prxy5605's picture
Training in progress, step 50, checkpoint
21ab0a3 verified
raw
history blame
9.92 kB
{
"best_metric": 0.9678934812545776,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.1774622892635315,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00354924578527063,
"grad_norm": 0.0637773647904396,
"learning_rate": 1e-05,
"loss": 1.008,
"step": 1
},
{
"epoch": 0.00354924578527063,
"eval_loss": 2.846020221710205,
"eval_runtime": 13.8102,
"eval_samples_per_second": 34.395,
"eval_steps_per_second": 8.617,
"step": 1
},
{
"epoch": 0.00709849157054126,
"grad_norm": 0.05443616583943367,
"learning_rate": 2e-05,
"loss": 0.8655,
"step": 2
},
{
"epoch": 0.01064773735581189,
"grad_norm": 0.10277120023965836,
"learning_rate": 3e-05,
"loss": 1.0278,
"step": 3
},
{
"epoch": 0.01419698314108252,
"grad_norm": 0.13329511880874634,
"learning_rate": 4e-05,
"loss": 0.8857,
"step": 4
},
{
"epoch": 0.01774622892635315,
"grad_norm": 0.17435085773468018,
"learning_rate": 5e-05,
"loss": 0.9234,
"step": 5
},
{
"epoch": 0.02129547471162378,
"grad_norm": 0.15340793132781982,
"learning_rate": 6e-05,
"loss": 1.098,
"step": 6
},
{
"epoch": 0.024844720496894408,
"grad_norm": 0.2555595636367798,
"learning_rate": 7e-05,
"loss": 1.057,
"step": 7
},
{
"epoch": 0.02839396628216504,
"grad_norm": 0.26080092787742615,
"learning_rate": 8e-05,
"loss": 1.2819,
"step": 8
},
{
"epoch": 0.03194321206743567,
"grad_norm": 0.2657241225242615,
"learning_rate": 9e-05,
"loss": 1.3631,
"step": 9
},
{
"epoch": 0.0354924578527063,
"grad_norm": 0.3126522898674011,
"learning_rate": 0.0001,
"loss": 1.3238,
"step": 10
},
{
"epoch": 0.03904170363797693,
"grad_norm": 0.36192429065704346,
"learning_rate": 9.999316524962345e-05,
"loss": 1.3867,
"step": 11
},
{
"epoch": 0.04259094942324756,
"grad_norm": 0.4159677028656006,
"learning_rate": 9.997266286704631e-05,
"loss": 1.2123,
"step": 12
},
{
"epoch": 0.04614019520851819,
"grad_norm": 0.3637048006057739,
"learning_rate": 9.993849845741524e-05,
"loss": 1.7588,
"step": 13
},
{
"epoch": 0.049689440993788817,
"grad_norm": 0.2503468096256256,
"learning_rate": 9.989068136093873e-05,
"loss": 1.4214,
"step": 14
},
{
"epoch": 0.05323868677905945,
"grad_norm": 0.25303223729133606,
"learning_rate": 9.98292246503335e-05,
"loss": 1.4821,
"step": 15
},
{
"epoch": 0.05678793256433008,
"grad_norm": 0.22958573698997498,
"learning_rate": 9.975414512725057e-05,
"loss": 1.2406,
"step": 16
},
{
"epoch": 0.06033717834960071,
"grad_norm": 0.4449329078197479,
"learning_rate": 9.966546331768191e-05,
"loss": 1.6172,
"step": 17
},
{
"epoch": 0.06388642413487133,
"grad_norm": 0.5130823850631714,
"learning_rate": 9.956320346634876e-05,
"loss": 1.3429,
"step": 18
},
{
"epoch": 0.06743566992014197,
"grad_norm": 0.4500519037246704,
"learning_rate": 9.944739353007344e-05,
"loss": 1.5301,
"step": 19
},
{
"epoch": 0.0709849157054126,
"grad_norm": 0.7953326106071472,
"learning_rate": 9.931806517013612e-05,
"loss": 1.5241,
"step": 20
},
{
"epoch": 0.07453416149068323,
"grad_norm": 0.6240103244781494,
"learning_rate": 9.917525374361912e-05,
"loss": 1.6553,
"step": 21
},
{
"epoch": 0.07808340727595386,
"grad_norm": 0.5798241496086121,
"learning_rate": 9.901899829374047e-05,
"loss": 1.4224,
"step": 22
},
{
"epoch": 0.08163265306122448,
"grad_norm": 0.5938167572021484,
"learning_rate": 9.884934153917997e-05,
"loss": 1.3839,
"step": 23
},
{
"epoch": 0.08518189884649512,
"grad_norm": 0.5691270232200623,
"learning_rate": 9.86663298624003e-05,
"loss": 1.3292,
"step": 24
},
{
"epoch": 0.08873114463176575,
"grad_norm": 0.6260955333709717,
"learning_rate": 9.847001329696653e-05,
"loss": 1.1849,
"step": 25
},
{
"epoch": 0.09228039041703638,
"grad_norm": 0.5980312824249268,
"learning_rate": 9.826044551386744e-05,
"loss": 1.1255,
"step": 26
},
{
"epoch": 0.09582963620230701,
"grad_norm": 0.663174569606781,
"learning_rate": 9.803768380684242e-05,
"loss": 1.1381,
"step": 27
},
{
"epoch": 0.09937888198757763,
"grad_norm": 0.7026616334915161,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9606,
"step": 28
},
{
"epoch": 0.10292812777284827,
"grad_norm": 0.5387756824493408,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0924,
"step": 29
},
{
"epoch": 0.1064773735581189,
"grad_norm": 0.6604188084602356,
"learning_rate": 9.729086208503174e-05,
"loss": 1.0046,
"step": 30
},
{
"epoch": 0.11002661934338953,
"grad_norm": 0.6040458679199219,
"learning_rate": 9.701596950580806e-05,
"loss": 0.7719,
"step": 31
},
{
"epoch": 0.11357586512866016,
"grad_norm": 0.43716174364089966,
"learning_rate": 9.672822322997305e-05,
"loss": 0.5854,
"step": 32
},
{
"epoch": 0.11712511091393078,
"grad_norm": 0.3770456910133362,
"learning_rate": 9.642770192448536e-05,
"loss": 0.6235,
"step": 33
},
{
"epoch": 0.12067435669920142,
"grad_norm": 0.4428984522819519,
"learning_rate": 9.611448774886924e-05,
"loss": 0.5695,
"step": 34
},
{
"epoch": 0.12422360248447205,
"grad_norm": 0.4358701705932617,
"learning_rate": 9.578866633275288e-05,
"loss": 0.5757,
"step": 35
},
{
"epoch": 0.12777284826974267,
"grad_norm": 0.5269954800605774,
"learning_rate": 9.545032675245813e-05,
"loss": 0.5932,
"step": 36
},
{
"epoch": 0.1313220940550133,
"grad_norm": 0.38701364398002625,
"learning_rate": 9.509956150664796e-05,
"loss": 0.6304,
"step": 37
},
{
"epoch": 0.13487133984028393,
"grad_norm": 0.45931679010391235,
"learning_rate": 9.473646649103818e-05,
"loss": 0.4312,
"step": 38
},
{
"epoch": 0.13842058562555457,
"grad_norm": 0.5391808152198792,
"learning_rate": 9.43611409721806e-05,
"loss": 0.8634,
"step": 39
},
{
"epoch": 0.1419698314108252,
"grad_norm": 0.4739307761192322,
"learning_rate": 9.397368756032445e-05,
"loss": 0.6318,
"step": 40
},
{
"epoch": 0.14551907719609583,
"grad_norm": 0.5952427387237549,
"learning_rate": 9.357421218136386e-05,
"loss": 1.0713,
"step": 41
},
{
"epoch": 0.14906832298136646,
"grad_norm": 0.413387656211853,
"learning_rate": 9.316282404787871e-05,
"loss": 0.5576,
"step": 42
},
{
"epoch": 0.1526175687666371,
"grad_norm": 0.4225512146949768,
"learning_rate": 9.273963562927695e-05,
"loss": 0.5857,
"step": 43
},
{
"epoch": 0.15616681455190773,
"grad_norm": 0.44275951385498047,
"learning_rate": 9.230476262104677e-05,
"loss": 0.7878,
"step": 44
},
{
"epoch": 0.15971606033717836,
"grad_norm": 0.5345599055290222,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9226,
"step": 45
},
{
"epoch": 0.16326530612244897,
"grad_norm": 0.4804178476333618,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8944,
"step": 46
},
{
"epoch": 0.1668145519077196,
"grad_norm": 0.6126044392585754,
"learning_rate": 9.093124073433463e-05,
"loss": 1.0157,
"step": 47
},
{
"epoch": 0.17036379769299023,
"grad_norm": 0.4933929443359375,
"learning_rate": 9.045084971874738e-05,
"loss": 0.6229,
"step": 48
},
{
"epoch": 0.17391304347826086,
"grad_norm": 0.5160196423530579,
"learning_rate": 8.995939984474624e-05,
"loss": 0.5569,
"step": 49
},
{
"epoch": 0.1774622892635315,
"grad_norm": 0.4330124855041504,
"learning_rate": 8.945702546981969e-05,
"loss": 0.4704,
"step": 50
},
{
"epoch": 0.1774622892635315,
"eval_loss": 0.9678934812545776,
"eval_runtime": 13.9565,
"eval_samples_per_second": 34.034,
"eval_steps_per_second": 8.527,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"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": 1.7041556540227584e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}