nttx's picture
Training in progress, step 50, checkpoint
ae823a9 verified
raw
history blame
10 kB
{
"best_metric": 1.872589349746704,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.17316017316017315,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003463203463203463,
"grad_norm": 31.35883331298828,
"learning_rate": 1.6666666666666668e-07,
"loss": 20.8426,
"step": 1
},
{
"epoch": 0.003463203463203463,
"eval_loss": 5.685926914215088,
"eval_runtime": 43.7011,
"eval_samples_per_second": 11.121,
"eval_steps_per_second": 1.396,
"step": 1
},
{
"epoch": 0.006926406926406926,
"grad_norm": 33.130226135253906,
"learning_rate": 3.3333333333333335e-07,
"loss": 22.0101,
"step": 2
},
{
"epoch": 0.01038961038961039,
"grad_norm": 39.378414154052734,
"learning_rate": 5.000000000000001e-07,
"loss": 22.2764,
"step": 3
},
{
"epoch": 0.013852813852813853,
"grad_norm": 34.96480941772461,
"learning_rate": 6.666666666666667e-07,
"loss": 22.9555,
"step": 4
},
{
"epoch": 0.017316017316017316,
"grad_norm": 48.61725997924805,
"learning_rate": 8.333333333333333e-07,
"loss": 23.0175,
"step": 5
},
{
"epoch": 0.02077922077922078,
"grad_norm": 34.086490631103516,
"learning_rate": 1.0000000000000002e-06,
"loss": 21.0193,
"step": 6
},
{
"epoch": 0.024242424242424242,
"grad_norm": 38.7364501953125,
"learning_rate": 1.1666666666666668e-06,
"loss": 22.5784,
"step": 7
},
{
"epoch": 0.027705627705627706,
"grad_norm": 39.01831817626953,
"learning_rate": 1.3333333333333334e-06,
"loss": 20.7766,
"step": 8
},
{
"epoch": 0.03116883116883117,
"grad_norm": 34.76799011230469,
"learning_rate": 1.5e-06,
"loss": 21.0997,
"step": 9
},
{
"epoch": 0.03463203463203463,
"grad_norm": 38.45253372192383,
"learning_rate": 1.6666666666666667e-06,
"loss": 22.8249,
"step": 10
},
{
"epoch": 0.0380952380952381,
"grad_norm": 36.21504211425781,
"learning_rate": 1.8333333333333333e-06,
"loss": 23.0677,
"step": 11
},
{
"epoch": 0.04155844155844156,
"grad_norm": 37.140689849853516,
"learning_rate": 2.0000000000000003e-06,
"loss": 22.3829,
"step": 12
},
{
"epoch": 0.045021645021645025,
"grad_norm": 36.58159637451172,
"learning_rate": 2.166666666666667e-06,
"loss": 20.8327,
"step": 13
},
{
"epoch": 0.048484848484848485,
"grad_norm": 43.1791877746582,
"learning_rate": 2.3333333333333336e-06,
"loss": 22.4572,
"step": 14
},
{
"epoch": 0.05194805194805195,
"grad_norm": 44.443504333496094,
"learning_rate": 2.5e-06,
"loss": 21.75,
"step": 15
},
{
"epoch": 0.05541125541125541,
"grad_norm": 33.40351867675781,
"learning_rate": 2.666666666666667e-06,
"loss": 22.1455,
"step": 16
},
{
"epoch": 0.05887445887445888,
"grad_norm": 31.733808517456055,
"learning_rate": 2.8333333333333335e-06,
"loss": 21.7431,
"step": 17
},
{
"epoch": 0.06233766233766234,
"grad_norm": 41.90239334106445,
"learning_rate": 3e-06,
"loss": 21.5187,
"step": 18
},
{
"epoch": 0.0658008658008658,
"grad_norm": 34.9976921081543,
"learning_rate": 3.1666666666666667e-06,
"loss": 20.3569,
"step": 19
},
{
"epoch": 0.06926406926406926,
"grad_norm": 40.77792739868164,
"learning_rate": 3.3333333333333333e-06,
"loss": 21.8229,
"step": 20
},
{
"epoch": 0.07272727272727272,
"grad_norm": 34.52332305908203,
"learning_rate": 3.5e-06,
"loss": 19.9848,
"step": 21
},
{
"epoch": 0.0761904761904762,
"grad_norm": 38.9856071472168,
"learning_rate": 3.6666666666666666e-06,
"loss": 21.5279,
"step": 22
},
{
"epoch": 0.07965367965367966,
"grad_norm": 31.066797256469727,
"learning_rate": 3.833333333333334e-06,
"loss": 19.8577,
"step": 23
},
{
"epoch": 0.08311688311688312,
"grad_norm": 39.29490280151367,
"learning_rate": 4.000000000000001e-06,
"loss": 21.8956,
"step": 24
},
{
"epoch": 0.08658008658008658,
"grad_norm": 34.29649353027344,
"learning_rate": 4.166666666666667e-06,
"loss": 19.3129,
"step": 25
},
{
"epoch": 0.09004329004329005,
"grad_norm": 40.38904571533203,
"learning_rate": 4.333333333333334e-06,
"loss": 19.886,
"step": 26
},
{
"epoch": 0.09350649350649351,
"grad_norm": 31.812652587890625,
"learning_rate": 4.5e-06,
"loss": 19.737,
"step": 27
},
{
"epoch": 0.09696969696969697,
"grad_norm": 29.289228439331055,
"learning_rate": 4.666666666666667e-06,
"loss": 19.719,
"step": 28
},
{
"epoch": 0.10043290043290043,
"grad_norm": 24.274932861328125,
"learning_rate": 4.833333333333333e-06,
"loss": 18.8488,
"step": 29
},
{
"epoch": 0.1038961038961039,
"grad_norm": 22.817913055419922,
"learning_rate": 5e-06,
"loss": 18.5549,
"step": 30
},
{
"epoch": 0.10735930735930736,
"grad_norm": 31.569385528564453,
"learning_rate": 4.997482666353287e-06,
"loss": 18.9354,
"step": 31
},
{
"epoch": 0.11082251082251082,
"grad_norm": 29.37864875793457,
"learning_rate": 4.989935734988098e-06,
"loss": 18.5526,
"step": 32
},
{
"epoch": 0.11428571428571428,
"grad_norm": 27.965068817138672,
"learning_rate": 4.977374404419838e-06,
"loss": 18.0301,
"step": 33
},
{
"epoch": 0.11774891774891776,
"grad_norm": 32.30046081542969,
"learning_rate": 4.959823971496575e-06,
"loss": 17.3138,
"step": 34
},
{
"epoch": 0.12121212121212122,
"grad_norm": 40.9820671081543,
"learning_rate": 4.937319780454559e-06,
"loss": 17.3738,
"step": 35
},
{
"epoch": 0.12467532467532468,
"grad_norm": 30.207578659057617,
"learning_rate": 4.909907151739634e-06,
"loss": 16.0394,
"step": 36
},
{
"epoch": 0.12813852813852813,
"grad_norm": 31.173616409301758,
"learning_rate": 4.8776412907378845e-06,
"loss": 15.4044,
"step": 37
},
{
"epoch": 0.1316017316017316,
"grad_norm": 31.443645477294922,
"learning_rate": 4.8405871765993435e-06,
"loss": 16.2677,
"step": 38
},
{
"epoch": 0.13506493506493505,
"grad_norm": 31.47043228149414,
"learning_rate": 4.7988194313786275e-06,
"loss": 14.5855,
"step": 39
},
{
"epoch": 0.13852813852813853,
"grad_norm": 35.3460807800293,
"learning_rate": 4.752422169756048e-06,
"loss": 14.1389,
"step": 40
},
{
"epoch": 0.141991341991342,
"grad_norm": 37.52539825439453,
"learning_rate": 4.701488829641845e-06,
"loss": 13.6456,
"step": 41
},
{
"epoch": 0.14545454545454545,
"grad_norm": 35.187889099121094,
"learning_rate": 4.646121984004666e-06,
"loss": 12.3752,
"step": 42
},
{
"epoch": 0.14891774891774892,
"grad_norm": 42.479244232177734,
"learning_rate": 4.586433134303257e-06,
"loss": 11.4697,
"step": 43
},
{
"epoch": 0.1523809523809524,
"grad_norm": 35.67093276977539,
"learning_rate": 4.522542485937369e-06,
"loss": 10.3407,
"step": 44
},
{
"epoch": 0.15584415584415584,
"grad_norm": 39.49524688720703,
"learning_rate": 4.454578706170075e-06,
"loss": 10.1719,
"step": 45
},
{
"epoch": 0.15930735930735931,
"grad_norm": 31.268983840942383,
"learning_rate": 4.382678665009028e-06,
"loss": 9.6938,
"step": 46
},
{
"epoch": 0.16277056277056276,
"grad_norm": 33.51130676269531,
"learning_rate": 4.3069871595684795e-06,
"loss": 9.3956,
"step": 47
},
{
"epoch": 0.16623376623376623,
"grad_norm": 25.20319938659668,
"learning_rate": 4.227656622467162e-06,
"loss": 8.5967,
"step": 48
},
{
"epoch": 0.1696969696969697,
"grad_norm": 31.2619571685791,
"learning_rate": 4.144846814849282e-06,
"loss": 8.2624,
"step": 49
},
{
"epoch": 0.17316017316017315,
"grad_norm": 27.691686630249023,
"learning_rate": 4.058724504646834e-06,
"loss": 8.4329,
"step": 50
},
{
"epoch": 0.17316017316017315,
"eval_loss": 1.872589349746704,
"eval_runtime": 44.32,
"eval_samples_per_second": 10.966,
"eval_steps_per_second": 1.376,
"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": 6.65254329581568e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}