| { | |
| "best_metric": 1.8900460004806519, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.17086715079026057, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034173430158052115, | |
| "grad_norm": 0.07864680886268616, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034173430158052115, | |
| "eval_loss": 2.046931266784668, | |
| "eval_runtime": 122.2662, | |
| "eval_samples_per_second": 16.129, | |
| "eval_steps_per_second": 2.02, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006834686031610423, | |
| "grad_norm": 0.09447265416383743, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010252029047415635, | |
| "grad_norm": 0.10480182617902756, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.9556, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013669372063220846, | |
| "grad_norm": 0.11258616298437119, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.9728, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01708671507902606, | |
| "grad_norm": 0.12434285879135132, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0055, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02050405809483127, | |
| "grad_norm": 0.14639486372470856, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02392140111063648, | |
| "grad_norm": 0.1694047600030899, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0046, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027338744126441692, | |
| "grad_norm": 0.16869021952152252, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0154, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030756087142246903, | |
| "grad_norm": 0.1600915789604187, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.926, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03417343015805212, | |
| "grad_norm": 0.17793232202529907, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9622, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037590773173857325, | |
| "grad_norm": 0.2077552080154419, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0053, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04100811618966254, | |
| "grad_norm": 0.25057899951934814, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.9317, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04442545920546775, | |
| "grad_norm": 0.19499827921390533, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8691, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04784280222127296, | |
| "grad_norm": 0.16723503172397614, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05126014523707817, | |
| "grad_norm": 0.14489641785621643, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.054677488252883384, | |
| "grad_norm": 0.11865174770355225, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9004, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05809483126868859, | |
| "grad_norm": 0.10974455624818802, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.9666, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.061512174284493806, | |
| "grad_norm": 0.11703076958656311, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.893, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06492951730029901, | |
| "grad_norm": 0.12468042224645615, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.862, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06834686031610424, | |
| "grad_norm": 0.1354500949382782, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07176420333190944, | |
| "grad_norm": 0.14160864055156708, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.9624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07518154634771465, | |
| "grad_norm": 0.15593528747558594, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9027, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07859888936351986, | |
| "grad_norm": 0.16523024439811707, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9159, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08201623237932508, | |
| "grad_norm": 0.19258223474025726, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.921, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08543357539513029, | |
| "grad_norm": 0.3083195984363556, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08543357539513029, | |
| "eval_loss": 1.8972411155700684, | |
| "eval_runtime": 108.7731, | |
| "eval_samples_per_second": 18.129, | |
| "eval_steps_per_second": 2.271, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0888509184109355, | |
| "grad_norm": 0.10595165938138962, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8922, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0922682614267407, | |
| "grad_norm": 0.11757422983646393, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8751, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09568560444254592, | |
| "grad_norm": 0.1445239782333374, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09910294745835113, | |
| "grad_norm": 0.13264216482639313, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.908, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10252029047415634, | |
| "grad_norm": 0.12971806526184082, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.9422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10593763348996156, | |
| "grad_norm": 0.12412116676568985, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.9381, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10935497650576677, | |
| "grad_norm": 0.13017012178897858, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8708, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11277231952157198, | |
| "grad_norm": 0.12155024707317352, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9103, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11618966253737718, | |
| "grad_norm": 0.12652578949928284, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.9216, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1196070055531824, | |
| "grad_norm": 0.13414131104946136, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8772, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12302434856898761, | |
| "grad_norm": 0.16717028617858887, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8883, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12644169158479282, | |
| "grad_norm": 0.19632896780967712, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.877, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12985903460059803, | |
| "grad_norm": 0.09393993020057678, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7997, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13327637761640324, | |
| "grad_norm": 0.0870269238948822, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.8741, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13669372063220847, | |
| "grad_norm": 0.09241853654384613, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8601, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14011106364801368, | |
| "grad_norm": 0.09979937970638275, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.891, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14352840666381889, | |
| "grad_norm": 0.10324066132307053, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.9562, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1469457496796241, | |
| "grad_norm": 0.10628210008144379, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.9238, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1503630926954293, | |
| "grad_norm": 0.1087057814002037, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8855, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1537804357112345, | |
| "grad_norm": 0.11976548284292221, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.8984, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15719777872703972, | |
| "grad_norm": 0.13553528487682343, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9285, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16061512174284495, | |
| "grad_norm": 0.13018624484539032, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.9068, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16403246475865016, | |
| "grad_norm": 0.14239846169948578, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9332, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16744980777445537, | |
| "grad_norm": 0.1821918785572052, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.923, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17086715079026057, | |
| "grad_norm": 0.28308120369911194, | |
| "learning_rate": 0.0, | |
| "loss": 1.8405, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17086715079026057, | |
| "eval_loss": 1.8900460004806519, | |
| "eval_runtime": 106.1673, | |
| "eval_samples_per_second": 18.574, | |
| "eval_steps_per_second": 2.327, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |