| { | |
| "best_metric": 11.832261085510254, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09005966452774963, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018011932905549926, | |
| "grad_norm": 0.4836229085922241, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018011932905549926, | |
| "eval_loss": 11.944238662719727, | |
| "eval_runtime": 29.629, | |
| "eval_samples_per_second": 126.228, | |
| "eval_steps_per_second": 15.795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003602386581109985, | |
| "grad_norm": 0.4692229926586151, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9448, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005403579871664978, | |
| "grad_norm": 0.4656652510166168, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00720477316221997, | |
| "grad_norm": 0.47113367915153503, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9406, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009005966452774964, | |
| "grad_norm": 0.49717453122138977, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.935, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010807159743329957, | |
| "grad_norm": 0.4713899493217468, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.93, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01260835303388495, | |
| "grad_norm": 0.49840787053108215, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01440954632443994, | |
| "grad_norm": 0.4253399968147278, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9331, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016210739614994935, | |
| "grad_norm": 0.4758889377117157, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018011932905549928, | |
| "grad_norm": 0.47827309370040894, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9184, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01981312619610492, | |
| "grad_norm": 0.4822375774383545, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9224, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021614319486659914, | |
| "grad_norm": 0.4610523283481598, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9071, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023415512777214906, | |
| "grad_norm": 0.40992528200149536, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9184, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0252167060677699, | |
| "grad_norm": 0.426434189081192, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9042, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02701789935832489, | |
| "grad_norm": 0.44922393560409546, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.8979, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02881909264887988, | |
| "grad_norm": 0.5032673478126526, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.8922, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.030620285939434874, | |
| "grad_norm": 0.5120476484298706, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.8911, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03242147922998987, | |
| "grad_norm": 0.5485901236534119, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.8884, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03422267252054486, | |
| "grad_norm": 0.5173953175544739, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.8938, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.036023865811099856, | |
| "grad_norm": 0.5765029191970825, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.8828, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.037825059101654845, | |
| "grad_norm": 0.6179419159889221, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.8809, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03962625239220984, | |
| "grad_norm": 0.5752896070480347, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.8891, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04142744568276483, | |
| "grad_norm": 0.6997311115264893, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.8762, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04322863897331983, | |
| "grad_norm": 0.6879186630249023, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.8733, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04502983226387482, | |
| "grad_norm": 0.654765248298645, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.8922, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04502983226387482, | |
| "eval_loss": 11.866266250610352, | |
| "eval_runtime": 38.7127, | |
| "eval_samples_per_second": 96.609, | |
| "eval_steps_per_second": 12.089, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04683102555442981, | |
| "grad_norm": 0.6474030017852783, | |
| "learning_rate": 5e-05, | |
| "loss": 11.8627, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 0.6563072204589844, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.8594, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0504334121355398, | |
| "grad_norm": 0.6200706362724304, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.8628, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05223460542609479, | |
| "grad_norm": 0.7235188484191895, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.8635, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05403579871664978, | |
| "grad_norm": 0.7191481590270996, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.8525, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05583699200720477, | |
| "grad_norm": 0.6996354460716248, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.8521, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05763818529775976, | |
| "grad_norm": 0.6822149753570557, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.8534, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05943937858831476, | |
| "grad_norm": 0.7697290182113647, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.8328, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06124057187886975, | |
| "grad_norm": 0.7364133596420288, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.8511, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06304176516942474, | |
| "grad_norm": 0.8046404719352722, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.8493, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06484295845997974, | |
| "grad_norm": 0.7927674651145935, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.8398, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06664415175053473, | |
| "grad_norm": 0.7487473487854004, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.85, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06844534504108972, | |
| "grad_norm": 0.8775519132614136, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.8442, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07024653833164471, | |
| "grad_norm": 0.8876802921295166, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.8308, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07204773162219971, | |
| "grad_norm": 0.7719692587852478, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.8375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0738489249127547, | |
| "grad_norm": 0.7725573182106018, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.8272, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07565011820330969, | |
| "grad_norm": 0.8153325319290161, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.8334, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07745131149386468, | |
| "grad_norm": 0.7966391444206238, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.8349, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07925250478441968, | |
| "grad_norm": 0.8197851181030273, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.8284, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08105369807497467, | |
| "grad_norm": 0.7913408279418945, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.8388, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08285489136552966, | |
| "grad_norm": 0.8576236963272095, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.8242, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08465608465608465, | |
| "grad_norm": 0.8047311902046204, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.8493, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08645727794663965, | |
| "grad_norm": 0.662825882434845, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.8526, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08825847123719464, | |
| "grad_norm": 0.8610819578170776, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.832, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09005966452774963, | |
| "grad_norm": 0.7742445468902588, | |
| "learning_rate": 0.0, | |
| "loss": 11.8454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09005966452774963, | |
| "eval_loss": 11.832261085510254, | |
| "eval_runtime": 15.1468, | |
| "eval_samples_per_second": 246.917, | |
| "eval_steps_per_second": 30.898, | |
| "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": 417735062323200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |