{
"best_metric": 1.4524505138397217,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.4333694474539545,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00866738894907909,
"grad_norm": 33.48080062866211,
"learning_rate": 5e-05,
"loss": 54.4829,
"step": 1
},
{
"epoch": 0.00866738894907909,
"eval_loss": 1.9447823762893677,
"eval_runtime": 1.6805,
"eval_samples_per_second": 29.753,
"eval_steps_per_second": 7.736,
"step": 1
},
{
"epoch": 0.01733477789815818,
"grad_norm": 37.40660858154297,
"learning_rate": 0.0001,
"loss": 67.9683,
"step": 2
},
{
"epoch": 0.02600216684723727,
"grad_norm": 36.08869171142578,
"learning_rate": 9.990365154573717e-05,
"loss": 59.4156,
"step": 3
},
{
"epoch": 0.03466955579631636,
"grad_norm": 29.739288330078125,
"learning_rate": 9.961501876182148e-05,
"loss": 60.0192,
"step": 4
},
{
"epoch": 0.04333694474539545,
"grad_norm": 29.204097747802734,
"learning_rate": 9.913533761814537e-05,
"loss": 56.788,
"step": 5
},
{
"epoch": 0.05200433369447454,
"grad_norm": 20.075462341308594,
"learning_rate": 9.846666218300807e-05,
"loss": 65.0943,
"step": 6
},
{
"epoch": 0.06067172264355363,
"grad_norm": 25.222434997558594,
"learning_rate": 9.761185582727977e-05,
"loss": 62.6278,
"step": 7
},
{
"epoch": 0.06933911159263272,
"grad_norm": 20.052955627441406,
"learning_rate": 9.657457896300791e-05,
"loss": 59.7374,
"step": 8
},
{
"epoch": 0.0780065005417118,
"grad_norm": 29.25498390197754,
"learning_rate": 9.535927336897098e-05,
"loss": 55.3679,
"step": 9
},
{
"epoch": 0.0866738894907909,
"grad_norm": 28.908437728881836,
"learning_rate": 9.397114317029975e-05,
"loss": 51.6582,
"step": 10
},
{
"epoch": 0.09534127843986999,
"grad_norm": 30.49123191833496,
"learning_rate": 9.241613255361455e-05,
"loss": 39.6568,
"step": 11
},
{
"epoch": 0.10400866738894908,
"grad_norm": 42.93205642700195,
"learning_rate": 9.070090031310558e-05,
"loss": 30.9448,
"step": 12
},
{
"epoch": 0.11267605633802817,
"grad_norm": 36.81696701049805,
"learning_rate": 8.883279133655399e-05,
"loss": 40.7136,
"step": 13
},
{
"epoch": 0.12134344528710726,
"grad_norm": 48.10126495361328,
"learning_rate": 8.681980515339464e-05,
"loss": 47.0138,
"step": 14
},
{
"epoch": 0.13001083423618634,
"grad_norm": 31.382658004760742,
"learning_rate": 8.467056167950311e-05,
"loss": 48.1751,
"step": 15
},
{
"epoch": 0.13867822318526543,
"grad_norm": 35.335357666015625,
"learning_rate": 8.239426430539243e-05,
"loss": 52.9875,
"step": 16
},
{
"epoch": 0.14734561213434452,
"grad_norm": 50.4722785949707,
"learning_rate": 8.000066048588211e-05,
"loss": 54.7339,
"step": 17
},
{
"epoch": 0.1560130010834236,
"grad_norm": 43.65807342529297,
"learning_rate": 7.75e-05,
"loss": 61.6515,
"step": 18
},
{
"epoch": 0.1646803900325027,
"grad_norm": 24.18115997314453,
"learning_rate": 7.490299105985507e-05,
"loss": 63.4512,
"step": 19
},
{
"epoch": 0.1733477789815818,
"grad_norm": 17.75979995727539,
"learning_rate": 7.222075445642904e-05,
"loss": 61.9979,
"step": 20
},
{
"epoch": 0.1820151679306609,
"grad_norm": 17.052209854125977,
"learning_rate": 6.946477593864228e-05,
"loss": 55.7179,
"step": 21
},
{
"epoch": 0.19068255687973998,
"grad_norm": 18.24669075012207,
"learning_rate": 6.664685702961344e-05,
"loss": 50.7537,
"step": 22
},
{
"epoch": 0.19934994582881907,
"grad_norm": 21.08188247680664,
"learning_rate": 6.377906449072578e-05,
"loss": 50.985,
"step": 23
},
{
"epoch": 0.20801733477789816,
"grad_norm": 25.197586059570312,
"learning_rate": 6.087367864990233e-05,
"loss": 33.4469,
"step": 24
},
{
"epoch": 0.21668472372697725,
"grad_norm": 48.54851531982422,
"learning_rate": 5.794314081535644e-05,
"loss": 25.6124,
"step": 25
},
{
"epoch": 0.21668472372697725,
"eval_loss": 1.498545527458191,
"eval_runtime": 1.7268,
"eval_samples_per_second": 28.955,
"eval_steps_per_second": 7.528,
"step": 25
},
{
"epoch": 0.22535211267605634,
"grad_norm": 32.12018966674805,
"learning_rate": 5.500000000000001e-05,
"loss": 50.9971,
"step": 26
},
{
"epoch": 0.23401950162513543,
"grad_norm": 38.02103805541992,
"learning_rate": 5.205685918464356e-05,
"loss": 50.2586,
"step": 27
},
{
"epoch": 0.24268689057421453,
"grad_norm": 32.75697708129883,
"learning_rate": 4.912632135009769e-05,
"loss": 50.45,
"step": 28
},
{
"epoch": 0.2513542795232936,
"grad_norm": 18.196666717529297,
"learning_rate": 4.6220935509274235e-05,
"loss": 51.8491,
"step": 29
},
{
"epoch": 0.2600216684723727,
"grad_norm": 16.83131217956543,
"learning_rate": 4.3353142970386564e-05,
"loss": 59.5798,
"step": 30
},
{
"epoch": 0.26868905742145177,
"grad_norm": 20.428844451904297,
"learning_rate": 4.053522406135775e-05,
"loss": 63.1483,
"step": 31
},
{
"epoch": 0.27735644637053086,
"grad_norm": 26.761188507080078,
"learning_rate": 3.777924554357096e-05,
"loss": 68.5665,
"step": 32
},
{
"epoch": 0.28602383531960995,
"grad_norm": 28.98684310913086,
"learning_rate": 3.509700894014496e-05,
"loss": 60.8287,
"step": 33
},
{
"epoch": 0.29469122426868904,
"grad_norm": 28.409412384033203,
"learning_rate": 3.250000000000001e-05,
"loss": 53.0851,
"step": 34
},
{
"epoch": 0.30335861321776814,
"grad_norm": 22.734962463378906,
"learning_rate": 2.9999339514117912e-05,
"loss": 53.2058,
"step": 35
},
{
"epoch": 0.3120260021668472,
"grad_norm": 23.15952491760254,
"learning_rate": 2.760573569460757e-05,
"loss": 38.0991,
"step": 36
},
{
"epoch": 0.3206933911159263,
"grad_norm": 22.231393814086914,
"learning_rate": 2.53294383204969e-05,
"loss": 33.401,
"step": 37
},
{
"epoch": 0.3293607800650054,
"grad_norm": 25.417402267456055,
"learning_rate": 2.3180194846605367e-05,
"loss": 33.4547,
"step": 38
},
{
"epoch": 0.3380281690140845,
"grad_norm": 14.123833656311035,
"learning_rate": 2.1167208663446025e-05,
"loss": 49.6472,
"step": 39
},
{
"epoch": 0.3466955579631636,
"grad_norm": 12.762784957885742,
"learning_rate": 1.9299099686894423e-05,
"loss": 50.7568,
"step": 40
},
{
"epoch": 0.3553629469122427,
"grad_norm": 12.12992000579834,
"learning_rate": 1.758386744638546e-05,
"loss": 49.1412,
"step": 41
},
{
"epoch": 0.3640303358613218,
"grad_norm": 11.25378131866455,
"learning_rate": 1.602885682970026e-05,
"loss": 55.4105,
"step": 42
},
{
"epoch": 0.37269772481040087,
"grad_norm": 11.424920082092285,
"learning_rate": 1.464072663102903e-05,
"loss": 57.2247,
"step": 43
},
{
"epoch": 0.38136511375947996,
"grad_norm": 11.259847640991211,
"learning_rate": 1.3425421036992098e-05,
"loss": 60.8376,
"step": 44
},
{
"epoch": 0.39003250270855905,
"grad_norm": 11.650426864624023,
"learning_rate": 1.2388144172720251e-05,
"loss": 60.549,
"step": 45
},
{
"epoch": 0.39869989165763814,
"grad_norm": 12.492819786071777,
"learning_rate": 1.1533337816991932e-05,
"loss": 58.7039,
"step": 46
},
{
"epoch": 0.40736728060671723,
"grad_norm": 13.810831069946289,
"learning_rate": 1.0864662381854632e-05,
"loss": 53.8405,
"step": 47
},
{
"epoch": 0.4160346695557963,
"grad_norm": 15.549020767211914,
"learning_rate": 1.0384981238178534e-05,
"loss": 46.2514,
"step": 48
},
{
"epoch": 0.4247020585048754,
"grad_norm": 20.43636703491211,
"learning_rate": 1.0096348454262845e-05,
"loss": 29.5193,
"step": 49
},
{
"epoch": 0.4333694474539545,
"grad_norm": 34.72649383544922,
"learning_rate": 1e-05,
"loss": 25.3959,
"step": 50
},
{
"epoch": 0.4333694474539545,
"eval_loss": 1.4524505138397217,
"eval_runtime": 1.7327,
"eval_samples_per_second": 28.856,
"eval_steps_per_second": 7.503,
"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": 2.482250105801933e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}