| { | |
| "best_metric": 1.1413780450820923, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2575245453082247, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005150490906164494, | |
| "grad_norm": 1.6360301971435547, | |
| "learning_rate": 5e-05, | |
| "loss": 1.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "eval_loss": 1.8850927352905273, | |
| "eval_runtime": 3.9577, | |
| "eval_samples_per_second": 12.634, | |
| "eval_steps_per_second": 3.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010300981812328988, | |
| "grad_norm": 1.687415361404419, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 1.6830966472625732, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020601963624657976, | |
| "grad_norm": 1.520763874053955, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.5323, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02575245453082247, | |
| "grad_norm": 1.2332735061645508, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4831, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 0.957449734210968, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3928, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03605343634315146, | |
| "grad_norm": 0.9580352902412415, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3336, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04120392724931595, | |
| "grad_norm": 0.9211961030960083, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3421, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 0.9401556253433228, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05150490906164494, | |
| "grad_norm": 1.0537054538726807, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1164, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05665539996780943, | |
| "grad_norm": 1.024180293083191, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0345, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 1.2686243057250977, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0674, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06695638178013842, | |
| "grad_norm": 1.3576205968856812, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6091, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07210687268630292, | |
| "grad_norm": 0.9457244873046875, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4211, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 0.6527680158615112, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.3348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0824078544986319, | |
| "grad_norm": 0.8764634132385254, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3786, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0875583454047964, | |
| "grad_norm": 0.7613826394081116, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.26, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 0.8126055598258972, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2384, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 0.7038941979408264, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1189, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10300981812328988, | |
| "grad_norm": 0.7687941193580627, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 0.8610501885414124, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2106, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11331079993561886, | |
| "grad_norm": 0.7789077758789062, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.08, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11846129084178336, | |
| "grad_norm": 0.8925905227661133, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.0633, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 1.111682653427124, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0581, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "grad_norm": 1.133190393447876, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "eval_loss": 1.1935243606567383, | |
| "eval_runtime": 4.029, | |
| "eval_samples_per_second": 12.41, | |
| "eval_steps_per_second": 3.227, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13391276356027684, | |
| "grad_norm": 0.7202064990997314, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4946, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13906325446644133, | |
| "grad_norm": 0.6264328956604004, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.306, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14421374537260584, | |
| "grad_norm": 0.6478198766708374, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14936423627877032, | |
| "grad_norm": 0.668978750705719, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3147, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 0.632352352142334, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1565, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15966521809109932, | |
| "grad_norm": 0.6676881313323975, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1182, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1648157089972638, | |
| "grad_norm": 0.7223697304725647, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0622, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1699661999034283, | |
| "grad_norm": 0.7997718453407288, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.1029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1751166908095928, | |
| "grad_norm": 0.8181374073028564, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0938, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18026718171575729, | |
| "grad_norm": 0.8765294551849365, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18541767262192177, | |
| "grad_norm": 0.9284154772758484, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.9693, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19056816352808628, | |
| "grad_norm": 1.0015588998794556, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.9085, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19571865443425077, | |
| "grad_norm": 0.6769429445266724, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.431, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20086914534041525, | |
| "grad_norm": 0.6472747921943665, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3343, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20601963624657976, | |
| "grad_norm": 0.6668629050254822, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2378, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21117012715274425, | |
| "grad_norm": 0.6501740217208862, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2057, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21632061805890873, | |
| "grad_norm": 0.6348807215690613, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.2059, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22147110896507324, | |
| "grad_norm": 0.6721872687339783, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1817, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22662159987123773, | |
| "grad_norm": 0.71291184425354, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1455, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2317720907774022, | |
| "grad_norm": 0.7063342928886414, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1157, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23692258168356672, | |
| "grad_norm": 0.7762175798416138, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0917, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2420730725897312, | |
| "grad_norm": 0.8917137384414673, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0488, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2472235634958957, | |
| "grad_norm": 0.9136678576469421, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9057, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2523740544020602, | |
| "grad_norm": 1.0555641651153564, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0153, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "grad_norm": 1.1923260688781738, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8982, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "eval_loss": 1.1413780450820923, | |
| "eval_runtime": 4.0246, | |
| "eval_samples_per_second": 12.424, | |
| "eval_steps_per_second": 3.23, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |