| { | |
| "best_metric": 0.14273174107074738, | |
| "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": 195.5614013671875, | |
| "learning_rate": 5e-05, | |
| "loss": 183.4214, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "eval_loss": 6.080627918243408, | |
| "eval_runtime": 4.0984, | |
| "eval_samples_per_second": 12.2, | |
| "eval_steps_per_second": 3.172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010300981812328988, | |
| "grad_norm": 212.53482055664062, | |
| "learning_rate": 0.0001, | |
| "loss": 184.5833, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 182.6468963623047, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 173.0269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020601963624657976, | |
| "grad_norm": 172.3017120361328, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 161.0496, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02575245453082247, | |
| "grad_norm": 148.2727813720703, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 127.753, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 159.01747131347656, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 109.5256, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03605343634315146, | |
| "grad_norm": 125.15324401855469, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 84.6997, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04120392724931595, | |
| "grad_norm": 95.49300384521484, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 76.9491, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 85.85482025146484, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 69.9889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05150490906164494, | |
| "grad_norm": 102.58478546142578, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 64.823, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05665539996780943, | |
| "grad_norm": 96.248291015625, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 62.2639, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 107.83429718017578, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 56.1169, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06695638178013842, | |
| "grad_norm": 96.302001953125, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 63.8062, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07210687268630292, | |
| "grad_norm": 139.03134155273438, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 47.5832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 91.16569519042969, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 41.2896, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0824078544986319, | |
| "grad_norm": 101.69834899902344, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 40.1252, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0875583454047964, | |
| "grad_norm": 94.4932861328125, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 35.824, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 65.91960906982422, | |
| "learning_rate": 7.75e-05, | |
| "loss": 32.7603, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 45.94514846801758, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 28.143, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10300981812328988, | |
| "grad_norm": 49.135292053222656, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 24.3015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 52.58118438720703, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 24.7888, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11331079993561886, | |
| "grad_norm": 40.06536865234375, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 21.0641, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11846129084178336, | |
| "grad_norm": 61.566043853759766, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 19.7781, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 54.66169357299805, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 20.4498, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "grad_norm": 158.48204040527344, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 31.4924, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "eval_loss": 0.5459790825843811, | |
| "eval_runtime": 4.1249, | |
| "eval_samples_per_second": 12.121, | |
| "eval_steps_per_second": 3.152, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13391276356027684, | |
| "grad_norm": 135.01632690429688, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 19.2796, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13906325446644133, | |
| "grad_norm": 122.40741729736328, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 20.3915, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14421374537260584, | |
| "grad_norm": 77.29145050048828, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 15.7624, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14936423627877032, | |
| "grad_norm": 71.43122863769531, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 16.1651, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 60.62587356567383, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15966521809109932, | |
| "grad_norm": 69.12200927734375, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 14.7872, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1648157089972638, | |
| "grad_norm": 48.978023529052734, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 8.8029, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1699661999034283, | |
| "grad_norm": 47.26166534423828, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.5402, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1751166908095928, | |
| "grad_norm": 49.96639633178711, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 8.8643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18026718171575729, | |
| "grad_norm": 47.3193359375, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.71, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18541767262192177, | |
| "grad_norm": 55.040592193603516, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 9.0711, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19056816352808628, | |
| "grad_norm": 60.64955520629883, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.7455, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19571865443425077, | |
| "grad_norm": 96.02499389648438, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 14.7612, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20086914534041525, | |
| "grad_norm": 68.96138763427734, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.6281, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20601963624657976, | |
| "grad_norm": 78.70532989501953, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 9.8648, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21117012715274425, | |
| "grad_norm": 73.4675521850586, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.5117, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21632061805890873, | |
| "grad_norm": 60.545936584472656, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.5021, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22147110896507324, | |
| "grad_norm": 47.23418045043945, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 7.5249, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22662159987123773, | |
| "grad_norm": 33.51955795288086, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 5.3886, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2317720907774022, | |
| "grad_norm": 40.547977447509766, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 5.9733, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23692258168356672, | |
| "grad_norm": 34.97176742553711, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 5.6807, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2420730725897312, | |
| "grad_norm": 79.3729476928711, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.1564, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2472235634958957, | |
| "grad_norm": 46.89299011230469, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.3804, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2523740544020602, | |
| "grad_norm": 77.9176025390625, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 8.2541, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "grad_norm": 107.83366394042969, | |
| "learning_rate": 1e-05, | |
| "loss": 10.4399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2575245453082247, | |
| "eval_loss": 0.14273174107074738, | |
| "eval_runtime": 4.1412, | |
| "eval_samples_per_second": 12.074, | |
| "eval_steps_per_second": 3.139, | |
| "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": 5.259104775831552e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |