Dnsx077's picture
Training in progress, step 50, checkpoint
8d0d9a3 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.003957104981995172,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.914209963990345e-05,
"grad_norm": 0.45526230335235596,
"learning_rate": 0.0001,
"loss": 2.6313,
"step": 1
},
{
"epoch": 7.914209963990345e-05,
"eval_loss": NaN,
"eval_runtime": 1683.6782,
"eval_samples_per_second": 3.16,
"eval_steps_per_second": 1.58,
"step": 1
},
{
"epoch": 0.0001582841992798069,
"grad_norm": 1.0217220783233643,
"learning_rate": 0.0002,
"loss": 2.4539,
"step": 2
},
{
"epoch": 0.00023742629891971033,
"grad_norm": 0.44594258069992065,
"learning_rate": 0.00019978589232386035,
"loss": 2.3191,
"step": 3
},
{
"epoch": 0.0003165683985596138,
"grad_norm": NaN,
"learning_rate": 0.00019914448613738106,
"loss": 4.5371,
"step": 4
},
{
"epoch": 0.00039571049819951725,
"grad_norm": NaN,
"learning_rate": 0.00019807852804032305,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.00047485259783942065,
"grad_norm": NaN,
"learning_rate": 0.00019659258262890683,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.0005539946974793241,
"grad_norm": NaN,
"learning_rate": 0.0001946930129495106,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.0006331367971192276,
"grad_norm": NaN,
"learning_rate": 0.0001923879532511287,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.000712278896759131,
"grad_norm": NaN,
"learning_rate": 0.00018968727415326884,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.0007914209963990345,
"grad_norm": NaN,
"learning_rate": 0.00018660254037844388,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.000870563096038938,
"grad_norm": NaN,
"learning_rate": 0.00018314696123025454,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.0009497051956788413,
"grad_norm": NaN,
"learning_rate": 0.00017933533402912354,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.0010288472953187448,
"grad_norm": NaN,
"learning_rate": 0.00017518398074789775,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.0011079893949586482,
"grad_norm": NaN,
"learning_rate": 0.00017071067811865476,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.0011871314945985517,
"grad_norm": NaN,
"learning_rate": 0.00016593458151000688,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.0012662735942384552,
"grad_norm": NaN,
"learning_rate": 0.00016087614290087208,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.0013454156938783586,
"grad_norm": NaN,
"learning_rate": 0.00015555702330196023,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.001424557793518262,
"grad_norm": NaN,
"learning_rate": 0.00015000000000000001,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.0015036998931581655,
"grad_norm": NaN,
"learning_rate": 0.00014422886902190014,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.001582841992798069,
"grad_norm": NaN,
"learning_rate": 0.000138268343236509,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.0016619840924379725,
"grad_norm": NaN,
"learning_rate": 0.00013214394653031616,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.001741126192077876,
"grad_norm": NaN,
"learning_rate": 0.00012588190451025207,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.0018202682917177794,
"grad_norm": NaN,
"learning_rate": 0.00011950903220161285,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.0018994103913576826,
"grad_norm": NaN,
"learning_rate": 0.00011305261922200519,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.001978552490997586,
"grad_norm": NaN,
"learning_rate": 0.00010654031292301432,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.001978552490997586,
"eval_loss": NaN,
"eval_runtime": 1673.9743,
"eval_samples_per_second": 3.179,
"eval_steps_per_second": 1.59,
"step": 25
},
{
"epoch": 0.0020576945906374895,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.002136836690277393,
"grad_norm": NaN,
"learning_rate": 9.345968707698569e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.0022159787899172965,
"grad_norm": NaN,
"learning_rate": 8.694738077799488e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.0022951208895572,
"grad_norm": NaN,
"learning_rate": 8.049096779838719e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.0023742629891971034,
"grad_norm": NaN,
"learning_rate": 7.411809548974792e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.002453405088837007,
"grad_norm": NaN,
"learning_rate": 6.785605346968386e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.0025325471884769103,
"grad_norm": NaN,
"learning_rate": 6.173165676349103e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.0026116892881168138,
"grad_norm": NaN,
"learning_rate": 5.577113097809989e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.0026908313877567172,
"grad_norm": NaN,
"learning_rate": 5.000000000000002e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.0027699734873966207,
"grad_norm": NaN,
"learning_rate": 4.444297669803981e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.002849115587036524,
"grad_norm": NaN,
"learning_rate": 3.9123857099127936e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.0029282576866764276,
"grad_norm": NaN,
"learning_rate": 3.406541848999312e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.003007399786316331,
"grad_norm": NaN,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.0030865418859562345,
"grad_norm": NaN,
"learning_rate": 2.4816019252102273e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.003165683985596138,
"grad_norm": NaN,
"learning_rate": 2.0664665970876496e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.0032448260852360414,
"grad_norm": NaN,
"learning_rate": 1.6853038769745467e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.003323968184875945,
"grad_norm": NaN,
"learning_rate": 1.339745962155613e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.0034031102845158484,
"grad_norm": NaN,
"learning_rate": 1.0312725846731175e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.003482252384155752,
"grad_norm": NaN,
"learning_rate": 7.612046748871327e-06,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.0035613944837956553,
"grad_norm": NaN,
"learning_rate": 5.306987050489442e-06,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.0036405365834355588,
"grad_norm": NaN,
"learning_rate": 3.40741737109318e-06,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.0037196786830754618,
"grad_norm": NaN,
"learning_rate": 1.921471959676957e-06,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.0037988207827153652,
"grad_norm": NaN,
"learning_rate": 8.555138626189618e-07,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.0038779628823552687,
"grad_norm": NaN,
"learning_rate": 2.141076761396521e-07,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.003957104981995172,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.003957104981995172,
"eval_loss": NaN,
"eval_runtime": 1673.2204,
"eval_samples_per_second": 3.18,
"eval_steps_per_second": 1.59,
"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": 6.59230637948928e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}