dada22231's picture
Training in progress, step 50, checkpoint
148c5ce verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.12463000467362517,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0024926000934725034,
"grad_norm": 34.01936721801758,
"learning_rate": 5e-05,
"loss": 51.3449,
"step": 1
},
{
"epoch": 0.0024926000934725034,
"eval_loss": 2.1383278369903564,
"eval_runtime": 3.5335,
"eval_samples_per_second": 14.15,
"eval_steps_per_second": 3.679,
"step": 1
},
{
"epoch": 0.004985200186945007,
"grad_norm": 34.66087341308594,
"learning_rate": 0.0001,
"loss": 53.1527,
"step": 2
},
{
"epoch": 0.00747780028041751,
"grad_norm": 30.127349853515625,
"learning_rate": 9.990365154573717e-05,
"loss": 52.1352,
"step": 3
},
{
"epoch": 0.009970400373890013,
"grad_norm": 22.915531158447266,
"learning_rate": 9.961501876182148e-05,
"loss": 49.9646,
"step": 4
},
{
"epoch": 0.012463000467362517,
"grad_norm": 52.97492980957031,
"learning_rate": 9.913533761814537e-05,
"loss": 52.959,
"step": 5
},
{
"epoch": 0.01495560056083502,
"grad_norm": 49.64532470703125,
"learning_rate": 9.846666218300807e-05,
"loss": 53.6426,
"step": 6
},
{
"epoch": 0.017448200654307525,
"grad_norm": 25.895368576049805,
"learning_rate": 9.761185582727977e-05,
"loss": 52.3593,
"step": 7
},
{
"epoch": 0.019940800747780027,
"grad_norm": 20.97550392150879,
"learning_rate": 9.657457896300791e-05,
"loss": 51.3943,
"step": 8
},
{
"epoch": 0.022433400841252532,
"grad_norm": 14.574114799499512,
"learning_rate": 9.535927336897098e-05,
"loss": 53.4097,
"step": 9
},
{
"epoch": 0.024926000934725034,
"grad_norm": 21.26239776611328,
"learning_rate": 9.397114317029975e-05,
"loss": 54.8947,
"step": 10
},
{
"epoch": 0.02741860102819754,
"grad_norm": 24.055912017822266,
"learning_rate": 9.241613255361455e-05,
"loss": 54.7964,
"step": 11
},
{
"epoch": 0.02991120112167004,
"grad_norm": 30.55950164794922,
"learning_rate": 9.070090031310558e-05,
"loss": 57.7224,
"step": 12
},
{
"epoch": 0.032403801215142546,
"grad_norm": 26.02332878112793,
"learning_rate": 8.883279133655399e-05,
"loss": 56.8336,
"step": 13
},
{
"epoch": 0.03489640130861505,
"grad_norm": 23.84014892578125,
"learning_rate": 8.681980515339464e-05,
"loss": 45.4639,
"step": 14
},
{
"epoch": 0.037389001402087556,
"grad_norm": 20.399507522583008,
"learning_rate": 8.467056167950311e-05,
"loss": 45.2857,
"step": 15
},
{
"epoch": 0.039881601495560054,
"grad_norm": 13.766602516174316,
"learning_rate": 8.239426430539243e-05,
"loss": 45.9527,
"step": 16
},
{
"epoch": 0.04237420158903256,
"grad_norm": 10.404088020324707,
"learning_rate": 8.000066048588211e-05,
"loss": 47.2076,
"step": 17
},
{
"epoch": 0.044866801682505064,
"grad_norm": 9.640239715576172,
"learning_rate": 7.75e-05,
"loss": 46.6353,
"step": 18
},
{
"epoch": 0.04735940177597757,
"grad_norm": 10.350581169128418,
"learning_rate": 7.490299105985507e-05,
"loss": 47.2987,
"step": 19
},
{
"epoch": 0.04985200186945007,
"grad_norm": 11.253185272216797,
"learning_rate": 7.222075445642904e-05,
"loss": 48.2336,
"step": 20
},
{
"epoch": 0.05234460196292257,
"grad_norm": 11.232816696166992,
"learning_rate": 6.946477593864228e-05,
"loss": 47.7288,
"step": 21
},
{
"epoch": 0.05483720205639508,
"grad_norm": 12.71604061126709,
"learning_rate": 6.664685702961344e-05,
"loss": 50.7921,
"step": 22
},
{
"epoch": 0.05732980214986758,
"grad_norm": 15.633907318115234,
"learning_rate": 6.377906449072578e-05,
"loss": 50.814,
"step": 23
},
{
"epoch": 0.05982240224334008,
"grad_norm": 22.674806594848633,
"learning_rate": 6.087367864990233e-05,
"loss": 56.9851,
"step": 24
},
{
"epoch": 0.062315002336812586,
"grad_norm": 44.97622299194336,
"learning_rate": 5.794314081535644e-05,
"loss": 60.9695,
"step": 25
},
{
"epoch": 0.062315002336812586,
"eval_loss": 1.6849799156188965,
"eval_runtime": 3.5862,
"eval_samples_per_second": 13.942,
"eval_steps_per_second": 3.625,
"step": 25
},
{
"epoch": 0.06480760243028509,
"grad_norm": 12.182744979858398,
"learning_rate": 5.500000000000001e-05,
"loss": 39.6703,
"step": 26
},
{
"epoch": 0.0673002025237576,
"grad_norm": 9.66840934753418,
"learning_rate": 5.205685918464356e-05,
"loss": 41.0538,
"step": 27
},
{
"epoch": 0.0697928026172301,
"grad_norm": 7.723933219909668,
"learning_rate": 4.912632135009769e-05,
"loss": 40.8829,
"step": 28
},
{
"epoch": 0.0722854027107026,
"grad_norm": 10.423388481140137,
"learning_rate": 4.6220935509274235e-05,
"loss": 41.5667,
"step": 29
},
{
"epoch": 0.07477800280417511,
"grad_norm": 11.415440559387207,
"learning_rate": 4.3353142970386564e-05,
"loss": 42.001,
"step": 30
},
{
"epoch": 0.0772706028976476,
"grad_norm": 9.448587417602539,
"learning_rate": 4.053522406135775e-05,
"loss": 44.3011,
"step": 31
},
{
"epoch": 0.07976320299112011,
"grad_norm": 8.649128913879395,
"learning_rate": 3.777924554357096e-05,
"loss": 42.1353,
"step": 32
},
{
"epoch": 0.08225580308459261,
"grad_norm": 9.245633125305176,
"learning_rate": 3.509700894014496e-05,
"loss": 42.307,
"step": 33
},
{
"epoch": 0.08474840317806512,
"grad_norm": 10.58106517791748,
"learning_rate": 3.250000000000001e-05,
"loss": 44.1531,
"step": 34
},
{
"epoch": 0.08724100327153762,
"grad_norm": 12.213338851928711,
"learning_rate": 2.9999339514117912e-05,
"loss": 44.9653,
"step": 35
},
{
"epoch": 0.08973360336501013,
"grad_norm": 18.405900955200195,
"learning_rate": 2.760573569460757e-05,
"loss": 48.0947,
"step": 36
},
{
"epoch": 0.09222620345848263,
"grad_norm": 22.227853775024414,
"learning_rate": 2.53294383204969e-05,
"loss": 50.5871,
"step": 37
},
{
"epoch": 0.09471880355195514,
"grad_norm": 31.471637725830078,
"learning_rate": 2.3180194846605367e-05,
"loss": 50.5865,
"step": 38
},
{
"epoch": 0.09721140364542763,
"grad_norm": 8.112051010131836,
"learning_rate": 2.1167208663446025e-05,
"loss": 37.6254,
"step": 39
},
{
"epoch": 0.09970400373890013,
"grad_norm": 7.1719441413879395,
"learning_rate": 1.9299099686894423e-05,
"loss": 38.5991,
"step": 40
},
{
"epoch": 0.10219660383237264,
"grad_norm": 6.442931175231934,
"learning_rate": 1.758386744638546e-05,
"loss": 39.739,
"step": 41
},
{
"epoch": 0.10468920392584515,
"grad_norm": 5.925367832183838,
"learning_rate": 1.602885682970026e-05,
"loss": 40.6377,
"step": 42
},
{
"epoch": 0.10718180401931765,
"grad_norm": 6.379517555236816,
"learning_rate": 1.464072663102903e-05,
"loss": 41.3528,
"step": 43
},
{
"epoch": 0.10967440411279016,
"grad_norm": 8.130070686340332,
"learning_rate": 1.3425421036992098e-05,
"loss": 41.3185,
"step": 44
},
{
"epoch": 0.11216700420626266,
"grad_norm": 8.644542694091797,
"learning_rate": 1.2388144172720251e-05,
"loss": 43.0408,
"step": 45
},
{
"epoch": 0.11465960429973517,
"grad_norm": 10.712021827697754,
"learning_rate": 1.1533337816991932e-05,
"loss": 41.6555,
"step": 46
},
{
"epoch": 0.11715220439320767,
"grad_norm": 11.649221420288086,
"learning_rate": 1.0864662381854632e-05,
"loss": 43.8152,
"step": 47
},
{
"epoch": 0.11964480448668016,
"grad_norm": 14.572856903076172,
"learning_rate": 1.0384981238178534e-05,
"loss": 45.252,
"step": 48
},
{
"epoch": 0.12213740458015267,
"grad_norm": 19.085554122924805,
"learning_rate": 1.0096348454262845e-05,
"loss": 47.54,
"step": 49
},
{
"epoch": 0.12463000467362517,
"grad_norm": 31.62267303466797,
"learning_rate": 1e-05,
"loss": 54.4587,
"step": 50
},
{
"epoch": 0.12463000467362517,
"eval_loss": 1.5832980871200562,
"eval_runtime": 3.8011,
"eval_samples_per_second": 13.154,
"eval_steps_per_second": 3.42,
"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": 5.573829327763538e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}