ryusangwon's picture
End of training
2ba3ffe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.702247191011236,
"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": 4.988295880149813e-05,
"loss": 1.7828,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.976591760299626e-05,
"loss": 1.7581,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.964887640449438e-05,
"loss": 1.7499,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.953183520599251e-05,
"loss": 1.7351,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.941479400749064e-05,
"loss": 1.6748,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.929775280898877e-05,
"loss": 1.6994,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.918071161048689e-05,
"loss": 1.6761,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.906367041198502e-05,
"loss": 1.6459,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.8946629213483144e-05,
"loss": 1.6372,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.882958801498127e-05,
"loss": 1.6715,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.87125468164794e-05,
"loss": 1.6141,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 4.859550561797753e-05,
"loss": 1.6354,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.8478464419475654e-05,
"loss": 1.6343,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.836142322097378e-05,
"loss": 1.6072,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.824438202247191e-05,
"loss": 1.6131,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.812734082397004e-05,
"loss": 1.6301,
"step": 160
},
{
"epoch": 0.12,
"learning_rate": 4.801029962546817e-05,
"loss": 1.597,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.789325842696629e-05,
"loss": 1.5489,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 4.777621722846442e-05,
"loss": 1.5998,
"step": 190
},
{
"epoch": 0.14,
"learning_rate": 4.765917602996255e-05,
"loss": 1.6023,
"step": 200
},
{
"epoch": 0.15,
"learning_rate": 4.754213483146068e-05,
"loss": 1.6847,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 4.742509363295881e-05,
"loss": 1.5816,
"step": 220
},
{
"epoch": 0.16,
"learning_rate": 4.730805243445693e-05,
"loss": 1.673,
"step": 230
},
{
"epoch": 0.17,
"learning_rate": 4.719101123595506e-05,
"loss": 1.6192,
"step": 240
},
{
"epoch": 0.18,
"learning_rate": 4.707397003745318e-05,
"loss": 1.6183,
"step": 250
},
{
"epoch": 0.18,
"learning_rate": 4.695692883895131e-05,
"loss": 1.6262,
"step": 260
},
{
"epoch": 0.19,
"learning_rate": 4.683988764044944e-05,
"loss": 1.5945,
"step": 270
},
{
"epoch": 0.2,
"learning_rate": 4.6722846441947563e-05,
"loss": 1.659,
"step": 280
},
{
"epoch": 0.2,
"learning_rate": 4.660580524344569e-05,
"loss": 1.6135,
"step": 290
},
{
"epoch": 0.21,
"learning_rate": 4.648876404494382e-05,
"loss": 1.6102,
"step": 300
},
{
"epoch": 0.22,
"learning_rate": 4.637172284644195e-05,
"loss": 1.6202,
"step": 310
},
{
"epoch": 0.22,
"learning_rate": 4.625468164794008e-05,
"loss": 1.6499,
"step": 320
},
{
"epoch": 0.23,
"learning_rate": 4.61376404494382e-05,
"loss": 1.656,
"step": 330
},
{
"epoch": 0.24,
"learning_rate": 4.602059925093633e-05,
"loss": 1.629,
"step": 340
},
{
"epoch": 0.25,
"learning_rate": 4.590355805243446e-05,
"loss": 1.6194,
"step": 350
},
{
"epoch": 0.25,
"learning_rate": 4.578651685393259e-05,
"loss": 1.6308,
"step": 360
},
{
"epoch": 0.26,
"learning_rate": 4.566947565543072e-05,
"loss": 1.6013,
"step": 370
},
{
"epoch": 0.27,
"learning_rate": 4.555243445692884e-05,
"loss": 1.6103,
"step": 380
},
{
"epoch": 0.27,
"learning_rate": 4.543539325842697e-05,
"loss": 1.6281,
"step": 390
},
{
"epoch": 0.28,
"learning_rate": 4.531835205992509e-05,
"loss": 1.5684,
"step": 400
},
{
"epoch": 0.29,
"learning_rate": 4.520131086142322e-05,
"loss": 1.6165,
"step": 410
},
{
"epoch": 0.29,
"learning_rate": 4.508426966292135e-05,
"loss": 1.6187,
"step": 420
},
{
"epoch": 0.3,
"learning_rate": 4.496722846441947e-05,
"loss": 1.6211,
"step": 430
},
{
"epoch": 0.31,
"learning_rate": 4.48501872659176e-05,
"loss": 1.6104,
"step": 440
},
{
"epoch": 0.32,
"learning_rate": 4.473314606741573e-05,
"loss": 1.6058,
"step": 450
},
{
"epoch": 0.32,
"learning_rate": 4.461610486891386e-05,
"loss": 1.5639,
"step": 460
},
{
"epoch": 0.33,
"learning_rate": 4.449906367041199e-05,
"loss": 1.5879,
"step": 470
},
{
"epoch": 0.34,
"learning_rate": 4.438202247191011e-05,
"loss": 1.5911,
"step": 480
},
{
"epoch": 0.34,
"learning_rate": 4.426498127340824e-05,
"loss": 1.6679,
"step": 490
},
{
"epoch": 0.35,
"learning_rate": 4.414794007490637e-05,
"loss": 1.578,
"step": 500
},
{
"epoch": 0.36,
"learning_rate": 4.40308988764045e-05,
"loss": 1.6275,
"step": 510
},
{
"epoch": 0.37,
"learning_rate": 4.391385767790263e-05,
"loss": 1.5811,
"step": 520
},
{
"epoch": 0.37,
"learning_rate": 4.379681647940075e-05,
"loss": 1.5688,
"step": 530
},
{
"epoch": 0.38,
"learning_rate": 4.367977528089888e-05,
"loss": 1.6364,
"step": 540
},
{
"epoch": 0.39,
"learning_rate": 4.3562734082397e-05,
"loss": 1.5866,
"step": 550
},
{
"epoch": 0.39,
"learning_rate": 4.344569288389513e-05,
"loss": 1.6161,
"step": 560
},
{
"epoch": 0.4,
"learning_rate": 4.332865168539326e-05,
"loss": 1.6424,
"step": 570
},
{
"epoch": 0.41,
"learning_rate": 4.321161048689138e-05,
"loss": 1.623,
"step": 580
},
{
"epoch": 0.41,
"learning_rate": 4.309456928838951e-05,
"loss": 1.5842,
"step": 590
},
{
"epoch": 0.42,
"learning_rate": 4.297752808988764e-05,
"loss": 1.6077,
"step": 600
},
{
"epoch": 0.43,
"learning_rate": 4.286048689138577e-05,
"loss": 1.6583,
"step": 610
},
{
"epoch": 0.44,
"learning_rate": 4.27434456928839e-05,
"loss": 1.6026,
"step": 620
},
{
"epoch": 0.44,
"learning_rate": 4.262640449438202e-05,
"loss": 1.6292,
"step": 630
},
{
"epoch": 0.45,
"learning_rate": 4.250936329588015e-05,
"loss": 1.6292,
"step": 640
},
{
"epoch": 0.46,
"learning_rate": 4.239232209737828e-05,
"loss": 1.5891,
"step": 650
},
{
"epoch": 0.46,
"learning_rate": 4.227528089887641e-05,
"loss": 1.6386,
"step": 660
},
{
"epoch": 0.47,
"learning_rate": 4.215823970037454e-05,
"loss": 1.6162,
"step": 670
},
{
"epoch": 0.48,
"learning_rate": 4.204119850187267e-05,
"loss": 1.5891,
"step": 680
},
{
"epoch": 0.48,
"learning_rate": 4.192415730337079e-05,
"loss": 1.614,
"step": 690
},
{
"epoch": 0.49,
"learning_rate": 4.180711610486892e-05,
"loss": 1.6487,
"step": 700
},
{
"epoch": 0.5,
"learning_rate": 4.169007490636704e-05,
"loss": 1.6591,
"step": 710
},
{
"epoch": 0.51,
"learning_rate": 4.157303370786517e-05,
"loss": 1.5986,
"step": 720
},
{
"epoch": 0.51,
"learning_rate": 4.14559925093633e-05,
"loss": 1.6107,
"step": 730
},
{
"epoch": 0.52,
"learning_rate": 4.133895131086142e-05,
"loss": 1.6195,
"step": 740
},
{
"epoch": 0.53,
"learning_rate": 4.122191011235955e-05,
"loss": 1.6278,
"step": 750
},
{
"epoch": 0.53,
"learning_rate": 4.110486891385768e-05,
"loss": 1.5987,
"step": 760
},
{
"epoch": 0.54,
"learning_rate": 4.098782771535581e-05,
"loss": 1.5816,
"step": 770
},
{
"epoch": 0.55,
"learning_rate": 4.087078651685394e-05,
"loss": 1.6183,
"step": 780
},
{
"epoch": 0.55,
"learning_rate": 4.075374531835206e-05,
"loss": 1.5796,
"step": 790
},
{
"epoch": 0.56,
"learning_rate": 4.063670411985019e-05,
"loss": 1.6078,
"step": 800
},
{
"epoch": 0.57,
"learning_rate": 4.051966292134832e-05,
"loss": 1.5659,
"step": 810
},
{
"epoch": 0.58,
"learning_rate": 4.040262172284645e-05,
"loss": 1.6024,
"step": 820
},
{
"epoch": 0.58,
"learning_rate": 4.028558052434458e-05,
"loss": 1.6321,
"step": 830
},
{
"epoch": 0.59,
"learning_rate": 4.01685393258427e-05,
"loss": 1.6139,
"step": 840
},
{
"epoch": 0.6,
"learning_rate": 4.005149812734083e-05,
"loss": 1.5753,
"step": 850
},
{
"epoch": 0.6,
"learning_rate": 3.993445692883895e-05,
"loss": 1.6109,
"step": 860
},
{
"epoch": 0.61,
"learning_rate": 3.981741573033708e-05,
"loss": 1.6098,
"step": 870
},
{
"epoch": 0.62,
"learning_rate": 3.970037453183521e-05,
"loss": 1.6277,
"step": 880
},
{
"epoch": 0.62,
"learning_rate": 3.958333333333333e-05,
"loss": 1.661,
"step": 890
},
{
"epoch": 0.63,
"learning_rate": 3.946629213483146e-05,
"loss": 1.6179,
"step": 900
},
{
"epoch": 0.64,
"learning_rate": 3.934925093632959e-05,
"loss": 1.6417,
"step": 910
},
{
"epoch": 0.65,
"learning_rate": 3.923220973782772e-05,
"loss": 1.622,
"step": 920
},
{
"epoch": 0.65,
"learning_rate": 3.911516853932585e-05,
"loss": 1.6275,
"step": 930
},
{
"epoch": 0.66,
"learning_rate": 3.899812734082397e-05,
"loss": 1.6297,
"step": 940
},
{
"epoch": 0.67,
"learning_rate": 3.88810861423221e-05,
"loss": 1.6049,
"step": 950
},
{
"epoch": 0.67,
"learning_rate": 3.876404494382023e-05,
"loss": 1.6347,
"step": 960
},
{
"epoch": 0.68,
"learning_rate": 3.864700374531836e-05,
"loss": 1.5998,
"step": 970
},
{
"epoch": 0.69,
"learning_rate": 3.8529962546816486e-05,
"loss": 1.6305,
"step": 980
},
{
"epoch": 0.7,
"learning_rate": 3.841292134831461e-05,
"loss": 1.6281,
"step": 990
},
{
"epoch": 0.7,
"learning_rate": 3.829588014981274e-05,
"loss": 1.6223,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4272,
"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
}