{ "best_metric": 13.72530460357666, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.834862385321101, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03669724770642202, "grad_norm": Infinity, "learning_rate": 1.1400000000000001e-05, "loss": 13.1412, "step": 1 }, { "epoch": 0.03669724770642202, "eval_loss": 13.767973899841309, "eval_runtime": 8.9409, "eval_samples_per_second": 41.159, "eval_steps_per_second": 1.342, "step": 1 }, { "epoch": 0.07339449541284404, "grad_norm": Infinity, "learning_rate": 2.2800000000000002e-05, "loss": 13.246, "step": 2 }, { "epoch": 0.11009174311926606, "grad_norm": Infinity, "learning_rate": 3.42e-05, "loss": 13.3118, "step": 3 }, { "epoch": 0.14678899082568808, "grad_norm": Infinity, "learning_rate": 4.5600000000000004e-05, "loss": 13.7866, "step": 4 }, { "epoch": 0.1834862385321101, "grad_norm": Infinity, "learning_rate": 5.7e-05, "loss": 14.2103, "step": 5 }, { "epoch": 0.22018348623853212, "grad_norm": Infinity, "learning_rate": 6.84e-05, "loss": 14.7943, "step": 6 }, { "epoch": 0.25688073394495414, "grad_norm": Infinity, "learning_rate": 7.98e-05, "loss": 13.2983, "step": 7 }, { "epoch": 0.29357798165137616, "grad_norm": Infinity, "learning_rate": 9.120000000000001e-05, "loss": 12.9136, "step": 8 }, { "epoch": 0.3302752293577982, "grad_norm": Infinity, "learning_rate": 0.00010260000000000001, "loss": 12.7573, "step": 9 }, { "epoch": 0.3669724770642202, "grad_norm": Infinity, "learning_rate": 0.000114, "loss": 14.1044, "step": 10 }, { "epoch": 0.4036697247706422, "grad_norm": Infinity, "learning_rate": 0.00011394574863016591, "loss": 13.9062, "step": 11 }, { "epoch": 0.44036697247706424, "grad_norm": Infinity, "learning_rate": 0.0001137830977912295, "loss": 14.4365, "step": 12 }, { "epoch": 0.47706422018348627, "grad_norm": Infinity, "learning_rate": 0.0001135123570983072, "loss": 13.7386, "step": 13 }, { "epoch": 0.5137614678899083, "grad_norm": Infinity, "learning_rate": 0.00011313404192169587, "loss": 13.0317, "step": 14 }, { "epoch": 0.5504587155963303, "grad_norm": Infinity, "learning_rate": 0.00011264887240583621, "loss": 13.0585, "step": 15 }, { "epoch": 0.5871559633027523, "grad_norm": Infinity, "learning_rate": 0.0001120577720984769, "loss": 13.5512, "step": 16 }, { "epoch": 0.6238532110091743, "grad_norm": Infinity, "learning_rate": 0.00011136186619264893, "loss": 13.8095, "step": 17 }, { "epoch": 0.6605504587155964, "grad_norm": Infinity, "learning_rate": 0.00011056247938479678, "loss": 14.5567, "step": 18 }, { "epoch": 0.6972477064220184, "grad_norm": Infinity, "learning_rate": 0.00010966113335314335, "loss": 13.6495, "step": 19 }, { "epoch": 0.7339449541284404, "grad_norm": Infinity, "learning_rate": 0.00010865954386108906, "loss": 13.0206, "step": 20 }, { "epoch": 0.7706422018348624, "grad_norm": Infinity, "learning_rate": 0.00010755961749115863, "loss": 13.0672, "step": 21 }, { "epoch": 0.8073394495412844, "grad_norm": Infinity, "learning_rate": 0.00010636344801571301, "loss": 13.6291, "step": 22 }, { "epoch": 0.8440366972477065, "grad_norm": Infinity, "learning_rate": 0.00010507331241133449, "loss": 13.6346, "step": 23 }, { "epoch": 0.8807339449541285, "grad_norm": Infinity, "learning_rate": 0.00010369166652447254, "loss": 14.2408, "step": 24 }, { "epoch": 0.9174311926605505, "grad_norm": Infinity, "learning_rate": 0.00010222114039660041, "loss": 14.5945, "step": 25 }, { "epoch": 0.9541284403669725, "grad_norm": Infinity, "learning_rate": 0.00010066453325778175, "loss": 13.3547, "step": 26 }, { "epoch": 0.9908256880733946, "grad_norm": Infinity, "learning_rate": 9.902480819817708e-05, "loss": 14.5751, "step": 27 }, { "epoch": 1.0275229357798166, "grad_norm": Infinity, "learning_rate": 9.730508652763321e-05, "loss": 25.995, "step": 28 }, { "epoch": 1.0642201834862386, "grad_norm": Infinity, "learning_rate": 9.550864183409265e-05, "loss": 13.2655, "step": 29 }, { "epoch": 1.1009174311926606, "grad_norm": Infinity, "learning_rate": 9.363889375213274e-05, "loss": 12.5753, "step": 30 }, { "epoch": 1.1376146788990826, "grad_norm": Infinity, "learning_rate": 9.169940145349708e-05, "loss": 14.7334, "step": 31 }, { "epoch": 1.1743119266055047, "grad_norm": Infinity, "learning_rate": 8.969385687200964e-05, "loss": 12.8298, "step": 32 }, { "epoch": 1.2110091743119267, "grad_norm": Infinity, "learning_rate": 8.762607767576898e-05, "loss": 13.0432, "step": 33 }, { "epoch": 1.2477064220183487, "grad_norm": Infinity, "learning_rate": 8.55e-05, "loss": 15.5636, "step": 34 }, { "epoch": 1.2844036697247707, "grad_norm": Infinity, "learning_rate": 8.331967095439695e-05, "loss": 13.7782, "step": 35 }, { "epoch": 1.3211009174311927, "grad_norm": Infinity, "learning_rate": 8.108924091921987e-05, "loss": 12.2361, "step": 36 }, { "epoch": 1.3577981651376148, "grad_norm": Infinity, "learning_rate": 7.881295564481013e-05, "loss": 13.2064, "step": 37 }, { "epoch": 1.3944954128440368, "grad_norm": Infinity, "learning_rate": 7.649514816956313e-05, "loss": 13.3538, "step": 38 }, { "epoch": 1.4311926605504588, "grad_norm": Infinity, "learning_rate": 7.414023057174356e-05, "loss": 15.4216, "step": 39 }, { "epoch": 1.4678899082568808, "grad_norm": Infinity, "learning_rate": 7.175268557084368e-05, "loss": 12.778, "step": 40 }, { "epoch": 1.5045871559633026, "grad_norm": Infinity, "learning_rate": 6.933705799447187e-05, "loss": 16.2756, "step": 41 }, { "epoch": 1.5412844036697249, "grad_norm": Infinity, "learning_rate": 6.689794612701504e-05, "loss": 11.5718, "step": 42 }, { "epoch": 1.5779816513761467, "grad_norm": Infinity, "learning_rate": 6.443999295654295e-05, "loss": 13.2457, "step": 43 }, { "epoch": 1.614678899082569, "grad_norm": Infinity, "learning_rate": 6.196787733661653e-05, "loss": 10.1196, "step": 44 }, { "epoch": 1.6513761467889907, "grad_norm": Infinity, "learning_rate": 5.948630507982416e-05, "loss": 19.2206, "step": 45 }, { "epoch": 1.688073394495413, "grad_norm": Infinity, "learning_rate": 5.7e-05, "loss": 6.1591, "step": 46 }, { "epoch": 1.7247706422018347, "grad_norm": Infinity, "learning_rate": 5.451369492017586e-05, "loss": 21.1335, "step": 47 }, { "epoch": 1.761467889908257, "grad_norm": Infinity, "learning_rate": 5.2032122663383485e-05, "loss": 12.4404, "step": 48 }, { "epoch": 1.7981651376146788, "grad_norm": Infinity, "learning_rate": 4.956000704345708e-05, "loss": 13.207, "step": 49 }, { "epoch": 1.834862385321101, "grad_norm": Infinity, "learning_rate": 4.7102053872984975e-05, "loss": 8.0453, "step": 50 }, { "epoch": 1.834862385321101, "eval_loss": 13.72530460357666, "eval_runtime": 7.9114, "eval_samples_per_second": 46.515, "eval_steps_per_second": 1.517, "step": 50 } ], "logging_steps": 1, "max_steps": 82, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "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": 5.0781150955700224e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }