aleegis12's picture
Training in progress, step 50, checkpoint
4d420fd verified
raw
history blame
9.93 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.3508771929824561,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007017543859649123,
"grad_norm": 0.00020061875693500042,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.007017543859649123,
"eval_loss": 11.5,
"eval_runtime": 1.1045,
"eval_samples_per_second": 217.291,
"eval_steps_per_second": 54.323,
"step": 1
},
{
"epoch": 0.014035087719298246,
"grad_norm": 7.806254143361002e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.021052631578947368,
"grad_norm": 0.00010668490722309798,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.028070175438596492,
"grad_norm": 0.000133075489429757,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.03508771929824561,
"grad_norm": 4.940497092320584e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.042105263157894736,
"grad_norm": 9.403337026014924e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.04912280701754386,
"grad_norm": 9.405195305589586e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.056140350877192984,
"grad_norm": 0.00017732367268763483,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.06315789473684211,
"grad_norm": 7.712566730333492e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.07017543859649122,
"grad_norm": 0.00010726985783549026,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.07719298245614035,
"grad_norm": 0.00010846000077435747,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.08421052631578947,
"grad_norm": 0.00021638412727043033,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.0912280701754386,
"grad_norm": 0.00023320304171647877,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.09824561403508772,
"grad_norm": 0.0002806849079206586,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.10526315789473684,
"grad_norm": 9.014399984152988e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.11228070175438597,
"grad_norm": 8.092244388535619e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.11929824561403508,
"grad_norm": 0.00010682821448426694,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.12631578947368421,
"grad_norm": 0.00014715925499331206,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.00014980002015363425,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.14035087719298245,
"grad_norm": 0.0001737991551635787,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.14736842105263157,
"grad_norm": 0.00019362883176654577,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.1543859649122807,
"grad_norm": 0.00013303550076670945,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.16140350877192983,
"grad_norm": 0.00018823579011950642,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.16842105263157894,
"grad_norm": 0.0002998728887178004,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.17543859649122806,
"grad_norm": 9.449676872463897e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.1824561403508772,
"grad_norm": 0.00018421528511680663,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.18947368421052632,
"grad_norm": 0.0002451211621519178,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.19649122807017544,
"grad_norm": 0.00021305055997800082,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.20350877192982456,
"grad_norm": 0.0004315518890507519,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.21052631578947367,
"grad_norm": 0.0004159727832302451,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.21754385964912282,
"grad_norm": 0.0002781561342999339,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.22456140350877193,
"grad_norm": 0.00028718082467094064,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.23157894736842105,
"grad_norm": 0.000403701706090942,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.23859649122807017,
"grad_norm": 0.0002168155333492905,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.24561403508771928,
"grad_norm": 0.000404708698624745,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.25263157894736843,
"grad_norm": 0.00020163772569503635,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.2596491228070175,
"grad_norm": 0.00015444487507920712,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.0002228071098215878,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.2736842105263158,
"grad_norm": 0.0002681512269191444,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.2807017543859649,
"grad_norm": 0.00019258982501924038,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.28771929824561404,
"grad_norm": 0.0001639794063521549,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.29473684210526313,
"grad_norm": 0.0004290377255529165,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.3017543859649123,
"grad_norm": 0.0002691711124498397,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.3087719298245614,
"grad_norm": 0.00019797404820565134,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.3157894736842105,
"grad_norm": 0.00041717771091498435,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.32280701754385965,
"grad_norm": 0.00022527396504301578,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.3298245614035088,
"grad_norm": 0.0008209713269025087,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.3368421052631579,
"grad_norm": 0.000559433305170387,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.34385964912280703,
"grad_norm": 0.0007027975516393781,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.3508771929824561,
"grad_norm": 0.0005637676222249866,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.3508771929824561,
"eval_loss": 11.5,
"eval_runtime": 1.0968,
"eval_samples_per_second": 218.823,
"eval_steps_per_second": 54.706,
"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": 8039615692800.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}