
"loss": 2.5455,
"step": 2120
},
{
"epoch": 3.21,
"learning_rate": 3.396084337349398e-05,
"loss": 2.5263,
"step": 2130
},
{
"epoch": 3.22,
"learning_rate": 3.38855421686747e-05,
"loss": 2.4951,
"step": 2140
},
{
"epoch": 3.24,
"learning_rate": 3.381024096385542e-05,
"loss": 2.5009,
"step": 2150
},
{
"epoch": 3.25,
"learning_rate": 3.3734939759036146e-05,
"loss": 2.5164,
"step": 2160
},
{
"epoch": 3.27,
"learning_rate": 3.365963855421687e-05,
"loss": 2.5079,
"step": 2170
},
{
"epoch": 3.28,
"learning_rate": 3.358433734939759e-05,
"loss": 2.4612,
"step": 2180
},
{
"epoch": 3.3,
"learning_rate": 3.350903614457832e-05,
"loss": 2.4669,
"step": 2190
},
{
"epoch": 3.31,
"learning_rate": 3.343373493975904e-05,
"loss": 2.4784,
"step": 2200
},
{
"epoch": 3.33,
"learning_rate": 3.335843373493976e-05,
"loss": 2.4726,
"step": 2210
},
{
"epoch": 3.34,
"learning_rate": 3.3283132530120484e-05,
"loss": 2.5054,
"step": 2220
},
{
"epoch": 3.36,
"learning_rate": 3.320783132530121e-05,
"loss": 2.5058,
"step": 2230
},
{
"epoch": 3.37,
"learning_rate": 3.313253012048193e-05,
"loss": 2.4783,
"step": 2240
},
{
"epoch": 3.39,
"learning_rate": 3.305722891566265e-05,
"loss": 2.5145,
"step": 2250
},
{
"epoch": 3.4,
"learning_rate": 3.2981927710843376e-05,
"loss": 2.5295,
"step": 2260
},
{
"epoch": 3.42,
"learning_rate": 3.2906626506024095e-05,
"loss": 2.4965,
"step": 2270
},
{
"epoch": 3.43,
"learning_rate": 3.283132530120482e-05,
"loss": 2.4859,
"step": 2280
},
{
"epoch": 3.45,
"learning_rate": 3.275602409638555e-05,
"loss": 2.4612,
"step": 2290
},
{
"epoch": 3.46,
"learning_rate": 3.268072289156627e-05,
"loss": 2.5565,
"step": 2300
},
{
"epoch": 3.48,
"learning_rate": 3.260542168674699e-05,
"loss": 2.5422,
"step": 2310
},
{
"epoch": 3.49,
"learning_rate": 3.253012048192771e-05,
"loss": 2.5718,
"step": 2320
},
{
"epoch": 3.51,
"learning_rate": 3.245481927710843e-05,
"loss": 2.5312,
"step": 2330
},
{
"epoch": 3.52,
"learning_rate": 3.237951807228915e-05,
"loss": 2.541,
"step": 2340
},
{
"epoch": 3.54,
"learning_rate": 3.2304216867469886e-05,
"loss": 2.507,
"step": 2350
},
{
"epoch": 3.55,
"learning_rate": 3.2228915662650605e-05,
"loss": 2.52,
"step": 2360
},
{
"epoch": 3.57,
"learning_rate": 3.2153614457831325e-05,
"loss": 2.5591,
"step": 2370
},
{
"epoch": 3.58,
"learning_rate": 3.207831325301205e-05,
"loss": 2.5054,
"step": 2380
},
{
"epoch": 3.6,
"learning_rate": 3.200301204819277e-05,
"loss": 2.4614,
"step": 2390
},
{
"epoch": 3.61,
"learning_rate": 3.192771084337349e-05,
"loss": 2.5055,
"step": 2400
},
{
"epoch": 3.63,
"learning_rate": 3.1852409638554224e-05,
"loss": 2.5534,
"step": 2410
},
{
"epoch": 3.64,
"learning_rate": 3.177710843373494e-05,
"loss": 2.4795,
"step": 2420
},
{
"epoch": 3.66,
"learning_rate": 3.170180722891566e-05,
"loss": 2.4741,
"step": 2430
},
{
"epoch": 3.67,
"learning_rate": 3.162650602409639e-05,
"loss": 2.4908,
"step": 2440
},
{
"epoch": 3.69,
"learning_rate": 3.155120481927711e-05,
"loss": 2.4974,
"step": 2450
},
{
"epoch": 3.7,
"learning_rate": 3.147590361445783e-05,
"loss": 2.4895,
"step": 2460
},
{
"epoch": 3.72,
"learning_rate": 3.1400602409638555e-05,
"loss": 2.492,
"step": 2470
},
{
"epoch": 3.73,
"learning_rate": 3.132530120481928e-05,
"loss": 2.4952,
"step": 2480
},
{
"epoch": 3.75,
"learning_rate": 3.125e-05,
"loss": 2.4629,
"step": 2490
},
{
"epoch": 3.76,
"learning_rate": 3.117469879518072e-05,
"loss": 2.5128,
"step": 2500
},
{
"epoch": 3.78,
"learning_rate": 3.1099397590361447e-05,
"loss": 2.4906,
"step": 2510
},
{
"epoch": 3.79,
"learning_rate": 3.102409638554217e-05,
"loss": 2.5128,
"step": 2520
},
{
"epoch": 3.81,
"learning_rate": 3.094879518072289e-05,
"loss": 2.5232,
"step": 2530
},
{
"epoch": 3.82,
"learning_rate": 3.087349397590362e-05,
"loss": 2.497,
"step": 2540
},
{
"epoch": 3.84,
"learning_rate": 3.079819277108434e-05,
"loss": 2.4846,
"step": 2550
},
{
"epoch": 3.86,
"learning_rate": 3.072289156626506e-05,
"loss": 2.5096,
"step": 2560
},
{
"epoch": 3.87,
"learning_rate": 3.0647590361445784e-05,
"loss": 2.5142,
"step": 2570
},
{
"epoch": 3.89,
"learning_rate": 3.057228915662651e-05,
"loss": 2.485,
"step": 2580
},
{
"epoch": 3.9,
"learning_rate": 3.049698795180723e-05,
"loss": 2.5429,
"step": 2590
},
{
"epoch": 3.92,
"learning_rate": 3.0421686746987953e-05,
"loss": 2.4776,
"step": 2600
},
{
"epoch": 3.93,
"learning_rate": 3.0346385542168676e-05,
"loss": 2.5325,
"step": 2610
},
{
"epoch": 3.95,
"learning_rate": 3.02710843373494e-05,
"loss": 2.4744,
"step": 2620
},
{
"epoch": 3.96,
"learning_rate": 3.019578313253012e-05,
"loss": 2.5357,
"step": 2630
},
{
"epoch": 3.98,
"learning_rate": 3.012048192771085e-05,
"loss": 2.4785,
"step": 2640
},
{
"epoch": 3.99,
"learning_rate": 3.004518072289157e-05,
"loss": 2.479,
"step": 2650
},
{
"epoch": 4.0,
"eval_accuracy": 0.1,
"eval_loss": 2.4893734455108643,
"eval_runtime": 88.3349,
"eval_samples_per_second": 84.904,
"eval_steps_per_second": 5.309,
"step": 2656
},
{
"epoch": 4.01,
"learning_rate": 2.996987951807229e-05,
"loss": 2.5363,
"step": 2660
},
{
"epoch": 4.02,
"learning_rate": 2.9894578313253014e-05,
"loss": 2.4889,
"step": 2670
},
{
"epoch": 4.04,
"learning_rate": 2.9819277108433734e-05,
"loss": 2.4864,
"step": 2680
},
{
"epoch": 4.05,
"learning_rate": 2.9743975903614457e-05,
"loss": 2.4692,
"step": 2690
},
{
"epoch": 4.07,
"learning_rate": 2.9668674698795183e-05,
"loss": 2.517,
"step": 2700
},
{
"epoch": 4.08,
"learning_rate": 2.9593373493975906e-05,
"loss": 2.4686,
"step": 2710
},
{
"epoch": 4.1,
"learning_rate": 2.951807228915663e-05,
"loss": 2.5523,
"step": 2720
},
{
"epoch": 4.11,
"learning_rate": 2.9442771084337352e-05,
"loss": 2.4604,
"step": 2730
},
{
"epoch": 4.13,
"learning_rate": 2.9367469879518072e-05,
"loss": 2.481,
"step": 2740
},
{
"epoch": 4.14,
"learning_rate": 2.9292168674698795e-05,
"loss": 2.4952,
"step": 2750
},
{
"epoch": 4.16,
"learning_rate": 2.921686746987952e-05,
"loss": 2.4523,
"step": 2760
},
{
"epoch": 4.17,
"learning_rate": 2.9141566265060244e-05,
"loss": 2.4656,
"step": 2770
},
{
"epoch": 4.19,
"learning_rate": 2.9066265060240967e-05,
"loss": 2.5053,
"step": 2780
},
{
"epoch": 4.2,
"learning_rate": 2.8990963855421687e-05,
"loss": 2.4706,
"step": 2790
},
{
"epoch": 4.22,
"learning_rate": 2.891566265060241e-05,
"loss": 2.4952,
"step": 2800
},
{
"epoch": 4.23,
"learning_rate": 2.8840361445783133e-05,
"loss": 2.4745,
"step": 2810
},
{
"epoch": 4.25,
"learning_rate": 2.876506024096386e-05,
"loss": 2.4846,
"step": 2820
},
{
"epoch": 4.26,
"learning_rate": 2.8689759036144582e-05,
"loss": 2.4638,
"step": 2830
},
{
"epoch": 4.28,
"learning_rate": 2.86144578313253e-05,
"loss": 2.4963,
"step": 2840
},
{
"epoch": 4.29,
"learning_rate": 2.8539156626506025e-05,
"loss": 2.5034,
"step": 2850
},
{
"epoch": 4.31,
"learning_rate": 2.8463855421686748e-05,
"loss": 2.4673,
"step": 2860
},
{
"epoch": 4.32,
"learning_rate": 2.838855421686747e-05,
"loss": 2.4521,
"step": 2870
},
{
"epoch": 4.34,
"learning_rate": 2.8313253012048197e-05,
"loss": 2.5127,
"step": 2880
},
{
"epoch": 4.35,
"learning_rate": 2.823795180722892e-05,
"loss": 2.5123,
"step": 2890
},
{
"epoch": 4.37,
"learning_rate": 2.816265060240964e-05,
"loss": 2.4752,
"step": 2900
},
{
"epoch": 4.38,
"learning_rate": 2.8087349397590362e-05,
"loss": 2.5014,
"step": 2910
},
{
"epoch": 4.4,
"learning_rate": 2.8012048192771085e-05,
"loss": 2.5098,
"step": 2920
},
{
"epoch": 4.41,
"learning_rate": 2.7936746987951805e-05,
"loss": 2.4752,
"step": 2930
},
{
"epoch": 4.43,
"learning_rate": 2.7861445783132535e-05,
"loss": 2.4531,
"step": 2940
},
{
"epoch": 4.44,
"learning_rate": 2.7786144578313254e-05,
"loss": 2.4507,
"step": 2950
},
{
"epoch": 4.46,
"learning_rate": 2.7710843373493977e-05,
"loss": 2.4901,
"step": 2960
},
{
"epoch": 4.47,
"learning_rate": 2.76355421686747e-05,
"loss": 2.4274,
"step": 2970
},
{
"epoch": 4.49,
"learning_rate": 2.756024096385542e-05,
"loss": 2.4702,
"step": 2980
},
{
"epoch": 4.5,
"learning_rate": 2.7484939759036143e-05,
"loss": 2.4793,
"step": 2990
},
{
"epoch": 4.52,
"learning_rate": 2.7409638554216873e-05,
"loss": 2.5091,
"step": 3000
},
{
"epoch": 4.53,
"learning_rate": 2.7334337349397592e-05,
"loss": 2.4586,
"step": 3010
},
{
"epoch": 4.55,
"learning_rate": 2.7259036144578315e-05,
"loss": 2.4695,
"step": 3020
},
{
"epoch": 4.56,
"learning_rate": 2.7183734939759038e-05,
"loss": 2.4831,
"step": 3030
},
{
"epoch": 4.58,
"learning_rate": 2.7108433734939758e-05,
"loss": 2.4624,
"step": 3040
},
{
"epoch": 4.59,
"learning_rate": 2.703313253012048e-05,
"loss": 2.4333,
"step": 3050
},
{
"epoch": 4.61,
"learning_rate": 2.6957831325301207e-05,
"loss": 2.4513,
"step": 3060
},
{
"epoch": 4.62,
"learning_rate": 2.688253012048193e-05,
"loss": 2.436,
"step": 3070
},
{
"epoch": 4.64,
"learning_rate": 2.6807228915662653e-05,
"loss": 2.4721,
"step": 3080
},
{
"epoch": 4.65,
"learning_rate": 2.6731927710843373e-05,
"loss": 2.4648,
"step": 3090
},
{
"epoch": 4.67,
"learning_rate": 2.6656626506024096e-05,
"loss": 2.4092,
"step": 3100
},
{
"epoch": 4.68,
"learning_rate": 2.658132530120482e-05,
"loss": 2.4654,
"step": 3110
},
{
"epoch": 4.7,
"learning_rate": 2.6506024096385545e-05,
"loss": 2.4912,
"step": 3120
},
{
"epoch": 4.71,
"learning_rate": 2.6430722891566268e-05,
"loss": 2.4248,
"step": 3130
},
{
"epoch": 4.73,
"learning_rate": 2.635542168674699e-05,
"loss": 2.4756,
"step": 3140
},
{
"epoch": 4.74,
"learning_rate": 2.628012048192771e-05,
"loss": 2.4355,
"step": 3150
},
{
"epoch": 4.76,
"learning_rate": 2.6204819277108434e-05,
"loss": 2.4313,
"step": 3160
},
{
"epoch": 4.77,
"learning_rate": 2.6129518072289157e-05,
"loss": 2.458,
"step": 3170
},
{
"epoch": 4.79,
"learning_rate": 2.6054216867469883e-05,
"loss": 2.4521,
"step": 3180
},
{
"epoch": 4.8,
"learning_rate": 2.5978915662650606e-05,
"loss": 2.4578,
"step": 3190
},
{
"epoch": 4.82,
"learning_rate": 2.5903614457831325e-05,
"loss": 2.4403,
"step": 3200
},
{
"epoch": 4.83,
"learning_rate": 2.582831325301205e-05,
"loss": 2.4692,
"step": 3210
},
{
"epoch": 4.85,
"learning_rate": 2.575301204819277e-05,
"loss": 2.4578,
"step": 3220
},
{
"epoch": 4.86,
"learning_rate": 2.567771084337349e-05,
"loss": 2.4624,
"step": 3230
},
{
"epoch": 4.88,
"learning_rate": 2.560240963855422e-05,
"loss": 2.4869,
"step": 3240
},
{
"epoch": 4.89,
"learning_rate": 2.552710843373494e-05,
"loss": 2.4656,
"step": 3250
},
{
"epoch": 4.91,
"learning_rate": 2.5451807228915663e-05,
"loss": 2.4149,
"step": 3260
},
{
"epoch": 4.92,
"learning_rate": 2.5376506024096386e-05,
"loss": 2.452,
"step": 3270
},
{
"epoch": 4.94,
"learning_rate": 2.530120481927711e-05,
"loss": 2.4622,
"step": 3280
},
{
"epoch": 4.95,
"learning_rate": 2.522590361445783e-05,
"loss": 2.4479,
"step": 3290
},
{
"epoch": 4.97,
"learning_rate": 2.515060240963856e-05,
"loss": 2.4514,
"step": 3300
},
{
"epoch": 4.98,
"learning_rate": 2.5075301204819278e-05,
"loss": 2.4341,
"step": 3310
},
{
"epoch": 5.0,
"learning_rate": 2.5e-05,
"loss": 2.4179,
"step": 3320
},
{
"epoch": 5.0,
"eval_accuracy": 0.09466666666666666,
"eval_loss": 2.4404096603393555,
"eval_runtime": 89.296,
"eval_samples_per_second": 83.99,
"eval_steps_per_second": 5.252,
"step": 3320
},
{
"epoch": 5.02,
"learning_rate": 2.4924698795180724e-05,
"loss": 2.4961,
"step": 3330
},
{
"epoch": 5.03,
"learning_rate": 2.4849397590361447e-05,
"loss": 2.4329,
"step": 3340
},
{
"epoch": 5.05,
"learning_rate": 2.477409638554217e-05,
"loss": 2.4589,
"step": 3350
},
{
"epoch": 5.06,
"learning_rate": 2.4698795180722893e-05,
"loss": 2.4571,
"step": 3360
},
{
"epoch": 5.08,
"learning_rate": 2.4623493975903616e-05,
"loss": 2.4124,
"step": 3370
},
{
"epoch": 5.09,
"learning_rate": 2.454819277108434e-05,
"loss": 2.4009,
"step": 3380
},
{
"epoch": 5.11,
"learning_rate": 2.4472891566265062e-05,
"loss": 2.4346,
"step": 3390
},
{
"epoch": 5.12,
"learning_rate": 2.4397590361445785e-05,
"loss": 2.4584,
"step": 3400
},
{
"epoch": 5.14,
"learning_rate": 2.4322289156626508e-05,
"loss": 2.4309,
"step": 3410
},
{
"epoch": 5.15,
"learning_rate": 2.4246987951807228e-05,
"loss": 2.4128,
"step": 3420
},
{
"epoch": 5.17,
"learning_rate": 2.4171686746987954e-05,
"loss": 2.4343,
"step": 3430
},
{
"epoch": 5.18,
"learning_rate": 2.4096385542168677e-05,
"loss": 2.4824,
"step": 3440
},
{
"epoch": 5.2,
"learning_rate": 2.4021084337349397e-05,
"loss": 2.4489,
"step": 3450
},
{
"epoch": 5.21,
"learning_rate": 2.3945783132530123e-05,
"loss": 2.4503,
"step": 3460
},
{
"epoch": 5.23,
"learning_rate": 2.3870481927710846e-05,
"loss": 2.4152,
"step": 3470
},
{
"epoch": 5.24,
"learning_rate": 2.3795180722891565e-05,
"loss": 2.4467,
"step": 3480
},
{
"epoch": 5.26,
"learning_rate": 2.3719879518072292e-05,
"loss": 2.4164,
"step": 3490
},
{
"epoch": 5.27,
"learning_rate": 2.364457831325301e-05,
"loss": 2.4403,
"step": 3500
},
{
"epoch": 5.29,
"learning_rate": 2.3569277108433734e-05,
"loss": 2.4458,
"step": 3510
},
{
"epoch": 5.3,
"learning_rate": 2.349397590361446e-05,
"loss": 2.4409,
"step": 3520
},
{
"epoch": 5.32,
"learning_rate": 2.341867469879518e-05,
"loss": 2.3775,
"step": 3530
},
{
"epoch": 5.33,
"learning_rate": 2.3343373493975903e-05,
"loss": 2.4205,
"step": 3540
},
{
"epoch": 5.35,
"learning_rate": 2.326807228915663e-05,
"loss": 2.4296,
"step": 3550
},
{
"epoch": 5.36,
"learning_rate": 2.319277108433735e-05,
"loss": 2.4372,
"step": 3560
},
{
"epoch": 5.38,
"learning_rate": 2.3117469879518072e-05,
"loss": 2.4454,
"step": 3570
},
{
"epoch": 5.39,
"learning_rate": 2.3042168674698795e-05,
"loss": 2.4135,
"step": 3580
},
{
"epoch": 5.41,
"learning_rate": 2.2966867469879518e-05,
"loss": 2.4442,
"step": 3590
},
{
"epoch": 5.42,
"learning_rate": 2.289156626506024e-05,
"loss": 2.3982,
"step": 3600
},
{
"epoch": 5.44,
"learning_rate": 2.2816265060240964e-05,
"loss": 2.4006,
"step": 3610
},
{
"epoch": 5.45,
"learning_rate": 2.2740963855421687e-05,
"loss": 2.4232,
"step": 3620
},
{
"epoch": 5.47,
"learning_rate": 2.266566265060241e-05,
"loss": 2.4277,
"step": 3630
},
{
"epoch": 5.48,
"learning_rate": 2.2590361445783133e-05,
"loss": 2.4212,
"step": 3640
},
{
"epoch": 5.5,
"learning_rate": 2.2515060240963856e-05,
"loss": 2.429,
"step": 3650
},
{
"epoch": 5.51,
"learning_rate": 2.243975903614458e-05,
"loss": 2.4011,
"step": 3660
},
{
"epoch": 5.53,
"learning_rate": 2.2364457831325302e-05,
"loss": 2.3976,
"step": 3670
},
{
"epoch": 5.54,
"learning_rate": 2.2289156626506025e-05,
"loss": 2.4228,
"step": 3680
},
{
"epoch": 5.56,
"learning_rate": 2.2213855421686748e-05,
"loss": 2.4326,
"step": 3690
},
{
"epoch": 5.57,
"learning_rate": 2.213855421686747e-05,
"loss": 2.4325,
"step": 3700
},
{
"epoch": 5.59,
"learning_rate": 2.2063253012048194e-05,
"loss": 2.3598,
"step": 3710
},
{
"epoch": 5.6,
"learning_rate": 2.1987951807228917e-05,
"loss": 2.4177,
"step": 3720
},
{
"epoch": 5.62,
"learning_rate": 2.191265060240964e-05,
"loss": 2.3965,
"step": 3730
},
{
"epoch": 5.63,
"learning_rate": 2.1837349397590363e-05,
"loss": 2.4322,
"step": 3740
},
{
"epoch": 5.65,
"learning_rate": 2.1762048192771086e-05,
"loss": 2.4419,
"step": 3750
},
{
"epoch": 5.66,
"learning_rate": 2.168674698795181e-05,
"loss": 2.3857,
"step": 3760
},
{
"epoch": 5.68,
"learning_rate": 2.1611445783132532e-05,
"loss": 2.3885,
"step": 3770
},
{
"epoch": 5.69,
"learning_rate": 2.1536144578313255e-05,
"loss": 2.3996,
"step": 3780
},
{
"epoch": 5.71,
"learning_rate": 2.1460843373493978e-05,
"loss": 2.4086,
"step": 3790
},
{
"epoch": 5.72,
"learning_rate": 2.13855421686747e-05,
"loss": 2.4339,
"step": 3800
},
{
"epoch": 5.74,
"learning_rate": 2.1310240963855424e-05,
"loss": 2.4346,
"step": 3810
},
{
"epoch": 5.75,
"learning_rate": 2.1234939759036147e-05,
"loss": 2.4393,
"step": 3820
},
{
"epoch": 5.77,
"learning_rate": 2.1159638554216866e-05,
"loss": 2.4097,
"step": 3830
},
{
"epoch": 5.78,
"learning_rate": 2.1084337349397593e-05,
"loss": 2.4278,
"step": 3840
},
{
"epoch": 5.8,
"learning_rate": 2.1009036144578316e-05,
"loss": 2.4109,
"step": 3850
},
{
"epoch": 5.81,
"learning_rate": 2.0933734939759035e-05,
"loss": 2.4208,
"step": 3860
},
{
"epoch": 5.83,
"learning_rate": 2.0858433734939762e-05,
"loss": 2.4159,
"step": 3870
},
{
"epoch": 5.84,
"learning_rate": 2.0783132530120485e-05,
"loss": 2.4191,
"step": 3880
},
{
"epoch": 5.86,
"learning_rate": 2.0707831325301204e-05,
"loss": 2.3934,
"step": 3890
},
{
"epoch": 5.87,
"learning_rate": 2.063253012048193e-05,
"loss": 2.4151,
"step": 3900
},
{
"epoch": 5.89,
"learning_rate": 2.055722891566265e-05,
"loss": 2.4172,
"step": 3910
},
{
"epoch": 5.9,
"learning_rate": 2.0481927710843373e-05,
"loss": 2.4317,
"step": 3920
},
{
"epoch": 5.92,
"learning_rate": 2.04066265060241e-05,
"loss": 2.3632,
"step": 3930
},
{
"epoch": 5.93,
"learning_rate": 2.033132530120482e-05,
"loss": 2.3705,
"step": 3940
},
{
"epoch": 5.95,
"learning_rate": 2.0256024096385542e-05,
"loss": 2.4036,
"step": 3950
},
{
"epoch": 5.96,
"learning_rate": 2.018072289156627e-05,
"loss": 2.3888,
"step": 3960
},
{
"epoch": 5.98,
"learning_rate": 2.0105421686746988e-05,
"loss": 2.4079,
"step": 3970
},
{
"epoch": 5.99,
"learning_rate": 2.003012048192771e-05,
"loss": 2.3881,
"step": 3980
},
{
"epoch": 6.0,
"eval_accuracy": 0.102,
"eval_loss": 2.3931188583374023,
"eval_runtime": 89.7706,
"eval_samples_per_second": 83.546,
"eval_steps_per_second": 5.224,
"step": 3984
},
{
"epoch": 6.01,
"learning_rate": 1.9954819277108437e-05,
"loss": 2.4873,
"step": 3990
},
{
"epoch": 6.02,
"learning_rate": 1.9879518072289157e-05,
"loss": 2.385,
"step": 4000
},
{
"epoch": 6.04,
"learning_rate": 1.980421686746988e-05,
"loss": 2.3956,
"step": 4010
},
{
"epoch": 6.05,
"learning_rate": 1.9728915662650603e-05,
"loss": 2.3882,
"step": 4020
},
{
"epoch": 6.07,
"learning_rate": 1.9653614457831326e-05,
"loss": 2.4048,
"step": 4030
},
{
"epoch": 6.08,
"learning_rate": 1.957831325301205e-05,
"loss": 2.3765,
"step": 4040
},
{
"epoch": 6.1,
"learning_rate": 1.9503012048192772e-05,
"loss": 2.3934,
"step": 4050
},
{
"epoch": 6.11,
"learning_rate": 1.9427710843373495e-05,
"loss": 2.3784,
"step": 4060
},
{
"epoch": 6.13,
"learning_rate": 1.9352409638554218e-05,
"loss": 2.3991,
"step": 4070
},
{
"epoch": 6.14,
"learning_rate": 1.927710843373494e-05,
"loss": 2.4025,
"step": 4080
},
{
"epoch": 6.16,
"learning_rate": 1.9201807228915664e-05,
"loss": 2.4011,
"step": 4090
},
{
"epoch": 6.17,
"learning_rate": 1.9126506024096387e-05,
"loss": 2.3931,
"step": 4100
},
{
"epoch": 6.19,
"learning_rate": 1.905120481927711e-05,
"loss": 2.4194,
"step": 4110
},
{
"epoch": 6.2,
"learning_rate": 1.8975903614457833e-05,
"loss": 2.3913,
"step": 4120
},
{
"epoch": 6.22,
"learning_rate": 1.8900602409638556e-05,
"loss": 2.3892,
"step": 4130
},
{
"epoch": 6.23,
"learning_rate": 1.882530120481928e-05,
"loss": 2.4361,
"step": 4140
},
{
"epoch": 6.25,
"learning_rate": 1.8750000000000002e-05,
"loss": 2.3755,
"step": 4150
},
{
"epoch": 6.26,
"learning_rate": 1.867469879518072e-05,
"loss": 2.4297,
"step": 4160
},
{
"epoch": 6.28,
"learning_rate": 1.8599397590361448e-05,
"loss": 2.3606,
"step": 4170
},
{
"epoch": 6.3,
"learning_rate": 1.852409638554217e-05,
"loss": 2.3626,
"step": 4180
},
{
"epoch": 6.31,
"learning_rate": 1.844879518072289e-05,
"loss": 2.3632,
"step": 4190
},
{
"epoch": 6.33,
"learning_rate": 1.8373493975903617e-05,
"loss": 2.381,
"step": 4200
},
{
"epoch": 6.34,
"learning_rate": 1.829819277108434e-05,
"loss": 2.4075,
"step": 4210
},
{
"epoch": 6.36,
"learning_rate": 1.822289156626506e-05,
"loss": 2.4029,
"step": 4220
},
{
"epoch": 6.37,
"learning_rate": 1.8147590361445786e-05,
"loss": 2.3773,
"step": 4230
},
{
"epoch": 6.39,
"learning_rate": 1.8072289156626505e-05,
"loss": 2.3792,
"step": 4240
},
{
"epoch": 6.4,
"learning_rate": 1.7996987951807228e-05,
"loss": 2.3947,
"step": 4250
},
{
"epoch": 6.42,
"learning_rate": 1.7921686746987955e-05,
"loss": 2.3803,
"step": 4260
},
{
"epoch": 6.43,
"learning_rate": 1.7846385542168674e-05,
"loss": 2.3772,
"step": 4270
},
{
"epoch": 6.45,
"learning_rate": 1.7771084337349397e-05,
"loss": 2.403,
"step": 4280
},
{
"epoch": 6.46,
"learning_rate": 1.7695783132530123e-05,
"loss": 2.3912,
"step": 4290
},
{
"epoch": 6.48,
"learning_rate": 1.7620481927710843e-05,
"loss": 2.4002,
"step": 4300
},
{
"epoch": 6.49,
"learning_rate": 1.7545180722891566e-05,
"loss": 2.3728,
"step": 4310
},
{
"epoch": 6.51,
"learning_rate": 1.7469879518072292e-05,
"loss": 2.3921,
"step": 4320
},
{
"epoch": 6.52,
"learning_rate": 1.7394578313253012e-05,
"loss": 2.404,
"step": 4330
},
{
"epoch": 6.54,
"learning_rate": 1.7319277108433735e-05,
"loss": 2.4003,
"step": 4340
},
{
"epoch": 6.55,
"learning_rate": 1.7243975903614458e-05,
"loss": 2.381,
"step": 4350
},
{
"epoch": 6.57,
"learning_rate": 1.716867469879518e-05,
"loss": 2.4061,
"step": 4360
},
{
"epoch": 6.58,
"learning_rate": 1.7093373493975904e-05,
"loss": 2.3938,
"step": 4370
},
{
"epoch": 6.6,
"learning_rate": 1.7018072289156627e-05,
"loss": 2.3488,
"step": 4380
},
{
"epoch": 6.61,
"learning_rate": 1.694277108433735e-05,
"loss": 2.374,
"step": 4390
},
{
"epoch": 6.63,
"learning_rate": 1.6867469879518073e-05,
"loss": 2.4029,
"step": 4400
},
{
"epoch": 6.64,
"learning_rate": 1.6792168674698796e-05,
"loss": 2.3884,
"step": 4410
},
{
"epoch": 6.66,
"learning_rate": 1.671686746987952e-05,
"loss": 2.3727,
"step": 4420
},
{
"epoch": 6.67,
"learning_rate": 1.6641566265060242e-05,
"loss": 2.3766,
"step": 4430
},
{
"epoch": 6.69,
"learning_rate": 1.6566265060240965e-05,
"loss": 2.3937,
"step": 4440
},
{
"epoch": 6.7,
"learning_rate": 1.6490963855421688e-05,
"loss": 2.3661,
"step": 4450
},
{
"epoch": 6.72,
"learning_rate": 1.641566265060241e-05,
"loss": 2.3744,
"step": 4460
},
{
"epoch": 6.73,
"learning_rate": 1.6340361445783134e-05,
"loss": 2.3885,
"step": 4470
},
{
"epoch": 6.75,
"learning_rate": 1.6265060240963857e-05,
"loss": 2.3679,
"step": 4480
},
{
"epoch": 6.76,
"learning_rate": 1.6189759036144576e-05,
"loss": 2.398,
"step": 4490
},
{
"epoch": 6.78,
"learning_rate": 1.6114457831325303e-05,
"loss": 2.3671,
"step": 4500
},
{
"epoch": 6.79,
"learning_rate": 1.6039156626506026e-05,
"loss": 2.3837,
"step": 4510
},
{
"epoch": 6.81,
"learning_rate": 1.5963855421686745e-05,
"loss": 2.3591,
"step": 4520
},
{
"epoch": 6.82,
"learning_rate": 1.588855421686747e-05,
"loss": 2.3798,
"step": 4530
},
{
"epoch": 6.84,
"learning_rate": 1.5813253012048195e-05,
"loss": 2.3887,
"step": 4540
},
{
"epoch": 6.85,
"learning_rate": 1.5737951807228914e-05,
"loss": 2.3971,
"step": 4550
},
{
"epoch": 6.87,
"learning_rate": 1.566265060240964e-05,
"loss": 2.3582,
"step": 4560
},
{
"epoch": 6.88,
"learning_rate": 1.558734939759036e-05,
"loss": 2.3698,
"step": 4570
},
{
"epoch": 6.9,
"learning_rate": 1.5512048192771086e-05,
"loss": 2.3878,
"step": 4580
},
{
"epoch": 6.91,
"learning_rate": 1.543674698795181e-05,
"loss": 2.3941,
"step": 4590
},
{
"epoch": 6.93,
"learning_rate": 1.536144578313253e-05,
"loss": 2.3655,
"step": 4600
},
{
"epoch": 6.94,
"learning_rate": 1.5286144578313255e-05,
"loss": 2.3902,
"step": 4610
},
{
"epoch": 6.96,
"learning_rate": 1.5210843373493977e-05,
"loss": 2.3656,
"step": 4620
},
{
"epoch": 6.97,
"learning_rate": 1.51355421686747e-05,
"loss": 2.372,
"step": 4630
},
{
"epoch": 6.99,
"learning_rate": 1.5060240963855424e-05,
"loss": 2.3597,
"step": 4640
},
{
"epoch": 7.0,
"eval_accuracy": 0.09666666666666666,
"eval_loss": 2.3744025230407715,
"eval_runtime": 88.5662,
"eval_samples_per_second": 84.682,
"eval_steps_per_second": 5.295,
"step": 4648
},
{
"epoch": 7.0,
"learning_rate": 1.4984939759036146e-05,
"loss": 2.4019,
"step": 4650
},
{
"epoch": 7.02,
"learning_rate": 1.4909638554216867e-05,
"loss": 2.3753,
"step": 4660
},
{
"epoch": 7.03,
"learning_rate": 1.4834337349397592e-05,
"loss": 2.3541,
"step": 4670
},
{
"epoch": 7.05,
"learning_rate": 1.4759036144578315e-05,
"loss": 2.3742,
"step": 4680
},
{
"epoch": 7.06,
"learning_rate": 1.4683734939759036e-05,
"loss": 2.3839,
"step": 4690
},
{
"epoch": 7.08,
"learning_rate": 1.460843373493976e-05,
"loss": 2.3662,
"step": 4700
},
{
"epoch": 7.09,
"learning_rate": 1.4533132530120484e-05,
"loss": 2.3624,
"step": 4710
},
{
"epoch": 7.11,
"learning_rate": 1.4457831325301205e-05,
"loss": 2.396,
"step": 4720
},
{
"epoch": 7.12,
"learning_rate": 1.438253012048193e-05,
"loss": 2.3903,
"step": 4730
},
{
"epoch": 7.14,
"learning_rate": 1.430722891566265e-05,
"loss": 2.362,
"step": 4740
},
{
"epoch": 7.15,
"learning_rate": 1.4231927710843374e-05,
"loss": 2.3778,
"step": 4750
},
{
"epoch": 7.17,
"learning_rate": 1.4156626506024098e-05,
"loss": 2.3875,
"step": 4760
},
{
"epoch": 7.18,
"learning_rate": 1.408132530120482e-05,
"loss": 2.3775,
"step": 4770
},
{
"epoch": 7.2,
"learning_rate": 1.4006024096385543e-05,
"loss": 2.3776,
"step": 4780
},
{
"epoch": 7.21,
"learning_rate": 1.3930722891566267e-05,
"loss": 2.3979,
"step": 4790
},
{
"epoch": 7.23,
"learning_rate": 1.3855421686746989e-05,
"loss": 2.3477,
"step": 4800
},
{
"epoch": 7.24,
"learning_rate": 1.378012048192771e-05,
"loss": 2.3558,
"step": 4810
},
{
"epoch": 7.26,
"learning_rate": 1.3704819277108436e-05,
"loss": 2.4065,
"step": 4820
},
{
"epoch": 7.27,
"learning_rate": 1.3629518072289158e-05,
"loss": 2.3601,
"step": 4830
},
{
"epoch": 7.29,
"learning_rate": 1.3554216867469879e-05,
"loss": 2.362,
"step": 4840
},
{
"epoch": 7.3,
"learning_rate": 1.3478915662650604e-05,
"loss": 2.3862,
"step": 4850
},
{
"epoch": 7.32,
"learning_rate": 1.3403614457831327e-05,
"loss": 2.3734,
"step": 4860
},
{
"epoch": 7.33,
"learning_rate": 1.3328313253012048e-05,
"loss": 2.3674,
"step": 4870
},
{
"epoch": 7.35,
"learning_rate": 1.3253012048192772e-05,
"loss": 2.3781,
"step": 4880
},
{
"epoch": 7.36,
"learning_rate": 1.3177710843373495e-05,
"loss": 2.3554,
"step": 4890
},
{
"epoch": 7.38,
"learning_rate": 1.3102409638554217e-05,
"loss": 2.3918,
"step": 4900
},
{
"epoch": 7.39,
"learning_rate": 1.3027108433734941e-05,
"loss": 2.34,
"step": 4910
},
{
"epoch": 7.41,
"learning_rate": 1.2951807228915663e-05,
"loss": 2.3702,
"step": 4920
},
{
"epoch": 7.42,
"learning_rate": 1.2876506024096386e-05,
"loss": 2.3564,
"step": 4930
},
{
"epoch": 7.44,
"learning_rate": 1.280120481927711e-05,
"loss": 2.3614,
"step": 4940
},
{
"epoch": 7.45,
"learning_rate": 1.2725903614457832e-05,
"loss": 2.3495,
"step": 4950
},
{
"epoch": 7.47,
"learning_rate": 1.2650602409638555e-05,
"loss": 2.3732,
"step": 4960
},
{
"epoch": 7.48,
"learning_rate": 1.257530120481928e-05,
"loss": 2.3572,
"step": 4970
},
{
"epoch": 7.5,
"learning_rate": 1.25e-05,
"loss": 2.3752,
"step": 4980
},
{
"epoch": 7.51,
"learning_rate": 1.2424698795180724e-05,
"loss": 2.3437,
"step": 4990
},
{
"epoch": 7.53,
"learning_rate": 1.2349397590361447e-05,
"loss": 2.3856,
"step": 5000
},
{
"epoch": 7.54,
"learning_rate": 1.227409638554217e-05,
"loss": 2.3955,
"step": 5010
},
{
"epoch": 7.56,
"learning_rate": 1.2198795180722893e-05,
"loss": 2.4012,
"step": 5020
},
{
"epoch": 7.58,
"learning_rate": 1.2123493975903614e-05,
"loss": 2.3732,
"step": 5030
},
{
"epoch": 7.59,
"learning_rate": 1.2048192771084338e-05,
"loss": 2.3588,
"step": 5040
},
{
"epoch": 7.61,
"learning_rate": 1.1972891566265061e-05,
"loss": 2.3589,
"step": 5050
},
{
"epoch": 7.62,
"learning_rate": 1.1897590361445783e-05,
"loss": 2.368,
"step": 5060
},
{
"epoch": 7.64,
"learning_rate": 1.1822289156626506e-05,
"loss": 2.3614,
"step": 5070
},
{
"epoch": 7.65,
"learning_rate": 1.174698795180723e-05,
"loss": 2.3616,
"step": 5080
},
{
"epoch": 7.67,
"learning_rate": 1.1671686746987952e-05,
"loss": 2.3572,
"step": 5090
},
{
"epoch": 7.68,
"learning_rate": 1.1596385542168675e-05,
"loss": 2.3828,
"step": 5100
},
{
"epoch": 7.7,
"learning_rate": 1.1521084337349398e-05,
"loss": 2.3688,
"step": 5110
},
{
"epoch": 7.71,
"learning_rate": 1.144578313253012e-05,
"loss": 2.3892,
"step": 5120
},
{
"epoch": 7.73,
"learning_rate": 1.1370481927710844e-05,
"loss": 2.3528,
"step": 5130
},
{
"epoch": 7.74,
"learning_rate": 1.1295180722891567e-05,
"loss": 2.3768,
"step": 5140
},
{
"epoch": 7.76,
"learning_rate": 1.121987951807229e-05,
"loss": 2.3506,
"step": 5150
},
{
"epoch": 7.77,
"learning_rate": 1.1144578313253013e-05,
"loss": 2.3728,
"step": 5160
},
{
"epoch": 7.79,
"learning_rate": 1.1069277108433736e-05,
"loss": 2.3518,
"step": 5170
},
{
"epoch": 7.8,
"learning_rate": 1.0993975903614459e-05,
"loss": 2.3489,
"step": 5180
},
{
"epoch": 7.82,
"learning_rate": 1.0918674698795181e-05,
"loss": 2.3682,
"step": 5190
},
{
"epoch": 7.83,
"learning_rate": 1.0843373493975904e-05,
"loss": 2.3764,
"step": 5200
},
{
"epoch": 7.85,
"learning_rate": 1.0768072289156627e-05,
"loss": 2.3499,
"step": 5210
},
{
"epoch": 7.86,
"learning_rate": 1.069277108433735e-05,
"loss": 2.3569,
"step": 5220
},
{
"epoch": 7.88,
"learning_rate": 1.0617469879518073e-05,
"loss": 2.3602,
"step": 5230
},
{
"epoch": 7.89,
"learning_rate": 1.0542168674698796e-05,
"loss": 2.3609,
"step": 5240
},
{
"epoch": 7.91,
"learning_rate": 1.0466867469879518e-05,
"loss": 2.3573,
"step": 5250
},
{
"epoch": 7.92,
"learning_rate": 1.0391566265060242e-05,
"loss": 2.3624,
"step": 5260
},
{
"epoch": 7.94,
"learning_rate": 1.0316265060240965e-05,
"loss": 2.3676,
"step": 5270
},
{
"epoch": 7.95,
"learning_rate": 1.0240963855421687e-05,
"loss": 2.3665,
"step": 5280
},
{
"epoch": 7.97,
"learning_rate": 1.016566265060241e-05,
"loss": 2.3585,
"step": 5290
},
{
"epoch": 7.98,
"learning_rate": 1.0090361445783134e-05,
"loss": 2.3498,
"step": 5300
},
{
"epoch": 8.0,
"learning_rate": 1.0015060240963856e-05,
"loss": 2.3721,
"step": 5310
},
{
"epoch": 8.0,
"eval_accuracy": 0.09346666666666667,
"eval_loss": 2.366736888885498,
"eval_runtime": 88.9858,
"eval_samples_per_second": 84.283,
"eval_steps_per_second": 5.271,
"step": 5312
},
{
"epoch": 8.01,
"learning_rate": 9.939759036144579e-06,
"loss": 2.4001,
"step": 5320
},
{
"epoch": 8.03,
"learning_rate": 9.864457831325302e-06,
"loss": 2.3524,
"step": 5330
},
{
"epoch": 8.04,
"learning_rate": 9.789156626506024e-06,
"loss": 2.3508,
"step": 5340
},
{
"epoch": 8.06,
"learning_rate": 9.713855421686747e-06,
"loss": 2.3609,
"step": 5350
},
{
"epoch": 8.07,
"learning_rate": 9.63855421686747e-06,
"loss": 2.3533,
"step": 5360
},
{
"epoch": 8.09,
"learning_rate": 9.563253012048193e-06,
"loss": 2.3546,
"step": 5370
},
{
"epoch": 8.1,
"learning_rate": 9.487951807228916e-06,
"loss": 2.3648,
"step": 5380
},
{
"epoch": 8.12,
"learning_rate": 9.41265060240964e-06,
"loss": 2.3627,
"step": 5390
},
{
"epoch": 8.13,
"learning_rate": 9.33734939759036e-06,
"loss": 2.3538,
"step": 5400
},
{
"epoch": 8.15,
"learning_rate": 9.262048192771085e-06,
"loss": 2.3581,
"step": 5410
},
{
"epoch": 8.16,
"learning_rate": 9.186746987951808e-06,
"loss": 2.3473,
"step": 5420
},
{
"epoch": 8.18,
"learning_rate": 9.11144578313253e-06,
"loss": 2.3438,
"step": 5430
},
{
"epoch": 8.19,
"learning_rate": 9.036144578313253e-06,
"loss": 2.3473,
"step": 5440
},
{
"epoch": 8.21,
"learning_rate": 8.960843373493977e-06,
"loss": 2.3603,
"step": 5450
},
{
"epoch": 8.22,
"learning_rate": 8.885542168674699e-06,
"loss": 2.3731,
"step": 5460
},
{
"epoch": 8.24,
"learning_rate": 8.810240963855422e-06,
"loss": 2.3714,
"step": 5470
},
{
"epoch": 8.25,
"learning_rate": 8.734939759036146e-06,
"loss": 2.3507,
"step": 5480
},
{
"epoch": 8.27,
"learning_rate": 8.659638554216867e-06,
"loss": 2.3747,
"step": 5490
},
{
"epoch": 8.28,
"learning_rate": 8.58433734939759e-06,
"loss": 2.3499,
"step": 5500
},
{
"epoch": 8.3,
"learning_rate": 8.509036144578313e-06,
"loss": 2.3481,
"step": 5510
},
{
"epoch": 8.31,
"learning_rate": 8.433734939759036e-06,
"loss": 2.3652,
"step": 5520
},
{
"epoch": 8.33,
"learning_rate": 8.35843373493976e-06,
"loss": 2.3737,
"step": 5530
},
{
"epoch": 8.34,
"learning_rate": 8.283132530120482e-06,
"loss": 2.3401,
"step": 5540
},
{
"epoch": 8.36,
"learning_rate": 8.207831325301205e-06,
"loss": 2.3348,
"step": 5550
},
{
"epoch": 8.37,
"learning_rate": 8.132530120481928e-06,
"loss": 2.3438,
"step": 5560
},
{
"epoch": 8.39,
"learning_rate": 8.057228915662651e-06,
"loss": 2.3618,
"step": 5570
},
{
"epoch": 8.4,
"learning_rate": 7.981927710843373e-06,
"loss": 2.3633,
"step": 5580
},
{
"epoch": 8.42,
"learning_rate": 7.906626506024097e-06,
"loss": 2.3791,
"step": 5590
},
{
"epoch": 8.43,
"learning_rate": 7.83132530120482e-06,
"loss": 2.3659,
"step": 5600
},
{
"epoch": 8.45,
"learning_rate": 7.756024096385543e-06,
"loss": 2.3663,
"step": 5610
},
{
"epoch": 8.46,
"learning_rate": 7.680722891566265e-06,
"loss": 2.3675,
"step": 5620
},
{
"epoch": 8.48,
"learning_rate": 7.605421686746988e-06,
"loss": 2.357,
"step": 5630
},
{
"epoch": 8.49,
"learning_rate": 7.530120481927712e-06,
"loss": 2.3479,
"step": 5640
},
{
"epoch": 8.51,
"learning_rate": 7.4548192771084335e-06,
"loss": 2.3548,
"step": 5650
},
{
"epoch": 8.52,
"learning_rate": 7.379518072289157e-06,
"loss": 2.363,
"step": 5660
},
{
"epoch": 8.54,
"learning_rate": 7.30421686746988e-06,
"loss": 2.37,
"step": 5670
},
{
"epoch": 8.55,
"learning_rate": 7.228915662650602e-06,
"loss": 2.3748,
"step": 5680
},
{
"epoch": 8.57,
"learning_rate": 7.153614457831325e-06,
"loss": 2.3464,
"step": 5690
},
{
"epoch": 8.58,
"learning_rate": 7.078313253012049e-06,
"loss": 2.3478,
"step": 5700
},
{
"epoch": 8.6,
"learning_rate": 7.003012048192771e-06,
"loss": 2.3466,
"step": 5710
},
{
"epoch": 8.61,
"learning_rate": 6.927710843373494e-06,
"loss": 2.3452,
"step": 5720
},
{
"epoch": 8.63,
"learning_rate": 6.852409638554218e-06,
"loss": 2.3445,
"step": 5730
},
{
"epoch": 8.64,
"learning_rate": 6.7771084337349394e-06,
"loss": 2.3432,
"step": 5740
},
{
"epoch": 8.66,
"learning_rate": 6.701807228915663e-06,
"loss": 2.3437,
"step": 5750
},
{
"epoch": 8.67,
"learning_rate": 6.626506024096386e-06,
"loss": 2.3583,
"step": 5760
},
{
"epoch": 8.69,
"learning_rate": 6.551204819277108e-06,
"loss": 2.3792,
"step": 5770
},
{
"epoch": 8.7,
"learning_rate": 6.475903614457831e-06,
"loss": 2.3393,
"step": 5780
},
{
"epoch": 8.72,
"learning_rate": 6.400602409638555e-06,
"loss": 2.3634,
"step": 5790
},
{
"epoch": 8.73,
"learning_rate": 6.325301204819277e-06,
"loss": 2.3552,
"step": 5800
},
{
"epoch": 8.75,
"learning_rate": 6.25e-06,
"loss": 2.3372,
"step": 5810
},
{
"epoch": 8.76,
"learning_rate": 6.174698795180723e-06,
"loss": 2.3421,
"step": 5820
},
{
"epoch": 8.78,
"learning_rate": 6.099397590361446e-06,
"loss": 2.3555,
"step": 5830
},
{
"epoch": 8.79,
"learning_rate": 6.024096385542169e-06,
"loss": 2.3465,
"step": 5840
},
{
"epoch": 8.81,
"learning_rate": 5.948795180722891e-06,
"loss": 2.3619,
"step": 5850
},
{
"epoch": 8.82,
"learning_rate": 5.873493975903615e-06,
"loss": 2.3394,
"step": 5860
},
{
"epoch": 8.84,
"learning_rate": 5.798192771084337e-06,
"loss": 2.3813,
"step": 5870
},
{
"epoch": 8.86,
"learning_rate": 5.72289156626506e-06,
"loss": 2.34,
"step": 5880
},
{
"epoch": 8.87,
"learning_rate": 5.647590361445783e-06,
"loss": 2.3559,
"step": 5890
},
{
"epoch": 8.89,
"learning_rate": 5.572289156626506e-06,
"loss": 2.3413,
"step": 5900
},
{
"epoch": 8.9,
"learning_rate": 5.496987951807229e-06,
"loss": 2.3469,
"step": 5910
},
{
"epoch": 8.92,
"learning_rate": 5.421686746987952e-06,
"loss": 2.35,
"step": 5920
},
{
"epoch": 8.93,
"learning_rate": 5.346385542168675e-06,
"loss": 2.358,
"step": 5930
},
{
"epoch": 8.95,
"learning_rate": 5.271084337349398e-06,
"loss": 2.357,
"step": 5940
},
{
"epoch": 8.96,
"learning_rate": 5.195783132530121e-06,
"loss": 2.3736,
"step": 5950
},
{
"epoch": 8.98,
"learning_rate": 5.120481927710843e-06,
"loss": 2.3486,
"step": 5960
},
{
"epoch": 8.99,
"learning_rate": 5.045180722891567e-06,
"loss": 2.3456,
"step": 5970
},
{
"epoch": 9.0,
"eval_accuracy": 0.1036,
"eval_loss": 2.34945011138916,
"eval_runtime": 89.3165,
"eval_samples_per_second": 83.971,
"eval_steps_per_second": 5.251,
"step": 5976
},
{
"epoch": 9.01,
"learning_rate": 4.969879518072289e-06,
"loss": 2.3932,
"step": 5980
},
{
"epoch": 9.02,
"learning_rate": 4.894578313253012e-06,
"loss": 2.3381,
"step": 5990
},
{
"epoch": 9.04,
"learning_rate": 4.819277108433735e-06,
"loss": 2.3458,
"step": 6000
},
{
"epoch": 9.05,
"learning_rate": 4.743975903614458e-06,
"loss": 2.3483,
"step": 6010
},
{
"epoch": 9.07,
"learning_rate": 4.66867469879518e-06,
"loss": 2.3492,
"step": 6020
},
{
"epoch": 9.08,
"learning_rate": 4.593373493975904e-06,
"loss": 2.363,
"step": 6030
},
{
"epoch": 9.1,
"learning_rate": 4.518072289156626e-06,
"loss": 2.3461,
"step": 6040
},
{
"epoch": 9.11,
"learning_rate": 4.442771084337349e-06,
"loss": 2.3263,
"step": 6050
},
{
"epoch": 9.13,
"learning_rate": 4.367469879518073e-06,
"loss": 2.3446,
"step": 6060
},
{
"epoch": 9.14,
"learning_rate": 4.292168674698795e-06,
"loss": 2.3492,
"step": 6070
},
{
"epoch": 9.16,
"learning_rate": 4.216867469879518e-06,
"loss": 2.3547,
"step": 6080
},
{
"epoch": 9.17,
"learning_rate": 4.141566265060241e-06,
"loss": 2.3578,
"step": 6090
},
{
"epoch": 9.19,
"learning_rate": 4.066265060240964e-06,
"loss": 2.3575,
"step": 6100
},
{
"epoch": 9.2,
"learning_rate": 3.990963855421686e-06,
"loss": 2.37,
"step": 6110
},
{
"epoch": 9.22,
"learning_rate": 3.91566265060241e-06,
"loss": 2.3309,
"step": 6120
},
{
"epoch": 9.23,
"learning_rate": 3.840361445783132e-06,
"loss": 2.3272,
"step": 6130
},
{
"epoch": 9.25,
"learning_rate": 3.765060240963856e-06,
"loss": 2.3461,
"step": 6140
},
{
"epoch": 9.26,
"learning_rate": 3.6897590361445786e-06,
"loss": 2.3622,
"step": 6150
},
{
"epoch": 9.28,
"learning_rate": 3.614457831325301e-06,
"loss": 2.3574,
"step": 6160
},
{
"epoch": 9.29,
"learning_rate": 3.5391566265060246e-06,
"loss": 2.3448,
"step": 6170
},
{
"epoch": 9.31,
"learning_rate": 3.463855421686747e-06,
"loss": 2.3468,
"step": 6180
},
{
"epoch": 9.32,
"learning_rate": 3.3885542168674697e-06,
"loss": 2.3576,
"step": 6190
},
{
"epoch": 9.34,
"learning_rate": 3.313253012048193e-06,
"loss": 2.3443,
"step": 6200
},
{
"epoch": 9.35,
"learning_rate": 3.2379518072289157e-06,
"loss": 2.3561,
"step": 6210
},
{
"epoch": 9.37,
"learning_rate": 3.1626506024096387e-06,
"loss": 2.3564,
"step": 6220
},
{
"epoch": 9.38,
"learning_rate": 3.0873493975903616e-06,
"loss": 2.3243,
"step": 6230
},
{
"epoch": 9.4,
"learning_rate": 3.0120481927710846e-06,
"loss": 2.3521,
"step": 6240
},
{
"epoch": 9.41,
"learning_rate": 2.9367469879518076e-06,
"loss": 2.3574,
"step": 6250
},
{
"epoch": 9.43,
"learning_rate": 2.86144578313253e-06,
"loss": 2.3711,
"step": 6260
},
{
"epoch": 9.44,
"learning_rate": 2.786144578313253e-06,
"loss": 2.3457,
"step": 6270
},
{
"epoch": 9.46,
"learning_rate": 2.710843373493976e-06,
"loss": 2.3374,
"step": 6280
},
{
"epoch": 9.47,
"learning_rate": 2.635542168674699e-06,
"loss": 2.3487,
"step": 6290
},
{
"epoch": 9.49,
"learning_rate": 2.5602409638554217e-06,
"loss": 2.3415,
"step": 6300
},
{
"epoch": 9.5,
"learning_rate": 2.4849397590361446e-06,
"loss": 2.356,
"step": 6310
},
{
"epoch": 9.52,
"learning_rate": 2.4096385542168676e-06,
"loss": 2.3409,
"step": 6320
},
{
"epoch": 9.53,
"learning_rate": 2.33433734939759e-06,
"loss": 2.3431,
"step": 6330
},
{
"epoch": 9.55,
"learning_rate": 2.259036144578313e-06,
"loss": 2.3382,
"step": 6340
},
{
"epoch": 9.56,
"learning_rate": 2.1837349397590366e-06,
"loss": 2.3546,
"step": 6350
},
{
"epoch": 9.58,
"learning_rate": 2.108433734939759e-06,
"loss": 2.3461,
"step": 6360
},
{
"epoch": 9.59,
"learning_rate": 2.033132530120482e-06,
"loss": 2.355,
"step": 6370
},
{
"epoch": 9.61,
"learning_rate": 1.957831325301205e-06,
"loss": 2.3541,
"step": 6380
},
{
"epoch": 9.62,
"learning_rate": 1.882530120481928e-06,
"loss": 2.3402,
"step": 6390
},
{
"epoch": 9.64,
"learning_rate": 1.8072289156626506e-06,
"loss": 2.3381,
"step": 6400
},
{
"epoch": 9.65,
"learning_rate": 1.7319277108433736e-06,
"loss": 2.3463,
"step": 6410
},
{
"epoch": 9.67,
"learning_rate": 1.6566265060240966e-06,
"loss": 2.3386,
"step": 6420
},
{
"epoch": 9.68,
"learning_rate": 1.5813253012048193e-06,
"loss": 2.3251,
"step": 6430
},
{
"epoch": 9.7,
"learning_rate": 1.5060240963855423e-06,
"loss": 2.3473,
"step": 6440
},
{
"epoch": 9.71,
"learning_rate": 1.430722891566265e-06,
"loss": 2.3398,
"step": 6450
},
{
"epoch": 9.73,
"learning_rate": 1.355421686746988e-06,
"loss": 2.347,
"step": 6460
},
{
"epoch": 9.74,
"learning_rate": 1.2801204819277108e-06,
"loss": 2.3439,
"step": 6470
},
{
"epoch": 9.76,
"learning_rate": 1.2048192771084338e-06,
"loss": 2.372,
"step": 6480
},
{
"epoch": 9.77,
"learning_rate": 1.1295180722891566e-06,
"loss": 2.3419,
"step": 6490
},
{
"epoch": 9.79,
"learning_rate": 1.0542168674698796e-06,
"loss": 2.3514,
"step": 6500
},
{
"epoch": 9.8,
"learning_rate": 9.789156626506025e-07,
"loss": 2.3408,
"step": 6510
},
{
"epoch": 9.82,
"learning_rate": 9.036144578313253e-07,
"loss": 2.3531,
"step": 6520
},
{
"epoch": 9.83,
"learning_rate": 8.283132530120483e-07,
"loss": 2.3511,
"step": 6530
},
{
"epoch": 9.85,
"learning_rate": 7.530120481927712e-07,
"loss": 2.351,
"step": 6540
},
{
"epoch": 9.86,
"learning_rate": 6.77710843373494e-07,
"loss": 2.3652,
"step": 6550
},
{
"epoch": 9.88,
"learning_rate": 6.024096385542169e-07,
"loss": 2.3332,
"step": 6560
},
{
"epoch": 9.89,
"learning_rate": 5.271084337349398e-07,
"loss": 2.3325,
"step": 6570
},
{
"epoch": 9.91,
"learning_rate": 4.5180722891566265e-07,
"loss": 2.3646,
"step": 6580
},
{
"epoch": 9.92,
"learning_rate": 3.765060240963856e-07,
"loss": 2.3587,
"step": 6590
},
{
"epoch": 9.94,
"learning_rate": 3.0120481927710845e-07,
"loss": 2.3622,
"step": 6600
},
{
"epoch": 9.95,
"learning_rate": 2.2590361445783133e-07,
"loss": 2.345,
"step": 6610
},
{
"epoch": 9.97,
"learning_rate": 1.5060240963855423e-07,
"loss": 2.3493,
"step": 6620
},
{
"epoch": 9.98,
"learning_rate": 7.530120481927711e-08,
"loss": 2.3601,
"step": 6630
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 2.3361,
"step": 6640
},
{
"epoch": 10.0,
"eval_accuracy": 0.10253333333333334,
"eval_loss": 2.347257375717163,
"eval_runtime": 88.4974,
"eval_samples_per_second": 84.748,
"eval_steps_per_second": 5.3,
"step": 6640
},
{
"epoch": 10.0,
"step": 6640,
"total_flos": 3.2936147019070783e+19,
"train_loss": 2.389983481671437,
"train_runtime": 10181.4642,
"train_samples_per_second": 41.743,
"train_steps_per_second": 0.652
}
],
"max_steps": 6640,
"num_train_epochs": 10,
"total_flos": 3.2936147019070783e+19,
"trial_name": null,
"trial_params": null
}