{ "best_metric": 1.1276003122329712, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.033818058843422386, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006763611768684477, "grad_norm": 2.210228681564331, "learning_rate": 2e-05, "loss": 5.2324, "step": 1 }, { "epoch": 0.0006763611768684477, "eval_loss": 1.3878569602966309, "eval_runtime": 62.4568, "eval_samples_per_second": 39.868, "eval_steps_per_second": 4.995, "step": 1 }, { "epoch": 0.0013527223537368955, "grad_norm": 2.4433717727661133, "learning_rate": 4e-05, "loss": 5.1105, "step": 2 }, { "epoch": 0.002029083530605343, "grad_norm": 2.504581928253174, "learning_rate": 6e-05, "loss": 5.0322, "step": 3 }, { "epoch": 0.002705444707473791, "grad_norm": 2.3368101119995117, "learning_rate": 8e-05, "loss": 5.1913, "step": 4 }, { "epoch": 0.0033818058843422386, "grad_norm": 2.202308416366577, "learning_rate": 0.0001, "loss": 4.6383, "step": 5 }, { "epoch": 0.004058167061210686, "grad_norm": 1.9372011423110962, "learning_rate": 9.987820251299122e-05, "loss": 4.8722, "step": 6 }, { "epoch": 0.0047345282380791345, "grad_norm": 2.3214731216430664, "learning_rate": 9.951340343707852e-05, "loss": 4.7582, "step": 7 }, { "epoch": 0.005410889414947582, "grad_norm": 2.0861144065856934, "learning_rate": 9.890738003669029e-05, "loss": 4.6053, "step": 8 }, { "epoch": 0.00608725059181603, "grad_norm": 1.699201226234436, "learning_rate": 9.806308479691595e-05, "loss": 4.3391, "step": 9 }, { "epoch": 0.006763611768684477, "grad_norm": 1.7300448417663574, "learning_rate": 9.698463103929542e-05, "loss": 4.7776, "step": 10 }, { "epoch": 0.0074399729455529254, "grad_norm": 1.5897445678710938, "learning_rate": 9.567727288213005e-05, "loss": 4.5046, "step": 11 }, { "epoch": 0.008116334122421373, "grad_norm": 1.7118216753005981, "learning_rate": 9.414737964294636e-05, "loss": 4.5287, "step": 12 }, { "epoch": 0.00879269529928982, "grad_norm": 1.6620103120803833, "learning_rate": 9.24024048078213e-05, "loss": 4.6679, "step": 13 }, { "epoch": 0.009469056476158269, "grad_norm": 1.6078102588653564, "learning_rate": 9.045084971874738e-05, "loss": 4.6585, "step": 14 }, { "epoch": 0.010145417653026716, "grad_norm": 1.708989143371582, "learning_rate": 8.83022221559489e-05, "loss": 4.6418, "step": 15 }, { "epoch": 0.010821778829895164, "grad_norm": 1.634358286857605, "learning_rate": 8.596699001693255e-05, "loss": 4.7981, "step": 16 }, { "epoch": 0.011498140006763611, "grad_norm": 1.641950249671936, "learning_rate": 8.345653031794292e-05, "loss": 4.6754, "step": 17 }, { "epoch": 0.01217450118363206, "grad_norm": 1.6090244054794312, "learning_rate": 8.07830737662829e-05, "loss": 4.7456, "step": 18 }, { "epoch": 0.012850862360500507, "grad_norm": 1.5953105688095093, "learning_rate": 7.795964517353735e-05, "loss": 4.6286, "step": 19 }, { "epoch": 0.013527223537368955, "grad_norm": 1.5897241830825806, "learning_rate": 7.500000000000001e-05, "loss": 4.5854, "step": 20 }, { "epoch": 0.014203584714237404, "grad_norm": 1.5782119035720825, "learning_rate": 7.191855733945387e-05, "loss": 4.9393, "step": 21 }, { "epoch": 0.014879945891105851, "grad_norm": 1.5145971775054932, "learning_rate": 6.873032967079561e-05, "loss": 4.5412, "step": 22 }, { "epoch": 0.015556307067974298, "grad_norm": 1.4755655527114868, "learning_rate": 6.545084971874738e-05, "loss": 4.5503, "step": 23 }, { "epoch": 0.016232668244842745, "grad_norm": 1.4611729383468628, "learning_rate": 6.209609477998338e-05, "loss": 4.5544, "step": 24 }, { "epoch": 0.016909029421711193, "grad_norm": 1.5055865049362183, "learning_rate": 5.868240888334653e-05, "loss": 4.6855, "step": 25 }, { "epoch": 0.016909029421711193, "eval_loss": 1.1481486558914185, "eval_runtime": 63.488, "eval_samples_per_second": 39.22, "eval_steps_per_second": 4.914, "step": 25 }, { "epoch": 0.01758539059857964, "grad_norm": 1.4838390350341797, "learning_rate": 5.522642316338268e-05, "loss": 4.6324, "step": 26 }, { "epoch": 0.01826175177544809, "grad_norm": 1.5631728172302246, "learning_rate": 5.174497483512506e-05, "loss": 4.7677, "step": 27 }, { "epoch": 0.018938112952316538, "grad_norm": 1.4975249767303467, "learning_rate": 4.825502516487497e-05, "loss": 4.4577, "step": 28 }, { "epoch": 0.019614474129184985, "grad_norm": 1.5627292394638062, "learning_rate": 4.477357683661734e-05, "loss": 4.4784, "step": 29 }, { "epoch": 0.020290835306053433, "grad_norm": 1.6029400825500488, "learning_rate": 4.131759111665349e-05, "loss": 4.672, "step": 30 }, { "epoch": 0.02096719648292188, "grad_norm": 1.5164552927017212, "learning_rate": 3.790390522001662e-05, "loss": 4.7107, "step": 31 }, { "epoch": 0.021643557659790327, "grad_norm": 1.4938106536865234, "learning_rate": 3.4549150281252636e-05, "loss": 4.2752, "step": 32 }, { "epoch": 0.022319918836658775, "grad_norm": 1.6547623872756958, "learning_rate": 3.12696703292044e-05, "loss": 4.6671, "step": 33 }, { "epoch": 0.022996280013527222, "grad_norm": 1.5448929071426392, "learning_rate": 2.8081442660546125e-05, "loss": 4.347, "step": 34 }, { "epoch": 0.023672641190395673, "grad_norm": 1.615652322769165, "learning_rate": 2.500000000000001e-05, "loss": 4.6043, "step": 35 }, { "epoch": 0.02434900236726412, "grad_norm": 1.6707816123962402, "learning_rate": 2.2040354826462668e-05, "loss": 4.7418, "step": 36 }, { "epoch": 0.025025363544132567, "grad_norm": 1.640742301940918, "learning_rate": 1.9216926233717085e-05, "loss": 4.7379, "step": 37 }, { "epoch": 0.025701724721001015, "grad_norm": 1.592197299003601, "learning_rate": 1.6543469682057106e-05, "loss": 4.6499, "step": 38 }, { "epoch": 0.026378085897869462, "grad_norm": 1.702347755432129, "learning_rate": 1.4033009983067452e-05, "loss": 4.6663, "step": 39 }, { "epoch": 0.02705444707473791, "grad_norm": 1.5496896505355835, "learning_rate": 1.1697777844051105e-05, "loss": 4.4641, "step": 40 }, { "epoch": 0.027730808251606356, "grad_norm": 1.818640947341919, "learning_rate": 9.549150281252633e-06, "loss": 4.676, "step": 41 }, { "epoch": 0.028407169428474807, "grad_norm": 1.699539065361023, "learning_rate": 7.597595192178702e-06, "loss": 4.515, "step": 42 }, { "epoch": 0.029083530605343254, "grad_norm": 1.6481209993362427, "learning_rate": 5.852620357053651e-06, "loss": 4.4317, "step": 43 }, { "epoch": 0.029759891782211702, "grad_norm": 1.679146647453308, "learning_rate": 4.322727117869951e-06, "loss": 4.6045, "step": 44 }, { "epoch": 0.03043625295908015, "grad_norm": 1.7702221870422363, "learning_rate": 3.0153689607045845e-06, "loss": 4.5777, "step": 45 }, { "epoch": 0.031112614135948596, "grad_norm": 1.8951936960220337, "learning_rate": 1.9369152030840556e-06, "loss": 4.546, "step": 46 }, { "epoch": 0.03178897531281705, "grad_norm": 1.952268362045288, "learning_rate": 1.0926199633097157e-06, "loss": 4.6064, "step": 47 }, { "epoch": 0.03246533648968549, "grad_norm": 1.949053406715393, "learning_rate": 4.865965629214819e-07, "loss": 4.4643, "step": 48 }, { "epoch": 0.03314169766655394, "grad_norm": 2.287039279937744, "learning_rate": 1.2179748700879012e-07, "loss": 4.7819, "step": 49 }, { "epoch": 0.033818058843422386, "grad_norm": 3.5385773181915283, "learning_rate": 0.0, "loss": 5.4656, "step": 50 }, { "epoch": 0.033818058843422386, "eval_loss": 1.1276003122329712, "eval_runtime": 63.5618, "eval_samples_per_second": 39.174, "eval_steps_per_second": 4.909, "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": 5, "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": 1.935689084043264e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }