nttx's picture
Training in progress, step 50, checkpoint
801d847 verified
raw
history blame
9.99 kB
{
"best_metric": 1.661128044128418,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.19083969465648856,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003816793893129771,
"grad_norm": 1.1639742851257324,
"learning_rate": 1.6666666666666668e-07,
"loss": 1.7599,
"step": 1
},
{
"epoch": 0.003816793893129771,
"eval_loss": 1.690576195716858,
"eval_runtime": 10.0391,
"eval_samples_per_second": 10.957,
"eval_steps_per_second": 1.395,
"step": 1
},
{
"epoch": 0.007633587786259542,
"grad_norm": 0.9837440848350525,
"learning_rate": 3.3333333333333335e-07,
"loss": 1.7152,
"step": 2
},
{
"epoch": 0.011450381679389313,
"grad_norm": 1.191903829574585,
"learning_rate": 5.000000000000001e-07,
"loss": 1.8818,
"step": 3
},
{
"epoch": 0.015267175572519083,
"grad_norm": 1.2343465089797974,
"learning_rate": 6.666666666666667e-07,
"loss": 1.9395,
"step": 4
},
{
"epoch": 0.019083969465648856,
"grad_norm": 1.1668846607208252,
"learning_rate": 8.333333333333333e-07,
"loss": 1.9077,
"step": 5
},
{
"epoch": 0.022900763358778626,
"grad_norm": 1.2681121826171875,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.25,
"step": 6
},
{
"epoch": 0.026717557251908396,
"grad_norm": 1.410936951637268,
"learning_rate": 1.1666666666666668e-06,
"loss": 2.1375,
"step": 7
},
{
"epoch": 0.030534351145038167,
"grad_norm": 1.2283226251602173,
"learning_rate": 1.3333333333333334e-06,
"loss": 2.0093,
"step": 8
},
{
"epoch": 0.03435114503816794,
"grad_norm": 1.3780529499053955,
"learning_rate": 1.5e-06,
"loss": 2.2188,
"step": 9
},
{
"epoch": 0.03816793893129771,
"grad_norm": 1.2002503871917725,
"learning_rate": 1.6666666666666667e-06,
"loss": 2.01,
"step": 10
},
{
"epoch": 0.04198473282442748,
"grad_norm": 1.1847559213638306,
"learning_rate": 1.8333333333333333e-06,
"loss": 1.9388,
"step": 11
},
{
"epoch": 0.04580152671755725,
"grad_norm": 1.1541310548782349,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9568,
"step": 12
},
{
"epoch": 0.04961832061068702,
"grad_norm": 1.1507000923156738,
"learning_rate": 2.166666666666667e-06,
"loss": 1.9077,
"step": 13
},
{
"epoch": 0.05343511450381679,
"grad_norm": 1.1916567087173462,
"learning_rate": 2.3333333333333336e-06,
"loss": 1.9743,
"step": 14
},
{
"epoch": 0.05725190839694656,
"grad_norm": 1.2536592483520508,
"learning_rate": 2.5e-06,
"loss": 2.0885,
"step": 15
},
{
"epoch": 0.061068702290076333,
"grad_norm": 1.296707034111023,
"learning_rate": 2.666666666666667e-06,
"loss": 2.3976,
"step": 16
},
{
"epoch": 0.0648854961832061,
"grad_norm": 1.2552423477172852,
"learning_rate": 2.8333333333333335e-06,
"loss": 1.9453,
"step": 17
},
{
"epoch": 0.06870229007633588,
"grad_norm": 1.0085850954055786,
"learning_rate": 3e-06,
"loss": 1.1812,
"step": 18
},
{
"epoch": 0.07251908396946564,
"grad_norm": 1.083329200744629,
"learning_rate": 3.1666666666666667e-06,
"loss": 1.5001,
"step": 19
},
{
"epoch": 0.07633587786259542,
"grad_norm": 1.091967225074768,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.5606,
"step": 20
},
{
"epoch": 0.08015267175572519,
"grad_norm": 1.0827946662902832,
"learning_rate": 3.5e-06,
"loss": 1.5546,
"step": 21
},
{
"epoch": 0.08396946564885496,
"grad_norm": 1.137137532234192,
"learning_rate": 3.6666666666666666e-06,
"loss": 1.6243,
"step": 22
},
{
"epoch": 0.08778625954198473,
"grad_norm": 1.0543386936187744,
"learning_rate": 3.833333333333334e-06,
"loss": 1.4913,
"step": 23
},
{
"epoch": 0.0916030534351145,
"grad_norm": 1.092016577720642,
"learning_rate": 4.000000000000001e-06,
"loss": 1.4779,
"step": 24
},
{
"epoch": 0.09541984732824428,
"grad_norm": 1.1408716440200806,
"learning_rate": 4.166666666666667e-06,
"loss": 1.7049,
"step": 25
},
{
"epoch": 0.09923664122137404,
"grad_norm": 1.2250564098358154,
"learning_rate": 4.333333333333334e-06,
"loss": 1.6621,
"step": 26
},
{
"epoch": 0.10305343511450382,
"grad_norm": 1.0289937257766724,
"learning_rate": 4.5e-06,
"loss": 1.5643,
"step": 27
},
{
"epoch": 0.10687022900763359,
"grad_norm": 1.1041069030761719,
"learning_rate": 4.666666666666667e-06,
"loss": 1.4019,
"step": 28
},
{
"epoch": 0.11068702290076336,
"grad_norm": 1.0776981115341187,
"learning_rate": 4.833333333333333e-06,
"loss": 1.3278,
"step": 29
},
{
"epoch": 0.11450381679389313,
"grad_norm": 1.094165325164795,
"learning_rate": 5e-06,
"loss": 1.3775,
"step": 30
},
{
"epoch": 0.1183206106870229,
"grad_norm": 1.0802825689315796,
"learning_rate": 4.997482666353287e-06,
"loss": 1.3885,
"step": 31
},
{
"epoch": 0.12213740458015267,
"grad_norm": 1.177674651145935,
"learning_rate": 4.989935734988098e-06,
"loss": 1.4748,
"step": 32
},
{
"epoch": 0.12595419847328243,
"grad_norm": 1.188259482383728,
"learning_rate": 4.977374404419838e-06,
"loss": 1.5043,
"step": 33
},
{
"epoch": 0.1297709923664122,
"grad_norm": 1.1320470571517944,
"learning_rate": 4.959823971496575e-06,
"loss": 1.5926,
"step": 34
},
{
"epoch": 0.13358778625954199,
"grad_norm": 1.0940425395965576,
"learning_rate": 4.937319780454559e-06,
"loss": 1.3909,
"step": 35
},
{
"epoch": 0.13740458015267176,
"grad_norm": 1.0931893587112427,
"learning_rate": 4.909907151739634e-06,
"loss": 1.5625,
"step": 36
},
{
"epoch": 0.14122137404580154,
"grad_norm": 1.0794775485992432,
"learning_rate": 4.8776412907378845e-06,
"loss": 1.4332,
"step": 37
},
{
"epoch": 0.1450381679389313,
"grad_norm": 1.135691523551941,
"learning_rate": 4.8405871765993435e-06,
"loss": 1.4607,
"step": 38
},
{
"epoch": 0.14885496183206107,
"grad_norm": 1.143457055091858,
"learning_rate": 4.7988194313786275e-06,
"loss": 1.5162,
"step": 39
},
{
"epoch": 0.15267175572519084,
"grad_norm": 1.1650444269180298,
"learning_rate": 4.752422169756048e-06,
"loss": 1.5281,
"step": 40
},
{
"epoch": 0.15648854961832062,
"grad_norm": 1.0388603210449219,
"learning_rate": 4.701488829641845e-06,
"loss": 1.2957,
"step": 41
},
{
"epoch": 0.16030534351145037,
"grad_norm": 1.0882115364074707,
"learning_rate": 4.646121984004666e-06,
"loss": 1.4225,
"step": 42
},
{
"epoch": 0.16412213740458015,
"grad_norm": 1.115893840789795,
"learning_rate": 4.586433134303257e-06,
"loss": 1.3005,
"step": 43
},
{
"epoch": 0.16793893129770993,
"grad_norm": 1.2251698970794678,
"learning_rate": 4.522542485937369e-06,
"loss": 1.3565,
"step": 44
},
{
"epoch": 0.1717557251908397,
"grad_norm": 1.0498777627944946,
"learning_rate": 4.454578706170075e-06,
"loss": 1.1824,
"step": 45
},
{
"epoch": 0.17557251908396945,
"grad_norm": 1.0242071151733398,
"learning_rate": 4.382678665009028e-06,
"loss": 1.2668,
"step": 46
},
{
"epoch": 0.17938931297709923,
"grad_norm": 1.2367092370986938,
"learning_rate": 4.3069871595684795e-06,
"loss": 1.2987,
"step": 47
},
{
"epoch": 0.183206106870229,
"grad_norm": 1.0739256143569946,
"learning_rate": 4.227656622467162e-06,
"loss": 1.3642,
"step": 48
},
{
"epoch": 0.18702290076335878,
"grad_norm": 1.1677788496017456,
"learning_rate": 4.144846814849282e-06,
"loss": 1.4148,
"step": 49
},
{
"epoch": 0.19083969465648856,
"grad_norm": 0.8875530958175659,
"learning_rate": 4.058724504646834e-06,
"loss": 1.2016,
"step": 50
},
{
"epoch": 0.19083969465648856,
"eval_loss": 1.661128044128418,
"eval_runtime": 9.665,
"eval_samples_per_second": 11.381,
"eval_steps_per_second": 1.449,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": false
},
"attributes": {}
}
},
"total_flos": 7101382096060416.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}