bbytxt's picture
Training in progress, step 50, checkpoint
adebade verified
raw
history blame
9.92 kB
{
"best_metric": 1.4491695165634155,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.0427715996578272,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000855431993156544,
"grad_norm": 2.352600574493408,
"learning_rate": 1e-05,
"loss": 4.8284,
"step": 1
},
{
"epoch": 0.000855431993156544,
"eval_loss": 1.5003745555877686,
"eval_runtime": 8.1601,
"eval_samples_per_second": 120.709,
"eval_steps_per_second": 30.269,
"step": 1
},
{
"epoch": 0.001710863986313088,
"grad_norm": 2.2152650356292725,
"learning_rate": 2e-05,
"loss": 4.6729,
"step": 2
},
{
"epoch": 0.0025662959794696323,
"grad_norm": 3.0072169303894043,
"learning_rate": 3e-05,
"loss": 4.1083,
"step": 3
},
{
"epoch": 0.003421727972626176,
"grad_norm": 4.585644245147705,
"learning_rate": 4e-05,
"loss": 2.6223,
"step": 4
},
{
"epoch": 0.00427715996578272,
"grad_norm": 4.366663932800293,
"learning_rate": 5e-05,
"loss": 1.0921,
"step": 5
},
{
"epoch": 0.0051325919589392645,
"grad_norm": 2.732001304626465,
"learning_rate": 6e-05,
"loss": 0.8305,
"step": 6
},
{
"epoch": 0.005988023952095809,
"grad_norm": 2.6135103702545166,
"learning_rate": 7e-05,
"loss": 0.7626,
"step": 7
},
{
"epoch": 0.006843455945252352,
"grad_norm": 2.3796298503875732,
"learning_rate": 8e-05,
"loss": 0.8145,
"step": 8
},
{
"epoch": 0.007698887938408896,
"grad_norm": 2.055875301361084,
"learning_rate": 9e-05,
"loss": 0.6454,
"step": 9
},
{
"epoch": 0.00855431993156544,
"grad_norm": 1.9896808862686157,
"learning_rate": 0.0001,
"loss": 0.768,
"step": 10
},
{
"epoch": 0.009409751924721984,
"grad_norm": 1.5508729219436646,
"learning_rate": 9.99695413509548e-05,
"loss": 0.6364,
"step": 11
},
{
"epoch": 0.010265183917878529,
"grad_norm": 1.433290958404541,
"learning_rate": 9.987820251299122e-05,
"loss": 0.6402,
"step": 12
},
{
"epoch": 0.011120615911035072,
"grad_norm": 1.0565850734710693,
"learning_rate": 9.972609476841367e-05,
"loss": 0.5274,
"step": 13
},
{
"epoch": 0.011976047904191617,
"grad_norm": 1.059982419013977,
"learning_rate": 9.951340343707852e-05,
"loss": 0.4195,
"step": 14
},
{
"epoch": 0.01283147989734816,
"grad_norm": 2.2911834716796875,
"learning_rate": 9.924038765061042e-05,
"loss": 0.5623,
"step": 15
},
{
"epoch": 0.013686911890504704,
"grad_norm": 1.2333793640136719,
"learning_rate": 9.890738003669029e-05,
"loss": 0.5258,
"step": 16
},
{
"epoch": 0.01454234388366125,
"grad_norm": 1.084723711013794,
"learning_rate": 9.851478631379982e-05,
"loss": 0.6243,
"step": 17
},
{
"epoch": 0.015397775876817793,
"grad_norm": 0.7262724041938782,
"learning_rate": 9.806308479691595e-05,
"loss": 0.3692,
"step": 18
},
{
"epoch": 0.016253207869974338,
"grad_norm": 1.5828852653503418,
"learning_rate": 9.755282581475769e-05,
"loss": 0.3979,
"step": 19
},
{
"epoch": 0.01710863986313088,
"grad_norm": 1.155763030052185,
"learning_rate": 9.698463103929542e-05,
"loss": 0.3792,
"step": 20
},
{
"epoch": 0.017964071856287425,
"grad_norm": 0.7279295921325684,
"learning_rate": 9.635919272833938e-05,
"loss": 0.3955,
"step": 21
},
{
"epoch": 0.018819503849443968,
"grad_norm": 0.7820014953613281,
"learning_rate": 9.567727288213005e-05,
"loss": 0.404,
"step": 22
},
{
"epoch": 0.019674935842600515,
"grad_norm": 0.7350875735282898,
"learning_rate": 9.493970231495835e-05,
"loss": 0.3896,
"step": 23
},
{
"epoch": 0.020530367835757058,
"grad_norm": 0.780421257019043,
"learning_rate": 9.414737964294636e-05,
"loss": 0.432,
"step": 24
},
{
"epoch": 0.0213857998289136,
"grad_norm": 1.194251298904419,
"learning_rate": 9.330127018922194e-05,
"loss": 0.4828,
"step": 25
},
{
"epoch": 0.022241231822070145,
"grad_norm": 0.9555559158325195,
"learning_rate": 9.24024048078213e-05,
"loss": 0.4872,
"step": 26
},
{
"epoch": 0.023096663815226688,
"grad_norm": 0.5422655344009399,
"learning_rate": 9.145187862775209e-05,
"loss": 0.4849,
"step": 27
},
{
"epoch": 0.023952095808383235,
"grad_norm": 0.7013706564903259,
"learning_rate": 9.045084971874738e-05,
"loss": 0.4789,
"step": 28
},
{
"epoch": 0.02480752780153978,
"grad_norm": 0.6927315592765808,
"learning_rate": 8.940053768033609e-05,
"loss": 0.5087,
"step": 29
},
{
"epoch": 0.02566295979469632,
"grad_norm": 0.7441868185997009,
"learning_rate": 8.83022221559489e-05,
"loss": 0.571,
"step": 30
},
{
"epoch": 0.026518391787852865,
"grad_norm": 0.9051419496536255,
"learning_rate": 8.715724127386972e-05,
"loss": 0.5053,
"step": 31
},
{
"epoch": 0.02737382378100941,
"grad_norm": 0.9479249715805054,
"learning_rate": 8.596699001693255e-05,
"loss": 0.6193,
"step": 32
},
{
"epoch": 0.028229255774165955,
"grad_norm": 0.5198885202407837,
"learning_rate": 8.473291852294987e-05,
"loss": 0.5146,
"step": 33
},
{
"epoch": 0.0290846877673225,
"grad_norm": 0.5799432396888733,
"learning_rate": 8.345653031794292e-05,
"loss": 0.5284,
"step": 34
},
{
"epoch": 0.029940119760479042,
"grad_norm": 0.7015302181243896,
"learning_rate": 8.213938048432697e-05,
"loss": 0.5627,
"step": 35
},
{
"epoch": 0.030795551753635585,
"grad_norm": 0.6689801216125488,
"learning_rate": 8.07830737662829e-05,
"loss": 0.6305,
"step": 36
},
{
"epoch": 0.03165098374679213,
"grad_norm": 0.7400729656219482,
"learning_rate": 7.938926261462366e-05,
"loss": 0.5877,
"step": 37
},
{
"epoch": 0.032506415739948676,
"grad_norm": 0.981304407119751,
"learning_rate": 7.795964517353735e-05,
"loss": 0.7527,
"step": 38
},
{
"epoch": 0.033361847733105215,
"grad_norm": 1.042090654373169,
"learning_rate": 7.649596321166024e-05,
"loss": 0.7431,
"step": 39
},
{
"epoch": 0.03421727972626176,
"grad_norm": 0.9239062070846558,
"learning_rate": 7.500000000000001e-05,
"loss": 0.7556,
"step": 40
},
{
"epoch": 0.03507271171941831,
"grad_norm": 0.708960771560669,
"learning_rate": 7.347357813929454e-05,
"loss": 0.6573,
"step": 41
},
{
"epoch": 0.03592814371257485,
"grad_norm": 1.1409260034561157,
"learning_rate": 7.191855733945387e-05,
"loss": 0.7552,
"step": 42
},
{
"epoch": 0.036783575705731396,
"grad_norm": 1.2339162826538086,
"learning_rate": 7.033683215379002e-05,
"loss": 0.7546,
"step": 43
},
{
"epoch": 0.037639007698887936,
"grad_norm": 1.501574993133545,
"learning_rate": 6.873032967079561e-05,
"loss": 0.8573,
"step": 44
},
{
"epoch": 0.03849443969204448,
"grad_norm": 2.9573240280151367,
"learning_rate": 6.710100716628344e-05,
"loss": 0.733,
"step": 45
},
{
"epoch": 0.03934987168520103,
"grad_norm": 2.3327925205230713,
"learning_rate": 6.545084971874738e-05,
"loss": 0.7521,
"step": 46
},
{
"epoch": 0.04020530367835757,
"grad_norm": 1.8159849643707275,
"learning_rate": 6.378186779084995e-05,
"loss": 0.8454,
"step": 47
},
{
"epoch": 0.041060735671514116,
"grad_norm": 1.5403494834899902,
"learning_rate": 6.209609477998338e-05,
"loss": 0.8458,
"step": 48
},
{
"epoch": 0.041916167664670656,
"grad_norm": 1.8811618089675903,
"learning_rate": 6.0395584540887963e-05,
"loss": 1.049,
"step": 49
},
{
"epoch": 0.0427715996578272,
"grad_norm": 3.8858306407928467,
"learning_rate": 5.868240888334653e-05,
"loss": 1.698,
"step": 50
},
{
"epoch": 0.0427715996578272,
"eval_loss": 1.4491695165634155,
"eval_runtime": 7.3642,
"eval_samples_per_second": 133.755,
"eval_steps_per_second": 33.541,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 770548602765312.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}