{ "best_metric": 11.9196138381958, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.5444015444015444, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03088803088803089, "grad_norm": 0.06109972670674324, "learning_rate": 5e-05, "loss": 11.9221, "step": 1 }, { "epoch": 0.03088803088803089, "eval_loss": 11.928597450256348, "eval_runtime": 0.828, "eval_samples_per_second": 264.478, "eval_steps_per_second": 33.814, "step": 1 }, { "epoch": 0.06177606177606178, "grad_norm": 0.07205282151699066, "learning_rate": 0.0001, "loss": 11.926, "step": 2 }, { "epoch": 0.09266409266409266, "grad_norm": 0.0648089349269867, "learning_rate": 9.989294616193017e-05, "loss": 11.9224, "step": 3 }, { "epoch": 0.12355212355212356, "grad_norm": 0.08991728723049164, "learning_rate": 9.957224306869053e-05, "loss": 11.9314, "step": 4 }, { "epoch": 0.15444015444015444, "grad_norm": 0.10385900735855103, "learning_rate": 9.903926402016153e-05, "loss": 11.9305, "step": 5 }, { "epoch": 0.18532818532818532, "grad_norm": 0.08745633810758591, "learning_rate": 9.829629131445342e-05, "loss": 11.9325, "step": 6 }, { "epoch": 0.21621621621621623, "grad_norm": 0.09449993818998337, "learning_rate": 9.73465064747553e-05, "loss": 11.9301, "step": 7 }, { "epoch": 0.2471042471042471, "grad_norm": 0.11885674297809601, "learning_rate": 9.619397662556435e-05, "loss": 11.9337, "step": 8 }, { "epoch": 0.277992277992278, "grad_norm": 0.061852987855672836, "learning_rate": 9.484363707663442e-05, "loss": 11.9292, "step": 9 }, { "epoch": 0.3088803088803089, "grad_norm": 0.05906722694635391, "learning_rate": 9.330127018922194e-05, "loss": 11.9272, "step": 10 }, { "epoch": 0.33976833976833976, "grad_norm": 0.06637009233236313, "learning_rate": 9.157348061512727e-05, "loss": 11.9279, "step": 11 }, { "epoch": 0.37065637065637064, "grad_norm": 0.08344832062721252, "learning_rate": 8.966766701456177e-05, "loss": 11.9264, "step": 12 }, { "epoch": 0.4015444015444015, "grad_norm": 0.09188637137413025, "learning_rate": 8.759199037394887e-05, "loss": 11.9299, "step": 13 }, { "epoch": 0.43243243243243246, "grad_norm": 0.10101278871297836, "learning_rate": 8.535533905932738e-05, "loss": 11.9287, "step": 14 }, { "epoch": 0.46332046332046334, "grad_norm": 0.11991675198078156, "learning_rate": 8.296729075500344e-05, "loss": 11.9296, "step": 15 }, { "epoch": 0.4942084942084942, "grad_norm": 0.12269867956638336, "learning_rate": 8.043807145043604e-05, "loss": 11.9358, "step": 16 }, { "epoch": 0.525096525096525, "grad_norm": 0.06880807876586914, "learning_rate": 7.777851165098012e-05, "loss": 11.9237, "step": 17 }, { "epoch": 0.555984555984556, "grad_norm": 0.0790449008345604, "learning_rate": 7.500000000000001e-05, "loss": 11.9237, "step": 18 }, { "epoch": 0.5868725868725869, "grad_norm": 0.07787377387285233, "learning_rate": 7.211443451095007e-05, "loss": 11.927, "step": 19 }, { "epoch": 0.6177606177606177, "grad_norm": 0.10630682855844498, "learning_rate": 6.91341716182545e-05, "loss": 11.9244, "step": 20 }, { "epoch": 0.6486486486486487, "grad_norm": 0.1050586923956871, "learning_rate": 6.607197326515808e-05, "loss": 11.9249, "step": 21 }, { "epoch": 0.6795366795366795, "grad_norm": 0.12070325016975403, "learning_rate": 6.294095225512603e-05, "loss": 11.9281, "step": 22 }, { "epoch": 0.7104247104247104, "grad_norm": 0.11996880918741226, "learning_rate": 5.9754516100806423e-05, "loss": 11.9255, "step": 23 }, { "epoch": 0.7413127413127413, "grad_norm": 0.16234727203845978, "learning_rate": 5.6526309611002594e-05, "loss": 11.9262, "step": 24 }, { "epoch": 0.7722007722007722, "grad_norm": 0.07762131094932556, "learning_rate": 5.327015646150716e-05, "loss": 11.9224, "step": 25 }, { "epoch": 0.7722007722007722, "eval_loss": 11.924177169799805, "eval_runtime": 0.7805, "eval_samples_per_second": 280.597, "eval_steps_per_second": 35.875, "step": 25 }, { "epoch": 0.803088803088803, "grad_norm": 0.07824923098087311, "learning_rate": 5e-05, "loss": 11.9248, "step": 26 }, { "epoch": 0.833976833976834, "grad_norm": 0.1009729653596878, "learning_rate": 4.6729843538492847e-05, "loss": 11.9261, "step": 27 }, { "epoch": 0.8648648648648649, "grad_norm": 0.12158763408660889, "learning_rate": 4.347369038899744e-05, "loss": 11.9224, "step": 28 }, { "epoch": 0.8957528957528957, "grad_norm": 0.14848434925079346, "learning_rate": 4.0245483899193595e-05, "loss": 11.9251, "step": 29 }, { "epoch": 0.9266409266409267, "grad_norm": 0.15349432826042175, "learning_rate": 3.705904774487396e-05, "loss": 11.9235, "step": 30 }, { "epoch": 0.9575289575289575, "grad_norm": 0.1826583743095398, "learning_rate": 3.392802673484193e-05, "loss": 11.9222, "step": 31 }, { "epoch": 0.9884169884169884, "grad_norm": 0.16778188943862915, "learning_rate": 3.086582838174551e-05, "loss": 11.9317, "step": 32 }, { "epoch": 1.0193050193050193, "grad_norm": 0.1833105981349945, "learning_rate": 2.7885565489049946e-05, "loss": 19.424, "step": 33 }, { "epoch": 1.05019305019305, "grad_norm": 0.0869530737400055, "learning_rate": 2.500000000000001e-05, "loss": 12.095, "step": 34 }, { "epoch": 1.0810810810810811, "grad_norm": 0.11778981238603592, "learning_rate": 2.2221488349019903e-05, "loss": 11.902, "step": 35 }, { "epoch": 1.111969111969112, "grad_norm": 0.1222325935959816, "learning_rate": 1.9561928549563968e-05, "loss": 12.3136, "step": 36 }, { "epoch": 1.1428571428571428, "grad_norm": 0.14096081256866455, "learning_rate": 1.703270924499656e-05, "loss": 11.603, "step": 37 }, { "epoch": 1.1737451737451738, "grad_norm": 0.15266837179660797, "learning_rate": 1.4644660940672627e-05, "loss": 11.896, "step": 38 }, { "epoch": 1.2046332046332047, "grad_norm": 0.15551863610744476, "learning_rate": 1.2408009626051137e-05, "loss": 11.6295, "step": 39 }, { "epoch": 1.2355212355212355, "grad_norm": 0.19857841730117798, "learning_rate": 1.0332332985438248e-05, "loss": 12.065, "step": 40 }, { "epoch": 1.2664092664092665, "grad_norm": 0.13945285975933075, "learning_rate": 8.426519384872733e-06, "loss": 11.2033, "step": 41 }, { "epoch": 1.2972972972972974, "grad_norm": 0.09375537186861038, "learning_rate": 6.698729810778065e-06, "loss": 12.0239, "step": 42 }, { "epoch": 1.3281853281853282, "grad_norm": 0.11622730642557144, "learning_rate": 5.156362923365588e-06, "loss": 13.0858, "step": 43 }, { "epoch": 1.359073359073359, "grad_norm": 0.13087835907936096, "learning_rate": 3.8060233744356633e-06, "loss": 11.6548, "step": 44 }, { "epoch": 1.3899613899613898, "grad_norm": 0.17029710114002228, "learning_rate": 2.653493525244721e-06, "loss": 11.7197, "step": 45 }, { "epoch": 1.420849420849421, "grad_norm": 0.14172868430614471, "learning_rate": 1.70370868554659e-06, "loss": 11.5624, "step": 46 }, { "epoch": 1.4517374517374517, "grad_norm": 0.16212929785251617, "learning_rate": 9.607359798384785e-07, "loss": 11.9965, "step": 47 }, { "epoch": 1.4826254826254825, "grad_norm": 0.19312851130962372, "learning_rate": 4.277569313094809e-07, "loss": 12.248, "step": 48 }, { "epoch": 1.5135135135135136, "grad_norm": 0.13117873668670654, "learning_rate": 1.0705383806982606e-07, "loss": 10.6341, "step": 49 }, { "epoch": 1.5444015444015444, "grad_norm": 0.09648028761148453, "learning_rate": 0.0, "loss": 13.4304, "step": 50 }, { "epoch": 1.5444015444015444, "eval_loss": 11.9196138381958, "eval_runtime": 0.7842, "eval_samples_per_second": 279.277, "eval_steps_per_second": 35.707, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 1042494259200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }