| { | |
| "best_metric": 0.4202527701854706, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3109211037699184, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006218422075398368, | |
| "grad_norm": 0.2913303077220917, | |
| "learning_rate": 5e-05, | |
| "loss": 0.475, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006218422075398368, | |
| "eval_loss": 0.5045433640480042, | |
| "eval_runtime": 0.5095, | |
| "eval_samples_per_second": 98.132, | |
| "eval_steps_per_second": 25.514, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012436844150796735, | |
| "grad_norm": 0.38276663422584534, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018655266226195105, | |
| "grad_norm": 0.3404656946659088, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.5005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02487368830159347, | |
| "grad_norm": 0.3976130783557892, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.5058, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03109211037699184, | |
| "grad_norm": 0.43010473251342773, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.4751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731053245239021, | |
| "grad_norm": 0.3909026086330414, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04352895452778857, | |
| "grad_norm": 0.4095744490623474, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.4334, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04974737660318694, | |
| "grad_norm": 0.3364117443561554, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4534, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05596579867858531, | |
| "grad_norm": 0.38661929965019226, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06218422075398368, | |
| "grad_norm": 0.3577762246131897, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4222, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06840264282938205, | |
| "grad_norm": 0.38591301441192627, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07462106490478042, | |
| "grad_norm": 0.4137956500053406, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4788, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08083948698017877, | |
| "grad_norm": 0.34584131836891174, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.51, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08705790905557714, | |
| "grad_norm": 0.34742724895477295, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5087, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09327633113097551, | |
| "grad_norm": 0.28792425990104675, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5012, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09949475320637388, | |
| "grad_norm": 0.27981409430503845, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4516, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10571317528177225, | |
| "grad_norm": 0.24301674962043762, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.434, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11193159735717062, | |
| "grad_norm": 0.2562877833843231, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.434, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11815001943256899, | |
| "grad_norm": 0.286357581615448, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4251, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12436844150796736, | |
| "grad_norm": 0.2870616614818573, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.43, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13058686358336571, | |
| "grad_norm": 0.3156386613845825, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3893, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1368052856587641, | |
| "grad_norm": 0.3494302034378052, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14302370773416245, | |
| "grad_norm": 0.3314909040927887, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4718, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14924212980956084, | |
| "grad_norm": 0.4106487035751343, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.471, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1554605518849592, | |
| "grad_norm": 0.5664718151092529, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4542, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1554605518849592, | |
| "eval_loss": 0.4245748519897461, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 98.859, | |
| "eval_steps_per_second": 25.703, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16167897396035755, | |
| "grad_norm": 0.20568077266216278, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4854, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16789739603575593, | |
| "grad_norm": 0.231986865401268, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17411581811115429, | |
| "grad_norm": 0.22924061119556427, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4573, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18033424018655267, | |
| "grad_norm": 0.26050734519958496, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4439, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18655266226195102, | |
| "grad_norm": 0.2478851079940796, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 0.2619074285030365, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4037, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19898950641274776, | |
| "grad_norm": 0.2379845380783081, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.3882, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20520792848814615, | |
| "grad_norm": 0.23740604519844055, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4082, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2114263505635445, | |
| "grad_norm": 0.2532176077365875, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4227, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21764477263894286, | |
| "grad_norm": 0.2832277715206146, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4474, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22386319471434124, | |
| "grad_norm": 0.3031919598579407, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4277, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2300816167897396, | |
| "grad_norm": 0.35860636830329895, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4453, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23630003886513798, | |
| "grad_norm": 0.16608692705631256, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24251846094053633, | |
| "grad_norm": 0.1570015847682953, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4632, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24873688301593472, | |
| "grad_norm": 0.17254012823104858, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.446, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2549553050913331, | |
| "grad_norm": 0.1886199414730072, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4512, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26117372716673143, | |
| "grad_norm": 0.19815868139266968, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4144, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2673921492421298, | |
| "grad_norm": 0.2087705135345459, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.3708, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2736105713175282, | |
| "grad_norm": 0.22395019233226776, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4433, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.27982899339292655, | |
| "grad_norm": 0.23942124843597412, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.417, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2860474154683249, | |
| "grad_norm": 0.23817619681358337, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4103, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29226583754372326, | |
| "grad_norm": 0.2759843170642853, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4418, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2984842596191217, | |
| "grad_norm": 0.31546300649642944, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4751, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30470268169452003, | |
| "grad_norm": 0.34774115681648254, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4728, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "grad_norm": 0.5190607905387878, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5034, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "eval_loss": 0.4202527701854706, | |
| "eval_runtime": 0.5035, | |
| "eval_samples_per_second": 99.296, | |
| "eval_steps_per_second": 25.817, | |
| "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": 2.549622476111872e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |