ryusangwon's picture
End of training
2ba3ffe verified
raw
history blame
12.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7468259895444361,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.98755290017426e-05,
"loss": 1.7894,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.975105800348519e-05,
"loss": 1.7882,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.962658700522779e-05,
"loss": 1.7888,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.9502116006970375e-05,
"loss": 1.7571,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.937764500871298e-05,
"loss": 1.6783,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.9253174010455565e-05,
"loss": 1.7087,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.912870301219816e-05,
"loss": 1.6953,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.9004232013940755e-05,
"loss": 1.7138,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 4.887976101568335e-05,
"loss": 1.7006,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.8755290017425944e-05,
"loss": 1.7249,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.863081901916854e-05,
"loss": 1.7191,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 4.850634802091113e-05,
"loss": 1.7209,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 4.838187702265373e-05,
"loss": 1.7355,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.825740602439632e-05,
"loss": 1.7021,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.813293502613891e-05,
"loss": 1.6662,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 4.800846402788151e-05,
"loss": 1.6849,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 4.78839930296241e-05,
"loss": 1.6748,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.7759522031366697e-05,
"loss": 1.6886,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 4.763505103310929e-05,
"loss": 1.6572,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 4.751058003485188e-05,
"loss": 1.7132,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 4.738610903659448e-05,
"loss": 1.7098,
"step": 210
},
{
"epoch": 0.16,
"learning_rate": 4.726163803833707e-05,
"loss": 1.7283,
"step": 220
},
{
"epoch": 0.17,
"learning_rate": 4.7137167040079664e-05,
"loss": 1.7039,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 4.701269604182226e-05,
"loss": 1.6921,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 4.6888225043564854e-05,
"loss": 1.6824,
"step": 250
},
{
"epoch": 0.19,
"learning_rate": 4.676375404530744e-05,
"loss": 1.7253,
"step": 260
},
{
"epoch": 0.2,
"learning_rate": 4.6639283047050044e-05,
"loss": 1.6768,
"step": 270
},
{
"epoch": 0.21,
"learning_rate": 4.651481204879263e-05,
"loss": 1.6796,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 4.6390341050535227e-05,
"loss": 1.7304,
"step": 290
},
{
"epoch": 0.22,
"learning_rate": 4.626587005227782e-05,
"loss": 1.7468,
"step": 300
},
{
"epoch": 0.23,
"learning_rate": 4.6141399054020416e-05,
"loss": 1.6347,
"step": 310
},
{
"epoch": 0.24,
"learning_rate": 4.601692805576301e-05,
"loss": 1.676,
"step": 320
},
{
"epoch": 0.25,
"learning_rate": 4.5892457057505606e-05,
"loss": 1.66,
"step": 330
},
{
"epoch": 0.25,
"learning_rate": 4.5767986059248194e-05,
"loss": 1.6637,
"step": 340
},
{
"epoch": 0.26,
"learning_rate": 4.5643515060990796e-05,
"loss": 1.6949,
"step": 350
},
{
"epoch": 0.27,
"learning_rate": 4.5519044062733384e-05,
"loss": 1.6827,
"step": 360
},
{
"epoch": 0.28,
"learning_rate": 4.539457306447598e-05,
"loss": 1.657,
"step": 370
},
{
"epoch": 0.28,
"learning_rate": 4.5270102066218574e-05,
"loss": 1.6471,
"step": 380
},
{
"epoch": 0.29,
"learning_rate": 4.514563106796117e-05,
"loss": 1.6854,
"step": 390
},
{
"epoch": 0.3,
"learning_rate": 4.502116006970376e-05,
"loss": 1.6739,
"step": 400
},
{
"epoch": 0.31,
"learning_rate": 4.489668907144636e-05,
"loss": 1.6935,
"step": 410
},
{
"epoch": 0.31,
"learning_rate": 4.4772218073188946e-05,
"loss": 1.6717,
"step": 420
},
{
"epoch": 0.32,
"learning_rate": 4.464774707493155e-05,
"loss": 1.668,
"step": 430
},
{
"epoch": 0.33,
"learning_rate": 4.4523276076674136e-05,
"loss": 1.623,
"step": 440
},
{
"epoch": 0.34,
"learning_rate": 4.439880507841673e-05,
"loss": 1.6589,
"step": 450
},
{
"epoch": 0.34,
"learning_rate": 4.4274334080159326e-05,
"loss": 1.6845,
"step": 460
},
{
"epoch": 0.35,
"learning_rate": 4.414986308190192e-05,
"loss": 1.6748,
"step": 470
},
{
"epoch": 0.36,
"learning_rate": 4.4025392083644516e-05,
"loss": 1.6744,
"step": 480
},
{
"epoch": 0.37,
"learning_rate": 4.390092108538711e-05,
"loss": 1.6794,
"step": 490
},
{
"epoch": 0.37,
"learning_rate": 4.37764500871297e-05,
"loss": 1.6958,
"step": 500
},
{
"epoch": 0.38,
"learning_rate": 4.36519790888723e-05,
"loss": 1.689,
"step": 510
},
{
"epoch": 0.39,
"learning_rate": 4.352750809061489e-05,
"loss": 1.673,
"step": 520
},
{
"epoch": 0.4,
"learning_rate": 4.340303709235748e-05,
"loss": 1.6969,
"step": 530
},
{
"epoch": 0.4,
"learning_rate": 4.327856609410008e-05,
"loss": 1.6572,
"step": 540
},
{
"epoch": 0.41,
"learning_rate": 4.315409509584267e-05,
"loss": 1.6773,
"step": 550
},
{
"epoch": 0.42,
"learning_rate": 4.302962409758526e-05,
"loss": 1.7103,
"step": 560
},
{
"epoch": 0.43,
"learning_rate": 4.290515309932786e-05,
"loss": 1.6945,
"step": 570
},
{
"epoch": 0.43,
"learning_rate": 4.278068210107045e-05,
"loss": 1.6924,
"step": 580
},
{
"epoch": 0.44,
"learning_rate": 4.2656211102813046e-05,
"loss": 1.663,
"step": 590
},
{
"epoch": 0.45,
"learning_rate": 4.253174010455564e-05,
"loss": 1.7125,
"step": 600
},
{
"epoch": 0.46,
"learning_rate": 4.2407269106298235e-05,
"loss": 1.6773,
"step": 610
},
{
"epoch": 0.46,
"learning_rate": 4.228279810804083e-05,
"loss": 1.6429,
"step": 620
},
{
"epoch": 0.47,
"learning_rate": 4.2158327109783425e-05,
"loss": 1.647,
"step": 630
},
{
"epoch": 0.48,
"learning_rate": 4.203385611152601e-05,
"loss": 1.6819,
"step": 640
},
{
"epoch": 0.49,
"learning_rate": 4.1909385113268615e-05,
"loss": 1.6821,
"step": 650
},
{
"epoch": 0.49,
"learning_rate": 4.17849141150112e-05,
"loss": 1.6817,
"step": 660
},
{
"epoch": 0.5,
"learning_rate": 4.16604431167538e-05,
"loss": 1.7326,
"step": 670
},
{
"epoch": 0.51,
"learning_rate": 4.153597211849639e-05,
"loss": 1.7005,
"step": 680
},
{
"epoch": 0.52,
"learning_rate": 4.141150112023899e-05,
"loss": 1.6551,
"step": 690
},
{
"epoch": 0.52,
"learning_rate": 4.128703012198158e-05,
"loss": 1.6715,
"step": 700
},
{
"epoch": 0.53,
"learning_rate": 4.116255912372418e-05,
"loss": 1.6409,
"step": 710
},
{
"epoch": 0.54,
"learning_rate": 4.1038088125466765e-05,
"loss": 1.7092,
"step": 720
},
{
"epoch": 0.55,
"learning_rate": 4.091361712720937e-05,
"loss": 1.7256,
"step": 730
},
{
"epoch": 0.55,
"learning_rate": 4.0789146128951955e-05,
"loss": 1.6652,
"step": 740
},
{
"epoch": 0.56,
"learning_rate": 4.066467513069455e-05,
"loss": 1.7242,
"step": 750
},
{
"epoch": 0.57,
"learning_rate": 4.0540204132437145e-05,
"loss": 1.6713,
"step": 760
},
{
"epoch": 0.58,
"learning_rate": 4.041573313417974e-05,
"loss": 1.6638,
"step": 770
},
{
"epoch": 0.58,
"learning_rate": 4.029126213592233e-05,
"loss": 1.6803,
"step": 780
},
{
"epoch": 0.59,
"learning_rate": 4.016679113766493e-05,
"loss": 1.6866,
"step": 790
},
{
"epoch": 0.6,
"learning_rate": 4.004232013940752e-05,
"loss": 1.6938,
"step": 800
},
{
"epoch": 0.6,
"learning_rate": 3.991784914115011e-05,
"loss": 1.6803,
"step": 810
},
{
"epoch": 0.61,
"learning_rate": 3.979337814289271e-05,
"loss": 1.686,
"step": 820
},
{
"epoch": 0.62,
"learning_rate": 3.96689071446353e-05,
"loss": 1.6646,
"step": 830
},
{
"epoch": 0.63,
"learning_rate": 3.95444361463779e-05,
"loss": 1.6767,
"step": 840
},
{
"epoch": 0.63,
"learning_rate": 3.941996514812049e-05,
"loss": 1.6823,
"step": 850
},
{
"epoch": 0.64,
"learning_rate": 3.929549414986308e-05,
"loss": 1.6679,
"step": 860
},
{
"epoch": 0.65,
"learning_rate": 3.917102315160568e-05,
"loss": 1.6843,
"step": 870
},
{
"epoch": 0.66,
"learning_rate": 3.904655215334827e-05,
"loss": 1.6083,
"step": 880
},
{
"epoch": 0.66,
"learning_rate": 3.8922081155090865e-05,
"loss": 1.6627,
"step": 890
},
{
"epoch": 0.67,
"learning_rate": 3.879761015683346e-05,
"loss": 1.6619,
"step": 900
},
{
"epoch": 0.68,
"learning_rate": 3.8673139158576054e-05,
"loss": 1.7028,
"step": 910
},
{
"epoch": 0.69,
"learning_rate": 3.854866816031865e-05,
"loss": 1.7299,
"step": 920
},
{
"epoch": 0.69,
"learning_rate": 3.8424197162061244e-05,
"loss": 1.6906,
"step": 930
},
{
"epoch": 0.7,
"learning_rate": 3.829972616380383e-05,
"loss": 1.7047,
"step": 940
},
{
"epoch": 0.71,
"learning_rate": 3.8175255165546434e-05,
"loss": 1.6661,
"step": 950
},
{
"epoch": 0.72,
"learning_rate": 3.805078416728902e-05,
"loss": 1.6984,
"step": 960
},
{
"epoch": 0.72,
"learning_rate": 3.792631316903162e-05,
"loss": 1.6619,
"step": 970
},
{
"epoch": 0.73,
"learning_rate": 3.780184217077421e-05,
"loss": 1.7073,
"step": 980
},
{
"epoch": 0.74,
"learning_rate": 3.7677371172516806e-05,
"loss": 1.6487,
"step": 990
},
{
"epoch": 0.75,
"learning_rate": 3.7552900174259395e-05,
"loss": 1.6707,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4017,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6.3202482192384e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}