{ "best_metric": 6.911670684814453, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.4125838060856111, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008251676121712223, "grad_norm": 0.19168157875537872, "learning_rate": 5e-05, "loss": 6.8773, "step": 1 }, { "epoch": 0.008251676121712223, "eval_loss": 6.937580585479736, "eval_runtime": 0.7847, "eval_samples_per_second": 1041.193, "eval_steps_per_second": 131.264, "step": 1 }, { "epoch": 0.016503352243424446, "grad_norm": 0.18501441180706024, "learning_rate": 0.0001, "loss": 6.858, "step": 2 }, { "epoch": 0.02475502836513667, "grad_norm": 0.2035323530435562, "learning_rate": 9.989294616193017e-05, "loss": 6.8447, "step": 3 }, { "epoch": 0.03300670448684889, "grad_norm": 0.18418113887310028, "learning_rate": 9.957224306869053e-05, "loss": 6.8303, "step": 4 }, { "epoch": 0.041258380608561115, "grad_norm": 0.1808152049779892, "learning_rate": 9.903926402016153e-05, "loss": 6.8184, "step": 5 }, { "epoch": 0.04951005673027334, "grad_norm": 0.18681049346923828, "learning_rate": 9.829629131445342e-05, "loss": 6.8055, "step": 6 }, { "epoch": 0.05776173285198556, "grad_norm": 0.1917319893836975, "learning_rate": 9.73465064747553e-05, "loss": 6.7878, "step": 7 }, { "epoch": 0.06601340897369778, "grad_norm": 0.21119892597198486, "learning_rate": 9.619397662556435e-05, "loss": 6.7692, "step": 8 }, { "epoch": 0.07426508509541001, "grad_norm": 0.21528777480125427, "learning_rate": 9.484363707663442e-05, "loss": 6.7501, "step": 9 }, { "epoch": 0.08251676121712223, "grad_norm": 0.25786951184272766, "learning_rate": 9.330127018922194e-05, "loss": 6.7128, "step": 10 }, { "epoch": 0.09076843733883445, "grad_norm": 0.2376754879951477, "learning_rate": 9.157348061512727e-05, "loss": 6.6128, "step": 11 }, { "epoch": 0.09902011346054668, "grad_norm": 0.30647096037864685, "learning_rate": 8.966766701456177e-05, "loss": 6.3771, "step": 12 }, { "epoch": 0.1072717895822589, "grad_norm": 0.1863364428281784, "learning_rate": 8.759199037394887e-05, "loss": 6.8238, "step": 13 }, { "epoch": 0.11552346570397112, "grad_norm": 0.19649076461791992, "learning_rate": 8.535533905932738e-05, "loss": 6.8565, "step": 14 }, { "epoch": 0.12377514182568335, "grad_norm": 0.2133394181728363, "learning_rate": 8.296729075500344e-05, "loss": 6.8416, "step": 15 }, { "epoch": 0.13202681794739557, "grad_norm": 0.20794269442558289, "learning_rate": 8.043807145043604e-05, "loss": 6.8263, "step": 16 }, { "epoch": 0.14027849406910778, "grad_norm": 0.19656820595264435, "learning_rate": 7.777851165098012e-05, "loss": 6.8141, "step": 17 }, { "epoch": 0.14853017019082002, "grad_norm": 0.19225075840950012, "learning_rate": 7.500000000000001e-05, "loss": 6.7973, "step": 18 }, { "epoch": 0.15678184631253222, "grad_norm": 0.21045391261577606, "learning_rate": 7.211443451095007e-05, "loss": 6.7831, "step": 19 }, { "epoch": 0.16503352243424446, "grad_norm": 0.21318703889846802, "learning_rate": 6.91341716182545e-05, "loss": 6.7698, "step": 20 }, { "epoch": 0.17328519855595667, "grad_norm": 0.2291601151227951, "learning_rate": 6.607197326515808e-05, "loss": 6.7493, "step": 21 }, { "epoch": 0.1815368746776689, "grad_norm": 0.24010586738586426, "learning_rate": 6.294095225512603e-05, "loss": 6.7229, "step": 22 }, { "epoch": 0.18978855079938112, "grad_norm": 0.24575382471084595, "learning_rate": 5.9754516100806423e-05, "loss": 6.6626, "step": 23 }, { "epoch": 0.19804022692109335, "grad_norm": 0.2697991132736206, "learning_rate": 5.6526309611002594e-05, "loss": 6.4914, "step": 24 }, { "epoch": 0.20629190304280556, "grad_norm": 0.30134379863739014, "learning_rate": 5.327015646150716e-05, "loss": 6.1847, "step": 25 }, { "epoch": 0.20629190304280556, "eval_loss": 6.917348861694336, "eval_runtime": 0.7988, "eval_samples_per_second": 1022.73, "eval_steps_per_second": 128.937, "step": 25 }, { "epoch": 0.2145435791645178, "grad_norm": 0.20306411385536194, "learning_rate": 5e-05, "loss": 6.8609, "step": 26 }, { "epoch": 0.22279525528623, "grad_norm": 0.21225464344024658, "learning_rate": 4.6729843538492847e-05, "loss": 6.8381, "step": 27 }, { "epoch": 0.23104693140794225, "grad_norm": 0.22277817130088806, "learning_rate": 4.347369038899744e-05, "loss": 6.8217, "step": 28 }, { "epoch": 0.23929860752965446, "grad_norm": 0.20864786207675934, "learning_rate": 4.0245483899193595e-05, "loss": 6.8098, "step": 29 }, { "epoch": 0.2475502836513667, "grad_norm": 0.19844458997249603, "learning_rate": 3.705904774487396e-05, "loss": 6.7979, "step": 30 }, { "epoch": 0.2558019597730789, "grad_norm": 0.2161320596933365, "learning_rate": 3.392802673484193e-05, "loss": 6.7851, "step": 31 }, { "epoch": 0.26405363589479114, "grad_norm": 0.220876544713974, "learning_rate": 3.086582838174551e-05, "loss": 6.7751, "step": 32 }, { "epoch": 0.2723053120165034, "grad_norm": 0.23456600308418274, "learning_rate": 2.7885565489049946e-05, "loss": 6.7556, "step": 33 }, { "epoch": 0.28055698813821556, "grad_norm": 0.2240019291639328, "learning_rate": 2.500000000000001e-05, "loss": 6.7395, "step": 34 }, { "epoch": 0.2888086642599278, "grad_norm": 0.24339325726032257, "learning_rate": 2.2221488349019903e-05, "loss": 6.7011, "step": 35 }, { "epoch": 0.29706034038164003, "grad_norm": 0.24602070450782776, "learning_rate": 1.9561928549563968e-05, "loss": 6.6213, "step": 36 }, { "epoch": 0.30531201650335227, "grad_norm": 0.3220696449279785, "learning_rate": 1.703270924499656e-05, "loss": 6.4113, "step": 37 }, { "epoch": 0.31356369262506445, "grad_norm": 0.1950099915266037, "learning_rate": 1.4644660940672627e-05, "loss": 6.8109, "step": 38 }, { "epoch": 0.3218153687467767, "grad_norm": 0.21527087688446045, "learning_rate": 1.2408009626051137e-05, "loss": 6.8417, "step": 39 }, { "epoch": 0.3300670448684889, "grad_norm": 0.22541527450084686, "learning_rate": 1.0332332985438248e-05, "loss": 6.827, "step": 40 }, { "epoch": 0.33831872099020116, "grad_norm": 0.2274940013885498, "learning_rate": 8.426519384872733e-06, "loss": 6.8097, "step": 41 }, { "epoch": 0.34657039711191334, "grad_norm": 0.21498613059520721, "learning_rate": 6.698729810778065e-06, "loss": 6.7978, "step": 42 }, { "epoch": 0.3548220732336256, "grad_norm": 0.21291977167129517, "learning_rate": 5.156362923365588e-06, "loss": 6.7875, "step": 43 }, { "epoch": 0.3630737493553378, "grad_norm": 0.21820193529129028, "learning_rate": 3.8060233744356633e-06, "loss": 6.7742, "step": 44 }, { "epoch": 0.37132542547705005, "grad_norm": 0.22569087147712708, "learning_rate": 2.653493525244721e-06, "loss": 6.7579, "step": 45 }, { "epoch": 0.37957710159876223, "grad_norm": 0.23315046727657318, "learning_rate": 1.70370868554659e-06, "loss": 6.7395, "step": 46 }, { "epoch": 0.38782877772047447, "grad_norm": 0.24797138571739197, "learning_rate": 9.607359798384785e-07, "loss": 6.7078, "step": 47 }, { "epoch": 0.3960804538421867, "grad_norm": 0.26854848861694336, "learning_rate": 4.277569313094809e-07, "loss": 6.6595, "step": 48 }, { "epoch": 0.4043321299638989, "grad_norm": 0.25083285570144653, "learning_rate": 1.0705383806982606e-07, "loss": 6.531, "step": 49 }, { "epoch": 0.4125838060856111, "grad_norm": 0.267659991979599, "learning_rate": 0.0, "loss": 6.2156, "step": 50 }, { "epoch": 0.4125838060856111, "eval_loss": 6.911670684814453, "eval_runtime": 0.828, "eval_samples_per_second": 986.759, "eval_steps_per_second": 124.402, "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": 5705957376000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }