{
"best_metric": 1.0860586166381836,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.05678188657818156,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011356377315636312,
"grad_norm": 0.44248098134994507,
"learning_rate": 5e-05,
"loss": 0.9817,
"step": 1
},
{
"epoch": 0.0011356377315636312,
"eval_loss": 1.2888797521591187,
"eval_runtime": 43.0895,
"eval_samples_per_second": 137.69,
"eval_steps_per_second": 17.22,
"step": 1
},
{
"epoch": 0.0022712754631272624,
"grad_norm": 0.4765216112136841,
"learning_rate": 0.0001,
"loss": 1.0479,
"step": 2
},
{
"epoch": 0.0034069131946908937,
"grad_norm": 0.4120439887046814,
"learning_rate": 9.989294616193017e-05,
"loss": 1.0244,
"step": 3
},
{
"epoch": 0.004542550926254525,
"grad_norm": 0.45249271392822266,
"learning_rate": 9.957224306869053e-05,
"loss": 1.1028,
"step": 4
},
{
"epoch": 0.005678188657818156,
"grad_norm": 0.493412584066391,
"learning_rate": 9.903926402016153e-05,
"loss": 1.0797,
"step": 5
},
{
"epoch": 0.0068138263893817875,
"grad_norm": 0.5234484076499939,
"learning_rate": 9.829629131445342e-05,
"loss": 1.0833,
"step": 6
},
{
"epoch": 0.007949464120945418,
"grad_norm": 0.4893084168434143,
"learning_rate": 9.73465064747553e-05,
"loss": 1.0104,
"step": 7
},
{
"epoch": 0.00908510185250905,
"grad_norm": 0.44374406337738037,
"learning_rate": 9.619397662556435e-05,
"loss": 1.0527,
"step": 8
},
{
"epoch": 0.01022073958407268,
"grad_norm": 0.5221227407455444,
"learning_rate": 9.484363707663442e-05,
"loss": 1.077,
"step": 9
},
{
"epoch": 0.011356377315636311,
"grad_norm": 0.6887457966804504,
"learning_rate": 9.330127018922194e-05,
"loss": 1.275,
"step": 10
},
{
"epoch": 0.012492015047199944,
"grad_norm": 0.8918617367744446,
"learning_rate": 9.157348061512727e-05,
"loss": 1.2428,
"step": 11
},
{
"epoch": 0.013627652778763575,
"grad_norm": 1.2448235750198364,
"learning_rate": 8.966766701456177e-05,
"loss": 1.3729,
"step": 12
},
{
"epoch": 0.014763290510327206,
"grad_norm": 0.4785754680633545,
"learning_rate": 8.759199037394887e-05,
"loss": 0.8452,
"step": 13
},
{
"epoch": 0.015898928241890837,
"grad_norm": 0.37022310495376587,
"learning_rate": 8.535533905932738e-05,
"loss": 0.899,
"step": 14
},
{
"epoch": 0.017034565973454468,
"grad_norm": 0.45012906193733215,
"learning_rate": 8.296729075500344e-05,
"loss": 1.0393,
"step": 15
},
{
"epoch": 0.0181702037050181,
"grad_norm": 0.42740723490715027,
"learning_rate": 8.043807145043604e-05,
"loss": 1.0453,
"step": 16
},
{
"epoch": 0.01930584143658173,
"grad_norm": 0.4445900321006775,
"learning_rate": 7.777851165098012e-05,
"loss": 1.0891,
"step": 17
},
{
"epoch": 0.02044147916814536,
"grad_norm": 0.42049741744995117,
"learning_rate": 7.500000000000001e-05,
"loss": 1.1098,
"step": 18
},
{
"epoch": 0.02157711689970899,
"grad_norm": 0.4503211975097656,
"learning_rate": 7.211443451095007e-05,
"loss": 1.1623,
"step": 19
},
{
"epoch": 0.022712754631272623,
"grad_norm": 0.41351017355918884,
"learning_rate": 6.91341716182545e-05,
"loss": 1.1624,
"step": 20
},
{
"epoch": 0.023848392362836254,
"grad_norm": 0.42763012647628784,
"learning_rate": 6.607197326515808e-05,
"loss": 1.0766,
"step": 21
},
{
"epoch": 0.024984030094399888,
"grad_norm": 0.5273652672767639,
"learning_rate": 6.294095225512603e-05,
"loss": 1.202,
"step": 22
},
{
"epoch": 0.02611966782596352,
"grad_norm": 0.6357163786888123,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.2158,
"step": 23
},
{
"epoch": 0.02725530555752715,
"grad_norm": 0.9283555150032043,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.3415,
"step": 24
},
{
"epoch": 0.02839094328909078,
"grad_norm": 1.512017846107483,
"learning_rate": 5.327015646150716e-05,
"loss": 1.3185,
"step": 25
},
{
"epoch": 0.02839094328909078,
"eval_loss": 1.0937927961349487,
"eval_runtime": 42.7702,
"eval_samples_per_second": 138.718,
"eval_steps_per_second": 17.349,
"step": 25
},
{
"epoch": 0.029526581020654412,
"grad_norm": 0.26916369795799255,
"learning_rate": 5e-05,
"loss": 0.8223,
"step": 26
},
{
"epoch": 0.030662218752218043,
"grad_norm": 0.28640347719192505,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.9502,
"step": 27
},
{
"epoch": 0.031797856483781674,
"grad_norm": 0.29415908455848694,
"learning_rate": 4.347369038899744e-05,
"loss": 0.9528,
"step": 28
},
{
"epoch": 0.032933494215345305,
"grad_norm": 0.300428569316864,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.0052,
"step": 29
},
{
"epoch": 0.034069131946908936,
"grad_norm": 0.3093526065349579,
"learning_rate": 3.705904774487396e-05,
"loss": 1.0124,
"step": 30
},
{
"epoch": 0.03520476967847257,
"grad_norm": 0.32666245102882385,
"learning_rate": 3.392802673484193e-05,
"loss": 0.975,
"step": 31
},
{
"epoch": 0.0363404074100362,
"grad_norm": 0.34878939390182495,
"learning_rate": 3.086582838174551e-05,
"loss": 1.1806,
"step": 32
},
{
"epoch": 0.03747604514159983,
"grad_norm": 0.37372487783432007,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.1176,
"step": 33
},
{
"epoch": 0.03861168287316346,
"grad_norm": 0.46194377541542053,
"learning_rate": 2.500000000000001e-05,
"loss": 1.1524,
"step": 34
},
{
"epoch": 0.03974732060472709,
"grad_norm": 0.591774046421051,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.1847,
"step": 35
},
{
"epoch": 0.04088295833629072,
"grad_norm": 0.7484531998634338,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.3388,
"step": 36
},
{
"epoch": 0.04201859606785435,
"grad_norm": 0.8685662746429443,
"learning_rate": 1.703270924499656e-05,
"loss": 1.3402,
"step": 37
},
{
"epoch": 0.04315423379941798,
"grad_norm": 0.3701391816139221,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.8519,
"step": 38
},
{
"epoch": 0.044289871530981614,
"grad_norm": 0.2335858792066574,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.9027,
"step": 39
},
{
"epoch": 0.045425509262545245,
"grad_norm": 0.24511219561100006,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.0077,
"step": 40
},
{
"epoch": 0.046561146994108876,
"grad_norm": 0.2630201578140259,
"learning_rate": 8.426519384872733e-06,
"loss": 0.9539,
"step": 41
},
{
"epoch": 0.04769678472567251,
"grad_norm": 0.28861838579177856,
"learning_rate": 6.698729810778065e-06,
"loss": 1.1378,
"step": 42
},
{
"epoch": 0.048832422457236145,
"grad_norm": 0.3146965801715851,
"learning_rate": 5.156362923365588e-06,
"loss": 1.0489,
"step": 43
},
{
"epoch": 0.049968060188799776,
"grad_norm": 0.3190613389015198,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.0681,
"step": 44
},
{
"epoch": 0.05110369792036341,
"grad_norm": 0.32654303312301636,
"learning_rate": 2.653493525244721e-06,
"loss": 1.083,
"step": 45
},
{
"epoch": 0.05223933565192704,
"grad_norm": 0.39204129576683044,
"learning_rate": 1.70370868554659e-06,
"loss": 1.0401,
"step": 46
},
{
"epoch": 0.05337497338349067,
"grad_norm": 0.4339013695716858,
"learning_rate": 9.607359798384785e-07,
"loss": 1.0863,
"step": 47
},
{
"epoch": 0.0545106111150543,
"grad_norm": 0.5439497828483582,
"learning_rate": 4.277569313094809e-07,
"loss": 1.2212,
"step": 48
},
{
"epoch": 0.05564624884661793,
"grad_norm": 0.7164722084999084,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.3335,
"step": 49
},
{
"epoch": 0.05678188657818156,
"grad_norm": 1.4054168462753296,
"learning_rate": 0.0,
"loss": 1.5089,
"step": 50
},
{
"epoch": 0.05678188657818156,
"eval_loss": 1.0860586166381836,
"eval_runtime": 42.7723,
"eval_samples_per_second": 138.711,
"eval_steps_per_second": 17.348,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 2.977002323705856e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}