DeepDream2045's picture
Training in progress, step 50, checkpoint
ed00735 verified
{
"best_metric": 6.924746990203857,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.010696188145949487,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00021392376291898973,
"grad_norm": 0.084352046251297,
"learning_rate": 5e-05,
"loss": 6.9391,
"step": 1
},
{
"epoch": 0.00021392376291898973,
"eval_loss": 6.939151287078857,
"eval_runtime": 22.5661,
"eval_samples_per_second": 1395.547,
"eval_steps_per_second": 174.465,
"step": 1
},
{
"epoch": 0.00042784752583797947,
"grad_norm": 0.08244480937719345,
"learning_rate": 0.0001,
"loss": 6.9384,
"step": 2
},
{
"epoch": 0.0006417712887569693,
"grad_norm": 0.08688157051801682,
"learning_rate": 9.989294616193017e-05,
"loss": 6.9393,
"step": 3
},
{
"epoch": 0.0008556950516759589,
"grad_norm": 0.09273950755596161,
"learning_rate": 9.957224306869053e-05,
"loss": 6.9373,
"step": 4
},
{
"epoch": 0.0010696188145949488,
"grad_norm": 0.09501701593399048,
"learning_rate": 9.903926402016153e-05,
"loss": 6.9383,
"step": 5
},
{
"epoch": 0.0012835425775139385,
"grad_norm": 0.09917747974395752,
"learning_rate": 9.829629131445342e-05,
"loss": 6.9381,
"step": 6
},
{
"epoch": 0.0014974663404329282,
"grad_norm": 0.10376238822937012,
"learning_rate": 9.73465064747553e-05,
"loss": 6.9364,
"step": 7
},
{
"epoch": 0.0017113901033519179,
"grad_norm": 0.11044597625732422,
"learning_rate": 9.619397662556435e-05,
"loss": 6.9352,
"step": 8
},
{
"epoch": 0.0019253138662709078,
"grad_norm": 0.11213497817516327,
"learning_rate": 9.484363707663442e-05,
"loss": 6.9355,
"step": 9
},
{
"epoch": 0.0021392376291898977,
"grad_norm": 0.11234603077173233,
"learning_rate": 9.330127018922194e-05,
"loss": 6.9373,
"step": 10
},
{
"epoch": 0.0023531613921088873,
"grad_norm": 0.12427860498428345,
"learning_rate": 9.157348061512727e-05,
"loss": 6.9339,
"step": 11
},
{
"epoch": 0.002567085155027877,
"grad_norm": 0.13528341054916382,
"learning_rate": 8.966766701456177e-05,
"loss": 6.9354,
"step": 12
},
{
"epoch": 0.0027810089179468667,
"grad_norm": 0.10144588351249695,
"learning_rate": 8.759199037394887e-05,
"loss": 6.9326,
"step": 13
},
{
"epoch": 0.0029949326808658564,
"grad_norm": 0.08907917141914368,
"learning_rate": 8.535533905932738e-05,
"loss": 6.9358,
"step": 14
},
{
"epoch": 0.003208856443784846,
"grad_norm": 0.09633015841245651,
"learning_rate": 8.296729075500344e-05,
"loss": 6.9317,
"step": 15
},
{
"epoch": 0.0034227802067038357,
"grad_norm": 0.09162943065166473,
"learning_rate": 8.043807145043604e-05,
"loss": 6.9326,
"step": 16
},
{
"epoch": 0.003636703969622826,
"grad_norm": 0.10051411390304565,
"learning_rate": 7.777851165098012e-05,
"loss": 6.9315,
"step": 17
},
{
"epoch": 0.0038506277325418155,
"grad_norm": 0.09999406337738037,
"learning_rate": 7.500000000000001e-05,
"loss": 6.9309,
"step": 18
},
{
"epoch": 0.004064551495460805,
"grad_norm": 0.10973299294710159,
"learning_rate": 7.211443451095007e-05,
"loss": 6.9314,
"step": 19
},
{
"epoch": 0.004278475258379795,
"grad_norm": 0.10994168370962143,
"learning_rate": 6.91341716182545e-05,
"loss": 6.9305,
"step": 20
},
{
"epoch": 0.004492399021298785,
"grad_norm": 0.11387638747692108,
"learning_rate": 6.607197326515808e-05,
"loss": 6.9333,
"step": 21
},
{
"epoch": 0.004706322784217775,
"grad_norm": 0.11845920979976654,
"learning_rate": 6.294095225512603e-05,
"loss": 6.9282,
"step": 22
},
{
"epoch": 0.004920246547136764,
"grad_norm": 0.12084134668111801,
"learning_rate": 5.9754516100806423e-05,
"loss": 6.9278,
"step": 23
},
{
"epoch": 0.005134170310055754,
"grad_norm": 0.13196800649166107,
"learning_rate": 5.6526309611002594e-05,
"loss": 6.9267,
"step": 24
},
{
"epoch": 0.005348094072974744,
"grad_norm": 0.15287362039089203,
"learning_rate": 5.327015646150716e-05,
"loss": 6.9285,
"step": 25
},
{
"epoch": 0.005348094072974744,
"eval_loss": 6.9282989501953125,
"eval_runtime": 23.0115,
"eval_samples_per_second": 1368.531,
"eval_steps_per_second": 171.088,
"step": 25
},
{
"epoch": 0.005562017835893733,
"grad_norm": 0.0925169289112091,
"learning_rate": 5e-05,
"loss": 6.9306,
"step": 26
},
{
"epoch": 0.005775941598812723,
"grad_norm": 0.09849868714809418,
"learning_rate": 4.6729843538492847e-05,
"loss": 6.9295,
"step": 27
},
{
"epoch": 0.005989865361731713,
"grad_norm": 0.10103553533554077,
"learning_rate": 4.347369038899744e-05,
"loss": 6.927,
"step": 28
},
{
"epoch": 0.0062037891246507024,
"grad_norm": 0.10405988246202469,
"learning_rate": 4.0245483899193595e-05,
"loss": 6.9273,
"step": 29
},
{
"epoch": 0.006417712887569692,
"grad_norm": 0.11038113385438919,
"learning_rate": 3.705904774487396e-05,
"loss": 6.9269,
"step": 30
},
{
"epoch": 0.006631636650488682,
"grad_norm": 0.11047299206256866,
"learning_rate": 3.392802673484193e-05,
"loss": 6.9259,
"step": 31
},
{
"epoch": 0.0068455604134076715,
"grad_norm": 0.11552471667528152,
"learning_rate": 3.086582838174551e-05,
"loss": 6.9253,
"step": 32
},
{
"epoch": 0.007059484176326661,
"grad_norm": 0.12445191293954849,
"learning_rate": 2.7885565489049946e-05,
"loss": 6.9267,
"step": 33
},
{
"epoch": 0.007273407939245652,
"grad_norm": 0.11612529307603836,
"learning_rate": 2.500000000000001e-05,
"loss": 6.9276,
"step": 34
},
{
"epoch": 0.007487331702164641,
"grad_norm": 0.13253656029701233,
"learning_rate": 2.2221488349019903e-05,
"loss": 6.925,
"step": 35
},
{
"epoch": 0.007701255465083631,
"grad_norm": 0.13963279128074646,
"learning_rate": 1.9561928549563968e-05,
"loss": 6.9247,
"step": 36
},
{
"epoch": 0.00791517922800262,
"grad_norm": 0.14887762069702148,
"learning_rate": 1.703270924499656e-05,
"loss": 6.922,
"step": 37
},
{
"epoch": 0.00812910299092161,
"grad_norm": 0.10967689752578735,
"learning_rate": 1.4644660940672627e-05,
"loss": 6.9273,
"step": 38
},
{
"epoch": 0.0083430267538406,
"grad_norm": 0.10133490711450577,
"learning_rate": 1.2408009626051137e-05,
"loss": 6.9261,
"step": 39
},
{
"epoch": 0.00855695051675959,
"grad_norm": 0.10881227254867554,
"learning_rate": 1.0332332985438248e-05,
"loss": 6.9287,
"step": 40
},
{
"epoch": 0.00877087427967858,
"grad_norm": 0.10970684885978699,
"learning_rate": 8.426519384872733e-06,
"loss": 6.9248,
"step": 41
},
{
"epoch": 0.00898479804259757,
"grad_norm": 0.11278239637613297,
"learning_rate": 6.698729810778065e-06,
"loss": 6.9259,
"step": 42
},
{
"epoch": 0.00919872180551656,
"grad_norm": 0.12211595475673676,
"learning_rate": 5.156362923365588e-06,
"loss": 6.9251,
"step": 43
},
{
"epoch": 0.00941264556843555,
"grad_norm": 0.11529412865638733,
"learning_rate": 3.8060233744356633e-06,
"loss": 6.9224,
"step": 44
},
{
"epoch": 0.009626569331354539,
"grad_norm": 0.11878494918346405,
"learning_rate": 2.653493525244721e-06,
"loss": 6.9249,
"step": 45
},
{
"epoch": 0.009840493094273529,
"grad_norm": 0.1319645345211029,
"learning_rate": 1.70370868554659e-06,
"loss": 6.9217,
"step": 46
},
{
"epoch": 0.010054416857192518,
"grad_norm": 0.11767640709877014,
"learning_rate": 9.607359798384785e-07,
"loss": 6.9275,
"step": 47
},
{
"epoch": 0.010268340620111508,
"grad_norm": 0.1403781920671463,
"learning_rate": 4.277569313094809e-07,
"loss": 6.922,
"step": 48
},
{
"epoch": 0.010482264383030498,
"grad_norm": 0.14114433526992798,
"learning_rate": 1.0705383806982606e-07,
"loss": 6.9211,
"step": 49
},
{
"epoch": 0.010696188145949487,
"grad_norm": 0.1653960794210434,
"learning_rate": 0.0,
"loss": 6.9217,
"step": 50
},
{
"epoch": 0.010696188145949487,
"eval_loss": 6.924746990203857,
"eval_runtime": 22.575,
"eval_samples_per_second": 1394.997,
"eval_steps_per_second": 174.397,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 5705957376000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}