{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 633, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.09, "learning_rate": 0.00015384615384615385, "loss": 2.5499, "step": 20 }, { "epoch": 0.19, "learning_rate": 0.00019538714991762767, "loss": 1.7484, "step": 40 }, { "epoch": 0.28, "learning_rate": 0.00018879736408566723, "loss": 1.5445, "step": 60 }, { "epoch": 0.38, "learning_rate": 0.00018220757825370676, "loss": 1.4988, "step": 80 }, { "epoch": 0.47, "learning_rate": 0.00017561779242174629, "loss": 1.4234, "step": 100 }, { "epoch": 0.57, "learning_rate": 0.00016902800658978584, "loss": 1.3635, "step": 120 }, { "epoch": 0.66, "learning_rate": 0.00016243822075782537, "loss": 1.2826, "step": 140 }, { "epoch": 0.76, "learning_rate": 0.00015584843492586492, "loss": 1.2112, "step": 160 }, { "epoch": 0.85, "learning_rate": 0.00014925864909390445, "loss": 1.2063, "step": 180 }, { "epoch": 0.95, "learning_rate": 0.000142668863261944, "loss": 1.2682, "step": 200 }, { "epoch": 1.04, "learning_rate": 0.00013607907742998354, "loss": 1.0148, "step": 220 }, { "epoch": 1.14, "learning_rate": 0.00012948929159802306, "loss": 0.8439, "step": 240 }, { "epoch": 1.23, "learning_rate": 0.00012289950576606262, "loss": 0.7722, "step": 260 }, { "epoch": 1.33, "learning_rate": 0.00011630971993410216, "loss": 0.8403, "step": 280 }, { "epoch": 1.42, "learning_rate": 0.00010971993410214168, "loss": 0.7227, "step": 300 }, { "epoch": 1.52, "learning_rate": 0.00010313014827018122, "loss": 0.7827, "step": 320 }, { "epoch": 1.61, "learning_rate": 9.654036243822076e-05, "loss": 0.711, "step": 340 }, { "epoch": 1.71, "learning_rate": 8.99505766062603e-05, "loss": 0.8146, "step": 360 }, { "epoch": 1.8, "learning_rate": 8.336079077429983e-05, "loss": 0.6851, "step": 380 }, { "epoch": 1.9, "learning_rate": 7.677100494233937e-05, "loss": 0.7673, "step": 400 }, { "epoch": 1.99, "learning_rate": 7.018121911037891e-05, "loss": 0.6934, "step": 420 }, { "epoch": 2.09, "learning_rate": 6.359143327841846e-05, "loss": 0.44, "step": 440 }, { "epoch": 2.18, "learning_rate": 5.7001647446458e-05, "loss": 0.4301, "step": 460 }, { "epoch": 2.27, "learning_rate": 5.041186161449754e-05, "loss": 0.4842, "step": 480 }, { "epoch": 2.37, "learning_rate": 4.382207578253707e-05, "loss": 0.4587, "step": 500 }, { "epoch": 2.46, "learning_rate": 3.723228995057661e-05, "loss": 0.365, "step": 520 }, { "epoch": 2.56, "learning_rate": 3.0642504118616144e-05, "loss": 0.4098, "step": 540 }, { "epoch": 2.65, "learning_rate": 2.4052718286655685e-05, "loss": 0.4867, "step": 560 }, { "epoch": 2.75, "learning_rate": 1.7462932454695224e-05, "loss": 0.4967, "step": 580 }, { "epoch": 2.84, "learning_rate": 1.0873146622734762e-05, "loss": 0.4172, "step": 600 }, { "epoch": 2.94, "learning_rate": 4.2833607907743006e-06, "loss": 0.3815, "step": 620 } ], "logging_steps": 20, "max_steps": 633, "num_train_epochs": 3, "save_steps": 500, "total_flos": 1.1297939941880064e+16, "trial_name": null, "trial_params": null }