{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.997677659080353, "eval_steps": 500, "global_step": 6725, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "learning_rate": 4.9628252788104095e-06, "loss": 1.9064, "step": 50 }, { "epoch": 0.07, "learning_rate": 4.925650557620818e-06, "loss": 1.8717, "step": 100 }, { "epoch": 0.11, "learning_rate": 4.888475836431228e-06, "loss": 1.863, "step": 150 }, { "epoch": 0.15, "learning_rate": 4.851301115241636e-06, "loss": 1.8702, "step": 200 }, { "epoch": 0.19, "learning_rate": 4.814126394052045e-06, "loss": 1.8228, "step": 250 }, { "epoch": 0.22, "learning_rate": 4.776951672862453e-06, "loss": 1.8228, "step": 300 }, { "epoch": 0.26, "learning_rate": 4.739776951672863e-06, "loss": 1.8336, "step": 350 }, { "epoch": 0.3, "learning_rate": 4.702602230483272e-06, "loss": 1.8533, "step": 400 }, { "epoch": 0.33, "learning_rate": 4.665427509293681e-06, "loss": 1.8284, "step": 450 }, { "epoch": 0.37, "learning_rate": 4.62825278810409e-06, "loss": 1.7964, "step": 500 }, { "epoch": 0.41, "learning_rate": 4.591078066914498e-06, "loss": 1.8245, "step": 550 }, { "epoch": 0.45, "learning_rate": 4.553903345724908e-06, "loss": 1.8342, "step": 600 }, { "epoch": 0.48, "learning_rate": 4.516728624535316e-06, "loss": 1.8119, "step": 650 }, { "epoch": 0.52, "learning_rate": 4.479553903345725e-06, "loss": 1.8344, "step": 700 }, { "epoch": 0.56, "learning_rate": 4.442379182156134e-06, "loss": 1.7995, "step": 750 }, { "epoch": 0.59, "learning_rate": 4.405204460966543e-06, "loss": 1.8055, "step": 800 }, { "epoch": 0.63, "learning_rate": 4.368029739776952e-06, "loss": 1.8143, "step": 850 }, { "epoch": 0.67, "learning_rate": 4.330855018587361e-06, "loss": 1.7934, "step": 900 }, { "epoch": 0.71, "learning_rate": 4.29368029739777e-06, "loss": 1.8042, "step": 950 }, { "epoch": 0.74, "learning_rate": 4.256505576208178e-06, "loss": 1.8193, "step": 1000 }, { "epoch": 0.78, "learning_rate": 4.219330855018588e-06, "loss": 1.788, "step": 1050 }, { "epoch": 0.82, "learning_rate": 4.182156133828997e-06, "loss": 1.8064, "step": 1100 }, { "epoch": 0.85, "learning_rate": 4.144981412639406e-06, "loss": 1.8078, "step": 1150 }, { "epoch": 0.89, "learning_rate": 4.107806691449814e-06, "loss": 1.7875, "step": 1200 }, { "epoch": 0.93, "learning_rate": 4.070631970260223e-06, "loss": 1.7841, "step": 1250 }, { "epoch": 0.97, "learning_rate": 4.033457249070632e-06, "loss": 1.8112, "step": 1300 }, { "epoch": 1.0, "learning_rate": 3.996282527881041e-06, "loss": 1.7616, "step": 1350 }, { "epoch": 1.04, "learning_rate": 3.9591078066914504e-06, "loss": 1.7768, "step": 1400 }, { "epoch": 1.08, "learning_rate": 3.921933085501859e-06, "loss": 1.7868, "step": 1450 }, { "epoch": 1.11, "learning_rate": 3.884758364312268e-06, "loss": 1.7582, "step": 1500 }, { "epoch": 1.15, "learning_rate": 3.847583643122677e-06, "loss": 1.765, "step": 1550 }, { "epoch": 1.19, "learning_rate": 3.810408921933086e-06, "loss": 1.745, "step": 1600 }, { "epoch": 1.23, "learning_rate": 3.7732342007434947e-06, "loss": 1.744, "step": 1650 }, { "epoch": 1.26, "learning_rate": 3.7360594795539034e-06, "loss": 1.7699, "step": 1700 }, { "epoch": 1.3, "learning_rate": 3.698884758364313e-06, "loss": 1.7533, "step": 1750 }, { "epoch": 1.34, "learning_rate": 3.6617100371747216e-06, "loss": 1.7777, "step": 1800 }, { "epoch": 1.37, "learning_rate": 3.6245353159851303e-06, "loss": 1.7703, "step": 1850 }, { "epoch": 1.41, "learning_rate": 3.5873605947955394e-06, "loss": 1.7683, "step": 1900 }, { "epoch": 1.45, "learning_rate": 3.550185873605948e-06, "loss": 1.7347, "step": 1950 }, { "epoch": 1.49, "learning_rate": 3.5130111524163572e-06, "loss": 1.795, "step": 2000 }, { "epoch": 1.52, "learning_rate": 3.4758364312267663e-06, "loss": 1.7617, "step": 2050 }, { "epoch": 1.56, "learning_rate": 3.438661710037175e-06, "loss": 1.779, "step": 2100 }, { "epoch": 1.6, "learning_rate": 3.4014869888475837e-06, "loss": 1.7368, "step": 2150 }, { "epoch": 1.63, "learning_rate": 3.3643122676579924e-06, "loss": 1.7389, "step": 2200 }, { "epoch": 1.67, "learning_rate": 3.327137546468402e-06, "loss": 1.7511, "step": 2250 }, { "epoch": 1.71, "learning_rate": 3.2899628252788106e-06, "loss": 1.7434, "step": 2300 }, { "epoch": 1.75, "learning_rate": 3.2527881040892197e-06, "loss": 1.7498, "step": 2350 }, { "epoch": 1.78, "learning_rate": 3.2156133828996284e-06, "loss": 1.7628, "step": 2400 }, { "epoch": 1.82, "learning_rate": 3.1784386617100375e-06, "loss": 1.7477, "step": 2450 }, { "epoch": 1.86, "learning_rate": 3.1412639405204466e-06, "loss": 1.7427, "step": 2500 }, { "epoch": 1.9, "learning_rate": 3.1040892193308553e-06, "loss": 1.7498, "step": 2550 }, { "epoch": 1.93, "learning_rate": 3.066914498141264e-06, "loss": 1.7589, "step": 2600 }, { "epoch": 1.97, "learning_rate": 3.0297397769516727e-06, "loss": 1.7384, "step": 2650 }, { "epoch": 2.01, "learning_rate": 2.9925650557620822e-06, "loss": 1.7577, "step": 2700 }, { "epoch": 2.04, "learning_rate": 2.955390334572491e-06, "loss": 1.7454, "step": 2750 }, { "epoch": 2.08, "learning_rate": 2.9182156133829e-06, "loss": 1.7235, "step": 2800 }, { "epoch": 2.12, "learning_rate": 2.8810408921933087e-06, "loss": 1.7398, "step": 2850 }, { "epoch": 2.16, "learning_rate": 2.843866171003718e-06, "loss": 1.762, "step": 2900 }, { "epoch": 2.19, "learning_rate": 2.806691449814127e-06, "loss": 1.7521, "step": 2950 }, { "epoch": 2.23, "learning_rate": 2.7695167286245356e-06, "loss": 1.7414, "step": 3000 }, { "epoch": 2.27, "learning_rate": 2.7323420074349443e-06, "loss": 1.7409, "step": 3050 }, { "epoch": 2.3, "learning_rate": 2.695167286245353e-06, "loss": 1.7334, "step": 3100 }, { "epoch": 2.34, "learning_rate": 2.6579925650557625e-06, "loss": 1.7119, "step": 3150 }, { "epoch": 2.38, "learning_rate": 2.6208178438661712e-06, "loss": 1.7257, "step": 3200 }, { "epoch": 2.42, "learning_rate": 2.5836431226765803e-06, "loss": 1.7319, "step": 3250 }, { "epoch": 2.45, "learning_rate": 2.546468401486989e-06, "loss": 1.7527, "step": 3300 }, { "epoch": 2.49, "learning_rate": 2.5092936802973977e-06, "loss": 1.7386, "step": 3350 }, { "epoch": 2.53, "learning_rate": 2.472118959107807e-06, "loss": 1.7368, "step": 3400 }, { "epoch": 2.56, "learning_rate": 2.434944237918216e-06, "loss": 1.7521, "step": 3450 }, { "epoch": 2.6, "learning_rate": 2.3977695167286246e-06, "loss": 1.7251, "step": 3500 }, { "epoch": 2.64, "learning_rate": 2.3605947955390337e-06, "loss": 1.7315, "step": 3550 }, { "epoch": 2.68, "learning_rate": 2.3234200743494424e-06, "loss": 1.7337, "step": 3600 }, { "epoch": 2.71, "learning_rate": 2.2862453531598515e-06, "loss": 1.71, "step": 3650 }, { "epoch": 2.75, "learning_rate": 2.2490706319702602e-06, "loss": 1.7086, "step": 3700 }, { "epoch": 2.79, "learning_rate": 2.2118959107806693e-06, "loss": 1.7308, "step": 3750 }, { "epoch": 2.82, "learning_rate": 2.1747211895910784e-06, "loss": 1.7246, "step": 3800 }, { "epoch": 2.86, "learning_rate": 2.137546468401487e-06, "loss": 1.7339, "step": 3850 }, { "epoch": 2.9, "learning_rate": 2.1003717472118962e-06, "loss": 1.7404, "step": 3900 }, { "epoch": 2.94, "learning_rate": 2.063197026022305e-06, "loss": 1.7253, "step": 3950 }, { "epoch": 2.97, "learning_rate": 2.0260223048327136e-06, "loss": 1.716, "step": 4000 }, { "epoch": 3.01, "learning_rate": 1.9888475836431227e-06, "loss": 1.7423, "step": 4050 }, { "epoch": 3.05, "learning_rate": 1.951672862453532e-06, "loss": 1.7203, "step": 4100 }, { "epoch": 3.08, "learning_rate": 1.9144981412639405e-06, "loss": 1.7063, "step": 4150 }, { "epoch": 3.12, "learning_rate": 1.8773234200743496e-06, "loss": 1.7304, "step": 4200 }, { "epoch": 3.16, "learning_rate": 1.8401486988847585e-06, "loss": 1.7125, "step": 4250 }, { "epoch": 3.2, "learning_rate": 1.8029739776951674e-06, "loss": 1.7448, "step": 4300 }, { "epoch": 3.23, "learning_rate": 1.7657992565055765e-06, "loss": 1.7127, "step": 4350 }, { "epoch": 3.27, "learning_rate": 1.7286245353159852e-06, "loss": 1.7353, "step": 4400 }, { "epoch": 3.31, "learning_rate": 1.6914498141263941e-06, "loss": 1.7128, "step": 4450 }, { "epoch": 3.34, "learning_rate": 1.6542750929368032e-06, "loss": 1.7262, "step": 4500 }, { "epoch": 3.38, "learning_rate": 1.617100371747212e-06, "loss": 1.7183, "step": 4550 }, { "epoch": 3.42, "learning_rate": 1.579925650557621e-06, "loss": 1.6963, "step": 4600 }, { "epoch": 3.46, "learning_rate": 1.54275092936803e-06, "loss": 1.7084, "step": 4650 }, { "epoch": 3.49, "learning_rate": 1.5055762081784388e-06, "loss": 1.7101, "step": 4700 }, { "epoch": 3.53, "learning_rate": 1.4684014869888477e-06, "loss": 1.7223, "step": 4750 }, { "epoch": 3.57, "learning_rate": 1.4312267657992564e-06, "loss": 1.7015, "step": 4800 }, { "epoch": 3.6, "learning_rate": 1.3940520446096655e-06, "loss": 1.7044, "step": 4850 }, { "epoch": 3.64, "learning_rate": 1.3568773234200744e-06, "loss": 1.7352, "step": 4900 }, { "epoch": 3.68, "learning_rate": 1.3197026022304835e-06, "loss": 1.7363, "step": 4950 }, { "epoch": 3.72, "learning_rate": 1.2825278810408922e-06, "loss": 1.7145, "step": 5000 }, { "epoch": 3.75, "learning_rate": 1.2453531598513011e-06, "loss": 1.7229, "step": 5050 }, { "epoch": 3.79, "learning_rate": 1.20817843866171e-06, "loss": 1.715, "step": 5100 }, { "epoch": 3.83, "learning_rate": 1.1710037174721191e-06, "loss": 1.7354, "step": 5150 }, { "epoch": 3.86, "learning_rate": 1.133828996282528e-06, "loss": 1.7074, "step": 5200 }, { "epoch": 3.9, "learning_rate": 1.096654275092937e-06, "loss": 1.7159, "step": 5250 }, { "epoch": 3.94, "learning_rate": 1.0594795539033458e-06, "loss": 1.7391, "step": 5300 }, { "epoch": 3.98, "learning_rate": 1.0223048327137547e-06, "loss": 1.688, "step": 5350 }, { "epoch": 4.01, "learning_rate": 9.851301115241636e-07, "loss": 1.7221, "step": 5400 }, { "epoch": 4.05, "learning_rate": 9.479553903345725e-07, "loss": 1.7209, "step": 5450 }, { "epoch": 4.09, "learning_rate": 9.107806691449815e-07, "loss": 1.7422, "step": 5500 }, { "epoch": 4.12, "learning_rate": 8.736059479553904e-07, "loss": 1.703, "step": 5550 }, { "epoch": 4.16, "learning_rate": 8.364312267657993e-07, "loss": 1.7399, "step": 5600 }, { "epoch": 4.2, "learning_rate": 7.992565055762081e-07, "loss": 1.7112, "step": 5650 }, { "epoch": 4.24, "learning_rate": 7.620817843866171e-07, "loss": 1.7074, "step": 5700 }, { "epoch": 4.27, "learning_rate": 7.24907063197026e-07, "loss": 1.7104, "step": 5750 }, { "epoch": 4.31, "learning_rate": 6.87732342007435e-07, "loss": 1.7184, "step": 5800 }, { "epoch": 4.35, "learning_rate": 6.505576208178439e-07, "loss": 1.7118, "step": 5850 }, { "epoch": 4.38, "learning_rate": 6.133828996282528e-07, "loss": 1.6882, "step": 5900 }, { "epoch": 4.42, "learning_rate": 5.762081784386617e-07, "loss": 1.6995, "step": 5950 }, { "epoch": 4.46, "learning_rate": 5.390334572490706e-07, "loss": 1.694, "step": 6000 }, { "epoch": 4.5, "learning_rate": 5.018587360594796e-07, "loss": 1.6957, "step": 6050 }, { "epoch": 4.53, "learning_rate": 4.646840148698885e-07, "loss": 1.7316, "step": 6100 }, { "epoch": 4.57, "learning_rate": 4.2750929368029745e-07, "loss": 1.6981, "step": 6150 }, { "epoch": 4.61, "learning_rate": 3.9033457249070635e-07, "loss": 1.7133, "step": 6200 }, { "epoch": 4.64, "learning_rate": 3.531598513011153e-07, "loss": 1.6907, "step": 6250 }, { "epoch": 4.68, "learning_rate": 3.1598513011152414e-07, "loss": 1.7058, "step": 6300 }, { "epoch": 4.72, "learning_rate": 2.788104089219331e-07, "loss": 1.7117, "step": 6350 }, { "epoch": 4.76, "learning_rate": 2.4163568773234205e-07, "loss": 1.7143, "step": 6400 }, { "epoch": 4.79, "learning_rate": 2.0446096654275095e-07, "loss": 1.7068, "step": 6450 }, { "epoch": 4.83, "learning_rate": 1.6728624535315985e-07, "loss": 1.6976, "step": 6500 }, { "epoch": 4.87, "learning_rate": 1.3011152416356877e-07, "loss": 1.7176, "step": 6550 }, { "epoch": 4.9, "learning_rate": 9.293680297397771e-08, "loss": 1.717, "step": 6600 }, { "epoch": 4.94, "learning_rate": 5.576208178438662e-08, "loss": 1.7004, "step": 6650 }, { "epoch": 4.98, "learning_rate": 1.858736059479554e-08, "loss": 1.7247, "step": 6700 }, { "epoch": 5.0, "step": 6725, "total_flos": 9.348094067612314e+16, "train_loss": 1.74816911605211, "train_runtime": 8144.5226, "train_samples_per_second": 158.606, "train_steps_per_second": 0.826 } ], "logging_steps": 50, "max_steps": 6725, "num_train_epochs": 5, "save_steps": 500, "total_flos": 9.348094067612314e+16, "trial_name": null, "trial_params": null }