diaenra's picture
Training in progress, step 50, checkpoint
b137032 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.0015008930313536555,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.0017860627073107e-05,
"grad_norm": 3.493117570877075,
"learning_rate": 0.0001,
"loss": 1.0048,
"step": 1
},
{
"epoch": 3.0017860627073107e-05,
"eval_loss": NaN,
"eval_runtime": 4690.3959,
"eval_samples_per_second": 2.991,
"eval_steps_per_second": 1.495,
"step": 1
},
{
"epoch": 6.0035721254146214e-05,
"grad_norm": 2.2091894149780273,
"learning_rate": 0.0002,
"loss": 0.6177,
"step": 2
},
{
"epoch": 9.005358188121933e-05,
"grad_norm": 12.579239845275879,
"learning_rate": 0.00019978589232386035,
"loss": 3.2664,
"step": 3
},
{
"epoch": 0.00012007144250829243,
"grad_norm": 4.013683795928955,
"learning_rate": 0.00019914448613738106,
"loss": 0.4527,
"step": 4
},
{
"epoch": 0.00015008930313536553,
"grad_norm": 9.094101905822754,
"learning_rate": 0.00019807852804032305,
"loss": 0.9347,
"step": 5
},
{
"epoch": 0.00018010716376243866,
"grad_norm": 15.784138679504395,
"learning_rate": 0.00019659258262890683,
"loss": 1.3421,
"step": 6
},
{
"epoch": 0.00021012502438951176,
"grad_norm": 2.611325740814209,
"learning_rate": 0.0001946930129495106,
"loss": 0.0857,
"step": 7
},
{
"epoch": 0.00024014288501658486,
"grad_norm": 4.040042877197266,
"learning_rate": 0.0001923879532511287,
"loss": 0.1064,
"step": 8
},
{
"epoch": 0.00027016074564365796,
"grad_norm": 0.0,
"learning_rate": 0.00018968727415326884,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.00030017860627073106,
"grad_norm": 0.0,
"learning_rate": 0.00018660254037844388,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.0003301964668978042,
"grad_norm": 3.977330207824707,
"learning_rate": 0.00018314696123025454,
"loss": 0.0744,
"step": 11
},
{
"epoch": 0.0003602143275248773,
"grad_norm": 0.0,
"learning_rate": 0.00017933533402912354,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.0003902321881519504,
"grad_norm": 1.0647913217544556,
"learning_rate": 0.00017518398074789775,
"loss": 0.0165,
"step": 13
},
{
"epoch": 0.0004202500487790235,
"grad_norm": 3.6986823081970215,
"learning_rate": 0.00017071067811865476,
"loss": 0.0304,
"step": 14
},
{
"epoch": 0.0004502679094060966,
"grad_norm": 0.0,
"learning_rate": 0.00016593458151000688,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.0004802857700331697,
"grad_norm": 0.10584675520658493,
"learning_rate": 0.00016087614290087208,
"loss": 0.0015,
"step": 16
},
{
"epoch": 0.0005103036306602428,
"grad_norm": 0.4548289477825165,
"learning_rate": 0.00015555702330196023,
"loss": 0.0066,
"step": 17
},
{
"epoch": 0.0005403214912873159,
"grad_norm": 0.03853747248649597,
"learning_rate": 0.00015000000000000001,
"loss": 0.0005,
"step": 18
},
{
"epoch": 0.000570339351914389,
"grad_norm": 0.0,
"learning_rate": 0.00014422886902190014,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.0006003572125414621,
"grad_norm": 12.873373985290527,
"learning_rate": 0.000138268343236509,
"loss": 0.0926,
"step": 20
},
{
"epoch": 0.0006303750731685353,
"grad_norm": 0.10906705260276794,
"learning_rate": 0.00013214394653031616,
"loss": 0.0004,
"step": 21
},
{
"epoch": 0.0006603929337956084,
"grad_norm": 0.05691908299922943,
"learning_rate": 0.00012588190451025207,
"loss": 0.0009,
"step": 22
},
{
"epoch": 0.0006904107944226815,
"grad_norm": 0.0,
"learning_rate": 0.00011950903220161285,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.0007204286550497546,
"grad_norm": 0.009437690488994122,
"learning_rate": 0.00011305261922200519,
"loss": 0.0002,
"step": 24
},
{
"epoch": 0.0007504465156768277,
"grad_norm": 0.0056793950498104095,
"learning_rate": 0.00010654031292301432,
"loss": 0.0002,
"step": 25
},
{
"epoch": 0.0007504465156768277,
"eval_loss": NaN,
"eval_runtime": 4700.8492,
"eval_samples_per_second": 2.984,
"eval_steps_per_second": 1.492,
"step": 25
},
{
"epoch": 0.0007804643763039008,
"grad_norm": 0.0,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.0008104822369309739,
"grad_norm": 11.411437034606934,
"learning_rate": 9.345968707698569e-05,
"loss": 0.4422,
"step": 27
},
{
"epoch": 0.000840500097558047,
"grad_norm": 0.0016927358228713274,
"learning_rate": 8.694738077799488e-05,
"loss": 0.0001,
"step": 28
},
{
"epoch": 0.0008705179581851201,
"grad_norm": 0.3806565999984741,
"learning_rate": 8.049096779838719e-05,
"loss": 0.0083,
"step": 29
},
{
"epoch": 0.0009005358188121932,
"grad_norm": 2.338160753250122,
"learning_rate": 7.411809548974792e-05,
"loss": 0.0228,
"step": 30
},
{
"epoch": 0.0009305536794392663,
"grad_norm": 3.414599895477295,
"learning_rate": 6.785605346968386e-05,
"loss": 0.0331,
"step": 31
},
{
"epoch": 0.0009605715400663394,
"grad_norm": 0.022703867405653,
"learning_rate": 6.173165676349103e-05,
"loss": 0.0003,
"step": 32
},
{
"epoch": 0.0009905894006934125,
"grad_norm": 0.0,
"learning_rate": 5.577113097809989e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.0010206072613204856,
"grad_norm": 0.0,
"learning_rate": 5.000000000000002e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.0010506251219475587,
"grad_norm": 0.0,
"learning_rate": 4.444297669803981e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.0010806429825746318,
"grad_norm": 0.19225087761878967,
"learning_rate": 3.9123857099127936e-05,
"loss": 0.0021,
"step": 36
},
{
"epoch": 0.001110660843201705,
"grad_norm": 0.0,
"learning_rate": 3.406541848999312e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.001140678703828778,
"grad_norm": 3.7654895782470703,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.0465,
"step": 38
},
{
"epoch": 0.0011706965644558511,
"grad_norm": 11.871513366699219,
"learning_rate": 2.4816019252102273e-05,
"loss": 0.2006,
"step": 39
},
{
"epoch": 0.0012007144250829242,
"grad_norm": 1.8782795667648315,
"learning_rate": 2.0664665970876496e-05,
"loss": 0.0129,
"step": 40
},
{
"epoch": 0.0012307322857099976,
"grad_norm": 10.00529670715332,
"learning_rate": 1.6853038769745467e-05,
"loss": 0.5964,
"step": 41
},
{
"epoch": 0.0012607501463370707,
"grad_norm": 0.6463675498962402,
"learning_rate": 1.339745962155613e-05,
"loss": 0.0065,
"step": 42
},
{
"epoch": 0.0012907680069641438,
"grad_norm": 0.0,
"learning_rate": 1.0312725846731175e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.0013207858675912169,
"grad_norm": 0.0,
"learning_rate": 7.612046748871327e-06,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.00135080372821829,
"grad_norm": 0.0,
"learning_rate": 5.306987050489442e-06,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.001380821588845363,
"grad_norm": 0.0,
"learning_rate": 3.40741737109318e-06,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.0014108394494724362,
"grad_norm": 0.0,
"learning_rate": 1.921471959676957e-06,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.0014408573100995093,
"grad_norm": 0.0,
"learning_rate": 8.555138626189618e-07,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.0014708751707265824,
"grad_norm": 0.0,
"learning_rate": 2.141076761396521e-07,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.0015008930313536555,
"grad_norm": 0.0,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.0015008930313536555,
"eval_loss": NaN,
"eval_runtime": 4703.3313,
"eval_samples_per_second": 2.982,
"eval_steps_per_second": 1.491,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7.455971246447002e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}