prxy5608's picture
Training in progress, step 50, checkpoint
66b9eb5 verified
raw
history blame
9.88 kB
{
"best_metric": 0.6033799052238464,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.7782101167315175,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01556420233463035,
"grad_norm": 9.139370918273926,
"learning_rate": 1e-05,
"loss": 0.8535,
"step": 1
},
{
"epoch": 0.01556420233463035,
"eval_loss": 0.888887882232666,
"eval_runtime": 4.8903,
"eval_samples_per_second": 22.085,
"eval_steps_per_second": 5.521,
"step": 1
},
{
"epoch": 0.0311284046692607,
"grad_norm": 9.370291709899902,
"learning_rate": 2e-05,
"loss": 0.9253,
"step": 2
},
{
"epoch": 0.04669260700389105,
"grad_norm": 7.656525611877441,
"learning_rate": 3e-05,
"loss": 0.9002,
"step": 3
},
{
"epoch": 0.0622568093385214,
"grad_norm": 3.6497480869293213,
"learning_rate": 4e-05,
"loss": 0.8366,
"step": 4
},
{
"epoch": 0.07782101167315175,
"grad_norm": 0.8219636082649231,
"learning_rate": 5e-05,
"loss": 0.7402,
"step": 5
},
{
"epoch": 0.0933852140077821,
"grad_norm": 0.8171916604042053,
"learning_rate": 6e-05,
"loss": 0.7317,
"step": 6
},
{
"epoch": 0.10894941634241245,
"grad_norm": 0.7215791940689087,
"learning_rate": 7e-05,
"loss": 0.7295,
"step": 7
},
{
"epoch": 0.1245136186770428,
"grad_norm": 0.6683509945869446,
"learning_rate": 8e-05,
"loss": 0.6973,
"step": 8
},
{
"epoch": 0.14007782101167315,
"grad_norm": 0.6624220609664917,
"learning_rate": 9e-05,
"loss": 0.7134,
"step": 9
},
{
"epoch": 0.1556420233463035,
"grad_norm": 0.7774540781974792,
"learning_rate": 0.0001,
"loss": 0.6417,
"step": 10
},
{
"epoch": 0.17120622568093385,
"grad_norm": 0.6136654019355774,
"learning_rate": 9.999263238525136e-05,
"loss": 0.6314,
"step": 11
},
{
"epoch": 0.1867704280155642,
"grad_norm": 0.5942745208740234,
"learning_rate": 9.997053171227526e-05,
"loss": 0.6433,
"step": 12
},
{
"epoch": 0.20233463035019456,
"grad_norm": 0.7222641706466675,
"learning_rate": 9.993370449424153e-05,
"loss": 0.6777,
"step": 13
},
{
"epoch": 0.2178988326848249,
"grad_norm": 0.6611757278442383,
"learning_rate": 9.988216158430033e-05,
"loss": 0.6507,
"step": 14
},
{
"epoch": 0.23346303501945526,
"grad_norm": 0.5460258722305298,
"learning_rate": 9.981591817238378e-05,
"loss": 0.625,
"step": 15
},
{
"epoch": 0.2490272373540856,
"grad_norm": 0.5874778628349304,
"learning_rate": 9.973499378072945e-05,
"loss": 0.6796,
"step": 16
},
{
"epoch": 0.26459143968871596,
"grad_norm": 0.42067644000053406,
"learning_rate": 9.963941225812701e-05,
"loss": 0.6118,
"step": 17
},
{
"epoch": 0.2801556420233463,
"grad_norm": 0.4198527932167053,
"learning_rate": 9.952920177288986e-05,
"loss": 0.6576,
"step": 18
},
{
"epoch": 0.29571984435797666,
"grad_norm": 0.45528435707092285,
"learning_rate": 9.940439480455386e-05,
"loss": 0.6441,
"step": 19
},
{
"epoch": 0.311284046692607,
"grad_norm": 0.4378451406955719,
"learning_rate": 9.926502813430545e-05,
"loss": 0.5701,
"step": 20
},
{
"epoch": 0.32684824902723736,
"grad_norm": 0.4284273386001587,
"learning_rate": 9.911114283414205e-05,
"loss": 0.5692,
"step": 21
},
{
"epoch": 0.3424124513618677,
"grad_norm": 0.4425485134124756,
"learning_rate": 9.89427842547679e-05,
"loss": 0.6107,
"step": 22
},
{
"epoch": 0.35797665369649806,
"grad_norm": 0.4803674519062042,
"learning_rate": 9.876000201222912e-05,
"loss": 0.6374,
"step": 23
},
{
"epoch": 0.3735408560311284,
"grad_norm": 0.45156747102737427,
"learning_rate": 9.856284997329158e-05,
"loss": 0.6015,
"step": 24
},
{
"epoch": 0.38910505836575876,
"grad_norm": 0.47944512963294983,
"learning_rate": 9.835138623956603e-05,
"loss": 0.6153,
"step": 25
},
{
"epoch": 0.4046692607003891,
"grad_norm": 0.5218237638473511,
"learning_rate": 9.812567313038542e-05,
"loss": 0.6695,
"step": 26
},
{
"epoch": 0.42023346303501946,
"grad_norm": 0.4772241711616516,
"learning_rate": 9.788577716443902e-05,
"loss": 0.6116,
"step": 27
},
{
"epoch": 0.4357976653696498,
"grad_norm": 0.48415690660476685,
"learning_rate": 9.763176904016913e-05,
"loss": 0.6178,
"step": 28
},
{
"epoch": 0.45136186770428016,
"grad_norm": 0.5117486119270325,
"learning_rate": 9.736372361493584e-05,
"loss": 0.6859,
"step": 29
},
{
"epoch": 0.4669260700389105,
"grad_norm": 0.4883125126361847,
"learning_rate": 9.708171988295631e-05,
"loss": 0.6596,
"step": 30
},
{
"epoch": 0.48249027237354086,
"grad_norm": 0.494489848613739,
"learning_rate": 9.678584095202468e-05,
"loss": 0.6489,
"step": 31
},
{
"epoch": 0.4980544747081712,
"grad_norm": 0.5451928973197937,
"learning_rate": 9.647617401902002e-05,
"loss": 0.6672,
"step": 32
},
{
"epoch": 0.5136186770428015,
"grad_norm": 0.36875829100608826,
"learning_rate": 9.61528103442088e-05,
"loss": 0.5941,
"step": 33
},
{
"epoch": 0.5291828793774319,
"grad_norm": 0.39669832587242126,
"learning_rate": 9.581584522435024e-05,
"loss": 0.6472,
"step": 34
},
{
"epoch": 0.5447470817120622,
"grad_norm": 0.37171563506126404,
"learning_rate": 9.546537796461179e-05,
"loss": 0.5654,
"step": 35
},
{
"epoch": 0.5603112840466926,
"grad_norm": 0.3935498893260956,
"learning_rate": 9.510151184930354e-05,
"loss": 0.6021,
"step": 36
},
{
"epoch": 0.5758754863813229,
"grad_norm": 0.43762218952178955,
"learning_rate": 9.472435411143978e-05,
"loss": 0.6841,
"step": 37
},
{
"epoch": 0.5914396887159533,
"grad_norm": 0.42783230543136597,
"learning_rate": 9.433401590113701e-05,
"loss": 0.6359,
"step": 38
},
{
"epoch": 0.6070038910505836,
"grad_norm": 0.4376448094844818,
"learning_rate": 9.393061225285743e-05,
"loss": 0.656,
"step": 39
},
{
"epoch": 0.622568093385214,
"grad_norm": 0.40691596269607544,
"learning_rate": 9.351426205150777e-05,
"loss": 0.6235,
"step": 40
},
{
"epoch": 0.6381322957198443,
"grad_norm": 0.45587652921676636,
"learning_rate": 9.308508799740341e-05,
"loss": 0.6901,
"step": 41
},
{
"epoch": 0.6536964980544747,
"grad_norm": 0.4364193379878998,
"learning_rate": 9.2643216570108e-05,
"loss": 0.6447,
"step": 42
},
{
"epoch": 0.669260700389105,
"grad_norm": 0.4265640079975128,
"learning_rate": 9.218877799115928e-05,
"loss": 0.6589,
"step": 43
},
{
"epoch": 0.6848249027237354,
"grad_norm": 0.4682093560695648,
"learning_rate": 9.172190618569236e-05,
"loss": 0.6511,
"step": 44
},
{
"epoch": 0.7003891050583657,
"grad_norm": 0.43623587489128113,
"learning_rate": 9.124273874297122e-05,
"loss": 0.5936,
"step": 45
},
{
"epoch": 0.7159533073929961,
"grad_norm": 0.48344677686691284,
"learning_rate": 9.075141687584057e-05,
"loss": 0.6775,
"step": 46
},
{
"epoch": 0.7315175097276264,
"grad_norm": 0.4627096652984619,
"learning_rate": 9.024808537910981e-05,
"loss": 0.5983,
"step": 47
},
{
"epoch": 0.7470817120622568,
"grad_norm": 0.49207404255867004,
"learning_rate": 8.973289258688125e-05,
"loss": 0.6198,
"step": 48
},
{
"epoch": 0.7626459143968871,
"grad_norm": 0.3565536439418793,
"learning_rate": 8.920599032883554e-05,
"loss": 0.6415,
"step": 49
},
{
"epoch": 0.7782101167315175,
"grad_norm": 0.37106260657310486,
"learning_rate": 8.86675338854865e-05,
"loss": 0.6197,
"step": 50
},
{
"epoch": 0.7782101167315175,
"eval_loss": 0.6033799052238464,
"eval_runtime": 5.08,
"eval_samples_per_second": 21.26,
"eval_steps_per_second": 5.315,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 193,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 2.481100047777792e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}