{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0032651728500877517, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00016325864250438759, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00016325864250438759, "eval_loss": NaN, "eval_runtime": 293.3937, "eval_samples_per_second": 8.79, "eval_steps_per_second": 4.397, "step": 1 }, { "epoch": 0.00032651728500877517, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0004897759275131628, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0006530345700175503, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0008162932125219379, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0008162932125219379, "eval_loss": NaN, "eval_runtime": 291.0201, "eval_samples_per_second": 8.862, "eval_steps_per_second": 4.433, "step": 5 }, { "epoch": 0.0009795518550263255, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.001142810497530713, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0013060691400351007, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0014693277825394882, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0016325864250438759, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.0016325864250438759, "eval_loss": NaN, "eval_runtime": 292.6392, "eval_samples_per_second": 8.813, "eval_steps_per_second": 4.408, "step": 10 }, { "epoch": 0.0017958450675482633, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.001959103710052651, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.0021223623525570383, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.0, "step": 13 }, { "epoch": 0.002285620995061426, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 0.0, "step": 14 }, { "epoch": 0.0024488796375658137, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.0024488796375658137, "eval_loss": NaN, "eval_runtime": 293.7107, "eval_samples_per_second": 8.781, "eval_steps_per_second": 4.392, "step": 15 }, { "epoch": 0.0026121382800702014, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.0027753969225745886, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 0.0, "step": 17 }, { "epoch": 0.0029386555650789763, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.003101914207583364, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.0032651728500877517, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.0032651728500877517, "eval_loss": NaN, "eval_runtime": 295.1241, "eval_samples_per_second": 8.739, "eval_steps_per_second": 4.371, "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": 664811429953536.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }