{ "best_metric": 11.5, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.028232636928289104, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000564652738565782, "grad_norm": 7.500299943785649e-06, "learning_rate": 2e-05, "loss": 46.0, "step": 1 }, { "epoch": 0.000564652738565782, "eval_loss": 11.5, "eval_runtime": 10.9095, "eval_samples_per_second": 273.432, "eval_steps_per_second": 34.19, "step": 1 }, { "epoch": 0.001129305477131564, "grad_norm": 1.1122405339847319e-05, "learning_rate": 4e-05, "loss": 46.0, "step": 2 }, { "epoch": 0.0016939582156973462, "grad_norm": 8.940000952861737e-06, "learning_rate": 6e-05, "loss": 46.0, "step": 3 }, { "epoch": 0.002258610954263128, "grad_norm": 8.511871783412062e-06, "learning_rate": 8e-05, "loss": 46.0, "step": 4 }, { "epoch": 0.00282326369282891, "grad_norm": 5.651030733133666e-06, "learning_rate": 0.0001, "loss": 46.0, "step": 5 }, { "epoch": 0.0033879164313946925, "grad_norm": 8.229234481405001e-06, "learning_rate": 9.987820251299122e-05, "loss": 46.0, "step": 6 }, { "epoch": 0.003952569169960474, "grad_norm": 9.415469321538694e-06, "learning_rate": 9.951340343707852e-05, "loss": 46.0, "step": 7 }, { "epoch": 0.004517221908526256, "grad_norm": 8.187973435269669e-06, "learning_rate": 9.890738003669029e-05, "loss": 46.0, "step": 8 }, { "epoch": 0.005081874647092038, "grad_norm": 7.2857960731198546e-06, "learning_rate": 9.806308479691595e-05, "loss": 46.0, "step": 9 }, { "epoch": 0.00564652738565782, "grad_norm": 1.6082320144050755e-05, "learning_rate": 9.698463103929542e-05, "loss": 46.0, "step": 10 }, { "epoch": 0.006211180124223602, "grad_norm": 1.651693310122937e-05, "learning_rate": 9.567727288213005e-05, "loss": 46.0, "step": 11 }, { "epoch": 0.006775832862789385, "grad_norm": 1.0514751920709386e-05, "learning_rate": 9.414737964294636e-05, "loss": 46.0, "step": 12 }, { "epoch": 0.007340485601355167, "grad_norm": 9.371266060043126e-06, "learning_rate": 9.24024048078213e-05, "loss": 46.0, "step": 13 }, { "epoch": 0.007905138339920948, "grad_norm": 7.268322860909393e-06, "learning_rate": 9.045084971874738e-05, "loss": 46.0, "step": 14 }, { "epoch": 0.00846979107848673, "grad_norm": 1.8917759007308632e-05, "learning_rate": 8.83022221559489e-05, "loss": 46.0, "step": 15 }, { "epoch": 0.009034443817052512, "grad_norm": 1.2781561963493004e-05, "learning_rate": 8.596699001693255e-05, "loss": 46.0, "step": 16 }, { "epoch": 0.009599096555618294, "grad_norm": 1.7548791220178828e-05, "learning_rate": 8.345653031794292e-05, "loss": 46.0, "step": 17 }, { "epoch": 0.010163749294184076, "grad_norm": 1.7257760191569105e-05, "learning_rate": 8.07830737662829e-05, "loss": 46.0, "step": 18 }, { "epoch": 0.010728402032749858, "grad_norm": 1.1552216165000573e-05, "learning_rate": 7.795964517353735e-05, "loss": 46.0, "step": 19 }, { "epoch": 0.01129305477131564, "grad_norm": 2.4854924049577676e-05, "learning_rate": 7.500000000000001e-05, "loss": 46.0, "step": 20 }, { "epoch": 0.011857707509881422, "grad_norm": 1.4226163330022246e-05, "learning_rate": 7.191855733945387e-05, "loss": 46.0, "step": 21 }, { "epoch": 0.012422360248447204, "grad_norm": 1.6801439414848574e-05, "learning_rate": 6.873032967079561e-05, "loss": 46.0, "step": 22 }, { "epoch": 0.012987012987012988, "grad_norm": 1.8362190530751832e-05, "learning_rate": 6.545084971874738e-05, "loss": 46.0, "step": 23 }, { "epoch": 0.01355166572557877, "grad_norm": 1.9349768990650773e-05, "learning_rate": 6.209609477998338e-05, "loss": 46.0, "step": 24 }, { "epoch": 0.014116318464144552, "grad_norm": 2.4139199013006873e-05, "learning_rate": 5.868240888334653e-05, "loss": 46.0, "step": 25 }, { "epoch": 0.014116318464144552, "eval_loss": 11.5, "eval_runtime": 10.8588, "eval_samples_per_second": 274.707, "eval_steps_per_second": 34.35, "step": 25 }, { "epoch": 0.014680971202710334, "grad_norm": 1.840215190895833e-05, "learning_rate": 5.522642316338268e-05, "loss": 46.0, "step": 26 }, { "epoch": 0.015245623941276116, "grad_norm": 3.8565991417272016e-05, "learning_rate": 5.174497483512506e-05, "loss": 46.0, "step": 27 }, { "epoch": 0.015810276679841896, "grad_norm": 2.9693477699765936e-05, "learning_rate": 4.825502516487497e-05, "loss": 46.0, "step": 28 }, { "epoch": 0.01637492941840768, "grad_norm": 2.882287481043022e-05, "learning_rate": 4.477357683661734e-05, "loss": 46.0, "step": 29 }, { "epoch": 0.01693958215697346, "grad_norm": 3.970301986555569e-05, "learning_rate": 4.131759111665349e-05, "loss": 46.0, "step": 30 }, { "epoch": 0.017504234895539244, "grad_norm": 3.102942355326377e-05, "learning_rate": 3.790390522001662e-05, "loss": 46.0, "step": 31 }, { "epoch": 0.018068887634105024, "grad_norm": 4.0613354940433055e-05, "learning_rate": 3.4549150281252636e-05, "loss": 46.0, "step": 32 }, { "epoch": 0.018633540372670808, "grad_norm": 3.106529402430169e-05, "learning_rate": 3.12696703292044e-05, "loss": 46.0, "step": 33 }, { "epoch": 0.019198193111236588, "grad_norm": 2.9168139008106664e-05, "learning_rate": 2.8081442660546125e-05, "loss": 46.0, "step": 34 }, { "epoch": 0.019762845849802372, "grad_norm": 4.332400203566067e-05, "learning_rate": 2.500000000000001e-05, "loss": 46.0, "step": 35 }, { "epoch": 0.020327498588368152, "grad_norm": 3.693047983688302e-05, "learning_rate": 2.2040354826462668e-05, "loss": 46.0, "step": 36 }, { "epoch": 0.020892151326933936, "grad_norm": 5.083263386040926e-05, "learning_rate": 1.9216926233717085e-05, "loss": 46.0, "step": 37 }, { "epoch": 0.021456804065499716, "grad_norm": 3.0578623409383e-05, "learning_rate": 1.6543469682057106e-05, "loss": 46.0, "step": 38 }, { "epoch": 0.0220214568040655, "grad_norm": 5.107508332002908e-05, "learning_rate": 1.4033009983067452e-05, "loss": 46.0, "step": 39 }, { "epoch": 0.02258610954263128, "grad_norm": 3.723540430655703e-05, "learning_rate": 1.1697777844051105e-05, "loss": 46.0, "step": 40 }, { "epoch": 0.023150762281197064, "grad_norm": 3.612995715229772e-05, "learning_rate": 9.549150281252633e-06, "loss": 46.0, "step": 41 }, { "epoch": 0.023715415019762844, "grad_norm": 2.876175676647108e-05, "learning_rate": 7.597595192178702e-06, "loss": 46.0, "step": 42 }, { "epoch": 0.024280067758328628, "grad_norm": 3.682672104332596e-05, "learning_rate": 5.852620357053651e-06, "loss": 46.0, "step": 43 }, { "epoch": 0.024844720496894408, "grad_norm": 9.715460328152403e-05, "learning_rate": 4.322727117869951e-06, "loss": 46.0, "step": 44 }, { "epoch": 0.025409373235460192, "grad_norm": 6.549270619871095e-05, "learning_rate": 3.0153689607045845e-06, "loss": 46.0, "step": 45 }, { "epoch": 0.025974025974025976, "grad_norm": 6.900445441715419e-05, "learning_rate": 1.9369152030840556e-06, "loss": 46.0, "step": 46 }, { "epoch": 0.026538678712591756, "grad_norm": 0.00015088528743945062, "learning_rate": 1.0926199633097157e-06, "loss": 46.0, "step": 47 }, { "epoch": 0.02710333145115754, "grad_norm": 6.665437103947625e-05, "learning_rate": 4.865965629214819e-07, "loss": 46.0, "step": 48 }, { "epoch": 0.02766798418972332, "grad_norm": 6.30583890597336e-05, "learning_rate": 1.2179748700879012e-07, "loss": 46.0, "step": 49 }, { "epoch": 0.028232636928289104, "grad_norm": 0.0001458668411942199, "learning_rate": 0.0, "loss": 46.0, "step": 50 }, { "epoch": 0.028232636928289104, "eval_loss": 11.5, "eval_runtime": 10.903, "eval_samples_per_second": 273.595, "eval_steps_per_second": 34.211, "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": 1 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7094960848896.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }