{ "best_metric": 1.8184459209442139, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.31545741324921134, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006309148264984227, "grad_norm": 0.38407275080680847, "learning_rate": 5e-05, "loss": 2.0506, "step": 1 }, { "epoch": 0.006309148264984227, "eval_loss": 2.064948558807373, "eval_runtime": 28.4339, "eval_samples_per_second": 37.561, "eval_steps_per_second": 4.713, "step": 1 }, { "epoch": 0.012618296529968454, "grad_norm": 0.41005808115005493, "learning_rate": 0.0001, "loss": 2.0795, "step": 2 }, { "epoch": 0.01892744479495268, "grad_norm": 0.34803804755210876, "learning_rate": 9.989294616193017e-05, "loss": 2.032, "step": 3 }, { "epoch": 0.025236593059936908, "grad_norm": 0.2697660028934479, "learning_rate": 9.957224306869053e-05, "loss": 2.0105, "step": 4 }, { "epoch": 0.031545741324921134, "grad_norm": 0.45508819818496704, "learning_rate": 9.903926402016153e-05, "loss": 2.0487, "step": 5 }, { "epoch": 0.03785488958990536, "grad_norm": 0.37418580055236816, "learning_rate": 9.829629131445342e-05, "loss": 1.9617, "step": 6 }, { "epoch": 0.04416403785488959, "grad_norm": 0.2754422128200531, "learning_rate": 9.73465064747553e-05, "loss": 1.9205, "step": 7 }, { "epoch": 0.050473186119873815, "grad_norm": 0.2884434163570404, "learning_rate": 9.619397662556435e-05, "loss": 1.8945, "step": 8 }, { "epoch": 0.056782334384858045, "grad_norm": 0.25097694993019104, "learning_rate": 9.484363707663442e-05, "loss": 1.9137, "step": 9 }, { "epoch": 0.06309148264984227, "grad_norm": 0.24270197749137878, "learning_rate": 9.330127018922194e-05, "loss": 1.8692, "step": 10 }, { "epoch": 0.0694006309148265, "grad_norm": 0.27715644240379333, "learning_rate": 9.157348061512727e-05, "loss": 1.9172, "step": 11 }, { "epoch": 0.07570977917981073, "grad_norm": 0.44105395674705505, "learning_rate": 8.966766701456177e-05, "loss": 1.9184, "step": 12 }, { "epoch": 0.08201892744479496, "grad_norm": 0.2739848792552948, "learning_rate": 8.759199037394887e-05, "loss": 1.8539, "step": 13 }, { "epoch": 0.08832807570977919, "grad_norm": 0.2893473207950592, "learning_rate": 8.535533905932738e-05, "loss": 1.8923, "step": 14 }, { "epoch": 0.0946372239747634, "grad_norm": 0.2849172353744507, "learning_rate": 8.296729075500344e-05, "loss": 1.9218, "step": 15 }, { "epoch": 0.10094637223974763, "grad_norm": 0.2226078063249588, "learning_rate": 8.043807145043604e-05, "loss": 1.9088, "step": 16 }, { "epoch": 0.10725552050473186, "grad_norm": 0.20577310025691986, "learning_rate": 7.777851165098012e-05, "loss": 1.8555, "step": 17 }, { "epoch": 0.11356466876971609, "grad_norm": 0.20768675208091736, "learning_rate": 7.500000000000001e-05, "loss": 1.8645, "step": 18 }, { "epoch": 0.11987381703470032, "grad_norm": 0.21939949691295624, "learning_rate": 7.211443451095007e-05, "loss": 1.9289, "step": 19 }, { "epoch": 0.12618296529968454, "grad_norm": 0.2331872582435608, "learning_rate": 6.91341716182545e-05, "loss": 1.9202, "step": 20 }, { "epoch": 0.13249211356466878, "grad_norm": 0.21545597910881042, "learning_rate": 6.607197326515808e-05, "loss": 1.8425, "step": 21 }, { "epoch": 0.138801261829653, "grad_norm": 0.20941980183124542, "learning_rate": 6.294095225512603e-05, "loss": 1.8339, "step": 22 }, { "epoch": 0.14511041009463724, "grad_norm": 0.20397980511188507, "learning_rate": 5.9754516100806423e-05, "loss": 1.8441, "step": 23 }, { "epoch": 0.15141955835962145, "grad_norm": 0.28763625025749207, "learning_rate": 5.6526309611002594e-05, "loss": 1.83, "step": 24 }, { "epoch": 0.15772870662460567, "grad_norm": 0.4689052104949951, "learning_rate": 5.327015646150716e-05, "loss": 1.7203, "step": 25 }, { "epoch": 0.15772870662460567, "eval_loss": 1.839776635169983, "eval_runtime": 28.4176, "eval_samples_per_second": 37.582, "eval_steps_per_second": 4.715, "step": 25 }, { "epoch": 0.1640378548895899, "grad_norm": 0.22183643281459808, "learning_rate": 5e-05, "loss": 1.8731, "step": 26 }, { "epoch": 0.17034700315457413, "grad_norm": 0.23239830136299133, "learning_rate": 4.6729843538492847e-05, "loss": 1.8823, "step": 27 }, { "epoch": 0.17665615141955837, "grad_norm": 0.25411996245384216, "learning_rate": 4.347369038899744e-05, "loss": 1.8687, "step": 28 }, { "epoch": 0.1829652996845426, "grad_norm": 0.2557433843612671, "learning_rate": 4.0245483899193595e-05, "loss": 1.874, "step": 29 }, { "epoch": 0.1892744479495268, "grad_norm": 0.2673349380493164, "learning_rate": 3.705904774487396e-05, "loss": 1.8471, "step": 30 }, { "epoch": 0.19558359621451105, "grad_norm": 0.2484605759382248, "learning_rate": 3.392802673484193e-05, "loss": 1.859, "step": 31 }, { "epoch": 0.20189274447949526, "grad_norm": 0.2173624187707901, "learning_rate": 3.086582838174551e-05, "loss": 1.849, "step": 32 }, { "epoch": 0.2082018927444795, "grad_norm": 0.21619372069835663, "learning_rate": 2.7885565489049946e-05, "loss": 1.8267, "step": 33 }, { "epoch": 0.21451104100946372, "grad_norm": 0.21120446920394897, "learning_rate": 2.500000000000001e-05, "loss": 1.8038, "step": 34 }, { "epoch": 0.22082018927444794, "grad_norm": 0.19982676208019257, "learning_rate": 2.2221488349019903e-05, "loss": 1.7969, "step": 35 }, { "epoch": 0.22712933753943218, "grad_norm": 0.24043601751327515, "learning_rate": 1.9561928549563968e-05, "loss": 1.7976, "step": 36 }, { "epoch": 0.2334384858044164, "grad_norm": 0.30931851267814636, "learning_rate": 1.703270924499656e-05, "loss": 1.754, "step": 37 }, { "epoch": 0.23974763406940064, "grad_norm": 0.27804020047187805, "learning_rate": 1.4644660940672627e-05, "loss": 1.7745, "step": 38 }, { "epoch": 0.24605678233438485, "grad_norm": 0.22666315734386444, "learning_rate": 1.2408009626051137e-05, "loss": 1.8337, "step": 39 }, { "epoch": 0.25236593059936907, "grad_norm": 0.22043730318546295, "learning_rate": 1.0332332985438248e-05, "loss": 1.8697, "step": 40 }, { "epoch": 0.2586750788643533, "grad_norm": 0.20328503847122192, "learning_rate": 8.426519384872733e-06, "loss": 1.8674, "step": 41 }, { "epoch": 0.26498422712933756, "grad_norm": 0.1999230980873108, "learning_rate": 6.698729810778065e-06, "loss": 1.8426, "step": 42 }, { "epoch": 0.27129337539432175, "grad_norm": 0.19739872217178345, "learning_rate": 5.156362923365588e-06, "loss": 1.8265, "step": 43 }, { "epoch": 0.277602523659306, "grad_norm": 0.18016493320465088, "learning_rate": 3.8060233744356633e-06, "loss": 1.8518, "step": 44 }, { "epoch": 0.28391167192429023, "grad_norm": 0.17923451960086823, "learning_rate": 2.653493525244721e-06, "loss": 1.8326, "step": 45 }, { "epoch": 0.2902208201892745, "grad_norm": 0.18921245634555817, "learning_rate": 1.70370868554659e-06, "loss": 1.7991, "step": 46 }, { "epoch": 0.29652996845425866, "grad_norm": 0.21040190756320953, "learning_rate": 9.607359798384785e-07, "loss": 1.8368, "step": 47 }, { "epoch": 0.3028391167192429, "grad_norm": 0.20501868426799774, "learning_rate": 4.277569313094809e-07, "loss": 1.8485, "step": 48 }, { "epoch": 0.30914826498422715, "grad_norm": 0.2552344501018524, "learning_rate": 1.0705383806982606e-07, "loss": 1.8671, "step": 49 }, { "epoch": 0.31545741324921134, "grad_norm": 0.3954026401042938, "learning_rate": 0.0, "loss": 1.7277, "step": 50 }, { "epoch": 0.31545741324921134, "eval_loss": 1.8184459209442139, "eval_runtime": 28.5162, "eval_samples_per_second": 37.452, "eval_steps_per_second": 4.699, "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": 5.968083617316864e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }