{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.034129692832764506, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017064846416382253, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0017064846416382253, "eval_loss": NaN, "eval_runtime": 24.7399, "eval_samples_per_second": 9.984, "eval_steps_per_second": 5.012, "step": 1 }, { "epoch": 0.0034129692832764505, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.005119453924914676, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.006825938566552901, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.008532423208191127, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.008532423208191127, "eval_loss": NaN, "eval_runtime": 23.7145, "eval_samples_per_second": 10.416, "eval_steps_per_second": 5.229, "step": 5 }, { "epoch": 0.010238907849829351, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.011945392491467578, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.013651877133105802, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.015358361774744027, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.017064846416382253, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.017064846416382253, "eval_loss": NaN, "eval_runtime": 23.6066, "eval_samples_per_second": 10.463, "eval_steps_per_second": 5.253, "step": 10 }, { "epoch": 0.01877133105802048, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.020477815699658702, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.02218430034129693, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.0, "step": 13 }, { "epoch": 0.023890784982935155, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 0.0, "step": 14 }, { "epoch": 0.025597269624573378, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.025597269624573378, "eval_loss": NaN, "eval_runtime": 23.7323, "eval_samples_per_second": 10.408, "eval_steps_per_second": 5.225, "step": 15 }, { "epoch": 0.027303754266211604, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.02901023890784983, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 0.0, "step": 17 }, { "epoch": 0.030716723549488054, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.032423208191126277, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.034129692832764506, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.034129692832764506, "eval_loss": NaN, "eval_runtime": 23.6903, "eval_samples_per_second": 10.426, "eval_steps_per_second": 5.234, "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": 3286330465320960.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }