{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 7010, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07, "learning_rate": 4.964336661911555e-05, "loss": 2.1394, "step": 50 }, { "epoch": 0.14, "learning_rate": 4.92867332382311e-05, "loss": 1.9883, "step": 100 }, { "epoch": 0.21, "learning_rate": 4.893009985734665e-05, "loss": 1.9832, "step": 150 }, { "epoch": 0.29, "learning_rate": 4.85734664764622e-05, "loss": 1.9561, "step": 200 }, { "epoch": 0.36, "learning_rate": 4.821683309557775e-05, "loss": 1.9404, "step": 250 }, { "epoch": 0.43, "learning_rate": 4.7860199714693296e-05, "loss": 1.9088, "step": 300 }, { "epoch": 0.5, "learning_rate": 4.7503566333808845e-05, "loss": 1.8832, "step": 350 }, { "epoch": 0.57, "learning_rate": 4.7146932952924393e-05, "loss": 1.8853, "step": 400 }, { "epoch": 0.64, "learning_rate": 4.679029957203995e-05, "loss": 1.8799, "step": 450 }, { "epoch": 0.71, "learning_rate": 4.64336661911555e-05, "loss": 1.825, "step": 500 }, { "epoch": 0.78, "learning_rate": 4.607703281027104e-05, "loss": 1.8531, "step": 550 }, { "epoch": 0.86, "learning_rate": 4.572039942938659e-05, "loss": 1.847, "step": 600 }, { "epoch": 0.93, "learning_rate": 4.5363766048502145e-05, "loss": 1.8485, "step": 650 }, { "epoch": 1.0, "learning_rate": 4.5007132667617693e-05, "loss": 1.83, "step": 700 }, { "epoch": 1.07, "learning_rate": 4.4650499286733236e-05, "loss": 1.8062, "step": 750 }, { "epoch": 1.14, "learning_rate": 4.429386590584879e-05, "loss": 1.806, "step": 800 }, { "epoch": 1.21, "learning_rate": 4.393723252496434e-05, "loss": 1.7829, "step": 850 }, { "epoch": 1.28, "learning_rate": 4.358059914407989e-05, "loss": 1.7775, "step": 900 }, { "epoch": 1.36, "learning_rate": 4.322396576319544e-05, "loss": 1.7954, "step": 950 }, { "epoch": 1.43, "learning_rate": 4.286733238231099e-05, "loss": 1.794, "step": 1000 }, { "epoch": 1.5, "learning_rate": 4.2510699001426536e-05, "loss": 1.7848, "step": 1050 }, { "epoch": 1.57, "learning_rate": 4.2154065620542085e-05, "loss": 1.7733, "step": 1100 }, { "epoch": 1.64, "learning_rate": 4.1797432239657633e-05, "loss": 1.7579, "step": 1150 }, { "epoch": 1.71, "learning_rate": 4.144079885877318e-05, "loss": 1.7667, "step": 1200 }, { "epoch": 1.78, "learning_rate": 4.108416547788873e-05, "loss": 1.7709, "step": 1250 }, { "epoch": 1.85, "learning_rate": 4.072753209700429e-05, "loss": 1.7481, "step": 1300 }, { "epoch": 1.93, "learning_rate": 4.037089871611983e-05, "loss": 1.7354, "step": 1350 }, { "epoch": 2.0, "learning_rate": 4.001426533523538e-05, "loss": 1.7537, "step": 1400 }, { "epoch": 2.07, "learning_rate": 3.965763195435093e-05, "loss": 1.7301, "step": 1450 }, { "epoch": 2.14, "learning_rate": 3.930099857346648e-05, "loss": 1.7135, "step": 1500 }, { "epoch": 2.21, "learning_rate": 3.8944365192582024e-05, "loss": 1.7132, "step": 1550 }, { "epoch": 2.28, "learning_rate": 3.858773181169757e-05, "loss": 1.7312, "step": 1600 }, { "epoch": 2.35, "learning_rate": 3.823109843081313e-05, "loss": 1.7184, "step": 1650 }, { "epoch": 2.43, "learning_rate": 3.787446504992868e-05, "loss": 1.7202, "step": 1700 }, { "epoch": 2.5, "learning_rate": 3.751783166904422e-05, "loss": 1.7139, "step": 1750 }, { "epoch": 2.57, "learning_rate": 3.716119828815977e-05, "loss": 1.721, "step": 1800 }, { "epoch": 2.64, "learning_rate": 3.6804564907275324e-05, "loss": 1.7021, "step": 1850 }, { "epoch": 2.71, "learning_rate": 3.644793152639087e-05, "loss": 1.722, "step": 1900 }, { "epoch": 2.78, "learning_rate": 3.609129814550642e-05, "loss": 1.6787, "step": 1950 }, { "epoch": 2.85, "learning_rate": 3.573466476462197e-05, "loss": 1.7017, "step": 2000 }, { "epoch": 2.92, "learning_rate": 3.537803138373752e-05, "loss": 1.7102, "step": 2050 }, { "epoch": 3.0, "learning_rate": 3.502139800285307e-05, "loss": 1.6821, "step": 2100 }, { "epoch": 3.07, "learning_rate": 3.466476462196862e-05, "loss": 1.6934, "step": 2150 }, { "epoch": 3.14, "learning_rate": 3.430813124108417e-05, "loss": 1.6817, "step": 2200 }, { "epoch": 3.21, "learning_rate": 3.3951497860199716e-05, "loss": 1.6769, "step": 2250 }, { "epoch": 3.28, "learning_rate": 3.3594864479315264e-05, "loss": 1.6836, "step": 2300 }, { "epoch": 3.35, "learning_rate": 3.323823109843081e-05, "loss": 1.6666, "step": 2350 }, { "epoch": 3.42, "learning_rate": 3.288159771754636e-05, "loss": 1.6788, "step": 2400 }, { "epoch": 3.5, "learning_rate": 3.252496433666191e-05, "loss": 1.6446, "step": 2450 }, { "epoch": 3.57, "learning_rate": 3.216833095577747e-05, "loss": 1.6658, "step": 2500 }, { "epoch": 3.64, "learning_rate": 3.1811697574893016e-05, "loss": 1.6523, "step": 2550 }, { "epoch": 3.71, "learning_rate": 3.145506419400856e-05, "loss": 1.6794, "step": 2600 }, { "epoch": 3.78, "learning_rate": 3.1098430813124107e-05, "loss": 1.6551, "step": 2650 }, { "epoch": 3.85, "learning_rate": 3.074179743223966e-05, "loss": 1.6595, "step": 2700 }, { "epoch": 3.92, "learning_rate": 3.0385164051355208e-05, "loss": 1.6518, "step": 2750 }, { "epoch": 3.99, "learning_rate": 3.0028530670470757e-05, "loss": 1.6226, "step": 2800 }, { "epoch": 4.07, "learning_rate": 2.967189728958631e-05, "loss": 1.6458, "step": 2850 }, { "epoch": 4.14, "learning_rate": 2.9315263908701858e-05, "loss": 1.6407, "step": 2900 }, { "epoch": 4.21, "learning_rate": 2.8958630527817403e-05, "loss": 1.6321, "step": 2950 }, { "epoch": 4.28, "learning_rate": 2.8601997146932952e-05, "loss": 1.6502, "step": 3000 }, { "epoch": 4.35, "learning_rate": 2.8245363766048504e-05, "loss": 1.6438, "step": 3050 }, { "epoch": 4.42, "learning_rate": 2.7888730385164053e-05, "loss": 1.6428, "step": 3100 }, { "epoch": 4.49, "learning_rate": 2.75320970042796e-05, "loss": 1.633, "step": 3150 }, { "epoch": 4.56, "learning_rate": 2.7175463623395154e-05, "loss": 1.6245, "step": 3200 }, { "epoch": 4.64, "learning_rate": 2.68188302425107e-05, "loss": 1.6337, "step": 3250 }, { "epoch": 4.71, "learning_rate": 2.646219686162625e-05, "loss": 1.6511, "step": 3300 }, { "epoch": 4.78, "learning_rate": 2.6105563480741794e-05, "loss": 1.6104, "step": 3350 }, { "epoch": 4.85, "learning_rate": 2.574893009985735e-05, "loss": 1.614, "step": 3400 }, { "epoch": 4.92, "learning_rate": 2.5392296718972895e-05, "loss": 1.6038, "step": 3450 }, { "epoch": 4.99, "learning_rate": 2.5035663338088444e-05, "loss": 1.6365, "step": 3500 }, { "epoch": 5.06, "learning_rate": 2.4679029957203993e-05, "loss": 1.6022, "step": 3550 }, { "epoch": 5.14, "learning_rate": 2.4322396576319545e-05, "loss": 1.6039, "step": 3600 }, { "epoch": 5.21, "learning_rate": 2.396576319543509e-05, "loss": 1.5874, "step": 3650 }, { "epoch": 5.28, "learning_rate": 2.3609129814550643e-05, "loss": 1.5715, "step": 3700 }, { "epoch": 5.35, "learning_rate": 2.3252496433666192e-05, "loss": 1.601, "step": 3750 }, { "epoch": 5.42, "learning_rate": 2.289586305278174e-05, "loss": 1.5898, "step": 3800 }, { "epoch": 5.49, "learning_rate": 2.253922967189729e-05, "loss": 1.6232, "step": 3850 }, { "epoch": 5.56, "learning_rate": 2.218259629101284e-05, "loss": 1.6, "step": 3900 }, { "epoch": 5.63, "learning_rate": 2.1825962910128388e-05, "loss": 1.5911, "step": 3950 }, { "epoch": 5.71, "learning_rate": 2.146932952924394e-05, "loss": 1.5976, "step": 4000 }, { "epoch": 5.78, "learning_rate": 2.111269614835949e-05, "loss": 1.5734, "step": 4050 }, { "epoch": 5.85, "learning_rate": 2.0756062767475038e-05, "loss": 1.6059, "step": 4100 }, { "epoch": 5.92, "learning_rate": 2.0399429386590586e-05, "loss": 1.5414, "step": 4150 }, { "epoch": 5.99, "learning_rate": 2.0042796005706135e-05, "loss": 1.5934, "step": 4200 }, { "epoch": 6.06, "learning_rate": 1.9686162624821684e-05, "loss": 1.5541, "step": 4250 }, { "epoch": 6.13, "learning_rate": 1.9329529243937233e-05, "loss": 1.5748, "step": 4300 }, { "epoch": 6.21, "learning_rate": 1.8972895863052782e-05, "loss": 1.5502, "step": 4350 }, { "epoch": 6.28, "learning_rate": 1.861626248216833e-05, "loss": 1.5512, "step": 4400 }, { "epoch": 6.35, "learning_rate": 1.8259629101283883e-05, "loss": 1.5841, "step": 4450 }, { "epoch": 6.42, "learning_rate": 1.790299572039943e-05, "loss": 1.6056, "step": 4500 }, { "epoch": 6.49, "learning_rate": 1.754636233951498e-05, "loss": 1.5843, "step": 4550 }, { "epoch": 6.56, "learning_rate": 1.718972895863053e-05, "loss": 1.5775, "step": 4600 }, { "epoch": 6.63, "learning_rate": 1.683309557774608e-05, "loss": 1.567, "step": 4650 }, { "epoch": 6.7, "learning_rate": 1.6476462196861628e-05, "loss": 1.5395, "step": 4700 }, { "epoch": 6.78, "learning_rate": 1.6119828815977176e-05, "loss": 1.6035, "step": 4750 }, { "epoch": 6.85, "learning_rate": 1.5763195435092725e-05, "loss": 1.5744, "step": 4800 }, { "epoch": 6.92, "learning_rate": 1.5406562054208274e-05, "loss": 1.5538, "step": 4850 }, { "epoch": 6.99, "learning_rate": 1.5049928673323823e-05, "loss": 1.5561, "step": 4900 }, { "epoch": 7.06, "learning_rate": 1.4693295292439374e-05, "loss": 1.5545, "step": 4950 }, { "epoch": 7.13, "learning_rate": 1.433666191155492e-05, "loss": 1.5433, "step": 5000 }, { "epoch": 7.2, "learning_rate": 1.3980028530670471e-05, "loss": 1.536, "step": 5050 }, { "epoch": 7.28, "learning_rate": 1.362339514978602e-05, "loss": 1.5689, "step": 5100 }, { "epoch": 7.35, "learning_rate": 1.326676176890157e-05, "loss": 1.5497, "step": 5150 }, { "epoch": 7.42, "learning_rate": 1.291012838801712e-05, "loss": 1.5449, "step": 5200 }, { "epoch": 7.49, "learning_rate": 1.2553495007132669e-05, "loss": 1.5663, "step": 5250 }, { "epoch": 7.56, "learning_rate": 1.2196861626248217e-05, "loss": 1.5725, "step": 5300 }, { "epoch": 7.63, "learning_rate": 1.1840228245363768e-05, "loss": 1.5291, "step": 5350 }, { "epoch": 7.7, "learning_rate": 1.1483594864479317e-05, "loss": 1.5607, "step": 5400 }, { "epoch": 7.77, "learning_rate": 1.1126961483594866e-05, "loss": 1.5361, "step": 5450 }, { "epoch": 7.85, "learning_rate": 1.0770328102710415e-05, "loss": 1.5743, "step": 5500 }, { "epoch": 7.92, "learning_rate": 1.0413694721825964e-05, "loss": 1.5484, "step": 5550 }, { "epoch": 7.99, "learning_rate": 1.0057061340941512e-05, "loss": 1.5238, "step": 5600 }, { "epoch": 8.06, "learning_rate": 9.700427960057063e-06, "loss": 1.5493, "step": 5650 }, { "epoch": 8.13, "learning_rate": 9.343794579172612e-06, "loss": 1.5216, "step": 5700 }, { "epoch": 8.2, "learning_rate": 8.98716119828816e-06, "loss": 1.5233, "step": 5750 }, { "epoch": 8.27, "learning_rate": 8.63052781740371e-06, "loss": 1.5664, "step": 5800 }, { "epoch": 8.35, "learning_rate": 8.273894436519259e-06, "loss": 1.557, "step": 5850 }, { "epoch": 8.42, "learning_rate": 7.917261055634807e-06, "loss": 1.5289, "step": 5900 }, { "epoch": 8.49, "learning_rate": 7.560627674750358e-06, "loss": 1.5276, "step": 5950 }, { "epoch": 8.56, "learning_rate": 7.203994293865907e-06, "loss": 1.579, "step": 6000 }, { "epoch": 8.63, "learning_rate": 6.847360912981456e-06, "loss": 1.5147, "step": 6050 }, { "epoch": 8.7, "learning_rate": 6.490727532097005e-06, "loss": 1.5442, "step": 6100 }, { "epoch": 8.77, "learning_rate": 6.1340941512125535e-06, "loss": 1.5118, "step": 6150 }, { "epoch": 8.84, "learning_rate": 5.777460770328103e-06, "loss": 1.525, "step": 6200 }, { "epoch": 8.92, "learning_rate": 5.420827389443652e-06, "loss": 1.5131, "step": 6250 }, { "epoch": 8.99, "learning_rate": 5.064194008559201e-06, "loss": 1.5268, "step": 6300 }, { "epoch": 9.06, "learning_rate": 4.707560627674751e-06, "loss": 1.5325, "step": 6350 }, { "epoch": 9.13, "learning_rate": 4.3509272467903e-06, "loss": 1.5153, "step": 6400 }, { "epoch": 9.2, "learning_rate": 3.9942938659058485e-06, "loss": 1.5342, "step": 6450 }, { "epoch": 9.27, "learning_rate": 3.6376604850213982e-06, "loss": 1.5422, "step": 6500 }, { "epoch": 9.34, "learning_rate": 3.2810271041369475e-06, "loss": 1.5243, "step": 6550 }, { "epoch": 9.42, "learning_rate": 2.924393723252497e-06, "loss": 1.5273, "step": 6600 }, { "epoch": 9.49, "learning_rate": 2.5677603423680457e-06, "loss": 1.5353, "step": 6650 }, { "epoch": 9.56, "learning_rate": 2.211126961483595e-06, "loss": 1.537, "step": 6700 }, { "epoch": 9.63, "learning_rate": 1.8544935805991443e-06, "loss": 1.5333, "step": 6750 }, { "epoch": 9.7, "learning_rate": 1.4978601997146932e-06, "loss": 1.5402, "step": 6800 }, { "epoch": 9.77, "learning_rate": 1.1412268188302427e-06, "loss": 1.5236, "step": 6850 }, { "epoch": 9.84, "learning_rate": 7.845934379457918e-07, "loss": 1.5204, "step": 6900 }, { "epoch": 9.91, "learning_rate": 4.27960057061341e-07, "loss": 1.5038, "step": 6950 }, { "epoch": 9.99, "learning_rate": 7.132667617689017e-08, "loss": 1.5403, "step": 7000 }, { "epoch": 10.0, "step": 7010, "total_flos": 7384869485936640.0, "train_loss": 1.6471780081788416, "train_runtime": 2443.9537, "train_samples_per_second": 91.692, "train_steps_per_second": 2.868 } ], "max_steps": 7010, "num_train_epochs": 10, "total_flos": 7384869485936640.0, "trial_name": null, "trial_params": null }