aleegis11's picture
Training in progress, step 50, checkpoint
6a4ebb8 verified
raw
history blame
9.97 kB
{
"best_metric": 0.04401622712612152,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.007979253939756632,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00015958507879513265,
"grad_norm": 91.70167541503906,
"learning_rate": 1e-05,
"loss": 12.0695,
"step": 1
},
{
"epoch": 0.00015958507879513265,
"eval_loss": 12.273541450500488,
"eval_runtime": 806.9351,
"eval_samples_per_second": 13.079,
"eval_steps_per_second": 3.27,
"step": 1
},
{
"epoch": 0.0003191701575902653,
"grad_norm": 102.95516967773438,
"learning_rate": 2e-05,
"loss": 11.8707,
"step": 2
},
{
"epoch": 0.00047875523638539794,
"grad_norm": 94.14151000976562,
"learning_rate": 3e-05,
"loss": 10.347,
"step": 3
},
{
"epoch": 0.0006383403151805306,
"grad_norm": 74.24517059326172,
"learning_rate": 4e-05,
"loss": 6.7574,
"step": 4
},
{
"epoch": 0.0007979253939756633,
"grad_norm": 80.98632049560547,
"learning_rate": 5e-05,
"loss": 1.8561,
"step": 5
},
{
"epoch": 0.0009575104727707959,
"grad_norm": 2.4279086589813232,
"learning_rate": 6e-05,
"loss": 0.0256,
"step": 6
},
{
"epoch": 0.0011170955515659286,
"grad_norm": 0.00727560929954052,
"learning_rate": 7e-05,
"loss": 0.0001,
"step": 7
},
{
"epoch": 0.0012766806303610612,
"grad_norm": 43.05037307739258,
"learning_rate": 8e-05,
"loss": 1.1148,
"step": 8
},
{
"epoch": 0.001436265709156194,
"grad_norm": 243.4115753173828,
"learning_rate": 9e-05,
"loss": 3.5722,
"step": 9
},
{
"epoch": 0.0015958507879513266,
"grad_norm": 0.0019942147191613913,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.0017554358667464592,
"grad_norm": 19.9483699798584,
"learning_rate": 9.999316524962345e-05,
"loss": 0.394,
"step": 11
},
{
"epoch": 0.0019150209455415918,
"grad_norm": 6.683404445648193,
"learning_rate": 9.997266286704631e-05,
"loss": 0.2813,
"step": 12
},
{
"epoch": 0.0020746060243367246,
"grad_norm": 23.342052459716797,
"learning_rate": 9.993849845741524e-05,
"loss": 0.8593,
"step": 13
},
{
"epoch": 0.002234191103131857,
"grad_norm": 6.088518142700195,
"learning_rate": 9.989068136093873e-05,
"loss": 0.2156,
"step": 14
},
{
"epoch": 0.0023937761819269898,
"grad_norm": 1.7149337530136108,
"learning_rate": 9.98292246503335e-05,
"loss": 0.1325,
"step": 15
},
{
"epoch": 0.0025533612607221224,
"grad_norm": 0.6034479737281799,
"learning_rate": 9.975414512725057e-05,
"loss": 0.0729,
"step": 16
},
{
"epoch": 0.002712946339517255,
"grad_norm": 1.5753737688064575,
"learning_rate": 9.966546331768191e-05,
"loss": 0.1833,
"step": 17
},
{
"epoch": 0.002872531418312388,
"grad_norm": 1.3809409141540527,
"learning_rate": 9.956320346634876e-05,
"loss": 0.0813,
"step": 18
},
{
"epoch": 0.0030321164971075206,
"grad_norm": 0.7744306325912476,
"learning_rate": 9.944739353007344e-05,
"loss": 0.061,
"step": 19
},
{
"epoch": 0.003191701575902653,
"grad_norm": 3.3979737758636475,
"learning_rate": 9.931806517013612e-05,
"loss": 0.1148,
"step": 20
},
{
"epoch": 0.0033512866546977858,
"grad_norm": 1.116274356842041,
"learning_rate": 9.917525374361912e-05,
"loss": 0.075,
"step": 21
},
{
"epoch": 0.0035108717334929184,
"grad_norm": 2.1139369010925293,
"learning_rate": 9.901899829374047e-05,
"loss": 0.158,
"step": 22
},
{
"epoch": 0.003670456812288051,
"grad_norm": 0.871885359287262,
"learning_rate": 9.884934153917997e-05,
"loss": 0.0271,
"step": 23
},
{
"epoch": 0.0038300418910831835,
"grad_norm": 3.1295361518859863,
"learning_rate": 9.86663298624003e-05,
"loss": 0.0878,
"step": 24
},
{
"epoch": 0.003989626969878316,
"grad_norm": 0.11067342013120651,
"learning_rate": 9.847001329696653e-05,
"loss": 0.0019,
"step": 25
},
{
"epoch": 0.004149212048673449,
"grad_norm": 4.298526287078857,
"learning_rate": 9.826044551386744e-05,
"loss": 0.0829,
"step": 26
},
{
"epoch": 0.004308797127468581,
"grad_norm": 6.691145896911621,
"learning_rate": 9.803768380684242e-05,
"loss": 0.0746,
"step": 27
},
{
"epoch": 0.004468382206263714,
"grad_norm": 0.22768229246139526,
"learning_rate": 9.780178907671789e-05,
"loss": 0.0034,
"step": 28
},
{
"epoch": 0.004627967285058847,
"grad_norm": 2.516052007675171,
"learning_rate": 9.755282581475769e-05,
"loss": 0.0364,
"step": 29
},
{
"epoch": 0.0047875523638539795,
"grad_norm": 6.500372886657715,
"learning_rate": 9.729086208503174e-05,
"loss": 0.0606,
"step": 30
},
{
"epoch": 0.0049471374426491126,
"grad_norm": 5.292369842529297,
"learning_rate": 9.701596950580806e-05,
"loss": 0.0527,
"step": 31
},
{
"epoch": 0.005106722521444245,
"grad_norm": 5.458245754241943,
"learning_rate": 9.672822322997305e-05,
"loss": 0.0554,
"step": 32
},
{
"epoch": 0.005266307600239378,
"grad_norm": 4.49389123916626,
"learning_rate": 9.642770192448536e-05,
"loss": 0.0532,
"step": 33
},
{
"epoch": 0.00542589267903451,
"grad_norm": 1.8657965660095215,
"learning_rate": 9.611448774886924e-05,
"loss": 0.0099,
"step": 34
},
{
"epoch": 0.005585477757829643,
"grad_norm": 10.926817893981934,
"learning_rate": 9.578866633275288e-05,
"loss": 0.0738,
"step": 35
},
{
"epoch": 0.005745062836624776,
"grad_norm": 10.781157493591309,
"learning_rate": 9.545032675245813e-05,
"loss": 0.0477,
"step": 36
},
{
"epoch": 0.005904647915419908,
"grad_norm": 9.783218383789062,
"learning_rate": 9.509956150664796e-05,
"loss": 0.1485,
"step": 37
},
{
"epoch": 0.006064232994215041,
"grad_norm": 1.8303381204605103,
"learning_rate": 9.473646649103818e-05,
"loss": 0.0364,
"step": 38
},
{
"epoch": 0.006223818073010173,
"grad_norm": 2.6647450923919678,
"learning_rate": 9.43611409721806e-05,
"loss": 0.0676,
"step": 39
},
{
"epoch": 0.006383403151805306,
"grad_norm": 0.9746254086494446,
"learning_rate": 9.397368756032445e-05,
"loss": 0.0147,
"step": 40
},
{
"epoch": 0.0065429882306004385,
"grad_norm": 2.5695393085479736,
"learning_rate": 9.357421218136386e-05,
"loss": 0.2064,
"step": 41
},
{
"epoch": 0.0067025733093955715,
"grad_norm": 2.2885403633117676,
"learning_rate": 9.316282404787871e-05,
"loss": 0.0852,
"step": 42
},
{
"epoch": 0.0068621583881907046,
"grad_norm": 2.5603082180023193,
"learning_rate": 9.273963562927695e-05,
"loss": 0.084,
"step": 43
},
{
"epoch": 0.007021743466985837,
"grad_norm": 1.8648403882980347,
"learning_rate": 9.230476262104677e-05,
"loss": 0.0348,
"step": 44
},
{
"epoch": 0.00718132854578097,
"grad_norm": 1.890605092048645,
"learning_rate": 9.185832391312644e-05,
"loss": 0.0602,
"step": 45
},
{
"epoch": 0.007340913624576102,
"grad_norm": 3.5145490169525146,
"learning_rate": 9.140044155740101e-05,
"loss": 0.1955,
"step": 46
},
{
"epoch": 0.007500498703371235,
"grad_norm": 2.490647315979004,
"learning_rate": 9.093124073433463e-05,
"loss": 0.0714,
"step": 47
},
{
"epoch": 0.007660083782166367,
"grad_norm": 1.671553611755371,
"learning_rate": 9.045084971874738e-05,
"loss": 0.0452,
"step": 48
},
{
"epoch": 0.0078196688609615,
"grad_norm": 1.9121739864349365,
"learning_rate": 8.995939984474624e-05,
"loss": 0.149,
"step": 49
},
{
"epoch": 0.007979253939756632,
"grad_norm": 1.8590110540390015,
"learning_rate": 8.945702546981969e-05,
"loss": 0.0543,
"step": 50
},
{
"epoch": 0.007979253939756632,
"eval_loss": 0.04401622712612152,
"eval_runtime": 811.03,
"eval_samples_per_second": 13.013,
"eval_steps_per_second": 3.254,
"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": 7.580280733197926e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}