{ "best_metric": 0.8705747127532959, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.2635046113306983, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005270092226613966, "grad_norm": 10.324965476989746, "learning_rate": 5e-05, "loss": 20.2502, "step": 1 }, { "epoch": 0.005270092226613966, "eval_loss": 1.2747288942337036, "eval_runtime": 99.2994, "eval_samples_per_second": 12.87, "eval_steps_per_second": 1.611, "step": 1 }, { "epoch": 0.010540184453227932, "grad_norm": 9.909070014953613, "learning_rate": 0.0001, "loss": 21.298, "step": 2 }, { "epoch": 0.015810276679841896, "grad_norm": 9.973806381225586, "learning_rate": 9.989294616193017e-05, "loss": 21.1651, "step": 3 }, { "epoch": 0.021080368906455864, "grad_norm": 7.567232131958008, "learning_rate": 9.957224306869053e-05, "loss": 20.472, "step": 4 }, { "epoch": 0.026350461133069828, "grad_norm": 5.911794185638428, "learning_rate": 9.903926402016153e-05, "loss": 20.0485, "step": 5 }, { "epoch": 0.03162055335968379, "grad_norm": 5.7655205726623535, "learning_rate": 9.829629131445342e-05, "loss": 17.7948, "step": 6 }, { "epoch": 0.03689064558629776, "grad_norm": 5.374915599822998, "learning_rate": 9.73465064747553e-05, "loss": 15.4831, "step": 7 }, { "epoch": 0.04216073781291173, "grad_norm": 4.3298821449279785, "learning_rate": 9.619397662556435e-05, "loss": 14.8715, "step": 8 }, { "epoch": 0.04743083003952569, "grad_norm": 4.3553643226623535, "learning_rate": 9.484363707663442e-05, "loss": 14.4571, "step": 9 }, { "epoch": 0.052700922266139656, "grad_norm": 4.488785266876221, "learning_rate": 9.330127018922194e-05, "loss": 14.4374, "step": 10 }, { "epoch": 0.057971014492753624, "grad_norm": 5.779847621917725, "learning_rate": 9.157348061512727e-05, "loss": 14.4675, "step": 11 }, { "epoch": 0.06324110671936758, "grad_norm": 5.094208717346191, "learning_rate": 8.966766701456177e-05, "loss": 15.4172, "step": 12 }, { "epoch": 0.06851119894598155, "grad_norm": 8.054232597351074, "learning_rate": 8.759199037394887e-05, "loss": 15.6023, "step": 13 }, { "epoch": 0.07378129117259552, "grad_norm": 8.434983253479004, "learning_rate": 8.535533905932738e-05, "loss": 15.8352, "step": 14 }, { "epoch": 0.07905138339920949, "grad_norm": 5.801580429077148, "learning_rate": 8.296729075500344e-05, "loss": 16.2017, "step": 15 }, { "epoch": 0.08432147562582346, "grad_norm": 5.0842509269714355, "learning_rate": 8.043807145043604e-05, "loss": 16.3074, "step": 16 }, { "epoch": 0.08959156785243742, "grad_norm": 4.890789031982422, "learning_rate": 7.777851165098012e-05, "loss": 16.5253, "step": 17 }, { "epoch": 0.09486166007905138, "grad_norm": 5.724118709564209, "learning_rate": 7.500000000000001e-05, "loss": 16.0264, "step": 18 }, { "epoch": 0.10013175230566534, "grad_norm": 3.7091915607452393, "learning_rate": 7.211443451095007e-05, "loss": 14.0671, "step": 19 }, { "epoch": 0.10540184453227931, "grad_norm": 3.7077553272247314, "learning_rate": 6.91341716182545e-05, "loss": 13.2983, "step": 20 }, { "epoch": 0.11067193675889328, "grad_norm": 3.371248483657837, "learning_rate": 6.607197326515808e-05, "loss": 13.469, "step": 21 }, { "epoch": 0.11594202898550725, "grad_norm": 3.0618107318878174, "learning_rate": 6.294095225512603e-05, "loss": 13.3668, "step": 22 }, { "epoch": 0.12121212121212122, "grad_norm": 3.0709140300750732, "learning_rate": 5.9754516100806423e-05, "loss": 13.7794, "step": 23 }, { "epoch": 0.12648221343873517, "grad_norm": 3.5011112689971924, "learning_rate": 5.6526309611002594e-05, "loss": 13.6792, "step": 24 }, { "epoch": 0.13175230566534915, "grad_norm": 4.160451412200928, "learning_rate": 5.327015646150716e-05, "loss": 14.3606, "step": 25 }, { "epoch": 0.13175230566534915, "eval_loss": 0.9058130383491516, "eval_runtime": 99.7144, "eval_samples_per_second": 12.817, "eval_steps_per_second": 1.605, "step": 25 }, { "epoch": 0.1370223978919631, "grad_norm": 6.496657371520996, "learning_rate": 5e-05, "loss": 14.1128, "step": 26 }, { "epoch": 0.1422924901185771, "grad_norm": 6.763591289520264, "learning_rate": 4.6729843538492847e-05, "loss": 15.1578, "step": 27 }, { "epoch": 0.14756258234519104, "grad_norm": 6.154540538787842, "learning_rate": 4.347369038899744e-05, "loss": 14.8887, "step": 28 }, { "epoch": 0.152832674571805, "grad_norm": 5.286479949951172, "learning_rate": 4.0245483899193595e-05, "loss": 15.2464, "step": 29 }, { "epoch": 0.15810276679841898, "grad_norm": 4.394895553588867, "learning_rate": 3.705904774487396e-05, "loss": 15.6726, "step": 30 }, { "epoch": 0.16337285902503293, "grad_norm": 3.7572078704833984, "learning_rate": 3.392802673484193e-05, "loss": 14.6112, "step": 31 }, { "epoch": 0.1686429512516469, "grad_norm": 4.391316890716553, "learning_rate": 3.086582838174551e-05, "loss": 12.8835, "step": 32 }, { "epoch": 0.17391304347826086, "grad_norm": 4.463949680328369, "learning_rate": 2.7885565489049946e-05, "loss": 12.9088, "step": 33 }, { "epoch": 0.17918313570487485, "grad_norm": 3.8616714477539062, "learning_rate": 2.500000000000001e-05, "loss": 13.0846, "step": 34 }, { "epoch": 0.1844532279314888, "grad_norm": 4.396023750305176, "learning_rate": 2.2221488349019903e-05, "loss": 13.2153, "step": 35 }, { "epoch": 0.18972332015810275, "grad_norm": 4.106069564819336, "learning_rate": 1.9561928549563968e-05, "loss": 13.286, "step": 36 }, { "epoch": 0.19499341238471674, "grad_norm": 4.250127792358398, "learning_rate": 1.703270924499656e-05, "loss": 13.9948, "step": 37 }, { "epoch": 0.2002635046113307, "grad_norm": 3.1949825286865234, "learning_rate": 1.4644660940672627e-05, "loss": 14.2964, "step": 38 }, { "epoch": 0.20553359683794467, "grad_norm": 3.5179386138916016, "learning_rate": 1.2408009626051137e-05, "loss": 14.2741, "step": 39 }, { "epoch": 0.21080368906455862, "grad_norm": 4.0739970207214355, "learning_rate": 1.0332332985438248e-05, "loss": 14.7172, "step": 40 }, { "epoch": 0.2160737812911726, "grad_norm": 4.186811447143555, "learning_rate": 8.426519384872733e-06, "loss": 15.4209, "step": 41 }, { "epoch": 0.22134387351778656, "grad_norm": 4.2096452713012695, "learning_rate": 6.698729810778065e-06, "loss": 15.429, "step": 42 }, { "epoch": 0.22661396574440051, "grad_norm": 4.489388465881348, "learning_rate": 5.156362923365588e-06, "loss": 15.578, "step": 43 }, { "epoch": 0.2318840579710145, "grad_norm": 3.9326608180999756, "learning_rate": 3.8060233744356633e-06, "loss": 13.0144, "step": 44 }, { "epoch": 0.23715415019762845, "grad_norm": 3.543126106262207, "learning_rate": 2.653493525244721e-06, "loss": 13.1908, "step": 45 }, { "epoch": 0.24242424242424243, "grad_norm": 2.9515583515167236, "learning_rate": 1.70370868554659e-06, "loss": 12.4912, "step": 46 }, { "epoch": 0.24769433465085638, "grad_norm": 2.6371042728424072, "learning_rate": 9.607359798384785e-07, "loss": 13.0061, "step": 47 }, { "epoch": 0.25296442687747034, "grad_norm": 2.5240566730499268, "learning_rate": 4.277569313094809e-07, "loss": 13.5621, "step": 48 }, { "epoch": 0.25823451910408435, "grad_norm": 3.0576345920562744, "learning_rate": 1.0705383806982606e-07, "loss": 13.9055, "step": 49 }, { "epoch": 0.2635046113306983, "grad_norm": 3.395519971847534, "learning_rate": 0.0, "loss": 13.8772, "step": 50 }, { "epoch": 0.2635046113306983, "eval_loss": 0.8705747127532959, "eval_runtime": 100.1532, "eval_samples_per_second": 12.76, "eval_steps_per_second": 1.598, "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": 7.873865919150162e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }