{ "best_metric": 4.832469463348389, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.018947019397011107, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00037894038794022213, "grad_norm": 3.85332989692688, "learning_rate": 5e-05, "loss": 7.9055, "step": 1 }, { "epoch": 0.00037894038794022213, "eval_loss": 10.32066535949707, "eval_runtime": 49.7576, "eval_samples_per_second": 357.292, "eval_steps_per_second": 44.677, "step": 1 }, { "epoch": 0.0007578807758804443, "grad_norm": 4.732010841369629, "learning_rate": 0.0001, "loss": 8.9497, "step": 2 }, { "epoch": 0.0011368211638206665, "grad_norm": 6.777773380279541, "learning_rate": 9.989294616193017e-05, "loss": 9.2294, "step": 3 }, { "epoch": 0.0015157615517608885, "grad_norm": 5.981103420257568, "learning_rate": 9.957224306869053e-05, "loss": 9.0466, "step": 4 }, { "epoch": 0.0018947019397011107, "grad_norm": 6.652340888977051, "learning_rate": 9.903926402016153e-05, "loss": 9.5321, "step": 5 }, { "epoch": 0.002273642327641333, "grad_norm": 6.979233264923096, "learning_rate": 9.829629131445342e-05, "loss": 9.0279, "step": 6 }, { "epoch": 0.002652582715581555, "grad_norm": 5.1045098304748535, "learning_rate": 9.73465064747553e-05, "loss": 8.9, "step": 7 }, { "epoch": 0.003031523103521777, "grad_norm": 5.81050443649292, "learning_rate": 9.619397662556435e-05, "loss": 8.9322, "step": 8 }, { "epoch": 0.0034104634914619994, "grad_norm": 4.246511459350586, "learning_rate": 9.484363707663442e-05, "loss": 8.7202, "step": 9 }, { "epoch": 0.0037894038794022214, "grad_norm": 5.267040252685547, "learning_rate": 9.330127018922194e-05, "loss": 8.849, "step": 10 }, { "epoch": 0.004168344267342443, "grad_norm": 4.847978591918945, "learning_rate": 9.157348061512727e-05, "loss": 9.0714, "step": 11 }, { "epoch": 0.004547284655282666, "grad_norm": 4.391917705535889, "learning_rate": 8.966766701456177e-05, "loss": 9.0887, "step": 12 }, { "epoch": 0.004926225043222888, "grad_norm": 3.459029197692871, "learning_rate": 8.759199037394887e-05, "loss": 7.3196, "step": 13 }, { "epoch": 0.00530516543116311, "grad_norm": 2.6703901290893555, "learning_rate": 8.535533905932738e-05, "loss": 6.6516, "step": 14 }, { "epoch": 0.005684105819103332, "grad_norm": 2.962366819381714, "learning_rate": 8.296729075500344e-05, "loss": 6.7315, "step": 15 }, { "epoch": 0.006063046207043554, "grad_norm": 3.2031960487365723, "learning_rate": 8.043807145043604e-05, "loss": 6.7804, "step": 16 }, { "epoch": 0.006441986594983777, "grad_norm": 3.1914448738098145, "learning_rate": 7.777851165098012e-05, "loss": 6.5232, "step": 17 }, { "epoch": 0.006820926982923999, "grad_norm": 3.29257869720459, "learning_rate": 7.500000000000001e-05, "loss": 6.498, "step": 18 }, { "epoch": 0.007199867370864221, "grad_norm": 3.7383933067321777, "learning_rate": 7.211443451095007e-05, "loss": 6.475, "step": 19 }, { "epoch": 0.007578807758804443, "grad_norm": 3.9719223976135254, "learning_rate": 6.91341716182545e-05, "loss": 6.3644, "step": 20 }, { "epoch": 0.007957748146744666, "grad_norm": 3.7263057231903076, "learning_rate": 6.607197326515808e-05, "loss": 6.4056, "step": 21 }, { "epoch": 0.008336688534684887, "grad_norm": 4.621120929718018, "learning_rate": 6.294095225512603e-05, "loss": 6.1503, "step": 22 }, { "epoch": 0.00871562892262511, "grad_norm": 4.670963287353516, "learning_rate": 5.9754516100806423e-05, "loss": 6.0622, "step": 23 }, { "epoch": 0.009094569310565332, "grad_norm": 4.76012659072876, "learning_rate": 5.6526309611002594e-05, "loss": 5.9367, "step": 24 }, { "epoch": 0.009473509698505553, "grad_norm": 5.220454216003418, "learning_rate": 5.327015646150716e-05, "loss": 5.9759, "step": 25 }, { "epoch": 0.009473509698505553, "eval_loss": 5.363160133361816, "eval_runtime": 49.7192, "eval_samples_per_second": 357.568, "eval_steps_per_second": 44.711, "step": 25 }, { "epoch": 0.009852450086445776, "grad_norm": 2.8592782020568848, "learning_rate": 5e-05, "loss": 5.1642, "step": 26 }, { "epoch": 0.010231390474385997, "grad_norm": 3.3668901920318604, "learning_rate": 4.6729843538492847e-05, "loss": 4.9931, "step": 27 }, { "epoch": 0.01061033086232622, "grad_norm": 3.769247531890869, "learning_rate": 4.347369038899744e-05, "loss": 5.0043, "step": 28 }, { "epoch": 0.010989271250266443, "grad_norm": 4.0553297996521, "learning_rate": 4.0245483899193595e-05, "loss": 5.0804, "step": 29 }, { "epoch": 0.011368211638206664, "grad_norm": 3.99537992477417, "learning_rate": 3.705904774487396e-05, "loss": 5.123, "step": 30 }, { "epoch": 0.011747152026146887, "grad_norm": 4.698930263519287, "learning_rate": 3.392802673484193e-05, "loss": 5.0135, "step": 31 }, { "epoch": 0.012126092414087108, "grad_norm": 4.247986316680908, "learning_rate": 3.086582838174551e-05, "loss": 4.9207, "step": 32 }, { "epoch": 0.012505032802027331, "grad_norm": 3.5553126335144043, "learning_rate": 2.7885565489049946e-05, "loss": 4.9427, "step": 33 }, { "epoch": 0.012883973189967554, "grad_norm": 3.068984031677246, "learning_rate": 2.500000000000001e-05, "loss": 4.9177, "step": 34 }, { "epoch": 0.013262913577907775, "grad_norm": 3.0896942615509033, "learning_rate": 2.2221488349019903e-05, "loss": 4.9117, "step": 35 }, { "epoch": 0.013641853965847998, "grad_norm": 2.157078266143799, "learning_rate": 1.9561928549563968e-05, "loss": 4.8537, "step": 36 }, { "epoch": 0.014020794353788219, "grad_norm": 3.4221081733703613, "learning_rate": 1.703270924499656e-05, "loss": 5.1317, "step": 37 }, { "epoch": 0.014399734741728442, "grad_norm": 2.8120241165161133, "learning_rate": 1.4644660940672627e-05, "loss": 5.0818, "step": 38 }, { "epoch": 0.014778675129668664, "grad_norm": 3.566973924636841, "learning_rate": 1.2408009626051137e-05, "loss": 4.7874, "step": 39 }, { "epoch": 0.015157615517608886, "grad_norm": 3.3742949962615967, "learning_rate": 1.0332332985438248e-05, "loss": 4.8105, "step": 40 }, { "epoch": 0.015536555905549108, "grad_norm": 2.7615294456481934, "learning_rate": 8.426519384872733e-06, "loss": 4.736, "step": 41 }, { "epoch": 0.01591549629348933, "grad_norm": 2.8716986179351807, "learning_rate": 6.698729810778065e-06, "loss": 4.8706, "step": 42 }, { "epoch": 0.016294436681429554, "grad_norm": 2.268878221511841, "learning_rate": 5.156362923365588e-06, "loss": 5.0533, "step": 43 }, { "epoch": 0.016673377069369773, "grad_norm": 2.9596915245056152, "learning_rate": 3.8060233744356633e-06, "loss": 4.745, "step": 44 }, { "epoch": 0.017052317457309996, "grad_norm": 2.2583632469177246, "learning_rate": 2.653493525244721e-06, "loss": 4.6773, "step": 45 }, { "epoch": 0.01743125784525022, "grad_norm": 3.824549674987793, "learning_rate": 1.70370868554659e-06, "loss": 4.8859, "step": 46 }, { "epoch": 0.017810198233190442, "grad_norm": 2.705209970474243, "learning_rate": 9.607359798384785e-07, "loss": 4.986, "step": 47 }, { "epoch": 0.018189138621130665, "grad_norm": 2.4990625381469727, "learning_rate": 4.277569313094809e-07, "loss": 5.0115, "step": 48 }, { "epoch": 0.018568079009070884, "grad_norm": 2.7045373916625977, "learning_rate": 1.0705383806982606e-07, "loss": 4.8936, "step": 49 }, { "epoch": 0.018947019397011107, "grad_norm": 3.766317367553711, "learning_rate": 0.0, "loss": 5.2797, "step": 50 }, { "epoch": 0.018947019397011107, "eval_loss": 4.832469463348389, "eval_runtime": 49.6333, "eval_samples_per_second": 358.187, "eval_steps_per_second": 44.788, "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": 1.13737243557888e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }