| { | |
| "best_metric": 0.1474180370569229, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4303388918773534, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008606777837547068, | |
| "grad_norm": 5.814489364624023, | |
| "learning_rate": 5e-05, | |
| "loss": 14.3715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008606777837547068, | |
| "eval_loss": 14.403732299804688, | |
| "eval_runtime": 41.7706, | |
| "eval_samples_per_second": 18.745, | |
| "eval_steps_per_second": 2.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017213555675094135, | |
| "grad_norm": 5.941817283630371, | |
| "learning_rate": 0.0001, | |
| "loss": 14.4735, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025820333512641205, | |
| "grad_norm": 6.171922206878662, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 14.3683, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03442711135018827, | |
| "grad_norm": 7.644290447235107, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 12.9919, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04303388918773534, | |
| "grad_norm": 8.061711311340332, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.9351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05164066702528241, | |
| "grad_norm": 8.332938194274902, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 8.9269, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06024744486282948, | |
| "grad_norm": 9.02269172668457, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 7.3836, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06885422270037654, | |
| "grad_norm": 10.347013473510742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.6498, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07746100053792361, | |
| "grad_norm": 9.94497299194336, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.7987, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08606777837547068, | |
| "grad_norm": 9.184467315673828, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2879, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09467455621301775, | |
| "grad_norm": 6.1321330070495605, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9545, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10328133405056482, | |
| "grad_norm": 2.657087802886963, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 2.4808380603790283, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12049488972565896, | |
| "grad_norm": 1.52351713180542, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2603, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.129101667563206, | |
| "grad_norm": 1.8346631526947021, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2488, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13770844540075308, | |
| "grad_norm": 1.2056642770767212, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2372, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14631522323830015, | |
| "grad_norm": 1.5382812023162842, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2179, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15492200107584722, | |
| "grad_norm": 2.6922852993011475, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2249, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1635287789133943, | |
| "grad_norm": 3.349630117416382, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2289, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17213555675094136, | |
| "grad_norm": 0.883138120174408, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18074233458848843, | |
| "grad_norm": 2.308549165725708, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1986, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1893491124260355, | |
| "grad_norm": 1.3709138631820679, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1763, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19795589026358257, | |
| "grad_norm": 2.6249375343322754, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1874, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20656266810112964, | |
| "grad_norm": 2.1404147148132324, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1705, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2151694459386767, | |
| "grad_norm": 2.190812587738037, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1771, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2151694459386767, | |
| "eval_loss": 0.17070253193378448, | |
| "eval_runtime": 41.7261, | |
| "eval_samples_per_second": 18.765, | |
| "eval_steps_per_second": 2.349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22377622377622378, | |
| "grad_norm": 1.3157997131347656, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1844, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23238300161377085, | |
| "grad_norm": 1.5786244869232178, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1856, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24098977945131791, | |
| "grad_norm": 1.4797031879425049, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1923, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24959655728886498, | |
| "grad_norm": 1.3135018348693848, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1545, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.258203335126412, | |
| "grad_norm": 0.7757309079170227, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2668101129639591, | |
| "grad_norm": 0.3259675204753876, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1615, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27541689080150616, | |
| "grad_norm": 0.931290328502655, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1578, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28402366863905326, | |
| "grad_norm": 0.6277098059654236, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.169, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2926304464766003, | |
| "grad_norm": 0.8366173505783081, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1595, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3012372243141474, | |
| "grad_norm": 0.5190151929855347, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1427, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30984400215169444, | |
| "grad_norm": 0.6579331755638123, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1588, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31845077998924154, | |
| "grad_norm": 0.419669508934021, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1486, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3270575578267886, | |
| "grad_norm": 1.265913486480713, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2152, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3356643356643357, | |
| "grad_norm": 0.9634343385696411, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.16, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3442711135018827, | |
| "grad_norm": 1.310472011566162, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3528778913394298, | |
| "grad_norm": 1.4859728813171387, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1651, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.36148466917697686, | |
| "grad_norm": 0.327387273311615, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1324, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37009144701452396, | |
| "grad_norm": 0.47807979583740234, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1191, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.378698224852071, | |
| "grad_norm": 0.46331387758255005, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1532, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3873050026896181, | |
| "grad_norm": 0.4438972473144531, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1326, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39591178052716514, | |
| "grad_norm": 0.9701945781707764, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1572, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40451855836471223, | |
| "grad_norm": 0.7769740223884583, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.155, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4131253362022593, | |
| "grad_norm": 0.9505748152732849, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1522, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42173211403980637, | |
| "grad_norm": 2.1793980598449707, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1555, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4303388918773534, | |
| "grad_norm": 2.068118095397949, | |
| "learning_rate": 0.0, | |
| "loss": 0.1583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4303388918773534, | |
| "eval_loss": 0.1474180370569229, | |
| "eval_runtime": 41.7113, | |
| "eval_samples_per_second": 18.772, | |
| "eval_steps_per_second": 2.349, | |
| "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": 1.1111570021023744e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |