diaenra's picture
Training in progress, step 50, checkpoint
50dd6ee verified
{
"best_metric": 2.119426727294922,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.2702702702702703,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005405405405405406,
"grad_norm": 0.16381613910198212,
"learning_rate": 2e-05,
"loss": 2.3432,
"step": 1
},
{
"epoch": 0.005405405405405406,
"eval_loss": 2.171922206878662,
"eval_runtime": 16.6123,
"eval_samples_per_second": 4.695,
"eval_steps_per_second": 2.348,
"step": 1
},
{
"epoch": 0.010810810810810811,
"grad_norm": 0.18275554478168488,
"learning_rate": 4e-05,
"loss": 2.2107,
"step": 2
},
{
"epoch": 0.016216216216216217,
"grad_norm": 0.19883139431476593,
"learning_rate": 6e-05,
"loss": 2.0782,
"step": 3
},
{
"epoch": 0.021621621621621623,
"grad_norm": 0.17207121849060059,
"learning_rate": 8e-05,
"loss": 2.4458,
"step": 4
},
{
"epoch": 0.02702702702702703,
"grad_norm": 0.17877055704593658,
"learning_rate": 0.0001,
"loss": 2.0913,
"step": 5
},
{
"epoch": 0.032432432432432434,
"grad_norm": 0.180442675948143,
"learning_rate": 9.997266286704631e-05,
"loss": 2.3307,
"step": 6
},
{
"epoch": 0.03783783783783784,
"grad_norm": 0.19494755566120148,
"learning_rate": 9.989068136093873e-05,
"loss": 2.4467,
"step": 7
},
{
"epoch": 0.043243243243243246,
"grad_norm": 0.19875937700271606,
"learning_rate": 9.975414512725057e-05,
"loss": 2.4425,
"step": 8
},
{
"epoch": 0.04864864864864865,
"grad_norm": 0.19535940885543823,
"learning_rate": 9.956320346634876e-05,
"loss": 2.4534,
"step": 9
},
{
"epoch": 0.05405405405405406,
"grad_norm": 0.22583356499671936,
"learning_rate": 9.931806517013612e-05,
"loss": 2.1556,
"step": 10
},
{
"epoch": 0.05945945945945946,
"grad_norm": 0.21046710014343262,
"learning_rate": 9.901899829374047e-05,
"loss": 2.4369,
"step": 11
},
{
"epoch": 0.06486486486486487,
"grad_norm": 0.21617771685123444,
"learning_rate": 9.86663298624003e-05,
"loss": 2.1116,
"step": 12
},
{
"epoch": 0.07027027027027027,
"grad_norm": 0.1935390830039978,
"learning_rate": 9.826044551386744e-05,
"loss": 2.1569,
"step": 13
},
{
"epoch": 0.07567567567567568,
"grad_norm": 0.21900971233844757,
"learning_rate": 9.780178907671789e-05,
"loss": 2.1244,
"step": 14
},
{
"epoch": 0.08108108108108109,
"grad_norm": 0.1987326294183731,
"learning_rate": 9.729086208503174e-05,
"loss": 2.2487,
"step": 15
},
{
"epoch": 0.08648648648648649,
"grad_norm": 0.19258294999599457,
"learning_rate": 9.672822322997305e-05,
"loss": 2.3195,
"step": 16
},
{
"epoch": 0.0918918918918919,
"grad_norm": 0.18117763102054596,
"learning_rate": 9.611448774886924e-05,
"loss": 2.2694,
"step": 17
},
{
"epoch": 0.0972972972972973,
"grad_norm": 0.20509183406829834,
"learning_rate": 9.545032675245813e-05,
"loss": 2.0377,
"step": 18
},
{
"epoch": 0.10270270270270271,
"grad_norm": 0.21269042789936066,
"learning_rate": 9.473646649103818e-05,
"loss": 2.1798,
"step": 19
},
{
"epoch": 0.10810810810810811,
"grad_norm": 0.25054454803466797,
"learning_rate": 9.397368756032445e-05,
"loss": 2.176,
"step": 20
},
{
"epoch": 0.11351351351351352,
"grad_norm": 0.21175694465637207,
"learning_rate": 9.316282404787871e-05,
"loss": 2.1471,
"step": 21
},
{
"epoch": 0.11891891891891893,
"grad_norm": 0.21485082805156708,
"learning_rate": 9.230476262104677e-05,
"loss": 2.1054,
"step": 22
},
{
"epoch": 0.12432432432432433,
"grad_norm": 0.215715229511261,
"learning_rate": 9.140044155740101e-05,
"loss": 2.2539,
"step": 23
},
{
"epoch": 0.12972972972972974,
"grad_norm": 0.2235511839389801,
"learning_rate": 9.045084971874738e-05,
"loss": 1.967,
"step": 24
},
{
"epoch": 0.13513513513513514,
"grad_norm": 0.24300596117973328,
"learning_rate": 8.945702546981969e-05,
"loss": 2.2239,
"step": 25
},
{
"epoch": 0.13513513513513514,
"eval_loss": 2.119426727294922,
"eval_runtime": 16.6129,
"eval_samples_per_second": 4.695,
"eval_steps_per_second": 2.348,
"step": 25
},
{
"epoch": 0.14054054054054055,
"grad_norm": 0.23708048462867737,
"learning_rate": 8.842005554284296e-05,
"loss": 2.1888,
"step": 26
},
{
"epoch": 0.14594594594594595,
"grad_norm": 0.2406768947839737,
"learning_rate": 8.73410738492077e-05,
"loss": 2.1915,
"step": 27
},
{
"epoch": 0.15135135135135136,
"grad_norm": 0.24808815121650696,
"learning_rate": 8.622126023955446e-05,
"loss": 2.0992,
"step": 28
},
{
"epoch": 0.15675675675675677,
"grad_norm": 0.25979381799697876,
"learning_rate": 8.506183921362443e-05,
"loss": 2.1816,
"step": 29
},
{
"epoch": 0.16216216216216217,
"grad_norm": 0.26246872544288635,
"learning_rate": 8.386407858128706e-05,
"loss": 2.1843,
"step": 30
},
{
"epoch": 0.16756756756756758,
"grad_norm": 0.23941665887832642,
"learning_rate": 8.262928807620843e-05,
"loss": 2.2098,
"step": 31
},
{
"epoch": 0.17297297297297298,
"grad_norm": 0.2462311089038849,
"learning_rate": 8.135881792367686e-05,
"loss": 2.0607,
"step": 32
},
{
"epoch": 0.1783783783783784,
"grad_norm": 0.2824133038520813,
"learning_rate": 8.005405736415126e-05,
"loss": 2.1525,
"step": 33
},
{
"epoch": 0.1837837837837838,
"grad_norm": 0.3467615842819214,
"learning_rate": 7.871643313414718e-05,
"loss": 2.0407,
"step": 34
},
{
"epoch": 0.1891891891891892,
"grad_norm": 0.30004552006721497,
"learning_rate": 7.734740790612136e-05,
"loss": 2.1346,
"step": 35
},
{
"epoch": 0.1945945945945946,
"grad_norm": 0.29786911606788635,
"learning_rate": 7.594847868906076e-05,
"loss": 2.1989,
"step": 36
},
{
"epoch": 0.2,
"grad_norm": 0.3035438358783722,
"learning_rate": 7.452117519152542e-05,
"loss": 1.9934,
"step": 37
},
{
"epoch": 0.20540540540540542,
"grad_norm": 0.3192494213581085,
"learning_rate": 7.30670581489344e-05,
"loss": 2.1614,
"step": 38
},
{
"epoch": 0.21081081081081082,
"grad_norm": 0.32142555713653564,
"learning_rate": 7.158771761692464e-05,
"loss": 2.142,
"step": 39
},
{
"epoch": 0.21621621621621623,
"grad_norm": 0.2814510762691498,
"learning_rate": 7.008477123264848e-05,
"loss": 2.1949,
"step": 40
},
{
"epoch": 0.22162162162162163,
"grad_norm": 0.27261224389076233,
"learning_rate": 6.855986244591104e-05,
"loss": 2.2867,
"step": 41
},
{
"epoch": 0.22702702702702704,
"grad_norm": 0.3069376051425934,
"learning_rate": 6.701465872208216e-05,
"loss": 2.4095,
"step": 42
},
{
"epoch": 0.23243243243243245,
"grad_norm": 0.30093446373939514,
"learning_rate": 6.545084971874738e-05,
"loss": 2.2246,
"step": 43
},
{
"epoch": 0.23783783783783785,
"grad_norm": 0.37811461091041565,
"learning_rate": 6.387014543809223e-05,
"loss": 2.2689,
"step": 44
},
{
"epoch": 0.24324324324324326,
"grad_norm": 0.4132545292377472,
"learning_rate": 6.227427435703997e-05,
"loss": 2.1285,
"step": 45
},
{
"epoch": 0.24864864864864866,
"grad_norm": 0.4661512076854706,
"learning_rate": 6.066498153718735e-05,
"loss": 2.4561,
"step": 46
},
{
"epoch": 0.25405405405405407,
"grad_norm": 0.18825818598270416,
"learning_rate": 5.90440267166055e-05,
"loss": 2.1234,
"step": 47
},
{
"epoch": 0.2594594594594595,
"grad_norm": 0.17494626343250275,
"learning_rate": 5.74131823855921e-05,
"loss": 2.0999,
"step": 48
},
{
"epoch": 0.2648648648648649,
"grad_norm": 0.1872102916240692,
"learning_rate": 5.577423184847932e-05,
"loss": 2.2597,
"step": 49
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.1854385882616043,
"learning_rate": 5.4128967273616625e-05,
"loss": 2.3098,
"step": 50
},
{
"epoch": 0.2702702702702703,
"eval_loss": 2.1201837062835693,
"eval_runtime": 16.9001,
"eval_samples_per_second": 4.615,
"eval_steps_per_second": 2.308,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 5.304494077457203e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}