{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8229775327133569, "eval_steps": 500, "global_step": 10000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.973833272194737e-06, "loss": 0.2911, "step": 25 }, { "epoch": 0.0, "learning_rate": 6.195318418690893e-06, "loss": 0.2716, "step": 50 }, { "epoch": 0.01, "learning_rate": 6.881634451095711e-06, "loss": 0.3044, "step": 75 }, { "epoch": 0.01, "learning_rate": 7.361221988663844e-06, "loss": 0.3361, "step": 100 }, { "epoch": 0.01, "learning_rate": 7.730207550743121e-06, "loss": 0.3092, "step": 125 }, { "epoch": 0.01, "learning_rate": 8.03016458599496e-06, "loss": 0.3179, "step": 150 }, { "epoch": 0.01, "learning_rate": 8.282894746203441e-06, "loss": 0.3034, "step": 175 }, { "epoch": 0.02, "learning_rate": 8.501266121799902e-06, "loss": 0.3162, "step": 200 }, { "epoch": 0.02, "learning_rate": 8.693512601774437e-06, "loss": 0.3477, "step": 225 }, { "epoch": 0.02, "learning_rate": 8.865222471593567e-06, "loss": 0.2986, "step": 250 }, { "epoch": 0.02, "learning_rate": 9.020362953730323e-06, "loss": 0.3015, "step": 275 }, { "epoch": 0.02, "learning_rate": 9.161852281961698e-06, "loss": 0.2827, "step": 300 }, { "epoch": 0.03, "learning_rate": 9.29189975311636e-06, "loss": 0.331, "step": 325 }, { "epoch": 0.03, "learning_rate": 9.412218256259678e-06, "loss": 0.3151, "step": 350 }, { "epoch": 0.03, "learning_rate": 9.524162683365145e-06, "loss": 0.3265, "step": 375 }, { "epoch": 0.03, "learning_rate": 9.62882322733502e-06, "loss": 0.3534, "step": 400 }, { "epoch": 0.03, "learning_rate": 9.727090137141168e-06, "loss": 0.333, "step": 425 }, { "epoch": 0.04, "learning_rate": 9.819699807237934e-06, "loss": 0.3401, "step": 450 }, { "epoch": 0.04, "learning_rate": 9.907268307310855e-06, "loss": 0.3187, "step": 475 }, { "epoch": 0.04, "learning_rate": 9.990316248055788e-06, "loss": 0.2805, "step": 500 }, { "epoch": 0.04, "learning_rate": 9.977894736842106e-06, "loss": 0.3064, "step": 525 }, { "epoch": 0.05, "learning_rate": 9.951578947368423e-06, "loss": 0.3111, "step": 550 }, { "epoch": 0.05, "learning_rate": 9.925263157894738e-06, "loss": 0.3216, "step": 575 }, { "epoch": 0.05, "learning_rate": 9.898947368421054e-06, "loss": 0.2801, "step": 600 }, { "epoch": 0.05, "learning_rate": 9.87263157894737e-06, "loss": 0.3215, "step": 625 }, { "epoch": 0.05, "learning_rate": 9.846315789473684e-06, "loss": 0.3076, "step": 650 }, { "epoch": 0.06, "learning_rate": 9.820000000000001e-06, "loss": 0.3093, "step": 675 }, { "epoch": 0.06, "learning_rate": 9.793684210526316e-06, "loss": 0.3283, "step": 700 }, { "epoch": 0.06, "learning_rate": 9.767368421052632e-06, "loss": 0.3067, "step": 725 }, { "epoch": 0.06, "learning_rate": 9.741052631578947e-06, "loss": 0.3007, "step": 750 }, { "epoch": 0.06, "learning_rate": 9.714736842105264e-06, "loss": 0.3346, "step": 775 }, { "epoch": 0.07, "learning_rate": 9.68842105263158e-06, "loss": 0.3065, "step": 800 }, { "epoch": 0.07, "learning_rate": 9.662105263157896e-06, "loss": 0.2789, "step": 825 }, { "epoch": 0.07, "learning_rate": 9.635789473684212e-06, "loss": 0.2787, "step": 850 }, { "epoch": 0.07, "learning_rate": 9.609473684210527e-06, "loss": 0.3096, "step": 875 }, { "epoch": 0.07, "learning_rate": 9.583157894736842e-06, "loss": 0.3124, "step": 900 }, { "epoch": 0.08, "learning_rate": 9.556842105263159e-06, "loss": 0.318, "step": 925 }, { "epoch": 0.08, "learning_rate": 9.530526315789474e-06, "loss": 0.3009, "step": 950 }, { "epoch": 0.08, "learning_rate": 9.50421052631579e-06, "loss": 0.3188, "step": 975 }, { "epoch": 0.08, "learning_rate": 9.477894736842106e-06, "loss": 0.3381, "step": 1000 }, { "epoch": 0.08, "learning_rate": 9.451578947368422e-06, "loss": 0.3111, "step": 1025 }, { "epoch": 0.09, "learning_rate": 9.426315789473685e-06, "loss": 0.3211, "step": 1050 }, { "epoch": 0.09, "learning_rate": 9.4e-06, "loss": 0.2732, "step": 1075 }, { "epoch": 0.09, "learning_rate": 9.373684210526316e-06, "loss": 0.2863, "step": 1100 }, { "epoch": 0.09, "learning_rate": 9.347368421052633e-06, "loss": 0.278, "step": 1125 }, { "epoch": 0.09, "learning_rate": 9.321052631578948e-06, "loss": 0.2769, "step": 1150 }, { "epoch": 0.1, "learning_rate": 9.29578947368421e-06, "loss": 0.3114, "step": 1175 }, { "epoch": 0.1, "learning_rate": 9.269473684210527e-06, "loss": 0.3132, "step": 1200 }, { "epoch": 0.1, "learning_rate": 9.243157894736842e-06, "loss": 0.2859, "step": 1225 }, { "epoch": 0.1, "learning_rate": 9.216842105263159e-06, "loss": 0.3041, "step": 1250 }, { "epoch": 0.1, "learning_rate": 9.190526315789474e-06, "loss": 0.3011, "step": 1275 }, { "epoch": 0.11, "learning_rate": 9.16421052631579e-06, "loss": 0.3565, "step": 1300 }, { "epoch": 0.11, "learning_rate": 9.137894736842106e-06, "loss": 0.3007, "step": 1325 }, { "epoch": 0.11, "learning_rate": 9.11157894736842e-06, "loss": 0.3157, "step": 1350 }, { "epoch": 0.11, "learning_rate": 9.085263157894739e-06, "loss": 0.2861, "step": 1375 }, { "epoch": 0.12, "learning_rate": 9.058947368421054e-06, "loss": 0.3105, "step": 1400 }, { "epoch": 0.12, "learning_rate": 9.032631578947369e-06, "loss": 0.2818, "step": 1425 }, { "epoch": 0.12, "learning_rate": 9.006315789473685e-06, "loss": 0.288, "step": 1450 }, { "epoch": 0.12, "learning_rate": 8.98e-06, "loss": 0.2906, "step": 1475 }, { "epoch": 0.12, "learning_rate": 8.953684210526317e-06, "loss": 0.3028, "step": 1500 }, { "epoch": 0.13, "learning_rate": 8.927368421052632e-06, "loss": 0.3187, "step": 1525 }, { "epoch": 0.13, "learning_rate": 8.901052631578949e-06, "loss": 0.2838, "step": 1550 }, { "epoch": 0.13, "learning_rate": 8.874736842105264e-06, "loss": 0.2909, "step": 1575 }, { "epoch": 0.13, "learning_rate": 8.848421052631579e-06, "loss": 0.3033, "step": 1600 }, { "epoch": 0.13, "learning_rate": 8.822105263157895e-06, "loss": 0.3133, "step": 1625 }, { "epoch": 0.14, "learning_rate": 8.79578947368421e-06, "loss": 0.3189, "step": 1650 }, { "epoch": 0.14, "learning_rate": 8.769473684210527e-06, "loss": 0.2803, "step": 1675 }, { "epoch": 0.14, "learning_rate": 8.743157894736842e-06, "loss": 0.2783, "step": 1700 }, { "epoch": 0.14, "learning_rate": 8.716842105263159e-06, "loss": 0.2969, "step": 1725 }, { "epoch": 0.14, "learning_rate": 8.690526315789475e-06, "loss": 0.294, "step": 1750 }, { "epoch": 0.15, "learning_rate": 8.66421052631579e-06, "loss": 0.2969, "step": 1775 }, { "epoch": 0.15, "learning_rate": 8.637894736842107e-06, "loss": 0.2893, "step": 1800 }, { "epoch": 0.15, "learning_rate": 8.611578947368422e-06, "loss": 0.2782, "step": 1825 }, { "epoch": 0.15, "learning_rate": 8.585263157894737e-06, "loss": 0.2821, "step": 1850 }, { "epoch": 0.15, "learning_rate": 8.558947368421054e-06, "loss": 0.3172, "step": 1875 }, { "epoch": 0.16, "learning_rate": 8.532631578947368e-06, "loss": 0.2874, "step": 1900 }, { "epoch": 0.16, "learning_rate": 8.506315789473685e-06, "loss": 0.2862, "step": 1925 }, { "epoch": 0.16, "learning_rate": 8.48e-06, "loss": 0.3067, "step": 1950 }, { "epoch": 0.16, "learning_rate": 8.453684210526317e-06, "loss": 0.2936, "step": 1975 }, { "epoch": 0.16, "learning_rate": 8.427368421052632e-06, "loss": 0.292, "step": 2000 }, { "epoch": 0.17, "learning_rate": 8.401052631578947e-06, "loss": 0.2907, "step": 2025 }, { "epoch": 0.17, "learning_rate": 8.374736842105265e-06, "loss": 0.2992, "step": 2050 }, { "epoch": 0.17, "learning_rate": 8.34842105263158e-06, "loss": 0.3135, "step": 2075 }, { "epoch": 0.17, "learning_rate": 8.322105263157895e-06, "loss": 0.29, "step": 2100 }, { "epoch": 0.17, "learning_rate": 8.295789473684212e-06, "loss": 0.2971, "step": 2125 }, { "epoch": 0.18, "learning_rate": 8.269473684210527e-06, "loss": 0.2728, "step": 2150 }, { "epoch": 0.18, "learning_rate": 8.243157894736843e-06, "loss": 0.3034, "step": 2175 }, { "epoch": 0.18, "learning_rate": 8.216842105263158e-06, "loss": 0.3127, "step": 2200 }, { "epoch": 0.18, "learning_rate": 8.190526315789475e-06, "loss": 0.2763, "step": 2225 }, { "epoch": 0.19, "learning_rate": 8.16421052631579e-06, "loss": 0.271, "step": 2250 }, { "epoch": 0.19, "learning_rate": 8.137894736842105e-06, "loss": 0.2928, "step": 2275 }, { "epoch": 0.19, "learning_rate": 8.111578947368422e-06, "loss": 0.2631, "step": 2300 }, { "epoch": 0.19, "learning_rate": 8.085263157894737e-06, "loss": 0.2718, "step": 2325 }, { "epoch": 0.19, "learning_rate": 8.058947368421053e-06, "loss": 0.2446, "step": 2350 }, { "epoch": 0.2, "learning_rate": 8.032631578947368e-06, "loss": 0.2605, "step": 2375 }, { "epoch": 0.2, "learning_rate": 8.006315789473685e-06, "loss": 0.3162, "step": 2400 }, { "epoch": 0.2, "learning_rate": 7.980000000000002e-06, "loss": 0.2813, "step": 2425 }, { "epoch": 0.2, "learning_rate": 7.953684210526316e-06, "loss": 0.3089, "step": 2450 }, { "epoch": 0.2, "learning_rate": 7.927368421052633e-06, "loss": 0.2781, "step": 2475 }, { "epoch": 0.21, "learning_rate": 7.901052631578948e-06, "loss": 0.2922, "step": 2500 }, { "epoch": 0.21, "learning_rate": 7.874736842105263e-06, "loss": 0.2815, "step": 2525 }, { "epoch": 0.21, "learning_rate": 7.84842105263158e-06, "loss": 0.3169, "step": 2550 }, { "epoch": 0.21, "learning_rate": 7.822105263157895e-06, "loss": 0.2972, "step": 2575 }, { "epoch": 0.21, "learning_rate": 7.795789473684211e-06, "loss": 0.2665, "step": 2600 }, { "epoch": 0.22, "learning_rate": 7.769473684210526e-06, "loss": 0.3149, "step": 2625 }, { "epoch": 0.22, "learning_rate": 7.743157894736843e-06, "loss": 0.2909, "step": 2650 }, { "epoch": 0.22, "learning_rate": 7.716842105263158e-06, "loss": 0.3011, "step": 2675 }, { "epoch": 0.22, "learning_rate": 7.690526315789475e-06, "loss": 0.2796, "step": 2700 }, { "epoch": 0.22, "learning_rate": 7.665263157894737e-06, "loss": 0.2854, "step": 2725 }, { "epoch": 0.23, "learning_rate": 7.638947368421054e-06, "loss": 0.2423, "step": 2750 }, { "epoch": 0.23, "learning_rate": 7.61263157894737e-06, "loss": 0.2515, "step": 2775 }, { "epoch": 0.23, "learning_rate": 7.586315789473685e-06, "loss": 0.262, "step": 2800 }, { "epoch": 0.23, "learning_rate": 7.5600000000000005e-06, "loss": 0.2886, "step": 2825 }, { "epoch": 0.23, "learning_rate": 7.533684210526316e-06, "loss": 0.2685, "step": 2850 }, { "epoch": 0.24, "learning_rate": 7.507368421052632e-06, "loss": 0.2905, "step": 2875 }, { "epoch": 0.24, "learning_rate": 7.481052631578948e-06, "loss": 0.2779, "step": 2900 }, { "epoch": 0.24, "learning_rate": 7.454736842105264e-06, "loss": 0.2687, "step": 2925 }, { "epoch": 0.24, "learning_rate": 7.4284210526315796e-06, "loss": 0.2618, "step": 2950 }, { "epoch": 0.24, "learning_rate": 7.4021052631578945e-06, "loss": 0.2931, "step": 2975 }, { "epoch": 0.25, "learning_rate": 7.37578947368421e-06, "loss": 0.2764, "step": 3000 }, { "epoch": 0.25, "learning_rate": 7.349473684210527e-06, "loss": 0.2738, "step": 3025 }, { "epoch": 0.25, "learning_rate": 7.323157894736843e-06, "loss": 0.3016, "step": 3050 }, { "epoch": 0.25, "learning_rate": 7.296842105263159e-06, "loss": 0.308, "step": 3075 }, { "epoch": 0.26, "learning_rate": 7.2705263157894745e-06, "loss": 0.2791, "step": 3100 }, { "epoch": 0.26, "learning_rate": 7.245263157894738e-06, "loss": 0.2367, "step": 3125 }, { "epoch": 0.26, "learning_rate": 7.218947368421053e-06, "loss": 0.2715, "step": 3150 }, { "epoch": 0.26, "learning_rate": 7.192631578947369e-06, "loss": 0.2637, "step": 3175 }, { "epoch": 0.26, "learning_rate": 7.1663157894736844e-06, "loss": 0.2618, "step": 3200 }, { "epoch": 0.27, "learning_rate": 7.14e-06, "loss": 0.3005, "step": 3225 }, { "epoch": 0.27, "learning_rate": 7.113684210526316e-06, "loss": 0.2772, "step": 3250 }, { "epoch": 0.27, "learning_rate": 7.087368421052632e-06, "loss": 0.263, "step": 3275 }, { "epoch": 0.27, "learning_rate": 7.0610526315789486e-06, "loss": 0.2828, "step": 3300 }, { "epoch": 0.27, "learning_rate": 7.034736842105264e-06, "loss": 0.2733, "step": 3325 }, { "epoch": 0.28, "learning_rate": 7.00842105263158e-06, "loss": 0.2733, "step": 3350 }, { "epoch": 0.28, "learning_rate": 6.982105263157896e-06, "loss": 0.2987, "step": 3375 }, { "epoch": 0.28, "learning_rate": 6.955789473684211e-06, "loss": 0.2789, "step": 3400 }, { "epoch": 0.28, "learning_rate": 6.929473684210527e-06, "loss": 0.2579, "step": 3425 }, { "epoch": 0.28, "learning_rate": 6.903157894736843e-06, "loss": 0.2624, "step": 3450 }, { "epoch": 0.29, "learning_rate": 6.8768421052631584e-06, "loss": 0.2566, "step": 3475 }, { "epoch": 0.29, "learning_rate": 6.850526315789474e-06, "loss": 0.2585, "step": 3500 }, { "epoch": 0.29, "learning_rate": 6.82421052631579e-06, "loss": 0.2707, "step": 3525 }, { "epoch": 0.29, "learning_rate": 6.797894736842106e-06, "loss": 0.2676, "step": 3550 }, { "epoch": 0.29, "learning_rate": 6.771578947368421e-06, "loss": 0.2609, "step": 3575 }, { "epoch": 0.3, "learning_rate": 6.745263157894737e-06, "loss": 0.287, "step": 3600 }, { "epoch": 0.3, "learning_rate": 6.7189473684210525e-06, "loss": 0.2738, "step": 3625 }, { "epoch": 0.3, "learning_rate": 6.692631578947369e-06, "loss": 0.2999, "step": 3650 }, { "epoch": 0.3, "learning_rate": 6.666315789473685e-06, "loss": 0.2781, "step": 3675 }, { "epoch": 0.3, "learning_rate": 6.640000000000001e-06, "loss": 0.2635, "step": 3700 }, { "epoch": 0.31, "learning_rate": 6.613684210526317e-06, "loss": 0.2851, "step": 3725 }, { "epoch": 0.31, "learning_rate": 6.5873684210526324e-06, "loss": 0.2797, "step": 3750 }, { "epoch": 0.31, "learning_rate": 6.561052631578948e-06, "loss": 0.2699, "step": 3775 }, { "epoch": 0.31, "learning_rate": 6.534736842105264e-06, "loss": 0.2723, "step": 3800 }, { "epoch": 0.31, "learning_rate": 6.508421052631579e-06, "loss": 0.2554, "step": 3825 }, { "epoch": 0.32, "learning_rate": 6.482105263157895e-06, "loss": 0.2652, "step": 3850 }, { "epoch": 0.32, "learning_rate": 6.455789473684211e-06, "loss": 0.2598, "step": 3875 }, { "epoch": 0.32, "learning_rate": 6.4294736842105265e-06, "loss": 0.2722, "step": 3900 }, { "epoch": 0.32, "learning_rate": 6.403157894736842e-06, "loss": 0.276, "step": 3925 }, { "epoch": 0.33, "learning_rate": 6.376842105263158e-06, "loss": 0.2766, "step": 3950 }, { "epoch": 0.33, "learning_rate": 6.350526315789474e-06, "loss": 0.2281, "step": 3975 }, { "epoch": 0.33, "learning_rate": 6.324210526315791e-06, "loss": 0.2417, "step": 4000 }, { "epoch": 0.33, "learning_rate": 6.2978947368421064e-06, "loss": 0.2835, "step": 4025 }, { "epoch": 0.33, "learning_rate": 6.271578947368422e-06, "loss": 0.2561, "step": 4050 }, { "epoch": 0.34, "learning_rate": 6.245263157894737e-06, "loss": 0.2404, "step": 4075 }, { "epoch": 0.34, "learning_rate": 6.218947368421053e-06, "loss": 0.2871, "step": 4100 }, { "epoch": 0.34, "learning_rate": 6.192631578947369e-06, "loss": 0.2727, "step": 4125 }, { "epoch": 0.34, "learning_rate": 6.166315789473685e-06, "loss": 0.2904, "step": 4150 }, { "epoch": 0.34, "learning_rate": 6.1400000000000005e-06, "loss": 0.2797, "step": 4175 }, { "epoch": 0.35, "learning_rate": 6.113684210526316e-06, "loss": 0.2639, "step": 4200 }, { "epoch": 0.35, "learning_rate": 6.087368421052632e-06, "loss": 0.2515, "step": 4225 }, { "epoch": 0.35, "learning_rate": 6.061052631578947e-06, "loss": 0.2511, "step": 4250 }, { "epoch": 0.35, "learning_rate": 6.034736842105263e-06, "loss": 0.2887, "step": 4275 }, { "epoch": 0.35, "learning_rate": 6.008421052631579e-06, "loss": 0.2978, "step": 4300 }, { "epoch": 0.36, "learning_rate": 5.982105263157895e-06, "loss": 0.2527, "step": 4325 }, { "epoch": 0.36, "learning_rate": 5.955789473684211e-06, "loss": 0.2603, "step": 4350 }, { "epoch": 0.36, "learning_rate": 5.929473684210527e-06, "loss": 0.2543, "step": 4375 }, { "epoch": 0.36, "learning_rate": 5.903157894736843e-06, "loss": 0.273, "step": 4400 }, { "epoch": 0.36, "learning_rate": 5.876842105263159e-06, "loss": 0.2618, "step": 4425 }, { "epoch": 0.37, "learning_rate": 5.8505263157894745e-06, "loss": 0.2507, "step": 4450 }, { "epoch": 0.37, "learning_rate": 5.82421052631579e-06, "loss": 0.2727, "step": 4475 }, { "epoch": 0.37, "learning_rate": 5.797894736842105e-06, "loss": 0.247, "step": 4500 }, { "epoch": 0.37, "learning_rate": 5.771578947368421e-06, "loss": 0.2776, "step": 4525 }, { "epoch": 0.37, "learning_rate": 5.745263157894737e-06, "loss": 0.265, "step": 4550 }, { "epoch": 0.38, "learning_rate": 5.718947368421053e-06, "loss": 0.2435, "step": 4575 }, { "epoch": 0.38, "learning_rate": 5.6926315789473686e-06, "loss": 0.2648, "step": 4600 }, { "epoch": 0.38, "learning_rate": 5.666315789473684e-06, "loss": 0.2609, "step": 4625 }, { "epoch": 0.38, "learning_rate": 5.64e-06, "loss": 0.261, "step": 4650 }, { "epoch": 0.38, "learning_rate": 5.613684210526317e-06, "loss": 0.2394, "step": 4675 }, { "epoch": 0.39, "learning_rate": 5.587368421052633e-06, "loss": 0.2782, "step": 4700 }, { "epoch": 0.39, "learning_rate": 5.5610526315789485e-06, "loss": 0.2652, "step": 4725 }, { "epoch": 0.39, "learning_rate": 5.5347368421052635e-06, "loss": 0.2611, "step": 4750 }, { "epoch": 0.39, "learning_rate": 5.508421052631579e-06, "loss": 0.2421, "step": 4775 }, { "epoch": 0.4, "learning_rate": 5.482105263157895e-06, "loss": 0.2718, "step": 4800 }, { "epoch": 0.4, "learning_rate": 5.455789473684211e-06, "loss": 0.242, "step": 4825 }, { "epoch": 0.4, "learning_rate": 5.429473684210527e-06, "loss": 0.2975, "step": 4850 }, { "epoch": 0.4, "learning_rate": 5.403157894736843e-06, "loss": 0.2579, "step": 4875 }, { "epoch": 0.4, "learning_rate": 5.376842105263158e-06, "loss": 0.2727, "step": 4900 }, { "epoch": 0.41, "learning_rate": 5.350526315789473e-06, "loss": 0.258, "step": 4925 }, { "epoch": 0.41, "learning_rate": 5.324210526315789e-06, "loss": 0.2813, "step": 4950 }, { "epoch": 0.41, "learning_rate": 5.297894736842105e-06, "loss": 0.2398, "step": 4975 }, { "epoch": 0.41, "learning_rate": 5.271578947368422e-06, "loss": 0.2801, "step": 5000 }, { "epoch": 0.41, "learning_rate": 5.2452631578947375e-06, "loss": 0.3113, "step": 5025 }, { "epoch": 0.42, "learning_rate": 5.218947368421053e-06, "loss": 0.2597, "step": 5050 }, { "epoch": 0.42, "learning_rate": 5.192631578947369e-06, "loss": 0.2435, "step": 5075 }, { "epoch": 0.42, "learning_rate": 5.166315789473685e-06, "loss": 0.283, "step": 5100 }, { "epoch": 0.42, "learning_rate": 5.142105263157895e-06, "loss": 0.32, "step": 5125 }, { "epoch": 0.42, "learning_rate": 5.115789473684211e-06, "loss": 0.2682, "step": 5150 }, { "epoch": 0.43, "learning_rate": 5.089473684210527e-06, "loss": 0.2547, "step": 5175 }, { "epoch": 0.43, "learning_rate": 5.0631578947368424e-06, "loss": 0.2734, "step": 5200 }, { "epoch": 0.43, "learning_rate": 5.036842105263157e-06, "loss": 0.279, "step": 5225 }, { "epoch": 0.43, "learning_rate": 5.010526315789475e-06, "loss": 0.279, "step": 5250 }, { "epoch": 0.43, "learning_rate": 4.98421052631579e-06, "loss": 0.2692, "step": 5275 }, { "epoch": 0.44, "learning_rate": 4.957894736842106e-06, "loss": 0.2608, "step": 5300 }, { "epoch": 0.44, "learning_rate": 4.9315789473684215e-06, "loss": 0.2801, "step": 5325 }, { "epoch": 0.44, "learning_rate": 4.905263157894737e-06, "loss": 0.2544, "step": 5350 }, { "epoch": 0.44, "learning_rate": 4.878947368421053e-06, "loss": 0.2413, "step": 5375 }, { "epoch": 0.44, "learning_rate": 4.852631578947369e-06, "loss": 0.2669, "step": 5400 }, { "epoch": 0.45, "learning_rate": 4.826315789473685e-06, "loss": 0.2671, "step": 5425 }, { "epoch": 0.45, "learning_rate": 4.801052631578948e-06, "loss": 0.2484, "step": 5450 }, { "epoch": 0.45, "learning_rate": 4.774736842105264e-06, "loss": 0.2685, "step": 5475 }, { "epoch": 0.45, "learning_rate": 4.748421052631579e-06, "loss": 0.2565, "step": 5500 }, { "epoch": 0.45, "learning_rate": 4.722105263157895e-06, "loss": 0.2798, "step": 5525 }, { "epoch": 0.46, "learning_rate": 4.695789473684211e-06, "loss": 0.2561, "step": 5550 }, { "epoch": 0.46, "learning_rate": 4.669473684210526e-06, "loss": 0.232, "step": 5575 }, { "epoch": 0.46, "learning_rate": 4.643157894736843e-06, "loss": 0.277, "step": 5600 }, { "epoch": 0.46, "learning_rate": 4.616842105263158e-06, "loss": 0.2998, "step": 5625 }, { "epoch": 0.46, "learning_rate": 4.590526315789474e-06, "loss": 0.2634, "step": 5650 }, { "epoch": 0.47, "learning_rate": 4.56421052631579e-06, "loss": 0.2818, "step": 5675 }, { "epoch": 0.47, "learning_rate": 4.5378947368421055e-06, "loss": 0.2736, "step": 5700 }, { "epoch": 0.47, "learning_rate": 4.511578947368421e-06, "loss": 0.2359, "step": 5725 }, { "epoch": 0.47, "learning_rate": 4.485263157894737e-06, "loss": 0.2341, "step": 5750 }, { "epoch": 0.48, "learning_rate": 4.458947368421053e-06, "loss": 0.2836, "step": 5775 }, { "epoch": 0.48, "learning_rate": 4.432631578947369e-06, "loss": 0.2534, "step": 5800 }, { "epoch": 0.48, "learning_rate": 4.406315789473685e-06, "loss": 0.2506, "step": 5825 }, { "epoch": 0.48, "learning_rate": 4.38e-06, "loss": 0.2631, "step": 5850 }, { "epoch": 0.48, "learning_rate": 4.353684210526316e-06, "loss": 0.2366, "step": 5875 }, { "epoch": 0.49, "learning_rate": 4.327368421052632e-06, "loss": 0.281, "step": 5900 }, { "epoch": 0.49, "learning_rate": 4.301052631578948e-06, "loss": 0.2684, "step": 5925 }, { "epoch": 0.49, "learning_rate": 4.274736842105264e-06, "loss": 0.2742, "step": 5950 }, { "epoch": 0.49, "learning_rate": 4.2484210526315795e-06, "loss": 0.2572, "step": 5975 }, { "epoch": 0.49, "learning_rate": 4.222105263157895e-06, "loss": 0.2459, "step": 6000 }, { "epoch": 0.5, "learning_rate": 4.195789473684211e-06, "loss": 0.2479, "step": 6025 }, { "epoch": 0.5, "learning_rate": 4.169473684210527e-06, "loss": 0.2423, "step": 6050 }, { "epoch": 0.5, "learning_rate": 4.143157894736842e-06, "loss": 0.2355, "step": 6075 }, { "epoch": 0.5, "learning_rate": 4.116842105263158e-06, "loss": 0.2498, "step": 6100 }, { "epoch": 0.5, "learning_rate": 4.090526315789474e-06, "loss": 0.2489, "step": 6125 }, { "epoch": 0.51, "learning_rate": 4.06421052631579e-06, "loss": 0.276, "step": 6150 }, { "epoch": 0.51, "learning_rate": 4.037894736842106e-06, "loss": 0.2767, "step": 6175 }, { "epoch": 0.51, "learning_rate": 4.011578947368421e-06, "loss": 0.2621, "step": 6200 }, { "epoch": 0.51, "learning_rate": 3.985263157894737e-06, "loss": 0.2589, "step": 6225 }, { "epoch": 0.51, "learning_rate": 3.958947368421053e-06, "loss": 0.2693, "step": 6250 }, { "epoch": 0.52, "learning_rate": 3.9326315789473685e-06, "loss": 0.2586, "step": 6275 }, { "epoch": 0.52, "learning_rate": 3.906315789473685e-06, "loss": 0.2725, "step": 6300 }, { "epoch": 0.52, "learning_rate": 3.88e-06, "loss": 0.2553, "step": 6325 }, { "epoch": 0.52, "learning_rate": 3.853684210526316e-06, "loss": 0.2363, "step": 6350 }, { "epoch": 0.52, "learning_rate": 3.827368421052632e-06, "loss": 0.2375, "step": 6375 }, { "epoch": 0.53, "learning_rate": 3.8010526315789476e-06, "loss": 0.2571, "step": 6400 }, { "epoch": 0.53, "learning_rate": 3.7747368421052634e-06, "loss": 0.2463, "step": 6425 }, { "epoch": 0.53, "learning_rate": 3.7484210526315796e-06, "loss": 0.229, "step": 6450 }, { "epoch": 0.53, "learning_rate": 3.722105263157895e-06, "loss": 0.2521, "step": 6475 }, { "epoch": 0.53, "learning_rate": 3.695789473684211e-06, "loss": 0.229, "step": 6500 }, { "epoch": 0.54, "learning_rate": 3.6694736842105267e-06, "loss": 0.2194, "step": 6525 }, { "epoch": 0.54, "learning_rate": 3.6431578947368425e-06, "loss": 0.2768, "step": 6550 }, { "epoch": 0.54, "learning_rate": 3.616842105263158e-06, "loss": 0.2258, "step": 6575 }, { "epoch": 0.54, "learning_rate": 3.5905263157894737e-06, "loss": 0.2575, "step": 6600 }, { "epoch": 0.55, "learning_rate": 3.56421052631579e-06, "loss": 0.2257, "step": 6625 }, { "epoch": 0.55, "learning_rate": 3.5378947368421058e-06, "loss": 0.2649, "step": 6650 }, { "epoch": 0.55, "learning_rate": 3.5115789473684216e-06, "loss": 0.2361, "step": 6675 }, { "epoch": 0.55, "learning_rate": 3.485263157894737e-06, "loss": 0.2449, "step": 6700 }, { "epoch": 0.55, "learning_rate": 3.458947368421053e-06, "loss": 0.2551, "step": 6725 }, { "epoch": 0.56, "learning_rate": 3.4326315789473686e-06, "loss": 0.2364, "step": 6750 }, { "epoch": 0.56, "learning_rate": 3.4063157894736844e-06, "loss": 0.2254, "step": 6775 }, { "epoch": 0.56, "learning_rate": 3.3800000000000007e-06, "loss": 0.2196, "step": 6800 }, { "epoch": 0.56, "learning_rate": 3.353684210526316e-06, "loss": 0.2816, "step": 6825 }, { "epoch": 0.56, "learning_rate": 3.327368421052632e-06, "loss": 0.2372, "step": 6850 }, { "epoch": 0.57, "learning_rate": 3.3010526315789477e-06, "loss": 0.2487, "step": 6875 }, { "epoch": 0.57, "learning_rate": 3.2747368421052635e-06, "loss": 0.2218, "step": 6900 }, { "epoch": 0.57, "learning_rate": 3.248421052631579e-06, "loss": 0.2679, "step": 6925 }, { "epoch": 0.57, "learning_rate": 3.2221052631578947e-06, "loss": 0.2331, "step": 6950 }, { "epoch": 0.57, "learning_rate": 3.195789473684211e-06, "loss": 0.2385, "step": 6975 }, { "epoch": 0.58, "learning_rate": 3.169473684210527e-06, "loss": 0.2622, "step": 7000 }, { "epoch": 0.58, "learning_rate": 3.1431578947368426e-06, "loss": 0.2414, "step": 7025 }, { "epoch": 0.58, "learning_rate": 3.116842105263158e-06, "loss": 0.2612, "step": 7050 }, { "epoch": 0.58, "learning_rate": 3.090526315789474e-06, "loss": 0.2443, "step": 7075 }, { "epoch": 0.58, "learning_rate": 3.0642105263157896e-06, "loss": 0.231, "step": 7100 }, { "epoch": 0.59, "learning_rate": 3.037894736842106e-06, "loss": 0.2389, "step": 7125 }, { "epoch": 0.59, "learning_rate": 3.0115789473684213e-06, "loss": 0.2258, "step": 7150 }, { "epoch": 0.59, "learning_rate": 2.985263157894737e-06, "loss": 0.2532, "step": 7175 }, { "epoch": 0.59, "learning_rate": 2.958947368421053e-06, "loss": 0.2287, "step": 7200 }, { "epoch": 0.59, "learning_rate": 2.9326315789473687e-06, "loss": 0.2577, "step": 7225 }, { "epoch": 0.6, "learning_rate": 2.906315789473684e-06, "loss": 0.2548, "step": 7250 }, { "epoch": 0.6, "learning_rate": 2.88e-06, "loss": 0.2532, "step": 7275 }, { "epoch": 0.6, "learning_rate": 2.853684210526316e-06, "loss": 0.2461, "step": 7300 }, { "epoch": 0.6, "learning_rate": 2.827368421052632e-06, "loss": 0.2503, "step": 7325 }, { "epoch": 0.6, "learning_rate": 2.801052631578948e-06, "loss": 0.2251, "step": 7350 }, { "epoch": 0.61, "learning_rate": 2.7747368421052632e-06, "loss": 0.2211, "step": 7375 }, { "epoch": 0.61, "learning_rate": 2.748421052631579e-06, "loss": 0.2443, "step": 7400 }, { "epoch": 0.61, "learning_rate": 2.722105263157895e-06, "loss": 0.2669, "step": 7425 }, { "epoch": 0.61, "learning_rate": 2.6978947368421053e-06, "loss": 0.2653, "step": 7450 }, { "epoch": 0.62, "learning_rate": 2.671578947368421e-06, "loss": 0.2541, "step": 7475 }, { "epoch": 0.62, "learning_rate": 2.645263157894737e-06, "loss": 0.2707, "step": 7500 }, { "epoch": 0.62, "learning_rate": 2.6189473684210524e-06, "loss": 0.2514, "step": 7525 }, { "epoch": 0.62, "learning_rate": 2.592631578947369e-06, "loss": 0.2291, "step": 7550 }, { "epoch": 0.62, "learning_rate": 2.5663157894736844e-06, "loss": 0.2773, "step": 7575 }, { "epoch": 0.63, "learning_rate": 2.5400000000000002e-06, "loss": 0.2454, "step": 7600 }, { "epoch": 0.63, "learning_rate": 2.513684210526316e-06, "loss": 0.2171, "step": 7625 }, { "epoch": 0.63, "learning_rate": 2.4873684210526315e-06, "loss": 0.2577, "step": 7650 }, { "epoch": 0.63, "learning_rate": 2.4610526315789477e-06, "loss": 0.2396, "step": 7675 }, { "epoch": 0.63, "learning_rate": 2.4347368421052635e-06, "loss": 0.2296, "step": 7700 }, { "epoch": 0.64, "learning_rate": 2.408421052631579e-06, "loss": 0.233, "step": 7725 }, { "epoch": 0.64, "learning_rate": 2.382105263157895e-06, "loss": 0.2491, "step": 7750 }, { "epoch": 0.64, "learning_rate": 2.3557894736842106e-06, "loss": 0.255, "step": 7775 }, { "epoch": 0.64, "learning_rate": 2.3294736842105264e-06, "loss": 0.2359, "step": 7800 }, { "epoch": 0.64, "learning_rate": 2.3031578947368426e-06, "loss": 0.2572, "step": 7825 }, { "epoch": 0.65, "learning_rate": 2.276842105263158e-06, "loss": 0.2054, "step": 7850 }, { "epoch": 0.65, "learning_rate": 2.250526315789474e-06, "loss": 0.2587, "step": 7875 }, { "epoch": 0.65, "learning_rate": 2.2242105263157896e-06, "loss": 0.2429, "step": 7900 }, { "epoch": 0.65, "learning_rate": 2.1978947368421055e-06, "loss": 0.2509, "step": 7925 }, { "epoch": 0.65, "learning_rate": 2.1715789473684213e-06, "loss": 0.2411, "step": 7950 }, { "epoch": 0.66, "learning_rate": 2.145263157894737e-06, "loss": 0.2483, "step": 7975 }, { "epoch": 0.66, "learning_rate": 2.118947368421053e-06, "loss": 0.2016, "step": 8000 }, { "epoch": 0.66, "learning_rate": 2.0926315789473687e-06, "loss": 0.2326, "step": 8025 }, { "epoch": 0.66, "learning_rate": 2.066315789473684e-06, "loss": 0.2546, "step": 8050 }, { "epoch": 0.66, "learning_rate": 2.04e-06, "loss": 0.2752, "step": 8075 }, { "epoch": 0.67, "learning_rate": 2.013684210526316e-06, "loss": 0.2537, "step": 8100 }, { "epoch": 0.67, "learning_rate": 1.9873684210526316e-06, "loss": 0.2765, "step": 8125 }, { "epoch": 0.67, "learning_rate": 1.9610526315789474e-06, "loss": 0.2335, "step": 8150 }, { "epoch": 0.67, "learning_rate": 1.9347368421052632e-06, "loss": 0.2534, "step": 8175 }, { "epoch": 0.67, "learning_rate": 1.908421052631579e-06, "loss": 0.2309, "step": 8200 }, { "epoch": 0.68, "learning_rate": 1.8821052631578949e-06, "loss": 0.2459, "step": 8225 }, { "epoch": 0.68, "learning_rate": 1.8557894736842109e-06, "loss": 0.2456, "step": 8250 }, { "epoch": 0.68, "learning_rate": 1.8294736842105265e-06, "loss": 0.2305, "step": 8275 }, { "epoch": 0.68, "learning_rate": 1.8031578947368423e-06, "loss": 0.2571, "step": 8300 }, { "epoch": 0.69, "learning_rate": 1.776842105263158e-06, "loss": 0.2656, "step": 8325 }, { "epoch": 0.69, "learning_rate": 1.750526315789474e-06, "loss": 0.2602, "step": 8350 }, { "epoch": 0.69, "learning_rate": 1.7242105263157896e-06, "loss": 0.2643, "step": 8375 }, { "epoch": 0.69, "learning_rate": 1.6978947368421054e-06, "loss": 0.2756, "step": 8400 }, { "epoch": 0.69, "learning_rate": 1.6715789473684212e-06, "loss": 0.2415, "step": 8425 }, { "epoch": 0.7, "learning_rate": 1.6473684210526317e-06, "loss": 0.2629, "step": 8450 }, { "epoch": 0.7, "learning_rate": 1.6210526315789473e-06, "loss": 0.2397, "step": 8475 }, { "epoch": 0.7, "learning_rate": 1.5947368421052633e-06, "loss": 0.2288, "step": 8500 }, { "epoch": 0.7, "learning_rate": 1.5684210526315791e-06, "loss": 0.255, "step": 8525 }, { "epoch": 0.7, "learning_rate": 1.5421052631578947e-06, "loss": 0.2228, "step": 8550 }, { "epoch": 0.71, "learning_rate": 1.5157894736842108e-06, "loss": 0.2332, "step": 8575 }, { "epoch": 0.71, "learning_rate": 1.4894736842105264e-06, "loss": 0.2099, "step": 8600 }, { "epoch": 0.71, "learning_rate": 1.4631578947368422e-06, "loss": 0.2404, "step": 8625 }, { "epoch": 0.71, "learning_rate": 1.4368421052631582e-06, "loss": 0.2636, "step": 8650 }, { "epoch": 0.71, "learning_rate": 1.4105263157894738e-06, "loss": 0.2462, "step": 8675 }, { "epoch": 0.72, "learning_rate": 1.3842105263157896e-06, "loss": 0.2426, "step": 8700 }, { "epoch": 0.72, "learning_rate": 1.3578947368421052e-06, "loss": 0.2494, "step": 8725 }, { "epoch": 0.72, "learning_rate": 1.3315789473684213e-06, "loss": 0.2604, "step": 8750 }, { "epoch": 0.72, "learning_rate": 1.3052631578947369e-06, "loss": 0.225, "step": 8775 }, { "epoch": 0.72, "learning_rate": 1.2789473684210527e-06, "loss": 0.2314, "step": 8800 }, { "epoch": 0.73, "learning_rate": 1.2526315789473687e-06, "loss": 0.2362, "step": 8825 }, { "epoch": 0.73, "learning_rate": 1.2263157894736843e-06, "loss": 0.2735, "step": 8850 }, { "epoch": 0.73, "learning_rate": 1.2000000000000002e-06, "loss": 0.2441, "step": 8875 }, { "epoch": 0.73, "learning_rate": 1.173684210526316e-06, "loss": 0.219, "step": 8900 }, { "epoch": 0.73, "learning_rate": 1.1473684210526316e-06, "loss": 0.242, "step": 8925 }, { "epoch": 0.74, "learning_rate": 1.1210526315789474e-06, "loss": 0.2393, "step": 8950 }, { "epoch": 0.74, "learning_rate": 1.0947368421052632e-06, "loss": 0.2291, "step": 8975 }, { "epoch": 0.74, "learning_rate": 1.068421052631579e-06, "loss": 0.2447, "step": 9000 }, { "epoch": 0.74, "learning_rate": 1.0421052631578949e-06, "loss": 0.2795, "step": 9025 }, { "epoch": 0.74, "learning_rate": 1.0157894736842105e-06, "loss": 0.2236, "step": 9050 }, { "epoch": 0.75, "learning_rate": 9.894736842105265e-07, "loss": 0.2581, "step": 9075 }, { "epoch": 0.75, "learning_rate": 9.631578947368423e-07, "loss": 0.2094, "step": 9100 }, { "epoch": 0.75, "learning_rate": 9.368421052631579e-07, "loss": 0.2606, "step": 9125 }, { "epoch": 0.75, "learning_rate": 9.105263157894737e-07, "loss": 0.2394, "step": 9150 }, { "epoch": 0.76, "learning_rate": 8.842105263157895e-07, "loss": 0.2355, "step": 9175 }, { "epoch": 0.76, "learning_rate": 8.578947368421054e-07, "loss": 0.2432, "step": 9200 }, { "epoch": 0.76, "learning_rate": 8.315789473684212e-07, "loss": 0.2433, "step": 9225 }, { "epoch": 0.76, "learning_rate": 8.052631578947369e-07, "loss": 0.2542, "step": 9250 }, { "epoch": 0.76, "learning_rate": 7.789473684210527e-07, "loss": 0.2276, "step": 9275 }, { "epoch": 0.77, "learning_rate": 7.526315789473684e-07, "loss": 0.2382, "step": 9300 }, { "epoch": 0.77, "learning_rate": 7.263157894736843e-07, "loss": 0.2553, "step": 9325 }, { "epoch": 0.77, "learning_rate": 7.000000000000001e-07, "loss": 0.2382, "step": 9350 }, { "epoch": 0.77, "learning_rate": 6.736842105263158e-07, "loss": 0.2811, "step": 9375 }, { "epoch": 0.77, "learning_rate": 6.473684210526317e-07, "loss": 0.2544, "step": 9400 }, { "epoch": 0.78, "learning_rate": 6.210526315789474e-07, "loss": 0.256, "step": 9425 }, { "epoch": 0.78, "learning_rate": 5.947368421052632e-07, "loss": 0.2512, "step": 9450 }, { "epoch": 0.78, "learning_rate": 5.705263157894737e-07, "loss": 0.2567, "step": 9475 }, { "epoch": 0.78, "learning_rate": 5.442105263157895e-07, "loss": 0.217, "step": 9500 }, { "epoch": 0.78, "learning_rate": 5.178947368421052e-07, "loss": 0.2337, "step": 9525 }, { "epoch": 0.79, "learning_rate": 4.915789473684211e-07, "loss": 0.2528, "step": 9550 }, { "epoch": 0.79, "learning_rate": 4.652631578947369e-07, "loss": 0.2273, "step": 9575 }, { "epoch": 0.79, "learning_rate": 4.389473684210527e-07, "loss": 0.2427, "step": 9600 }, { "epoch": 0.79, "learning_rate": 4.1263157894736846e-07, "loss": 0.2173, "step": 9625 }, { "epoch": 0.79, "learning_rate": 3.8631578947368423e-07, "loss": 0.2343, "step": 9650 }, { "epoch": 0.8, "learning_rate": 3.6e-07, "loss": 0.2471, "step": 9675 }, { "epoch": 0.8, "learning_rate": 3.3368421052631587e-07, "loss": 0.2498, "step": 9700 }, { "epoch": 0.8, "learning_rate": 3.073684210526316e-07, "loss": 0.26, "step": 9725 }, { "epoch": 0.8, "learning_rate": 2.810526315789474e-07, "loss": 0.2354, "step": 9750 }, { "epoch": 0.8, "learning_rate": 2.5473684210526316e-07, "loss": 0.2611, "step": 9775 }, { "epoch": 0.81, "learning_rate": 2.2842105263157898e-07, "loss": 0.2485, "step": 9800 }, { "epoch": 0.81, "learning_rate": 2.0210526315789475e-07, "loss": 0.2666, "step": 9825 }, { "epoch": 0.81, "learning_rate": 1.7578947368421054e-07, "loss": 0.2406, "step": 9850 }, { "epoch": 0.81, "learning_rate": 1.4947368421052633e-07, "loss": 0.2331, "step": 9875 }, { "epoch": 0.81, "learning_rate": 1.2315789473684212e-07, "loss": 0.2459, "step": 9900 }, { "epoch": 0.82, "learning_rate": 9.68421052631579e-08, "loss": 0.2303, "step": 9925 }, { "epoch": 0.82, "learning_rate": 7.05263157894737e-08, "loss": 0.2313, "step": 9950 }, { "epoch": 0.82, "learning_rate": 4.421052631578947e-08, "loss": 0.2474, "step": 9975 }, { "epoch": 0.82, "learning_rate": 1.7894736842105265e-08, "loss": 0.2436, "step": 10000 }, { "epoch": 0.82, "step": 10000, "total_flos": 2.8754981281385677e+19, "train_loss": 0.26775399169921876, "train_runtime": 9181.5505, "train_samples_per_second": 17.426, "train_steps_per_second": 1.089 } ], "logging_steps": 25, "max_steps": 10000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "total_flos": 2.8754981281385677e+19, "train_batch_size": 16, "trial_name": null, "trial_params": null }