{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.00042659841092091935, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.1329920546045965e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 2.1329920546045965e-05, "eval_loss": NaN, "eval_runtime": 1545.188, "eval_samples_per_second": 12.775, "eval_steps_per_second": 6.388, "step": 1 }, { "epoch": 4.265984109209193e-05, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 6.39897616381379e-05, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 8.531968218418386e-05, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00010664960273022984, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.00010664960273022984, "eval_loss": NaN, "eval_runtime": 1534.9499, "eval_samples_per_second": 12.86, "eval_steps_per_second": 6.43, "step": 5 }, { "epoch": 0.0001279795232762758, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.00014930944382232175, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.00017063936436836772, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00019196928491441368, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00021329920546045967, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.00021329920546045967, "eval_loss": NaN, "eval_runtime": 1534.7224, "eval_samples_per_second": 12.862, "eval_steps_per_second": 6.431, "step": 10 }, { "epoch": 0.00023462912600650564, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.0002559590465525516, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.00027728896709859754, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.0, "step": 13 }, { "epoch": 0.0002986188876446435, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 0.0, "step": 14 }, { "epoch": 0.00031994880819068947, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.00031994880819068947, "eval_loss": NaN, "eval_runtime": 1538.3855, "eval_samples_per_second": 12.832, "eval_steps_per_second": 6.416, "step": 15 }, { "epoch": 0.00034127872873673543, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.0003626086492827814, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 0.0, "step": 17 }, { "epoch": 0.00038393856982882736, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.0004052684903748733, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.00042659841092091935, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.00042659841092091935, "eval_loss": NaN, "eval_runtime": 1537.0916, "eval_samples_per_second": 12.842, "eval_steps_per_second": 6.421, "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": 1572382401626112.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }