{ "best_metric": 0.834536612033844, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.19061234214915415, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003812246842983083, "grad_norm": 0.29896801710128784, "learning_rate": 5e-05, "loss": 0.9351, "step": 1 }, { "epoch": 0.003812246842983083, "eval_loss": 0.934563934803009, "eval_runtime": 12.3409, "eval_samples_per_second": 143.263, "eval_steps_per_second": 17.908, "step": 1 }, { "epoch": 0.007624493685966166, "grad_norm": 0.34194695949554443, "learning_rate": 0.0001, "loss": 0.9268, "step": 2 }, { "epoch": 0.01143674052894925, "grad_norm": 0.29837003350257874, "learning_rate": 9.989294616193017e-05, "loss": 0.8997, "step": 3 }, { "epoch": 0.015248987371932332, "grad_norm": 0.27154502272605896, "learning_rate": 9.957224306869053e-05, "loss": 0.9221, "step": 4 }, { "epoch": 0.019061234214915415, "grad_norm": 0.3175603151321411, "learning_rate": 9.903926402016153e-05, "loss": 0.9216, "step": 5 }, { "epoch": 0.0228734810578985, "grad_norm": 0.30236729979515076, "learning_rate": 9.829629131445342e-05, "loss": 0.9274, "step": 6 }, { "epoch": 0.02668572790088158, "grad_norm": 0.29152992367744446, "learning_rate": 9.73465064747553e-05, "loss": 0.866, "step": 7 }, { "epoch": 0.030497974743864665, "grad_norm": 0.2672061324119568, "learning_rate": 9.619397662556435e-05, "loss": 0.7957, "step": 8 }, { "epoch": 0.034310221586847746, "grad_norm": 0.30671226978302, "learning_rate": 9.484363707663442e-05, "loss": 0.9114, "step": 9 }, { "epoch": 0.03812246842983083, "grad_norm": 0.27908194065093994, "learning_rate": 9.330127018922194e-05, "loss": 0.8905, "step": 10 }, { "epoch": 0.041934715272813915, "grad_norm": 0.2735025882720947, "learning_rate": 9.157348061512727e-05, "loss": 0.8844, "step": 11 }, { "epoch": 0.045746962115797, "grad_norm": 0.2878081500530243, "learning_rate": 8.966766701456177e-05, "loss": 0.8938, "step": 12 }, { "epoch": 0.049559208958780084, "grad_norm": 0.2187119871377945, "learning_rate": 8.759199037394887e-05, "loss": 0.9131, "step": 13 }, { "epoch": 0.05337145580176316, "grad_norm": 0.1985989660024643, "learning_rate": 8.535533905932738e-05, "loss": 0.8329, "step": 14 }, { "epoch": 0.057183702644746245, "grad_norm": 0.20740792155265808, "learning_rate": 8.296729075500344e-05, "loss": 0.9375, "step": 15 }, { "epoch": 0.06099594948772933, "grad_norm": 0.19763857126235962, "learning_rate": 8.043807145043604e-05, "loss": 0.8005, "step": 16 }, { "epoch": 0.06480819633071241, "grad_norm": 0.2020978331565857, "learning_rate": 7.777851165098012e-05, "loss": 0.8573, "step": 17 }, { "epoch": 0.06862044317369549, "grad_norm": 0.2145608812570572, "learning_rate": 7.500000000000001e-05, "loss": 0.8462, "step": 18 }, { "epoch": 0.07243269001667858, "grad_norm": 0.21993571519851685, "learning_rate": 7.211443451095007e-05, "loss": 0.8402, "step": 19 }, { "epoch": 0.07624493685966166, "grad_norm": 0.2236100733280182, "learning_rate": 6.91341716182545e-05, "loss": 0.8336, "step": 20 }, { "epoch": 0.08005718370264475, "grad_norm": 0.22653716802597046, "learning_rate": 6.607197326515808e-05, "loss": 0.8506, "step": 21 }, { "epoch": 0.08386943054562783, "grad_norm": 0.2271314263343811, "learning_rate": 6.294095225512603e-05, "loss": 0.7991, "step": 22 }, { "epoch": 0.0876816773886109, "grad_norm": 0.2490874081850052, "learning_rate": 5.9754516100806423e-05, "loss": 0.8077, "step": 23 }, { "epoch": 0.091493924231594, "grad_norm": 0.25286605954170227, "learning_rate": 5.6526309611002594e-05, "loss": 0.7909, "step": 24 }, { "epoch": 0.09530617107457708, "grad_norm": 0.2924603819847107, "learning_rate": 5.327015646150716e-05, "loss": 0.8297, "step": 25 }, { "epoch": 0.09530617107457708, "eval_loss": 0.8427870869636536, "eval_runtime": 12.269, "eval_samples_per_second": 144.103, "eval_steps_per_second": 18.013, "step": 25 }, { "epoch": 0.09911841791756017, "grad_norm": 0.17822329699993134, "learning_rate": 5e-05, "loss": 0.8759, "step": 26 }, { "epoch": 0.10293066476054324, "grad_norm": 0.19967198371887207, "learning_rate": 4.6729843538492847e-05, "loss": 0.9197, "step": 27 }, { "epoch": 0.10674291160352632, "grad_norm": 0.193215474486351, "learning_rate": 4.347369038899744e-05, "loss": 0.8492, "step": 28 }, { "epoch": 0.11055515844650941, "grad_norm": 0.20109039545059204, "learning_rate": 4.0245483899193595e-05, "loss": 0.9079, "step": 29 }, { "epoch": 0.11436740528949249, "grad_norm": 0.194575235247612, "learning_rate": 3.705904774487396e-05, "loss": 0.8235, "step": 30 }, { "epoch": 0.11817965213247558, "grad_norm": 0.20027762651443481, "learning_rate": 3.392802673484193e-05, "loss": 0.8734, "step": 31 }, { "epoch": 0.12199189897545866, "grad_norm": 0.20569324493408203, "learning_rate": 3.086582838174551e-05, "loss": 0.803, "step": 32 }, { "epoch": 0.12580414581844174, "grad_norm": 0.20961406826972961, "learning_rate": 2.7885565489049946e-05, "loss": 0.8384, "step": 33 }, { "epoch": 0.12961639266142483, "grad_norm": 0.22293621301651, "learning_rate": 2.500000000000001e-05, "loss": 0.8662, "step": 34 }, { "epoch": 0.13342863950440792, "grad_norm": 0.234574556350708, "learning_rate": 2.2221488349019903e-05, "loss": 0.8503, "step": 35 }, { "epoch": 0.13724088634739098, "grad_norm": 0.23952020704746246, "learning_rate": 1.9561928549563968e-05, "loss": 0.795, "step": 36 }, { "epoch": 0.14105313319037407, "grad_norm": 0.2741438150405884, "learning_rate": 1.703270924499656e-05, "loss": 0.8032, "step": 37 }, { "epoch": 0.14486538003335717, "grad_norm": 0.1847420185804367, "learning_rate": 1.4644660940672627e-05, "loss": 0.9403, "step": 38 }, { "epoch": 0.14867762687634023, "grad_norm": 0.16584894061088562, "learning_rate": 1.2408009626051137e-05, "loss": 0.8382, "step": 39 }, { "epoch": 0.15248987371932332, "grad_norm": 0.17006836831569672, "learning_rate": 1.0332332985438248e-05, "loss": 0.8401, "step": 40 }, { "epoch": 0.1563021205623064, "grad_norm": 0.18232592940330505, "learning_rate": 8.426519384872733e-06, "loss": 0.846, "step": 41 }, { "epoch": 0.1601143674052895, "grad_norm": 0.18416273593902588, "learning_rate": 6.698729810778065e-06, "loss": 0.8676, "step": 42 }, { "epoch": 0.16392661424827257, "grad_norm": 0.1950211077928543, "learning_rate": 5.156362923365588e-06, "loss": 0.8468, "step": 43 }, { "epoch": 0.16773886109125566, "grad_norm": 0.1942923367023468, "learning_rate": 3.8060233744356633e-06, "loss": 0.7969, "step": 44 }, { "epoch": 0.17155110793423875, "grad_norm": 0.20313581824302673, "learning_rate": 2.653493525244721e-06, "loss": 0.8521, "step": 45 }, { "epoch": 0.1753633547772218, "grad_norm": 0.21020546555519104, "learning_rate": 1.70370868554659e-06, "loss": 0.839, "step": 46 }, { "epoch": 0.1791756016202049, "grad_norm": 0.21436075866222382, "learning_rate": 9.607359798384785e-07, "loss": 0.7975, "step": 47 }, { "epoch": 0.182987848463188, "grad_norm": 0.23240768909454346, "learning_rate": 4.277569313094809e-07, "loss": 0.7909, "step": 48 }, { "epoch": 0.1868000953061711, "grad_norm": 0.2519844174385071, "learning_rate": 1.0705383806982606e-07, "loss": 0.8479, "step": 49 }, { "epoch": 0.19061234214915415, "grad_norm": 0.2938311696052551, "learning_rate": 0.0, "loss": 0.8513, "step": 50 }, { "epoch": 0.19061234214915415, "eval_loss": 0.834536612033844, "eval_runtime": 12.3488, "eval_samples_per_second": 143.172, "eval_steps_per_second": 17.896, "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": 2.9585460372176896e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }