{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0007064953415463417, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.532476707731709e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 3.532476707731709e-05, "eval_loss": NaN, "eval_runtime": 3274.7079, "eval_samples_per_second": 3.64, "eval_steps_per_second": 1.82, "step": 1 }, { "epoch": 7.064953415463417e-05, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00010597430123195125, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00014129906830926835, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00017662383538658542, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.00017662383538658542, "eval_loss": NaN, "eval_runtime": 2958.9683, "eval_samples_per_second": 4.028, "eval_steps_per_second": 2.014, "step": 5 }, { "epoch": 0.0002119486024639025, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.00024727336954121957, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0002825981366185367, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00031792290369585377, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00035324767077317084, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.00035324767077317084, "eval_loss": NaN, "eval_runtime": 2492.5468, "eval_samples_per_second": 4.782, "eval_steps_per_second": 2.391, "step": 10 }, { "epoch": 0.0003885724378504879, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.000423897204927805, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.0004592219720051221, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.0, "step": 13 }, { "epoch": 0.0004945467390824391, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 0.0, "step": 14 }, { "epoch": 0.0005298715061597563, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.0005298715061597563, "eval_loss": NaN, "eval_runtime": 1822.7626, "eval_samples_per_second": 6.54, "eval_steps_per_second": 3.27, "step": 15 }, { "epoch": 0.0005651962732370734, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.0006005210403143904, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 0.0, "step": 17 }, { "epoch": 0.0006358458073917075, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.0006711705744690246, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.0007064953415463417, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.0007064953415463417, "eval_loss": NaN, "eval_runtime": 3002.2126, "eval_samples_per_second": 3.97, "eval_steps_per_second": 1.985, "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": 3505339571896320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }