25-17 / trainer_state.json
AlekseyKorshuk's picture
huggingartists
14ac1f8
{
"best_metric": 1.6076909303665161,
"best_model_checkpoint": "output/25-17/checkpoint-1440",
"epoch": 9.0,
"global_step": 1440,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.0001368696722497127,
"loss": 2.507,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 0.0001358818702356616,
"loss": 2.2788,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.00013424610703122953,
"loss": 2.1702,
"step": 15
},
{
"epoch": 0.12,
"learning_rate": 0.00013197813593027427,
"loss": 2.0479,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.00012909979873429716,
"loss": 2.0181,
"step": 25
},
{
"epoch": 0.19,
"learning_rate": 0.0001256388154039546,
"loss": 2.0362,
"step": 30
},
{
"epoch": 0.22,
"learning_rate": 0.00012162851710068375,
"loss": 2.1176,
"step": 35
},
{
"epoch": 0.25,
"learning_rate": 0.00011710752518939715,
"loss": 1.9178,
"step": 40
},
{
"epoch": 0.28,
"learning_rate": 0.00011211937929362608,
"loss": 2.0539,
"step": 45
},
{
"epoch": 0.31,
"learning_rate": 0.00010671211798514472,
"loss": 1.9318,
"step": 50
},
{
"epoch": 0.34,
"learning_rate": 0.00010093781614626346,
"loss": 2.0317,
"step": 55
},
{
"epoch": 0.38,
"learning_rate": 9.485208346024516e-05,
"loss": 1.9618,
"step": 60
},
{
"epoch": 0.41,
"learning_rate": 8.851352885965611e-05,
"loss": 1.9205,
"step": 65
},
{
"epoch": 0.44,
"learning_rate": 8.19831960903064e-05,
"loss": 1.8521,
"step": 70
},
{
"epoch": 0.47,
"learning_rate": 7.532397582660788e-05,
"loss": 1.8699,
"step": 75
},
{
"epoch": 0.5,
"learning_rate": 6.86e-05,
"loss": 1.9852,
"step": 80
},
{
"epoch": 0.53,
"learning_rate": 6.187602417339214e-05,
"loss": 1.8576,
"step": 85
},
{
"epoch": 0.56,
"learning_rate": 5.52168039096936e-05,
"loss": 1.93,
"step": 90
},
{
"epoch": 0.59,
"learning_rate": 4.8686471140343896e-05,
"loss": 2.0017,
"step": 95
},
{
"epoch": 0.62,
"learning_rate": 4.2347916539754844e-05,
"loss": 1.9962,
"step": 100
},
{
"epoch": 0.66,
"learning_rate": 3.6262183853736556e-05,
"loss": 1.9731,
"step": 105
},
{
"epoch": 0.69,
"learning_rate": 3.0487882014855305e-05,
"loss": 1.9197,
"step": 110
},
{
"epoch": 0.72,
"learning_rate": 2.5080620706373927e-05,
"loss": 1.8595,
"step": 115
},
{
"epoch": 0.75,
"learning_rate": 2.0092474810602843e-05,
"loss": 1.925,
"step": 120
},
{
"epoch": 0.78,
"learning_rate": 1.557148289931624e-05,
"loss": 1.9259,
"step": 125
},
{
"epoch": 0.81,
"learning_rate": 1.1561184596045389e-05,
"loss": 1.8582,
"step": 130
},
{
"epoch": 0.84,
"learning_rate": 8.100201265702852e-06,
"loss": 1.8858,
"step": 135
},
{
"epoch": 0.88,
"learning_rate": 5.22186406972573e-06,
"loss": 1.8995,
"step": 140
},
{
"epoch": 0.91,
"learning_rate": 2.953892968770475e-06,
"loss": 1.9137,
"step": 145
},
{
"epoch": 0.94,
"learning_rate": 1.3181297643383925e-06,
"loss": 1.8872,
"step": 150
},
{
"epoch": 0.97,
"learning_rate": 3.303277502872983e-07,
"loss": 1.8137,
"step": 155
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.9111,
"step": 160
},
{
"epoch": 1.0,
"eval_loss": 1.8344975709915161,
"eval_runtime": 11.0703,
"eval_samples_per_second": 22.583,
"eval_steps_per_second": 2.891,
"step": 160
},
{
"epoch": 1.03,
"learning_rate": 3.303277502872907e-07,
"loss": 1.8983,
"step": 165
},
{
"epoch": 1.06,
"learning_rate": 1.3181297643383925e-06,
"loss": 1.8515,
"step": 170
},
{
"epoch": 1.09,
"learning_rate": 2.9538929687704672e-06,
"loss": 1.8853,
"step": 175
},
{
"epoch": 1.12,
"learning_rate": 5.2218640697257225e-06,
"loss": 1.8512,
"step": 180
},
{
"epoch": 1.16,
"learning_rate": 8.100201265702843e-06,
"loss": 1.8684,
"step": 185
},
{
"epoch": 1.19,
"learning_rate": 1.1561184596045382e-05,
"loss": 1.8168,
"step": 190
},
{
"epoch": 1.22,
"learning_rate": 1.5571482899316234e-05,
"loss": 1.876,
"step": 195
},
{
"epoch": 1.25,
"learning_rate": 2.009247481060283e-05,
"loss": 1.8544,
"step": 200
},
{
"epoch": 1.28,
"learning_rate": 2.508062070637389e-05,
"loss": 1.7766,
"step": 205
},
{
"epoch": 1.31,
"learning_rate": 3.048788201485529e-05,
"loss": 1.9737,
"step": 210
},
{
"epoch": 1.34,
"learning_rate": 3.626218385373654e-05,
"loss": 1.8173,
"step": 215
},
{
"epoch": 1.38,
"learning_rate": 4.234791653975481e-05,
"loss": 1.7998,
"step": 220
},
{
"epoch": 1.41,
"learning_rate": 4.8686471140343875e-05,
"loss": 1.8463,
"step": 225
},
{
"epoch": 1.44,
"learning_rate": 5.5216803909693576e-05,
"loss": 1.8385,
"step": 230
},
{
"epoch": 1.47,
"learning_rate": 6.187602417339216e-05,
"loss": 1.8556,
"step": 235
},
{
"epoch": 1.5,
"learning_rate": 6.859999999999999e-05,
"loss": 1.7617,
"step": 240
},
{
"epoch": 1.53,
"learning_rate": 7.532397582660782e-05,
"loss": 1.7911,
"step": 245
},
{
"epoch": 1.56,
"learning_rate": 8.19831960903064e-05,
"loss": 1.7528,
"step": 250
},
{
"epoch": 1.59,
"learning_rate": 8.85135288596561e-05,
"loss": 1.8805,
"step": 255
},
{
"epoch": 1.62,
"learning_rate": 9.485208346024518e-05,
"loss": 1.9808,
"step": 260
},
{
"epoch": 1.66,
"learning_rate": 0.00010093781614626343,
"loss": 1.8408,
"step": 265
},
{
"epoch": 1.69,
"learning_rate": 0.00010671211798514468,
"loss": 1.9133,
"step": 270
},
{
"epoch": 1.72,
"learning_rate": 0.00011211937929362609,
"loss": 1.8695,
"step": 275
},
{
"epoch": 1.75,
"learning_rate": 0.00011710752518939715,
"loss": 1.8373,
"step": 280
},
{
"epoch": 1.78,
"learning_rate": 0.00012162851710068373,
"loss": 1.7998,
"step": 285
},
{
"epoch": 1.81,
"learning_rate": 0.0001256388154039546,
"loss": 1.9473,
"step": 290
},
{
"epoch": 1.84,
"learning_rate": 0.00012909979873429716,
"loss": 1.8208,
"step": 295
},
{
"epoch": 1.88,
"learning_rate": 0.00013197813593027427,
"loss": 1.8304,
"step": 300
},
{
"epoch": 1.91,
"learning_rate": 0.00013424610703122953,
"loss": 1.7997,
"step": 305
},
{
"epoch": 1.94,
"learning_rate": 0.0001358818702356616,
"loss": 1.8045,
"step": 310
},
{
"epoch": 1.97,
"learning_rate": 0.0001368696722497127,
"loss": 1.8645,
"step": 315
},
{
"epoch": 2.0,
"learning_rate": 0.0001372,
"loss": 1.8994,
"step": 320
},
{
"epoch": 2.0,
"eval_loss": 1.8014581203460693,
"eval_runtime": 11.0626,
"eval_samples_per_second": 22.599,
"eval_steps_per_second": 2.893,
"step": 320
},
{
"epoch": 2.03,
"learning_rate": 0.0001368696722497127,
"loss": 1.7444,
"step": 325
},
{
"epoch": 2.06,
"learning_rate": 0.0001358818702356616,
"loss": 1.8609,
"step": 330
},
{
"epoch": 2.09,
"learning_rate": 0.00013424610703122953,
"loss": 1.6945,
"step": 335
},
{
"epoch": 2.12,
"learning_rate": 0.00013197813593027427,
"loss": 1.7166,
"step": 340
},
{
"epoch": 2.16,
"learning_rate": 0.00012909979873429716,
"loss": 1.738,
"step": 345
},
{
"epoch": 2.19,
"learning_rate": 0.0001256388154039546,
"loss": 1.8311,
"step": 350
},
{
"epoch": 2.22,
"learning_rate": 0.00012162851710068375,
"loss": 1.7936,
"step": 355
},
{
"epoch": 2.25,
"learning_rate": 0.00011710752518939717,
"loss": 1.7759,
"step": 360
},
{
"epoch": 2.28,
"learning_rate": 0.00011211937929362612,
"loss": 1.8082,
"step": 365
},
{
"epoch": 2.31,
"learning_rate": 0.00010671211798514472,
"loss": 1.7213,
"step": 370
},
{
"epoch": 2.34,
"learning_rate": 0.00010093781614626346,
"loss": 1.7968,
"step": 375
},
{
"epoch": 2.38,
"learning_rate": 9.48520834602452e-05,
"loss": 1.8208,
"step": 380
},
{
"epoch": 2.41,
"learning_rate": 8.851352885965613e-05,
"loss": 1.6572,
"step": 385
},
{
"epoch": 2.44,
"learning_rate": 8.198319609030645e-05,
"loss": 1.8122,
"step": 390
},
{
"epoch": 2.47,
"learning_rate": 7.532397582660786e-05,
"loss": 1.7665,
"step": 395
},
{
"epoch": 2.5,
"learning_rate": 6.860000000000001e-05,
"loss": 1.8777,
"step": 400
},
{
"epoch": 2.53,
"learning_rate": 6.187602417339219e-05,
"loss": 1.6834,
"step": 405
},
{
"epoch": 2.56,
"learning_rate": 5.5216803909693664e-05,
"loss": 1.7483,
"step": 410
},
{
"epoch": 2.59,
"learning_rate": 4.868647114034385e-05,
"loss": 1.6818,
"step": 415
},
{
"epoch": 2.62,
"learning_rate": 4.234791653975484e-05,
"loss": 1.7057,
"step": 420
},
{
"epoch": 2.66,
"learning_rate": 3.6262183853736576e-05,
"loss": 1.8172,
"step": 425
},
{
"epoch": 2.69,
"learning_rate": 3.0487882014855322e-05,
"loss": 1.7146,
"step": 430
},
{
"epoch": 2.72,
"learning_rate": 2.5080620706373965e-05,
"loss": 1.6912,
"step": 435
},
{
"epoch": 2.75,
"learning_rate": 2.0092474810602897e-05,
"loss": 1.7294,
"step": 440
},
{
"epoch": 2.78,
"learning_rate": 1.5571482899316234e-05,
"loss": 1.7523,
"step": 445
},
{
"epoch": 2.81,
"learning_rate": 1.1561184596045404e-05,
"loss": 1.768,
"step": 450
},
{
"epoch": 2.84,
"learning_rate": 8.100201265702858e-06,
"loss": 1.6234,
"step": 455
},
{
"epoch": 2.88,
"learning_rate": 5.221864069725753e-06,
"loss": 1.7473,
"step": 460
},
{
"epoch": 2.91,
"learning_rate": 2.9538929687704977e-06,
"loss": 1.8052,
"step": 465
},
{
"epoch": 2.94,
"learning_rate": 1.318129764338385e-06,
"loss": 1.6156,
"step": 470
},
{
"epoch": 2.97,
"learning_rate": 3.303277502872907e-07,
"loss": 1.6744,
"step": 475
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 1.7333,
"step": 480
},
{
"epoch": 3.0,
"eval_loss": 1.7123054265975952,
"eval_runtime": 11.0761,
"eval_samples_per_second": 22.571,
"eval_steps_per_second": 2.889,
"step": 480
},
{
"epoch": 3.03,
"learning_rate": 3.303277502872907e-07,
"loss": 1.6392,
"step": 485
},
{
"epoch": 3.06,
"learning_rate": 1.3181297643383773e-06,
"loss": 1.6924,
"step": 490
},
{
"epoch": 3.09,
"learning_rate": 2.9538929687704825e-06,
"loss": 1.667,
"step": 495
},
{
"epoch": 3.12,
"learning_rate": 5.22186406972573e-06,
"loss": 1.6132,
"step": 500
},
{
"epoch": 3.16,
"learning_rate": 8.100201265702836e-06,
"loss": 1.6915,
"step": 505
},
{
"epoch": 3.19,
"learning_rate": 1.1561184596045374e-05,
"loss": 1.6571,
"step": 510
},
{
"epoch": 3.22,
"learning_rate": 1.5571482899316204e-05,
"loss": 1.5234,
"step": 515
},
{
"epoch": 3.25,
"learning_rate": 2.0092474810602867e-05,
"loss": 1.6652,
"step": 520
},
{
"epoch": 3.28,
"learning_rate": 2.5080620706373927e-05,
"loss": 1.6542,
"step": 525
},
{
"epoch": 3.31,
"learning_rate": 3.0487882014855275e-05,
"loss": 1.6505,
"step": 530
},
{
"epoch": 3.34,
"learning_rate": 3.626218385373653e-05,
"loss": 1.6654,
"step": 535
},
{
"epoch": 3.38,
"learning_rate": 4.234791653975479e-05,
"loss": 1.8283,
"step": 540
},
{
"epoch": 3.41,
"learning_rate": 4.868647114034381e-05,
"loss": 1.6716,
"step": 545
},
{
"epoch": 3.44,
"learning_rate": 5.5216803909693624e-05,
"loss": 1.7675,
"step": 550
},
{
"epoch": 3.47,
"learning_rate": 6.187602417339214e-05,
"loss": 1.6728,
"step": 555
},
{
"epoch": 3.5,
"learning_rate": 6.859999999999997e-05,
"loss": 1.6103,
"step": 560
},
{
"epoch": 3.53,
"learning_rate": 7.53239758266078e-05,
"loss": 1.6445,
"step": 565
},
{
"epoch": 3.56,
"learning_rate": 8.198319609030632e-05,
"loss": 1.6708,
"step": 570
},
{
"epoch": 3.59,
"learning_rate": 8.851352885965614e-05,
"loss": 1.7189,
"step": 575
},
{
"epoch": 3.62,
"learning_rate": 9.485208346024516e-05,
"loss": 1.7617,
"step": 580
},
{
"epoch": 3.66,
"learning_rate": 0.00010093781614626343,
"loss": 1.6343,
"step": 585
},
{
"epoch": 3.69,
"learning_rate": 0.00010671211798514468,
"loss": 1.7267,
"step": 590
},
{
"epoch": 3.72,
"learning_rate": 0.00011211937929362604,
"loss": 1.6865,
"step": 595
},
{
"epoch": 3.75,
"learning_rate": 0.0001171075251893971,
"loss": 1.6896,
"step": 600
},
{
"epoch": 3.78,
"learning_rate": 0.00012162851710068375,
"loss": 1.716,
"step": 605
},
{
"epoch": 3.81,
"learning_rate": 0.0001256388154039546,
"loss": 1.7558,
"step": 610
},
{
"epoch": 3.84,
"learning_rate": 0.00012909979873429713,
"loss": 1.749,
"step": 615
},
{
"epoch": 3.88,
"learning_rate": 0.00013197813593027427,
"loss": 1.8024,
"step": 620
},
{
"epoch": 3.91,
"learning_rate": 0.0001342461070312295,
"loss": 1.6423,
"step": 625
},
{
"epoch": 3.94,
"learning_rate": 0.0001358818702356616,
"loss": 1.713,
"step": 630
},
{
"epoch": 3.97,
"learning_rate": 0.0001368696722497127,
"loss": 1.7649,
"step": 635
},
{
"epoch": 4.0,
"learning_rate": 0.0001372,
"loss": 1.5134,
"step": 640
},
{
"epoch": 4.0,
"eval_loss": 1.7136940956115723,
"eval_runtime": 11.1178,
"eval_samples_per_second": 22.487,
"eval_steps_per_second": 2.878,
"step": 640
},
{
"epoch": 4.03,
"learning_rate": 0.0001368696722497127,
"loss": 1.6853,
"step": 645
},
{
"epoch": 4.06,
"learning_rate": 0.00013588187023566163,
"loss": 1.6863,
"step": 650
},
{
"epoch": 4.09,
"learning_rate": 0.00013424610703122953,
"loss": 1.7064,
"step": 655
},
{
"epoch": 4.12,
"learning_rate": 0.00013197813593027427,
"loss": 1.6835,
"step": 660
},
{
"epoch": 4.16,
"learning_rate": 0.0001290997987342972,
"loss": 1.571,
"step": 665
},
{
"epoch": 4.19,
"learning_rate": 0.00012563881540395464,
"loss": 1.5507,
"step": 670
},
{
"epoch": 4.22,
"learning_rate": 0.00012162851710068381,
"loss": 1.5875,
"step": 675
},
{
"epoch": 4.25,
"learning_rate": 0.00011710752518939714,
"loss": 1.705,
"step": 680
},
{
"epoch": 4.28,
"learning_rate": 0.00011211937929362608,
"loss": 1.6864,
"step": 685
},
{
"epoch": 4.31,
"learning_rate": 0.00010671211798514474,
"loss": 1.6228,
"step": 690
},
{
"epoch": 4.34,
"learning_rate": 0.00010093781614626347,
"loss": 1.6698,
"step": 695
},
{
"epoch": 4.38,
"learning_rate": 9.485208346024522e-05,
"loss": 1.4768,
"step": 700
},
{
"epoch": 4.41,
"learning_rate": 8.851352885965621e-05,
"loss": 1.636,
"step": 705
},
{
"epoch": 4.44,
"learning_rate": 8.198319609030639e-05,
"loss": 1.6327,
"step": 710
},
{
"epoch": 4.47,
"learning_rate": 7.532397582660788e-05,
"loss": 1.6404,
"step": 715
},
{
"epoch": 4.5,
"learning_rate": 6.860000000000003e-05,
"loss": 1.7279,
"step": 720
},
{
"epoch": 4.53,
"learning_rate": 6.18760241733922e-05,
"loss": 1.5857,
"step": 725
},
{
"epoch": 4.56,
"learning_rate": 5.5216803909693685e-05,
"loss": 1.5979,
"step": 730
},
{
"epoch": 4.59,
"learning_rate": 4.8686471140343875e-05,
"loss": 1.5906,
"step": 735
},
{
"epoch": 4.62,
"learning_rate": 4.234791653975485e-05,
"loss": 1.6215,
"step": 740
},
{
"epoch": 4.66,
"learning_rate": 3.626218385373659e-05,
"loss": 1.6579,
"step": 745
},
{
"epoch": 4.69,
"learning_rate": 3.0487882014855336e-05,
"loss": 1.6602,
"step": 750
},
{
"epoch": 4.72,
"learning_rate": 2.508062070637398e-05,
"loss": 1.6282,
"step": 755
},
{
"epoch": 4.75,
"learning_rate": 2.0092474810602914e-05,
"loss": 1.652,
"step": 760
},
{
"epoch": 4.78,
"learning_rate": 1.557148289931624e-05,
"loss": 1.5612,
"step": 765
},
{
"epoch": 4.81,
"learning_rate": 1.1561184596045413e-05,
"loss": 1.6313,
"step": 770
},
{
"epoch": 4.84,
"learning_rate": 8.100201265702867e-06,
"loss": 1.5685,
"step": 775
},
{
"epoch": 4.88,
"learning_rate": 5.221864069725753e-06,
"loss": 1.6143,
"step": 780
},
{
"epoch": 4.91,
"learning_rate": 2.9538929687704977e-06,
"loss": 1.5863,
"step": 785
},
{
"epoch": 4.94,
"learning_rate": 1.3181297643383925e-06,
"loss": 1.4505,
"step": 790
},
{
"epoch": 4.97,
"learning_rate": 3.303277502872983e-07,
"loss": 1.6715,
"step": 795
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 1.5892,
"step": 800
},
{
"epoch": 5.0,
"eval_loss": 1.6500141620635986,
"eval_runtime": 11.0924,
"eval_samples_per_second": 22.538,
"eval_steps_per_second": 2.885,
"step": 800
},
{
"epoch": 5.03,
"learning_rate": 3.303277502872907e-07,
"loss": 1.4254,
"step": 805
},
{
"epoch": 5.06,
"learning_rate": 1.3181297643383773e-06,
"loss": 1.5428,
"step": 810
},
{
"epoch": 5.09,
"learning_rate": 2.9538929687704367e-06,
"loss": 1.5335,
"step": 815
},
{
"epoch": 5.12,
"learning_rate": 5.221864069725677e-06,
"loss": 1.5308,
"step": 820
},
{
"epoch": 5.16,
"learning_rate": 8.100201265702767e-06,
"loss": 1.5882,
"step": 825
},
{
"epoch": 5.19,
"learning_rate": 1.1561184596045435e-05,
"loss": 1.5799,
"step": 830
},
{
"epoch": 5.22,
"learning_rate": 1.5571482899316272e-05,
"loss": 1.5356,
"step": 835
},
{
"epoch": 5.25,
"learning_rate": 2.0092474810602853e-05,
"loss": 1.5285,
"step": 840
},
{
"epoch": 5.28,
"learning_rate": 2.5080620706373914e-05,
"loss": 1.5356,
"step": 845
},
{
"epoch": 5.31,
"learning_rate": 3.048788201485526e-05,
"loss": 1.5041,
"step": 850
},
{
"epoch": 5.34,
"learning_rate": 3.6262183853736515e-05,
"loss": 1.5689,
"step": 855
},
{
"epoch": 5.38,
"learning_rate": 4.2347916539754777e-05,
"loss": 1.4609,
"step": 860
},
{
"epoch": 5.41,
"learning_rate": 4.868647114034379e-05,
"loss": 1.6113,
"step": 865
},
{
"epoch": 5.44,
"learning_rate": 5.521680390969348e-05,
"loss": 1.6169,
"step": 870
},
{
"epoch": 5.47,
"learning_rate": 6.1876024173392e-05,
"loss": 1.6431,
"step": 875
},
{
"epoch": 5.5,
"learning_rate": 6.859999999999984e-05,
"loss": 1.5976,
"step": 880
},
{
"epoch": 5.53,
"learning_rate": 7.532397582660791e-05,
"loss": 1.5969,
"step": 885
},
{
"epoch": 5.56,
"learning_rate": 8.198319609030643e-05,
"loss": 1.5681,
"step": 890
},
{
"epoch": 5.59,
"learning_rate": 8.851352885965613e-05,
"loss": 1.6318,
"step": 895
},
{
"epoch": 5.62,
"learning_rate": 9.485208346024515e-05,
"loss": 1.5222,
"step": 900
},
{
"epoch": 5.66,
"learning_rate": 0.00010093781614626339,
"loss": 1.5517,
"step": 905
},
{
"epoch": 5.69,
"learning_rate": 0.00010671211798514466,
"loss": 1.5481,
"step": 910
},
{
"epoch": 5.72,
"learning_rate": 0.00011211937929362601,
"loss": 1.6196,
"step": 915
},
{
"epoch": 5.75,
"learning_rate": 0.00011710752518939709,
"loss": 1.488,
"step": 920
},
{
"epoch": 5.78,
"learning_rate": 0.00012162851710068368,
"loss": 1.6155,
"step": 925
},
{
"epoch": 5.81,
"learning_rate": 0.00012563881540395453,
"loss": 1.628,
"step": 930
},
{
"epoch": 5.84,
"learning_rate": 0.0001290997987342972,
"loss": 1.6143,
"step": 935
},
{
"epoch": 5.88,
"learning_rate": 0.0001319781359302743,
"loss": 1.6028,
"step": 940
},
{
"epoch": 5.91,
"learning_rate": 0.00013424610703122953,
"loss": 1.4802,
"step": 945
},
{
"epoch": 5.94,
"learning_rate": 0.0001358818702356616,
"loss": 1.6464,
"step": 950
},
{
"epoch": 5.97,
"learning_rate": 0.0001368696722497127,
"loss": 1.6216,
"step": 955
},
{
"epoch": 6.0,
"learning_rate": 0.0001372,
"loss": 1.5782,
"step": 960
},
{
"epoch": 6.0,
"eval_loss": 1.6669092178344727,
"eval_runtime": 11.103,
"eval_samples_per_second": 22.517,
"eval_steps_per_second": 2.882,
"step": 960
},
{
"epoch": 6.03,
"learning_rate": 0.00013686967224971273,
"loss": 1.4996,
"step": 965
},
{
"epoch": 6.06,
"learning_rate": 0.00013588187023566163,
"loss": 1.5676,
"step": 970
},
{
"epoch": 6.09,
"learning_rate": 0.00013424610703122958,
"loss": 1.4658,
"step": 975
},
{
"epoch": 6.12,
"learning_rate": 0.00013197813593027432,
"loss": 1.4962,
"step": 980
},
{
"epoch": 6.16,
"learning_rate": 0.00012909979873429724,
"loss": 1.5933,
"step": 985
},
{
"epoch": 6.19,
"learning_rate": 0.00012563881540395458,
"loss": 1.4505,
"step": 990
},
{
"epoch": 6.22,
"learning_rate": 0.00012162851710068373,
"loss": 1.5865,
"step": 995
},
{
"epoch": 6.25,
"learning_rate": 0.00011710752518939715,
"loss": 1.665,
"step": 1000
},
{
"epoch": 6.28,
"learning_rate": 0.00011211937929362609,
"loss": 1.556,
"step": 1005
},
{
"epoch": 6.31,
"learning_rate": 0.00010671211798514474,
"loss": 1.5632,
"step": 1010
},
{
"epoch": 6.34,
"learning_rate": 0.00010093781614626349,
"loss": 1.5849,
"step": 1015
},
{
"epoch": 6.38,
"learning_rate": 9.485208346024524e-05,
"loss": 1.5667,
"step": 1020
},
{
"epoch": 6.41,
"learning_rate": 8.851352885965622e-05,
"loss": 1.4537,
"step": 1025
},
{
"epoch": 6.44,
"learning_rate": 8.198319609030653e-05,
"loss": 1.4866,
"step": 1030
},
{
"epoch": 6.47,
"learning_rate": 7.532397582660802e-05,
"loss": 1.4058,
"step": 1035
},
{
"epoch": 6.5,
"learning_rate": 6.859999999999993e-05,
"loss": 1.4442,
"step": 1040
},
{
"epoch": 6.53,
"learning_rate": 6.18760241733921e-05,
"loss": 1.4465,
"step": 1045
},
{
"epoch": 6.56,
"learning_rate": 5.5216803909693576e-05,
"loss": 1.5129,
"step": 1050
},
{
"epoch": 6.59,
"learning_rate": 4.868647114034389e-05,
"loss": 1.4484,
"step": 1055
},
{
"epoch": 6.62,
"learning_rate": 4.2347916539754865e-05,
"loss": 1.6054,
"step": 1060
},
{
"epoch": 6.66,
"learning_rate": 3.62621838537366e-05,
"loss": 1.6134,
"step": 1065
},
{
"epoch": 6.69,
"learning_rate": 3.0487882014855342e-05,
"loss": 1.4736,
"step": 1070
},
{
"epoch": 6.72,
"learning_rate": 2.5080620706373995e-05,
"loss": 1.5124,
"step": 1075
},
{
"epoch": 6.75,
"learning_rate": 2.009247481060292e-05,
"loss": 1.528,
"step": 1080
},
{
"epoch": 6.78,
"learning_rate": 1.5571482899316333e-05,
"loss": 1.602,
"step": 1085
},
{
"epoch": 6.81,
"learning_rate": 1.1561184596045489e-05,
"loss": 1.5229,
"step": 1090
},
{
"epoch": 6.84,
"learning_rate": 8.100201265702821e-06,
"loss": 1.5871,
"step": 1095
},
{
"epoch": 6.88,
"learning_rate": 5.221864069725715e-06,
"loss": 1.5468,
"step": 1100
},
{
"epoch": 6.91,
"learning_rate": 2.9538929687704672e-06,
"loss": 1.4325,
"step": 1105
},
{
"epoch": 6.94,
"learning_rate": 1.3181297643383925e-06,
"loss": 1.5777,
"step": 1110
},
{
"epoch": 6.97,
"learning_rate": 3.303277502872983e-07,
"loss": 1.5088,
"step": 1115
},
{
"epoch": 7.0,
"learning_rate": 0.0,
"loss": 1.4601,
"step": 1120
},
{
"epoch": 7.0,
"eval_loss": 1.6244831085205078,
"eval_runtime": 11.094,
"eval_samples_per_second": 22.535,
"eval_steps_per_second": 2.884,
"step": 1120
},
{
"epoch": 7.03,
"learning_rate": 3.303277502872831e-07,
"loss": 1.487,
"step": 1125
},
{
"epoch": 7.06,
"learning_rate": 1.3181297643383697e-06,
"loss": 1.4971,
"step": 1130
},
{
"epoch": 7.09,
"learning_rate": 2.9538929687704367e-06,
"loss": 1.4361,
"step": 1135
},
{
"epoch": 7.12,
"learning_rate": 5.221864069725669e-06,
"loss": 1.4751,
"step": 1140
},
{
"epoch": 7.16,
"learning_rate": 8.10020126570276e-06,
"loss": 1.3822,
"step": 1145
},
{
"epoch": 7.19,
"learning_rate": 1.156118459604542e-05,
"loss": 1.4882,
"step": 1150
},
{
"epoch": 7.22,
"learning_rate": 1.5571482899316258e-05,
"loss": 1.4465,
"step": 1155
},
{
"epoch": 7.25,
"learning_rate": 2.0092474810602836e-05,
"loss": 1.3924,
"step": 1160
},
{
"epoch": 7.28,
"learning_rate": 2.5080620706373904e-05,
"loss": 1.4828,
"step": 1165
},
{
"epoch": 7.31,
"learning_rate": 3.0487882014855254e-05,
"loss": 1.4428,
"step": 1170
},
{
"epoch": 7.34,
"learning_rate": 3.6262183853736495e-05,
"loss": 1.6162,
"step": 1175
},
{
"epoch": 7.38,
"learning_rate": 4.234791653975476e-05,
"loss": 1.368,
"step": 1180
},
{
"epoch": 7.41,
"learning_rate": 4.868647114034377e-05,
"loss": 1.4922,
"step": 1185
},
{
"epoch": 7.44,
"learning_rate": 5.521680390969347e-05,
"loss": 1.4195,
"step": 1190
},
{
"epoch": 7.47,
"learning_rate": 6.187602417339198e-05,
"loss": 1.4896,
"step": 1195
},
{
"epoch": 7.5,
"learning_rate": 6.859999999999982e-05,
"loss": 1.4594,
"step": 1200
},
{
"epoch": 7.53,
"learning_rate": 7.53239758266079e-05,
"loss": 1.4228,
"step": 1205
},
{
"epoch": 7.56,
"learning_rate": 8.19831960903064e-05,
"loss": 1.4571,
"step": 1210
},
{
"epoch": 7.59,
"learning_rate": 8.851352885965611e-05,
"loss": 1.4634,
"step": 1215
},
{
"epoch": 7.62,
"learning_rate": 9.485208346024514e-05,
"loss": 1.5054,
"step": 1220
},
{
"epoch": 7.66,
"learning_rate": 0.00010093781614626339,
"loss": 1.4162,
"step": 1225
},
{
"epoch": 7.69,
"learning_rate": 0.00010671211798514465,
"loss": 1.5479,
"step": 1230
},
{
"epoch": 7.72,
"learning_rate": 0.00011211937929362601,
"loss": 1.4107,
"step": 1235
},
{
"epoch": 7.75,
"learning_rate": 0.00011710752518939706,
"loss": 1.4738,
"step": 1240
},
{
"epoch": 7.78,
"learning_rate": 0.00012162851710068366,
"loss": 1.4738,
"step": 1245
},
{
"epoch": 7.81,
"learning_rate": 0.0001256388154039545,
"loss": 1.497,
"step": 1250
},
{
"epoch": 7.84,
"learning_rate": 0.0001290997987342972,
"loss": 1.5329,
"step": 1255
},
{
"epoch": 7.88,
"learning_rate": 0.0001319781359302743,
"loss": 1.4608,
"step": 1260
},
{
"epoch": 7.91,
"learning_rate": 0.00013424610703122953,
"loss": 1.5795,
"step": 1265
},
{
"epoch": 7.94,
"learning_rate": 0.0001358818702356616,
"loss": 1.5419,
"step": 1270
},
{
"epoch": 7.97,
"learning_rate": 0.0001368696722497127,
"loss": 1.4443,
"step": 1275
},
{
"epoch": 8.0,
"learning_rate": 0.0001372,
"loss": 1.4799,
"step": 1280
},
{
"epoch": 8.0,
"eval_loss": 1.6402026414871216,
"eval_runtime": 11.1984,
"eval_samples_per_second": 22.325,
"eval_steps_per_second": 2.858,
"step": 1280
},
{
"epoch": 8.03,
"learning_rate": 0.00013686967224971273,
"loss": 1.4584,
"step": 1285
},
{
"epoch": 8.06,
"learning_rate": 0.00013588187023566163,
"loss": 1.4089,
"step": 1290
},
{
"epoch": 8.09,
"learning_rate": 0.00013424610703122958,
"loss": 1.55,
"step": 1295
},
{
"epoch": 8.12,
"learning_rate": 0.00013197813593027432,
"loss": 1.4449,
"step": 1300
},
{
"epoch": 8.16,
"learning_rate": 0.00012909979873429724,
"loss": 1.367,
"step": 1305
},
{
"epoch": 8.19,
"learning_rate": 0.00012563881540395458,
"loss": 1.5241,
"step": 1310
},
{
"epoch": 8.22,
"learning_rate": 0.00012162851710068375,
"loss": 1.5117,
"step": 1315
},
{
"epoch": 8.25,
"learning_rate": 0.00011710752518939715,
"loss": 1.4418,
"step": 1320
},
{
"epoch": 8.28,
"learning_rate": 0.00011211937929362609,
"loss": 1.5439,
"step": 1325
},
{
"epoch": 8.31,
"learning_rate": 0.00010671211798514476,
"loss": 1.3722,
"step": 1330
},
{
"epoch": 8.34,
"learning_rate": 0.0001009378161462635,
"loss": 1.4284,
"step": 1335
},
{
"epoch": 8.38,
"learning_rate": 9.485208346024526e-05,
"loss": 1.516,
"step": 1340
},
{
"epoch": 8.41,
"learning_rate": 8.851352885965623e-05,
"loss": 1.3386,
"step": 1345
},
{
"epoch": 8.44,
"learning_rate": 8.198319609030655e-05,
"loss": 1.4559,
"step": 1350
},
{
"epoch": 8.47,
"learning_rate": 7.532397582660803e-05,
"loss": 1.6084,
"step": 1355
},
{
"epoch": 8.5,
"learning_rate": 6.859999999999995e-05,
"loss": 1.4138,
"step": 1360
},
{
"epoch": 8.53,
"learning_rate": 6.187602417339212e-05,
"loss": 1.3939,
"step": 1365
},
{
"epoch": 8.56,
"learning_rate": 5.5216803909693596e-05,
"loss": 1.4058,
"step": 1370
},
{
"epoch": 8.59,
"learning_rate": 4.86864711403439e-05,
"loss": 1.4439,
"step": 1375
},
{
"epoch": 8.62,
"learning_rate": 4.2347916539754885e-05,
"loss": 1.345,
"step": 1380
},
{
"epoch": 8.66,
"learning_rate": 3.626218385373662e-05,
"loss": 1.4172,
"step": 1385
},
{
"epoch": 8.69,
"learning_rate": 3.048788201485536e-05,
"loss": 1.4024,
"step": 1390
},
{
"epoch": 8.72,
"learning_rate": 2.5080620706374002e-05,
"loss": 1.4443,
"step": 1395
},
{
"epoch": 8.75,
"learning_rate": 2.0092474810602934e-05,
"loss": 1.4758,
"step": 1400
},
{
"epoch": 8.78,
"learning_rate": 1.5571482899316343e-05,
"loss": 1.4565,
"step": 1405
},
{
"epoch": 8.81,
"learning_rate": 1.1561184596045496e-05,
"loss": 1.3571,
"step": 1410
},
{
"epoch": 8.84,
"learning_rate": 8.100201265702828e-06,
"loss": 1.478,
"step": 1415
},
{
"epoch": 8.88,
"learning_rate": 5.2218640697257225e-06,
"loss": 1.452,
"step": 1420
},
{
"epoch": 8.91,
"learning_rate": 2.953892968770475e-06,
"loss": 1.3222,
"step": 1425
},
{
"epoch": 8.94,
"learning_rate": 1.3181297643384001e-06,
"loss": 1.426,
"step": 1430
},
{
"epoch": 8.97,
"learning_rate": 3.303277502872983e-07,
"loss": 1.4787,
"step": 1435
},
{
"epoch": 9.0,
"learning_rate": 0.0,
"loss": 1.353,
"step": 1440
},
{
"epoch": 9.0,
"eval_loss": 1.6076909303665161,
"eval_runtime": 11.1829,
"eval_samples_per_second": 22.355,
"eval_steps_per_second": 2.862,
"step": 1440
}
],
"max_steps": 1600,
"num_train_epochs": 10,
"total_flos": 1505042104320000.0,
"trial_name": null,
"trial_params": null
}