{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.01473676454334451, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005894705817337803, "grad_norm": 0.0, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0005894705817337803, "eval_loss": NaN, "eval_runtime": 162.7704, "eval_samples_per_second": 70.215, "eval_steps_per_second": 8.779, "step": 1 }, { "epoch": 0.0011789411634675606, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.001768411745201341, "grad_norm": 0.0, "learning_rate": 9.989294616193017e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0023578823269351213, "grad_norm": 0.0, "learning_rate": 9.957224306869053e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0029473529086689017, "grad_norm": 0.0, "learning_rate": 9.903926402016153e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.003536823490402682, "grad_norm": 0.0, "learning_rate": 9.829629131445342e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.004126294072136463, "grad_norm": 0.0, "learning_rate": 9.73465064747553e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.0047157646538702426, "grad_norm": 0.0, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.005305235235604023, "grad_norm": 0.0, "learning_rate": 9.484363707663442e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.005894705817337803, "grad_norm": 0.0, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.006484176399071583, "grad_norm": 0.0, "learning_rate": 9.157348061512727e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.007073646980805364, "grad_norm": 0.0, "learning_rate": 8.966766701456177e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.007663117562539144, "grad_norm": 0.0, "learning_rate": 8.759199037394887e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.008252588144272925, "grad_norm": 0.0, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.008842058726006706, "grad_norm": 0.0, "learning_rate": 8.296729075500344e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.009431529307740485, "grad_norm": 0.0, "learning_rate": 8.043807145043604e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.010020999889474266, "grad_norm": 0.0, "learning_rate": 7.777851165098012e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.010610470471208047, "grad_norm": 0.0, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.011199941052941826, "grad_norm": 0.0, "learning_rate": 7.211443451095007e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.011789411634675607, "grad_norm": 0.0, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.012378882216409388, "grad_norm": 0.0, "learning_rate": 6.607197326515808e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.012968352798143167, "grad_norm": 0.0, "learning_rate": 6.294095225512603e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.013557823379876948, "grad_norm": 0.0, "learning_rate": 5.9754516100806423e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.014147293961610729, "grad_norm": 0.0, "learning_rate": 5.6526309611002594e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.01473676454334451, "grad_norm": 0.0, "learning_rate": 5.327015646150716e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.01473676454334451, "eval_loss": NaN, "eval_runtime": 162.7739, "eval_samples_per_second": 70.214, "eval_steps_per_second": 8.779, "step": 25 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 208867531161600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }