| { | |
| "best_metric": 0.09452027827501297, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5590496156533893, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011180992313067784, | |
| "grad_norm": 6.014316558837891, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011180992313067784, | |
| "eval_loss": 10.163934707641602, | |
| "eval_runtime": 32.1765, | |
| "eval_samples_per_second": 18.74, | |
| "eval_steps_per_second": 2.362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02236198462613557, | |
| "grad_norm": 6.439102649688721, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9731, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033542976939203356, | |
| "grad_norm": 6.967215061187744, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.4958, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04472396925227114, | |
| "grad_norm": 7.505433082580566, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.8178, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.055904961565338925, | |
| "grad_norm": 8.909493446350098, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.6003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06708595387840671, | |
| "grad_norm": 12.524182319641113, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.1761, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07826694619147449, | |
| "grad_norm": 6.86476993560791, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1079, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08944793850454227, | |
| "grad_norm": 10.740727424621582, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7838, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10062893081761007, | |
| "grad_norm": 5.934417247772217, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.3456, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11180992313067785, | |
| "grad_norm": 12.906644821166992, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.637, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12299091544374563, | |
| "grad_norm": 3.0609428882598877, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2706, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13417190775681342, | |
| "grad_norm": 1.5875135660171509, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1453529000698812, | |
| "grad_norm": 4.589207172393799, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5825, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15653389238294899, | |
| "grad_norm": 4.4860687255859375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16771488469601678, | |
| "grad_norm": 5.661064624786377, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17889587700908455, | |
| "grad_norm": 8.47767448425293, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3519, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19007686932215234, | |
| "grad_norm": 4.212504863739014, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20125786163522014, | |
| "grad_norm": 10.1459379196167, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3296, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2124388539482879, | |
| "grad_norm": 5.815060615539551, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2287, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2236198462613557, | |
| "grad_norm": 3.6872353553771973, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2348008385744235, | |
| "grad_norm": 3.417405605316162, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24598183088749126, | |
| "grad_norm": 0.8942554593086243, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1196, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25716282320055905, | |
| "grad_norm": 0.7683413624763489, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26834381551362685, | |
| "grad_norm": 1.0292158126831055, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27952480782669464, | |
| "grad_norm": 0.9193266034126282, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27952480782669464, | |
| "eval_loss": 0.22263145446777344, | |
| "eval_runtime": 69.6363, | |
| "eval_samples_per_second": 8.659, | |
| "eval_steps_per_second": 1.091, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2907058001397624, | |
| "grad_norm": 5.87585973739624, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5248, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 4.513538360595703, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3769, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31306778476589797, | |
| "grad_norm": 2.861530065536499, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2658, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32424877707896577, | |
| "grad_norm": 0.7928971648216248, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1659, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33542976939203356, | |
| "grad_norm": 1.8722455501556396, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3466107617051013, | |
| "grad_norm": 2.7152228355407715, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1319, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3577917540181691, | |
| "grad_norm": 2.2692229747772217, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1242, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3689727463312369, | |
| "grad_norm": 0.5245362520217896, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0629, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3801537386443047, | |
| "grad_norm": 1.132564902305603, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0908, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3913347309573725, | |
| "grad_norm": 1.2288964986801147, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0981, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4025157232704403, | |
| "grad_norm": 0.7781267762184143, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0663, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.413696715583508, | |
| "grad_norm": 0.3532390892505646, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0344, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4248777078965758, | |
| "grad_norm": 0.6690967082977295, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1157, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4360587002096436, | |
| "grad_norm": 1.3647629022598267, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2326, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4472396925227114, | |
| "grad_norm": 0.9862391948699951, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4584206848357792, | |
| "grad_norm": 1.4872350692749023, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1551, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.469601677148847, | |
| "grad_norm": 1.287073016166687, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1289, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4807826694619147, | |
| "grad_norm": 0.897722601890564, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0894, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4919636617749825, | |
| "grad_norm": 0.5648239850997925, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0794, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "grad_norm": 0.7147127389907837, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0481, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5143256464011181, | |
| "grad_norm": 0.3847064971923828, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0593, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5255066387141859, | |
| "grad_norm": 0.7142338752746582, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0618, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5366876310272537, | |
| "grad_norm": 0.399740070104599, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0515, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5478686233403215, | |
| "grad_norm": 1.3028299808502197, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0517, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5590496156533893, | |
| "grad_norm": 2.2355709075927734, | |
| "learning_rate": 0.0, | |
| "loss": 0.0565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5590496156533893, | |
| "eval_loss": 0.09452027827501297, | |
| "eval_runtime": 32.1913, | |
| "eval_samples_per_second": 18.732, | |
| "eval_steps_per_second": 2.361, | |
| "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 | |
| } | |