{ "best_metric": 0.5959730744361877, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.06441742491343909, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012883484982687816, "grad_norm": 47.74828338623047, "learning_rate": 5e-05, "loss": 60.1193, "step": 1 }, { "epoch": 0.0012883484982687816, "eval_loss": 2.737609624862671, "eval_runtime": 4.0363, "eval_samples_per_second": 12.388, "eval_steps_per_second": 3.221, "step": 1 }, { "epoch": 0.0025766969965375633, "grad_norm": 52.07981872558594, "learning_rate": 0.0001, "loss": 65.2752, "step": 2 }, { "epoch": 0.0038650454948063453, "grad_norm": 53.02178955078125, "learning_rate": 9.990365154573717e-05, "loss": 71.0158, "step": 3 }, { "epoch": 0.0051533939930751265, "grad_norm": 49.45180130004883, "learning_rate": 9.961501876182148e-05, "loss": 64.6643, "step": 4 }, { "epoch": 0.006441742491343909, "grad_norm": 53.41954803466797, "learning_rate": 9.913533761814537e-05, "loss": 63.4683, "step": 5 }, { "epoch": 0.007730090989612691, "grad_norm": 57.45022964477539, "learning_rate": 9.846666218300807e-05, "loss": 58.8768, "step": 6 }, { "epoch": 0.009018439487881473, "grad_norm": 53.29356384277344, "learning_rate": 9.761185582727977e-05, "loss": 55.455, "step": 7 }, { "epoch": 0.010306787986150253, "grad_norm": 58.60855484008789, "learning_rate": 9.657457896300791e-05, "loss": 53.6345, "step": 8 }, { "epoch": 0.011595136484419035, "grad_norm": 43.34990310668945, "learning_rate": 9.535927336897098e-05, "loss": 49.319, "step": 9 }, { "epoch": 0.012883484982687817, "grad_norm": 51.94438934326172, "learning_rate": 9.397114317029975e-05, "loss": 47.5107, "step": 10 }, { "epoch": 0.0141718334809566, "grad_norm": 89.59423065185547, "learning_rate": 9.241613255361455e-05, "loss": 48.6819, "step": 11 }, { "epoch": 0.015460181979225381, "grad_norm": 62.05713653564453, "learning_rate": 9.070090031310558e-05, "loss": 46.9314, "step": 12 }, { "epoch": 0.016748530477494163, "grad_norm": 60.64547348022461, "learning_rate": 8.883279133655399e-05, "loss": 40.062, "step": 13 }, { "epoch": 0.018036878975762945, "grad_norm": 60.0198974609375, "learning_rate": 8.681980515339464e-05, "loss": 31.1011, "step": 14 }, { "epoch": 0.019325227474031724, "grad_norm": 31.260957717895508, "learning_rate": 8.467056167950311e-05, "loss": 32.1334, "step": 15 }, { "epoch": 0.020613575972300506, "grad_norm": 28.64781379699707, "learning_rate": 8.239426430539243e-05, "loss": 30.3827, "step": 16 }, { "epoch": 0.021901924470569288, "grad_norm": 26.1505184173584, "learning_rate": 8.000066048588211e-05, "loss": 31.5791, "step": 17 }, { "epoch": 0.02319027296883807, "grad_norm": 24.561674118041992, "learning_rate": 7.75e-05, "loss": 31.1872, "step": 18 }, { "epoch": 0.024478621467106852, "grad_norm": 24.411466598510742, "learning_rate": 7.490299105985507e-05, "loss": 31.015, "step": 19 }, { "epoch": 0.025766969965375634, "grad_norm": 27.378705978393555, "learning_rate": 7.222075445642904e-05, "loss": 30.0596, "step": 20 }, { "epoch": 0.027055318463644416, "grad_norm": 25.522066116333008, "learning_rate": 6.946477593864228e-05, "loss": 29.9801, "step": 21 }, { "epoch": 0.0283436669619132, "grad_norm": 25.884302139282227, "learning_rate": 6.664685702961344e-05, "loss": 30.5391, "step": 22 }, { "epoch": 0.02963201546018198, "grad_norm": 24.257429122924805, "learning_rate": 6.377906449072578e-05, "loss": 27.3257, "step": 23 }, { "epoch": 0.030920363958450763, "grad_norm": 26.360279083251953, "learning_rate": 6.087367864990233e-05, "loss": 27.9433, "step": 24 }, { "epoch": 0.032208712456719545, "grad_norm": 33.31407928466797, "learning_rate": 5.794314081535644e-05, "loss": 25.2059, "step": 25 }, { "epoch": 0.032208712456719545, "eval_loss": 0.8500383496284485, "eval_runtime": 4.0452, "eval_samples_per_second": 12.36, "eval_steps_per_second": 3.214, "step": 25 }, { "epoch": 0.03349706095498833, "grad_norm": 36.786380767822266, "learning_rate": 5.500000000000001e-05, "loss": 24.4882, "step": 26 }, { "epoch": 0.03478540945325711, "grad_norm": 30.23247718811035, "learning_rate": 5.205685918464356e-05, "loss": 20.899, "step": 27 }, { "epoch": 0.03607375795152589, "grad_norm": 25.97867774963379, "learning_rate": 4.912632135009769e-05, "loss": 21.0023, "step": 28 }, { "epoch": 0.03736210644979467, "grad_norm": 25.808292388916016, "learning_rate": 4.6220935509274235e-05, "loss": 21.7714, "step": 29 }, { "epoch": 0.03865045494806345, "grad_norm": 25.219738006591797, "learning_rate": 4.3353142970386564e-05, "loss": 21.4146, "step": 30 }, { "epoch": 0.03993880344633223, "grad_norm": 25.33234405517578, "learning_rate": 4.053522406135775e-05, "loss": 20.8488, "step": 31 }, { "epoch": 0.04122715194460101, "grad_norm": 25.538942337036133, "learning_rate": 3.777924554357096e-05, "loss": 20.4944, "step": 32 }, { "epoch": 0.042515500442869794, "grad_norm": 21.4976806640625, "learning_rate": 3.509700894014496e-05, "loss": 20.7936, "step": 33 }, { "epoch": 0.043803848941138576, "grad_norm": 20.464054107666016, "learning_rate": 3.250000000000001e-05, "loss": 20.0772, "step": 34 }, { "epoch": 0.04509219743940736, "grad_norm": 22.029733657836914, "learning_rate": 2.9999339514117912e-05, "loss": 19.865, "step": 35 }, { "epoch": 0.04638054593767614, "grad_norm": 24.57637596130371, "learning_rate": 2.760573569460757e-05, "loss": 20.4681, "step": 36 }, { "epoch": 0.04766889443594492, "grad_norm": 28.762798309326172, "learning_rate": 2.53294383204969e-05, "loss": 20.6765, "step": 37 }, { "epoch": 0.048957242934213704, "grad_norm": 24.132606506347656, "learning_rate": 2.3180194846605367e-05, "loss": 19.2762, "step": 38 }, { "epoch": 0.050245591432482486, "grad_norm": 23.08111572265625, "learning_rate": 2.1167208663446025e-05, "loss": 16.6165, "step": 39 }, { "epoch": 0.05153393993075127, "grad_norm": 31.887020111083984, "learning_rate": 1.9299099686894423e-05, "loss": 17.2033, "step": 40 }, { "epoch": 0.05282228842902005, "grad_norm": 24.805381774902344, "learning_rate": 1.758386744638546e-05, "loss": 17.0512, "step": 41 }, { "epoch": 0.05411063692728883, "grad_norm": 20.134519577026367, "learning_rate": 1.602885682970026e-05, "loss": 18.2023, "step": 42 }, { "epoch": 0.055398985425557615, "grad_norm": 21.636701583862305, "learning_rate": 1.464072663102903e-05, "loss": 18.1528, "step": 43 }, { "epoch": 0.0566873339238264, "grad_norm": 20.0654239654541, "learning_rate": 1.3425421036992098e-05, "loss": 17.2441, "step": 44 }, { "epoch": 0.05797568242209518, "grad_norm": 22.05454444885254, "learning_rate": 1.2388144172720251e-05, "loss": 17.1469, "step": 45 }, { "epoch": 0.05926403092036396, "grad_norm": 24.00516700744629, "learning_rate": 1.1533337816991932e-05, "loss": 17.1651, "step": 46 }, { "epoch": 0.06055237941863274, "grad_norm": 26.142593383789062, "learning_rate": 1.0864662381854632e-05, "loss": 17.647, "step": 47 }, { "epoch": 0.061840727916901525, "grad_norm": 31.736303329467773, "learning_rate": 1.0384981238178534e-05, "loss": 18.2049, "step": 48 }, { "epoch": 0.06312907641517031, "grad_norm": 26.826133728027344, "learning_rate": 1.0096348454262845e-05, "loss": 17.8961, "step": 49 }, { "epoch": 0.06441742491343909, "grad_norm": 34.61617660522461, "learning_rate": 1e-05, "loss": 17.9098, "step": 50 }, { "epoch": 0.06441742491343909, "eval_loss": 0.5959730744361877, "eval_runtime": 4.0545, "eval_samples_per_second": 12.332, "eval_steps_per_second": 3.206, "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": 5.268143856628531e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }