fs8 / checkpoint-2700 /trainer_state.json
aixk's picture
Upload folder using huggingface_hub
4e2edd4 verified
Raw
History Blame Contribute Delete
45.8 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1428099173553719,
"eval_steps": 500,
"global_step": 2700,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005289256198347108,
"grad_norm": 2042.0159912109375,
"learning_rate": 3.2e-07,
"loss": 8.126,
"step": 10
},
{
"epoch": 0.0010578512396694215,
"grad_norm": 132.607666015625,
"learning_rate": 1.12e-06,
"loss": 8.0108,
"step": 20
},
{
"epoch": 0.0015867768595041322,
"grad_norm": 117.4473876953125,
"learning_rate": 1.92e-06,
"loss": 7.8388,
"step": 30
},
{
"epoch": 0.002115702479338843,
"grad_norm": 58.00923538208008,
"learning_rate": 2.72e-06,
"loss": 7.7671,
"step": 40
},
{
"epoch": 0.002644628099173554,
"grad_norm": 62.31724166870117,
"learning_rate": 3.52e-06,
"loss": 7.821,
"step": 50
},
{
"epoch": 0.0031735537190082643,
"grad_norm": 99.75863647460938,
"learning_rate": 4.32e-06,
"loss": 7.6772,
"step": 60
},
{
"epoch": 0.0037024793388429752,
"grad_norm": 337.9526672363281,
"learning_rate": 5.12e-06,
"loss": 7.8172,
"step": 70
},
{
"epoch": 0.004231404958677686,
"grad_norm": 95.75334167480469,
"learning_rate": 5.920000000000001e-06,
"loss": 7.6801,
"step": 80
},
{
"epoch": 0.004760330578512397,
"grad_norm": 589.1984252929688,
"learning_rate": 6.72e-06,
"loss": 7.7462,
"step": 90
},
{
"epoch": 0.005289256198347108,
"grad_norm": 115.37745666503906,
"learning_rate": 7.520000000000001e-06,
"loss": 7.5665,
"step": 100
},
{
"epoch": 0.005818181818181818,
"grad_norm": 104.31098937988281,
"learning_rate": 8.32e-06,
"loss": 7.6031,
"step": 110
},
{
"epoch": 0.006347107438016529,
"grad_norm": 357.35272216796875,
"learning_rate": 9.12e-06,
"loss": 7.6829,
"step": 120
},
{
"epoch": 0.00687603305785124,
"grad_norm": 299.00555419921875,
"learning_rate": 9.92e-06,
"loss": 7.6717,
"step": 130
},
{
"epoch": 0.0074049586776859504,
"grad_norm": 593.5489501953125,
"learning_rate": 1.072e-05,
"loss": 7.6622,
"step": 140
},
{
"epoch": 0.007933884297520661,
"grad_norm": 174.9026336669922,
"learning_rate": 1.152e-05,
"loss": 7.595,
"step": 150
},
{
"epoch": 0.008462809917355372,
"grad_norm": 199.49935913085938,
"learning_rate": 1.232e-05,
"loss": 7.5791,
"step": 160
},
{
"epoch": 0.008991735537190083,
"grad_norm": 557.2059936523438,
"learning_rate": 1.3120000000000001e-05,
"loss": 7.7285,
"step": 170
},
{
"epoch": 0.009520661157024794,
"grad_norm": 333.83441162109375,
"learning_rate": 1.3919999999999999e-05,
"loss": 7.6101,
"step": 180
},
{
"epoch": 0.010049586776859505,
"grad_norm": 213.27163696289062,
"learning_rate": 1.472e-05,
"loss": 7.6139,
"step": 190
},
{
"epoch": 0.010578512396694216,
"grad_norm": 192.46920776367188,
"learning_rate": 1.552e-05,
"loss": 7.4358,
"step": 200
},
{
"epoch": 0.011107438016528925,
"grad_norm": 369.1148986816406,
"learning_rate": 1.6320000000000003e-05,
"loss": 7.4565,
"step": 210
},
{
"epoch": 0.011636363636363636,
"grad_norm": 244.7185821533203,
"learning_rate": 1.712e-05,
"loss": 7.3962,
"step": 220
},
{
"epoch": 0.012165289256198347,
"grad_norm": 308.51544189453125,
"learning_rate": 1.792e-05,
"loss": 7.4273,
"step": 230
},
{
"epoch": 0.012694214876033057,
"grad_norm": 208.3214569091797,
"learning_rate": 1.872e-05,
"loss": 7.3567,
"step": 240
},
{
"epoch": 0.013223140495867768,
"grad_norm": 121.53463745117188,
"learning_rate": 1.9520000000000003e-05,
"loss": 7.4131,
"step": 250
},
{
"epoch": 0.01375206611570248,
"grad_norm": 124.09678649902344,
"learning_rate": 2.032e-05,
"loss": 7.426,
"step": 260
},
{
"epoch": 0.01428099173553719,
"grad_norm": 237.53346252441406,
"learning_rate": 2.112e-05,
"loss": 7.377,
"step": 270
},
{
"epoch": 0.014809917355371901,
"grad_norm": 174.61985778808594,
"learning_rate": 2.192e-05,
"loss": 7.3773,
"step": 280
},
{
"epoch": 0.015338842975206612,
"grad_norm": 86.74190521240234,
"learning_rate": 2.2720000000000003e-05,
"loss": 7.3686,
"step": 290
},
{
"epoch": 0.015867768595041323,
"grad_norm": 123.0051498413086,
"learning_rate": 2.3520000000000002e-05,
"loss": 7.363,
"step": 300
},
{
"epoch": 0.016396694214876033,
"grad_norm": 149.46461486816406,
"learning_rate": 2.432e-05,
"loss": 7.3321,
"step": 310
},
{
"epoch": 0.016925619834710744,
"grad_norm": 129.9262237548828,
"learning_rate": 2.512e-05,
"loss": 7.3589,
"step": 320
},
{
"epoch": 0.017454545454545455,
"grad_norm": 287.2998962402344,
"learning_rate": 2.592e-05,
"loss": 7.3022,
"step": 330
},
{
"epoch": 0.017983471074380166,
"grad_norm": 149.36317443847656,
"learning_rate": 2.672e-05,
"loss": 7.1559,
"step": 340
},
{
"epoch": 0.018512396694214877,
"grad_norm": 133.55393981933594,
"learning_rate": 2.752e-05,
"loss": 7.2833,
"step": 350
},
{
"epoch": 0.019041322314049588,
"grad_norm": 111.75740814208984,
"learning_rate": 2.8320000000000003e-05,
"loss": 7.0669,
"step": 360
},
{
"epoch": 0.0195702479338843,
"grad_norm": 108.92760467529297,
"learning_rate": 2.9120000000000002e-05,
"loss": 7.2586,
"step": 370
},
{
"epoch": 0.02009917355371901,
"grad_norm": 160.08486938476562,
"learning_rate": 2.9920000000000005e-05,
"loss": 7.2912,
"step": 380
},
{
"epoch": 0.02062809917355372,
"grad_norm": 115.86800384521484,
"learning_rate": 3.072e-05,
"loss": 7.1553,
"step": 390
},
{
"epoch": 0.02115702479338843,
"grad_norm": 131.96246337890625,
"learning_rate": 3.1519999999999996e-05,
"loss": 7.0865,
"step": 400
},
{
"epoch": 0.021685950413223142,
"grad_norm": 175.23385620117188,
"learning_rate": 3.232e-05,
"loss": 7.1718,
"step": 410
},
{
"epoch": 0.02221487603305785,
"grad_norm": 130.51516723632812,
"learning_rate": 3.312e-05,
"loss": 7.1449,
"step": 420
},
{
"epoch": 0.02274380165289256,
"grad_norm": 142.1250762939453,
"learning_rate": 3.392e-05,
"loss": 7.0811,
"step": 430
},
{
"epoch": 0.02327272727272727,
"grad_norm": 93.60326385498047,
"learning_rate": 3.472e-05,
"loss": 7.0511,
"step": 440
},
{
"epoch": 0.023801652892561982,
"grad_norm": 85.3148193359375,
"learning_rate": 3.5520000000000006e-05,
"loss": 7.057,
"step": 450
},
{
"epoch": 0.024330578512396693,
"grad_norm": 77.96083068847656,
"learning_rate": 3.6320000000000005e-05,
"loss": 7.0768,
"step": 460
},
{
"epoch": 0.024859504132231404,
"grad_norm": 64.50347900390625,
"learning_rate": 3.712e-05,
"loss": 7.0468,
"step": 470
},
{
"epoch": 0.025388429752066115,
"grad_norm": 89.8930892944336,
"learning_rate": 3.792e-05,
"loss": 6.9279,
"step": 480
},
{
"epoch": 0.025917355371900826,
"grad_norm": 103.4708251953125,
"learning_rate": 3.872e-05,
"loss": 6.8665,
"step": 490
},
{
"epoch": 0.026446280991735537,
"grad_norm": 96.82048034667969,
"learning_rate": 3.952e-05,
"loss": 6.9254,
"step": 500
},
{
"epoch": 0.026975206611570247,
"grad_norm": 127.65508270263672,
"learning_rate": 4.032e-05,
"loss": 6.9533,
"step": 510
},
{
"epoch": 0.02750413223140496,
"grad_norm": 123.8250503540039,
"learning_rate": 4.1120000000000006e-05,
"loss": 6.8762,
"step": 520
},
{
"epoch": 0.02803305785123967,
"grad_norm": 80.71707153320312,
"learning_rate": 4.1920000000000005e-05,
"loss": 6.9264,
"step": 530
},
{
"epoch": 0.02856198347107438,
"grad_norm": 76.69340515136719,
"learning_rate": 4.2720000000000004e-05,
"loss": 6.8932,
"step": 540
},
{
"epoch": 0.02909090909090909,
"grad_norm": 64.87788391113281,
"learning_rate": 4.352e-05,
"loss": 6.8852,
"step": 550
},
{
"epoch": 0.029619834710743802,
"grad_norm": 55.4420280456543,
"learning_rate": 4.432e-05,
"loss": 6.8624,
"step": 560
},
{
"epoch": 0.030148760330578513,
"grad_norm": 83.48722076416016,
"learning_rate": 4.512e-05,
"loss": 6.791,
"step": 570
},
{
"epoch": 0.030677685950413223,
"grad_norm": 67.83543395996094,
"learning_rate": 4.592e-05,
"loss": 6.78,
"step": 580
},
{
"epoch": 0.031206611570247934,
"grad_norm": 75.6465072631836,
"learning_rate": 4.672e-05,
"loss": 6.7436,
"step": 590
},
{
"epoch": 0.031735537190082645,
"grad_norm": 57.24126434326172,
"learning_rate": 4.7520000000000006e-05,
"loss": 6.6183,
"step": 600
},
{
"epoch": 0.032264462809917356,
"grad_norm": 53.670318603515625,
"learning_rate": 4.8320000000000005e-05,
"loss": 6.7423,
"step": 610
},
{
"epoch": 0.03279338842975207,
"grad_norm": 90.657958984375,
"learning_rate": 4.9120000000000004e-05,
"loss": 6.796,
"step": 620
},
{
"epoch": 0.03332231404958678,
"grad_norm": 59.86640167236328,
"learning_rate": 4.992e-05,
"loss": 6.6875,
"step": 630
},
{
"epoch": 0.03385123966942149,
"grad_norm": 82.00715637207031,
"learning_rate": 5.072e-05,
"loss": 6.8297,
"step": 640
},
{
"epoch": 0.0343801652892562,
"grad_norm": 77.67565155029297,
"learning_rate": 5.152e-05,
"loss": 6.6996,
"step": 650
},
{
"epoch": 0.03490909090909091,
"grad_norm": 76.80774688720703,
"learning_rate": 5.232e-05,
"loss": 6.6164,
"step": 660
},
{
"epoch": 0.03543801652892562,
"grad_norm": 90.92999267578125,
"learning_rate": 5.3120000000000006e-05,
"loss": 6.6109,
"step": 670
},
{
"epoch": 0.03596694214876033,
"grad_norm": 60.101036071777344,
"learning_rate": 5.3920000000000006e-05,
"loss": 6.6207,
"step": 680
},
{
"epoch": 0.03649586776859504,
"grad_norm": 71.14286804199219,
"learning_rate": 5.4720000000000005e-05,
"loss": 6.6988,
"step": 690
},
{
"epoch": 0.037024793388429754,
"grad_norm": 79.58287048339844,
"learning_rate": 5.5520000000000004e-05,
"loss": 6.6793,
"step": 700
},
{
"epoch": 0.037553719008264465,
"grad_norm": 57.14976119995117,
"learning_rate": 5.632e-05,
"loss": 6.5679,
"step": 710
},
{
"epoch": 0.038082644628099176,
"grad_norm": 48.05242919921875,
"learning_rate": 5.712000000000001e-05,
"loss": 6.6146,
"step": 720
},
{
"epoch": 0.03861157024793389,
"grad_norm": 44.47470474243164,
"learning_rate": 5.792000000000001e-05,
"loss": 6.5374,
"step": 730
},
{
"epoch": 0.0391404958677686,
"grad_norm": 51.66844177246094,
"learning_rate": 5.872000000000001e-05,
"loss": 6.4478,
"step": 740
},
{
"epoch": 0.03966942148760331,
"grad_norm": 54.69235610961914,
"learning_rate": 5.952e-05,
"loss": 6.4556,
"step": 750
},
{
"epoch": 0.04019834710743802,
"grad_norm": 62.92082214355469,
"learning_rate": 6.032e-05,
"loss": 6.494,
"step": 760
},
{
"epoch": 0.04072727272727273,
"grad_norm": 59.18268585205078,
"learning_rate": 6.112e-05,
"loss": 6.4632,
"step": 770
},
{
"epoch": 0.04125619834710744,
"grad_norm": 43.41447448730469,
"learning_rate": 6.192e-05,
"loss": 6.4568,
"step": 780
},
{
"epoch": 0.04178512396694215,
"grad_norm": 68.496337890625,
"learning_rate": 6.272e-05,
"loss": 6.3378,
"step": 790
},
{
"epoch": 0.04231404958677686,
"grad_norm": 55.83193588256836,
"learning_rate": 6.352e-05,
"loss": 6.5272,
"step": 800
},
{
"epoch": 0.042842975206611573,
"grad_norm": 52.77011489868164,
"learning_rate": 6.432000000000001e-05,
"loss": 6.3882,
"step": 810
},
{
"epoch": 0.043371900826446284,
"grad_norm": 47.83772659301758,
"learning_rate": 6.512e-05,
"loss": 6.3745,
"step": 820
},
{
"epoch": 0.04390082644628099,
"grad_norm": 64.70166015625,
"learning_rate": 6.592e-05,
"loss": 6.3783,
"step": 830
},
{
"epoch": 0.0444297520661157,
"grad_norm": 69.14620208740234,
"learning_rate": 6.672e-05,
"loss": 6.403,
"step": 840
},
{
"epoch": 0.04495867768595041,
"grad_norm": 41.3566780090332,
"learning_rate": 6.752e-05,
"loss": 6.273,
"step": 850
},
{
"epoch": 0.04548760330578512,
"grad_norm": 57.124813079833984,
"learning_rate": 6.832000000000001e-05,
"loss": 6.3434,
"step": 860
},
{
"epoch": 0.04601652892561983,
"grad_norm": 47.598854064941406,
"learning_rate": 6.912e-05,
"loss": 6.2613,
"step": 870
},
{
"epoch": 0.04654545454545454,
"grad_norm": 63.111759185791016,
"learning_rate": 6.992000000000001e-05,
"loss": 6.2488,
"step": 880
},
{
"epoch": 0.047074380165289254,
"grad_norm": 53.83757781982422,
"learning_rate": 7.072000000000001e-05,
"loss": 6.1787,
"step": 890
},
{
"epoch": 0.047603305785123964,
"grad_norm": 42.92972946166992,
"learning_rate": 7.151999999999999e-05,
"loss": 6.2455,
"step": 900
},
{
"epoch": 0.048132231404958675,
"grad_norm": 40.897098541259766,
"learning_rate": 7.232e-05,
"loss": 6.1776,
"step": 910
},
{
"epoch": 0.048661157024793386,
"grad_norm": 67.57796478271484,
"learning_rate": 7.312e-05,
"loss": 6.0933,
"step": 920
},
{
"epoch": 0.0491900826446281,
"grad_norm": 54.34871292114258,
"learning_rate": 7.392e-05,
"loss": 6.1669,
"step": 930
},
{
"epoch": 0.04971900826446281,
"grad_norm": 46.664188385009766,
"learning_rate": 7.472e-05,
"loss": 6.0994,
"step": 940
},
{
"epoch": 0.05024793388429752,
"grad_norm": 40.62440490722656,
"learning_rate": 7.552e-05,
"loss": 6.1375,
"step": 950
},
{
"epoch": 0.05077685950413223,
"grad_norm": 40.99917221069336,
"learning_rate": 7.632e-05,
"loss": 6.0468,
"step": 960
},
{
"epoch": 0.05130578512396694,
"grad_norm": 41.27398681640625,
"learning_rate": 7.712000000000001e-05,
"loss": 6.0949,
"step": 970
},
{
"epoch": 0.05183471074380165,
"grad_norm": 40.87042236328125,
"learning_rate": 7.792e-05,
"loss": 6.0498,
"step": 980
},
{
"epoch": 0.05236363636363636,
"grad_norm": 41.66493606567383,
"learning_rate": 7.872e-05,
"loss": 6.0707,
"step": 990
},
{
"epoch": 0.05289256198347107,
"grad_norm": 36.58250427246094,
"learning_rate": 7.952000000000001e-05,
"loss": 6.0559,
"step": 1000
},
{
"epoch": 0.053421487603305784,
"grad_norm": 34.69593048095703,
"learning_rate": 8.032e-05,
"loss": 6.0294,
"step": 1010
},
{
"epoch": 0.053950413223140495,
"grad_norm": 36.51956558227539,
"learning_rate": 8.112000000000001e-05,
"loss": 6.008,
"step": 1020
},
{
"epoch": 0.054479338842975206,
"grad_norm": 38.489219665527344,
"learning_rate": 8.192e-05,
"loss": 5.9906,
"step": 1030
},
{
"epoch": 0.05500826446280992,
"grad_norm": 35.57550048828125,
"learning_rate": 8.272000000000001e-05,
"loss": 5.9222,
"step": 1040
},
{
"epoch": 0.05553719008264463,
"grad_norm": 36.05617904663086,
"learning_rate": 8.352000000000001e-05,
"loss": 6.0426,
"step": 1050
},
{
"epoch": 0.05606611570247934,
"grad_norm": 31.7716121673584,
"learning_rate": 8.431999999999999e-05,
"loss": 5.9889,
"step": 1060
},
{
"epoch": 0.05659504132231405,
"grad_norm": 34.74286651611328,
"learning_rate": 8.512e-05,
"loss": 5.8873,
"step": 1070
},
{
"epoch": 0.05712396694214876,
"grad_norm": 45.21353530883789,
"learning_rate": 8.592e-05,
"loss": 5.9505,
"step": 1080
},
{
"epoch": 0.05765289256198347,
"grad_norm": 30.405447006225586,
"learning_rate": 8.672e-05,
"loss": 5.8087,
"step": 1090
},
{
"epoch": 0.05818181818181818,
"grad_norm": 30.943218231201172,
"learning_rate": 8.752e-05,
"loss": 5.7337,
"step": 1100
},
{
"epoch": 0.05871074380165289,
"grad_norm": 32.396610260009766,
"learning_rate": 8.832000000000001e-05,
"loss": 5.7989,
"step": 1110
},
{
"epoch": 0.059239669421487604,
"grad_norm": 31.198833465576172,
"learning_rate": 8.912e-05,
"loss": 5.8181,
"step": 1120
},
{
"epoch": 0.059768595041322314,
"grad_norm": 40.59803009033203,
"learning_rate": 8.992e-05,
"loss": 5.8761,
"step": 1130
},
{
"epoch": 0.060297520661157025,
"grad_norm": 43.126766204833984,
"learning_rate": 9.072e-05,
"loss": 5.8239,
"step": 1140
},
{
"epoch": 0.060826446280991736,
"grad_norm": 39.69029998779297,
"learning_rate": 9.152e-05,
"loss": 5.7444,
"step": 1150
},
{
"epoch": 0.06135537190082645,
"grad_norm": 28.941499710083008,
"learning_rate": 9.232000000000001e-05,
"loss": 5.8256,
"step": 1160
},
{
"epoch": 0.06188429752066116,
"grad_norm": 46.216552734375,
"learning_rate": 9.312e-05,
"loss": 5.8361,
"step": 1170
},
{
"epoch": 0.06241322314049587,
"grad_norm": 42.1989860534668,
"learning_rate": 9.392000000000001e-05,
"loss": 5.7034,
"step": 1180
},
{
"epoch": 0.06294214876033058,
"grad_norm": 36.610836029052734,
"learning_rate": 9.472000000000001e-05,
"loss": 5.7089,
"step": 1190
},
{
"epoch": 0.06347107438016529,
"grad_norm": 38.280452728271484,
"learning_rate": 9.552000000000001e-05,
"loss": 5.8296,
"step": 1200
},
{
"epoch": 0.064,
"grad_norm": 42.162864685058594,
"learning_rate": 9.632e-05,
"loss": 5.833,
"step": 1210
},
{
"epoch": 0.06452892561983471,
"grad_norm": 58.0146369934082,
"learning_rate": 9.712e-05,
"loss": 5.6257,
"step": 1220
},
{
"epoch": 0.06505785123966942,
"grad_norm": 72.400634765625,
"learning_rate": 9.792e-05,
"loss": 5.6169,
"step": 1230
},
{
"epoch": 0.06558677685950413,
"grad_norm": 41.95994186401367,
"learning_rate": 9.872e-05,
"loss": 5.6194,
"step": 1240
},
{
"epoch": 0.06611570247933884,
"grad_norm": 38.22507858276367,
"learning_rate": 9.952e-05,
"loss": 5.5854,
"step": 1250
},
{
"epoch": 0.06664462809917356,
"grad_norm": 36.9998664855957,
"learning_rate": 0.00010032000000000002,
"loss": 5.5598,
"step": 1260
},
{
"epoch": 0.06717355371900827,
"grad_norm": 30.84783363342285,
"learning_rate": 0.00010112000000000002,
"loss": 5.4868,
"step": 1270
},
{
"epoch": 0.06770247933884298,
"grad_norm": 35.899383544921875,
"learning_rate": 0.00010192000000000001,
"loss": 5.4559,
"step": 1280
},
{
"epoch": 0.06823140495867769,
"grad_norm": 32.75505828857422,
"learning_rate": 0.00010271999999999999,
"loss": 5.6184,
"step": 1290
},
{
"epoch": 0.0687603305785124,
"grad_norm": 40.69361877441406,
"learning_rate": 0.00010352,
"loss": 5.5495,
"step": 1300
},
{
"epoch": 0.06928925619834711,
"grad_norm": 43.96121597290039,
"learning_rate": 0.00010431999999999999,
"loss": 5.585,
"step": 1310
},
{
"epoch": 0.06981818181818182,
"grad_norm": 34.5072021484375,
"learning_rate": 0.00010512,
"loss": 5.518,
"step": 1320
},
{
"epoch": 0.07034710743801653,
"grad_norm": 46.74812698364258,
"learning_rate": 0.00010592,
"loss": 5.4283,
"step": 1330
},
{
"epoch": 0.07087603305785124,
"grad_norm": 48.960025787353516,
"learning_rate": 0.00010672,
"loss": 5.4234,
"step": 1340
},
{
"epoch": 0.07140495867768595,
"grad_norm": 47.75209045410156,
"learning_rate": 0.00010752,
"loss": 5.4553,
"step": 1350
},
{
"epoch": 0.07193388429752066,
"grad_norm": 43.6797981262207,
"learning_rate": 0.00010831999999999999,
"loss": 5.3252,
"step": 1360
},
{
"epoch": 0.07246280991735538,
"grad_norm": 48.113887786865234,
"learning_rate": 0.00010912,
"loss": 5.4867,
"step": 1370
},
{
"epoch": 0.07299173553719009,
"grad_norm": 42.719642639160156,
"learning_rate": 0.00010992,
"loss": 5.3672,
"step": 1380
},
{
"epoch": 0.0735206611570248,
"grad_norm": 51.8200798034668,
"learning_rate": 0.00011072,
"loss": 5.2117,
"step": 1390
},
{
"epoch": 0.07404958677685951,
"grad_norm": 72.69532012939453,
"learning_rate": 0.00011152,
"loss": 5.3722,
"step": 1400
},
{
"epoch": 0.07457851239669422,
"grad_norm": 56.0296745300293,
"learning_rate": 0.00011232000000000001,
"loss": 5.2986,
"step": 1410
},
{
"epoch": 0.07510743801652893,
"grad_norm": 48.64356994628906,
"learning_rate": 0.00011312,
"loss": 5.3451,
"step": 1420
},
{
"epoch": 0.07563636363636364,
"grad_norm": 62.179046630859375,
"learning_rate": 0.00011392000000000001,
"loss": 5.3301,
"step": 1430
},
{
"epoch": 0.07616528925619835,
"grad_norm": 95.21004486083984,
"learning_rate": 0.00011472,
"loss": 5.2516,
"step": 1440
},
{
"epoch": 0.07669421487603306,
"grad_norm": 76.14125061035156,
"learning_rate": 0.00011552,
"loss": 5.1788,
"step": 1450
},
{
"epoch": 0.07722314049586777,
"grad_norm": 79.47603607177734,
"learning_rate": 0.00011632000000000001,
"loss": 5.2876,
"step": 1460
},
{
"epoch": 0.07775206611570248,
"grad_norm": 101.11727142333984,
"learning_rate": 0.00011712,
"loss": 5.1364,
"step": 1470
},
{
"epoch": 0.0782809917355372,
"grad_norm": 82.6675796508789,
"learning_rate": 0.00011792000000000001,
"loss": 5.2109,
"step": 1480
},
{
"epoch": 0.0788099173553719,
"grad_norm": 82.03048706054688,
"learning_rate": 0.00011872000000000002,
"loss": 5.2076,
"step": 1490
},
{
"epoch": 0.07933884297520662,
"grad_norm": 56.5334358215332,
"learning_rate": 0.00011952000000000001,
"loss": 5.2379,
"step": 1500
},
{
"epoch": 0.07986776859504133,
"grad_norm": 77.19476318359375,
"learning_rate": 0.00012032000000000001,
"loss": 5.2414,
"step": 1510
},
{
"epoch": 0.08039669421487604,
"grad_norm": 76.6305160522461,
"learning_rate": 0.00012112,
"loss": 5.1135,
"step": 1520
},
{
"epoch": 0.08092561983471075,
"grad_norm": 183.71173095703125,
"learning_rate": 0.00012192000000000001,
"loss": 5.1305,
"step": 1530
},
{
"epoch": 0.08145454545454546,
"grad_norm": 103.42782592773438,
"learning_rate": 0.00012272000000000002,
"loss": 5.0707,
"step": 1540
},
{
"epoch": 0.08198347107438017,
"grad_norm": 89.39161682128906,
"learning_rate": 0.00012352,
"loss": 5.0448,
"step": 1550
},
{
"epoch": 0.08251239669421488,
"grad_norm": 128.94386291503906,
"learning_rate": 0.00012432,
"loss": 5.0627,
"step": 1560
},
{
"epoch": 0.08304132231404959,
"grad_norm": 114.81316375732422,
"learning_rate": 0.00012512000000000002,
"loss": 5.0173,
"step": 1570
},
{
"epoch": 0.0835702479338843,
"grad_norm": 85.47364807128906,
"learning_rate": 0.00012592000000000001,
"loss": 5.0522,
"step": 1580
},
{
"epoch": 0.08409917355371901,
"grad_norm": 97.26194763183594,
"learning_rate": 0.00012672,
"loss": 5.0868,
"step": 1590
},
{
"epoch": 0.08462809917355373,
"grad_norm": 186.6729278564453,
"learning_rate": 0.00012752,
"loss": 5.0442,
"step": 1600
},
{
"epoch": 0.08515702479338844,
"grad_norm": 79.75817108154297,
"learning_rate": 0.00012832,
"loss": 4.9309,
"step": 1610
},
{
"epoch": 0.08568595041322315,
"grad_norm": 98.72312927246094,
"learning_rate": 0.00012911999999999998,
"loss": 4.9763,
"step": 1620
},
{
"epoch": 0.08621487603305786,
"grad_norm": 99.25630950927734,
"learning_rate": 0.00012992,
"loss": 5.0555,
"step": 1630
},
{
"epoch": 0.08674380165289257,
"grad_norm": 113.07233428955078,
"learning_rate": 0.00013072,
"loss": 4.9236,
"step": 1640
},
{
"epoch": 0.08727272727272728,
"grad_norm": 116.71514892578125,
"learning_rate": 0.00013152,
"loss": 4.8469,
"step": 1650
},
{
"epoch": 0.08780165289256198,
"grad_norm": 183.65267944335938,
"learning_rate": 0.00013224000000000002,
"loss": 4.922,
"step": 1660
},
{
"epoch": 0.08833057851239669,
"grad_norm": 134.0264892578125,
"learning_rate": 0.00013304000000000001,
"loss": 4.8469,
"step": 1670
},
{
"epoch": 0.0888595041322314,
"grad_norm": 114.74702453613281,
"learning_rate": 0.00013384,
"loss": 4.891,
"step": 1680
},
{
"epoch": 0.08938842975206611,
"grad_norm": 124.9133529663086,
"learning_rate": 0.00013464,
"loss": 4.7879,
"step": 1690
},
{
"epoch": 0.08991735537190082,
"grad_norm": 141.5299530029297,
"learning_rate": 0.00013544000000000002,
"loss": 4.7898,
"step": 1700
},
{
"epoch": 0.09044628099173553,
"grad_norm": 93.27886962890625,
"learning_rate": 0.00013624,
"loss": 4.8604,
"step": 1710
},
{
"epoch": 0.09097520661157024,
"grad_norm": 194.52664184570312,
"learning_rate": 0.00013704,
"loss": 4.7352,
"step": 1720
},
{
"epoch": 0.09150413223140495,
"grad_norm": 118.92210388183594,
"learning_rate": 0.00013784000000000002,
"loss": 4.7951,
"step": 1730
},
{
"epoch": 0.09203305785123966,
"grad_norm": 167.02508544921875,
"learning_rate": 0.00013864000000000001,
"loss": 4.7964,
"step": 1740
},
{
"epoch": 0.09256198347107437,
"grad_norm": 105.10356903076172,
"learning_rate": 0.00013944,
"loss": 4.7212,
"step": 1750
},
{
"epoch": 0.09309090909090909,
"grad_norm": 91.76654052734375,
"learning_rate": 0.00014024000000000003,
"loss": 4.7349,
"step": 1760
},
{
"epoch": 0.0936198347107438,
"grad_norm": 102.53783416748047,
"learning_rate": 0.00014104000000000002,
"loss": 4.6718,
"step": 1770
},
{
"epoch": 0.09414876033057851,
"grad_norm": 129.4251251220703,
"learning_rate": 0.00014184,
"loss": 4.7727,
"step": 1780
},
{
"epoch": 0.09467768595041322,
"grad_norm": 243.75103759765625,
"learning_rate": 0.00014264,
"loss": 4.6279,
"step": 1790
},
{
"epoch": 0.09520661157024793,
"grad_norm": 119.21356964111328,
"learning_rate": 0.00014344,
"loss": 4.6609,
"step": 1800
},
{
"epoch": 0.09573553719008264,
"grad_norm": 178.49330139160156,
"learning_rate": 0.00014424,
"loss": 4.642,
"step": 1810
},
{
"epoch": 0.09626446280991735,
"grad_norm": 152.4857940673828,
"learning_rate": 0.00014504,
"loss": 4.6757,
"step": 1820
},
{
"epoch": 0.09679338842975206,
"grad_norm": 141.40493774414062,
"learning_rate": 0.00014584,
"loss": 4.6543,
"step": 1830
},
{
"epoch": 0.09732231404958677,
"grad_norm": 155.3096923828125,
"learning_rate": 0.00014664,
"loss": 4.5327,
"step": 1840
},
{
"epoch": 0.09785123966942148,
"grad_norm": 150.15298461914062,
"learning_rate": 0.00014744,
"loss": 4.6052,
"step": 1850
},
{
"epoch": 0.0983801652892562,
"grad_norm": 187.1421356201172,
"learning_rate": 0.00014824,
"loss": 4.4834,
"step": 1860
},
{
"epoch": 0.0989090909090909,
"grad_norm": 150.79815673828125,
"learning_rate": 0.00014904,
"loss": 4.5097,
"step": 1870
},
{
"epoch": 0.09943801652892562,
"grad_norm": 147.16586303710938,
"learning_rate": 0.00014984000000000002,
"loss": 4.5149,
"step": 1880
},
{
"epoch": 0.09996694214876033,
"grad_norm": 129.7955322265625,
"learning_rate": 0.00015064,
"loss": 4.5588,
"step": 1890
},
{
"epoch": 0.10049586776859504,
"grad_norm": 249.13198852539062,
"learning_rate": 0.00015144,
"loss": 4.5071,
"step": 1900
},
{
"epoch": 0.10102479338842975,
"grad_norm": 119.97147369384766,
"learning_rate": 0.00015224,
"loss": 4.5246,
"step": 1910
},
{
"epoch": 0.10155371900826446,
"grad_norm": 131.48204040527344,
"learning_rate": 0.00015304,
"loss": 4.3402,
"step": 1920
},
{
"epoch": 0.10208264462809917,
"grad_norm": 186.90174865722656,
"learning_rate": 0.00015384,
"loss": 4.403,
"step": 1930
},
{
"epoch": 0.10261157024793388,
"grad_norm": 146.8113250732422,
"learning_rate": 0.00015464,
"loss": 4.4193,
"step": 1940
},
{
"epoch": 0.10314049586776859,
"grad_norm": 150.3628387451172,
"learning_rate": 0.00015544000000000002,
"loss": 4.4478,
"step": 1950
},
{
"epoch": 0.1036694214876033,
"grad_norm": 112.74451446533203,
"learning_rate": 0.00015624,
"loss": 4.3628,
"step": 1960
},
{
"epoch": 0.10419834710743801,
"grad_norm": 239.00863647460938,
"learning_rate": 0.00015704,
"loss": 4.3369,
"step": 1970
},
{
"epoch": 0.10472727272727272,
"grad_norm": 126.43092346191406,
"learning_rate": 0.00015784000000000002,
"loss": 4.3286,
"step": 1980
},
{
"epoch": 0.10525619834710744,
"grad_norm": 185.16238403320312,
"learning_rate": 0.00015864,
"loss": 4.2692,
"step": 1990
},
{
"epoch": 0.10578512396694215,
"grad_norm": 128.131103515625,
"learning_rate": 0.00015944,
"loss": 4.2632,
"step": 2000
},
{
"epoch": 0.10631404958677686,
"grad_norm": 158.20382690429688,
"learning_rate": 0.00016024000000000002,
"loss": 4.2025,
"step": 2010
},
{
"epoch": 0.10684297520661157,
"grad_norm": 129.88511657714844,
"learning_rate": 0.00016104000000000002,
"loss": 4.3182,
"step": 2020
},
{
"epoch": 0.10737190082644628,
"grad_norm": 99.9822006225586,
"learning_rate": 0.00016184,
"loss": 4.2665,
"step": 2030
},
{
"epoch": 0.10790082644628099,
"grad_norm": 109.63304138183594,
"learning_rate": 0.00016264,
"loss": 4.1677,
"step": 2040
},
{
"epoch": 0.1084297520661157,
"grad_norm": 129.84288024902344,
"learning_rate": 0.00016344000000000002,
"loss": 4.2211,
"step": 2050
},
{
"epoch": 0.10895867768595041,
"grad_norm": 173.83929443359375,
"learning_rate": 0.00016424,
"loss": 4.177,
"step": 2060
},
{
"epoch": 0.10948760330578512,
"grad_norm": 152.7726287841797,
"learning_rate": 0.00016504,
"loss": 4.0519,
"step": 2070
},
{
"epoch": 0.11001652892561983,
"grad_norm": 99.01861572265625,
"learning_rate": 0.00016584000000000002,
"loss": 4.1148,
"step": 2080
},
{
"epoch": 0.11054545454545454,
"grad_norm": 149.03744506835938,
"learning_rate": 0.00016664000000000002,
"loss": 4.1625,
"step": 2090
},
{
"epoch": 0.11107438016528925,
"grad_norm": 76.12191009521484,
"learning_rate": 0.00016744,
"loss": 4.145,
"step": 2100
},
{
"epoch": 0.11160330578512397,
"grad_norm": 105.04821014404297,
"learning_rate": 0.00016824,
"loss": 4.0494,
"step": 2110
},
{
"epoch": 0.11213223140495868,
"grad_norm": 98.34203338623047,
"learning_rate": 0.00016904,
"loss": 4.0551,
"step": 2120
},
{
"epoch": 0.11266115702479339,
"grad_norm": 138.1121063232422,
"learning_rate": 0.00016984,
"loss": 3.9701,
"step": 2130
},
{
"epoch": 0.1131900826446281,
"grad_norm": 140.3077392578125,
"learning_rate": 0.00017064,
"loss": 4.0075,
"step": 2140
},
{
"epoch": 0.11371900826446281,
"grad_norm": 154.5470428466797,
"learning_rate": 0.00017144,
"loss": 4.1154,
"step": 2150
},
{
"epoch": 0.11424793388429752,
"grad_norm": 131.924072265625,
"learning_rate": 0.00017224,
"loss": 4.0457,
"step": 2160
},
{
"epoch": 0.11477685950413223,
"grad_norm": 77.7768325805664,
"learning_rate": 0.00017304,
"loss": 3.8566,
"step": 2170
},
{
"epoch": 0.11530578512396694,
"grad_norm": 164.1995086669922,
"learning_rate": 0.00017384,
"loss": 3.9619,
"step": 2180
},
{
"epoch": 0.11583471074380165,
"grad_norm": 81.0079345703125,
"learning_rate": 0.00017464,
"loss": 4.0439,
"step": 2190
},
{
"epoch": 0.11636363636363636,
"grad_norm": 120.98047637939453,
"learning_rate": 0.00017544000000000001,
"loss": 3.9237,
"step": 2200
},
{
"epoch": 0.11689256198347107,
"grad_norm": 114.70262145996094,
"learning_rate": 0.00017624,
"loss": 3.9856,
"step": 2210
},
{
"epoch": 0.11742148760330579,
"grad_norm": 161.363525390625,
"learning_rate": 0.00017704,
"loss": 3.8999,
"step": 2220
},
{
"epoch": 0.1179504132231405,
"grad_norm": 123.91844177246094,
"learning_rate": 0.00017784000000000002,
"loss": 3.9258,
"step": 2230
},
{
"epoch": 0.11847933884297521,
"grad_norm": 144.61944580078125,
"learning_rate": 0.00017864,
"loss": 3.9065,
"step": 2240
},
{
"epoch": 0.11900826446280992,
"grad_norm": 121.40870666503906,
"learning_rate": 0.00017944,
"loss": 3.858,
"step": 2250
},
{
"epoch": 0.11953719008264463,
"grad_norm": 76.07757568359375,
"learning_rate": 0.00018024,
"loss": 3.8494,
"step": 2260
},
{
"epoch": 0.12006611570247934,
"grad_norm": 99.82099914550781,
"learning_rate": 0.00018104000000000001,
"loss": 3.8841,
"step": 2270
},
{
"epoch": 0.12059504132231405,
"grad_norm": 121.70137786865234,
"learning_rate": 0.00018184,
"loss": 3.8417,
"step": 2280
},
{
"epoch": 0.12112396694214876,
"grad_norm": 152.82870483398438,
"learning_rate": 0.00018264,
"loss": 3.8361,
"step": 2290
},
{
"epoch": 0.12165289256198347,
"grad_norm": 117.6900405883789,
"learning_rate": 0.00018344000000000002,
"loss": 3.8021,
"step": 2300
},
{
"epoch": 0.12218181818181818,
"grad_norm": 103.37924194335938,
"learning_rate": 0.00018424,
"loss": 3.7797,
"step": 2310
},
{
"epoch": 0.1227107438016529,
"grad_norm": 102.50745391845703,
"learning_rate": 0.00018504,
"loss": 3.7944,
"step": 2320
},
{
"epoch": 0.1232396694214876,
"grad_norm": 120.54622650146484,
"learning_rate": 0.00018584000000000002,
"loss": 3.7223,
"step": 2330
},
{
"epoch": 0.12376859504132232,
"grad_norm": 105.47157287597656,
"learning_rate": 0.00018664000000000002,
"loss": 3.8349,
"step": 2340
},
{
"epoch": 0.12429752066115703,
"grad_norm": 96.26775360107422,
"learning_rate": 0.00018744,
"loss": 3.7478,
"step": 2350
},
{
"epoch": 0.12482644628099174,
"grad_norm": 94.46358489990234,
"learning_rate": 0.00018824000000000003,
"loss": 3.8027,
"step": 2360
},
{
"epoch": 0.12535537190082643,
"grad_norm": 78.01036071777344,
"learning_rate": 0.00018904000000000002,
"loss": 3.7505,
"step": 2370
},
{
"epoch": 0.12588429752066116,
"grad_norm": 143.33291625976562,
"learning_rate": 0.00018984,
"loss": 3.6221,
"step": 2380
},
{
"epoch": 0.12641322314049586,
"grad_norm": 89.04401397705078,
"learning_rate": 0.00019064000000000003,
"loss": 3.7705,
"step": 2390
},
{
"epoch": 0.12694214876033058,
"grad_norm": 111.32374572753906,
"learning_rate": 0.00019144000000000002,
"loss": 3.6446,
"step": 2400
},
{
"epoch": 0.12747107438016528,
"grad_norm": 98.54373168945312,
"learning_rate": 0.00019224000000000002,
"loss": 3.6462,
"step": 2410
},
{
"epoch": 0.128,
"grad_norm": 97.3410415649414,
"learning_rate": 0.00019304,
"loss": 3.6436,
"step": 2420
},
{
"epoch": 0.1285289256198347,
"grad_norm": 109.594482421875,
"learning_rate": 0.00019384,
"loss": 3.5529,
"step": 2430
},
{
"epoch": 0.12905785123966942,
"grad_norm": 70.01071166992188,
"learning_rate": 0.00019464,
"loss": 3.5879,
"step": 2440
},
{
"epoch": 0.12958677685950412,
"grad_norm": 69.51897430419922,
"learning_rate": 0.00019544,
"loss": 3.6464,
"step": 2450
},
{
"epoch": 0.13011570247933885,
"grad_norm": 120.34490966796875,
"learning_rate": 0.00019624,
"loss": 3.484,
"step": 2460
},
{
"epoch": 0.13064462809917354,
"grad_norm": 118.81869506835938,
"learning_rate": 0.00019704,
"loss": 3.6032,
"step": 2470
},
{
"epoch": 0.13117355371900827,
"grad_norm": 67.180419921875,
"learning_rate": 0.00019784,
"loss": 3.6563,
"step": 2480
},
{
"epoch": 0.13170247933884296,
"grad_norm": 125.26102447509766,
"learning_rate": 0.00019864,
"loss": 3.5318,
"step": 2490
},
{
"epoch": 0.1322314049586777,
"grad_norm": 59.11252975463867,
"learning_rate": 0.00019944,
"loss": 3.4811,
"step": 2500
},
{
"epoch": 0.1327603305785124,
"grad_norm": 82.9197006225586,
"learning_rate": 0.00020024000000000002,
"loss": 3.4466,
"step": 2510
},
{
"epoch": 0.1332892561983471,
"grad_norm": 100.01235961914062,
"learning_rate": 0.00020104000000000004,
"loss": 3.5225,
"step": 2520
},
{
"epoch": 0.1338181818181818,
"grad_norm": 87.4695816040039,
"learning_rate": 0.00020184000000000003,
"loss": 3.4633,
"step": 2530
},
{
"epoch": 0.13434710743801653,
"grad_norm": 101.63253021240234,
"learning_rate": 0.00020264000000000002,
"loss": 3.4765,
"step": 2540
},
{
"epoch": 0.13487603305785123,
"grad_norm": 83.96656799316406,
"learning_rate": 0.00020344000000000002,
"loss": 3.4347,
"step": 2550
},
{
"epoch": 0.13540495867768595,
"grad_norm": 76.25411224365234,
"learning_rate": 0.00020424000000000004,
"loss": 3.4415,
"step": 2560
},
{
"epoch": 0.13593388429752065,
"grad_norm": 67.98944091796875,
"learning_rate": 0.00020503999999999997,
"loss": 3.5213,
"step": 2570
},
{
"epoch": 0.13646280991735538,
"grad_norm": 50.266517639160156,
"learning_rate": 0.00020584,
"loss": 3.4601,
"step": 2580
},
{
"epoch": 0.13699173553719007,
"grad_norm": 76.60093688964844,
"learning_rate": 0.00020664,
"loss": 3.3739,
"step": 2590
},
{
"epoch": 0.1375206611570248,
"grad_norm": 74.61274719238281,
"learning_rate": 0.00020743999999999998,
"loss": 3.3986,
"step": 2600
},
{
"epoch": 0.1380495867768595,
"grad_norm": 51.82277297973633,
"learning_rate": 0.00020824,
"loss": 3.409,
"step": 2610
},
{
"epoch": 0.13857851239669422,
"grad_norm": 79.22560119628906,
"learning_rate": 0.00020904,
"loss": 3.2819,
"step": 2620
},
{
"epoch": 0.13910743801652892,
"grad_norm": 65.86051177978516,
"learning_rate": 0.00020983999999999998,
"loss": 3.3017,
"step": 2630
},
{
"epoch": 0.13963636363636364,
"grad_norm": 64.04843139648438,
"learning_rate": 0.00021064,
"loss": 3.3024,
"step": 2640
},
{
"epoch": 0.14016528925619834,
"grad_norm": 69.44876098632812,
"learning_rate": 0.00021144,
"loss": 3.3733,
"step": 2650
},
{
"epoch": 0.14069421487603306,
"grad_norm": 66.78265380859375,
"learning_rate": 0.00021224,
"loss": 3.2764,
"step": 2660
},
{
"epoch": 0.14122314049586776,
"grad_norm": 53.78641891479492,
"learning_rate": 0.00021304,
"loss": 3.279,
"step": 2670
},
{
"epoch": 0.14175206611570249,
"grad_norm": 94.14802551269531,
"learning_rate": 0.00021384,
"loss": 3.1926,
"step": 2680
},
{
"epoch": 0.14228099173553718,
"grad_norm": 61.65810012817383,
"learning_rate": 0.00021464,
"loss": 3.2856,
"step": 2690
},
{
"epoch": 0.1428099173553719,
"grad_norm": 64.04943084716797,
"learning_rate": 0.00021544,
"loss": 3.2339,
"step": 2700
}
],
"logging_steps": 10,
"max_steps": 10000000,
"num_input_tokens_seen": 0,
"num_train_epochs": 529,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.70709830602752e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}