| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08992805755395683, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017985611510791368, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017985611510791368, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5587, | |
| "eval_samples_per_second": 89.501, | |
| "eval_steps_per_second": 12.53, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035971223021582736, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00539568345323741, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995833517960035e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008992805755395683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.983341787205736e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01079136690647482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.962547939546805e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012589928057553957, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.933490480402273e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014388489208633094, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.89622321749732e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01618705035971223, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.85081516122375e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017985611510791366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.79735039684865e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019784172661870502, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.735927928807813e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02158273381294964, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.666661497372324e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023381294964028777, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.589679368027765e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.025179856115107913, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.505124093956045e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02697841726618705, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.413152252059749e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02877697841726619, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.313934153017741e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.030575539568345324, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.207653525908994e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03237410071942446, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.094507177988643e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0341726618705036, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.974704630246239e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03597122302158273, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.848467729421124e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03776978417266187, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.716030237193325e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.039568345323741004, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.577637397310749e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04136690647482014, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.433545481454206e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04316546762589928, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.284021314681265e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.044964028776978415, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.129341781327658e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.044964028776978415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.183, | |
| "eval_samples_per_second": 273.257, | |
| "eval_steps_per_second": 38.256, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.046762589928057555, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.969793312281237e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.048561151079136694, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.805671354577908e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.050359712230215826, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.637279824301728e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.052158273381294966, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.464930543802289e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0539568345323741, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.288942664271503e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05575539568345324, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.109642074749067e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05755395683453238, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.927360798650978e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05935251798561151, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.742436378938612e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06115107913669065, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.555211253066844e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06294964028776978, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.366032118868734e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06474820143884892, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.175249292550937e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06654676258992806, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9832160599887344e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0683453237410072, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.790288022521925e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07014388489208633, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.596822438463001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07194244604316546, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4031775615370004e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0737410071942446, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.209711977478078e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07553956834532374, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.016783940011267e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07733812949640288, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.824750707449064e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07913669064748201, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.633967881131266e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08093525179856115, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4447887469331574e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08273381294964029, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.25756362106139e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08453237410071943, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0726392013490235e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08633093525179857, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8903579252509345e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08812949640287769, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.711057335728499e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08992805755395683, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5350694561977125e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08992805755395683, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.1848, | |
| "eval_samples_per_second": 270.521, | |
| "eval_steps_per_second": 37.873, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 76, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21142437888000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |