dada22231's picture
Training in progress, step 50, checkpoint
b399f17 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.36883356385431076,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007376671277086215,
"grad_norm": 282.1716613769531,
"learning_rate": 5e-05,
"loss": 83.4419,
"step": 1
},
{
"epoch": 0.007376671277086215,
"eval_loss": 3.490344762802124,
"eval_runtime": 4.6987,
"eval_samples_per_second": 10.641,
"eval_steps_per_second": 2.767,
"step": 1
},
{
"epoch": 0.01475334255417243,
"grad_norm": 388.236083984375,
"learning_rate": 0.0001,
"loss": 96.3368,
"step": 2
},
{
"epoch": 0.022130013831258646,
"grad_norm": 221.40098571777344,
"learning_rate": 9.990365154573717e-05,
"loss": 93.5569,
"step": 3
},
{
"epoch": 0.02950668510834486,
"grad_norm": 142.23619079589844,
"learning_rate": 9.961501876182148e-05,
"loss": 78.4432,
"step": 4
},
{
"epoch": 0.036883356385431075,
"grad_norm": 110.13419342041016,
"learning_rate": 9.913533761814537e-05,
"loss": 72.3183,
"step": 5
},
{
"epoch": 0.04426002766251729,
"grad_norm": 115.39995574951172,
"learning_rate": 9.846666218300807e-05,
"loss": 76.6289,
"step": 6
},
{
"epoch": 0.0516366989396035,
"grad_norm": 113.59160614013672,
"learning_rate": 9.761185582727977e-05,
"loss": 72.5216,
"step": 7
},
{
"epoch": 0.05901337021668972,
"grad_norm": 119.02566528320312,
"learning_rate": 9.657457896300791e-05,
"loss": 72.8846,
"step": 8
},
{
"epoch": 0.06639004149377593,
"grad_norm": 110.38025665283203,
"learning_rate": 9.535927336897098e-05,
"loss": 73.8487,
"step": 9
},
{
"epoch": 0.07376671277086215,
"grad_norm": 89.96533966064453,
"learning_rate": 9.397114317029975e-05,
"loss": 71.8622,
"step": 10
},
{
"epoch": 0.08114338404794837,
"grad_norm": 101.28451538085938,
"learning_rate": 9.241613255361455e-05,
"loss": 67.3909,
"step": 11
},
{
"epoch": 0.08852005532503458,
"grad_norm": 115.35746765136719,
"learning_rate": 9.070090031310558e-05,
"loss": 73.3973,
"step": 12
},
{
"epoch": 0.0958967266021208,
"grad_norm": 104.906494140625,
"learning_rate": 8.883279133655399e-05,
"loss": 69.7098,
"step": 13
},
{
"epoch": 0.103273397879207,
"grad_norm": 119.27690887451172,
"learning_rate": 8.681980515339464e-05,
"loss": 64.5961,
"step": 14
},
{
"epoch": 0.11065006915629322,
"grad_norm": 84.15249633789062,
"learning_rate": 8.467056167950311e-05,
"loss": 62.0781,
"step": 15
},
{
"epoch": 0.11802674043337943,
"grad_norm": 76.08849334716797,
"learning_rate": 8.239426430539243e-05,
"loss": 60.6262,
"step": 16
},
{
"epoch": 0.12540341171046565,
"grad_norm": 66.6586685180664,
"learning_rate": 8.000066048588211e-05,
"loss": 61.2691,
"step": 17
},
{
"epoch": 0.13278008298755187,
"grad_norm": 82.03917694091797,
"learning_rate": 7.75e-05,
"loss": 62.1429,
"step": 18
},
{
"epoch": 0.14015675426463808,
"grad_norm": 88.91397094726562,
"learning_rate": 7.490299105985507e-05,
"loss": 64.2291,
"step": 19
},
{
"epoch": 0.1475334255417243,
"grad_norm": 84.50870513916016,
"learning_rate": 7.222075445642904e-05,
"loss": 63.3765,
"step": 20
},
{
"epoch": 0.15491009681881052,
"grad_norm": 87.00757598876953,
"learning_rate": 6.946477593864228e-05,
"loss": 63.7466,
"step": 21
},
{
"epoch": 0.16228676809589673,
"grad_norm": 95.2031021118164,
"learning_rate": 6.664685702961344e-05,
"loss": 62.1167,
"step": 22
},
{
"epoch": 0.16966343937298295,
"grad_norm": 92.69840240478516,
"learning_rate": 6.377906449072578e-05,
"loss": 60.9714,
"step": 23
},
{
"epoch": 0.17704011065006917,
"grad_norm": 102.94600677490234,
"learning_rate": 6.087367864990233e-05,
"loss": 61.412,
"step": 24
},
{
"epoch": 0.18441678192715538,
"grad_norm": 130.2623748779297,
"learning_rate": 5.794314081535644e-05,
"loss": 62.1074,
"step": 25
},
{
"epoch": 0.18441678192715538,
"eval_loss": 1.8811182975769043,
"eval_runtime": 4.7106,
"eval_samples_per_second": 10.614,
"eval_steps_per_second": 2.76,
"step": 25
},
{
"epoch": 0.1917934532042416,
"grad_norm": 105.9937515258789,
"learning_rate": 5.500000000000001e-05,
"loss": 60.4911,
"step": 26
},
{
"epoch": 0.1991701244813278,
"grad_norm": 97.24896240234375,
"learning_rate": 5.205685918464356e-05,
"loss": 64.2063,
"step": 27
},
{
"epoch": 0.206546795758414,
"grad_norm": 87.00945281982422,
"learning_rate": 4.912632135009769e-05,
"loss": 59.044,
"step": 28
},
{
"epoch": 0.21392346703550022,
"grad_norm": 68.81822204589844,
"learning_rate": 4.6220935509274235e-05,
"loss": 54.7829,
"step": 29
},
{
"epoch": 0.22130013831258644,
"grad_norm": 66.47765350341797,
"learning_rate": 4.3353142970386564e-05,
"loss": 57.293,
"step": 30
},
{
"epoch": 0.22867680958967265,
"grad_norm": 61.59925842285156,
"learning_rate": 4.053522406135775e-05,
"loss": 59.3897,
"step": 31
},
{
"epoch": 0.23605348086675887,
"grad_norm": 63.04508590698242,
"learning_rate": 3.777924554357096e-05,
"loss": 57.4565,
"step": 32
},
{
"epoch": 0.24343015214384509,
"grad_norm": 67.6324462890625,
"learning_rate": 3.509700894014496e-05,
"loss": 62.637,
"step": 33
},
{
"epoch": 0.2508068234209313,
"grad_norm": 70.709228515625,
"learning_rate": 3.250000000000001e-05,
"loss": 55.7258,
"step": 34
},
{
"epoch": 0.25818349469801755,
"grad_norm": 70.97118377685547,
"learning_rate": 2.9999339514117912e-05,
"loss": 58.9086,
"step": 35
},
{
"epoch": 0.26556016597510373,
"grad_norm": 78.88076782226562,
"learning_rate": 2.760573569460757e-05,
"loss": 59.4616,
"step": 36
},
{
"epoch": 0.2729368372521899,
"grad_norm": 83.21874237060547,
"learning_rate": 2.53294383204969e-05,
"loss": 60.5497,
"step": 37
},
{
"epoch": 0.28031350852927617,
"grad_norm": 85.22425842285156,
"learning_rate": 2.3180194846605367e-05,
"loss": 61.8729,
"step": 38
},
{
"epoch": 0.28769017980636236,
"grad_norm": 64.6729736328125,
"learning_rate": 2.1167208663446025e-05,
"loss": 54.9777,
"step": 39
},
{
"epoch": 0.2950668510834486,
"grad_norm": 70.6922836303711,
"learning_rate": 1.9299099686894423e-05,
"loss": 57.0679,
"step": 40
},
{
"epoch": 0.3024435223605348,
"grad_norm": 65.0792465209961,
"learning_rate": 1.758386744638546e-05,
"loss": 51.6961,
"step": 41
},
{
"epoch": 0.30982019363762103,
"grad_norm": 72.32954406738281,
"learning_rate": 1.602885682970026e-05,
"loss": 54.3178,
"step": 42
},
{
"epoch": 0.3171968649147072,
"grad_norm": 56.84644317626953,
"learning_rate": 1.464072663102903e-05,
"loss": 52.3778,
"step": 43
},
{
"epoch": 0.32457353619179347,
"grad_norm": 56.280426025390625,
"learning_rate": 1.3425421036992098e-05,
"loss": 53.9694,
"step": 44
},
{
"epoch": 0.33195020746887965,
"grad_norm": 58.49018859863281,
"learning_rate": 1.2388144172720251e-05,
"loss": 54.7155,
"step": 45
},
{
"epoch": 0.3393268787459659,
"grad_norm": 56.72845458984375,
"learning_rate": 1.1533337816991932e-05,
"loss": 53.9432,
"step": 46
},
{
"epoch": 0.3467035500230521,
"grad_norm": 70.70610809326172,
"learning_rate": 1.0864662381854632e-05,
"loss": 53.7918,
"step": 47
},
{
"epoch": 0.35408022130013833,
"grad_norm": 77.556884765625,
"learning_rate": 1.0384981238178534e-05,
"loss": 54.0723,
"step": 48
},
{
"epoch": 0.3614568925772245,
"grad_norm": 77.79217529296875,
"learning_rate": 1.0096348454262845e-05,
"loss": 59.7133,
"step": 49
},
{
"epoch": 0.36883356385431076,
"grad_norm": 116.21781921386719,
"learning_rate": 1e-05,
"loss": 58.3305,
"step": 50
},
{
"epoch": 0.36883356385431076,
"eval_loss": 1.7189912796020508,
"eval_runtime": 4.7421,
"eval_samples_per_second": 10.544,
"eval_steps_per_second": 2.741,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.658021338284032e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}