Nexspear's picture
Training in progress, step 50, checkpoint
abdb0b1 verified
raw
history blame
9.94 kB
{
"best_metric": 1.7446192502975464,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.018563207722294413,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00037126415444588826,
"grad_norm": 6.770651817321777,
"learning_rate": 1e-05,
"loss": 14.1005,
"step": 1
},
{
"epoch": 0.00037126415444588826,
"eval_loss": 4.361657619476318,
"eval_runtime": 561.9621,
"eval_samples_per_second": 8.073,
"eval_steps_per_second": 2.02,
"step": 1
},
{
"epoch": 0.0007425283088917765,
"grad_norm": 8.687636375427246,
"learning_rate": 2e-05,
"loss": 17.8128,
"step": 2
},
{
"epoch": 0.0011137924633376648,
"grad_norm": 8.961566925048828,
"learning_rate": 3e-05,
"loss": 18.9768,
"step": 3
},
{
"epoch": 0.001485056617783553,
"grad_norm": 8.438793182373047,
"learning_rate": 4e-05,
"loss": 18.1473,
"step": 4
},
{
"epoch": 0.0018563207722294413,
"grad_norm": 11.668978691101074,
"learning_rate": 5e-05,
"loss": 20.4785,
"step": 5
},
{
"epoch": 0.0022275849266753297,
"grad_norm": 12.654362678527832,
"learning_rate": 6e-05,
"loss": 20.2845,
"step": 6
},
{
"epoch": 0.0025988490811212177,
"grad_norm": 12.418852806091309,
"learning_rate": 7e-05,
"loss": 21.1342,
"step": 7
},
{
"epoch": 0.002970113235567106,
"grad_norm": 11.714797973632812,
"learning_rate": 8e-05,
"loss": 20.2635,
"step": 8
},
{
"epoch": 0.003341377390012994,
"grad_norm": 15.500533103942871,
"learning_rate": 9e-05,
"loss": 21.1619,
"step": 9
},
{
"epoch": 0.0037126415444588825,
"grad_norm": 14.004990577697754,
"learning_rate": 0.0001,
"loss": 21.6419,
"step": 10
},
{
"epoch": 0.0040839056989047705,
"grad_norm": 9.49889850616455,
"learning_rate": 9.99695413509548e-05,
"loss": 13.9394,
"step": 11
},
{
"epoch": 0.004455169853350659,
"grad_norm": 9.78544807434082,
"learning_rate": 9.987820251299122e-05,
"loss": 10.7483,
"step": 12
},
{
"epoch": 0.004826434007796547,
"grad_norm": 8.1702880859375,
"learning_rate": 9.972609476841367e-05,
"loss": 9.8475,
"step": 13
},
{
"epoch": 0.005197698162242435,
"grad_norm": 7.895254611968994,
"learning_rate": 9.951340343707852e-05,
"loss": 9.6974,
"step": 14
},
{
"epoch": 0.005568962316688323,
"grad_norm": 14.222855567932129,
"learning_rate": 9.924038765061042e-05,
"loss": 9.0982,
"step": 15
},
{
"epoch": 0.005940226471134212,
"grad_norm": 15.02148723602295,
"learning_rate": 9.890738003669029e-05,
"loss": 7.7513,
"step": 16
},
{
"epoch": 0.0063114906255801,
"grad_norm": 7.8985419273376465,
"learning_rate": 9.851478631379982e-05,
"loss": 8.2367,
"step": 17
},
{
"epoch": 0.006682754780025988,
"grad_norm": 9.158758163452148,
"learning_rate": 9.806308479691595e-05,
"loss": 8.205,
"step": 18
},
{
"epoch": 0.007054018934471877,
"grad_norm": 21.200363159179688,
"learning_rate": 9.755282581475769e-05,
"loss": 8.5559,
"step": 19
},
{
"epoch": 0.007425283088917765,
"grad_norm": 6.861835479736328,
"learning_rate": 9.698463103929542e-05,
"loss": 6.508,
"step": 20
},
{
"epoch": 0.007796547243363653,
"grad_norm": 4.614739418029785,
"learning_rate": 9.635919272833938e-05,
"loss": 7.8475,
"step": 21
},
{
"epoch": 0.008167811397809541,
"grad_norm": 6.366387844085693,
"learning_rate": 9.567727288213005e-05,
"loss": 7.4751,
"step": 22
},
{
"epoch": 0.008539075552255429,
"grad_norm": 6.066256999969482,
"learning_rate": 9.493970231495835e-05,
"loss": 7.2972,
"step": 23
},
{
"epoch": 0.008910339706701319,
"grad_norm": 5.310906887054443,
"learning_rate": 9.414737964294636e-05,
"loss": 6.0529,
"step": 24
},
{
"epoch": 0.009281603861147207,
"grad_norm": 5.21856164932251,
"learning_rate": 9.330127018922194e-05,
"loss": 6.9142,
"step": 25
},
{
"epoch": 0.009652868015593095,
"grad_norm": 4.360562324523926,
"learning_rate": 9.24024048078213e-05,
"loss": 7.5712,
"step": 26
},
{
"epoch": 0.010024132170038983,
"grad_norm": 5.237946510314941,
"learning_rate": 9.145187862775209e-05,
"loss": 7.2218,
"step": 27
},
{
"epoch": 0.01039539632448487,
"grad_norm": 6.701196193695068,
"learning_rate": 9.045084971874738e-05,
"loss": 6.7606,
"step": 28
},
{
"epoch": 0.010766660478930759,
"grad_norm": 5.245985507965088,
"learning_rate": 8.940053768033609e-05,
"loss": 6.9502,
"step": 29
},
{
"epoch": 0.011137924633376647,
"grad_norm": 4.025079727172852,
"learning_rate": 8.83022221559489e-05,
"loss": 5.8071,
"step": 30
},
{
"epoch": 0.011509188787822536,
"grad_norm": 5.323147773742676,
"learning_rate": 8.715724127386972e-05,
"loss": 6.8309,
"step": 31
},
{
"epoch": 0.011880452942268424,
"grad_norm": 4.425078868865967,
"learning_rate": 8.596699001693255e-05,
"loss": 6.5695,
"step": 32
},
{
"epoch": 0.012251717096714312,
"grad_norm": 4.665747165679932,
"learning_rate": 8.473291852294987e-05,
"loss": 6.1289,
"step": 33
},
{
"epoch": 0.0126229812511602,
"grad_norm": 4.494863986968994,
"learning_rate": 8.345653031794292e-05,
"loss": 6.1595,
"step": 34
},
{
"epoch": 0.012994245405606088,
"grad_norm": 4.774189472198486,
"learning_rate": 8.213938048432697e-05,
"loss": 6.2973,
"step": 35
},
{
"epoch": 0.013365509560051976,
"grad_norm": 4.161970615386963,
"learning_rate": 8.07830737662829e-05,
"loss": 6.7843,
"step": 36
},
{
"epoch": 0.013736773714497864,
"grad_norm": 4.1743292808532715,
"learning_rate": 7.938926261462366e-05,
"loss": 6.4967,
"step": 37
},
{
"epoch": 0.014108037868943754,
"grad_norm": 4.199504375457764,
"learning_rate": 7.795964517353735e-05,
"loss": 6.5638,
"step": 38
},
{
"epoch": 0.014479302023389642,
"grad_norm": 4.517217636108398,
"learning_rate": 7.649596321166024e-05,
"loss": 7.2976,
"step": 39
},
{
"epoch": 0.01485056617783553,
"grad_norm": 4.099196910858154,
"learning_rate": 7.500000000000001e-05,
"loss": 7.5602,
"step": 40
},
{
"epoch": 0.015221830332281418,
"grad_norm": 4.4114251136779785,
"learning_rate": 7.347357813929454e-05,
"loss": 6.7823,
"step": 41
},
{
"epoch": 0.015593094486727306,
"grad_norm": 4.016313552856445,
"learning_rate": 7.191855733945387e-05,
"loss": 6.5018,
"step": 42
},
{
"epoch": 0.015964358641173196,
"grad_norm": 4.02785587310791,
"learning_rate": 7.033683215379002e-05,
"loss": 6.4507,
"step": 43
},
{
"epoch": 0.016335622795619082,
"grad_norm": 4.262504577636719,
"learning_rate": 6.873032967079561e-05,
"loss": 6.1423,
"step": 44
},
{
"epoch": 0.016706886950064972,
"grad_norm": 3.9246904850006104,
"learning_rate": 6.710100716628344e-05,
"loss": 6.2621,
"step": 45
},
{
"epoch": 0.017078151104510858,
"grad_norm": 4.26507568359375,
"learning_rate": 6.545084971874738e-05,
"loss": 7.6392,
"step": 46
},
{
"epoch": 0.017449415258956748,
"grad_norm": 3.834524393081665,
"learning_rate": 6.378186779084995e-05,
"loss": 6.7854,
"step": 47
},
{
"epoch": 0.017820679413402638,
"grad_norm": 5.054991722106934,
"learning_rate": 6.209609477998338e-05,
"loss": 6.0353,
"step": 48
},
{
"epoch": 0.018191943567848524,
"grad_norm": 3.795661687850952,
"learning_rate": 6.0395584540887963e-05,
"loss": 5.4362,
"step": 49
},
{
"epoch": 0.018563207722294413,
"grad_norm": 4.460452556610107,
"learning_rate": 5.868240888334653e-05,
"loss": 6.807,
"step": 50
},
{
"epoch": 0.018563207722294413,
"eval_loss": 1.7446192502975464,
"eval_runtime": 566.7624,
"eval_samples_per_second": 8.005,
"eval_steps_per_second": 2.003,
"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": 7.954473927101645e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}