| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.000727868255845692, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.6393412792284596e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.6393412792284596e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 492.7765, | |
| "eval_samples_per_second": 23.479, | |
| "eval_steps_per_second": 11.74, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.278682558456919e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010918023837685379, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014557365116913838, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000181967063961423, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000181967063961423, | |
| "eval_loss": NaN, | |
| "eval_runtime": 490.7136, | |
| "eval_samples_per_second": 23.578, | |
| "eval_steps_per_second": 11.789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021836047675370757, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002547538895459922, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029114730233827677, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032754071513056135, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000363934127922846, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000363934127922846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 488.8715, | |
| "eval_samples_per_second": 23.667, | |
| "eval_steps_per_second": 11.833, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00040032754071513057, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00043672095350741515, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00047311436629969973, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005095077790919844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005459011918842689, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005459011918842689, | |
| "eval_loss": NaN, | |
| "eval_runtime": 491.2676, | |
| "eval_samples_per_second": 23.551, | |
| "eval_steps_per_second": 11.776, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005822946046765535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006186880174688382, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006550814302611227, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006914748430534073, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.000727868255845692, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000727868255845692, | |
| "eval_loss": NaN, | |
| "eval_runtime": 410.0052, | |
| "eval_samples_per_second": 28.219, | |
| "eval_steps_per_second": 14.11, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 291599986458624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |