jssky's picture
Training in progress, step 50, checkpoint
f329a6b verified
{
"best_metric": 15.69967269897461,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.2282453637660485,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00456490727532097,
"grad_norm": Infinity,
"learning_rate": 5e-05,
"loss": 16.673,
"step": 1
},
{
"epoch": 0.00456490727532097,
"eval_loss": 15.774482727050781,
"eval_runtime": 31.792,
"eval_samples_per_second": 46.427,
"eval_steps_per_second": 5.819,
"step": 1
},
{
"epoch": 0.00912981455064194,
"grad_norm": Infinity,
"learning_rate": 0.0001,
"loss": 16.6251,
"step": 2
},
{
"epoch": 0.013694721825962911,
"grad_norm": Infinity,
"learning_rate": 9.989294616193017e-05,
"loss": 17.1072,
"step": 3
},
{
"epoch": 0.01825962910128388,
"grad_norm": 5.014348616995701e+18,
"learning_rate": 9.957224306869053e-05,
"loss": 16.2808,
"step": 4
},
{
"epoch": 0.02282453637660485,
"grad_norm": 5.0599755320498586e+17,
"learning_rate": 9.903926402016153e-05,
"loss": 16.2487,
"step": 5
},
{
"epoch": 0.027389443651925822,
"grad_norm": 961895574011904.0,
"learning_rate": 9.829629131445342e-05,
"loss": 15.6785,
"step": 6
},
{
"epoch": 0.03195435092724679,
"grad_norm": 43263104909312.0,
"learning_rate": 9.73465064747553e-05,
"loss": 15.4593,
"step": 7
},
{
"epoch": 0.03651925820256776,
"grad_norm": 5765393285120.0,
"learning_rate": 9.619397662556435e-05,
"loss": 15.5441,
"step": 8
},
{
"epoch": 0.04108416547788873,
"grad_norm": 306334007296.0,
"learning_rate": 9.484363707663442e-05,
"loss": 15.293,
"step": 9
},
{
"epoch": 0.0456490727532097,
"grad_norm": 232679712.0,
"learning_rate": 9.330127018922194e-05,
"loss": 15.3428,
"step": 10
},
{
"epoch": 0.05021398002853067,
"grad_norm": 177450320.0,
"learning_rate": 9.157348061512727e-05,
"loss": 15.3079,
"step": 11
},
{
"epoch": 0.054778887303851644,
"grad_norm": 1787997312.0,
"learning_rate": 8.966766701456177e-05,
"loss": 14.9776,
"step": 12
},
{
"epoch": 0.05934379457917261,
"grad_norm": Infinity,
"learning_rate": 8.759199037394887e-05,
"loss": 15.512,
"step": 13
},
{
"epoch": 0.06390870185449359,
"grad_norm": Infinity,
"learning_rate": 8.535533905932738e-05,
"loss": 17.1451,
"step": 14
},
{
"epoch": 0.06847360912981455,
"grad_norm": Infinity,
"learning_rate": 8.296729075500344e-05,
"loss": 16.7529,
"step": 15
},
{
"epoch": 0.07303851640513552,
"grad_norm": Infinity,
"learning_rate": 8.043807145043604e-05,
"loss": 16.6548,
"step": 16
},
{
"epoch": 0.07760342368045649,
"grad_norm": 1.0578230259335823e+18,
"learning_rate": 7.777851165098012e-05,
"loss": 16.2374,
"step": 17
},
{
"epoch": 0.08216833095577745,
"grad_norm": 1.1442665613898547e+17,
"learning_rate": 7.500000000000001e-05,
"loss": 16.0268,
"step": 18
},
{
"epoch": 0.08673323823109844,
"grad_norm": 135361942519808.0,
"learning_rate": 7.211443451095007e-05,
"loss": 15.6473,
"step": 19
},
{
"epoch": 0.0912981455064194,
"grad_norm": 1047146044325888.0,
"learning_rate": 6.91341716182545e-05,
"loss": 15.6988,
"step": 20
},
{
"epoch": 0.09586305278174037,
"grad_norm": 148717537591296.0,
"learning_rate": 6.607197326515808e-05,
"loss": 15.1818,
"step": 21
},
{
"epoch": 0.10042796005706134,
"grad_norm": 318713135104.0,
"learning_rate": 6.294095225512603e-05,
"loss": 15.3194,
"step": 22
},
{
"epoch": 0.1049928673323823,
"grad_norm": 198569440.0,
"learning_rate": 5.9754516100806423e-05,
"loss": 15.0033,
"step": 23
},
{
"epoch": 0.10955777460770329,
"grad_norm": 1567645696.0,
"learning_rate": 5.6526309611002594e-05,
"loss": 15.2461,
"step": 24
},
{
"epoch": 0.11412268188302425,
"grad_norm": 18039058.0,
"learning_rate": 5.327015646150716e-05,
"loss": 14.4768,
"step": 25
},
{
"epoch": 0.11412268188302425,
"eval_loss": 15.784210205078125,
"eval_runtime": 31.7998,
"eval_samples_per_second": 46.415,
"eval_steps_per_second": 5.818,
"step": 25
},
{
"epoch": 0.11868758915834522,
"grad_norm": Infinity,
"learning_rate": 5e-05,
"loss": 16.8711,
"step": 26
},
{
"epoch": 0.12325249643366619,
"grad_norm": Infinity,
"learning_rate": 4.6729843538492847e-05,
"loss": 16.7578,
"step": 27
},
{
"epoch": 0.12781740370898717,
"grad_norm": Infinity,
"learning_rate": 4.347369038899744e-05,
"loss": 16.7029,
"step": 28
},
{
"epoch": 0.13238231098430814,
"grad_norm": 5.27922536617345e+18,
"learning_rate": 4.0245483899193595e-05,
"loss": 16.5378,
"step": 29
},
{
"epoch": 0.1369472182596291,
"grad_norm": 6.708468986247381e+18,
"learning_rate": 3.705904774487396e-05,
"loss": 16.1224,
"step": 30
},
{
"epoch": 0.14151212553495007,
"grad_norm": 2683090229002240.0,
"learning_rate": 3.392802673484193e-05,
"loss": 15.8674,
"step": 31
},
{
"epoch": 0.14607703281027104,
"grad_norm": 3340606772346880.0,
"learning_rate": 3.086582838174551e-05,
"loss": 15.854,
"step": 32
},
{
"epoch": 0.150641940085592,
"grad_norm": 20492406751232.0,
"learning_rate": 2.7885565489049946e-05,
"loss": 15.0143,
"step": 33
},
{
"epoch": 0.15520684736091298,
"grad_norm": 34113855488.0,
"learning_rate": 2.500000000000001e-05,
"loss": 15.5429,
"step": 34
},
{
"epoch": 0.15977175463623394,
"grad_norm": 21085825024.0,
"learning_rate": 2.2221488349019903e-05,
"loss": 15.3274,
"step": 35
},
{
"epoch": 0.1643366619115549,
"grad_norm": 363076768.0,
"learning_rate": 1.9561928549563968e-05,
"loss": 15.033,
"step": 36
},
{
"epoch": 0.1689015691868759,
"grad_norm": 78258952.0,
"learning_rate": 1.703270924499656e-05,
"loss": 14.8023,
"step": 37
},
{
"epoch": 0.17346647646219687,
"grad_norm": Infinity,
"learning_rate": 1.4644660940672627e-05,
"loss": 15.6378,
"step": 38
},
{
"epoch": 0.17803138373751784,
"grad_norm": Infinity,
"learning_rate": 1.2408009626051137e-05,
"loss": 17.1524,
"step": 39
},
{
"epoch": 0.1825962910128388,
"grad_norm": Infinity,
"learning_rate": 1.0332332985438248e-05,
"loss": 16.9398,
"step": 40
},
{
"epoch": 0.18716119828815977,
"grad_norm": 8.890011656185184e+18,
"learning_rate": 8.426519384872733e-06,
"loss": 16.5318,
"step": 41
},
{
"epoch": 0.19172610556348074,
"grad_norm": 9.98518735985705e+17,
"learning_rate": 6.698729810778065e-06,
"loss": 16.1866,
"step": 42
},
{
"epoch": 0.1962910128388017,
"grad_norm": 1.2888339579823718e+17,
"learning_rate": 5.156362923365588e-06,
"loss": 16.0467,
"step": 43
},
{
"epoch": 0.20085592011412268,
"grad_norm": 1114067540377600.0,
"learning_rate": 3.8060233744356633e-06,
"loss": 15.3093,
"step": 44
},
{
"epoch": 0.20542082738944364,
"grad_norm": 13566930321408.0,
"learning_rate": 2.653493525244721e-06,
"loss": 15.424,
"step": 45
},
{
"epoch": 0.2099857346647646,
"grad_norm": 246276662755328.0,
"learning_rate": 1.70370868554659e-06,
"loss": 15.2233,
"step": 46
},
{
"epoch": 0.21455064194008558,
"grad_norm": 4525861376.0,
"learning_rate": 9.607359798384785e-07,
"loss": 15.4909,
"step": 47
},
{
"epoch": 0.21911554921540657,
"grad_norm": 2824147200.0,
"learning_rate": 4.277569313094809e-07,
"loss": 15.2904,
"step": 48
},
{
"epoch": 0.22368045649072754,
"grad_norm": 143129056.0,
"learning_rate": 1.0705383806982606e-07,
"loss": 15.2153,
"step": 49
},
{
"epoch": 0.2282453637660485,
"grad_norm": 30752916.0,
"learning_rate": 0.0,
"loss": 14.4523,
"step": 50
},
{
"epoch": 0.2282453637660485,
"eval_loss": 15.69967269897461,
"eval_runtime": 31.7913,
"eval_samples_per_second": 46.428,
"eval_steps_per_second": 5.819,
"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": 2.974559326175232e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}