lesso12's picture
Training in progress, step 50, checkpoint
90fe7b4 verified
raw
history blame
9.96 kB
{
"best_metric": 0.9605554938316345,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.0638297872340425,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02127659574468085,
"grad_norm": 14.213656425476074,
"learning_rate": 1.1200000000000001e-05,
"loss": 4.4616,
"step": 1
},
{
"epoch": 0.02127659574468085,
"eval_loss": 3.8836147785186768,
"eval_runtime": 3.7874,
"eval_samples_per_second": 167.135,
"eval_steps_per_second": 5.281,
"step": 1
},
{
"epoch": 0.0425531914893617,
"grad_norm": 7.082957744598389,
"learning_rate": 2.2400000000000002e-05,
"loss": 3.8433,
"step": 2
},
{
"epoch": 0.06382978723404255,
"grad_norm": 5.922336578369141,
"learning_rate": 3.36e-05,
"loss": 3.5573,
"step": 3
},
{
"epoch": 0.0851063829787234,
"grad_norm": 5.772343158721924,
"learning_rate": 4.4800000000000005e-05,
"loss": 3.5562,
"step": 4
},
{
"epoch": 0.10638297872340426,
"grad_norm": 6.365505695343018,
"learning_rate": 5.6e-05,
"loss": 3.1005,
"step": 5
},
{
"epoch": 0.1276595744680851,
"grad_norm": 7.662172794342041,
"learning_rate": 6.72e-05,
"loss": 2.6307,
"step": 6
},
{
"epoch": 0.14893617021276595,
"grad_norm": 7.855373382568359,
"learning_rate": 7.84e-05,
"loss": 2.1008,
"step": 7
},
{
"epoch": 0.1702127659574468,
"grad_norm": 5.307789325714111,
"learning_rate": 8.960000000000001e-05,
"loss": 1.8141,
"step": 8
},
{
"epoch": 0.19148936170212766,
"grad_norm": 2.865940570831299,
"learning_rate": 0.0001008,
"loss": 1.8787,
"step": 9
},
{
"epoch": 0.2127659574468085,
"grad_norm": 1.4380123615264893,
"learning_rate": 0.000112,
"loss": 1.4918,
"step": 10
},
{
"epoch": 0.23404255319148937,
"grad_norm": 1.5105291604995728,
"learning_rate": 0.00011198389746057678,
"loss": 1.4308,
"step": 11
},
{
"epoch": 0.2553191489361702,
"grad_norm": 1.0955153703689575,
"learning_rate": 0.0001119355991027277,
"loss": 1.1133,
"step": 12
},
{
"epoch": 0.2765957446808511,
"grad_norm": 8.190502166748047,
"learning_rate": 0.00011185513270238886,
"loss": 0.7666,
"step": 13
},
{
"epoch": 0.2978723404255319,
"grad_norm": 12.864703178405762,
"learning_rate": 0.00011174254453503828,
"loss": 0.6613,
"step": 14
},
{
"epoch": 0.3191489361702128,
"grad_norm": 2.111825466156006,
"learning_rate": 0.00011159789934908318,
"loss": 1.6219,
"step": 15
},
{
"epoch": 0.3404255319148936,
"grad_norm": 1.2697428464889526,
"learning_rate": 0.00011142128032862395,
"loss": 1.4151,
"step": 16
},
{
"epoch": 0.3617021276595745,
"grad_norm": 0.5486758351325989,
"learning_rate": 0.00011121278904561553,
"loss": 1.2228,
"step": 17
},
{
"epoch": 0.3829787234042553,
"grad_norm": 0.6482474207878113,
"learning_rate": 0.0001109725454014545,
"loss": 1.1537,
"step": 18
},
{
"epoch": 0.40425531914893614,
"grad_norm": 1.133864402770996,
"learning_rate": 0.00011070068755802486,
"loss": 0.7857,
"step": 19
},
{
"epoch": 0.425531914893617,
"grad_norm": 0.4991963803768158,
"learning_rate": 0.00011039737185824234,
"loss": 0.1432,
"step": 20
},
{
"epoch": 0.44680851063829785,
"grad_norm": 0.7302205562591553,
"learning_rate": 0.00011006277273614316,
"loss": 1.3804,
"step": 21
},
{
"epoch": 0.46808510638297873,
"grad_norm": 0.6448777914047241,
"learning_rate": 0.00010969708261656854,
"loss": 1.4363,
"step": 22
},
{
"epoch": 0.48936170212765956,
"grad_norm": 0.6198523044586182,
"learning_rate": 0.00010930051180450303,
"loss": 1.2917,
"step": 23
},
{
"epoch": 0.5106382978723404,
"grad_norm": 0.40335163474082947,
"learning_rate": 0.00010887328836413005,
"loss": 1.2051,
"step": 24
},
{
"epoch": 0.5319148936170213,
"grad_norm": 0.5545335412025452,
"learning_rate": 0.00010841565798767423,
"loss": 0.9898,
"step": 25
},
{
"epoch": 0.5531914893617021,
"grad_norm": 1.7060941457748413,
"learning_rate": 0.00010792788385410628,
"loss": 0.0614,
"step": 26
},
{
"epoch": 0.574468085106383,
"grad_norm": 0.7902534008026123,
"learning_rate": 0.00010741024647779101,
"loss": 1.128,
"step": 27
},
{
"epoch": 0.5957446808510638,
"grad_norm": 0.44602009654045105,
"learning_rate": 0.00010686304354716622,
"loss": 1.4464,
"step": 28
},
{
"epoch": 0.6170212765957447,
"grad_norm": 0.3824542164802551,
"learning_rate": 0.00010628658975354491,
"loss": 1.2856,
"step": 29
},
{
"epoch": 0.6382978723404256,
"grad_norm": 0.42575424909591675,
"learning_rate": 0.00010568121661013911,
"loss": 1.134,
"step": 30
},
{
"epoch": 0.6595744680851063,
"grad_norm": 0.506963312625885,
"learning_rate": 0.00010504727226140981,
"loss": 0.9792,
"step": 31
},
{
"epoch": 0.6808510638297872,
"grad_norm": 0.46332627534866333,
"learning_rate": 0.00010438512128285228,
"loss": 0.3159,
"step": 32
},
{
"epoch": 0.7021276595744681,
"grad_norm": 0.4355514943599701,
"learning_rate": 0.00010369514447133208,
"loss": 0.8945,
"step": 33
},
{
"epoch": 0.723404255319149,
"grad_norm": 0.4772055447101593,
"learning_rate": 0.0001029777386260924,
"loss": 1.4357,
"step": 34
},
{
"epoch": 0.7446808510638298,
"grad_norm": 0.3987302780151367,
"learning_rate": 0.00010223331632055843,
"loss": 1.3066,
"step": 35
},
{
"epoch": 0.7659574468085106,
"grad_norm": 0.37436139583587646,
"learning_rate": 0.00010146230566507025,
"loss": 1.1248,
"step": 36
},
{
"epoch": 0.7872340425531915,
"grad_norm": 0.4493124783039093,
"learning_rate": 0.00010066515006068056,
"loss": 1.0106,
"step": 37
},
{
"epoch": 0.8085106382978723,
"grad_norm": 0.8829596042633057,
"learning_rate": 9.984230794415887e-05,
"loss": 0.4913,
"step": 38
},
{
"epoch": 0.8297872340425532,
"grad_norm": 0.5549487471580505,
"learning_rate": 9.899425252434878e-05,
"loss": 0.6699,
"step": 39
},
{
"epoch": 0.851063829787234,
"grad_norm": 0.4452535808086395,
"learning_rate": 9.812147151002993e-05,
"loss": 1.4244,
"step": 40
},
{
"epoch": 0.8723404255319149,
"grad_norm": 0.35962700843811035,
"learning_rate": 9.722446682944128e-05,
"loss": 1.2756,
"step": 41
},
{
"epoch": 0.8936170212765957,
"grad_norm": 0.3556835949420929,
"learning_rate": 9.630375434162683e-05,
"loss": 1.1866,
"step": 42
},
{
"epoch": 0.9148936170212766,
"grad_norm": 0.34359875321388245,
"learning_rate": 9.53598635397699e-05,
"loss": 1.0799,
"step": 43
},
{
"epoch": 0.9361702127659575,
"grad_norm": 0.5090391039848328,
"learning_rate": 9.43933372466865e-05,
"loss": 0.7165,
"step": 44
},
{
"epoch": 0.9574468085106383,
"grad_norm": 0.42997509241104126,
"learning_rate": 9.340473130265294e-05,
"loss": 1.0119,
"step": 45
},
{
"epoch": 0.9787234042553191,
"grad_norm": 0.3640575408935547,
"learning_rate": 9.239461424574742e-05,
"loss": 1.2632,
"step": 46
},
{
"epoch": 1.0,
"grad_norm": 0.3492790460586548,
"learning_rate": 9.136356698488885e-05,
"loss": 0.9953,
"step": 47
},
{
"epoch": 1.0212765957446808,
"grad_norm": 0.3192073702812195,
"learning_rate": 9.031218246576172e-05,
"loss": 0.21,
"step": 48
},
{
"epoch": 1.0425531914893618,
"grad_norm": 0.434736043214798,
"learning_rate": 8.924106532981847e-05,
"loss": 1.1353,
"step": 49
},
{
"epoch": 1.0638297872340425,
"grad_norm": 0.36542627215385437,
"learning_rate": 8.815083156655581e-05,
"loss": 1.3234,
"step": 50
},
{
"epoch": 1.0638297872340425,
"eval_loss": 0.9605554938316345,
"eval_runtime": 3.8841,
"eval_samples_per_second": 162.971,
"eval_steps_per_second": 5.149,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 141,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2.293237926592512e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}