{
"best_metric": 11.886322975158691,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.2084592145015105,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02416918429003021,
"grad_norm": 0.16678477823734283,
"learning_rate": 5e-05,
"loss": 11.9325,
"step": 1
},
{
"epoch": 0.02416918429003021,
"eval_loss": 11.933916091918945,
"eval_runtime": 0.7187,
"eval_samples_per_second": 69.57,
"eval_steps_per_second": 18.088,
"step": 1
},
{
"epoch": 0.04833836858006042,
"grad_norm": 0.21486212313175201,
"learning_rate": 0.0001,
"loss": 11.9342,
"step": 2
},
{
"epoch": 0.07250755287009064,
"grad_norm": 0.20214402675628662,
"learning_rate": 9.990365154573717e-05,
"loss": 11.9334,
"step": 3
},
{
"epoch": 0.09667673716012085,
"grad_norm": 0.22815577685832977,
"learning_rate": 9.961501876182148e-05,
"loss": 11.9318,
"step": 4
},
{
"epoch": 0.12084592145015106,
"grad_norm": 0.22736570239067078,
"learning_rate": 9.913533761814537e-05,
"loss": 11.9307,
"step": 5
},
{
"epoch": 0.14501510574018128,
"grad_norm": 0.26235222816467285,
"learning_rate": 9.846666218300807e-05,
"loss": 11.9287,
"step": 6
},
{
"epoch": 0.1691842900302115,
"grad_norm": 0.27037128806114197,
"learning_rate": 9.761185582727977e-05,
"loss": 11.9269,
"step": 7
},
{
"epoch": 0.1933534743202417,
"grad_norm": 0.33564624190330505,
"learning_rate": 9.657457896300791e-05,
"loss": 11.9265,
"step": 8
},
{
"epoch": 0.2175226586102719,
"grad_norm": 0.3858741521835327,
"learning_rate": 9.535927336897098e-05,
"loss": 11.9177,
"step": 9
},
{
"epoch": 0.24169184290030213,
"grad_norm": 0.4156636595726013,
"learning_rate": 9.397114317029975e-05,
"loss": 11.9182,
"step": 10
},
{
"epoch": 0.26586102719033233,
"grad_norm": 0.2522761821746826,
"learning_rate": 9.241613255361455e-05,
"loss": 11.9218,
"step": 11
},
{
"epoch": 0.29003021148036257,
"grad_norm": 0.3045474886894226,
"learning_rate": 9.070090031310558e-05,
"loss": 11.9201,
"step": 12
},
{
"epoch": 0.31419939577039274,
"grad_norm": 0.33387333154678345,
"learning_rate": 8.883279133655399e-05,
"loss": 11.918,
"step": 13
},
{
"epoch": 0.338368580060423,
"grad_norm": 0.35145607590675354,
"learning_rate": 8.681980515339464e-05,
"loss": 11.9163,
"step": 14
},
{
"epoch": 0.36253776435045315,
"grad_norm": 0.3631150424480438,
"learning_rate": 8.467056167950311e-05,
"loss": 11.9133,
"step": 15
},
{
"epoch": 0.3867069486404834,
"grad_norm": 0.37244999408721924,
"learning_rate": 8.239426430539243e-05,
"loss": 11.913,
"step": 16
},
{
"epoch": 0.4108761329305136,
"grad_norm": 0.37325963377952576,
"learning_rate": 8.000066048588211e-05,
"loss": 11.9079,
"step": 17
},
{
"epoch": 0.4350453172205438,
"grad_norm": 0.3925626277923584,
"learning_rate": 7.75e-05,
"loss": 11.9064,
"step": 18
},
{
"epoch": 0.459214501510574,
"grad_norm": 0.3912876844406128,
"learning_rate": 7.490299105985507e-05,
"loss": 11.9037,
"step": 19
},
{
"epoch": 0.48338368580060426,
"grad_norm": 0.4554908871650696,
"learning_rate": 7.222075445642904e-05,
"loss": 11.8981,
"step": 20
},
{
"epoch": 0.5075528700906344,
"grad_norm": 0.333280473947525,
"learning_rate": 6.946477593864228e-05,
"loss": 11.9102,
"step": 21
},
{
"epoch": 0.5317220543806647,
"grad_norm": 0.3596556782722473,
"learning_rate": 6.664685702961344e-05,
"loss": 11.9059,
"step": 22
},
{
"epoch": 0.5558912386706949,
"grad_norm": 0.3553027808666229,
"learning_rate": 6.377906449072578e-05,
"loss": 11.9032,
"step": 23
},
{
"epoch": 0.5800604229607251,
"grad_norm": 0.3382004499435425,
"learning_rate": 6.087367864990233e-05,
"loss": 11.9019,
"step": 24
},
{
"epoch": 0.6042296072507553,
"grad_norm": 0.3431967794895172,
"learning_rate": 5.794314081535644e-05,
"loss": 11.9007,
"step": 25
},
{
"epoch": 0.6042296072507553,
"eval_loss": 11.896537780761719,
"eval_runtime": 0.4202,
"eval_samples_per_second": 119.0,
"eval_steps_per_second": 30.94,
"step": 25
},
{
"epoch": 0.6283987915407855,
"grad_norm": 0.32997435331344604,
"learning_rate": 5.500000000000001e-05,
"loss": 11.8971,
"step": 26
},
{
"epoch": 0.6525679758308157,
"grad_norm": 0.30715274810791016,
"learning_rate": 5.205685918464356e-05,
"loss": 11.8941,
"step": 27
},
{
"epoch": 0.676737160120846,
"grad_norm": 0.29583367705345154,
"learning_rate": 4.912632135009769e-05,
"loss": 11.8952,
"step": 28
},
{
"epoch": 0.7009063444108762,
"grad_norm": 0.3171089291572571,
"learning_rate": 4.6220935509274235e-05,
"loss": 11.8913,
"step": 29
},
{
"epoch": 0.7250755287009063,
"grad_norm": 0.35418152809143066,
"learning_rate": 4.3353142970386564e-05,
"loss": 11.8905,
"step": 30
},
{
"epoch": 0.7492447129909365,
"grad_norm": 0.3350968062877655,
"learning_rate": 4.053522406135775e-05,
"loss": 11.8956,
"step": 31
},
{
"epoch": 0.7734138972809668,
"grad_norm": 0.3001876473426819,
"learning_rate": 3.777924554357096e-05,
"loss": 11.8968,
"step": 32
},
{
"epoch": 0.797583081570997,
"grad_norm": 0.3062438368797302,
"learning_rate": 3.509700894014496e-05,
"loss": 11.8931,
"step": 33
},
{
"epoch": 0.8217522658610272,
"grad_norm": 0.2976103723049164,
"learning_rate": 3.250000000000001e-05,
"loss": 11.8914,
"step": 34
},
{
"epoch": 0.8459214501510574,
"grad_norm": 0.2852192223072052,
"learning_rate": 2.9999339514117912e-05,
"loss": 11.8905,
"step": 35
},
{
"epoch": 0.8700906344410876,
"grad_norm": 0.27989819645881653,
"learning_rate": 2.760573569460757e-05,
"loss": 11.8896,
"step": 36
},
{
"epoch": 0.8942598187311178,
"grad_norm": 0.2709686756134033,
"learning_rate": 2.53294383204969e-05,
"loss": 11.8924,
"step": 37
},
{
"epoch": 0.918429003021148,
"grad_norm": 0.25340571999549866,
"learning_rate": 2.3180194846605367e-05,
"loss": 11.8902,
"step": 38
},
{
"epoch": 0.9425981873111783,
"grad_norm": 0.2850501835346222,
"learning_rate": 2.1167208663446025e-05,
"loss": 11.8876,
"step": 39
},
{
"epoch": 0.9667673716012085,
"grad_norm": 0.28280991315841675,
"learning_rate": 1.9299099686894423e-05,
"loss": 11.8828,
"step": 40
},
{
"epoch": 0.9909365558912386,
"grad_norm": 0.4183381497859955,
"learning_rate": 1.758386744638546e-05,
"loss": 11.8819,
"step": 41
},
{
"epoch": 1.0151057401812689,
"grad_norm": 0.5442397594451904,
"learning_rate": 1.602885682970026e-05,
"loss": 20.7319,
"step": 42
},
{
"epoch": 1.039274924471299,
"grad_norm": 0.25542905926704407,
"learning_rate": 1.464072663102903e-05,
"loss": 11.0284,
"step": 43
},
{
"epoch": 1.0634441087613293,
"grad_norm": 0.2500249147415161,
"learning_rate": 1.3425421036992098e-05,
"loss": 11.705,
"step": 44
},
{
"epoch": 1.0876132930513596,
"grad_norm": 0.2602107524871826,
"learning_rate": 1.2388144172720251e-05,
"loss": 11.9346,
"step": 45
},
{
"epoch": 1.1117824773413898,
"grad_norm": 0.2505055367946625,
"learning_rate": 1.1533337816991932e-05,
"loss": 11.8477,
"step": 46
},
{
"epoch": 1.13595166163142,
"grad_norm": 0.2512243390083313,
"learning_rate": 1.0864662381854632e-05,
"loss": 11.8917,
"step": 47
},
{
"epoch": 1.1601208459214503,
"grad_norm": 0.2396506816148758,
"learning_rate": 1.0384981238178534e-05,
"loss": 11.8054,
"step": 48
},
{
"epoch": 1.1842900302114803,
"grad_norm": 0.2575649917125702,
"learning_rate": 1.0096348454262845e-05,
"loss": 11.848,
"step": 49
},
{
"epoch": 1.2084592145015105,
"grad_norm": 0.29371464252471924,
"learning_rate": 1e-05,
"loss": 12.1832,
"step": 50
},
{
"epoch": 1.2084592145015105,
"eval_loss": 11.886322975158691,
"eval_runtime": 0.4237,
"eval_samples_per_second": 118.019,
"eval_steps_per_second": 30.685,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 418126689206272.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}