prxy5605's picture
Training in progress, step 100, checkpoint
154c90a verified
raw
history blame
18.8 kB
{
"best_metric": 0.8940727710723877,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.028328611898016998,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00028328611898016995,
"grad_norm": 2.4837124347686768,
"learning_rate": 5e-06,
"loss": 1.0328,
"step": 1
},
{
"epoch": 0.00028328611898016995,
"eval_loss": 1.364790678024292,
"eval_runtime": 482.3304,
"eval_samples_per_second": 12.328,
"eval_steps_per_second": 6.164,
"step": 1
},
{
"epoch": 0.0005665722379603399,
"grad_norm": 0.7393561005592346,
"learning_rate": 1e-05,
"loss": 1.044,
"step": 2
},
{
"epoch": 0.0008498583569405099,
"grad_norm": 0.5064038038253784,
"learning_rate": 1.5e-05,
"loss": 1.0228,
"step": 3
},
{
"epoch": 0.0011331444759206798,
"grad_norm": 1.1812818050384521,
"learning_rate": 2e-05,
"loss": 1.0907,
"step": 4
},
{
"epoch": 0.00141643059490085,
"grad_norm": 0.7924461364746094,
"learning_rate": 2.5e-05,
"loss": 1.1227,
"step": 5
},
{
"epoch": 0.0016997167138810198,
"grad_norm": 0.5778879523277283,
"learning_rate": 3e-05,
"loss": 1.0562,
"step": 6
},
{
"epoch": 0.00198300283286119,
"grad_norm": 0.7456988096237183,
"learning_rate": 3.5e-05,
"loss": 1.0785,
"step": 7
},
{
"epoch": 0.0022662889518413596,
"grad_norm": 0.5129983425140381,
"learning_rate": 4e-05,
"loss": 1.0225,
"step": 8
},
{
"epoch": 0.0025495750708215297,
"grad_norm": 0.4113961458206177,
"learning_rate": 4.5e-05,
"loss": 1.0419,
"step": 9
},
{
"epoch": 0.0028328611898017,
"grad_norm": 0.37529513239860535,
"learning_rate": 5e-05,
"loss": 0.9771,
"step": 10
},
{
"epoch": 0.0031161473087818695,
"grad_norm": 0.4042710065841675,
"learning_rate": 5.500000000000001e-05,
"loss": 0.9975,
"step": 11
},
{
"epoch": 0.0033994334277620396,
"grad_norm": 0.3994333744049072,
"learning_rate": 6e-05,
"loss": 1.0203,
"step": 12
},
{
"epoch": 0.0036827195467422098,
"grad_norm": 0.430587500333786,
"learning_rate": 6.500000000000001e-05,
"loss": 0.981,
"step": 13
},
{
"epoch": 0.00396600566572238,
"grad_norm": 0.4299090504646301,
"learning_rate": 7e-05,
"loss": 0.9638,
"step": 14
},
{
"epoch": 0.00424929178470255,
"grad_norm": 0.41372954845428467,
"learning_rate": 7.500000000000001e-05,
"loss": 0.9036,
"step": 15
},
{
"epoch": 0.004532577903682719,
"grad_norm": 0.4030589163303375,
"learning_rate": 8e-05,
"loss": 0.8851,
"step": 16
},
{
"epoch": 0.004815864022662889,
"grad_norm": 0.43109366297721863,
"learning_rate": 8.5e-05,
"loss": 0.9949,
"step": 17
},
{
"epoch": 0.0050991501416430595,
"grad_norm": 0.4088292419910431,
"learning_rate": 9e-05,
"loss": 0.9794,
"step": 18
},
{
"epoch": 0.00538243626062323,
"grad_norm": 0.3350220322608948,
"learning_rate": 9.5e-05,
"loss": 0.8792,
"step": 19
},
{
"epoch": 0.0056657223796034,
"grad_norm": 0.30330002307891846,
"learning_rate": 0.0001,
"loss": 0.878,
"step": 20
},
{
"epoch": 0.00594900849858357,
"grad_norm": 0.3451264500617981,
"learning_rate": 9.999238475781957e-05,
"loss": 0.8818,
"step": 21
},
{
"epoch": 0.006232294617563739,
"grad_norm": 0.3362950384616852,
"learning_rate": 9.99695413509548e-05,
"loss": 0.8614,
"step": 22
},
{
"epoch": 0.006515580736543909,
"grad_norm": 0.36854445934295654,
"learning_rate": 9.99314767377287e-05,
"loss": 0.8847,
"step": 23
},
{
"epoch": 0.006798866855524079,
"grad_norm": 0.3834778666496277,
"learning_rate": 9.987820251299122e-05,
"loss": 0.9134,
"step": 24
},
{
"epoch": 0.007082152974504249,
"grad_norm": 0.4009423851966858,
"learning_rate": 9.980973490458728e-05,
"loss": 0.8813,
"step": 25
},
{
"epoch": 0.0073654390934844195,
"grad_norm": 0.32073336839675903,
"learning_rate": 9.972609476841367e-05,
"loss": 0.8641,
"step": 26
},
{
"epoch": 0.00764872521246459,
"grad_norm": 0.3810870051383972,
"learning_rate": 9.962730758206611e-05,
"loss": 0.9017,
"step": 27
},
{
"epoch": 0.00793201133144476,
"grad_norm": 0.40584418177604675,
"learning_rate": 9.951340343707852e-05,
"loss": 0.9204,
"step": 28
},
{
"epoch": 0.00821529745042493,
"grad_norm": 0.29945215582847595,
"learning_rate": 9.938441702975689e-05,
"loss": 0.8645,
"step": 29
},
{
"epoch": 0.0084985835694051,
"grad_norm": 0.4067940413951874,
"learning_rate": 9.924038765061042e-05,
"loss": 0.9061,
"step": 30
},
{
"epoch": 0.008781869688385268,
"grad_norm": 0.4845235049724579,
"learning_rate": 9.908135917238321e-05,
"loss": 0.9485,
"step": 31
},
{
"epoch": 0.009065155807365438,
"grad_norm": 0.4056897461414337,
"learning_rate": 9.890738003669029e-05,
"loss": 0.9093,
"step": 32
},
{
"epoch": 0.009348441926345609,
"grad_norm": 0.43699613213539124,
"learning_rate": 9.871850323926177e-05,
"loss": 0.9523,
"step": 33
},
{
"epoch": 0.009631728045325779,
"grad_norm": 0.5528873205184937,
"learning_rate": 9.851478631379982e-05,
"loss": 0.8597,
"step": 34
},
{
"epoch": 0.009915014164305949,
"grad_norm": 0.5298404097557068,
"learning_rate": 9.829629131445342e-05,
"loss": 1.0194,
"step": 35
},
{
"epoch": 0.010198300283286119,
"grad_norm": 0.5607902407646179,
"learning_rate": 9.806308479691595e-05,
"loss": 0.9661,
"step": 36
},
{
"epoch": 0.010481586402266289,
"grad_norm": 0.6369351744651794,
"learning_rate": 9.781523779815179e-05,
"loss": 1.0808,
"step": 37
},
{
"epoch": 0.01076487252124646,
"grad_norm": 0.5015552639961243,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9148,
"step": 38
},
{
"epoch": 0.01104815864022663,
"grad_norm": 0.5619277954101562,
"learning_rate": 9.727592877996585e-05,
"loss": 1.0133,
"step": 39
},
{
"epoch": 0.0113314447592068,
"grad_norm": 0.7182181477546692,
"learning_rate": 9.698463103929542e-05,
"loss": 0.994,
"step": 40
},
{
"epoch": 0.01161473087818697,
"grad_norm": 0.7005313634872437,
"learning_rate": 9.667902132486009e-05,
"loss": 1.0247,
"step": 41
},
{
"epoch": 0.01189801699716714,
"grad_norm": 0.771409273147583,
"learning_rate": 9.635919272833938e-05,
"loss": 1.1388,
"step": 42
},
{
"epoch": 0.012181303116147308,
"grad_norm": 0.6452864408493042,
"learning_rate": 9.602524267262203e-05,
"loss": 1.0388,
"step": 43
},
{
"epoch": 0.012464589235127478,
"grad_norm": 0.7697048783302307,
"learning_rate": 9.567727288213005e-05,
"loss": 1.0937,
"step": 44
},
{
"epoch": 0.012747875354107648,
"grad_norm": 0.8071401119232178,
"learning_rate": 9.53153893518325e-05,
"loss": 0.938,
"step": 45
},
{
"epoch": 0.013031161473087818,
"grad_norm": 0.9409806728363037,
"learning_rate": 9.493970231495835e-05,
"loss": 1.23,
"step": 46
},
{
"epoch": 0.013314447592067988,
"grad_norm": 0.9912319779396057,
"learning_rate": 9.45503262094184e-05,
"loss": 1.0184,
"step": 47
},
{
"epoch": 0.013597733711048159,
"grad_norm": 1.4439435005187988,
"learning_rate": 9.414737964294636e-05,
"loss": 1.1788,
"step": 48
},
{
"epoch": 0.013881019830028329,
"grad_norm": 1.5036474466323853,
"learning_rate": 9.373098535696979e-05,
"loss": 1.0626,
"step": 49
},
{
"epoch": 0.014164305949008499,
"grad_norm": 2.3197476863861084,
"learning_rate": 9.330127018922194e-05,
"loss": 1.0557,
"step": 50
},
{
"epoch": 0.014164305949008499,
"eval_loss": 0.9729824066162109,
"eval_runtime": 485.1181,
"eval_samples_per_second": 12.257,
"eval_steps_per_second": 6.128,
"step": 50
},
{
"epoch": 0.014447592067988669,
"grad_norm": 0.3290400803089142,
"learning_rate": 9.285836503510562e-05,
"loss": 0.7674,
"step": 51
},
{
"epoch": 0.014730878186968839,
"grad_norm": 0.422162264585495,
"learning_rate": 9.24024048078213e-05,
"loss": 0.8912,
"step": 52
},
{
"epoch": 0.01501416430594901,
"grad_norm": 0.38885658979415894,
"learning_rate": 9.193352839727121e-05,
"loss": 0.8074,
"step": 53
},
{
"epoch": 0.01529745042492918,
"grad_norm": 0.32865843176841736,
"learning_rate": 9.145187862775209e-05,
"loss": 0.8353,
"step": 54
},
{
"epoch": 0.015580736543909348,
"grad_norm": 0.29051336646080017,
"learning_rate": 9.09576022144496e-05,
"loss": 0.8639,
"step": 55
},
{
"epoch": 0.01586402266288952,
"grad_norm": 0.2875722646713257,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8683,
"step": 56
},
{
"epoch": 0.01614730878186969,
"grad_norm": 0.26893699169158936,
"learning_rate": 8.993177550236464e-05,
"loss": 0.8548,
"step": 57
},
{
"epoch": 0.01643059490084986,
"grad_norm": 0.2714105248451233,
"learning_rate": 8.940053768033609e-05,
"loss": 0.8185,
"step": 58
},
{
"epoch": 0.01671388101983003,
"grad_norm": 0.2685096561908722,
"learning_rate": 8.885729807284856e-05,
"loss": 0.8188,
"step": 59
},
{
"epoch": 0.0169971671388102,
"grad_norm": 0.27536776661872864,
"learning_rate": 8.83022221559489e-05,
"loss": 0.806,
"step": 60
},
{
"epoch": 0.017280453257790367,
"grad_norm": 0.26395905017852783,
"learning_rate": 8.773547901113862e-05,
"loss": 0.7769,
"step": 61
},
{
"epoch": 0.017563739376770537,
"grad_norm": 0.28983741998672485,
"learning_rate": 8.715724127386972e-05,
"loss": 0.856,
"step": 62
},
{
"epoch": 0.017847025495750707,
"grad_norm": 0.24493105709552765,
"learning_rate": 8.656768508095853e-05,
"loss": 0.7598,
"step": 63
},
{
"epoch": 0.018130311614730877,
"grad_norm": 0.25833049416542053,
"learning_rate": 8.596699001693255e-05,
"loss": 0.8238,
"step": 64
},
{
"epoch": 0.018413597733711047,
"grad_norm": 0.23423363268375397,
"learning_rate": 8.535533905932738e-05,
"loss": 0.838,
"step": 65
},
{
"epoch": 0.018696883852691217,
"grad_norm": 0.24402977526187897,
"learning_rate": 8.473291852294987e-05,
"loss": 0.7818,
"step": 66
},
{
"epoch": 0.018980169971671387,
"grad_norm": 0.2572822868824005,
"learning_rate": 8.409991800312493e-05,
"loss": 0.8178,
"step": 67
},
{
"epoch": 0.019263456090651557,
"grad_norm": 0.24587130546569824,
"learning_rate": 8.345653031794292e-05,
"loss": 0.8298,
"step": 68
},
{
"epoch": 0.019546742209631728,
"grad_norm": 0.2567668557167053,
"learning_rate": 8.280295144952536e-05,
"loss": 0.82,
"step": 69
},
{
"epoch": 0.019830028328611898,
"grad_norm": 0.25297489762306213,
"learning_rate": 8.213938048432697e-05,
"loss": 0.7948,
"step": 70
},
{
"epoch": 0.020113314447592068,
"grad_norm": 0.24557141959667206,
"learning_rate": 8.146601955249188e-05,
"loss": 0.8097,
"step": 71
},
{
"epoch": 0.020396600566572238,
"grad_norm": 0.28915223479270935,
"learning_rate": 8.07830737662829e-05,
"loss": 0.7822,
"step": 72
},
{
"epoch": 0.020679886685552408,
"grad_norm": 0.2591084837913513,
"learning_rate": 8.009075115760243e-05,
"loss": 0.7799,
"step": 73
},
{
"epoch": 0.020963172804532578,
"grad_norm": 0.28063005208969116,
"learning_rate": 7.938926261462366e-05,
"loss": 0.85,
"step": 74
},
{
"epoch": 0.021246458923512748,
"grad_norm": 0.3160620927810669,
"learning_rate": 7.86788218175523e-05,
"loss": 0.8925,
"step": 75
},
{
"epoch": 0.02152974504249292,
"grad_norm": 0.3204711079597473,
"learning_rate": 7.795964517353735e-05,
"loss": 0.7994,
"step": 76
},
{
"epoch": 0.02181303116147309,
"grad_norm": 0.31728625297546387,
"learning_rate": 7.723195175075136e-05,
"loss": 0.865,
"step": 77
},
{
"epoch": 0.02209631728045326,
"grad_norm": 0.33611783385276794,
"learning_rate": 7.649596321166024e-05,
"loss": 0.8099,
"step": 78
},
{
"epoch": 0.02237960339943343,
"grad_norm": 0.3129088580608368,
"learning_rate": 7.575190374550272e-05,
"loss": 0.8857,
"step": 79
},
{
"epoch": 0.0226628895184136,
"grad_norm": 0.3404497802257538,
"learning_rate": 7.500000000000001e-05,
"loss": 0.8408,
"step": 80
},
{
"epoch": 0.02294617563739377,
"grad_norm": 0.31922274827957153,
"learning_rate": 7.424048101231686e-05,
"loss": 0.8155,
"step": 81
},
{
"epoch": 0.02322946175637394,
"grad_norm": 0.4240337610244751,
"learning_rate": 7.347357813929454e-05,
"loss": 0.9036,
"step": 82
},
{
"epoch": 0.02351274787535411,
"grad_norm": 0.402992308139801,
"learning_rate": 7.269952498697734e-05,
"loss": 0.9222,
"step": 83
},
{
"epoch": 0.02379603399433428,
"grad_norm": 0.4444620907306671,
"learning_rate": 7.191855733945387e-05,
"loss": 0.9426,
"step": 84
},
{
"epoch": 0.024079320113314446,
"grad_norm": 0.5036823153495789,
"learning_rate": 7.113091308703498e-05,
"loss": 0.8989,
"step": 85
},
{
"epoch": 0.024362606232294616,
"grad_norm": 0.5430697202682495,
"learning_rate": 7.033683215379002e-05,
"loss": 1.0644,
"step": 86
},
{
"epoch": 0.024645892351274786,
"grad_norm": 0.47117090225219727,
"learning_rate": 6.953655642446368e-05,
"loss": 0.8856,
"step": 87
},
{
"epoch": 0.024929178470254956,
"grad_norm": 0.6156890392303467,
"learning_rate": 6.873032967079561e-05,
"loss": 0.9403,
"step": 88
},
{
"epoch": 0.025212464589235126,
"grad_norm": 0.5698954463005066,
"learning_rate": 6.7918397477265e-05,
"loss": 0.8913,
"step": 89
},
{
"epoch": 0.025495750708215296,
"grad_norm": 0.5107197165489197,
"learning_rate": 6.710100716628344e-05,
"loss": 0.9912,
"step": 90
},
{
"epoch": 0.025779036827195467,
"grad_norm": 0.6079100966453552,
"learning_rate": 6.627840772285784e-05,
"loss": 0.9322,
"step": 91
},
{
"epoch": 0.026062322946175637,
"grad_norm": 0.6184947490692139,
"learning_rate": 6.545084971874738e-05,
"loss": 0.9983,
"step": 92
},
{
"epoch": 0.026345609065155807,
"grad_norm": 0.6620588302612305,
"learning_rate": 6.461858523613684e-05,
"loss": 0.9366,
"step": 93
},
{
"epoch": 0.026628895184135977,
"grad_norm": 0.7128224968910217,
"learning_rate": 6.378186779084995e-05,
"loss": 1.0045,
"step": 94
},
{
"epoch": 0.026912181303116147,
"grad_norm": 0.7751644253730774,
"learning_rate": 6.294095225512603e-05,
"loss": 0.8427,
"step": 95
},
{
"epoch": 0.027195467422096317,
"grad_norm": 0.8441152572631836,
"learning_rate": 6.209609477998338e-05,
"loss": 0.9694,
"step": 96
},
{
"epoch": 0.027478753541076487,
"grad_norm": 0.9727038145065308,
"learning_rate": 6.124755271719325e-05,
"loss": 1.0076,
"step": 97
},
{
"epoch": 0.027762039660056657,
"grad_norm": 0.9640235900878906,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.9572,
"step": 98
},
{
"epoch": 0.028045325779036828,
"grad_norm": 1.6535217761993408,
"learning_rate": 5.9540449768827246e-05,
"loss": 1.0303,
"step": 99
},
{
"epoch": 0.028328611898016998,
"grad_norm": 3.554504632949829,
"learning_rate": 5.868240888334653e-05,
"loss": 0.9742,
"step": 100
},
{
"epoch": 0.028328611898016998,
"eval_loss": 0.8940727710723877,
"eval_runtime": 484.5241,
"eval_samples_per_second": 12.272,
"eval_steps_per_second": 6.136,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.37604737531904e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}