big-baby-tape / trainer_state.json
AlekseyKorshuk's picture
huggingartists
df35c33
{
"best_metric": 1.5916674137115479,
"best_model_checkpoint": "output/big-baby-tape/checkpoint-1040",
"epoch": 8.0,
"global_step": 1040,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 5.001712368734975e-07,
"loss": 1.923,
"step": 5
},
{
"epoch": 0.08,
"learning_rate": 1.9933913245728244e-06,
"loss": 2.0321,
"step": 10
},
{
"epoch": 0.12,
"learning_rate": 4.457885751780542e-06,
"loss": 2.0426,
"step": 15
},
{
"epoch": 0.15,
"learning_rate": 7.857716640189785e-06,
"loss": 2.0776,
"step": 20
},
{
"epoch": 0.19,
"learning_rate": 1.2143306799695167e-05,
"loss": 1.9711,
"step": 25
},
{
"epoch": 0.23,
"learning_rate": 1.7252162675462473e-05,
"loss": 2.0637,
"step": 30
},
{
"epoch": 0.27,
"learning_rate": 2.3109785644681427e-05,
"loss": 1.8713,
"step": 35
},
{
"epoch": 0.31,
"learning_rate": 2.9630758374242703e-05,
"loss": 2.088,
"step": 40
},
{
"epoch": 0.35,
"learning_rate": 3.671999039779749e-05,
"loss": 1.9995,
"step": 45
},
{
"epoch": 0.38,
"learning_rate": 4.427410474888204e-05,
"loss": 2.0004,
"step": 50
},
{
"epoch": 0.42,
"learning_rate": 5.218294542987354e-05,
"loss": 1.9791,
"step": 55
},
{
"epoch": 0.46,
"learning_rate": 6.03311837344848e-05,
"loss": 1.882,
"step": 60
},
{
"epoch": 0.5,
"learning_rate": 6.859999999999999e-05,
"loss": 1.8736,
"step": 65
},
{
"epoch": 0.54,
"learning_rate": 7.686881626551516e-05,
"loss": 1.9173,
"step": 70
},
{
"epoch": 0.58,
"learning_rate": 8.501705457012643e-05,
"loss": 2.0122,
"step": 75
},
{
"epoch": 0.62,
"learning_rate": 9.292589525111794e-05,
"loss": 1.871,
"step": 80
},
{
"epoch": 0.65,
"learning_rate": 0.00010048000960220248,
"loss": 2.0619,
"step": 85
},
{
"epoch": 0.69,
"learning_rate": 0.00010756924162575728,
"loss": 1.9238,
"step": 90
},
{
"epoch": 0.73,
"learning_rate": 0.00011409021435531856,
"loss": 2.0238,
"step": 95
},
{
"epoch": 0.77,
"learning_rate": 0.0001199478373245375,
"loss": 1.9745,
"step": 100
},
{
"epoch": 0.81,
"learning_rate": 0.00012505669320030482,
"loss": 1.9809,
"step": 105
},
{
"epoch": 0.85,
"learning_rate": 0.0001293422833598102,
"loss": 1.8881,
"step": 110
},
{
"epoch": 0.88,
"learning_rate": 0.00013274211424821946,
"loss": 1.8788,
"step": 115
},
{
"epoch": 0.92,
"learning_rate": 0.00013520660867542716,
"loss": 1.984,
"step": 120
},
{
"epoch": 0.96,
"learning_rate": 0.00013669982876312649,
"loss": 1.9443,
"step": 125
},
{
"epoch": 1.0,
"learning_rate": 0.0001372,
"loss": 1.9006,
"step": 130
},
{
"epoch": 1.0,
"eval_loss": 1.9121332168579102,
"eval_runtime": 9.6453,
"eval_samples_per_second": 20.217,
"eval_steps_per_second": 2.592,
"step": 130
},
{
"epoch": 1.04,
"learning_rate": 0.0001366998287631265,
"loss": 1.8831,
"step": 135
},
{
"epoch": 1.08,
"learning_rate": 0.00013520660867542716,
"loss": 1.8547,
"step": 140
},
{
"epoch": 1.12,
"learning_rate": 0.00013274211424821946,
"loss": 1.87,
"step": 145
},
{
"epoch": 1.15,
"learning_rate": 0.00012934228335981023,
"loss": 1.8612,
"step": 150
},
{
"epoch": 1.19,
"learning_rate": 0.00012505669320030482,
"loss": 1.7875,
"step": 155
},
{
"epoch": 1.23,
"learning_rate": 0.00011994783732453754,
"loss": 1.8327,
"step": 160
},
{
"epoch": 1.27,
"learning_rate": 0.00011409021435531858,
"loss": 1.9541,
"step": 165
},
{
"epoch": 1.31,
"learning_rate": 0.00010756924162575734,
"loss": 1.8205,
"step": 170
},
{
"epoch": 1.35,
"learning_rate": 0.00010048000960220251,
"loss": 1.8993,
"step": 175
},
{
"epoch": 1.38,
"learning_rate": 9.292589525111797e-05,
"loss": 1.8431,
"step": 180
},
{
"epoch": 1.42,
"learning_rate": 8.501705457012652e-05,
"loss": 1.8127,
"step": 185
},
{
"epoch": 1.46,
"learning_rate": 7.686881626551514e-05,
"loss": 1.8428,
"step": 190
},
{
"epoch": 1.5,
"learning_rate": 6.860000000000001e-05,
"loss": 1.7509,
"step": 195
},
{
"epoch": 1.54,
"learning_rate": 6.03311837344849e-05,
"loss": 1.7859,
"step": 200
},
{
"epoch": 1.58,
"learning_rate": 5.218294542987351e-05,
"loss": 1.8358,
"step": 205
},
{
"epoch": 1.62,
"learning_rate": 4.427410474888207e-05,
"loss": 1.7393,
"step": 210
},
{
"epoch": 1.65,
"learning_rate": 3.6719990397797524e-05,
"loss": 1.8051,
"step": 215
},
{
"epoch": 1.69,
"learning_rate": 2.9630758374242683e-05,
"loss": 1.8083,
"step": 220
},
{
"epoch": 1.73,
"learning_rate": 2.310978564468145e-05,
"loss": 1.7062,
"step": 225
},
{
"epoch": 1.77,
"learning_rate": 1.7252162675462497e-05,
"loss": 1.7829,
"step": 230
},
{
"epoch": 1.81,
"learning_rate": 1.214330679969522e-05,
"loss": 1.7874,
"step": 235
},
{
"epoch": 1.85,
"learning_rate": 7.8577166401898e-06,
"loss": 1.8435,
"step": 240
},
{
"epoch": 1.88,
"learning_rate": 4.457885751780558e-06,
"loss": 1.8288,
"step": 245
},
{
"epoch": 1.92,
"learning_rate": 1.9933913245728472e-06,
"loss": 1.7984,
"step": 250
},
{
"epoch": 1.96,
"learning_rate": 5.001712368734975e-07,
"loss": 1.8331,
"step": 255
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 1.8175,
"step": 260
},
{
"epoch": 2.0,
"eval_loss": 1.8163535594940186,
"eval_runtime": 9.657,
"eval_samples_per_second": 20.193,
"eval_steps_per_second": 2.589,
"step": 260
},
{
"epoch": 2.04,
"learning_rate": 5.001712368734899e-07,
"loss": 1.7297,
"step": 265
},
{
"epoch": 2.08,
"learning_rate": 1.9933913245728396e-06,
"loss": 1.5719,
"step": 270
},
{
"epoch": 2.12,
"learning_rate": 4.457885751780535e-06,
"loss": 1.7261,
"step": 275
},
{
"epoch": 2.15,
"learning_rate": 7.857716640189778e-06,
"loss": 1.6366,
"step": 280
},
{
"epoch": 2.19,
"learning_rate": 1.2143306799695189e-05,
"loss": 1.8032,
"step": 285
},
{
"epoch": 2.23,
"learning_rate": 1.725216267546246e-05,
"loss": 1.8041,
"step": 290
},
{
"epoch": 2.27,
"learning_rate": 2.310978564468141e-05,
"loss": 1.752,
"step": 295
},
{
"epoch": 2.31,
"learning_rate": 2.9630758374242642e-05,
"loss": 1.831,
"step": 300
},
{
"epoch": 2.35,
"learning_rate": 3.671999039779748e-05,
"loss": 1.6489,
"step": 305
},
{
"epoch": 2.38,
"learning_rate": 4.427410474888202e-05,
"loss": 1.7224,
"step": 310
},
{
"epoch": 2.42,
"learning_rate": 5.218294542987346e-05,
"loss": 1.6862,
"step": 315
},
{
"epoch": 2.46,
"learning_rate": 6.033118373448485e-05,
"loss": 1.7129,
"step": 320
},
{
"epoch": 2.5,
"learning_rate": 6.859999999999997e-05,
"loss": 1.9049,
"step": 325
},
{
"epoch": 2.54,
"learning_rate": 7.68688162655151e-05,
"loss": 1.8259,
"step": 330
},
{
"epoch": 2.58,
"learning_rate": 8.501705457012648e-05,
"loss": 1.7537,
"step": 335
},
{
"epoch": 2.62,
"learning_rate": 9.292589525111793e-05,
"loss": 1.7193,
"step": 340
},
{
"epoch": 2.65,
"learning_rate": 0.00010048000960220248,
"loss": 1.7921,
"step": 345
},
{
"epoch": 2.69,
"learning_rate": 0.00010756924162575731,
"loss": 1.7727,
"step": 350
},
{
"epoch": 2.73,
"learning_rate": 0.00011409021435531856,
"loss": 1.8267,
"step": 355
},
{
"epoch": 2.77,
"learning_rate": 0.0001199478373245375,
"loss": 1.6066,
"step": 360
},
{
"epoch": 2.81,
"learning_rate": 0.0001250566932003048,
"loss": 1.757,
"step": 365
},
{
"epoch": 2.85,
"learning_rate": 0.00012934228335981018,
"loss": 1.7909,
"step": 370
},
{
"epoch": 2.88,
"learning_rate": 0.00013274211424821943,
"loss": 1.7481,
"step": 375
},
{
"epoch": 2.92,
"learning_rate": 0.00013520660867542716,
"loss": 1.7786,
"step": 380
},
{
"epoch": 2.96,
"learning_rate": 0.00013669982876312649,
"loss": 1.689,
"step": 385
},
{
"epoch": 3.0,
"learning_rate": 0.0001372,
"loss": 1.7754,
"step": 390
},
{
"epoch": 3.0,
"eval_loss": 1.8065567016601562,
"eval_runtime": 9.6575,
"eval_samples_per_second": 20.192,
"eval_steps_per_second": 2.589,
"step": 390
},
{
"epoch": 3.04,
"learning_rate": 0.0001366998287631265,
"loss": 1.6829,
"step": 395
},
{
"epoch": 3.08,
"learning_rate": 0.0001352066086754272,
"loss": 1.7295,
"step": 400
},
{
"epoch": 3.12,
"learning_rate": 0.0001327421142482195,
"loss": 1.6853,
"step": 405
},
{
"epoch": 3.15,
"learning_rate": 0.00012934228335981015,
"loss": 1.7343,
"step": 410
},
{
"epoch": 3.19,
"learning_rate": 0.00012505669320030482,
"loss": 1.7685,
"step": 415
},
{
"epoch": 3.23,
"learning_rate": 0.00011994783732453755,
"loss": 1.6945,
"step": 420
},
{
"epoch": 3.27,
"learning_rate": 0.00011409021435531858,
"loss": 1.7482,
"step": 425
},
{
"epoch": 3.31,
"learning_rate": 0.00010756924162575738,
"loss": 1.5529,
"step": 430
},
{
"epoch": 3.35,
"learning_rate": 0.00010048000960220263,
"loss": 1.7141,
"step": 435
},
{
"epoch": 3.38,
"learning_rate": 9.292589525111788e-05,
"loss": 1.6804,
"step": 440
},
{
"epoch": 3.42,
"learning_rate": 8.501705457012643e-05,
"loss": 1.7525,
"step": 445
},
{
"epoch": 3.46,
"learning_rate": 7.686881626551516e-05,
"loss": 1.6325,
"step": 450
},
{
"epoch": 3.5,
"learning_rate": 6.860000000000003e-05,
"loss": 1.6941,
"step": 455
},
{
"epoch": 3.54,
"learning_rate": 6.033118373448492e-05,
"loss": 1.5753,
"step": 460
},
{
"epoch": 3.58,
"learning_rate": 5.218294542987365e-05,
"loss": 1.6565,
"step": 465
},
{
"epoch": 3.62,
"learning_rate": 4.42741047488822e-05,
"loss": 1.6553,
"step": 470
},
{
"epoch": 3.65,
"learning_rate": 3.671999039779743e-05,
"loss": 1.5705,
"step": 475
},
{
"epoch": 3.69,
"learning_rate": 2.9630758374242696e-05,
"loss": 1.7043,
"step": 480
},
{
"epoch": 3.73,
"learning_rate": 2.3109785644681465e-05,
"loss": 1.5999,
"step": 485
},
{
"epoch": 3.77,
"learning_rate": 1.7252162675462504e-05,
"loss": 1.675,
"step": 490
},
{
"epoch": 3.81,
"learning_rate": 1.2143306799695228e-05,
"loss": 1.6187,
"step": 495
},
{
"epoch": 3.85,
"learning_rate": 7.857716640189861e-06,
"loss": 1.5483,
"step": 500
},
{
"epoch": 3.88,
"learning_rate": 4.4578857517805195e-06,
"loss": 1.6583,
"step": 505
},
{
"epoch": 3.92,
"learning_rate": 1.9933913245728244e-06,
"loss": 1.6295,
"step": 510
},
{
"epoch": 3.96,
"learning_rate": 5.001712368734975e-07,
"loss": 1.5502,
"step": 515
},
{
"epoch": 4.0,
"learning_rate": 0.0,
"loss": 1.7657,
"step": 520
},
{
"epoch": 4.0,
"eval_loss": 1.7459986209869385,
"eval_runtime": 9.6571,
"eval_samples_per_second": 20.192,
"eval_steps_per_second": 2.589,
"step": 520
},
{
"epoch": 4.04,
"learning_rate": 5.001712368734899e-07,
"loss": 1.7425,
"step": 525
},
{
"epoch": 4.08,
"learning_rate": 1.9933913245728015e-06,
"loss": 1.6693,
"step": 530
},
{
"epoch": 4.12,
"learning_rate": 4.457885751780535e-06,
"loss": 1.5825,
"step": 535
},
{
"epoch": 4.15,
"learning_rate": 7.857716640189824e-06,
"loss": 1.6875,
"step": 540
},
{
"epoch": 4.19,
"learning_rate": 1.2143306799695106e-05,
"loss": 1.6501,
"step": 545
},
{
"epoch": 4.23,
"learning_rate": 1.725216267546245e-05,
"loss": 1.5837,
"step": 550
},
{
"epoch": 4.27,
"learning_rate": 2.3109785644681495e-05,
"loss": 1.5563,
"step": 555
},
{
"epoch": 4.31,
"learning_rate": 2.963075837424263e-05,
"loss": 1.5985,
"step": 560
},
{
"epoch": 4.35,
"learning_rate": 3.6719990397797463e-05,
"loss": 1.606,
"step": 565
},
{
"epoch": 4.38,
"learning_rate": 4.4274104748882125e-05,
"loss": 1.6791,
"step": 570
},
{
"epoch": 4.42,
"learning_rate": 5.2182945429873444e-05,
"loss": 1.7505,
"step": 575
},
{
"epoch": 4.46,
"learning_rate": 6.033118373448483e-05,
"loss": 1.5154,
"step": 580
},
{
"epoch": 4.5,
"learning_rate": 6.859999999999984e-05,
"loss": 1.671,
"step": 585
},
{
"epoch": 4.54,
"learning_rate": 7.686881626551508e-05,
"loss": 1.5294,
"step": 590
},
{
"epoch": 4.58,
"learning_rate": 8.501705457012647e-05,
"loss": 1.5787,
"step": 595
},
{
"epoch": 4.62,
"learning_rate": 9.292589525111778e-05,
"loss": 1.7159,
"step": 600
},
{
"epoch": 4.65,
"learning_rate": 0.00010048000960220244,
"loss": 1.6876,
"step": 605
},
{
"epoch": 4.69,
"learning_rate": 0.0001075692416257573,
"loss": 1.6451,
"step": 610
},
{
"epoch": 4.73,
"learning_rate": 0.00011409021435531843,
"loss": 1.7096,
"step": 615
},
{
"epoch": 4.77,
"learning_rate": 0.00011994783732453749,
"loss": 1.6926,
"step": 620
},
{
"epoch": 4.81,
"learning_rate": 0.00012505669320030485,
"loss": 1.6774,
"step": 625
},
{
"epoch": 4.85,
"learning_rate": 0.00012934228335981013,
"loss": 1.769,
"step": 630
},
{
"epoch": 4.88,
"learning_rate": 0.00013274211424821943,
"loss": 1.6677,
"step": 635
},
{
"epoch": 4.92,
"learning_rate": 0.00013520660867542716,
"loss": 1.6415,
"step": 640
},
{
"epoch": 4.96,
"learning_rate": 0.00013669982876312649,
"loss": 1.6811,
"step": 645
},
{
"epoch": 5.0,
"learning_rate": 0.0001372,
"loss": 1.6017,
"step": 650
},
{
"epoch": 5.0,
"eval_loss": 1.6280437707901,
"eval_runtime": 9.7539,
"eval_samples_per_second": 20.3,
"eval_steps_per_second": 2.563,
"step": 650
},
{
"epoch": 5.04,
"learning_rate": 0.00013669982876312649,
"loss": 1.5983,
"step": 655
},
{
"epoch": 5.08,
"learning_rate": 0.0001352066086754272,
"loss": 1.6281,
"step": 660
},
{
"epoch": 5.12,
"learning_rate": 0.00013274211424821946,
"loss": 1.6583,
"step": 665
},
{
"epoch": 5.15,
"learning_rate": 0.00012934228335981018,
"loss": 1.5553,
"step": 670
},
{
"epoch": 5.19,
"learning_rate": 0.0001250566932003049,
"loss": 1.669,
"step": 675
},
{
"epoch": 5.23,
"learning_rate": 0.00011994783732453757,
"loss": 1.5035,
"step": 680
},
{
"epoch": 5.27,
"learning_rate": 0.00011409021435531852,
"loss": 1.5271,
"step": 685
},
{
"epoch": 5.31,
"learning_rate": 0.00010756924162575738,
"loss": 1.6283,
"step": 690
},
{
"epoch": 5.35,
"learning_rate": 0.00010048000960220254,
"loss": 1.5816,
"step": 695
},
{
"epoch": 5.38,
"learning_rate": 9.292589525111789e-05,
"loss": 1.537,
"step": 700
},
{
"epoch": 5.42,
"learning_rate": 8.501705457012655e-05,
"loss": 1.5076,
"step": 705
},
{
"epoch": 5.46,
"learning_rate": 7.686881626551518e-05,
"loss": 1.5273,
"step": 710
},
{
"epoch": 5.5,
"learning_rate": 6.859999999999993e-05,
"loss": 1.6255,
"step": 715
},
{
"epoch": 5.54,
"learning_rate": 6.033118373448493e-05,
"loss": 1.5228,
"step": 720
},
{
"epoch": 5.58,
"learning_rate": 5.2182945429873545e-05,
"loss": 1.4525,
"step": 725
},
{
"epoch": 5.62,
"learning_rate": 4.427410474888221e-05,
"loss": 1.5599,
"step": 730
},
{
"epoch": 5.65,
"learning_rate": 3.671999039779755e-05,
"loss": 1.7274,
"step": 735
},
{
"epoch": 5.69,
"learning_rate": 2.9630758374242713e-05,
"loss": 1.5442,
"step": 740
},
{
"epoch": 5.73,
"learning_rate": 2.3109785644681573e-05,
"loss": 1.4565,
"step": 745
},
{
"epoch": 5.77,
"learning_rate": 1.725216267546251e-05,
"loss": 1.4942,
"step": 750
},
{
"epoch": 5.81,
"learning_rate": 1.2143306799695167e-05,
"loss": 1.6139,
"step": 755
},
{
"epoch": 5.85,
"learning_rate": 7.857716640189868e-06,
"loss": 1.6282,
"step": 760
},
{
"epoch": 5.88,
"learning_rate": 4.457885751780565e-06,
"loss": 1.6596,
"step": 765
},
{
"epoch": 5.92,
"learning_rate": 1.9933913245728244e-06,
"loss": 1.5722,
"step": 770
},
{
"epoch": 5.96,
"learning_rate": 5.001712368735127e-07,
"loss": 1.5391,
"step": 775
},
{
"epoch": 6.0,
"learning_rate": 0.0,
"loss": 1.6218,
"step": 780
},
{
"epoch": 6.0,
"eval_loss": 1.5917974710464478,
"eval_runtime": 9.7962,
"eval_samples_per_second": 20.212,
"eval_steps_per_second": 2.552,
"step": 780
},
{
"epoch": 6.04,
"learning_rate": 5.001712368734975e-07,
"loss": 1.4457,
"step": 785
},
{
"epoch": 6.08,
"learning_rate": 1.9933913245728015e-06,
"loss": 1.5599,
"step": 790
},
{
"epoch": 6.12,
"learning_rate": 4.457885751780527e-06,
"loss": 1.4377,
"step": 795
},
{
"epoch": 6.15,
"learning_rate": 7.857716640189815e-06,
"loss": 1.4766,
"step": 800
},
{
"epoch": 6.19,
"learning_rate": 1.2143306799695099e-05,
"loss": 1.4534,
"step": 805
},
{
"epoch": 6.23,
"learning_rate": 1.7252162675462436e-05,
"loss": 1.4231,
"step": 810
},
{
"epoch": 6.27,
"learning_rate": 2.310978564468148e-05,
"loss": 1.5066,
"step": 815
},
{
"epoch": 6.31,
"learning_rate": 2.963075837424261e-05,
"loss": 1.4435,
"step": 820
},
{
"epoch": 6.35,
"learning_rate": 3.671999039779744e-05,
"loss": 1.5639,
"step": 825
},
{
"epoch": 6.38,
"learning_rate": 4.4274104748882104e-05,
"loss": 1.4327,
"step": 830
},
{
"epoch": 6.42,
"learning_rate": 5.218294542987343e-05,
"loss": 1.5161,
"step": 835
},
{
"epoch": 6.46,
"learning_rate": 6.0331183734484816e-05,
"loss": 1.412,
"step": 840
},
{
"epoch": 6.5,
"learning_rate": 6.859999999999982e-05,
"loss": 1.5963,
"step": 845
},
{
"epoch": 6.54,
"learning_rate": 7.686881626551506e-05,
"loss": 1.4996,
"step": 850
},
{
"epoch": 6.58,
"learning_rate": 8.501705457012646e-05,
"loss": 1.4342,
"step": 855
},
{
"epoch": 6.62,
"learning_rate": 9.292589525111778e-05,
"loss": 1.5237,
"step": 860
},
{
"epoch": 6.65,
"learning_rate": 0.00010048000960220244,
"loss": 1.5488,
"step": 865
},
{
"epoch": 6.69,
"learning_rate": 0.00010756924162575728,
"loss": 1.5456,
"step": 870
},
{
"epoch": 6.73,
"learning_rate": 0.00011409021435531843,
"loss": 1.4942,
"step": 875
},
{
"epoch": 6.77,
"learning_rate": 0.00011994783732453747,
"loss": 1.5108,
"step": 880
},
{
"epoch": 6.81,
"learning_rate": 0.00012505669320030482,
"loss": 1.5004,
"step": 885
},
{
"epoch": 6.85,
"learning_rate": 0.00012934228335981013,
"loss": 1.5133,
"step": 890
},
{
"epoch": 6.88,
"learning_rate": 0.00013274211424821943,
"loss": 1.5261,
"step": 895
},
{
"epoch": 6.92,
"learning_rate": 0.00013520660867542716,
"loss": 1.5521,
"step": 900
},
{
"epoch": 6.96,
"learning_rate": 0.00013669982876312649,
"loss": 1.6079,
"step": 905
},
{
"epoch": 7.0,
"learning_rate": 0.0001372,
"loss": 1.546,
"step": 910
},
{
"epoch": 7.0,
"eval_loss": 1.618756890296936,
"eval_runtime": 9.7835,
"eval_samples_per_second": 20.238,
"eval_steps_per_second": 2.555,
"step": 910
},
{
"epoch": 7.04,
"learning_rate": 0.00013669982876312649,
"loss": 1.2732,
"step": 915
},
{
"epoch": 7.08,
"learning_rate": 0.0001352066086754272,
"loss": 1.4751,
"step": 920
},
{
"epoch": 7.12,
"learning_rate": 0.00013274211424821948,
"loss": 1.5095,
"step": 925
},
{
"epoch": 7.15,
"learning_rate": 0.0001293422833598103,
"loss": 1.4858,
"step": 930
},
{
"epoch": 7.19,
"learning_rate": 0.0001250566932003049,
"loss": 1.5896,
"step": 935
},
{
"epoch": 7.23,
"learning_rate": 0.00011994783732453773,
"loss": 1.3257,
"step": 940
},
{
"epoch": 7.27,
"learning_rate": 0.00011409021435531852,
"loss": 1.5044,
"step": 945
},
{
"epoch": 7.31,
"learning_rate": 0.00010756924162575719,
"loss": 1.389,
"step": 950
},
{
"epoch": 7.35,
"learning_rate": 0.00010048000960220255,
"loss": 1.4434,
"step": 955
},
{
"epoch": 7.38,
"learning_rate": 9.29258952511179e-05,
"loss": 1.4208,
"step": 960
},
{
"epoch": 7.42,
"learning_rate": 8.501705457012658e-05,
"loss": 1.4817,
"step": 965
},
{
"epoch": 7.46,
"learning_rate": 7.68688162655152e-05,
"loss": 1.5339,
"step": 970
},
{
"epoch": 7.5,
"learning_rate": 6.859999999999995e-05,
"loss": 1.5614,
"step": 975
},
{
"epoch": 7.54,
"learning_rate": 6.0331183734484945e-05,
"loss": 1.4163,
"step": 980
},
{
"epoch": 7.58,
"learning_rate": 5.2182945429873566e-05,
"loss": 1.3478,
"step": 985
},
{
"epoch": 7.62,
"learning_rate": 4.4274104748882226e-05,
"loss": 1.502,
"step": 990
},
{
"epoch": 7.65,
"learning_rate": 3.6719990397797565e-05,
"loss": 1.52,
"step": 995
},
{
"epoch": 7.69,
"learning_rate": 2.9630758374242923e-05,
"loss": 1.3148,
"step": 1000
},
{
"epoch": 7.73,
"learning_rate": 2.310978564468158e-05,
"loss": 1.5192,
"step": 1005
},
{
"epoch": 7.77,
"learning_rate": 1.7252162675462368e-05,
"loss": 1.4457,
"step": 1010
},
{
"epoch": 7.81,
"learning_rate": 1.2143306799695174e-05,
"loss": 1.3958,
"step": 1015
},
{
"epoch": 7.85,
"learning_rate": 7.85771664018977e-06,
"loss": 1.5431,
"step": 1020
},
{
"epoch": 7.88,
"learning_rate": 4.457885751780573e-06,
"loss": 1.4051,
"step": 1025
},
{
"epoch": 7.92,
"learning_rate": 1.993391324572832e-06,
"loss": 1.4924,
"step": 1030
},
{
"epoch": 7.96,
"learning_rate": 5.001712368735127e-07,
"loss": 1.4193,
"step": 1035
},
{
"epoch": 8.0,
"learning_rate": 0.0,
"loss": 1.4695,
"step": 1040
},
{
"epoch": 8.0,
"eval_loss": 1.5916674137115479,
"eval_runtime": 9.7988,
"eval_samples_per_second": 20.206,
"eval_steps_per_second": 2.551,
"step": 1040
}
],
"max_steps": 1690,
"num_train_epochs": 13,
"total_flos": 1084361932800000.0,
"trial_name": null,
"trial_params": null
}