{ "best_metric": 0.2209298312664032, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.02768549280177187, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005537098560354374, "grad_norm": 83.63919067382812, "learning_rate": 5e-05, "loss": 5.3284, "step": 1 }, { "epoch": 0.0005537098560354374, "eval_loss": 5.616427421569824, "eval_runtime": 881.9672, "eval_samples_per_second": 13.795, "eval_steps_per_second": 1.725, "step": 1 }, { "epoch": 0.0011074197120708748, "grad_norm": 81.07270812988281, "learning_rate": 0.0001, "loss": 5.0392, "step": 2 }, { "epoch": 0.0016611295681063123, "grad_norm": 77.96538543701172, "learning_rate": 9.989294616193017e-05, "loss": 4.821, "step": 3 }, { "epoch": 0.0022148394241417496, "grad_norm": 248.20559692382812, "learning_rate": 9.957224306869053e-05, "loss": 4.2793, "step": 4 }, { "epoch": 0.0027685492801771874, "grad_norm": 470.4466552734375, "learning_rate": 9.903926402016153e-05, "loss": 3.1648, "step": 5 }, { "epoch": 0.0033222591362126247, "grad_norm": 244.6553192138672, "learning_rate": 9.829629131445342e-05, "loss": 1.8212, "step": 6 }, { "epoch": 0.003875968992248062, "grad_norm": 73.94499206542969, "learning_rate": 9.73465064747553e-05, "loss": 1.1359, "step": 7 }, { "epoch": 0.004429678848283499, "grad_norm": 52.48252487182617, "learning_rate": 9.619397662556435e-05, "loss": 0.639, "step": 8 }, { "epoch": 0.0049833887043189366, "grad_norm": 42.62266159057617, "learning_rate": 9.484363707663442e-05, "loss": 0.4366, "step": 9 }, { "epoch": 0.005537098560354375, "grad_norm": 55.48554229736328, "learning_rate": 9.330127018922194e-05, "loss": 0.2331, "step": 10 }, { "epoch": 0.006090808416389812, "grad_norm": 18.96228790283203, "learning_rate": 9.157348061512727e-05, "loss": 0.2517, "step": 11 }, { "epoch": 0.006644518272425249, "grad_norm": 600.3218994140625, "learning_rate": 8.966766701456177e-05, "loss": 3.1156, "step": 12 }, { "epoch": 0.007198228128460687, "grad_norm": 560.729736328125, "learning_rate": 8.759199037394887e-05, "loss": 2.4623, "step": 13 }, { "epoch": 0.007751937984496124, "grad_norm": 50.38520050048828, "learning_rate": 8.535533905932738e-05, "loss": 0.47, "step": 14 }, { "epoch": 0.008305647840531562, "grad_norm": 45.0614128112793, "learning_rate": 8.296729075500344e-05, "loss": 0.2445, "step": 15 }, { "epoch": 0.008859357696566999, "grad_norm": 16.783288955688477, "learning_rate": 8.043807145043604e-05, "loss": 0.0527, "step": 16 }, { "epoch": 0.009413067552602437, "grad_norm": 401.33197021484375, "learning_rate": 7.777851165098012e-05, "loss": 0.1234, "step": 17 }, { "epoch": 0.009966777408637873, "grad_norm": 127.39128875732422, "learning_rate": 7.500000000000001e-05, "loss": 0.0367, "step": 18 }, { "epoch": 0.010520487264673311, "grad_norm": 7.844943046569824, "learning_rate": 7.211443451095007e-05, "loss": 0.0225, "step": 19 }, { "epoch": 0.01107419712070875, "grad_norm": 4.442848205566406, "learning_rate": 6.91341716182545e-05, "loss": 0.0251, "step": 20 }, { "epoch": 0.011627906976744186, "grad_norm": 2.3369901180267334, "learning_rate": 6.607197326515808e-05, "loss": 0.0091, "step": 21 }, { "epoch": 0.012181616832779624, "grad_norm": 0.6338233947753906, "learning_rate": 6.294095225512603e-05, "loss": 0.0014, "step": 22 }, { "epoch": 0.01273532668881506, "grad_norm": 0.2525288164615631, "learning_rate": 5.9754516100806423e-05, "loss": 0.0004, "step": 23 }, { "epoch": 0.013289036544850499, "grad_norm": 202.52098083496094, "learning_rate": 5.6526309611002594e-05, "loss": 1.0549, "step": 24 }, { "epoch": 0.013842746400885935, "grad_norm": 749.843017578125, "learning_rate": 5.327015646150716e-05, "loss": 2.1561, "step": 25 }, { "epoch": 0.013842746400885935, "eval_loss": 0.2209298312664032, "eval_runtime": 882.1499, "eval_samples_per_second": 13.792, "eval_steps_per_second": 1.724, "step": 25 }, { "epoch": 0.014396456256921373, "grad_norm": 98.28343963623047, "learning_rate": 5e-05, "loss": 0.8503, "step": 26 }, { "epoch": 0.014950166112956811, "grad_norm": 14.48868465423584, "learning_rate": 4.6729843538492847e-05, "loss": 0.018, "step": 27 }, { "epoch": 0.015503875968992248, "grad_norm": 5.126861095428467, "learning_rate": 4.347369038899744e-05, "loss": 0.0071, "step": 28 }, { "epoch": 0.016057585825027684, "grad_norm": 1.48406982421875, "learning_rate": 4.0245483899193595e-05, "loss": 0.0024, "step": 29 }, { "epoch": 0.016611295681063124, "grad_norm": 13.655170440673828, "learning_rate": 3.705904774487396e-05, "loss": 0.0077, "step": 30 }, { "epoch": 0.01716500553709856, "grad_norm": 8.702022552490234, "learning_rate": 3.392802673484193e-05, "loss": 0.0046, "step": 31 }, { "epoch": 0.017718715393133997, "grad_norm": 4.665962219238281, "learning_rate": 3.086582838174551e-05, "loss": 0.0023, "step": 32 }, { "epoch": 0.018272425249169437, "grad_norm": 1.7277586460113525, "learning_rate": 2.7885565489049946e-05, "loss": 0.0009, "step": 33 }, { "epoch": 0.018826135105204873, "grad_norm": 0.4850597381591797, "learning_rate": 2.500000000000001e-05, "loss": 0.0004, "step": 34 }, { "epoch": 0.01937984496124031, "grad_norm": 0.1928061842918396, "learning_rate": 2.2221488349019903e-05, "loss": 0.0001, "step": 35 }, { "epoch": 0.019933554817275746, "grad_norm": 0.04373222589492798, "learning_rate": 1.9561928549563968e-05, "loss": 0.0001, "step": 36 }, { "epoch": 0.020487264673311186, "grad_norm": 323.9327087402344, "learning_rate": 1.703270924499656e-05, "loss": 2.4818, "step": 37 }, { "epoch": 0.021040974529346623, "grad_norm": 266.1087951660156, "learning_rate": 1.4644660940672627e-05, "loss": 1.7784, "step": 38 }, { "epoch": 0.02159468438538206, "grad_norm": 0.04026114568114281, "learning_rate": 1.2408009626051137e-05, "loss": 0.0001, "step": 39 }, { "epoch": 0.0221483942414175, "grad_norm": 0.03933119773864746, "learning_rate": 1.0332332985438248e-05, "loss": 0.0001, "step": 40 }, { "epoch": 0.022702104097452935, "grad_norm": 0.04323228821158409, "learning_rate": 8.426519384872733e-06, "loss": 0.0001, "step": 41 }, { "epoch": 0.023255813953488372, "grad_norm": 0.06206133961677551, "learning_rate": 6.698729810778065e-06, "loss": 0.0001, "step": 42 }, { "epoch": 0.023809523809523808, "grad_norm": 0.015565506182610989, "learning_rate": 5.156362923365588e-06, "loss": 0.0, "step": 43 }, { "epoch": 0.024363233665559248, "grad_norm": 0.057457469403743744, "learning_rate": 3.8060233744356633e-06, "loss": 0.0001, "step": 44 }, { "epoch": 0.024916943521594685, "grad_norm": 0.010861905291676521, "learning_rate": 2.653493525244721e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.02547065337763012, "grad_norm": 0.016795886680483818, "learning_rate": 1.70370868554659e-06, "loss": 0.0, "step": 46 }, { "epoch": 0.02602436323366556, "grad_norm": 0.04295491799712181, "learning_rate": 9.607359798384785e-07, "loss": 0.0001, "step": 47 }, { "epoch": 0.026578073089700997, "grad_norm": 0.08125736564397812, "learning_rate": 4.277569313094809e-07, "loss": 0.0002, "step": 48 }, { "epoch": 0.027131782945736434, "grad_norm": 101.67281341552734, "learning_rate": 1.0705383806982606e-07, "loss": 1.1258, "step": 49 }, { "epoch": 0.02768549280177187, "grad_norm": 486.48394775390625, "learning_rate": 0.0, "loss": 2.7297, "step": 50 }, { "epoch": 0.02768549280177187, "eval_loss": 0.3239246606826782, "eval_runtime": 882.1015, "eval_samples_per_second": 13.793, "eval_steps_per_second": 1.724, "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": 1 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.967137622687744e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }