dada22231's picture
Training in progress, step 50, checkpoint
d2d367f verified
{
"best_metric": 0.1662767380475998,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.13795481979651664,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0027590963959303327,
"grad_norm": 2.8736233711242676,
"learning_rate": 5e-05,
"loss": 1.6531,
"step": 1
},
{
"epoch": 0.0027590963959303327,
"eval_loss": 1.0923383235931396,
"eval_runtime": 4.3993,
"eval_samples_per_second": 11.365,
"eval_steps_per_second": 2.955,
"step": 1
},
{
"epoch": 0.0055181927918606655,
"grad_norm": 2.5027053356170654,
"learning_rate": 0.0001,
"loss": 1.4551,
"step": 2
},
{
"epoch": 0.008277289187790998,
"grad_norm": 1.5247098207473755,
"learning_rate": 9.990365154573717e-05,
"loss": 1.1081,
"step": 3
},
{
"epoch": 0.011036385583721331,
"grad_norm": 1.0242395401000977,
"learning_rate": 9.961501876182148e-05,
"loss": 0.8285,
"step": 4
},
{
"epoch": 0.013795481979651664,
"grad_norm": 0.873866856098175,
"learning_rate": 9.913533761814537e-05,
"loss": 0.6806,
"step": 5
},
{
"epoch": 0.016554578375581996,
"grad_norm": 0.7331669926643372,
"learning_rate": 9.846666218300807e-05,
"loss": 0.5174,
"step": 6
},
{
"epoch": 0.01931367477151233,
"grad_norm": 0.6170404553413391,
"learning_rate": 9.761185582727977e-05,
"loss": 0.4061,
"step": 7
},
{
"epoch": 0.022072771167442662,
"grad_norm": 0.4580063819885254,
"learning_rate": 9.657457896300791e-05,
"loss": 0.3352,
"step": 8
},
{
"epoch": 0.024831867563372995,
"grad_norm": 0.332847535610199,
"learning_rate": 9.535927336897098e-05,
"loss": 0.2812,
"step": 9
},
{
"epoch": 0.027590963959303327,
"grad_norm": 0.2888358533382416,
"learning_rate": 9.397114317029975e-05,
"loss": 0.2477,
"step": 10
},
{
"epoch": 0.03035006035523366,
"grad_norm": 0.29751214385032654,
"learning_rate": 9.241613255361455e-05,
"loss": 0.2295,
"step": 11
},
{
"epoch": 0.03310915675116399,
"grad_norm": 0.2564615309238434,
"learning_rate": 9.070090031310558e-05,
"loss": 0.2023,
"step": 12
},
{
"epoch": 0.035868253147094326,
"grad_norm": 0.6380288004875183,
"learning_rate": 8.883279133655399e-05,
"loss": 0.2306,
"step": 13
},
{
"epoch": 0.03862734954302466,
"grad_norm": 0.4050877094268799,
"learning_rate": 8.681980515339464e-05,
"loss": 0.1794,
"step": 14
},
{
"epoch": 0.04138644593895499,
"grad_norm": 0.38711509108543396,
"learning_rate": 8.467056167950311e-05,
"loss": 0.1707,
"step": 15
},
{
"epoch": 0.044145542334885324,
"grad_norm": 0.3676080107688904,
"learning_rate": 8.239426430539243e-05,
"loss": 0.1757,
"step": 16
},
{
"epoch": 0.046904638730815656,
"grad_norm": 0.20531894266605377,
"learning_rate": 8.000066048588211e-05,
"loss": 0.1725,
"step": 17
},
{
"epoch": 0.04966373512674599,
"grad_norm": 0.29787468910217285,
"learning_rate": 7.75e-05,
"loss": 0.1783,
"step": 18
},
{
"epoch": 0.05242283152267632,
"grad_norm": 0.17893420159816742,
"learning_rate": 7.490299105985507e-05,
"loss": 0.1797,
"step": 19
},
{
"epoch": 0.055181927918606655,
"grad_norm": 0.21105116605758667,
"learning_rate": 7.222075445642904e-05,
"loss": 0.1818,
"step": 20
},
{
"epoch": 0.05794102431453699,
"grad_norm": 0.21834588050842285,
"learning_rate": 6.946477593864228e-05,
"loss": 0.1932,
"step": 21
},
{
"epoch": 0.06070012071046732,
"grad_norm": 0.16078908741474152,
"learning_rate": 6.664685702961344e-05,
"loss": 0.1869,
"step": 22
},
{
"epoch": 0.06345921710639765,
"grad_norm": 0.2289479523897171,
"learning_rate": 6.377906449072578e-05,
"loss": 0.1856,
"step": 23
},
{
"epoch": 0.06621831350232799,
"grad_norm": 0.12230488657951355,
"learning_rate": 6.087367864990233e-05,
"loss": 0.1776,
"step": 24
},
{
"epoch": 0.06897740989825832,
"grad_norm": 0.1601058393716812,
"learning_rate": 5.794314081535644e-05,
"loss": 0.1569,
"step": 25
},
{
"epoch": 0.06897740989825832,
"eval_loss": 0.17924122512340546,
"eval_runtime": 4.4655,
"eval_samples_per_second": 11.197,
"eval_steps_per_second": 2.911,
"step": 25
},
{
"epoch": 0.07173650629418865,
"grad_norm": 0.5671409964561462,
"learning_rate": 5.500000000000001e-05,
"loss": 0.208,
"step": 26
},
{
"epoch": 0.07449560269011898,
"grad_norm": 0.20743843913078308,
"learning_rate": 5.205685918464356e-05,
"loss": 0.1561,
"step": 27
},
{
"epoch": 0.07725469908604932,
"grad_norm": 0.1487397849559784,
"learning_rate": 4.912632135009769e-05,
"loss": 0.1517,
"step": 28
},
{
"epoch": 0.08001379548197965,
"grad_norm": 0.14751917123794556,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.1527,
"step": 29
},
{
"epoch": 0.08277289187790998,
"grad_norm": 0.1772109568119049,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.1572,
"step": 30
},
{
"epoch": 0.08553198827384031,
"grad_norm": 0.17633143067359924,
"learning_rate": 4.053522406135775e-05,
"loss": 0.1685,
"step": 31
},
{
"epoch": 0.08829108466977065,
"grad_norm": 0.1450255960226059,
"learning_rate": 3.777924554357096e-05,
"loss": 0.1668,
"step": 32
},
{
"epoch": 0.09105018106570098,
"grad_norm": 0.12896516919136047,
"learning_rate": 3.509700894014496e-05,
"loss": 0.162,
"step": 33
},
{
"epoch": 0.09380927746163131,
"grad_norm": 0.15334802865982056,
"learning_rate": 3.250000000000001e-05,
"loss": 0.1835,
"step": 34
},
{
"epoch": 0.09656837385756165,
"grad_norm": 0.11007829010486603,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.1674,
"step": 35
},
{
"epoch": 0.09932747025349198,
"grad_norm": 0.10919762402772903,
"learning_rate": 2.760573569460757e-05,
"loss": 0.1785,
"step": 36
},
{
"epoch": 0.10208656664942231,
"grad_norm": 0.10813508927822113,
"learning_rate": 2.53294383204969e-05,
"loss": 0.1547,
"step": 37
},
{
"epoch": 0.10484566304535264,
"grad_norm": 0.47470805048942566,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.1636,
"step": 38
},
{
"epoch": 0.10760475944128298,
"grad_norm": 0.12728680670261383,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.1483,
"step": 39
},
{
"epoch": 0.11036385583721331,
"grad_norm": 0.08785061538219452,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.1464,
"step": 40
},
{
"epoch": 0.11312295223314364,
"grad_norm": 0.09421629458665848,
"learning_rate": 1.758386744638546e-05,
"loss": 0.1475,
"step": 41
},
{
"epoch": 0.11588204862907397,
"grad_norm": 0.12139090150594711,
"learning_rate": 1.602885682970026e-05,
"loss": 0.1508,
"step": 42
},
{
"epoch": 0.11864114502500431,
"grad_norm": 0.08867090195417404,
"learning_rate": 1.464072663102903e-05,
"loss": 0.1499,
"step": 43
},
{
"epoch": 0.12140024142093464,
"grad_norm": 0.10524087399244308,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.1575,
"step": 44
},
{
"epoch": 0.12415933781686497,
"grad_norm": 0.08246508240699768,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.1558,
"step": 45
},
{
"epoch": 0.1269184342127953,
"grad_norm": 0.09248940646648407,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.1731,
"step": 46
},
{
"epoch": 0.12967753060872564,
"grad_norm": 0.08393806219100952,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.1703,
"step": 47
},
{
"epoch": 0.13243662700465597,
"grad_norm": 0.0718834400177002,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.1612,
"step": 48
},
{
"epoch": 0.1351957234005863,
"grad_norm": 0.058842603117227554,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.1673,
"step": 49
},
{
"epoch": 0.13795481979651664,
"grad_norm": 0.0673556998372078,
"learning_rate": 1e-05,
"loss": 0.1551,
"step": 50
},
{
"epoch": 0.13795481979651664,
"eval_loss": 0.1662767380475998,
"eval_runtime": 4.3764,
"eval_samples_per_second": 11.425,
"eval_steps_per_second": 2.971,
"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": 6.067967323065549e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}