ryusangwon's picture
End of training
2ba3ffe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6906077348066298,
"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": 4.9884898710865566e-05,
"loss": 1.803,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.976979742173112e-05,
"loss": 1.781,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.965469613259669e-05,
"loss": 1.721,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.953959484346225e-05,
"loss": 1.6942,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 4.942449355432781e-05,
"loss": 1.7153,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.930939226519337e-05,
"loss": 1.6549,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.919429097605893e-05,
"loss": 1.6161,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.9079189686924495e-05,
"loss": 1.6448,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.896408839779006e-05,
"loss": 1.602,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.884898710865562e-05,
"loss": 1.6401,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.873388581952118e-05,
"loss": 1.5939,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 4.861878453038674e-05,
"loss": 1.6273,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.8503683241252305e-05,
"loss": 1.5847,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.838858195211787e-05,
"loss": 1.6303,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.8273480662983425e-05,
"loss": 1.5958,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.815837937384899e-05,
"loss": 1.628,
"step": 160
},
{
"epoch": 0.12,
"learning_rate": 4.804327808471455e-05,
"loss": 1.6073,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 4.7928176795580114e-05,
"loss": 1.6069,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 4.781307550644568e-05,
"loss": 1.5774,
"step": 190
},
{
"epoch": 0.14,
"learning_rate": 4.7697974217311234e-05,
"loss": 1.5908,
"step": 200
},
{
"epoch": 0.15,
"learning_rate": 4.75828729281768e-05,
"loss": 1.6272,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 4.746777163904236e-05,
"loss": 1.5789,
"step": 220
},
{
"epoch": 0.16,
"learning_rate": 4.7352670349907924e-05,
"loss": 1.6184,
"step": 230
},
{
"epoch": 0.17,
"learning_rate": 4.723756906077349e-05,
"loss": 1.5601,
"step": 240
},
{
"epoch": 0.17,
"learning_rate": 4.7122467771639044e-05,
"loss": 1.6025,
"step": 250
},
{
"epoch": 0.18,
"learning_rate": 4.700736648250461e-05,
"loss": 1.5405,
"step": 260
},
{
"epoch": 0.19,
"learning_rate": 4.6892265193370164e-05,
"loss": 1.5928,
"step": 270
},
{
"epoch": 0.19,
"learning_rate": 4.6777163904235734e-05,
"loss": 1.5753,
"step": 280
},
{
"epoch": 0.2,
"learning_rate": 4.666206261510129e-05,
"loss": 1.6019,
"step": 290
},
{
"epoch": 0.21,
"learning_rate": 4.6546961325966854e-05,
"loss": 1.6118,
"step": 300
},
{
"epoch": 0.21,
"learning_rate": 4.643186003683242e-05,
"loss": 1.6183,
"step": 310
},
{
"epoch": 0.22,
"learning_rate": 4.6316758747697973e-05,
"loss": 1.5882,
"step": 320
},
{
"epoch": 0.23,
"learning_rate": 4.6201657458563544e-05,
"loss": 1.5797,
"step": 330
},
{
"epoch": 0.23,
"learning_rate": 4.60865561694291e-05,
"loss": 1.6227,
"step": 340
},
{
"epoch": 0.24,
"learning_rate": 4.597145488029466e-05,
"loss": 1.5912,
"step": 350
},
{
"epoch": 0.25,
"learning_rate": 4.585635359116022e-05,
"loss": 1.5672,
"step": 360
},
{
"epoch": 0.26,
"learning_rate": 4.574125230202578e-05,
"loss": 1.612,
"step": 370
},
{
"epoch": 0.26,
"learning_rate": 4.5626151012891346e-05,
"loss": 1.6161,
"step": 380
},
{
"epoch": 0.27,
"learning_rate": 4.551104972375691e-05,
"loss": 1.6061,
"step": 390
},
{
"epoch": 0.28,
"learning_rate": 4.539594843462247e-05,
"loss": 1.5733,
"step": 400
},
{
"epoch": 0.28,
"learning_rate": 4.528084714548803e-05,
"loss": 1.5949,
"step": 410
},
{
"epoch": 0.29,
"learning_rate": 4.516574585635359e-05,
"loss": 1.6355,
"step": 420
},
{
"epoch": 0.3,
"learning_rate": 4.505064456721915e-05,
"loss": 1.6296,
"step": 430
},
{
"epoch": 0.3,
"learning_rate": 4.493554327808472e-05,
"loss": 1.592,
"step": 440
},
{
"epoch": 0.31,
"learning_rate": 4.4820441988950276e-05,
"loss": 1.5712,
"step": 450
},
{
"epoch": 0.32,
"learning_rate": 4.470534069981584e-05,
"loss": 1.6086,
"step": 460
},
{
"epoch": 0.32,
"learning_rate": 4.45902394106814e-05,
"loss": 1.5757,
"step": 470
},
{
"epoch": 0.33,
"learning_rate": 4.447513812154696e-05,
"loss": 1.5885,
"step": 480
},
{
"epoch": 0.34,
"learning_rate": 4.436003683241253e-05,
"loss": 1.5828,
"step": 490
},
{
"epoch": 0.35,
"learning_rate": 4.4244935543278086e-05,
"loss": 1.5782,
"step": 500
},
{
"epoch": 0.35,
"learning_rate": 4.412983425414365e-05,
"loss": 1.6,
"step": 510
},
{
"epoch": 0.36,
"learning_rate": 4.401473296500921e-05,
"loss": 1.5992,
"step": 520
},
{
"epoch": 0.37,
"learning_rate": 4.389963167587477e-05,
"loss": 1.5709,
"step": 530
},
{
"epoch": 0.37,
"learning_rate": 4.378453038674034e-05,
"loss": 1.5642,
"step": 540
},
{
"epoch": 0.38,
"learning_rate": 4.3669429097605895e-05,
"loss": 1.6253,
"step": 550
},
{
"epoch": 0.39,
"learning_rate": 4.355432780847146e-05,
"loss": 1.5742,
"step": 560
},
{
"epoch": 0.39,
"learning_rate": 4.3439226519337015e-05,
"loss": 1.5912,
"step": 570
},
{
"epoch": 0.4,
"learning_rate": 4.332412523020258e-05,
"loss": 1.587,
"step": 580
},
{
"epoch": 0.41,
"learning_rate": 4.320902394106814e-05,
"loss": 1.5834,
"step": 590
},
{
"epoch": 0.41,
"learning_rate": 4.3093922651933705e-05,
"loss": 1.6063,
"step": 600
},
{
"epoch": 0.42,
"learning_rate": 4.297882136279927e-05,
"loss": 1.5801,
"step": 610
},
{
"epoch": 0.43,
"learning_rate": 4.2863720073664825e-05,
"loss": 1.5947,
"step": 620
},
{
"epoch": 0.44,
"learning_rate": 4.274861878453039e-05,
"loss": 1.6001,
"step": 630
},
{
"epoch": 0.44,
"learning_rate": 4.263351749539595e-05,
"loss": 1.6476,
"step": 640
},
{
"epoch": 0.45,
"learning_rate": 4.2518416206261515e-05,
"loss": 1.6008,
"step": 650
},
{
"epoch": 0.46,
"learning_rate": 4.240331491712707e-05,
"loss": 1.6011,
"step": 660
},
{
"epoch": 0.46,
"learning_rate": 4.2288213627992634e-05,
"loss": 1.603,
"step": 670
},
{
"epoch": 0.47,
"learning_rate": 4.21731123388582e-05,
"loss": 1.5862,
"step": 680
},
{
"epoch": 0.48,
"learning_rate": 4.205801104972376e-05,
"loss": 1.6024,
"step": 690
},
{
"epoch": 0.48,
"learning_rate": 4.1942909760589324e-05,
"loss": 1.6072,
"step": 700
},
{
"epoch": 0.49,
"learning_rate": 4.182780847145488e-05,
"loss": 1.5769,
"step": 710
},
{
"epoch": 0.5,
"learning_rate": 4.1712707182320444e-05,
"loss": 1.5869,
"step": 720
},
{
"epoch": 0.5,
"learning_rate": 4.1597605893186e-05,
"loss": 1.5877,
"step": 730
},
{
"epoch": 0.51,
"learning_rate": 4.148250460405157e-05,
"loss": 1.6401,
"step": 740
},
{
"epoch": 0.52,
"learning_rate": 4.136740331491713e-05,
"loss": 1.6012,
"step": 750
},
{
"epoch": 0.52,
"learning_rate": 4.125230202578269e-05,
"loss": 1.5881,
"step": 760
},
{
"epoch": 0.53,
"learning_rate": 4.1137200736648254e-05,
"loss": 1.6215,
"step": 770
},
{
"epoch": 0.54,
"learning_rate": 4.102209944751381e-05,
"loss": 1.6339,
"step": 780
},
{
"epoch": 0.55,
"learning_rate": 4.090699815837938e-05,
"loss": 1.627,
"step": 790
},
{
"epoch": 0.55,
"learning_rate": 4.079189686924494e-05,
"loss": 1.595,
"step": 800
},
{
"epoch": 0.56,
"learning_rate": 4.06767955801105e-05,
"loss": 1.5975,
"step": 810
},
{
"epoch": 0.57,
"learning_rate": 4.056169429097606e-05,
"loss": 1.581,
"step": 820
},
{
"epoch": 0.57,
"learning_rate": 4.044659300184162e-05,
"loss": 1.6179,
"step": 830
},
{
"epoch": 0.58,
"learning_rate": 4.033149171270719e-05,
"loss": 1.5888,
"step": 840
},
{
"epoch": 0.59,
"learning_rate": 4.0216390423572746e-05,
"loss": 1.5645,
"step": 850
},
{
"epoch": 0.59,
"learning_rate": 4.010128913443831e-05,
"loss": 1.6079,
"step": 860
},
{
"epoch": 0.6,
"learning_rate": 3.9986187845303866e-05,
"loss": 1.5738,
"step": 870
},
{
"epoch": 0.61,
"learning_rate": 3.987108655616943e-05,
"loss": 1.5887,
"step": 880
},
{
"epoch": 0.61,
"learning_rate": 3.975598526703499e-05,
"loss": 1.6049,
"step": 890
},
{
"epoch": 0.62,
"learning_rate": 3.9640883977900556e-05,
"loss": 1.6021,
"step": 900
},
{
"epoch": 0.63,
"learning_rate": 3.952578268876612e-05,
"loss": 1.5762,
"step": 910
},
{
"epoch": 0.64,
"learning_rate": 3.9410681399631676e-05,
"loss": 1.5568,
"step": 920
},
{
"epoch": 0.64,
"learning_rate": 3.929558011049724e-05,
"loss": 1.5439,
"step": 930
},
{
"epoch": 0.65,
"learning_rate": 3.91804788213628e-05,
"loss": 1.5901,
"step": 940
},
{
"epoch": 0.66,
"learning_rate": 3.9065377532228366e-05,
"loss": 1.6208,
"step": 950
},
{
"epoch": 0.66,
"learning_rate": 3.895027624309392e-05,
"loss": 1.6169,
"step": 960
},
{
"epoch": 0.67,
"learning_rate": 3.8835174953959486e-05,
"loss": 1.6367,
"step": 970
},
{
"epoch": 0.68,
"learning_rate": 3.872007366482505e-05,
"loss": 1.6195,
"step": 980
},
{
"epoch": 0.68,
"learning_rate": 3.860497237569061e-05,
"loss": 1.6107,
"step": 990
},
{
"epoch": 0.69,
"learning_rate": 3.8489871086556175e-05,
"loss": 1.607,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4344,
"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
}