ALM-AHME's picture
End of training
d863a9d
raw
history blame
36.5 kB
{
"best_metric": 0.9852216748768473,
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20-Shuffled/checkpoint-1368",
"epoch": 11.947598253275109,
"global_step": 1368,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 2.029220779220779e-07,
"loss": 1.9523,
"step": 5
},
{
"epoch": 0.09,
"learning_rate": 4.058441558441558e-07,
"loss": 1.9457,
"step": 10
},
{
"epoch": 0.13,
"learning_rate": 6.087662337662339e-07,
"loss": 1.9612,
"step": 15
},
{
"epoch": 0.17,
"learning_rate": 8.116883116883116e-07,
"loss": 1.9457,
"step": 20
},
{
"epoch": 0.22,
"learning_rate": 1.0146103896103896e-06,
"loss": 1.9407,
"step": 25
},
{
"epoch": 0.26,
"learning_rate": 1.2175324675324677e-06,
"loss": 1.9508,
"step": 30
},
{
"epoch": 0.31,
"learning_rate": 1.4204545454545456e-06,
"loss": 1.9491,
"step": 35
},
{
"epoch": 0.35,
"learning_rate": 1.6233766233766232e-06,
"loss": 1.9445,
"step": 40
},
{
"epoch": 0.39,
"learning_rate": 1.8262987012987013e-06,
"loss": 1.9434,
"step": 45
},
{
"epoch": 0.44,
"learning_rate": 2.0292207792207792e-06,
"loss": 1.9398,
"step": 50
},
{
"epoch": 0.48,
"learning_rate": 2.2321428571428573e-06,
"loss": 1.9297,
"step": 55
},
{
"epoch": 0.52,
"learning_rate": 2.4350649350649354e-06,
"loss": 1.9422,
"step": 60
},
{
"epoch": 0.57,
"learning_rate": 2.637987012987013e-06,
"loss": 1.9275,
"step": 65
},
{
"epoch": 0.61,
"learning_rate": 2.840909090909091e-06,
"loss": 1.9269,
"step": 70
},
{
"epoch": 0.66,
"learning_rate": 3.043831168831169e-06,
"loss": 1.9152,
"step": 75
},
{
"epoch": 0.7,
"learning_rate": 3.2467532467532465e-06,
"loss": 1.9336,
"step": 80
},
{
"epoch": 0.74,
"learning_rate": 3.449675324675325e-06,
"loss": 1.9233,
"step": 85
},
{
"epoch": 0.79,
"learning_rate": 3.6525974025974027e-06,
"loss": 1.9191,
"step": 90
},
{
"epoch": 0.83,
"learning_rate": 3.855519480519481e-06,
"loss": 1.9093,
"step": 95
},
{
"epoch": 0.87,
"learning_rate": 4.0584415584415584e-06,
"loss": 1.9135,
"step": 100
},
{
"epoch": 0.92,
"learning_rate": 4.2613636363636365e-06,
"loss": 1.9034,
"step": 105
},
{
"epoch": 0.96,
"learning_rate": 4.464285714285715e-06,
"loss": 1.9014,
"step": 110
},
{
"epoch": 1.0,
"eval_accuracy": 0.3981937602627258,
"eval_loss": 1.8872182369232178,
"eval_runtime": 273.6883,
"eval_samples_per_second": 4.45,
"eval_steps_per_second": 0.281,
"step": 114
},
{
"epoch": 1.0,
"learning_rate": 4.667207792207792e-06,
"loss": 1.8834,
"step": 115
},
{
"epoch": 1.05,
"learning_rate": 4.870129870129871e-06,
"loss": 1.8904,
"step": 120
},
{
"epoch": 1.09,
"learning_rate": 5.073051948051948e-06,
"loss": 1.882,
"step": 125
},
{
"epoch": 1.14,
"learning_rate": 5.275974025974026e-06,
"loss": 1.8779,
"step": 130
},
{
"epoch": 1.18,
"learning_rate": 5.478896103896104e-06,
"loss": 1.8745,
"step": 135
},
{
"epoch": 1.22,
"learning_rate": 5.681818181818182e-06,
"loss": 1.8559,
"step": 140
},
{
"epoch": 1.27,
"learning_rate": 5.88474025974026e-06,
"loss": 1.8514,
"step": 145
},
{
"epoch": 1.31,
"learning_rate": 6.087662337662338e-06,
"loss": 1.8244,
"step": 150
},
{
"epoch": 1.35,
"learning_rate": 6.290584415584417e-06,
"loss": 1.82,
"step": 155
},
{
"epoch": 1.4,
"learning_rate": 6.493506493506493e-06,
"loss": 1.8196,
"step": 160
},
{
"epoch": 1.44,
"learning_rate": 6.696428571428572e-06,
"loss": 1.8163,
"step": 165
},
{
"epoch": 1.48,
"learning_rate": 6.89935064935065e-06,
"loss": 1.7813,
"step": 170
},
{
"epoch": 1.53,
"learning_rate": 7.102272727272728e-06,
"loss": 1.789,
"step": 175
},
{
"epoch": 1.57,
"learning_rate": 7.305194805194805e-06,
"loss": 1.7802,
"step": 180
},
{
"epoch": 1.62,
"learning_rate": 7.5081168831168834e-06,
"loss": 1.7511,
"step": 185
},
{
"epoch": 1.66,
"learning_rate": 7.711038961038962e-06,
"loss": 1.7404,
"step": 190
},
{
"epoch": 1.7,
"learning_rate": 7.91396103896104e-06,
"loss": 1.7345,
"step": 195
},
{
"epoch": 1.75,
"learning_rate": 8.116883116883117e-06,
"loss": 1.7248,
"step": 200
},
{
"epoch": 1.79,
"learning_rate": 8.319805194805196e-06,
"loss": 1.7112,
"step": 205
},
{
"epoch": 1.83,
"learning_rate": 8.522727272727273e-06,
"loss": 1.6794,
"step": 210
},
{
"epoch": 1.88,
"learning_rate": 8.72564935064935e-06,
"loss": 1.6574,
"step": 215
},
{
"epoch": 1.92,
"learning_rate": 8.92857142857143e-06,
"loss": 1.6914,
"step": 220
},
{
"epoch": 1.97,
"learning_rate": 9.131493506493508e-06,
"loss": 1.6303,
"step": 225
},
{
"epoch": 2.0,
"eval_accuracy": 0.5927750410509032,
"eval_loss": 1.6162906885147095,
"eval_runtime": 41.2879,
"eval_samples_per_second": 29.5,
"eval_steps_per_second": 1.865,
"step": 229
},
{
"epoch": 2.01,
"learning_rate": 9.334415584415584e-06,
"loss": 1.608,
"step": 230
},
{
"epoch": 2.05,
"learning_rate": 9.537337662337663e-06,
"loss": 1.6109,
"step": 235
},
{
"epoch": 2.1,
"learning_rate": 9.740259740259742e-06,
"loss": 1.5838,
"step": 240
},
{
"epoch": 2.14,
"learning_rate": 9.943181818181819e-06,
"loss": 1.5902,
"step": 245
},
{
"epoch": 2.18,
"learning_rate": 1.0146103896103896e-05,
"loss": 1.5408,
"step": 250
},
{
"epoch": 2.23,
"learning_rate": 1.0349025974025975e-05,
"loss": 1.505,
"step": 255
},
{
"epoch": 2.27,
"learning_rate": 1.0551948051948052e-05,
"loss": 1.5325,
"step": 260
},
{
"epoch": 2.31,
"learning_rate": 1.075487012987013e-05,
"loss": 1.5185,
"step": 265
},
{
"epoch": 2.36,
"learning_rate": 1.0957792207792208e-05,
"loss": 1.5277,
"step": 270
},
{
"epoch": 2.4,
"learning_rate": 1.1160714285714287e-05,
"loss": 1.5179,
"step": 275
},
{
"epoch": 2.45,
"learning_rate": 1.1363636363636365e-05,
"loss": 1.4338,
"step": 280
},
{
"epoch": 2.49,
"learning_rate": 1.1566558441558442e-05,
"loss": 1.4783,
"step": 285
},
{
"epoch": 2.53,
"learning_rate": 1.176948051948052e-05,
"loss": 1.4104,
"step": 290
},
{
"epoch": 2.58,
"learning_rate": 1.1972402597402598e-05,
"loss": 1.4168,
"step": 295
},
{
"epoch": 2.62,
"learning_rate": 1.2175324675324675e-05,
"loss": 1.3617,
"step": 300
},
{
"epoch": 2.66,
"learning_rate": 1.2378246753246754e-05,
"loss": 1.3425,
"step": 305
},
{
"epoch": 2.71,
"learning_rate": 1.2581168831168833e-05,
"loss": 1.317,
"step": 310
},
{
"epoch": 2.75,
"learning_rate": 1.2784090909090909e-05,
"loss": 1.4114,
"step": 315
},
{
"epoch": 2.79,
"learning_rate": 1.2987012987012986e-05,
"loss": 1.3512,
"step": 320
},
{
"epoch": 2.84,
"learning_rate": 1.3189935064935067e-05,
"loss": 1.3026,
"step": 325
},
{
"epoch": 2.88,
"learning_rate": 1.3392857142857144e-05,
"loss": 1.3261,
"step": 330
},
{
"epoch": 2.93,
"learning_rate": 1.359577922077922e-05,
"loss": 1.3273,
"step": 335
},
{
"epoch": 2.97,
"learning_rate": 1.37987012987013e-05,
"loss": 1.291,
"step": 340
},
{
"epoch": 3.0,
"eval_accuracy": 0.6773399014778325,
"eval_loss": 1.2219544649124146,
"eval_runtime": 41.4884,
"eval_samples_per_second": 29.358,
"eval_steps_per_second": 1.856,
"step": 343
},
{
"epoch": 3.01,
"learning_rate": 1.4001623376623377e-05,
"loss": 1.353,
"step": 345
},
{
"epoch": 3.06,
"learning_rate": 1.4204545454545456e-05,
"loss": 1.294,
"step": 350
},
{
"epoch": 3.1,
"learning_rate": 1.4407467532467533e-05,
"loss": 1.2475,
"step": 355
},
{
"epoch": 3.14,
"learning_rate": 1.461038961038961e-05,
"loss": 1.1985,
"step": 360
},
{
"epoch": 3.19,
"learning_rate": 1.481331168831169e-05,
"loss": 1.2283,
"step": 365
},
{
"epoch": 3.23,
"learning_rate": 1.5016233766233767e-05,
"loss": 1.1886,
"step": 370
},
{
"epoch": 3.28,
"learning_rate": 1.5219155844155844e-05,
"loss": 1.1673,
"step": 375
},
{
"epoch": 3.32,
"learning_rate": 1.5422077922077925e-05,
"loss": 1.1219,
"step": 380
},
{
"epoch": 3.36,
"learning_rate": 1.5625e-05,
"loss": 1.2191,
"step": 385
},
{
"epoch": 3.41,
"learning_rate": 1.582792207792208e-05,
"loss": 1.205,
"step": 390
},
{
"epoch": 3.45,
"learning_rate": 1.6030844155844158e-05,
"loss": 1.178,
"step": 395
},
{
"epoch": 3.49,
"learning_rate": 1.6233766233766234e-05,
"loss": 1.1588,
"step": 400
},
{
"epoch": 3.54,
"learning_rate": 1.6436688311688313e-05,
"loss": 1.2004,
"step": 405
},
{
"epoch": 3.58,
"learning_rate": 1.663961038961039e-05,
"loss": 1.1484,
"step": 410
},
{
"epoch": 3.62,
"learning_rate": 1.6842532467532467e-05,
"loss": 1.2333,
"step": 415
},
{
"epoch": 3.67,
"learning_rate": 1.7045454545454546e-05,
"loss": 1.1565,
"step": 420
},
{
"epoch": 3.71,
"learning_rate": 1.7248376623376625e-05,
"loss": 1.0677,
"step": 425
},
{
"epoch": 3.76,
"learning_rate": 1.74512987012987e-05,
"loss": 1.1271,
"step": 430
},
{
"epoch": 3.8,
"learning_rate": 1.7654220779220783e-05,
"loss": 0.9125,
"step": 435
},
{
"epoch": 3.84,
"learning_rate": 1.785714285714286e-05,
"loss": 1.1261,
"step": 440
},
{
"epoch": 3.89,
"learning_rate": 1.8060064935064934e-05,
"loss": 1.0694,
"step": 445
},
{
"epoch": 3.93,
"learning_rate": 1.8262987012987016e-05,
"loss": 1.0313,
"step": 450
},
{
"epoch": 3.97,
"learning_rate": 1.8465909090909092e-05,
"loss": 1.0813,
"step": 455
},
{
"epoch": 4.0,
"eval_accuracy": 0.7750410509031199,
"eval_loss": 0.9574336409568787,
"eval_runtime": 41.7866,
"eval_samples_per_second": 29.148,
"eval_steps_per_second": 1.843,
"step": 458
},
{
"epoch": 4.02,
"learning_rate": 1.8668831168831167e-05,
"loss": 0.9923,
"step": 460
},
{
"epoch": 4.06,
"learning_rate": 1.887175324675325e-05,
"loss": 1.0316,
"step": 465
},
{
"epoch": 4.1,
"learning_rate": 1.9074675324675325e-05,
"loss": 1.0292,
"step": 470
},
{
"epoch": 4.15,
"learning_rate": 1.9277597402597404e-05,
"loss": 1.0028,
"step": 475
},
{
"epoch": 4.19,
"learning_rate": 1.9480519480519483e-05,
"loss": 0.9421,
"step": 480
},
{
"epoch": 4.24,
"learning_rate": 1.968344155844156e-05,
"loss": 0.9741,
"step": 485
},
{
"epoch": 4.28,
"learning_rate": 1.9886363636363638e-05,
"loss": 0.9571,
"step": 490
},
{
"epoch": 4.32,
"learning_rate": 2.0089285714285717e-05,
"loss": 1.0524,
"step": 495
},
{
"epoch": 4.37,
"learning_rate": 2.0292207792207792e-05,
"loss": 1.0265,
"step": 500
},
{
"epoch": 4.41,
"learning_rate": 2.049512987012987e-05,
"loss": 0.9203,
"step": 505
},
{
"epoch": 4.45,
"learning_rate": 2.069805194805195e-05,
"loss": 0.8548,
"step": 510
},
{
"epoch": 4.5,
"learning_rate": 2.0900974025974026e-05,
"loss": 0.9264,
"step": 515
},
{
"epoch": 4.54,
"learning_rate": 2.1103896103896105e-05,
"loss": 0.9069,
"step": 520
},
{
"epoch": 4.59,
"learning_rate": 2.1306818181818183e-05,
"loss": 0.8999,
"step": 525
},
{
"epoch": 4.63,
"learning_rate": 2.150974025974026e-05,
"loss": 0.8484,
"step": 530
},
{
"epoch": 4.67,
"learning_rate": 2.171266233766234e-05,
"loss": 0.9169,
"step": 535
},
{
"epoch": 4.72,
"learning_rate": 2.1915584415584417e-05,
"loss": 0.9529,
"step": 540
},
{
"epoch": 4.76,
"learning_rate": 2.2118506493506492e-05,
"loss": 0.8057,
"step": 545
},
{
"epoch": 4.8,
"learning_rate": 2.2321428571428575e-05,
"loss": 0.9171,
"step": 550
},
{
"epoch": 4.85,
"learning_rate": 2.252435064935065e-05,
"loss": 0.8282,
"step": 555
},
{
"epoch": 4.89,
"learning_rate": 2.272727272727273e-05,
"loss": 0.753,
"step": 560
},
{
"epoch": 4.93,
"learning_rate": 2.2930194805194808e-05,
"loss": 0.9191,
"step": 565
},
{
"epoch": 4.98,
"learning_rate": 2.3133116883116884e-05,
"loss": 0.7168,
"step": 570
},
{
"epoch": 5.0,
"eval_accuracy": 0.7602627257799671,
"eval_loss": 0.7791566848754883,
"eval_runtime": 41.3764,
"eval_samples_per_second": 29.437,
"eval_steps_per_second": 1.861,
"step": 572
},
{
"epoch": 5.02,
"learning_rate": 2.3336038961038963e-05,
"loss": 0.7579,
"step": 575
},
{
"epoch": 5.07,
"learning_rate": 2.353896103896104e-05,
"loss": 0.7458,
"step": 580
},
{
"epoch": 5.11,
"learning_rate": 2.3741883116883117e-05,
"loss": 0.8286,
"step": 585
},
{
"epoch": 5.15,
"learning_rate": 2.3944805194805196e-05,
"loss": 0.7919,
"step": 590
},
{
"epoch": 5.2,
"learning_rate": 2.4147727272727275e-05,
"loss": 0.7038,
"step": 595
},
{
"epoch": 5.24,
"learning_rate": 2.435064935064935e-05,
"loss": 0.798,
"step": 600
},
{
"epoch": 5.28,
"learning_rate": 2.455357142857143e-05,
"loss": 0.9234,
"step": 605
},
{
"epoch": 5.33,
"learning_rate": 2.475649350649351e-05,
"loss": 0.8609,
"step": 610
},
{
"epoch": 5.37,
"learning_rate": 2.4959415584415584e-05,
"loss": 0.8748,
"step": 615
},
{
"epoch": 5.41,
"learning_rate": 2.5162337662337666e-05,
"loss": 0.6842,
"step": 620
},
{
"epoch": 5.46,
"learning_rate": 2.536525974025974e-05,
"loss": 0.8199,
"step": 625
},
{
"epoch": 5.5,
"learning_rate": 2.5568181818181817e-05,
"loss": 0.6946,
"step": 630
},
{
"epoch": 5.55,
"learning_rate": 2.57711038961039e-05,
"loss": 0.8134,
"step": 635
},
{
"epoch": 5.59,
"learning_rate": 2.5974025974025972e-05,
"loss": 0.7838,
"step": 640
},
{
"epoch": 5.63,
"learning_rate": 2.617694805194805e-05,
"loss": 0.7889,
"step": 645
},
{
"epoch": 5.68,
"learning_rate": 2.6379870129870133e-05,
"loss": 0.7277,
"step": 650
},
{
"epoch": 5.72,
"learning_rate": 2.6582792207792205e-05,
"loss": 0.678,
"step": 655
},
{
"epoch": 5.76,
"learning_rate": 2.6785714285714288e-05,
"loss": 0.7287,
"step": 660
},
{
"epoch": 5.81,
"learning_rate": 2.6988636363636367e-05,
"loss": 0.7018,
"step": 665
},
{
"epoch": 5.85,
"learning_rate": 2.719155844155844e-05,
"loss": 0.6496,
"step": 670
},
{
"epoch": 5.9,
"learning_rate": 2.739448051948052e-05,
"loss": 0.6684,
"step": 675
},
{
"epoch": 5.94,
"learning_rate": 2.75974025974026e-05,
"loss": 0.7137,
"step": 680
},
{
"epoch": 5.98,
"learning_rate": 2.780032467532468e-05,
"loss": 0.6184,
"step": 685
},
{
"epoch": 6.0,
"eval_accuracy": 0.867816091954023,
"eval_loss": 0.5539422631263733,
"eval_runtime": 41.7795,
"eval_samples_per_second": 29.153,
"eval_steps_per_second": 1.843,
"step": 687
},
{
"epoch": 6.03,
"learning_rate": 2.8003246753246755e-05,
"loss": 0.6205,
"step": 690
},
{
"epoch": 6.07,
"learning_rate": 2.8206168831168834e-05,
"loss": 0.5953,
"step": 695
},
{
"epoch": 6.11,
"learning_rate": 2.8409090909090912e-05,
"loss": 0.6818,
"step": 700
},
{
"epoch": 6.16,
"learning_rate": 2.8612012987012988e-05,
"loss": 0.6218,
"step": 705
},
{
"epoch": 6.2,
"learning_rate": 2.8814935064935067e-05,
"loss": 0.6739,
"step": 710
},
{
"epoch": 6.24,
"learning_rate": 2.9017857142857146e-05,
"loss": 0.5568,
"step": 715
},
{
"epoch": 6.29,
"learning_rate": 2.922077922077922e-05,
"loss": 0.6172,
"step": 720
},
{
"epoch": 6.33,
"learning_rate": 2.94237012987013e-05,
"loss": 0.6714,
"step": 725
},
{
"epoch": 6.38,
"learning_rate": 2.962662337662338e-05,
"loss": 0.6831,
"step": 730
},
{
"epoch": 6.42,
"learning_rate": 2.9829545454545455e-05,
"loss": 0.5986,
"step": 735
},
{
"epoch": 6.46,
"learning_rate": 3.0032467532467534e-05,
"loss": 0.6799,
"step": 740
},
{
"epoch": 6.51,
"learning_rate": 3.0235389610389613e-05,
"loss": 0.5172,
"step": 745
},
{
"epoch": 6.55,
"learning_rate": 3.0438311688311688e-05,
"loss": 0.6682,
"step": 750
},
{
"epoch": 6.59,
"learning_rate": 3.064123376623377e-05,
"loss": 0.5245,
"step": 755
},
{
"epoch": 6.64,
"learning_rate": 3.084415584415585e-05,
"loss": 0.6013,
"step": 760
},
{
"epoch": 6.68,
"learning_rate": 3.1047077922077925e-05,
"loss": 0.5115,
"step": 765
},
{
"epoch": 6.72,
"learning_rate": 3.125e-05,
"loss": 0.5272,
"step": 770
},
{
"epoch": 6.77,
"learning_rate": 3.145292207792208e-05,
"loss": 0.485,
"step": 775
},
{
"epoch": 6.81,
"learning_rate": 3.165584415584416e-05,
"loss": 0.6588,
"step": 780
},
{
"epoch": 6.86,
"learning_rate": 3.1858766233766234e-05,
"loss": 0.5066,
"step": 785
},
{
"epoch": 6.9,
"learning_rate": 3.2061688311688316e-05,
"loss": 0.4862,
"step": 790
},
{
"epoch": 6.94,
"learning_rate": 3.226461038961039e-05,
"loss": 0.4091,
"step": 795
},
{
"epoch": 6.99,
"learning_rate": 3.246753246753247e-05,
"loss": 0.677,
"step": 800
},
{
"epoch": 7.0,
"eval_accuracy": 0.8727422003284072,
"eval_loss": 0.4482496976852417,
"eval_runtime": 41.5406,
"eval_samples_per_second": 29.321,
"eval_steps_per_second": 1.854,
"step": 801
},
{
"epoch": 7.03,
"learning_rate": 3.267045454545455e-05,
"loss": 0.4498,
"step": 805
},
{
"epoch": 7.07,
"learning_rate": 3.2873376623376625e-05,
"loss": 0.5767,
"step": 810
},
{
"epoch": 7.12,
"learning_rate": 3.30762987012987e-05,
"loss": 0.5276,
"step": 815
},
{
"epoch": 7.16,
"learning_rate": 3.327922077922078e-05,
"loss": 0.4909,
"step": 820
},
{
"epoch": 7.21,
"learning_rate": 3.348214285714286e-05,
"loss": 0.5658,
"step": 825
},
{
"epoch": 7.25,
"learning_rate": 3.3685064935064934e-05,
"loss": 0.4413,
"step": 830
},
{
"epoch": 7.29,
"learning_rate": 3.388798701298702e-05,
"loss": 0.4046,
"step": 835
},
{
"epoch": 7.34,
"learning_rate": 3.409090909090909e-05,
"loss": 0.528,
"step": 840
},
{
"epoch": 7.38,
"learning_rate": 3.429383116883117e-05,
"loss": 0.3563,
"step": 845
},
{
"epoch": 7.42,
"learning_rate": 3.449675324675325e-05,
"loss": 0.7032,
"step": 850
},
{
"epoch": 7.47,
"learning_rate": 3.4699675324675326e-05,
"loss": 0.4867,
"step": 855
},
{
"epoch": 7.51,
"learning_rate": 3.49025974025974e-05,
"loss": 0.4171,
"step": 860
},
{
"epoch": 7.55,
"learning_rate": 3.5105519480519484e-05,
"loss": 0.4876,
"step": 865
},
{
"epoch": 7.6,
"learning_rate": 3.5308441558441566e-05,
"loss": 0.5591,
"step": 870
},
{
"epoch": 7.64,
"learning_rate": 3.5511363636363635e-05,
"loss": 0.5694,
"step": 875
},
{
"epoch": 7.69,
"learning_rate": 3.571428571428572e-05,
"loss": 0.4692,
"step": 880
},
{
"epoch": 7.73,
"learning_rate": 3.59172077922078e-05,
"loss": 0.4355,
"step": 885
},
{
"epoch": 7.77,
"learning_rate": 3.612012987012987e-05,
"loss": 0.4585,
"step": 890
},
{
"epoch": 7.82,
"learning_rate": 3.632305194805195e-05,
"loss": 0.4527,
"step": 895
},
{
"epoch": 7.86,
"learning_rate": 3.652597402597403e-05,
"loss": 0.534,
"step": 900
},
{
"epoch": 7.9,
"learning_rate": 3.67288961038961e-05,
"loss": 0.5621,
"step": 905
},
{
"epoch": 7.95,
"learning_rate": 3.6931818181818184e-05,
"loss": 0.4936,
"step": 910
},
{
"epoch": 7.99,
"learning_rate": 3.7134740259740266e-05,
"loss": 0.4876,
"step": 915
},
{
"epoch": 8.0,
"eval_accuracy": 0.9269293924466339,
"eval_loss": 0.32888495922088623,
"eval_runtime": 41.545,
"eval_samples_per_second": 29.318,
"eval_steps_per_second": 1.853,
"step": 916
},
{
"epoch": 8.03,
"learning_rate": 3.7337662337662335e-05,
"loss": 0.3788,
"step": 920
},
{
"epoch": 8.08,
"learning_rate": 3.754058441558442e-05,
"loss": 0.4377,
"step": 925
},
{
"epoch": 8.12,
"learning_rate": 3.77435064935065e-05,
"loss": 0.4436,
"step": 930
},
{
"epoch": 8.17,
"learning_rate": 3.794642857142857e-05,
"loss": 0.5716,
"step": 935
},
{
"epoch": 8.21,
"learning_rate": 3.814935064935065e-05,
"loss": 0.5563,
"step": 940
},
{
"epoch": 8.25,
"learning_rate": 3.835227272727273e-05,
"loss": 0.526,
"step": 945
},
{
"epoch": 8.3,
"learning_rate": 3.855519480519481e-05,
"loss": 0.3903,
"step": 950
},
{
"epoch": 8.34,
"learning_rate": 3.8758116883116884e-05,
"loss": 0.3263,
"step": 955
},
{
"epoch": 8.38,
"learning_rate": 3.8961038961038966e-05,
"loss": 0.5028,
"step": 960
},
{
"epoch": 8.43,
"learning_rate": 3.916396103896104e-05,
"loss": 0.3781,
"step": 965
},
{
"epoch": 8.47,
"learning_rate": 3.936688311688312e-05,
"loss": 0.3756,
"step": 970
},
{
"epoch": 8.52,
"learning_rate": 3.95698051948052e-05,
"loss": 0.4825,
"step": 975
},
{
"epoch": 8.56,
"learning_rate": 3.9772727272727275e-05,
"loss": 0.399,
"step": 980
},
{
"epoch": 8.6,
"learning_rate": 3.997564935064935e-05,
"loss": 0.4362,
"step": 985
},
{
"epoch": 8.65,
"learning_rate": 4.017857142857143e-05,
"loss": 0.4385,
"step": 990
},
{
"epoch": 8.69,
"learning_rate": 4.038149350649351e-05,
"loss": 0.4277,
"step": 995
},
{
"epoch": 8.73,
"learning_rate": 4.0584415584415584e-05,
"loss": 0.4211,
"step": 1000
},
{
"epoch": 8.78,
"learning_rate": 4.078733766233767e-05,
"loss": 0.3729,
"step": 1005
},
{
"epoch": 8.82,
"learning_rate": 4.099025974025974e-05,
"loss": 0.3427,
"step": 1010
},
{
"epoch": 8.86,
"learning_rate": 4.119318181818182e-05,
"loss": 0.4221,
"step": 1015
},
{
"epoch": 8.91,
"learning_rate": 4.13961038961039e-05,
"loss": 0.316,
"step": 1020
},
{
"epoch": 8.95,
"learning_rate": 4.1599025974025976e-05,
"loss": 0.5041,
"step": 1025
},
{
"epoch": 9.0,
"learning_rate": 4.180194805194805e-05,
"loss": 0.4,
"step": 1030
},
{
"epoch": 9.0,
"eval_accuracy": 0.9499178981937603,
"eval_loss": 0.23791643977165222,
"eval_runtime": 41.3669,
"eval_samples_per_second": 29.444,
"eval_steps_per_second": 1.861,
"step": 1030
},
{
"epoch": 9.04,
"learning_rate": 4.2004870129870134e-05,
"loss": 0.3897,
"step": 1035
},
{
"epoch": 9.08,
"learning_rate": 4.220779220779221e-05,
"loss": 0.3342,
"step": 1040
},
{
"epoch": 9.13,
"learning_rate": 4.2410714285714285e-05,
"loss": 0.3891,
"step": 1045
},
{
"epoch": 9.17,
"learning_rate": 4.261363636363637e-05,
"loss": 0.379,
"step": 1050
},
{
"epoch": 9.21,
"learning_rate": 4.281655844155844e-05,
"loss": 0.4199,
"step": 1055
},
{
"epoch": 9.26,
"learning_rate": 4.301948051948052e-05,
"loss": 0.4718,
"step": 1060
},
{
"epoch": 9.3,
"learning_rate": 4.32224025974026e-05,
"loss": 0.3834,
"step": 1065
},
{
"epoch": 9.34,
"learning_rate": 4.342532467532468e-05,
"loss": 0.3155,
"step": 1070
},
{
"epoch": 9.39,
"learning_rate": 4.362824675324675e-05,
"loss": 0.3672,
"step": 1075
},
{
"epoch": 9.43,
"learning_rate": 4.3831168831168834e-05,
"loss": 0.3521,
"step": 1080
},
{
"epoch": 9.48,
"learning_rate": 4.4034090909090916e-05,
"loss": 0.3689,
"step": 1085
},
{
"epoch": 9.52,
"learning_rate": 4.4237012987012985e-05,
"loss": 0.4642,
"step": 1090
},
{
"epoch": 9.56,
"learning_rate": 4.443993506493507e-05,
"loss": 0.5208,
"step": 1095
},
{
"epoch": 9.61,
"learning_rate": 4.464285714285715e-05,
"loss": 0.4228,
"step": 1100
},
{
"epoch": 9.65,
"learning_rate": 4.484577922077922e-05,
"loss": 0.3621,
"step": 1105
},
{
"epoch": 9.69,
"learning_rate": 4.50487012987013e-05,
"loss": 0.416,
"step": 1110
},
{
"epoch": 9.74,
"learning_rate": 4.525162337662338e-05,
"loss": 0.3168,
"step": 1115
},
{
"epoch": 9.78,
"learning_rate": 4.545454545454546e-05,
"loss": 0.3837,
"step": 1120
},
{
"epoch": 9.83,
"learning_rate": 4.5657467532467534e-05,
"loss": 0.5365,
"step": 1125
},
{
"epoch": 9.87,
"learning_rate": 4.5860389610389616e-05,
"loss": 0.3512,
"step": 1130
},
{
"epoch": 9.91,
"learning_rate": 4.606331168831169e-05,
"loss": 0.3027,
"step": 1135
},
{
"epoch": 9.96,
"learning_rate": 4.626623376623377e-05,
"loss": 0.3698,
"step": 1140
},
{
"epoch": 10.0,
"learning_rate": 4.646915584415585e-05,
"loss": 0.4122,
"step": 1145
},
{
"epoch": 10.0,
"eval_accuracy": 0.9351395730706076,
"eval_loss": 0.24517326056957245,
"eval_runtime": 41.719,
"eval_samples_per_second": 29.195,
"eval_steps_per_second": 1.846,
"step": 1145
},
{
"epoch": 10.04,
"learning_rate": 4.6672077922077925e-05,
"loss": 0.5587,
"step": 1150
},
{
"epoch": 10.09,
"learning_rate": 4.6875e-05,
"loss": 0.526,
"step": 1155
},
{
"epoch": 10.13,
"learning_rate": 4.707792207792208e-05,
"loss": 0.3711,
"step": 1160
},
{
"epoch": 10.17,
"learning_rate": 4.728084415584416e-05,
"loss": 0.241,
"step": 1165
},
{
"epoch": 10.22,
"learning_rate": 4.7483766233766234e-05,
"loss": 0.2986,
"step": 1170
},
{
"epoch": 10.26,
"learning_rate": 4.768668831168832e-05,
"loss": 0.3427,
"step": 1175
},
{
"epoch": 10.31,
"learning_rate": 4.788961038961039e-05,
"loss": 0.3038,
"step": 1180
},
{
"epoch": 10.35,
"learning_rate": 4.809253246753247e-05,
"loss": 0.3751,
"step": 1185
},
{
"epoch": 10.39,
"learning_rate": 4.829545454545455e-05,
"loss": 0.4363,
"step": 1190
},
{
"epoch": 10.44,
"learning_rate": 4.8498376623376626e-05,
"loss": 0.4679,
"step": 1195
},
{
"epoch": 10.48,
"learning_rate": 4.87012987012987e-05,
"loss": 0.4258,
"step": 1200
},
{
"epoch": 10.52,
"learning_rate": 4.8904220779220784e-05,
"loss": 0.3684,
"step": 1205
},
{
"epoch": 10.57,
"learning_rate": 4.910714285714286e-05,
"loss": 0.3698,
"step": 1210
},
{
"epoch": 10.61,
"learning_rate": 4.9310064935064935e-05,
"loss": 0.3574,
"step": 1215
},
{
"epoch": 10.66,
"learning_rate": 4.951298701298702e-05,
"loss": 0.2396,
"step": 1220
},
{
"epoch": 10.7,
"learning_rate": 4.971590909090909e-05,
"loss": 0.2608,
"step": 1225
},
{
"epoch": 10.74,
"learning_rate": 4.991883116883117e-05,
"loss": 0.3136,
"step": 1230
},
{
"epoch": 10.79,
"learning_rate": 4.889705882352941e-05,
"loss": 0.4472,
"step": 1235
},
{
"epoch": 10.83,
"learning_rate": 4.705882352941177e-05,
"loss": 0.4089,
"step": 1240
},
{
"epoch": 10.87,
"learning_rate": 4.522058823529412e-05,
"loss": 0.3355,
"step": 1245
},
{
"epoch": 10.92,
"learning_rate": 4.3382352941176474e-05,
"loss": 0.4199,
"step": 1250
},
{
"epoch": 10.96,
"learning_rate": 4.154411764705883e-05,
"loss": 0.4494,
"step": 1255
},
{
"epoch": 11.0,
"eval_accuracy": 0.958128078817734,
"eval_loss": 0.17895229160785675,
"eval_runtime": 41.7173,
"eval_samples_per_second": 29.197,
"eval_steps_per_second": 1.846,
"step": 1259
},
{
"epoch": 11.0,
"learning_rate": 3.970588235294117e-05,
"loss": 0.307,
"step": 1260
},
{
"epoch": 11.05,
"learning_rate": 3.786764705882353e-05,
"loss": 0.4496,
"step": 1265
},
{
"epoch": 11.09,
"learning_rate": 3.6029411764705886e-05,
"loss": 0.2769,
"step": 1270
},
{
"epoch": 11.14,
"learning_rate": 3.4191176470588236e-05,
"loss": 0.3289,
"step": 1275
},
{
"epoch": 11.18,
"learning_rate": 3.235294117647059e-05,
"loss": 0.2077,
"step": 1280
},
{
"epoch": 11.22,
"learning_rate": 3.0514705882352945e-05,
"loss": 0.287,
"step": 1285
},
{
"epoch": 11.27,
"learning_rate": 2.8676470588235295e-05,
"loss": 0.3158,
"step": 1290
},
{
"epoch": 11.31,
"learning_rate": 2.6838235294117648e-05,
"loss": 0.2375,
"step": 1295
},
{
"epoch": 11.35,
"learning_rate": 2.5e-05,
"loss": 0.2261,
"step": 1300
},
{
"epoch": 11.4,
"learning_rate": 2.3161764705882354e-05,
"loss": 0.3138,
"step": 1305
},
{
"epoch": 11.44,
"learning_rate": 2.1323529411764707e-05,
"loss": 0.1571,
"step": 1310
},
{
"epoch": 11.48,
"learning_rate": 1.948529411764706e-05,
"loss": 0.2473,
"step": 1315
},
{
"epoch": 11.53,
"learning_rate": 1.7647058823529414e-05,
"loss": 0.2055,
"step": 1320
},
{
"epoch": 11.57,
"learning_rate": 1.5808823529411763e-05,
"loss": 0.2225,
"step": 1325
},
{
"epoch": 11.62,
"learning_rate": 1.3970588235294118e-05,
"loss": 0.2046,
"step": 1330
},
{
"epoch": 11.66,
"learning_rate": 1.2132352941176471e-05,
"loss": 0.1629,
"step": 1335
},
{
"epoch": 11.7,
"learning_rate": 1.0294117647058824e-05,
"loss": 0.2075,
"step": 1340
},
{
"epoch": 11.75,
"learning_rate": 8.455882352941177e-06,
"loss": 0.2251,
"step": 1345
},
{
"epoch": 11.79,
"learning_rate": 6.61764705882353e-06,
"loss": 0.1449,
"step": 1350
},
{
"epoch": 11.83,
"learning_rate": 4.779411764705882e-06,
"loss": 0.2342,
"step": 1355
},
{
"epoch": 11.88,
"learning_rate": 2.9411764705882355e-06,
"loss": 0.1518,
"step": 1360
},
{
"epoch": 11.92,
"learning_rate": 1.1029411764705884e-06,
"loss": 0.2026,
"step": 1365
},
{
"epoch": 11.95,
"eval_accuracy": 0.9852216748768473,
"eval_loss": 0.09461534023284912,
"eval_runtime": 41.5773,
"eval_samples_per_second": 29.295,
"eval_steps_per_second": 1.852,
"step": 1368
},
{
"epoch": 11.95,
"step": 1368,
"total_flos": 7.740923166391597e+18,
"train_loss": 0.8764253104900757,
"train_runtime": 6223.024,
"train_samples_per_second": 7.04,
"train_steps_per_second": 0.22
}
],
"max_steps": 1368,
"num_train_epochs": 12,
"total_flos": 7.740923166391597e+18,
"trial_name": null,
"trial_params": null
}