{ "best_metric": 2.8374502658843994, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.055975370836831795, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001119507416736636, "grad_norm": 3.34368896484375, "learning_rate": 5e-05, "loss": 3.5896, "step": 1 }, { "epoch": 0.001119507416736636, "eval_loss": 4.406024932861328, "eval_runtime": 1.1008, "eval_samples_per_second": 45.42, "eval_steps_per_second": 11.809, "step": 1 }, { "epoch": 0.002239014833473272, "grad_norm": 4.087647914886475, "learning_rate": 0.0001, "loss": 3.5123, "step": 2 }, { "epoch": 0.0033585222502099076, "grad_norm": 3.0125415325164795, "learning_rate": 9.990365154573717e-05, "loss": 3.5154, "step": 3 }, { "epoch": 0.004478029666946544, "grad_norm": 2.377248525619507, "learning_rate": 9.961501876182148e-05, "loss": 3.2784, "step": 4 }, { "epoch": 0.00559753708368318, "grad_norm": 2.3651814460754395, "learning_rate": 9.913533761814537e-05, "loss": 3.0696, "step": 5 }, { "epoch": 0.006717044500419815, "grad_norm": 2.3409085273742676, "learning_rate": 9.846666218300807e-05, "loss": 3.1936, "step": 6 }, { "epoch": 0.00783655191715645, "grad_norm": 2.3004684448242188, "learning_rate": 9.761185582727977e-05, "loss": 3.1542, "step": 7 }, { "epoch": 0.008956059333893087, "grad_norm": 2.148057222366333, "learning_rate": 9.657457896300791e-05, "loss": 3.0746, "step": 8 }, { "epoch": 0.010075566750629723, "grad_norm": 2.226046085357666, "learning_rate": 9.535927336897098e-05, "loss": 3.1237, "step": 9 }, { "epoch": 0.01119507416736636, "grad_norm": 2.1537184715270996, "learning_rate": 9.397114317029975e-05, "loss": 3.0671, "step": 10 }, { "epoch": 0.012314581584102995, "grad_norm": 2.403182029724121, "learning_rate": 9.241613255361455e-05, "loss": 3.1898, "step": 11 }, { "epoch": 0.01343408900083963, "grad_norm": 2.4720571041107178, "learning_rate": 9.070090031310558e-05, "loss": 3.0379, "step": 12 }, { "epoch": 0.014553596417576267, "grad_norm": 2.195888042449951, "learning_rate": 8.883279133655399e-05, "loss": 2.7419, "step": 13 }, { "epoch": 0.0156731038343129, "grad_norm": 2.5835275650024414, "learning_rate": 8.681980515339464e-05, "loss": 2.9596, "step": 14 }, { "epoch": 0.016792611251049538, "grad_norm": 1.9123096466064453, "learning_rate": 8.467056167950311e-05, "loss": 2.8389, "step": 15 }, { "epoch": 0.017912118667786175, "grad_norm": 1.7275477647781372, "learning_rate": 8.239426430539243e-05, "loss": 2.8367, "step": 16 }, { "epoch": 0.01903162608452281, "grad_norm": 1.6926486492156982, "learning_rate": 8.000066048588211e-05, "loss": 2.8075, "step": 17 }, { "epoch": 0.020151133501259445, "grad_norm": 1.81813645362854, "learning_rate": 7.75e-05, "loss": 2.9821, "step": 18 }, { "epoch": 0.021270640917996082, "grad_norm": 2.1030478477478027, "learning_rate": 7.490299105985507e-05, "loss": 2.9935, "step": 19 }, { "epoch": 0.02239014833473272, "grad_norm": 1.7944860458374023, "learning_rate": 7.222075445642904e-05, "loss": 2.951, "step": 20 }, { "epoch": 0.023509655751469353, "grad_norm": 1.9337712526321411, "learning_rate": 6.946477593864228e-05, "loss": 2.9447, "step": 21 }, { "epoch": 0.02462916316820599, "grad_norm": 1.9297287464141846, "learning_rate": 6.664685702961344e-05, "loss": 2.8966, "step": 22 }, { "epoch": 0.025748670584942627, "grad_norm": 1.8980144262313843, "learning_rate": 6.377906449072578e-05, "loss": 2.9822, "step": 23 }, { "epoch": 0.02686817800167926, "grad_norm": 1.9796085357666016, "learning_rate": 6.087367864990233e-05, "loss": 2.9736, "step": 24 }, { "epoch": 0.027987685418415897, "grad_norm": 2.6855838298797607, "learning_rate": 5.794314081535644e-05, "loss": 2.9501, "step": 25 }, { "epoch": 0.027987685418415897, "eval_loss": 2.9117090702056885, "eval_runtime": 1.1004, "eval_samples_per_second": 45.439, "eval_steps_per_second": 11.814, "step": 25 }, { "epoch": 0.029107192835152534, "grad_norm": 1.6625885963439941, "learning_rate": 5.500000000000001e-05, "loss": 2.7708, "step": 26 }, { "epoch": 0.030226700251889168, "grad_norm": 1.8415322303771973, "learning_rate": 5.205685918464356e-05, "loss": 2.8309, "step": 27 }, { "epoch": 0.0313462076686258, "grad_norm": 1.7591997385025024, "learning_rate": 4.912632135009769e-05, "loss": 2.9998, "step": 28 }, { "epoch": 0.03246571508536244, "grad_norm": 1.868369221687317, "learning_rate": 4.6220935509274235e-05, "loss": 2.9777, "step": 29 }, { "epoch": 0.033585222502099076, "grad_norm": 1.7001196146011353, "learning_rate": 4.3353142970386564e-05, "loss": 2.9426, "step": 30 }, { "epoch": 0.03470472991883571, "grad_norm": 1.6648975610733032, "learning_rate": 4.053522406135775e-05, "loss": 2.961, "step": 31 }, { "epoch": 0.03582423733557235, "grad_norm": 1.6528427600860596, "learning_rate": 3.777924554357096e-05, "loss": 2.9583, "step": 32 }, { "epoch": 0.036943744752308987, "grad_norm": 1.6447185277938843, "learning_rate": 3.509700894014496e-05, "loss": 2.9051, "step": 33 }, { "epoch": 0.03806325216904562, "grad_norm": 1.9467555284500122, "learning_rate": 3.250000000000001e-05, "loss": 2.89, "step": 34 }, { "epoch": 0.039182759585782254, "grad_norm": 2.022052764892578, "learning_rate": 2.9999339514117912e-05, "loss": 2.9331, "step": 35 }, { "epoch": 0.04030226700251889, "grad_norm": 2.3610732555389404, "learning_rate": 2.760573569460757e-05, "loss": 2.8858, "step": 36 }, { "epoch": 0.04142177441925553, "grad_norm": 2.525616407394409, "learning_rate": 2.53294383204969e-05, "loss": 2.7781, "step": 37 }, { "epoch": 0.042541281835992165, "grad_norm": 1.4379932880401611, "learning_rate": 2.3180194846605367e-05, "loss": 2.8147, "step": 38 }, { "epoch": 0.0436607892527288, "grad_norm": 1.3367565870285034, "learning_rate": 2.1167208663446025e-05, "loss": 2.7604, "step": 39 }, { "epoch": 0.04478029666946544, "grad_norm": 1.3029029369354248, "learning_rate": 1.9299099686894423e-05, "loss": 2.8715, "step": 40 }, { "epoch": 0.04589980408620207, "grad_norm": 1.3365355730056763, "learning_rate": 1.758386744638546e-05, "loss": 2.9184, "step": 41 }, { "epoch": 0.047019311502938706, "grad_norm": 1.3175362348556519, "learning_rate": 1.602885682970026e-05, "loss": 2.8455, "step": 42 }, { "epoch": 0.04813881891967534, "grad_norm": 1.5100023746490479, "learning_rate": 1.464072663102903e-05, "loss": 2.8966, "step": 43 }, { "epoch": 0.04925832633641198, "grad_norm": 1.5187021493911743, "learning_rate": 1.3425421036992098e-05, "loss": 2.9616, "step": 44 }, { "epoch": 0.05037783375314862, "grad_norm": 1.5786397457122803, "learning_rate": 1.2388144172720251e-05, "loss": 2.9971, "step": 45 }, { "epoch": 0.051497341169885254, "grad_norm": 1.468232274055481, "learning_rate": 1.1533337816991932e-05, "loss": 2.9048, "step": 46 }, { "epoch": 0.052616848586621884, "grad_norm": 1.6899412870407104, "learning_rate": 1.0864662381854632e-05, "loss": 3.0045, "step": 47 }, { "epoch": 0.05373635600335852, "grad_norm": 1.7791612148284912, "learning_rate": 1.0384981238178534e-05, "loss": 2.874, "step": 48 }, { "epoch": 0.05485586342009516, "grad_norm": 1.8675801753997803, "learning_rate": 1.0096348454262845e-05, "loss": 2.8556, "step": 49 }, { "epoch": 0.055975370836831795, "grad_norm": 2.566417694091797, "learning_rate": 1e-05, "loss": 2.7583, "step": 50 }, { "epoch": 0.055975370836831795, "eval_loss": 2.8374502658843994, "eval_runtime": 1.0997, "eval_samples_per_second": 45.467, "eval_steps_per_second": 11.821, "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": 1.625316696124293e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }