ryusangwon's picture
End of training
2ba3ffe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7153075822603719,
"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": 4.988078206962327e-05,
"loss": 1.7518,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.976156413924655e-05,
"loss": 1.7804,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.964234620886982e-05,
"loss": 1.727,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.9523128278493086e-05,
"loss": 1.6974,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.940391034811636e-05,
"loss": 1.6927,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.928469241773963e-05,
"loss": 1.6302,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.91654744873629e-05,
"loss": 1.6878,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.904625655698618e-05,
"loss": 1.6706,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.8927038626609446e-05,
"loss": 1.6709,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.8807820696232716e-05,
"loss": 1.6876,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.868860276585599e-05,
"loss": 1.6377,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 4.856938483547926e-05,
"loss": 1.6348,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.845016690510253e-05,
"loss": 1.6682,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.8330948974725806e-05,
"loss": 1.632,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.8211731044349076e-05,
"loss": 1.663,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.8092513113972345e-05,
"loss": 1.6638,
"step": 160
},
{
"epoch": 0.12,
"learning_rate": 4.7973295183595614e-05,
"loss": 1.5964,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.785407725321889e-05,
"loss": 1.6738,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 4.773485932284216e-05,
"loss": 1.6489,
"step": 190
},
{
"epoch": 0.14,
"learning_rate": 4.761564139246543e-05,
"loss": 1.6609,
"step": 200
},
{
"epoch": 0.15,
"learning_rate": 4.74964234620887e-05,
"loss": 1.6356,
"step": 210
},
{
"epoch": 0.16,
"learning_rate": 4.7377205531711974e-05,
"loss": 1.6409,
"step": 220
},
{
"epoch": 0.16,
"learning_rate": 4.7257987601335244e-05,
"loss": 1.6418,
"step": 230
},
{
"epoch": 0.17,
"learning_rate": 4.713876967095851e-05,
"loss": 1.6824,
"step": 240
},
{
"epoch": 0.18,
"learning_rate": 4.701955174058178e-05,
"loss": 1.6345,
"step": 250
},
{
"epoch": 0.19,
"learning_rate": 4.690033381020505e-05,
"loss": 1.6219,
"step": 260
},
{
"epoch": 0.19,
"learning_rate": 4.678111587982833e-05,
"loss": 1.6633,
"step": 270
},
{
"epoch": 0.2,
"learning_rate": 4.66618979494516e-05,
"loss": 1.6067,
"step": 280
},
{
"epoch": 0.21,
"learning_rate": 4.6542680019074866e-05,
"loss": 1.653,
"step": 290
},
{
"epoch": 0.21,
"learning_rate": 4.642346208869814e-05,
"loss": 1.6371,
"step": 300
},
{
"epoch": 0.22,
"learning_rate": 4.630424415832141e-05,
"loss": 1.6492,
"step": 310
},
{
"epoch": 0.23,
"learning_rate": 4.618502622794468e-05,
"loss": 1.6222,
"step": 320
},
{
"epoch": 0.24,
"learning_rate": 4.606580829756796e-05,
"loss": 1.6677,
"step": 330
},
{
"epoch": 0.24,
"learning_rate": 4.5946590367191226e-05,
"loss": 1.595,
"step": 340
},
{
"epoch": 0.25,
"learning_rate": 4.5827372436814496e-05,
"loss": 1.6309,
"step": 350
},
{
"epoch": 0.26,
"learning_rate": 4.570815450643777e-05,
"loss": 1.6098,
"step": 360
},
{
"epoch": 0.26,
"learning_rate": 4.558893657606104e-05,
"loss": 1.6175,
"step": 370
},
{
"epoch": 0.27,
"learning_rate": 4.546971864568431e-05,
"loss": 1.6127,
"step": 380
},
{
"epoch": 0.28,
"learning_rate": 4.5350500715307586e-05,
"loss": 1.6326,
"step": 390
},
{
"epoch": 0.29,
"learning_rate": 4.5231282784930856e-05,
"loss": 1.626,
"step": 400
},
{
"epoch": 0.29,
"learning_rate": 4.5112064854554125e-05,
"loss": 1.5784,
"step": 410
},
{
"epoch": 0.3,
"learning_rate": 4.49928469241774e-05,
"loss": 1.6449,
"step": 420
},
{
"epoch": 0.31,
"learning_rate": 4.487362899380067e-05,
"loss": 1.619,
"step": 430
},
{
"epoch": 0.31,
"learning_rate": 4.475441106342394e-05,
"loss": 1.636,
"step": 440
},
{
"epoch": 0.32,
"learning_rate": 4.4635193133047216e-05,
"loss": 1.6003,
"step": 450
},
{
"epoch": 0.33,
"learning_rate": 4.4515975202670485e-05,
"loss": 1.623,
"step": 460
},
{
"epoch": 0.34,
"learning_rate": 4.4396757272293754e-05,
"loss": 1.6109,
"step": 470
},
{
"epoch": 0.34,
"learning_rate": 4.4277539341917024e-05,
"loss": 1.656,
"step": 480
},
{
"epoch": 0.35,
"learning_rate": 4.41583214115403e-05,
"loss": 1.6107,
"step": 490
},
{
"epoch": 0.36,
"learning_rate": 4.403910348116357e-05,
"loss": 1.6136,
"step": 500
},
{
"epoch": 0.36,
"learning_rate": 4.391988555078684e-05,
"loss": 1.6333,
"step": 510
},
{
"epoch": 0.37,
"learning_rate": 4.3800667620410114e-05,
"loss": 1.6259,
"step": 520
},
{
"epoch": 0.38,
"learning_rate": 4.3681449690033384e-05,
"loss": 1.6519,
"step": 530
},
{
"epoch": 0.39,
"learning_rate": 4.356223175965665e-05,
"loss": 1.6325,
"step": 540
},
{
"epoch": 0.39,
"learning_rate": 4.344301382927993e-05,
"loss": 1.632,
"step": 550
},
{
"epoch": 0.4,
"learning_rate": 4.33237958989032e-05,
"loss": 1.6382,
"step": 560
},
{
"epoch": 0.41,
"learning_rate": 4.320457796852647e-05,
"loss": 1.6114,
"step": 570
},
{
"epoch": 0.41,
"learning_rate": 4.3085360038149744e-05,
"loss": 1.5911,
"step": 580
},
{
"epoch": 0.42,
"learning_rate": 4.296614210777301e-05,
"loss": 1.629,
"step": 590
},
{
"epoch": 0.43,
"learning_rate": 4.284692417739628e-05,
"loss": 1.6607,
"step": 600
},
{
"epoch": 0.44,
"learning_rate": 4.272770624701956e-05,
"loss": 1.6122,
"step": 610
},
{
"epoch": 0.44,
"learning_rate": 4.260848831664283e-05,
"loss": 1.5969,
"step": 620
},
{
"epoch": 0.45,
"learning_rate": 4.24892703862661e-05,
"loss": 1.6497,
"step": 630
},
{
"epoch": 0.46,
"learning_rate": 4.237005245588937e-05,
"loss": 1.6098,
"step": 640
},
{
"epoch": 0.46,
"learning_rate": 4.225083452551264e-05,
"loss": 1.6341,
"step": 650
},
{
"epoch": 0.47,
"learning_rate": 4.213161659513591e-05,
"loss": 1.6244,
"step": 660
},
{
"epoch": 0.48,
"learning_rate": 4.201239866475918e-05,
"loss": 1.6425,
"step": 670
},
{
"epoch": 0.49,
"learning_rate": 4.189318073438245e-05,
"loss": 1.6436,
"step": 680
},
{
"epoch": 0.49,
"learning_rate": 4.1773962804005726e-05,
"loss": 1.6319,
"step": 690
},
{
"epoch": 0.5,
"learning_rate": 4.1654744873628996e-05,
"loss": 1.6273,
"step": 700
},
{
"epoch": 0.51,
"learning_rate": 4.1535526943252265e-05,
"loss": 1.6348,
"step": 710
},
{
"epoch": 0.52,
"learning_rate": 4.1416309012875534e-05,
"loss": 1.6447,
"step": 720
},
{
"epoch": 0.52,
"learning_rate": 4.129709108249881e-05,
"loss": 1.637,
"step": 730
},
{
"epoch": 0.53,
"learning_rate": 4.117787315212208e-05,
"loss": 1.603,
"step": 740
},
{
"epoch": 0.54,
"learning_rate": 4.105865522174535e-05,
"loss": 1.6257,
"step": 750
},
{
"epoch": 0.54,
"learning_rate": 4.0939437291368625e-05,
"loss": 1.6277,
"step": 760
},
{
"epoch": 0.55,
"learning_rate": 4.0820219360991894e-05,
"loss": 1.6331,
"step": 770
},
{
"epoch": 0.56,
"learning_rate": 4.0701001430615164e-05,
"loss": 1.6434,
"step": 780
},
{
"epoch": 0.57,
"learning_rate": 4.058178350023844e-05,
"loss": 1.6513,
"step": 790
},
{
"epoch": 0.57,
"learning_rate": 4.046256556986171e-05,
"loss": 1.6015,
"step": 800
},
{
"epoch": 0.58,
"learning_rate": 4.034334763948498e-05,
"loss": 1.6598,
"step": 810
},
{
"epoch": 0.59,
"learning_rate": 4.022412970910825e-05,
"loss": 1.6007,
"step": 820
},
{
"epoch": 0.59,
"learning_rate": 4.0104911778731524e-05,
"loss": 1.5911,
"step": 830
},
{
"epoch": 0.6,
"learning_rate": 3.998569384835479e-05,
"loss": 1.637,
"step": 840
},
{
"epoch": 0.61,
"learning_rate": 3.986647591797806e-05,
"loss": 1.572,
"step": 850
},
{
"epoch": 0.62,
"learning_rate": 3.974725798760134e-05,
"loss": 1.6409,
"step": 860
},
{
"epoch": 0.62,
"learning_rate": 3.962804005722461e-05,
"loss": 1.641,
"step": 870
},
{
"epoch": 0.63,
"learning_rate": 3.950882212684788e-05,
"loss": 1.6375,
"step": 880
},
{
"epoch": 0.64,
"learning_rate": 3.938960419647115e-05,
"loss": 1.6491,
"step": 890
},
{
"epoch": 0.64,
"learning_rate": 3.927038626609442e-05,
"loss": 1.6672,
"step": 900
},
{
"epoch": 0.65,
"learning_rate": 3.915116833571769e-05,
"loss": 1.6263,
"step": 910
},
{
"epoch": 0.66,
"learning_rate": 3.903195040534097e-05,
"loss": 1.5962,
"step": 920
},
{
"epoch": 0.67,
"learning_rate": 3.891273247496424e-05,
"loss": 1.6026,
"step": 930
},
{
"epoch": 0.67,
"learning_rate": 3.8793514544587506e-05,
"loss": 1.645,
"step": 940
},
{
"epoch": 0.68,
"learning_rate": 3.867429661421078e-05,
"loss": 1.6275,
"step": 950
},
{
"epoch": 0.69,
"learning_rate": 3.855507868383405e-05,
"loss": 1.6154,
"step": 960
},
{
"epoch": 0.69,
"learning_rate": 3.843586075345732e-05,
"loss": 1.6322,
"step": 970
},
{
"epoch": 0.7,
"learning_rate": 3.83166428230806e-05,
"loss": 1.6122,
"step": 980
},
{
"epoch": 0.71,
"learning_rate": 3.8197424892703866e-05,
"loss": 1.6158,
"step": 990
},
{
"epoch": 0.72,
"learning_rate": 3.8078206962327136e-05,
"loss": 1.5995,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4194,
"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
}