{ "best_metric": 1.5220385789871216, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.7525870178739417, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.015051740357478834, "grad_norm": 0.30326592922210693, "learning_rate": 5e-05, "loss": 1.876, "step": 1 }, { "epoch": 0.015051740357478834, "eval_loss": 1.6819216012954712, "eval_runtime": 4.7078, "eval_samples_per_second": 95.162, "eval_steps_per_second": 11.895, "step": 1 }, { "epoch": 0.030103480714957668, "grad_norm": 0.3032293915748596, "learning_rate": 0.0001, "loss": 1.7408, "step": 2 }, { "epoch": 0.045155221072436504, "grad_norm": 0.2913106083869934, "learning_rate": 9.989294616193017e-05, "loss": 1.7145, "step": 3 }, { "epoch": 0.060206961429915336, "grad_norm": 0.29114338755607605, "learning_rate": 9.957224306869053e-05, "loss": 1.7157, "step": 4 }, { "epoch": 0.07525870178739416, "grad_norm": 0.25170594453811646, "learning_rate": 9.903926402016153e-05, "loss": 1.7058, "step": 5 }, { "epoch": 0.09031044214487301, "grad_norm": 0.2432847023010254, "learning_rate": 9.829629131445342e-05, "loss": 1.6263, "step": 6 }, { "epoch": 0.10536218250235184, "grad_norm": 0.25478658080101013, "learning_rate": 9.73465064747553e-05, "loss": 1.6168, "step": 7 }, { "epoch": 0.12041392285983067, "grad_norm": 0.2547207176685333, "learning_rate": 9.619397662556435e-05, "loss": 1.5653, "step": 8 }, { "epoch": 0.1354656632173095, "grad_norm": 0.26701080799102783, "learning_rate": 9.484363707663442e-05, "loss": 1.6024, "step": 9 }, { "epoch": 0.15051740357478832, "grad_norm": 0.24688668549060822, "learning_rate": 9.330127018922194e-05, "loss": 1.5483, "step": 10 }, { "epoch": 0.16556914393226718, "grad_norm": 0.2912991940975189, "learning_rate": 9.157348061512727e-05, "loss": 1.5695, "step": 11 }, { "epoch": 0.18062088428974601, "grad_norm": 0.2975776791572571, "learning_rate": 8.966766701456177e-05, "loss": 1.5117, "step": 12 }, { "epoch": 0.19567262464722485, "grad_norm": 0.43362241983413696, "learning_rate": 8.759199037394887e-05, "loss": 1.8688, "step": 13 }, { "epoch": 0.21072436500470368, "grad_norm": 0.2660374343395233, "learning_rate": 8.535533905932738e-05, "loss": 1.6419, "step": 14 }, { "epoch": 0.2257761053621825, "grad_norm": 0.27868446707725525, "learning_rate": 8.296729075500344e-05, "loss": 1.6567, "step": 15 }, { "epoch": 0.24082784571966134, "grad_norm": 0.24767255783081055, "learning_rate": 8.043807145043604e-05, "loss": 1.6327, "step": 16 }, { "epoch": 0.2558795860771402, "grad_norm": 0.20685794949531555, "learning_rate": 7.777851165098012e-05, "loss": 1.5901, "step": 17 }, { "epoch": 0.270931326434619, "grad_norm": 0.1982223391532898, "learning_rate": 7.500000000000001e-05, "loss": 1.5787, "step": 18 }, { "epoch": 0.28598306679209784, "grad_norm": 0.22436381876468658, "learning_rate": 7.211443451095007e-05, "loss": 1.5481, "step": 19 }, { "epoch": 0.30103480714957664, "grad_norm": 0.2219945639371872, "learning_rate": 6.91341716182545e-05, "loss": 1.567, "step": 20 }, { "epoch": 0.3160865475070555, "grad_norm": 0.23472419381141663, "learning_rate": 6.607197326515808e-05, "loss": 1.5435, "step": 21 }, { "epoch": 0.33113828786453436, "grad_norm": 0.23438289761543274, "learning_rate": 6.294095225512603e-05, "loss": 1.5091, "step": 22 }, { "epoch": 0.34619002822201317, "grad_norm": 0.25232580304145813, "learning_rate": 5.9754516100806423e-05, "loss": 1.4863, "step": 23 }, { "epoch": 0.36124176857949203, "grad_norm": 0.25499510765075684, "learning_rate": 5.6526309611002594e-05, "loss": 1.4608, "step": 24 }, { "epoch": 0.37629350893697083, "grad_norm": 0.28822219371795654, "learning_rate": 5.327015646150716e-05, "loss": 1.4807, "step": 25 }, { "epoch": 0.37629350893697083, "eval_loss": 1.5451337099075317, "eval_runtime": 4.7983, "eval_samples_per_second": 93.367, "eval_steps_per_second": 11.671, "step": 25 }, { "epoch": 0.3913452492944497, "grad_norm": 0.28296566009521484, "learning_rate": 5e-05, "loss": 1.7819, "step": 26 }, { "epoch": 0.4063969896519285, "grad_norm": 0.20274849236011505, "learning_rate": 4.6729843538492847e-05, "loss": 1.5794, "step": 27 }, { "epoch": 0.42144873000940736, "grad_norm": 0.21083898842334747, "learning_rate": 4.347369038899744e-05, "loss": 1.6308, "step": 28 }, { "epoch": 0.43650047036688616, "grad_norm": 0.22384609282016754, "learning_rate": 4.0245483899193595e-05, "loss": 1.5835, "step": 29 }, { "epoch": 0.451552210724365, "grad_norm": 0.21215800940990448, "learning_rate": 3.705904774487396e-05, "loss": 1.5756, "step": 30 }, { "epoch": 0.4666039510818438, "grad_norm": 0.21465682983398438, "learning_rate": 3.392802673484193e-05, "loss": 1.5461, "step": 31 }, { "epoch": 0.4816556914393227, "grad_norm": 0.22286632657051086, "learning_rate": 3.086582838174551e-05, "loss": 1.5307, "step": 32 }, { "epoch": 0.4967074317968015, "grad_norm": 0.20866183936595917, "learning_rate": 2.7885565489049946e-05, "loss": 1.5032, "step": 33 }, { "epoch": 0.5117591721542804, "grad_norm": 0.20444150269031525, "learning_rate": 2.500000000000001e-05, "loss": 1.5325, "step": 34 }, { "epoch": 0.5268109125117592, "grad_norm": 0.22169455885887146, "learning_rate": 2.2221488349019903e-05, "loss": 1.4898, "step": 35 }, { "epoch": 0.541862652869238, "grad_norm": 0.23709993064403534, "learning_rate": 1.9561928549563968e-05, "loss": 1.4526, "step": 36 }, { "epoch": 0.5569143932267169, "grad_norm": 0.24914033710956573, "learning_rate": 1.703270924499656e-05, "loss": 1.4486, "step": 37 }, { "epoch": 0.5719661335841957, "grad_norm": 0.35478338599205017, "learning_rate": 1.4644660940672627e-05, "loss": 1.7652, "step": 38 }, { "epoch": 0.5870178739416745, "grad_norm": 0.23298819363117218, "learning_rate": 1.2408009626051137e-05, "loss": 1.5998, "step": 39 }, { "epoch": 0.6020696142991533, "grad_norm": 0.20077332854270935, "learning_rate": 1.0332332985438248e-05, "loss": 1.6111, "step": 40 }, { "epoch": 0.6171213546566322, "grad_norm": 0.21949784457683563, "learning_rate": 8.426519384872733e-06, "loss": 1.5686, "step": 41 }, { "epoch": 0.632173095014111, "grad_norm": 0.19444361329078674, "learning_rate": 6.698729810778065e-06, "loss": 1.5757, "step": 42 }, { "epoch": 0.6472248353715898, "grad_norm": 0.21272796392440796, "learning_rate": 5.156362923365588e-06, "loss": 1.5291, "step": 43 }, { "epoch": 0.6622765757290687, "grad_norm": 0.20493632555007935, "learning_rate": 3.8060233744356633e-06, "loss": 1.4783, "step": 44 }, { "epoch": 0.6773283160865475, "grad_norm": 0.2022678703069687, "learning_rate": 2.653493525244721e-06, "loss": 1.452, "step": 45 }, { "epoch": 0.6923800564440263, "grad_norm": 0.20927464962005615, "learning_rate": 1.70370868554659e-06, "loss": 1.5121, "step": 46 }, { "epoch": 0.7074317968015051, "grad_norm": 0.22144973278045654, "learning_rate": 9.607359798384785e-07, "loss": 1.4493, "step": 47 }, { "epoch": 0.7224835371589841, "grad_norm": 0.2366451472043991, "learning_rate": 4.277569313094809e-07, "loss": 1.4798, "step": 48 }, { "epoch": 0.7375352775164629, "grad_norm": 0.25476348400115967, "learning_rate": 1.0705383806982606e-07, "loss": 1.4312, "step": 49 }, { "epoch": 0.7525870178739417, "grad_norm": 0.30742359161376953, "learning_rate": 0.0, "loss": 1.4504, "step": 50 }, { "epoch": 0.7525870178739417, "eval_loss": 1.5220385789871216, "eval_runtime": 4.6057, "eval_samples_per_second": 97.271, "eval_steps_per_second": 12.159, "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": 8.672739346874368e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }