diaenra's picture
Training in progress, step 50, checkpoint
a7ffd2c verified
{
"best_metric": 0.9395787715911865,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.016244314489928524,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003248862897985705,
"grad_norm": 0.7047044038772583,
"learning_rate": 0.0001,
"loss": 1.9759,
"step": 1
},
{
"epoch": 0.0003248862897985705,
"eval_loss": 2.686628580093384,
"eval_runtime": 340.4839,
"eval_samples_per_second": 3.809,
"eval_steps_per_second": 1.906,
"step": 1
},
{
"epoch": 0.000649772579597141,
"grad_norm": 0.8073049783706665,
"learning_rate": 0.0002,
"loss": 2.5715,
"step": 2
},
{
"epoch": 0.0009746588693957114,
"grad_norm": 0.8195893168449402,
"learning_rate": 0.00019978589232386035,
"loss": 2.4832,
"step": 3
},
{
"epoch": 0.001299545159194282,
"grad_norm": 1.178743839263916,
"learning_rate": 0.00019914448613738106,
"loss": 2.1465,
"step": 4
},
{
"epoch": 0.0016244314489928524,
"grad_norm": 3.021273136138916,
"learning_rate": 0.00019807852804032305,
"loss": 2.0203,
"step": 5
},
{
"epoch": 0.001949317738791423,
"grad_norm": 1.3877650499343872,
"learning_rate": 0.00019659258262890683,
"loss": 1.8335,
"step": 6
},
{
"epoch": 0.0022742040285899934,
"grad_norm": 1.4954441785812378,
"learning_rate": 0.0001946930129495106,
"loss": 1.8058,
"step": 7
},
{
"epoch": 0.002599090318388564,
"grad_norm": 0.9874308705329895,
"learning_rate": 0.0001923879532511287,
"loss": 1.5395,
"step": 8
},
{
"epoch": 0.0029239766081871343,
"grad_norm": 1.0399869680404663,
"learning_rate": 0.00018968727415326884,
"loss": 1.626,
"step": 9
},
{
"epoch": 0.003248862897985705,
"grad_norm": 0.9299101829528809,
"learning_rate": 0.00018660254037844388,
"loss": 1.5091,
"step": 10
},
{
"epoch": 0.0035737491877842753,
"grad_norm": 0.9380367398262024,
"learning_rate": 0.00018314696123025454,
"loss": 1.4576,
"step": 11
},
{
"epoch": 0.003898635477582846,
"grad_norm": 0.990161657333374,
"learning_rate": 0.00017933533402912354,
"loss": 1.2058,
"step": 12
},
{
"epoch": 0.004223521767381416,
"grad_norm": 1.0648465156555176,
"learning_rate": 0.00017518398074789775,
"loss": 1.0389,
"step": 13
},
{
"epoch": 0.004548408057179987,
"grad_norm": 0.7876304388046265,
"learning_rate": 0.00017071067811865476,
"loss": 1.0257,
"step": 14
},
{
"epoch": 0.004873294346978557,
"grad_norm": 0.7823423743247986,
"learning_rate": 0.00016593458151000688,
"loss": 1.294,
"step": 15
},
{
"epoch": 0.005198180636777128,
"grad_norm": 1.018497109413147,
"learning_rate": 0.00016087614290087208,
"loss": 1.1339,
"step": 16
},
{
"epoch": 0.005523066926575698,
"grad_norm": 0.8195908069610596,
"learning_rate": 0.00015555702330196023,
"loss": 0.943,
"step": 17
},
{
"epoch": 0.005847953216374269,
"grad_norm": 0.914745032787323,
"learning_rate": 0.00015000000000000001,
"loss": 1.0052,
"step": 18
},
{
"epoch": 0.006172839506172839,
"grad_norm": 1.1211453676223755,
"learning_rate": 0.00014422886902190014,
"loss": 1.1446,
"step": 19
},
{
"epoch": 0.00649772579597141,
"grad_norm": 1.2552735805511475,
"learning_rate": 0.000138268343236509,
"loss": 1.1098,
"step": 20
},
{
"epoch": 0.00682261208576998,
"grad_norm": 0.9171386957168579,
"learning_rate": 0.00013214394653031616,
"loss": 0.9569,
"step": 21
},
{
"epoch": 0.007147498375568551,
"grad_norm": 0.934035062789917,
"learning_rate": 0.00012588190451025207,
"loss": 0.955,
"step": 22
},
{
"epoch": 0.007472384665367121,
"grad_norm": 1.086276888847351,
"learning_rate": 0.00011950903220161285,
"loss": 0.9235,
"step": 23
},
{
"epoch": 0.007797270955165692,
"grad_norm": 1.0728775262832642,
"learning_rate": 0.00011305261922200519,
"loss": 0.8594,
"step": 24
},
{
"epoch": 0.008122157244964262,
"grad_norm": 1.2129361629486084,
"learning_rate": 0.00010654031292301432,
"loss": 0.9563,
"step": 25
},
{
"epoch": 0.008122157244964262,
"eval_loss": 0.9595276117324829,
"eval_runtime": 342.6456,
"eval_samples_per_second": 3.785,
"eval_steps_per_second": 1.894,
"step": 25
},
{
"epoch": 0.008447043534762833,
"grad_norm": 1.1689411401748657,
"learning_rate": 0.0001,
"loss": 0.9271,
"step": 26
},
{
"epoch": 0.008771929824561403,
"grad_norm": 0.98142409324646,
"learning_rate": 9.345968707698569e-05,
"loss": 0.7725,
"step": 27
},
{
"epoch": 0.009096816114359974,
"grad_norm": 0.855100154876709,
"learning_rate": 8.694738077799488e-05,
"loss": 0.8737,
"step": 28
},
{
"epoch": 0.009421702404158544,
"grad_norm": 0.7963764667510986,
"learning_rate": 8.049096779838719e-05,
"loss": 0.7265,
"step": 29
},
{
"epoch": 0.009746588693957114,
"grad_norm": 0.6895178556442261,
"learning_rate": 7.411809548974792e-05,
"loss": 0.8324,
"step": 30
},
{
"epoch": 0.010071474983755685,
"grad_norm": 0.8792585730552673,
"learning_rate": 6.785605346968386e-05,
"loss": 0.7426,
"step": 31
},
{
"epoch": 0.010396361273554255,
"grad_norm": 0.7640400528907776,
"learning_rate": 6.173165676349103e-05,
"loss": 0.8364,
"step": 32
},
{
"epoch": 0.010721247563352826,
"grad_norm": 0.717138409614563,
"learning_rate": 5.577113097809989e-05,
"loss": 0.8579,
"step": 33
},
{
"epoch": 0.011046133853151396,
"grad_norm": 0.6296213269233704,
"learning_rate": 5.000000000000002e-05,
"loss": 0.7416,
"step": 34
},
{
"epoch": 0.011371020142949967,
"grad_norm": 0.6830035448074341,
"learning_rate": 4.444297669803981e-05,
"loss": 0.793,
"step": 35
},
{
"epoch": 0.011695906432748537,
"grad_norm": 0.866948664188385,
"learning_rate": 3.9123857099127936e-05,
"loss": 0.7564,
"step": 36
},
{
"epoch": 0.012020792722547108,
"grad_norm": 0.7266378998756409,
"learning_rate": 3.406541848999312e-05,
"loss": 0.9034,
"step": 37
},
{
"epoch": 0.012345679012345678,
"grad_norm": 0.752968966960907,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.8902,
"step": 38
},
{
"epoch": 0.012670565302144249,
"grad_norm": 0.6887612342834473,
"learning_rate": 2.4816019252102273e-05,
"loss": 0.7917,
"step": 39
},
{
"epoch": 0.01299545159194282,
"grad_norm": 0.913896918296814,
"learning_rate": 2.0664665970876496e-05,
"loss": 0.7918,
"step": 40
},
{
"epoch": 0.01332033788174139,
"grad_norm": 0.7052801847457886,
"learning_rate": 1.6853038769745467e-05,
"loss": 0.6793,
"step": 41
},
{
"epoch": 0.01364522417153996,
"grad_norm": 0.6854836940765381,
"learning_rate": 1.339745962155613e-05,
"loss": 0.7743,
"step": 42
},
{
"epoch": 0.01397011046133853,
"grad_norm": 0.6507396697998047,
"learning_rate": 1.0312725846731175e-05,
"loss": 0.8359,
"step": 43
},
{
"epoch": 0.014294996751137101,
"grad_norm": 0.7426648139953613,
"learning_rate": 7.612046748871327e-06,
"loss": 0.8788,
"step": 44
},
{
"epoch": 0.014619883040935672,
"grad_norm": 0.569381058216095,
"learning_rate": 5.306987050489442e-06,
"loss": 0.7171,
"step": 45
},
{
"epoch": 0.014944769330734242,
"grad_norm": 0.7846092581748962,
"learning_rate": 3.40741737109318e-06,
"loss": 0.7299,
"step": 46
},
{
"epoch": 0.015269655620532813,
"grad_norm": 0.6389809250831604,
"learning_rate": 1.921471959676957e-06,
"loss": 0.7145,
"step": 47
},
{
"epoch": 0.015594541910331383,
"grad_norm": 0.5611962676048279,
"learning_rate": 8.555138626189618e-07,
"loss": 0.6854,
"step": 48
},
{
"epoch": 0.015919428200129954,
"grad_norm": 0.8515998125076294,
"learning_rate": 2.141076761396521e-07,
"loss": 0.7188,
"step": 49
},
{
"epoch": 0.016244314489928524,
"grad_norm": 1.1273244619369507,
"learning_rate": 0.0,
"loss": 0.8396,
"step": 50
},
{
"epoch": 0.016244314489928524,
"eval_loss": 0.9395787715911865,
"eval_runtime": 342.6187,
"eval_samples_per_second": 3.786,
"eval_steps_per_second": 1.894,
"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": 6.53464644354048e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}