{ "best_metric": 0.4649864137172699, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.030677199171715623, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012270879668686248, "grad_norm": 0.16277451813220978, "learning_rate": 5e-05, "loss": 0.3831, "step": 1 }, { "epoch": 0.0012270879668686248, "eval_loss": 0.5771195292472839, "eval_runtime": 166.9944, "eval_samples_per_second": 32.875, "eval_steps_per_second": 4.114, "step": 1 }, { "epoch": 0.0024541759337372497, "grad_norm": 0.22337406873703003, "learning_rate": 0.0001, "loss": 0.5452, "step": 2 }, { "epoch": 0.0036812639006058748, "grad_norm": 0.24125908315181732, "learning_rate": 9.989294616193017e-05, "loss": 0.592, "step": 3 }, { "epoch": 0.004908351867474499, "grad_norm": 0.20937132835388184, "learning_rate": 9.957224306869053e-05, "loss": 0.576, "step": 4 }, { "epoch": 0.0061354398343431244, "grad_norm": 0.31259530782699585, "learning_rate": 9.903926402016153e-05, "loss": 0.5725, "step": 5 }, { "epoch": 0.0073625278012117495, "grad_norm": 0.2729087769985199, "learning_rate": 9.829629131445342e-05, "loss": 0.5477, "step": 6 }, { "epoch": 0.008589615768080374, "grad_norm": 0.18559280037879944, "learning_rate": 9.73465064747553e-05, "loss": 0.5244, "step": 7 }, { "epoch": 0.009816703734948999, "grad_norm": 0.18070900440216064, "learning_rate": 9.619397662556435e-05, "loss": 0.5123, "step": 8 }, { "epoch": 0.011043791701817624, "grad_norm": 0.1876116245985031, "learning_rate": 9.484363707663442e-05, "loss": 0.4676, "step": 9 }, { "epoch": 0.012270879668686249, "grad_norm": 0.1876431703567505, "learning_rate": 9.330127018922194e-05, "loss": 0.4238, "step": 10 }, { "epoch": 0.013497967635554874, "grad_norm": 0.21667154133319855, "learning_rate": 9.157348061512727e-05, "loss": 0.4415, "step": 11 }, { "epoch": 0.014725055602423499, "grad_norm": 0.2874070107936859, "learning_rate": 8.966766701456177e-05, "loss": 0.4583, "step": 12 }, { "epoch": 0.015952143569292122, "grad_norm": 0.15309716761112213, "learning_rate": 8.759199037394887e-05, "loss": 0.3069, "step": 13 }, { "epoch": 0.017179231536160747, "grad_norm": 0.20805510878562927, "learning_rate": 8.535533905932738e-05, "loss": 0.4467, "step": 14 }, { "epoch": 0.018406319503029372, "grad_norm": 0.2222377508878708, "learning_rate": 8.296729075500344e-05, "loss": 0.5267, "step": 15 }, { "epoch": 0.019633407469897998, "grad_norm": 0.17002098262310028, "learning_rate": 8.043807145043604e-05, "loss": 0.5049, "step": 16 }, { "epoch": 0.020860495436766623, "grad_norm": 0.1514810174703598, "learning_rate": 7.777851165098012e-05, "loss": 0.5431, "step": 17 }, { "epoch": 0.022087583403635248, "grad_norm": 0.16354860365390778, "learning_rate": 7.500000000000001e-05, "loss": 0.5318, "step": 18 }, { "epoch": 0.023314671370503873, "grad_norm": 0.18680204451084137, "learning_rate": 7.211443451095007e-05, "loss": 0.5211, "step": 19 }, { "epoch": 0.024541759337372498, "grad_norm": 0.17450307309627533, "learning_rate": 6.91341716182545e-05, "loss": 0.5126, "step": 20 }, { "epoch": 0.025768847304241123, "grad_norm": 0.16676221787929535, "learning_rate": 6.607197326515808e-05, "loss": 0.4745, "step": 21 }, { "epoch": 0.026995935271109748, "grad_norm": 0.1670372188091278, "learning_rate": 6.294095225512603e-05, "loss": 0.4372, "step": 22 }, { "epoch": 0.028223023237978373, "grad_norm": 0.17722724378108978, "learning_rate": 5.9754516100806423e-05, "loss": 0.4098, "step": 23 }, { "epoch": 0.029450111204846998, "grad_norm": 0.2052060216665268, "learning_rate": 5.6526309611002594e-05, "loss": 0.406, "step": 24 }, { "epoch": 0.030677199171715623, "grad_norm": 0.32859280705451965, "learning_rate": 5.327015646150716e-05, "loss": 0.4281, "step": 25 }, { "epoch": 0.030677199171715623, "eval_loss": 0.4649864137172699, "eval_runtime": 167.4814, "eval_samples_per_second": 32.78, "eval_steps_per_second": 4.102, "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": 2.9859068337822106e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }