dada22231's picture
Training in progress, step 50, checkpoint
ada22c4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4022121669180493,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008044243338360985,
"grad_norm": 605.9085693359375,
"learning_rate": 5e-05,
"loss": 119.0301,
"step": 1
},
{
"epoch": 0.008044243338360985,
"eval_loss": 3.8809421062469482,
"eval_runtime": 4.7235,
"eval_samples_per_second": 10.585,
"eval_steps_per_second": 2.752,
"step": 1
},
{
"epoch": 0.01608848667672197,
"grad_norm": 728.4609375,
"learning_rate": 0.0001,
"loss": 118.4882,
"step": 2
},
{
"epoch": 0.024132730015082957,
"grad_norm": 343.075439453125,
"learning_rate": 9.990365154573717e-05,
"loss": 84.1627,
"step": 3
},
{
"epoch": 0.03217697335344394,
"grad_norm": 267.0028991699219,
"learning_rate": 9.961501876182148e-05,
"loss": 60.8765,
"step": 4
},
{
"epoch": 0.04022121669180493,
"grad_norm": 227.43841552734375,
"learning_rate": 9.913533761814537e-05,
"loss": 54.7165,
"step": 5
},
{
"epoch": 0.048265460030165915,
"grad_norm": 141.04962158203125,
"learning_rate": 9.846666218300807e-05,
"loss": 53.5168,
"step": 6
},
{
"epoch": 0.0563097033685269,
"grad_norm": 136.1522979736328,
"learning_rate": 9.761185582727977e-05,
"loss": 46.229,
"step": 7
},
{
"epoch": 0.06435394670688788,
"grad_norm": 103.41104888916016,
"learning_rate": 9.657457896300791e-05,
"loss": 44.856,
"step": 8
},
{
"epoch": 0.07239819004524888,
"grad_norm": 122.4833984375,
"learning_rate": 9.535927336897098e-05,
"loss": 41.9286,
"step": 9
},
{
"epoch": 0.08044243338360986,
"grad_norm": 129.08062744140625,
"learning_rate": 9.397114317029975e-05,
"loss": 40.5141,
"step": 10
},
{
"epoch": 0.08848667672197084,
"grad_norm": 131.1678924560547,
"learning_rate": 9.241613255361455e-05,
"loss": 38.5526,
"step": 11
},
{
"epoch": 0.09653092006033183,
"grad_norm": 99.09686279296875,
"learning_rate": 9.070090031310558e-05,
"loss": 41.0654,
"step": 12
},
{
"epoch": 0.10457516339869281,
"grad_norm": 126.01998901367188,
"learning_rate": 8.883279133655399e-05,
"loss": 41.6152,
"step": 13
},
{
"epoch": 0.1126194067370538,
"grad_norm": 141.1000213623047,
"learning_rate": 8.681980515339464e-05,
"loss": 43.2946,
"step": 14
},
{
"epoch": 0.12066365007541478,
"grad_norm": 128.52944946289062,
"learning_rate": 8.467056167950311e-05,
"loss": 43.2944,
"step": 15
},
{
"epoch": 0.12870789341377575,
"grad_norm": 164.30210876464844,
"learning_rate": 8.239426430539243e-05,
"loss": 42.1249,
"step": 16
},
{
"epoch": 0.13675213675213677,
"grad_norm": 121.94607543945312,
"learning_rate": 8.000066048588211e-05,
"loss": 44.5202,
"step": 17
},
{
"epoch": 0.14479638009049775,
"grad_norm": 145.65963745117188,
"learning_rate": 7.75e-05,
"loss": 40.5531,
"step": 18
},
{
"epoch": 0.15284062342885874,
"grad_norm": 126.6897964477539,
"learning_rate": 7.490299105985507e-05,
"loss": 41.6405,
"step": 19
},
{
"epoch": 0.16088486676721972,
"grad_norm": 120.6353530883789,
"learning_rate": 7.222075445642904e-05,
"loss": 39.9783,
"step": 20
},
{
"epoch": 0.1689291101055807,
"grad_norm": 147.1504669189453,
"learning_rate": 6.946477593864228e-05,
"loss": 38.0907,
"step": 21
},
{
"epoch": 0.1769733534439417,
"grad_norm": 144.5216064453125,
"learning_rate": 6.664685702961344e-05,
"loss": 45.91,
"step": 22
},
{
"epoch": 0.18501759678230267,
"grad_norm": 177.2615966796875,
"learning_rate": 6.377906449072578e-05,
"loss": 40.3139,
"step": 23
},
{
"epoch": 0.19306184012066366,
"grad_norm": 115.59685516357422,
"learning_rate": 6.087367864990233e-05,
"loss": 38.696,
"step": 24
},
{
"epoch": 0.20110608345902464,
"grad_norm": 101.69725036621094,
"learning_rate": 5.794314081535644e-05,
"loss": 34.7107,
"step": 25
},
{
"epoch": 0.20110608345902464,
"eval_loss": 1.1880208253860474,
"eval_runtime": 4.7474,
"eval_samples_per_second": 10.532,
"eval_steps_per_second": 2.738,
"step": 25
},
{
"epoch": 0.20915032679738563,
"grad_norm": 115.21060943603516,
"learning_rate": 5.500000000000001e-05,
"loss": 41.097,
"step": 26
},
{
"epoch": 0.2171945701357466,
"grad_norm": 158.0090789794922,
"learning_rate": 5.205685918464356e-05,
"loss": 39.4104,
"step": 27
},
{
"epoch": 0.2252388134741076,
"grad_norm": 111.7906723022461,
"learning_rate": 4.912632135009769e-05,
"loss": 37.6126,
"step": 28
},
{
"epoch": 0.23328305681246858,
"grad_norm": 123.39836883544922,
"learning_rate": 4.6220935509274235e-05,
"loss": 37.3962,
"step": 29
},
{
"epoch": 0.24132730015082957,
"grad_norm": 124.10353088378906,
"learning_rate": 4.3353142970386564e-05,
"loss": 40.8343,
"step": 30
},
{
"epoch": 0.24937154348919055,
"grad_norm": 106.123291015625,
"learning_rate": 4.053522406135775e-05,
"loss": 39.4761,
"step": 31
},
{
"epoch": 0.2574157868275515,
"grad_norm": 96.61071014404297,
"learning_rate": 3.777924554357096e-05,
"loss": 37.6884,
"step": 32
},
{
"epoch": 0.2654600301659125,
"grad_norm": 123.42510986328125,
"learning_rate": 3.509700894014496e-05,
"loss": 36.3759,
"step": 33
},
{
"epoch": 0.27350427350427353,
"grad_norm": 88.63697814941406,
"learning_rate": 3.250000000000001e-05,
"loss": 36.8431,
"step": 34
},
{
"epoch": 0.2815485168426345,
"grad_norm": 169.19483947753906,
"learning_rate": 2.9999339514117912e-05,
"loss": 36.3033,
"step": 35
},
{
"epoch": 0.2895927601809955,
"grad_norm": 86.78917694091797,
"learning_rate": 2.760573569460757e-05,
"loss": 38.7072,
"step": 36
},
{
"epoch": 0.29763700351935646,
"grad_norm": 83.58650207519531,
"learning_rate": 2.53294383204969e-05,
"loss": 37.9871,
"step": 37
},
{
"epoch": 0.30568124685771747,
"grad_norm": 88.43095397949219,
"learning_rate": 2.3180194846605367e-05,
"loss": 35.836,
"step": 38
},
{
"epoch": 0.3137254901960784,
"grad_norm": 229.8590850830078,
"learning_rate": 2.1167208663446025e-05,
"loss": 39.1167,
"step": 39
},
{
"epoch": 0.32176973353443944,
"grad_norm": 111.63166046142578,
"learning_rate": 1.9299099686894423e-05,
"loss": 36.3088,
"step": 40
},
{
"epoch": 0.3298139768728004,
"grad_norm": 229.4169158935547,
"learning_rate": 1.758386744638546e-05,
"loss": 35.0117,
"step": 41
},
{
"epoch": 0.3378582202111614,
"grad_norm": 140.18325805664062,
"learning_rate": 1.602885682970026e-05,
"loss": 38.5012,
"step": 42
},
{
"epoch": 0.34590246354952237,
"grad_norm": 83.29537200927734,
"learning_rate": 1.464072663102903e-05,
"loss": 36.7094,
"step": 43
},
{
"epoch": 0.3539467068878834,
"grad_norm": 79.36915588378906,
"learning_rate": 1.3425421036992098e-05,
"loss": 37.5578,
"step": 44
},
{
"epoch": 0.36199095022624433,
"grad_norm": 145.71937561035156,
"learning_rate": 1.2388144172720251e-05,
"loss": 37.3472,
"step": 45
},
{
"epoch": 0.37003519356460535,
"grad_norm": 83.54203796386719,
"learning_rate": 1.1533337816991932e-05,
"loss": 38.3822,
"step": 46
},
{
"epoch": 0.3780794369029663,
"grad_norm": 81.59954071044922,
"learning_rate": 1.0864662381854632e-05,
"loss": 36.0854,
"step": 47
},
{
"epoch": 0.3861236802413273,
"grad_norm": 90.07756042480469,
"learning_rate": 1.0384981238178534e-05,
"loss": 36.0527,
"step": 48
},
{
"epoch": 0.3941679235796883,
"grad_norm": 94.21563720703125,
"learning_rate": 1.0096348454262845e-05,
"loss": 36.8875,
"step": 49
},
{
"epoch": 0.4022121669180493,
"grad_norm": 99.66661834716797,
"learning_rate": 1e-05,
"loss": 35.0076,
"step": 50
},
{
"epoch": 0.4022121669180493,
"eval_loss": 1.1387280225753784,
"eval_runtime": 4.7523,
"eval_samples_per_second": 10.521,
"eval_steps_per_second": 2.736,
"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
}