bbytxt's picture
Training in progress, step 50, checkpoint
8918f57 verified
raw
history blame
9.87 kB
{
"best_metric": 1.8364510536193848,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.33783783783783783,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006756756756756757,
"grad_norm": 1.4424006938934326,
"learning_rate": 1e-05,
"loss": 2.2896,
"step": 1
},
{
"epoch": 0.006756756756756757,
"eval_loss": 2.4700465202331543,
"eval_runtime": 18.613,
"eval_samples_per_second": 13.431,
"eval_steps_per_second": 3.385,
"step": 1
},
{
"epoch": 0.013513513513513514,
"grad_norm": 1.7567722797393799,
"learning_rate": 2e-05,
"loss": 2.3382,
"step": 2
},
{
"epoch": 0.02027027027027027,
"grad_norm": 1.7165125608444214,
"learning_rate": 3e-05,
"loss": 2.3747,
"step": 3
},
{
"epoch": 0.02702702702702703,
"grad_norm": 1.7339659929275513,
"learning_rate": 4e-05,
"loss": 2.3317,
"step": 4
},
{
"epoch": 0.033783783783783786,
"grad_norm": 1.658001184463501,
"learning_rate": 5e-05,
"loss": 2.2753,
"step": 5
},
{
"epoch": 0.04054054054054054,
"grad_norm": 1.4608352184295654,
"learning_rate": 6e-05,
"loss": 2.1977,
"step": 6
},
{
"epoch": 0.0472972972972973,
"grad_norm": 1.592839002609253,
"learning_rate": 7e-05,
"loss": 2.0545,
"step": 7
},
{
"epoch": 0.05405405405405406,
"grad_norm": 1.6094963550567627,
"learning_rate": 8e-05,
"loss": 1.9669,
"step": 8
},
{
"epoch": 0.060810810810810814,
"grad_norm": 2.4839794635772705,
"learning_rate": 9e-05,
"loss": 2.1095,
"step": 9
},
{
"epoch": 0.06756756756756757,
"grad_norm": 2.2013440132141113,
"learning_rate": 0.0001,
"loss": 2.0207,
"step": 10
},
{
"epoch": 0.07432432432432433,
"grad_norm": 1.868704915046692,
"learning_rate": 9.999316524962345e-05,
"loss": 2.219,
"step": 11
},
{
"epoch": 0.08108108108108109,
"grad_norm": 1.5163902044296265,
"learning_rate": 9.997266286704631e-05,
"loss": 1.7047,
"step": 12
},
{
"epoch": 0.08783783783783784,
"grad_norm": 1.818183183670044,
"learning_rate": 9.993849845741524e-05,
"loss": 1.7389,
"step": 13
},
{
"epoch": 0.0945945945945946,
"grad_norm": 1.8183751106262207,
"learning_rate": 9.989068136093873e-05,
"loss": 1.8483,
"step": 14
},
{
"epoch": 0.10135135135135136,
"grad_norm": 1.6848615407943726,
"learning_rate": 9.98292246503335e-05,
"loss": 1.9458,
"step": 15
},
{
"epoch": 0.10810810810810811,
"grad_norm": 1.4533350467681885,
"learning_rate": 9.975414512725057e-05,
"loss": 1.8722,
"step": 16
},
{
"epoch": 0.11486486486486487,
"grad_norm": 1.4766217470169067,
"learning_rate": 9.966546331768191e-05,
"loss": 1.6756,
"step": 17
},
{
"epoch": 0.12162162162162163,
"grad_norm": 1.6617404222488403,
"learning_rate": 9.956320346634876e-05,
"loss": 1.8676,
"step": 18
},
{
"epoch": 0.12837837837837837,
"grad_norm": 1.667425274848938,
"learning_rate": 9.944739353007344e-05,
"loss": 1.8379,
"step": 19
},
{
"epoch": 0.13513513513513514,
"grad_norm": 1.5992474555969238,
"learning_rate": 9.931806517013612e-05,
"loss": 1.7354,
"step": 20
},
{
"epoch": 0.14189189189189189,
"grad_norm": 1.6577551364898682,
"learning_rate": 9.917525374361912e-05,
"loss": 1.8265,
"step": 21
},
{
"epoch": 0.14864864864864866,
"grad_norm": 1.6034307479858398,
"learning_rate": 9.901899829374047e-05,
"loss": 1.783,
"step": 22
},
{
"epoch": 0.1554054054054054,
"grad_norm": 2.068225145339966,
"learning_rate": 9.884934153917997e-05,
"loss": 1.9163,
"step": 23
},
{
"epoch": 0.16216216216216217,
"grad_norm": 1.7155823707580566,
"learning_rate": 9.86663298624003e-05,
"loss": 1.8537,
"step": 24
},
{
"epoch": 0.16891891891891891,
"grad_norm": 1.703191876411438,
"learning_rate": 9.847001329696653e-05,
"loss": 1.839,
"step": 25
},
{
"epoch": 0.17567567567567569,
"grad_norm": 2.158104658126831,
"learning_rate": 9.826044551386744e-05,
"loss": 1.9672,
"step": 26
},
{
"epoch": 0.18243243243243243,
"grad_norm": 1.834190011024475,
"learning_rate": 9.803768380684242e-05,
"loss": 1.8346,
"step": 27
},
{
"epoch": 0.1891891891891892,
"grad_norm": 1.9021737575531006,
"learning_rate": 9.780178907671789e-05,
"loss": 1.7981,
"step": 28
},
{
"epoch": 0.19594594594594594,
"grad_norm": 1.9429136514663696,
"learning_rate": 9.755282581475769e-05,
"loss": 1.8159,
"step": 29
},
{
"epoch": 0.20270270270270271,
"grad_norm": 2.137256383895874,
"learning_rate": 9.729086208503174e-05,
"loss": 1.7183,
"step": 30
},
{
"epoch": 0.20945945945945946,
"grad_norm": 2.3155884742736816,
"learning_rate": 9.701596950580806e-05,
"loss": 1.8515,
"step": 31
},
{
"epoch": 0.21621621621621623,
"grad_norm": 2.3982532024383545,
"learning_rate": 9.672822322997305e-05,
"loss": 1.7351,
"step": 32
},
{
"epoch": 0.22297297297297297,
"grad_norm": 2.658118724822998,
"learning_rate": 9.642770192448536e-05,
"loss": 1.8166,
"step": 33
},
{
"epoch": 0.22972972972972974,
"grad_norm": 2.4856467247009277,
"learning_rate": 9.611448774886924e-05,
"loss": 1.9582,
"step": 34
},
{
"epoch": 0.23648648648648649,
"grad_norm": 3.3881924152374268,
"learning_rate": 9.578866633275288e-05,
"loss": 1.8473,
"step": 35
},
{
"epoch": 0.24324324324324326,
"grad_norm": 2.7870328426361084,
"learning_rate": 9.545032675245813e-05,
"loss": 1.7502,
"step": 36
},
{
"epoch": 0.25,
"grad_norm": 4.050192356109619,
"learning_rate": 9.509956150664796e-05,
"loss": 2.1093,
"step": 37
},
{
"epoch": 0.25675675675675674,
"grad_norm": 2.349740982055664,
"learning_rate": 9.473646649103818e-05,
"loss": 2.2211,
"step": 38
},
{
"epoch": 0.2635135135135135,
"grad_norm": 1.6817964315414429,
"learning_rate": 9.43611409721806e-05,
"loss": 2.1682,
"step": 39
},
{
"epoch": 0.2702702702702703,
"grad_norm": 1.4059157371520996,
"learning_rate": 9.397368756032445e-05,
"loss": 1.9945,
"step": 40
},
{
"epoch": 0.27702702702702703,
"grad_norm": 1.2649842500686646,
"learning_rate": 9.357421218136386e-05,
"loss": 1.927,
"step": 41
},
{
"epoch": 0.28378378378378377,
"grad_norm": 1.327721357345581,
"learning_rate": 9.316282404787871e-05,
"loss": 1.9329,
"step": 42
},
{
"epoch": 0.2905405405405405,
"grad_norm": 1.3768377304077148,
"learning_rate": 9.273963562927695e-05,
"loss": 2.0718,
"step": 43
},
{
"epoch": 0.2972972972972973,
"grad_norm": 1.3469047546386719,
"learning_rate": 9.230476262104677e-05,
"loss": 1.8375,
"step": 44
},
{
"epoch": 0.30405405405405406,
"grad_norm": 1.2437846660614014,
"learning_rate": 9.185832391312644e-05,
"loss": 1.6175,
"step": 45
},
{
"epoch": 0.3108108108108108,
"grad_norm": 1.410740613937378,
"learning_rate": 9.140044155740101e-05,
"loss": 1.909,
"step": 46
},
{
"epoch": 0.31756756756756754,
"grad_norm": 1.4747393131256104,
"learning_rate": 9.093124073433463e-05,
"loss": 1.7801,
"step": 47
},
{
"epoch": 0.32432432432432434,
"grad_norm": 1.3618700504302979,
"learning_rate": 9.045084971874738e-05,
"loss": 1.8941,
"step": 48
},
{
"epoch": 0.3310810810810811,
"grad_norm": 1.3720588684082031,
"learning_rate": 8.995939984474624e-05,
"loss": 1.7513,
"step": 49
},
{
"epoch": 0.33783783783783783,
"grad_norm": 1.4571261405944824,
"learning_rate": 8.945702546981969e-05,
"loss": 1.77,
"step": 50
},
{
"epoch": 0.33783783783783783,
"eval_loss": 1.8364510536193848,
"eval_runtime": 19.046,
"eval_samples_per_second": 13.126,
"eval_steps_per_second": 3.308,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 7.54256789372928e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}