{ "best_metric": 1.7819124460220337, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.018942084576407635, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00037884169152815265, "grad_norm": 10.302584648132324, "learning_rate": 5e-05, "loss": 9.3009, "step": 1 }, { "epoch": 0.00037884169152815265, "eval_loss": 11.692439079284668, "eval_runtime": 505.179, "eval_samples_per_second": 35.201, "eval_steps_per_second": 4.4, "step": 1 }, { "epoch": 0.0007576833830563053, "grad_norm": 10.505722999572754, "learning_rate": 0.0001, "loss": 10.312, "step": 2 }, { "epoch": 0.001136525074584458, "grad_norm": 12.538541793823242, "learning_rate": 9.989294616193017e-05, "loss": 10.3303, "step": 3 }, { "epoch": 0.0015153667661126106, "grad_norm": 17.592634201049805, "learning_rate": 9.957224306869053e-05, "loss": 8.3617, "step": 4 }, { "epoch": 0.0018942084576407633, "grad_norm": 10.421478271484375, "learning_rate": 9.903926402016153e-05, "loss": 6.5981, "step": 5 }, { "epoch": 0.002273050149168916, "grad_norm": 12.421805381774902, "learning_rate": 9.829629131445342e-05, "loss": 5.6562, "step": 6 }, { "epoch": 0.002651891840697069, "grad_norm": 11.059440612792969, "learning_rate": 9.73465064747553e-05, "loss": 4.7562, "step": 7 }, { "epoch": 0.0030307335322252212, "grad_norm": 10.304879188537598, "learning_rate": 9.619397662556435e-05, "loss": 3.6356, "step": 8 }, { "epoch": 0.003409575223753374, "grad_norm": 8.042673110961914, "learning_rate": 9.484363707663442e-05, "loss": 2.8173, "step": 9 }, { "epoch": 0.0037884169152815265, "grad_norm": 5.092674732208252, "learning_rate": 9.330127018922194e-05, "loss": 2.6009, "step": 10 }, { "epoch": 0.00416725860680968, "grad_norm": 6.48095178604126, "learning_rate": 9.157348061512727e-05, "loss": 2.4856, "step": 11 }, { "epoch": 0.004546100298337832, "grad_norm": 4.450168132781982, "learning_rate": 8.966766701456177e-05, "loss": 2.4173, "step": 12 }, { "epoch": 0.004924941989865985, "grad_norm": 10.408378601074219, "learning_rate": 8.759199037394887e-05, "loss": 2.3333, "step": 13 }, { "epoch": 0.005303783681394138, "grad_norm": 5.03222131729126, "learning_rate": 8.535533905932738e-05, "loss": 2.2746, "step": 14 }, { "epoch": 0.0056826253729222904, "grad_norm": 10.990303993225098, "learning_rate": 8.296729075500344e-05, "loss": 2.0516, "step": 15 }, { "epoch": 0.0060614670644504424, "grad_norm": 7.39019775390625, "learning_rate": 8.043807145043604e-05, "loss": 2.0911, "step": 16 }, { "epoch": 0.006440308755978595, "grad_norm": 5.295200824737549, "learning_rate": 7.777851165098012e-05, "loss": 1.964, "step": 17 }, { "epoch": 0.006819150447506748, "grad_norm": 3.3789727687835693, "learning_rate": 7.500000000000001e-05, "loss": 1.789, "step": 18 }, { "epoch": 0.007197992139034901, "grad_norm": 3.250417709350586, "learning_rate": 7.211443451095007e-05, "loss": 1.9583, "step": 19 }, { "epoch": 0.007576833830563053, "grad_norm": 3.274604320526123, "learning_rate": 6.91341716182545e-05, "loss": 1.7714, "step": 20 }, { "epoch": 0.007955675522091206, "grad_norm": 3.8370654582977295, "learning_rate": 6.607197326515808e-05, "loss": 1.9369, "step": 21 }, { "epoch": 0.00833451721361936, "grad_norm": 3.1080238819122314, "learning_rate": 6.294095225512603e-05, "loss": 1.8008, "step": 22 }, { "epoch": 0.008713358905147512, "grad_norm": 2.949986457824707, "learning_rate": 5.9754516100806423e-05, "loss": 1.8475, "step": 23 }, { "epoch": 0.009092200596675664, "grad_norm": 4.394115924835205, "learning_rate": 5.6526309611002594e-05, "loss": 2.1908, "step": 24 }, { "epoch": 0.009471042288203817, "grad_norm": 3.2628118991851807, "learning_rate": 5.327015646150716e-05, "loss": 1.8698, "step": 25 }, { "epoch": 0.009471042288203817, "eval_loss": 1.9056551456451416, "eval_runtime": 505.7267, "eval_samples_per_second": 35.163, "eval_steps_per_second": 4.396, "step": 25 }, { "epoch": 0.00984988397973197, "grad_norm": 11.075776100158691, "learning_rate": 5e-05, "loss": 1.9513, "step": 26 }, { "epoch": 0.010228725671260121, "grad_norm": 4.006396770477295, "learning_rate": 4.6729843538492847e-05, "loss": 1.7975, "step": 27 }, { "epoch": 0.010607567362788275, "grad_norm": 3.184319257736206, "learning_rate": 4.347369038899744e-05, "loss": 1.875, "step": 28 }, { "epoch": 0.010986409054316427, "grad_norm": 3.2057037353515625, "learning_rate": 4.0245483899193595e-05, "loss": 1.6062, "step": 29 }, { "epoch": 0.011365250745844581, "grad_norm": 4.042563438415527, "learning_rate": 3.705904774487396e-05, "loss": 1.7816, "step": 30 }, { "epoch": 0.011744092437372733, "grad_norm": 2.249629259109497, "learning_rate": 3.392802673484193e-05, "loss": 1.7139, "step": 31 }, { "epoch": 0.012122934128900885, "grad_norm": 2.8991994857788086, "learning_rate": 3.086582838174551e-05, "loss": 1.7144, "step": 32 }, { "epoch": 0.012501775820429039, "grad_norm": 2.710634231567383, "learning_rate": 2.7885565489049946e-05, "loss": 1.7614, "step": 33 }, { "epoch": 0.01288061751195719, "grad_norm": 2.834088087081909, "learning_rate": 2.500000000000001e-05, "loss": 1.7785, "step": 34 }, { "epoch": 0.013259459203485344, "grad_norm": 2.720170497894287, "learning_rate": 2.2221488349019903e-05, "loss": 1.813, "step": 35 }, { "epoch": 0.013638300895013496, "grad_norm": 2.524933338165283, "learning_rate": 1.9561928549563968e-05, "loss": 1.8267, "step": 36 }, { "epoch": 0.014017142586541648, "grad_norm": 2.3130557537078857, "learning_rate": 1.703270924499656e-05, "loss": 1.9053, "step": 37 }, { "epoch": 0.014395984278069802, "grad_norm": 2.778029441833496, "learning_rate": 1.4644660940672627e-05, "loss": 1.8611, "step": 38 }, { "epoch": 0.014774825969597954, "grad_norm": 2.314708709716797, "learning_rate": 1.2408009626051137e-05, "loss": 1.6435, "step": 39 }, { "epoch": 0.015153667661126106, "grad_norm": 2.738293170928955, "learning_rate": 1.0332332985438248e-05, "loss": 1.6773, "step": 40 }, { "epoch": 0.01553250935265426, "grad_norm": 2.5919830799102783, "learning_rate": 8.426519384872733e-06, "loss": 1.7022, "step": 41 }, { "epoch": 0.015911351044182412, "grad_norm": 2.239039421081543, "learning_rate": 6.698729810778065e-06, "loss": 1.6365, "step": 42 }, { "epoch": 0.016290192735710564, "grad_norm": 2.4477410316467285, "learning_rate": 5.156362923365588e-06, "loss": 1.6117, "step": 43 }, { "epoch": 0.01666903442723872, "grad_norm": 2.2895777225494385, "learning_rate": 3.8060233744356633e-06, "loss": 1.649, "step": 44 }, { "epoch": 0.01704787611876687, "grad_norm": 2.5630218982696533, "learning_rate": 2.653493525244721e-06, "loss": 1.6883, "step": 45 }, { "epoch": 0.017426717810295023, "grad_norm": 2.7641680240631104, "learning_rate": 1.70370868554659e-06, "loss": 1.821, "step": 46 }, { "epoch": 0.017805559501823175, "grad_norm": 2.8291962146759033, "learning_rate": 9.607359798384785e-07, "loss": 1.9129, "step": 47 }, { "epoch": 0.018184401193351327, "grad_norm": 2.2130260467529297, "learning_rate": 4.277569313094809e-07, "loss": 1.8267, "step": 48 }, { "epoch": 0.01856324288487948, "grad_norm": 2.9716482162475586, "learning_rate": 1.0705383806982606e-07, "loss": 1.7907, "step": 49 }, { "epoch": 0.018942084576407635, "grad_norm": 3.4197726249694824, "learning_rate": 0.0, "loss": 1.94, "step": 50 }, { "epoch": 0.018942084576407635, "eval_loss": 1.7819124460220337, "eval_runtime": 505.7599, "eval_samples_per_second": 35.161, "eval_steps_per_second": 4.395, "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 }