{ "best_metric": 0.024680091068148613, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.5908419497784343, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.011816838995568686, "grad_norm": 34.96453094482422, "learning_rate": 5e-05, "loss": 5.4741, "step": 1 }, { "epoch": 0.011816838995568686, "eval_loss": 10.668907165527344, "eval_runtime": 18.6229, "eval_samples_per_second": 30.608, "eval_steps_per_second": 3.866, "step": 1 }, { "epoch": 0.023633677991137372, "grad_norm": 46.173492431640625, "learning_rate": 0.0001, "loss": 6.1022, "step": 2 }, { "epoch": 0.03545051698670606, "grad_norm": 26.4172420501709, "learning_rate": 9.989294616193017e-05, "loss": 3.881, "step": 3 }, { "epoch": 0.047267355982274745, "grad_norm": 10.306843757629395, "learning_rate": 9.957224306869053e-05, "loss": 2.1076, "step": 4 }, { "epoch": 0.059084194977843424, "grad_norm": 6.41445255279541, "learning_rate": 9.903926402016153e-05, "loss": 1.7067, "step": 5 }, { "epoch": 0.07090103397341212, "grad_norm": 9.081036567687988, "learning_rate": 9.829629131445342e-05, "loss": 0.6988, "step": 6 }, { "epoch": 0.0827178729689808, "grad_norm": 4.39510440826416, "learning_rate": 9.73465064747553e-05, "loss": 0.2484, "step": 7 }, { "epoch": 0.09453471196454949, "grad_norm": 1.467455506324768, "learning_rate": 9.619397662556435e-05, "loss": 0.0562, "step": 8 }, { "epoch": 0.10635155096011817, "grad_norm": 0.15431492030620575, "learning_rate": 9.484363707663442e-05, "loss": 0.0051, "step": 9 }, { "epoch": 0.11816838995568685, "grad_norm": 0.5835440754890442, "learning_rate": 9.330127018922194e-05, "loss": 0.0049, "step": 10 }, { "epoch": 0.12998522895125553, "grad_norm": 0.10168576240539551, "learning_rate": 9.157348061512727e-05, "loss": 0.0014, "step": 11 }, { "epoch": 0.14180206794682423, "grad_norm": 0.024450739845633507, "learning_rate": 8.966766701456177e-05, "loss": 0.0005, "step": 12 }, { "epoch": 0.1536189069423929, "grad_norm": 5.102807998657227, "learning_rate": 8.759199037394887e-05, "loss": 1.0437, "step": 13 }, { "epoch": 0.1654357459379616, "grad_norm": 0.4708941876888275, "learning_rate": 8.535533905932738e-05, "loss": 0.0033, "step": 14 }, { "epoch": 0.17725258493353027, "grad_norm": 0.15717916190624237, "learning_rate": 8.296729075500344e-05, "loss": 0.0013, "step": 15 }, { "epoch": 0.18906942392909898, "grad_norm": 0.15204527974128723, "learning_rate": 8.043807145043604e-05, "loss": 0.0011, "step": 16 }, { "epoch": 0.20088626292466766, "grad_norm": 0.02739199809730053, "learning_rate": 7.777851165098012e-05, "loss": 0.0004, "step": 17 }, { "epoch": 0.21270310192023634, "grad_norm": 0.6835923194885254, "learning_rate": 7.500000000000001e-05, "loss": 0.0033, "step": 18 }, { "epoch": 0.22451994091580502, "grad_norm": 0.02322707325220108, "learning_rate": 7.211443451095007e-05, "loss": 0.0003, "step": 19 }, { "epoch": 0.2363367799113737, "grad_norm": 0.4679819345474243, "learning_rate": 6.91341716182545e-05, "loss": 0.0067, "step": 20 }, { "epoch": 0.2481536189069424, "grad_norm": 0.02195070870220661, "learning_rate": 6.607197326515808e-05, "loss": 0.0002, "step": 21 }, { "epoch": 0.25997045790251105, "grad_norm": 0.03607134148478508, "learning_rate": 6.294095225512603e-05, "loss": 0.0004, "step": 22 }, { "epoch": 0.2717872968980798, "grad_norm": 0.022569574415683746, "learning_rate": 5.9754516100806423e-05, "loss": 0.0002, "step": 23 }, { "epoch": 0.28360413589364847, "grad_norm": 0.3922696113586426, "learning_rate": 5.6526309611002594e-05, "loss": 0.0033, "step": 24 }, { "epoch": 0.29542097488921715, "grad_norm": 0.013420968316495419, "learning_rate": 5.327015646150716e-05, "loss": 0.0001, "step": 25 }, { "epoch": 0.29542097488921715, "eval_loss": 0.03865384683012962, "eval_runtime": 18.9077, "eval_samples_per_second": 30.146, "eval_steps_per_second": 3.808, "step": 25 }, { "epoch": 0.3072378138847858, "grad_norm": 2.0008926391601562, "learning_rate": 5e-05, "loss": 0.3063, "step": 26 }, { "epoch": 0.3190546528803545, "grad_norm": 0.007220223546028137, "learning_rate": 4.6729843538492847e-05, "loss": 0.0001, "step": 27 }, { "epoch": 0.3308714918759232, "grad_norm": 0.0031562913209199905, "learning_rate": 4.347369038899744e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.34268833087149186, "grad_norm": 0.01956658624112606, "learning_rate": 4.0245483899193595e-05, "loss": 0.0002, "step": 29 }, { "epoch": 0.35450516986706054, "grad_norm": 0.01140380185097456, "learning_rate": 3.705904774487396e-05, "loss": 0.0001, "step": 30 }, { "epoch": 0.3663220088626292, "grad_norm": 0.0098069803789258, "learning_rate": 3.392802673484193e-05, "loss": 0.0001, "step": 31 }, { "epoch": 0.37813884785819796, "grad_norm": 0.0027902915608137846, "learning_rate": 3.086582838174551e-05, "loss": 0.0001, "step": 32 }, { "epoch": 0.38995568685376664, "grad_norm": 0.010911458171904087, "learning_rate": 2.7885565489049946e-05, "loss": 0.0001, "step": 33 }, { "epoch": 0.4017725258493353, "grad_norm": 0.002692491514608264, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 34 }, { "epoch": 0.413589364844904, "grad_norm": 0.045907288789749146, "learning_rate": 2.2221488349019903e-05, "loss": 0.0003, "step": 35 }, { "epoch": 0.4254062038404727, "grad_norm": 0.026951441541314125, "learning_rate": 1.9561928549563968e-05, "loss": 0.0001, "step": 36 }, { "epoch": 0.43722304283604135, "grad_norm": 0.00568424304947257, "learning_rate": 1.703270924499656e-05, "loss": 0.0001, "step": 37 }, { "epoch": 0.44903988183161003, "grad_norm": 1.7761626243591309, "learning_rate": 1.4644660940672627e-05, "loss": 0.4578, "step": 38 }, { "epoch": 0.4608567208271787, "grad_norm": 0.029375163838267326, "learning_rate": 1.2408009626051137e-05, "loss": 0.0002, "step": 39 }, { "epoch": 0.4726735598227474, "grad_norm": 0.015356656163930893, "learning_rate": 1.0332332985438248e-05, "loss": 0.0002, "step": 40 }, { "epoch": 0.4844903988183161, "grad_norm": 0.3691544234752655, "learning_rate": 8.426519384872733e-06, "loss": 0.0008, "step": 41 }, { "epoch": 0.4963072378138848, "grad_norm": 0.02166283316910267, "learning_rate": 6.698729810778065e-06, "loss": 0.0002, "step": 42 }, { "epoch": 0.5081240768094535, "grad_norm": 0.10131458938121796, "learning_rate": 5.156362923365588e-06, "loss": 0.0004, "step": 43 }, { "epoch": 0.5199409158050221, "grad_norm": 0.01139977015554905, "learning_rate": 3.8060233744356633e-06, "loss": 0.0001, "step": 44 }, { "epoch": 0.5317577548005908, "grad_norm": 0.008314274251461029, "learning_rate": 2.653493525244721e-06, "loss": 0.0001, "step": 45 }, { "epoch": 0.5435745937961596, "grad_norm": 0.008410402573645115, "learning_rate": 1.70370868554659e-06, "loss": 0.0001, "step": 46 }, { "epoch": 0.5553914327917282, "grad_norm": 0.03753000497817993, "learning_rate": 9.607359798384785e-07, "loss": 0.0003, "step": 47 }, { "epoch": 0.5672082717872969, "grad_norm": 0.012496479786932468, "learning_rate": 4.277569313094809e-07, "loss": 0.0001, "step": 48 }, { "epoch": 0.5790251107828656, "grad_norm": 0.024329444393515587, "learning_rate": 1.0705383806982606e-07, "loss": 0.0002, "step": 49 }, { "epoch": 0.5908419497784343, "grad_norm": 0.010945094749331474, "learning_rate": 0.0, "loss": 0.0001, "step": 50 }, { "epoch": 0.5908419497784343, "eval_loss": 0.024680091068148613, "eval_runtime": 18.8907, "eval_samples_per_second": 30.174, "eval_steps_per_second": 3.811, "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": 6.027764453490033e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }