{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.0807836009290114, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0032313440371604563, "grad_norm": 0.0, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0032313440371604563, "eval_loss": NaN, "eval_runtime": 0.4941, "eval_samples_per_second": 101.204, "eval_steps_per_second": 26.313, "step": 1 }, { "epoch": 0.0064626880743209126, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.00969403211148137, "grad_norm": 0.0, "learning_rate": 9.990365154573717e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.012925376148641825, "grad_norm": 0.0, "learning_rate": 9.961501876182148e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.016156720185802283, "grad_norm": 0.0, "learning_rate": 9.913533761814537e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.01938806422296274, "grad_norm": 0.0, "learning_rate": 9.846666218300807e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.022619408260123194, "grad_norm": 0.0, "learning_rate": 9.761185582727977e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.02585075229728365, "grad_norm": 0.0, "learning_rate": 9.657457896300791e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.02908209633444411, "grad_norm": 0.0, "learning_rate": 9.535927336897098e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.032313440371604565, "grad_norm": 0.0, "learning_rate": 9.397114317029975e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.03554478440876502, "grad_norm": 0.0, "learning_rate": 9.241613255361455e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.03877612844592548, "grad_norm": 0.0, "learning_rate": 9.070090031310558e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.042007472483085936, "grad_norm": 0.0, "learning_rate": 8.883279133655399e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.04523881652024639, "grad_norm": 0.0, "learning_rate": 8.681980515339464e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.04847016055740685, "grad_norm": 0.0, "learning_rate": 8.467056167950311e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.0517015045945673, "grad_norm": 0.0, "learning_rate": 8.239426430539243e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.05493284863172776, "grad_norm": 0.0, "learning_rate": 8.000066048588211e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.05816419266888822, "grad_norm": 0.0, "learning_rate": 7.75e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.06139553670604867, "grad_norm": 0.0, "learning_rate": 7.490299105985507e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.06462688074320913, "grad_norm": 0.0, "learning_rate": 7.222075445642904e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.06785822478036958, "grad_norm": 0.0, "learning_rate": 6.946477593864228e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.07108956881753004, "grad_norm": 0.0, "learning_rate": 6.664685702961344e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.0743209128546905, "grad_norm": 0.0, "learning_rate": 6.377906449072578e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.07755225689185095, "grad_norm": 0.0, "learning_rate": 6.087367864990233e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.0807836009290114, "grad_norm": 0.0, "learning_rate": 5.794314081535644e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.0807836009290114, "eval_loss": NaN, "eval_runtime": 0.4862, "eval_samples_per_second": 102.835, "eval_steps_per_second": 26.737, "step": 25 } ], "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": false }, "attributes": {} } }, "total_flos": 1.27222702669824e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }