{ "best_metric": 0.2016909420490265, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.02594033722438392, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005188067444876783, "grad_norm": 7.081730842590332, "learning_rate": 5e-05, "loss": 0.8421, "step": 1 }, { "epoch": 0.0005188067444876783, "eval_loss": 0.9019366502761841, "eval_runtime": 437.5703, "eval_samples_per_second": 29.675, "eval_steps_per_second": 3.711, "step": 1 }, { "epoch": 0.0010376134889753567, "grad_norm": 9.299199104309082, "learning_rate": 0.0001, "loss": 0.7793, "step": 2 }, { "epoch": 0.0015564202334630351, "grad_norm": 13.41754150390625, "learning_rate": 9.989294616193017e-05, "loss": 0.8543, "step": 3 }, { "epoch": 0.0020752269779507134, "grad_norm": 13.402043342590332, "learning_rate": 9.957224306869053e-05, "loss": 0.7777, "step": 4 }, { "epoch": 0.0025940337224383916, "grad_norm": 15.691983222961426, "learning_rate": 9.903926402016153e-05, "loss": 0.5967, "step": 5 }, { "epoch": 0.0031128404669260703, "grad_norm": 13.358585357666016, "learning_rate": 9.829629131445342e-05, "loss": 0.4273, "step": 6 }, { "epoch": 0.0036316472114137485, "grad_norm": 8.41795825958252, "learning_rate": 9.73465064747553e-05, "loss": 0.2902, "step": 7 }, { "epoch": 0.004150453955901427, "grad_norm": 5.917006492614746, "learning_rate": 9.619397662556435e-05, "loss": 0.2733, "step": 8 }, { "epoch": 0.004669260700389105, "grad_norm": 5.552993297576904, "learning_rate": 9.484363707663442e-05, "loss": 0.2524, "step": 9 }, { "epoch": 0.005188067444876783, "grad_norm": 6.439959526062012, "learning_rate": 9.330127018922194e-05, "loss": 0.2657, "step": 10 }, { "epoch": 0.005706874189364461, "grad_norm": 7.775099277496338, "learning_rate": 9.157348061512727e-05, "loss": 0.2694, "step": 11 }, { "epoch": 0.0062256809338521405, "grad_norm": 7.171384334564209, "learning_rate": 8.966766701456177e-05, "loss": 0.2017, "step": 12 }, { "epoch": 0.006744487678339819, "grad_norm": 10.638527870178223, "learning_rate": 8.759199037394887e-05, "loss": 0.5616, "step": 13 }, { "epoch": 0.007263294422827497, "grad_norm": 13.433341979980469, "learning_rate": 8.535533905932738e-05, "loss": 0.5669, "step": 14 }, { "epoch": 0.007782101167315175, "grad_norm": 9.67660140991211, "learning_rate": 8.296729075500344e-05, "loss": 0.4109, "step": 15 }, { "epoch": 0.008300907911802853, "grad_norm": 7.229345321655273, "learning_rate": 8.043807145043604e-05, "loss": 0.2981, "step": 16 }, { "epoch": 0.008819714656290532, "grad_norm": 8.081628799438477, "learning_rate": 7.777851165098012e-05, "loss": 0.3206, "step": 17 }, { "epoch": 0.00933852140077821, "grad_norm": 9.81690502166748, "learning_rate": 7.500000000000001e-05, "loss": 0.2764, "step": 18 }, { "epoch": 0.009857328145265888, "grad_norm": 7.637274265289307, "learning_rate": 7.211443451095007e-05, "loss": 0.221, "step": 19 }, { "epoch": 0.010376134889753566, "grad_norm": 5.528214931488037, "learning_rate": 6.91341716182545e-05, "loss": 0.1908, "step": 20 }, { "epoch": 0.010894941634241245, "grad_norm": 3.7318928241729736, "learning_rate": 6.607197326515808e-05, "loss": 0.1766, "step": 21 }, { "epoch": 0.011413748378728923, "grad_norm": 3.994821548461914, "learning_rate": 6.294095225512603e-05, "loss": 0.1656, "step": 22 }, { "epoch": 0.011932555123216601, "grad_norm": 5.203790664672852, "learning_rate": 5.9754516100806423e-05, "loss": 0.1798, "step": 23 }, { "epoch": 0.012451361867704281, "grad_norm": 7.873574733734131, "learning_rate": 5.6526309611002594e-05, "loss": 0.2008, "step": 24 }, { "epoch": 0.01297016861219196, "grad_norm": 7.9323577880859375, "learning_rate": 5.327015646150716e-05, "loss": 0.2257, "step": 25 }, { "epoch": 0.01297016861219196, "eval_loss": 0.23500166833400726, "eval_runtime": 437.1248, "eval_samples_per_second": 29.705, "eval_steps_per_second": 3.715, "step": 25 }, { "epoch": 0.013488975356679637, "grad_norm": 5.023157119750977, "learning_rate": 5e-05, "loss": 0.6253, "step": 26 }, { "epoch": 0.014007782101167316, "grad_norm": 5.516411781311035, "learning_rate": 4.6729843538492847e-05, "loss": 0.4188, "step": 27 }, { "epoch": 0.014526588845654994, "grad_norm": 5.842824459075928, "learning_rate": 4.347369038899744e-05, "loss": 0.2729, "step": 28 }, { "epoch": 0.015045395590142672, "grad_norm": 4.38772439956665, "learning_rate": 4.0245483899193595e-05, "loss": 0.2712, "step": 29 }, { "epoch": 0.01556420233463035, "grad_norm": 3.1543498039245605, "learning_rate": 3.705904774487396e-05, "loss": 0.199, "step": 30 }, { "epoch": 0.016083009079118027, "grad_norm": 2.990983247756958, "learning_rate": 3.392802673484193e-05, "loss": 0.1729, "step": 31 }, { "epoch": 0.016601815823605707, "grad_norm": 2.678366184234619, "learning_rate": 3.086582838174551e-05, "loss": 0.1649, "step": 32 }, { "epoch": 0.017120622568093387, "grad_norm": 2.735597610473633, "learning_rate": 2.7885565489049946e-05, "loss": 0.1543, "step": 33 }, { "epoch": 0.017639429312581063, "grad_norm": 2.4318928718566895, "learning_rate": 2.500000000000001e-05, "loss": 0.1413, "step": 34 }, { "epoch": 0.018158236057068743, "grad_norm": 2.7358927726745605, "learning_rate": 2.2221488349019903e-05, "loss": 0.179, "step": 35 }, { "epoch": 0.01867704280155642, "grad_norm": 2.9356327056884766, "learning_rate": 1.9561928549563968e-05, "loss": 0.1509, "step": 36 }, { "epoch": 0.0191958495460441, "grad_norm": 4.213629245758057, "learning_rate": 1.703270924499656e-05, "loss": 0.1418, "step": 37 }, { "epoch": 0.019714656290531776, "grad_norm": 4.240565299987793, "learning_rate": 1.4644660940672627e-05, "loss": 0.4204, "step": 38 }, { "epoch": 0.020233463035019456, "grad_norm": 4.311905860900879, "learning_rate": 1.2408009626051137e-05, "loss": 0.3776, "step": 39 }, { "epoch": 0.020752269779507133, "grad_norm": 3.4479880332946777, "learning_rate": 1.0332332985438248e-05, "loss": 0.2912, "step": 40 }, { "epoch": 0.021271076523994813, "grad_norm": 4.918986797332764, "learning_rate": 8.426519384872733e-06, "loss": 0.1922, "step": 41 }, { "epoch": 0.02178988326848249, "grad_norm": 3.2301716804504395, "learning_rate": 6.698729810778065e-06, "loss": 0.2138, "step": 42 }, { "epoch": 0.02230869001297017, "grad_norm": 2.403172016143799, "learning_rate": 5.156362923365588e-06, "loss": 0.1792, "step": 43 }, { "epoch": 0.022827496757457846, "grad_norm": 2.350229024887085, "learning_rate": 3.8060233744356633e-06, "loss": 0.1477, "step": 44 }, { "epoch": 0.023346303501945526, "grad_norm": 2.546405076980591, "learning_rate": 2.653493525244721e-06, "loss": 0.1588, "step": 45 }, { "epoch": 0.023865110246433202, "grad_norm": 2.5611066818237305, "learning_rate": 1.70370868554659e-06, "loss": 0.128, "step": 46 }, { "epoch": 0.024383916990920882, "grad_norm": 2.391011953353882, "learning_rate": 9.607359798384785e-07, "loss": 0.1722, "step": 47 }, { "epoch": 0.024902723735408562, "grad_norm": 2.5774426460266113, "learning_rate": 4.277569313094809e-07, "loss": 0.1483, "step": 48 }, { "epoch": 0.02542153047989624, "grad_norm": 3.330007791519165, "learning_rate": 1.0705383806982606e-07, "loss": 0.1709, "step": 49 }, { "epoch": 0.02594033722438392, "grad_norm": 3.8662326335906982, "learning_rate": 0.0, "loss": 0.1231, "step": 50 }, { "epoch": 0.02594033722438392, "eval_loss": 0.2016909420490265, "eval_runtime": 437.7349, "eval_samples_per_second": 29.664, "eval_steps_per_second": 3.71, "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": 2.9717737929231565e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }