qwen3-4b-agent-v8 / trainer_state.json
SELEE's picture
Upload full fine-tuned Qwen3-4B-Instruct-2507 model (auto-generated README)
42b13a0 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1480,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013527223537368955,
"grad_norm": 110.5,
"learning_rate": 1.2162162162162163e-07,
"loss": 2.9783,
"step": 10
},
{
"epoch": 0.02705444707473791,
"grad_norm": 113.0,
"learning_rate": 2.567567567567567e-07,
"loss": 3.0679,
"step": 20
},
{
"epoch": 0.040581670612106865,
"grad_norm": 106.0,
"learning_rate": 3.918918918918919e-07,
"loss": 3.0966,
"step": 30
},
{
"epoch": 0.05410889414947582,
"grad_norm": 102.5,
"learning_rate": 5.270270270270269e-07,
"loss": 2.9748,
"step": 40
},
{
"epoch": 0.06763611768684477,
"grad_norm": 95.5,
"learning_rate": 6.621621621621622e-07,
"loss": 2.9264,
"step": 50
},
{
"epoch": 0.08116334122421373,
"grad_norm": 85.5,
"learning_rate": 7.972972972972972e-07,
"loss": 2.7277,
"step": 60
},
{
"epoch": 0.09469056476158269,
"grad_norm": 85.5,
"learning_rate": 9.324324324324324e-07,
"loss": 2.6271,
"step": 70
},
{
"epoch": 0.10821778829895164,
"grad_norm": 96.0,
"learning_rate": 1.0675675675675675e-06,
"loss": 2.4285,
"step": 80
},
{
"epoch": 0.1217450118363206,
"grad_norm": 70.0,
"learning_rate": 1.2027027027027026e-06,
"loss": 2.0623,
"step": 90
},
{
"epoch": 0.13527223537368954,
"grad_norm": 54.5,
"learning_rate": 1.3378378378378378e-06,
"loss": 1.7022,
"step": 100
},
{
"epoch": 0.1487994589110585,
"grad_norm": 31.5,
"learning_rate": 1.472972972972973e-06,
"loss": 1.4259,
"step": 110
},
{
"epoch": 0.16232668244842746,
"grad_norm": 19.375,
"learning_rate": 1.608108108108108e-06,
"loss": 1.1437,
"step": 120
},
{
"epoch": 0.17585390598579642,
"grad_norm": 13.0,
"learning_rate": 1.743243243243243e-06,
"loss": 0.9886,
"step": 130
},
{
"epoch": 0.18938112952316538,
"grad_norm": 9.625,
"learning_rate": 1.8783783783783783e-06,
"loss": 0.8594,
"step": 140
},
{
"epoch": 0.2029083530605343,
"grad_norm": 8.5,
"learning_rate": 1.9999972186150605e-06,
"loss": 0.7673,
"step": 150
},
{
"epoch": 0.21643557659790327,
"grad_norm": 5.78125,
"learning_rate": 1.9996634711432784e-06,
"loss": 0.7322,
"step": 160
},
{
"epoch": 0.22996280013527223,
"grad_norm": 6.09375,
"learning_rate": 1.9987736594069414e-06,
"loss": 0.6586,
"step": 170
},
{
"epoch": 0.2434900236726412,
"grad_norm": 5.40625,
"learning_rate": 1.997328278365126e-06,
"loss": 0.6214,
"step": 180
},
{
"epoch": 0.2570172472100101,
"grad_norm": 7.15625,
"learning_rate": 1.9953281320131465e-06,
"loss": 0.5825,
"step": 190
},
{
"epoch": 0.2705444707473791,
"grad_norm": 5.1875,
"learning_rate": 1.992774332935329e-06,
"loss": 0.5826,
"step": 200
},
{
"epoch": 0.28407169428474804,
"grad_norm": 4.875,
"learning_rate": 1.989668301686138e-06,
"loss": 0.5562,
"step": 210
},
{
"epoch": 0.297598917822117,
"grad_norm": 6.0625,
"learning_rate": 1.9860117659999875e-06,
"loss": 0.5323,
"step": 220
},
{
"epoch": 0.31112614135948596,
"grad_norm": 5.40625,
"learning_rate": 1.981806759830189e-06,
"loss": 0.5352,
"step": 230
},
{
"epoch": 0.3246533648968549,
"grad_norm": 5.3125,
"learning_rate": 1.9770556222175607e-06,
"loss": 0.5354,
"step": 240
},
{
"epoch": 0.3381805884342239,
"grad_norm": 4.125,
"learning_rate": 1.9717609959893315e-06,
"loss": 0.4923,
"step": 250
},
{
"epoch": 0.35170781197159284,
"grad_norm": 4.6875,
"learning_rate": 1.965925826289068e-06,
"loss": 0.4907,
"step": 260
},
{
"epoch": 0.3652350355089618,
"grad_norm": 5.34375,
"learning_rate": 1.9595533589384306e-06,
"loss": 0.4875,
"step": 270
},
{
"epoch": 0.37876225904633076,
"grad_norm": 5.09375,
"learning_rate": 1.952647138631682e-06,
"loss": 0.4771,
"step": 280
},
{
"epoch": 0.3922894825836997,
"grad_norm": 6.1875,
"learning_rate": 1.945211006963945e-06,
"loss": 0.4683,
"step": 290
},
{
"epoch": 0.4058167061210686,
"grad_norm": 4.96875,
"learning_rate": 1.937249100294311e-06,
"loss": 0.4597,
"step": 300
},
{
"epoch": 0.4193439296584376,
"grad_norm": 5.6875,
"learning_rate": 1.9287658474449836e-06,
"loss": 0.4553,
"step": 310
},
{
"epoch": 0.43287115319580655,
"grad_norm": 4.46875,
"learning_rate": 1.9197659672377386e-06,
"loss": 0.4499,
"step": 320
},
{
"epoch": 0.4463983767331755,
"grad_norm": 5.25,
"learning_rate": 1.9102544658690745e-06,
"loss": 0.4559,
"step": 330
},
{
"epoch": 0.45992560027054447,
"grad_norm": 4.625,
"learning_rate": 1.9002366341255067e-06,
"loss": 0.4354,
"step": 340
},
{
"epoch": 0.4734528238079134,
"grad_norm": 5.8125,
"learning_rate": 1.8897180444405612e-06,
"loss": 0.4524,
"step": 350
},
{
"epoch": 0.4869800473452824,
"grad_norm": 6.28125,
"learning_rate": 1.8787045477950988e-06,
"loss": 0.4259,
"step": 360
},
{
"epoch": 0.5005072708826513,
"grad_norm": 5.1875,
"learning_rate": 1.8672022704627e-06,
"loss": 0.4254,
"step": 370
},
{
"epoch": 0.5140344944200202,
"grad_norm": 5.875,
"learning_rate": 1.8552176106019153e-06,
"loss": 0.43,
"step": 380
},
{
"epoch": 0.5275617179573893,
"grad_norm": 6.65625,
"learning_rate": 1.8427572346972803e-06,
"loss": 0.415,
"step": 390
},
{
"epoch": 0.5410889414947582,
"grad_norm": 5.4375,
"learning_rate": 1.829828073851075e-06,
"loss": 0.4145,
"step": 400
},
{
"epoch": 0.5546161650321272,
"grad_norm": 6.90625,
"learning_rate": 1.8164373199278855e-06,
"loss": 0.4049,
"step": 410
},
{
"epoch": 0.5681433885694961,
"grad_norm": 4.90625,
"learning_rate": 1.8025924215541229e-06,
"loss": 0.4087,
"step": 420
},
{
"epoch": 0.5816706121068651,
"grad_norm": 5.8125,
"learning_rate": 1.7883010799747095e-06,
"loss": 0.4131,
"step": 430
},
{
"epoch": 0.595197835644234,
"grad_norm": 8.0,
"learning_rate": 1.7735712447692536e-06,
"loss": 0.4282,
"step": 440
},
{
"epoch": 0.608725059181603,
"grad_norm": 4.46875,
"learning_rate": 1.7584111094300824e-06,
"loss": 0.4094,
"step": 450
},
{
"epoch": 0.6222522827189719,
"grad_norm": 4.84375,
"learning_rate": 1.7428291068045998e-06,
"loss": 0.3987,
"step": 460
},
{
"epoch": 0.6357795062563408,
"grad_norm": 5.125,
"learning_rate": 1.726833904404504e-06,
"loss": 0.3932,
"step": 470
},
{
"epoch": 0.6493067297937098,
"grad_norm": 6.25,
"learning_rate": 1.7104343995844715e-06,
"loss": 0.4026,
"step": 480
},
{
"epoch": 0.6628339533310788,
"grad_norm": 5.25,
"learning_rate": 1.6936397145929877e-06,
"loss": 0.4307,
"step": 490
},
{
"epoch": 0.6763611768684478,
"grad_norm": 5.53125,
"learning_rate": 1.676459191498087e-06,
"loss": 0.3874,
"step": 500
},
{
"epoch": 0.6898884004058167,
"grad_norm": 6.03125,
"learning_rate": 1.6589023869908107e-06,
"loss": 0.3754,
"step": 510
},
{
"epoch": 0.7034156239431857,
"grad_norm": 7.21875,
"learning_rate": 1.6409790670692858e-06,
"loss": 0.3837,
"step": 520
},
{
"epoch": 0.7169428474805546,
"grad_norm": 6.3125,
"learning_rate": 1.6226992016063724e-06,
"loss": 0.3889,
"step": 530
},
{
"epoch": 0.7304700710179236,
"grad_norm": 6.125,
"learning_rate": 1.6040729588039088e-06,
"loss": 0.3778,
"step": 540
},
{
"epoch": 0.7439972945552925,
"grad_norm": 7.5,
"learning_rate": 1.5851106995366337e-06,
"loss": 0.3654,
"step": 550
},
{
"epoch": 0.7575245180926615,
"grad_norm": 7.125,
"learning_rate": 1.5658229715889345e-06,
"loss": 0.3725,
"step": 560
},
{
"epoch": 0.7710517416300304,
"grad_norm": 5.84375,
"learning_rate": 1.5462205037876272e-06,
"loss": 0.3743,
"step": 570
},
{
"epoch": 0.7845789651673994,
"grad_norm": 7.03125,
"learning_rate": 1.526314200034031e-06,
"loss": 0.39,
"step": 580
},
{
"epoch": 0.7981061887047683,
"grad_norm": 8.1875,
"learning_rate": 1.5061151332386564e-06,
"loss": 0.3562,
"step": 590
},
{
"epoch": 0.8116334122421373,
"grad_norm": 6.625,
"learning_rate": 1.4856345391618827e-06,
"loss": 0.3658,
"step": 600
},
{
"epoch": 0.8251606357795063,
"grad_norm": 6.4375,
"learning_rate": 1.4648838101640517e-06,
"loss": 0.3547,
"step": 610
},
{
"epoch": 0.8386878593168752,
"grad_norm": 5.75,
"learning_rate": 1.443874488868448e-06,
"loss": 0.3692,
"step": 620
},
{
"epoch": 0.8522150828542442,
"grad_norm": 7.03125,
"learning_rate": 1.4226182617406994e-06,
"loss": 0.3878,
"step": 630
},
{
"epoch": 0.8657423063916131,
"grad_norm": 6.875,
"learning_rate": 1.4011269525881635e-06,
"loss": 0.371,
"step": 640
},
{
"epoch": 0.8792695299289821,
"grad_norm": 7.03125,
"learning_rate": 1.379412515982917e-06,
"loss": 0.3665,
"step": 650
},
{
"epoch": 0.892796753466351,
"grad_norm": 9.6875,
"learning_rate": 1.3574870306120077e-06,
"loss": 0.3801,
"step": 660
},
{
"epoch": 0.90632397700372,
"grad_norm": 9.5,
"learning_rate": 1.335362692558667e-06,
"loss": 0.3746,
"step": 670
},
{
"epoch": 0.9198512005410889,
"grad_norm": 6.4375,
"learning_rate": 1.3130518085182222e-06,
"loss": 0.3675,
"step": 680
},
{
"epoch": 0.933378424078458,
"grad_norm": 7.21875,
"learning_rate": 1.2905667889524769e-06,
"loss": 0.3494,
"step": 690
},
{
"epoch": 0.9469056476158269,
"grad_norm": 7.09375,
"learning_rate": 1.2679201411863749e-06,
"loss": 0.3706,
"step": 700
},
{
"epoch": 0.9604328711531958,
"grad_norm": 6.0,
"learning_rate": 1.245124462450783e-06,
"loss": 0.3664,
"step": 710
},
{
"epoch": 0.9739600946905648,
"grad_norm": 5.8125,
"learning_rate": 1.2221924328752616e-06,
"loss": 0.3694,
"step": 720
},
{
"epoch": 0.9874873182279337,
"grad_norm": 7.65625,
"learning_rate": 1.199136808434725e-06,
"loss": 0.3601,
"step": 730
},
{
"epoch": 1.0,
"grad_norm": 13.0625,
"learning_rate": 1.1759704138539119e-06,
"loss": 0.3654,
"step": 740
},
{
"epoch": 1.013527223537369,
"grad_norm": 8.0625,
"learning_rate": 1.1527061354736127e-06,
"loss": 0.3354,
"step": 750
},
{
"epoch": 1.0270544470747378,
"grad_norm": 6.21875,
"learning_rate": 1.1293569140826237e-06,
"loss": 0.3584,
"step": 760
},
{
"epoch": 1.040581670612107,
"grad_norm": 7.625,
"learning_rate": 1.105935737719416e-06,
"loss": 0.3522,
"step": 770
},
{
"epoch": 1.0541088941494758,
"grad_norm": 8.125,
"learning_rate": 1.082455634447518e-06,
"loss": 0.3658,
"step": 780
},
{
"epoch": 1.0676361176868447,
"grad_norm": 6.46875,
"learning_rate": 1.0589296651086376e-06,
"loss": 0.3669,
"step": 790
},
{
"epoch": 1.0811633412242136,
"grad_norm": 6.0,
"learning_rate": 1.0353709160575487e-06,
"loss": 0.3513,
"step": 800
},
{
"epoch": 1.0946905647615828,
"grad_norm": 5.59375,
"learning_rate": 1.011792491882789e-06,
"loss": 0.3563,
"step": 810
},
{
"epoch": 1.1082177882989517,
"grad_norm": 6.3125,
"learning_rate": 9.882075081172112e-07,
"loss": 0.3527,
"step": 820
},
{
"epoch": 1.1217450118363206,
"grad_norm": 6.09375,
"learning_rate": 9.646290839424514e-07,
"loss": 0.351,
"step": 830
},
{
"epoch": 1.1352722353736895,
"grad_norm": 7.40625,
"learning_rate": 9.410703348913626e-07,
"loss": 0.363,
"step": 840
},
{
"epoch": 1.1487994589110584,
"grad_norm": 6.21875,
"learning_rate": 9.17544365552482e-07,
"loss": 0.3461,
"step": 850
},
{
"epoch": 1.1623266824484275,
"grad_norm": 9.1875,
"learning_rate": 8.94064262280584e-07,
"loss": 0.341,
"step": 860
},
{
"epoch": 1.1758539059857964,
"grad_norm": 6.75,
"learning_rate": 8.706430859173763e-07,
"loss": 0.3629,
"step": 870
},
{
"epoch": 1.1893811295231653,
"grad_norm": 5.84375,
"learning_rate": 8.472938645263874e-07,
"loss": 0.3517,
"step": 880
},
{
"epoch": 1.2029083530605342,
"grad_norm": 6.5625,
"learning_rate": 8.24029586146088e-07,
"loss": 0.3583,
"step": 890
},
{
"epoch": 1.2164355765979034,
"grad_norm": 6.28125,
"learning_rate": 8.00863191565275e-07,
"loss": 0.3587,
"step": 900
},
{
"epoch": 1.2299628001352723,
"grad_norm": 5.625,
"learning_rate": 7.778075671247385e-07,
"loss": 0.3413,
"step": 910
},
{
"epoch": 1.2434900236726412,
"grad_norm": 6.5625,
"learning_rate": 7.548755375492172e-07,
"loss": 0.3496,
"step": 920
},
{
"epoch": 1.25701724721001,
"grad_norm": 5.9375,
"learning_rate": 7.320798588136253e-07,
"loss": 0.346,
"step": 930
},
{
"epoch": 1.270544470747379,
"grad_norm": 6.0625,
"learning_rate": 7.094332110475234e-07,
"loss": 0.3389,
"step": 940
},
{
"epoch": 1.284071694284748,
"grad_norm": 7.34375,
"learning_rate": 6.869481914817779e-07,
"loss": 0.3491,
"step": 950
},
{
"epoch": 1.297598917822117,
"grad_norm": 7.21875,
"learning_rate": 6.646373074413329e-07,
"loss": 0.3394,
"step": 960
},
{
"epoch": 1.311126141359486,
"grad_norm": 9.5,
"learning_rate": 6.425129693879925e-07,
"loss": 0.3489,
"step": 970
},
{
"epoch": 1.324653364896855,
"grad_norm": 6.375,
"learning_rate": 6.205874840170832e-07,
"loss": 0.3424,
"step": 980
},
{
"epoch": 1.338180588434224,
"grad_norm": 6.96875,
"learning_rate": 5.988730474118367e-07,
"loss": 0.3559,
"step": 990
},
{
"epoch": 1.3517078119715928,
"grad_norm": 5.5625,
"learning_rate": 5.773817382593007e-07,
"loss": 0.3402,
"step": 1000
},
{
"epoch": 1.3652350355089617,
"grad_norm": 8.25,
"learning_rate": 5.561255111315523e-07,
"loss": 0.3494,
"step": 1010
},
{
"epoch": 1.3787622590463307,
"grad_norm": 6.40625,
"learning_rate": 5.351161898359484e-07,
"loss": 0.3321,
"step": 1020
},
{
"epoch": 1.3922894825836998,
"grad_norm": 9.5625,
"learning_rate": 5.143654608381171e-07,
"loss": 0.3432,
"step": 1030
},
{
"epoch": 1.4058167061210687,
"grad_norm": 6.90625,
"learning_rate": 4.938848667613436e-07,
"loss": 0.3378,
"step": 1040
},
{
"epoch": 1.4193439296584376,
"grad_norm": 7.6875,
"learning_rate": 4.7368579996596903e-07,
"loss": 0.3529,
"step": 1050
},
{
"epoch": 1.4328711531958065,
"grad_norm": 6.3125,
"learning_rate": 4.5377949621237255e-07,
"loss": 0.3541,
"step": 1060
},
{
"epoch": 1.4463983767331756,
"grad_norm": 6.0,
"learning_rate": 4.341770284110655e-07,
"loss": 0.3264,
"step": 1070
},
{
"epoch": 1.4599256002705445,
"grad_norm": 6.3125,
"learning_rate": 4.1488930046336623e-07,
"loss": 0.3408,
"step": 1080
},
{
"epoch": 1.4734528238079134,
"grad_norm": 8.25,
"learning_rate": 3.9592704119609124e-07,
"loss": 0.363,
"step": 1090
},
{
"epoch": 1.4869800473452823,
"grad_norm": 6.59375,
"learning_rate": 3.773007983936275e-07,
"loss": 0.3512,
"step": 1100
},
{
"epoch": 1.5005072708826512,
"grad_norm": 9.3125,
"learning_rate": 3.5902093293071423e-07,
"loss": 0.335,
"step": 1110
},
{
"epoch": 1.5140344944200201,
"grad_norm": 6.3125,
"learning_rate": 3.4109761300918917e-07,
"loss": 0.3461,
"step": 1120
},
{
"epoch": 1.5275617179573893,
"grad_norm": 6.53125,
"learning_rate": 3.2354080850191325e-07,
"loss": 0.3425,
"step": 1130
},
{
"epoch": 1.5410889414947582,
"grad_norm": 6.625,
"learning_rate": 3.0636028540701233e-07,
"loss": 0.34,
"step": 1140
},
{
"epoch": 1.5546161650321273,
"grad_norm": 6.75,
"learning_rate": 2.895656004155288e-07,
"loss": 0.3464,
"step": 1150
},
{
"epoch": 1.5681433885694962,
"grad_norm": 5.875,
"learning_rate": 2.7316609559549563e-07,
"loss": 0.341,
"step": 1160
},
{
"epoch": 1.581670612106865,
"grad_norm": 8.1875,
"learning_rate": 2.571708931954e-07,
"loss": 0.3426,
"step": 1170
},
{
"epoch": 1.595197835644234,
"grad_norm": 6.375,
"learning_rate": 2.4158889056991773e-07,
"loss": 0.3494,
"step": 1180
},
{
"epoch": 1.608725059181603,
"grad_norm": 6.625,
"learning_rate": 2.2642875523074613e-07,
"loss": 0.3509,
"step": 1190
},
{
"epoch": 1.6222522827189718,
"grad_norm": 5.9375,
"learning_rate": 2.1169892002529044e-07,
"loss": 0.3508,
"step": 1200
},
{
"epoch": 1.6357795062563407,
"grad_norm": 7.75,
"learning_rate": 1.9740757844587708e-07,
"loss": 0.3542,
"step": 1210
},
{
"epoch": 1.6493067297937098,
"grad_norm": 5.875,
"learning_rate": 1.835626800721144e-07,
"loss": 0.3559,
"step": 1220
},
{
"epoch": 1.6628339533310788,
"grad_norm": 5.75,
"learning_rate": 1.7017192614892506e-07,
"loss": 0.33,
"step": 1230
},
{
"epoch": 1.6763611768684479,
"grad_norm": 6.8125,
"learning_rate": 1.5724276530271962e-07,
"loss": 0.3553,
"step": 1240
},
{
"epoch": 1.6898884004058168,
"grad_norm": 6.625,
"learning_rate": 1.447823893980845e-07,
"loss": 0.3394,
"step": 1250
},
{
"epoch": 1.7034156239431857,
"grad_norm": 6.75,
"learning_rate": 1.3279772953729983e-07,
"loss": 0.3379,
"step": 1260
},
{
"epoch": 1.7169428474805546,
"grad_norm": 8.25,
"learning_rate": 1.21295452204901e-07,
"loss": 0.3532,
"step": 1270
},
{
"epoch": 1.7304700710179235,
"grad_norm": 6.5625,
"learning_rate": 1.1028195555943876e-07,
"loss": 0.3352,
"step": 1280
},
{
"epoch": 1.7439972945552924,
"grad_norm": 5.5,
"learning_rate": 9.976336587449307e-08,
"loss": 0.3532,
"step": 1290
},
{
"epoch": 1.7575245180926615,
"grad_norm": 8.75,
"learning_rate": 8.974553413092556e-08,
"loss": 0.3405,
"step": 1300
},
{
"epoch": 1.7710517416300304,
"grad_norm": 6.4375,
"learning_rate": 8.023403276226127e-08,
"loss": 0.3612,
"step": 1310
},
{
"epoch": 1.7845789651673996,
"grad_norm": 6.46875,
"learning_rate": 7.123415255501652e-08,
"loss": 0.3513,
"step": 1320
},
{
"epoch": 1.7981061887047685,
"grad_norm": 7.625,
"learning_rate": 6.27508997056888e-08,
"loss": 0.3525,
"step": 1330
},
{
"epoch": 1.8116334122421374,
"grad_norm": 6.78125,
"learning_rate": 5.478899303605511e-08,
"loss": 0.3466,
"step": 1340
},
{
"epoch": 1.8251606357795063,
"grad_norm": 6.15625,
"learning_rate": 4.735286136831806e-08,
"loss": 0.3486,
"step": 1350
},
{
"epoch": 1.8386878593168752,
"grad_norm": 6.65625,
"learning_rate": 4.0446641061569144e-08,
"loss": 0.3363,
"step": 1360
},
{
"epoch": 1.852215082854244,
"grad_norm": 7.84375,
"learning_rate": 3.4074173710931796e-08,
"loss": 0.3437,
"step": 1370
},
{
"epoch": 1.865742306391613,
"grad_norm": 8.0625,
"learning_rate": 2.8239004010668367e-08,
"loss": 0.3358,
"step": 1380
},
{
"epoch": 1.879269529928982,
"grad_norm": 7.09375,
"learning_rate": 2.294437778243963e-08,
"loss": 0.3632,
"step": 1390
},
{
"epoch": 1.892796753466351,
"grad_norm": 6.375,
"learning_rate": 1.8193240169810942e-08,
"loss": 0.381,
"step": 1400
},
{
"epoch": 1.9063239770037201,
"grad_norm": 6.3125,
"learning_rate": 1.3988234000012367e-08,
"loss": 0.3476,
"step": 1410
},
{
"epoch": 1.919851200541089,
"grad_norm": 6.71875,
"learning_rate": 1.0331698313861937e-08,
"loss": 0.3403,
"step": 1420
},
{
"epoch": 1.933378424078458,
"grad_norm": 6.1875,
"learning_rate": 7.22566706467076e-09,
"loss": 0.345,
"step": 1430
},
{
"epoch": 1.9469056476158269,
"grad_norm": 6.5625,
"learning_rate": 4.6718679868533725e-09,
"loss": 0.3618,
"step": 1440
},
{
"epoch": 1.9604328711531958,
"grad_norm": 7.78125,
"learning_rate": 2.671721634873725e-09,
"loss": 0.3297,
"step": 1450
},
{
"epoch": 1.9739600946905647,
"grad_norm": 7.46875,
"learning_rate": 1.2263405930585947e-09,
"loss": 0.3393,
"step": 1460
},
{
"epoch": 1.9874873182279336,
"grad_norm": 7.125,
"learning_rate": 3.365288567216407e-10,
"loss": 0.362,
"step": 1470
},
{
"epoch": 2.0,
"grad_norm": 11.3125,
"learning_rate": 2.7813849394764386e-12,
"loss": 0.3342,
"step": 1480
}
],
"logging_steps": 10,
"max_steps": 1480,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.144769262871982e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}