{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.028308563340410473, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0014154281670205238, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0014154281670205238, "eval_loss": NaN, "eval_runtime": 34.9735, "eval_samples_per_second": 8.521, "eval_steps_per_second": 4.26, "step": 1 }, { "epoch": 0.0028308563340410475, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.004246284501061571, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.005661712668082095, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.007077140835102618, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 1.1041, "step": 5 }, { "epoch": 0.007077140835102618, "eval_loss": NaN, "eval_runtime": 34.3699, "eval_samples_per_second": 8.67, "eval_steps_per_second": 4.335, "step": 5 }, { "epoch": 0.008492569002123142, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.009907997169143666, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.8733, "step": 7 }, { "epoch": 0.01132342533616419, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.5787, "step": 8 }, { "epoch": 0.012738853503184714, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 4.099, "step": 9 }, { "epoch": 0.014154281670205236, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.5726, "step": 10 }, { "epoch": 0.014154281670205236, "eval_loss": NaN, "eval_runtime": 33.462, "eval_samples_per_second": 8.906, "eval_steps_per_second": 4.453, "step": 10 }, { "epoch": 0.01556970983722576, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.016985138004246284, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.01840056617126681, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.9441, "step": 13 }, { "epoch": 0.019815994338287332, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 1.8664, "step": 14 }, { "epoch": 0.021231422505307854, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.021231422505307854, "eval_loss": NaN, "eval_runtime": 33.9481, "eval_samples_per_second": 8.778, "eval_steps_per_second": 4.389, "step": 15 }, { "epoch": 0.02264685067232838, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.024062278839348902, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 2.1042, "step": 17 }, { "epoch": 0.025477707006369428, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.02689313517338995, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 1.7534, "step": 19 }, { "epoch": 0.028308563340410473, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.028308563340410473, "eval_loss": NaN, "eval_runtime": 33.7655, "eval_samples_per_second": 8.826, "eval_steps_per_second": 4.413, "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": 2782892182732800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }