{ "best_metric": 0.6432160139083862, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.05021340697966357, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010042681395932714, "grad_norm": 2.254211187362671, "learning_rate": 5e-05, "loss": 4.4992, "step": 1 }, { "epoch": 0.0010042681395932714, "eval_loss": 4.846926212310791, "eval_runtime": 54.3122, "eval_samples_per_second": 123.527, "eval_steps_per_second": 15.448, "step": 1 }, { "epoch": 0.002008536279186543, "grad_norm": 2.391191005706787, "learning_rate": 0.0001, "loss": 4.6532, "step": 2 }, { "epoch": 0.003012804418779814, "grad_norm": 2.3409106731414795, "learning_rate": 9.989294616193017e-05, "loss": 4.6151, "step": 3 }, { "epoch": 0.004017072558373086, "grad_norm": 2.4473109245300293, "learning_rate": 9.957224306869053e-05, "loss": 4.3705, "step": 4 }, { "epoch": 0.005021340697966357, "grad_norm": 2.667924404144287, "learning_rate": 9.903926402016153e-05, "loss": 4.1708, "step": 5 }, { "epoch": 0.006025608837559628, "grad_norm": 2.763977527618408, "learning_rate": 9.829629131445342e-05, "loss": 3.9341, "step": 6 }, { "epoch": 0.007029876977152899, "grad_norm": 2.892425537109375, "learning_rate": 9.73465064747553e-05, "loss": 3.6912, "step": 7 }, { "epoch": 0.008034145116746171, "grad_norm": 2.695356607437134, "learning_rate": 9.619397662556435e-05, "loss": 3.4276, "step": 8 }, { "epoch": 0.009038413256339443, "grad_norm": 2.1879594326019287, "learning_rate": 9.484363707663442e-05, "loss": 3.1807, "step": 9 }, { "epoch": 0.010042681395932713, "grad_norm": 1.9437211751937866, "learning_rate": 9.330127018922194e-05, "loss": 3.1358, "step": 10 }, { "epoch": 0.011046949535525985, "grad_norm": 1.8152849674224854, "learning_rate": 9.157348061512727e-05, "loss": 3.0124, "step": 11 }, { "epoch": 0.012051217675119257, "grad_norm": 1.8355774879455566, "learning_rate": 8.966766701456177e-05, "loss": 2.9188, "step": 12 }, { "epoch": 0.013055485814712529, "grad_norm": 1.5440760850906372, "learning_rate": 8.759199037394887e-05, "loss": 2.1174, "step": 13 }, { "epoch": 0.014059753954305799, "grad_norm": 1.5962857007980347, "learning_rate": 8.535533905932738e-05, "loss": 2.0739, "step": 14 }, { "epoch": 0.01506402209389907, "grad_norm": 1.6025574207305908, "learning_rate": 8.296729075500344e-05, "loss": 2.036, "step": 15 }, { "epoch": 0.016068290233492342, "grad_norm": 1.5745021104812622, "learning_rate": 8.043807145043604e-05, "loss": 1.8686, "step": 16 }, { "epoch": 0.017072558373085613, "grad_norm": 1.7517650127410889, "learning_rate": 7.777851165098012e-05, "loss": 1.6934, "step": 17 }, { "epoch": 0.018076826512678886, "grad_norm": 1.8151655197143555, "learning_rate": 7.500000000000001e-05, "loss": 1.5154, "step": 18 }, { "epoch": 0.019081094652272156, "grad_norm": 1.9614224433898926, "learning_rate": 7.211443451095007e-05, "loss": 1.5002, "step": 19 }, { "epoch": 0.020085362791865426, "grad_norm": 2.0666980743408203, "learning_rate": 6.91341716182545e-05, "loss": 1.2345, "step": 20 }, { "epoch": 0.0210896309314587, "grad_norm": 1.8409059047698975, "learning_rate": 6.607197326515808e-05, "loss": 1.119, "step": 21 }, { "epoch": 0.02209389907105197, "grad_norm": 1.869633436203003, "learning_rate": 6.294095225512603e-05, "loss": 1.0931, "step": 22 }, { "epoch": 0.023098167210645244, "grad_norm": 1.5533496141433716, "learning_rate": 5.9754516100806423e-05, "loss": 0.9658, "step": 23 }, { "epoch": 0.024102435350238514, "grad_norm": 1.2804274559020996, "learning_rate": 5.6526309611002594e-05, "loss": 1.0114, "step": 24 }, { "epoch": 0.025106703489831784, "grad_norm": 1.034367561340332, "learning_rate": 5.327015646150716e-05, "loss": 0.8942, "step": 25 }, { "epoch": 0.025106703489831784, "eval_loss": 0.7862718105316162, "eval_runtime": 54.3985, "eval_samples_per_second": 123.331, "eval_steps_per_second": 15.423, "step": 25 }, { "epoch": 0.026110971629425057, "grad_norm": 1.1455990076065063, "learning_rate": 5e-05, "loss": 0.7459, "step": 26 }, { "epoch": 0.027115239769018327, "grad_norm": 1.5568510293960571, "learning_rate": 4.6729843538492847e-05, "loss": 0.7928, "step": 27 }, { "epoch": 0.028119507908611598, "grad_norm": 1.0878664255142212, "learning_rate": 4.347369038899744e-05, "loss": 0.7083, "step": 28 }, { "epoch": 0.02912377604820487, "grad_norm": 0.949036717414856, "learning_rate": 4.0245483899193595e-05, "loss": 0.6149, "step": 29 }, { "epoch": 0.03012804418779814, "grad_norm": 0.7017745971679688, "learning_rate": 3.705904774487396e-05, "loss": 0.6841, "step": 30 }, { "epoch": 0.031132312327391415, "grad_norm": 0.8500891923904419, "learning_rate": 3.392802673484193e-05, "loss": 0.6332, "step": 31 }, { "epoch": 0.032136580466984685, "grad_norm": 0.685302734375, "learning_rate": 3.086582838174551e-05, "loss": 0.629, "step": 32 }, { "epoch": 0.033140848606577955, "grad_norm": 0.7081299424171448, "learning_rate": 2.7885565489049946e-05, "loss": 0.643, "step": 33 }, { "epoch": 0.034145116746171225, "grad_norm": 0.7412989139556885, "learning_rate": 2.500000000000001e-05, "loss": 0.6929, "step": 34 }, { "epoch": 0.0351493848857645, "grad_norm": 0.747283399105072, "learning_rate": 2.2221488349019903e-05, "loss": 0.6811, "step": 35 }, { "epoch": 0.03615365302535777, "grad_norm": 0.8888285756111145, "learning_rate": 1.9561928549563968e-05, "loss": 0.6998, "step": 36 }, { "epoch": 0.03715792116495104, "grad_norm": 0.8620653748512268, "learning_rate": 1.703270924499656e-05, "loss": 0.8258, "step": 37 }, { "epoch": 0.03816218930454431, "grad_norm": 0.8505666255950928, "learning_rate": 1.4644660940672627e-05, "loss": 0.6338, "step": 38 }, { "epoch": 0.03916645744413758, "grad_norm": 0.9013793468475342, "learning_rate": 1.2408009626051137e-05, "loss": 0.6493, "step": 39 }, { "epoch": 0.04017072558373085, "grad_norm": 0.7170226573944092, "learning_rate": 1.0332332985438248e-05, "loss": 0.6643, "step": 40 }, { "epoch": 0.04117499372332413, "grad_norm": 0.7864304184913635, "learning_rate": 8.426519384872733e-06, "loss": 0.65, "step": 41 }, { "epoch": 0.0421792618629174, "grad_norm": 0.5616835355758667, "learning_rate": 6.698729810778065e-06, "loss": 0.5628, "step": 42 }, { "epoch": 0.04318353000251067, "grad_norm": 0.644270658493042, "learning_rate": 5.156362923365588e-06, "loss": 0.5768, "step": 43 }, { "epoch": 0.04418779814210394, "grad_norm": 0.650669276714325, "learning_rate": 3.8060233744356633e-06, "loss": 0.6751, "step": 44 }, { "epoch": 0.04519206628169721, "grad_norm": 0.6862338185310364, "learning_rate": 2.653493525244721e-06, "loss": 0.6439, "step": 45 }, { "epoch": 0.04619633442129049, "grad_norm": 0.7162413597106934, "learning_rate": 1.70370868554659e-06, "loss": 0.5825, "step": 46 }, { "epoch": 0.04720060256088376, "grad_norm": 0.7476317286491394, "learning_rate": 9.607359798384785e-07, "loss": 0.6402, "step": 47 }, { "epoch": 0.04820487070047703, "grad_norm": 0.6151590347290039, "learning_rate": 4.277569313094809e-07, "loss": 0.65, "step": 48 }, { "epoch": 0.0492091388400703, "grad_norm": 0.767148494720459, "learning_rate": 1.0705383806982606e-07, "loss": 0.7045, "step": 49 }, { "epoch": 0.05021340697966357, "grad_norm": 0.6965320706367493, "learning_rate": 0.0, "loss": 0.7126, "step": 50 }, { "epoch": 0.05021340697966357, "eval_loss": 0.6432160139083862, "eval_runtime": 54.4393, "eval_samples_per_second": 123.238, "eval_steps_per_second": 15.412, "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": 8.336768348717056e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }