{ "best_metric": 0.4198492467403412, "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": 0.2938142418861389, "learning_rate": 5e-05, "loss": 0.475, "step": 1 }, { "epoch": 0.006218422075398368, "eval_loss": 0.5045433640480042, "eval_runtime": 0.4948, "eval_samples_per_second": 101.053, "eval_steps_per_second": 26.274, "step": 1 }, { "epoch": 0.012436844150796735, "grad_norm": 0.3861386477947235, "learning_rate": 0.0001, "loss": 0.5375, "step": 2 }, { "epoch": 0.018655266226195105, "grad_norm": 0.34065696597099304, "learning_rate": 9.990365154573717e-05, "loss": 0.5006, "step": 3 }, { "epoch": 0.02487368830159347, "grad_norm": 0.40435275435447693, "learning_rate": 9.961501876182148e-05, "loss": 0.5056, "step": 4 }, { "epoch": 0.03109211037699184, "grad_norm": 0.43497732281684875, "learning_rate": 9.913533761814537e-05, "loss": 0.4753, "step": 5 }, { "epoch": 0.03731053245239021, "grad_norm": 0.3978385031223297, "learning_rate": 9.846666218300807e-05, "loss": 0.4252, "step": 6 }, { "epoch": 0.04352895452778857, "grad_norm": 0.4112544059753418, "learning_rate": 9.761185582727977e-05, "loss": 0.434, "step": 7 }, { "epoch": 0.04974737660318694, "grad_norm": 0.3372468948364258, "learning_rate": 9.657457896300791e-05, "loss": 0.4532, "step": 8 }, { "epoch": 0.05596579867858531, "grad_norm": 0.3874565064907074, "learning_rate": 9.535927336897098e-05, "loss": 0.4427, "step": 9 }, { "epoch": 0.06218422075398368, "grad_norm": 0.3573532998561859, "learning_rate": 9.397114317029975e-05, "loss": 0.4222, "step": 10 }, { "epoch": 0.06840264282938205, "grad_norm": 0.38587290048599243, "learning_rate": 9.241613255361455e-05, "loss": 0.4726, "step": 11 }, { "epoch": 0.07462106490478042, "grad_norm": 0.4130932092666626, "learning_rate": 9.070090031310558e-05, "loss": 0.479, "step": 12 }, { "epoch": 0.08083948698017877, "grad_norm": 0.344505250453949, "learning_rate": 8.883279133655399e-05, "loss": 0.5099, "step": 13 }, { "epoch": 0.08705790905557714, "grad_norm": 0.34664738178253174, "learning_rate": 8.681980515339464e-05, "loss": 0.5085, "step": 14 }, { "epoch": 0.09327633113097551, "grad_norm": 0.29058223962783813, "learning_rate": 8.467056167950311e-05, "loss": 0.5014, "step": 15 }, { "epoch": 0.09949475320637388, "grad_norm": 0.2800789773464203, "learning_rate": 8.239426430539243e-05, "loss": 0.4521, "step": 16 }, { "epoch": 0.10571317528177225, "grad_norm": 0.24397477507591248, "learning_rate": 8.000066048588211e-05, "loss": 0.4335, "step": 17 }, { "epoch": 0.11193159735717062, "grad_norm": 0.25632143020629883, "learning_rate": 7.75e-05, "loss": 0.4342, "step": 18 }, { "epoch": 0.11815001943256899, "grad_norm": 0.2876015901565552, "learning_rate": 7.490299105985507e-05, "loss": 0.4253, "step": 19 }, { "epoch": 0.12436844150796736, "grad_norm": 0.2885887026786804, "learning_rate": 7.222075445642904e-05, "loss": 0.4304, "step": 20 }, { "epoch": 0.13058686358336571, "grad_norm": 0.3172941505908966, "learning_rate": 6.946477593864228e-05, "loss": 0.3891, "step": 21 }, { "epoch": 0.1368052856587641, "grad_norm": 0.35131096839904785, "learning_rate": 6.664685702961344e-05, "loss": 0.471, "step": 22 }, { "epoch": 0.14302370773416245, "grad_norm": 0.3315542936325073, "learning_rate": 6.377906449072578e-05, "loss": 0.4715, "step": 23 }, { "epoch": 0.14924212980956084, "grad_norm": 0.41036635637283325, "learning_rate": 6.087367864990233e-05, "loss": 0.4712, "step": 24 }, { "epoch": 0.1554605518849592, "grad_norm": 0.5655457973480225, "learning_rate": 5.794314081535644e-05, "loss": 0.4544, "step": 25 }, { "epoch": 0.1554605518849592, "eval_loss": 0.4247874319553375, "eval_runtime": 0.49, "eval_samples_per_second": 102.041, "eval_steps_per_second": 26.531, "step": 25 }, { "epoch": 0.16167897396035755, "grad_norm": 0.21193577349185944, "learning_rate": 5.500000000000001e-05, "loss": 0.4856, "step": 26 }, { "epoch": 0.16789739603575593, "grad_norm": 0.23560740053653717, "learning_rate": 5.205685918464356e-05, "loss": 0.472, "step": 27 }, { "epoch": 0.17411581811115429, "grad_norm": 0.23074764013290405, "learning_rate": 4.912632135009769e-05, "loss": 0.4575, "step": 28 }, { "epoch": 0.18033424018655267, "grad_norm": 0.26272693276405334, "learning_rate": 4.6220935509274235e-05, "loss": 0.4441, "step": 29 }, { "epoch": 0.18655266226195102, "grad_norm": 0.247560054063797, "learning_rate": 4.3353142970386564e-05, "loss": 0.4636, "step": 30 }, { "epoch": 0.1927710843373494, "grad_norm": 0.2640223801136017, "learning_rate": 4.053522406135775e-05, "loss": 0.4034, "step": 31 }, { "epoch": 0.19898950641274776, "grad_norm": 0.23952776193618774, "learning_rate": 3.777924554357096e-05, "loss": 0.3886, "step": 32 }, { "epoch": 0.20520792848814615, "grad_norm": 0.23826071619987488, "learning_rate": 3.509700894014496e-05, "loss": 0.4077, "step": 33 }, { "epoch": 0.2114263505635445, "grad_norm": 0.2540220618247986, "learning_rate": 3.250000000000001e-05, "loss": 0.4229, "step": 34 }, { "epoch": 0.21764477263894286, "grad_norm": 0.28340867161750793, "learning_rate": 2.9999339514117912e-05, "loss": 0.4471, "step": 35 }, { "epoch": 0.22386319471434124, "grad_norm": 0.3024127185344696, "learning_rate": 2.760573569460757e-05, "loss": 0.4278, "step": 36 }, { "epoch": 0.2300816167897396, "grad_norm": 0.3641083836555481, "learning_rate": 2.53294383204969e-05, "loss": 0.4455, "step": 37 }, { "epoch": 0.23630003886513798, "grad_norm": 0.1657339334487915, "learning_rate": 2.3180194846605367e-05, "loss": 0.5267, "step": 38 }, { "epoch": 0.24251846094053633, "grad_norm": 0.157069593667984, "learning_rate": 2.1167208663446025e-05, "loss": 0.4632, "step": 39 }, { "epoch": 0.24873688301593472, "grad_norm": 0.17125950753688812, "learning_rate": 1.9299099686894423e-05, "loss": 0.4462, "step": 40 }, { "epoch": 0.2549553050913331, "grad_norm": 0.18847590684890747, "learning_rate": 1.758386744638546e-05, "loss": 0.4512, "step": 41 }, { "epoch": 0.26117372716673143, "grad_norm": 0.19772283732891083, "learning_rate": 1.602885682970026e-05, "loss": 0.414, "step": 42 }, { "epoch": 0.2673921492421298, "grad_norm": 0.20822468400001526, "learning_rate": 1.464072663102903e-05, "loss": 0.3711, "step": 43 }, { "epoch": 0.2736105713175282, "grad_norm": 0.2238302081823349, "learning_rate": 1.3425421036992098e-05, "loss": 0.4434, "step": 44 }, { "epoch": 0.27982899339292655, "grad_norm": 0.24059778451919556, "learning_rate": 1.2388144172720251e-05, "loss": 0.4171, "step": 45 }, { "epoch": 0.2860474154683249, "grad_norm": 0.23831042647361755, "learning_rate": 1.1533337816991932e-05, "loss": 0.4105, "step": 46 }, { "epoch": 0.29226583754372326, "grad_norm": 0.27717462182044983, "learning_rate": 1.0864662381854632e-05, "loss": 0.4423, "step": 47 }, { "epoch": 0.2984842596191217, "grad_norm": 0.31533050537109375, "learning_rate": 1.0384981238178534e-05, "loss": 0.4759, "step": 48 }, { "epoch": 0.30470268169452003, "grad_norm": 0.3454432487487793, "learning_rate": 1.0096348454262845e-05, "loss": 0.4729, "step": 49 }, { "epoch": 0.3109211037699184, "grad_norm": 0.5198519229888916, "learning_rate": 1e-05, "loss": 0.5038, "step": 50 }, { "epoch": 0.3109211037699184, "eval_loss": 0.4198492467403412, "eval_runtime": 0.4884, "eval_samples_per_second": 102.367, "eval_steps_per_second": 26.615, "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 }