{ "best_metric": 1.2412053346633911, "best_model_checkpoint": "./models/deberta-v3-large-all-v2/checkpoint-292273", "epoch": 1.0, "global_step": 292273, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 6.988120695377267e-06, "loss": 0.8116, "step": 500 }, { "epoch": 0.0, "learning_rate": 6.976145589910803e-06, "loss": 0.3656, "step": 1000 }, { "epoch": 0.01, "learning_rate": 6.964170484444338e-06, "loss": 0.3417, "step": 1500 }, { "epoch": 0.01, "learning_rate": 6.952195378977873e-06, "loss": 0.3577, "step": 2000 }, { "epoch": 0.01, "learning_rate": 6.940244223722342e-06, "loss": 0.3302, "step": 2500 }, { "epoch": 0.01, "learning_rate": 6.928269118255877e-06, "loss": 0.3478, "step": 3000 }, { "epoch": 0.01, "learning_rate": 6.916317963000345e-06, "loss": 0.3343, "step": 3500 }, { "epoch": 0.01, "learning_rate": 6.904342857533881e-06, "loss": 0.3814, "step": 4000 }, { "epoch": 0.02, "learning_rate": 6.892367752067416e-06, "loss": 0.2832, "step": 4500 }, { "epoch": 0.02, "learning_rate": 6.880392646600952e-06, "loss": 0.3181, "step": 5000 }, { "epoch": 0.02, "learning_rate": 6.86844149134542e-06, "loss": 0.2855, "step": 5500 }, { "epoch": 0.02, "learning_rate": 6.856466385878955e-06, "loss": 0.32, "step": 6000 }, { "epoch": 0.02, "learning_rate": 6.844491280412491e-06, "loss": 0.3108, "step": 6500 }, { "epoch": 0.02, "learning_rate": 6.832516174946026e-06, "loss": 0.3116, "step": 7000 }, { "epoch": 0.03, "learning_rate": 6.820541069479562e-06, "loss": 0.2832, "step": 7500 }, { "epoch": 0.03, "learning_rate": 6.808565964013098e-06, "loss": 0.333, "step": 8000 }, { "epoch": 0.03, "learning_rate": 6.796590858546633e-06, "loss": 0.3092, "step": 8500 }, { "epoch": 0.03, "learning_rate": 6.784615753080168e-06, "loss": 0.2621, "step": 9000 }, { "epoch": 0.03, "learning_rate": 6.772664597824636e-06, "loss": 0.3031, "step": 9500 }, { "epoch": 0.03, "learning_rate": 6.760689492358172e-06, "loss": 0.2695, "step": 10000 }, { "epoch": 0.04, "learning_rate": 6.748714386891708e-06, "loss": 0.2696, "step": 10500 }, { "epoch": 0.04, "learning_rate": 6.736739281425243e-06, "loss": 0.3249, "step": 11000 }, { "epoch": 0.04, "learning_rate": 6.724764175958778e-06, "loss": 0.3205, "step": 11500 }, { "epoch": 0.04, "learning_rate": 6.712789070492313e-06, "loss": 0.28, "step": 12000 }, { "epoch": 0.04, "learning_rate": 6.700861865447715e-06, "loss": 0.2783, "step": 12500 }, { "epoch": 0.04, "learning_rate": 6.688886759981251e-06, "loss": 0.3118, "step": 13000 }, { "epoch": 0.05, "learning_rate": 6.676911654514786e-06, "loss": 0.295, "step": 13500 }, { "epoch": 0.05, "learning_rate": 6.6649365490483205e-06, "loss": 0.2906, "step": 14000 }, { "epoch": 0.05, "learning_rate": 6.652961443581856e-06, "loss": 0.2481, "step": 14500 }, { "epoch": 0.05, "learning_rate": 6.640986338115392e-06, "loss": 0.3028, "step": 15000 }, { "epoch": 0.05, "learning_rate": 6.629011232648928e-06, "loss": 0.2575, "step": 15500 }, { "epoch": 0.05, "learning_rate": 6.617036127182463e-06, "loss": 0.2703, "step": 16000 }, { "epoch": 0.06, "learning_rate": 6.605084971926931e-06, "loss": 0.2849, "step": 16500 }, { "epoch": 0.06, "learning_rate": 6.593109866460466e-06, "loss": 0.3124, "step": 17000 }, { "epoch": 0.06, "learning_rate": 6.581134760994002e-06, "loss": 0.307, "step": 17500 }, { "epoch": 0.06, "learning_rate": 6.569159655527538e-06, "loss": 0.2734, "step": 18000 }, { "epoch": 0.06, "learning_rate": 6.557184550061073e-06, "loss": 0.2896, "step": 18500 }, { "epoch": 0.07, "learning_rate": 6.545233394805541e-06, "loss": 0.2735, "step": 19000 }, { "epoch": 0.07, "learning_rate": 6.533258289339076e-06, "loss": 0.31, "step": 19500 }, { "epoch": 0.07, "learning_rate": 6.521283183872612e-06, "loss": 0.2829, "step": 20000 }, { "epoch": 0.07, "learning_rate": 6.509308078406148e-06, "loss": 0.2994, "step": 20500 }, { "epoch": 0.07, "learning_rate": 6.497356923150616e-06, "loss": 0.3024, "step": 21000 }, { "epoch": 0.07, "learning_rate": 6.485381817684151e-06, "loss": 0.2991, "step": 21500 }, { "epoch": 0.08, "learning_rate": 6.473406712217687e-06, "loss": 0.295, "step": 22000 }, { "epoch": 0.08, "learning_rate": 6.461431606751222e-06, "loss": 0.2697, "step": 22500 }, { "epoch": 0.08, "learning_rate": 6.4494565012847576e-06, "loss": 0.297, "step": 23000 }, { "epoch": 0.08, "learning_rate": 6.437505346029226e-06, "loss": 0.2465, "step": 23500 }, { "epoch": 0.08, "learning_rate": 6.425530240562761e-06, "loss": 0.2666, "step": 24000 }, { "epoch": 0.08, "learning_rate": 6.413555135096297e-06, "loss": 0.2885, "step": 24500 }, { "epoch": 0.09, "learning_rate": 6.401580029629832e-06, "loss": 0.285, "step": 25000 }, { "epoch": 0.09, "learning_rate": 6.3896049241633675e-06, "loss": 0.2798, "step": 25500 }, { "epoch": 0.09, "learning_rate": 6.377629818696903e-06, "loss": 0.3039, "step": 26000 }, { "epoch": 0.09, "learning_rate": 6.365654713230439e-06, "loss": 0.2416, "step": 26500 }, { "epoch": 0.09, "learning_rate": 6.353679607763975e-06, "loss": 0.3344, "step": 27000 }, { "epoch": 0.09, "learning_rate": 6.341728452508442e-06, "loss": 0.257, "step": 27500 }, { "epoch": 0.1, "learning_rate": 6.3297533470419775e-06, "loss": 0.2741, "step": 28000 }, { "epoch": 0.1, "learning_rate": 6.317778241575513e-06, "loss": 0.2977, "step": 28500 }, { "epoch": 0.1, "learning_rate": 6.305827086319982e-06, "loss": 0.3057, "step": 29000 }, { "epoch": 0.1, "learning_rate": 6.293851980853517e-06, "loss": 0.2691, "step": 29500 }, { "epoch": 0.1, "learning_rate": 6.2818768753870526e-06, "loss": 0.2541, "step": 30000 }, { "epoch": 0.1, "learning_rate": 6.2699017699205874e-06, "loss": 0.2876, "step": 30500 }, { "epoch": 0.11, "learning_rate": 6.257926664454123e-06, "loss": 0.2978, "step": 31000 }, { "epoch": 0.11, "learning_rate": 6.245975509198592e-06, "loss": 0.2845, "step": 31500 }, { "epoch": 0.11, "learning_rate": 6.234000403732127e-06, "loss": 0.2955, "step": 32000 }, { "epoch": 0.11, "learning_rate": 6.222049248476596e-06, "loss": 0.2824, "step": 32500 }, { "epoch": 0.11, "learning_rate": 6.210074143010131e-06, "loss": 0.234, "step": 33000 }, { "epoch": 0.11, "learning_rate": 6.198099037543666e-06, "loss": 0.2723, "step": 33500 }, { "epoch": 0.12, "learning_rate": 6.186123932077202e-06, "loss": 0.3273, "step": 34000 }, { "epoch": 0.12, "learning_rate": 6.174148826610737e-06, "loss": 0.2879, "step": 34500 }, { "epoch": 0.12, "learning_rate": 6.1621737211442725e-06, "loss": 0.2364, "step": 35000 }, { "epoch": 0.12, "learning_rate": 6.150198615677808e-06, "loss": 0.2609, "step": 35500 }, { "epoch": 0.12, "learning_rate": 6.138223510211343e-06, "loss": 0.2811, "step": 36000 }, { "epoch": 0.12, "learning_rate": 6.126272354955812e-06, "loss": 0.2921, "step": 36500 }, { "epoch": 0.13, "learning_rate": 6.11432119970028e-06, "loss": 0.3001, "step": 37000 }, { "epoch": 0.13, "learning_rate": 6.1023460942338155e-06, "loss": 0.2618, "step": 37500 }, { "epoch": 0.13, "learning_rate": 6.090370988767351e-06, "loss": 0.2811, "step": 38000 }, { "epoch": 0.13, "learning_rate": 6.078395883300887e-06, "loss": 0.2683, "step": 38500 }, { "epoch": 0.13, "learning_rate": 6.066420777834422e-06, "loss": 0.2466, "step": 39000 }, { "epoch": 0.14, "learning_rate": 6.0544456723679575e-06, "loss": 0.2514, "step": 39500 }, { "epoch": 0.14, "learning_rate": 6.042470566901492e-06, "loss": 0.2994, "step": 40000 }, { "epoch": 0.14, "learning_rate": 6.030495461435028e-06, "loss": 0.2532, "step": 40500 }, { "epoch": 0.14, "learning_rate": 6.018520355968563e-06, "loss": 0.2966, "step": 41000 }, { "epoch": 0.14, "learning_rate": 6.006569200713032e-06, "loss": 0.26, "step": 41500 }, { "epoch": 0.14, "learning_rate": 5.9945940952465675e-06, "loss": 0.2524, "step": 42000 }, { "epoch": 0.15, "learning_rate": 5.982618989780102e-06, "loss": 0.3518, "step": 42500 }, { "epoch": 0.15, "learning_rate": 5.970667834524571e-06, "loss": 0.4247, "step": 43000 }, { "epoch": 0.15, "learning_rate": 5.95871667926904e-06, "loss": 0.4605, "step": 43500 }, { "epoch": 0.15, "learning_rate": 5.946765524013508e-06, "loss": 0.4111, "step": 44000 }, { "epoch": 0.15, "learning_rate": 5.934790418547044e-06, "loss": 0.3416, "step": 44500 }, { "epoch": 0.15, "learning_rate": 5.9228153130805785e-06, "loss": 0.2562, "step": 45000 }, { "epoch": 0.16, "learning_rate": 5.910840207614114e-06, "loss": 0.2773, "step": 45500 }, { "epoch": 0.16, "learning_rate": 5.89886510214765e-06, "loss": 0.2311, "step": 46000 }, { "epoch": 0.16, "learning_rate": 5.886889996681185e-06, "loss": 0.3196, "step": 46500 }, { "epoch": 0.16, "learning_rate": 5.87491489121472e-06, "loss": 0.2729, "step": 47000 }, { "epoch": 0.16, "learning_rate": 5.862939785748255e-06, "loss": 0.3177, "step": 47500 }, { "epoch": 0.16, "learning_rate": 5.850964680281791e-06, "loss": 0.2905, "step": 48000 }, { "epoch": 0.17, "learning_rate": 5.838989574815327e-06, "loss": 0.322, "step": 48500 }, { "epoch": 0.17, "learning_rate": 5.8270144693488625e-06, "loss": 0.2838, "step": 49000 }, { "epoch": 0.17, "learning_rate": 5.815039363882397e-06, "loss": 0.2668, "step": 49500 }, { "epoch": 0.17, "learning_rate": 5.803064258415933e-06, "loss": 0.2295, "step": 50000 }, { "epoch": 0.17, "learning_rate": 5.791137053371334e-06, "loss": 0.2489, "step": 50500 }, { "epoch": 0.17, "learning_rate": 5.77916194790487e-06, "loss": 0.2887, "step": 51000 }, { "epoch": 0.18, "learning_rate": 5.7671868424384056e-06, "loss": 0.2643, "step": 51500 }, { "epoch": 0.18, "learning_rate": 5.7552117369719404e-06, "loss": 0.2563, "step": 52000 }, { "epoch": 0.18, "learning_rate": 5.743236631505475e-06, "loss": 0.2604, "step": 52500 }, { "epoch": 0.18, "learning_rate": 5.731285476249944e-06, "loss": 0.2382, "step": 53000 }, { "epoch": 0.18, "learning_rate": 5.71931037078348e-06, "loss": 0.3063, "step": 53500 }, { "epoch": 0.18, "learning_rate": 5.7073352653170155e-06, "loss": 0.285, "step": 54000 }, { "epoch": 0.19, "learning_rate": 5.69536015985055e-06, "loss": 0.3499, "step": 54500 }, { "epoch": 0.19, "learning_rate": 5.683385054384086e-06, "loss": 0.3539, "step": 55000 }, { "epoch": 0.19, "learning_rate": 5.671409948917621e-06, "loss": 0.2731, "step": 55500 }, { "epoch": 0.19, "learning_rate": 5.659434843451157e-06, "loss": 0.3028, "step": 56000 }, { "epoch": 0.19, "learning_rate": 5.6474836881956255e-06, "loss": 0.3549, "step": 56500 }, { "epoch": 0.2, "learning_rate": 5.635508582729161e-06, "loss": 0.333, "step": 57000 }, { "epoch": 0.2, "learning_rate": 5.623533477262696e-06, "loss": 0.2349, "step": 57500 }, { "epoch": 0.2, "learning_rate": 5.611558371796231e-06, "loss": 0.329, "step": 58000 }, { "epoch": 0.2, "learning_rate": 5.599583266329767e-06, "loss": 0.2739, "step": 58500 }, { "epoch": 0.2, "learning_rate": 5.5876321110742354e-06, "loss": 0.3069, "step": 59000 }, { "epoch": 0.2, "learning_rate": 5.575657005607771e-06, "loss": 0.2472, "step": 59500 }, { "epoch": 0.21, "learning_rate": 5.563681900141306e-06, "loss": 0.2929, "step": 60000 }, { "epoch": 0.21, "learning_rate": 5.551706794674841e-06, "loss": 0.2743, "step": 60500 }, { "epoch": 0.21, "learning_rate": 5.539731689208377e-06, "loss": 0.304, "step": 61000 }, { "epoch": 0.21, "learning_rate": 5.527756583741912e-06, "loss": 0.2828, "step": 61500 }, { "epoch": 0.21, "learning_rate": 5.515805428486381e-06, "loss": 0.2407, "step": 62000 }, { "epoch": 0.21, "learning_rate": 5.503830323019916e-06, "loss": 0.228, "step": 62500 }, { "epoch": 0.22, "learning_rate": 5.491855217553452e-06, "loss": 0.2213, "step": 63000 }, { "epoch": 0.22, "learning_rate": 5.479880112086987e-06, "loss": 0.2989, "step": 63500 }, { "epoch": 0.22, "learning_rate": 5.467905006620522e-06, "loss": 0.2999, "step": 64000 }, { "epoch": 0.22, "learning_rate": 5.455929901154058e-06, "loss": 0.2966, "step": 64500 }, { "epoch": 0.22, "learning_rate": 5.443954795687594e-06, "loss": 0.2806, "step": 65000 }, { "epoch": 0.22, "learning_rate": 5.4319796902211294e-06, "loss": 0.3088, "step": 65500 }, { "epoch": 0.23, "learning_rate": 5.420004584754664e-06, "loss": 0.3368, "step": 66000 }, { "epoch": 0.23, "learning_rate": 5.408029479288199e-06, "loss": 0.2686, "step": 66500 }, { "epoch": 0.23, "learning_rate": 5.396054373821735e-06, "loss": 0.2887, "step": 67000 }, { "epoch": 0.23, "learning_rate": 5.384079268355271e-06, "loss": 0.2259, "step": 67500 }, { "epoch": 0.23, "learning_rate": 5.3721041628888055e-06, "loss": 0.2527, "step": 68000 }, { "epoch": 0.23, "learning_rate": 5.360129057422341e-06, "loss": 0.2642, "step": 68500 }, { "epoch": 0.24, "learning_rate": 5.348153951955877e-06, "loss": 0.2365, "step": 69000 }, { "epoch": 0.24, "learning_rate": 5.336178846489413e-06, "loss": 0.2573, "step": 69500 }, { "epoch": 0.24, "learning_rate": 5.324227691233881e-06, "loss": 0.2804, "step": 70000 }, { "epoch": 0.24, "learning_rate": 5.312252585767416e-06, "loss": 0.2953, "step": 70500 }, { "epoch": 0.24, "learning_rate": 5.300277480300951e-06, "loss": 0.2623, "step": 71000 }, { "epoch": 0.24, "learning_rate": 5.288302374834487e-06, "loss": 0.2324, "step": 71500 }, { "epoch": 0.25, "learning_rate": 5.276327269368023e-06, "loss": 0.305, "step": 72000 }, { "epoch": 0.25, "learning_rate": 5.264352163901558e-06, "loss": 0.277, "step": 72500 }, { "epoch": 0.25, "learning_rate": 5.252401008646026e-06, "loss": 0.2758, "step": 73000 }, { "epoch": 0.25, "learning_rate": 5.240425903179561e-06, "loss": 0.2505, "step": 73500 }, { "epoch": 0.25, "learning_rate": 5.228450797713097e-06, "loss": 0.2518, "step": 74000 }, { "epoch": 0.25, "learning_rate": 5.2164756922466326e-06, "loss": 0.2642, "step": 74500 }, { "epoch": 0.26, "learning_rate": 5.204500586780168e-06, "loss": 0.33, "step": 75000 }, { "epoch": 0.26, "learning_rate": 5.192525481313703e-06, "loss": 0.2136, "step": 75500 }, { "epoch": 0.26, "learning_rate": 5.180550375847238e-06, "loss": 0.2679, "step": 76000 }, { "epoch": 0.26, "learning_rate": 5.168575270380774e-06, "loss": 0.2467, "step": 76500 }, { "epoch": 0.26, "learning_rate": 5.1566241151252425e-06, "loss": 0.2634, "step": 77000 }, { "epoch": 0.27, "learning_rate": 5.144649009658778e-06, "loss": 0.2534, "step": 77500 }, { "epoch": 0.27, "learning_rate": 5.132673904192314e-06, "loss": 0.2633, "step": 78000 }, { "epoch": 0.27, "learning_rate": 5.120698798725848e-06, "loss": 0.2758, "step": 78500 }, { "epoch": 0.27, "learning_rate": 5.108723693259384e-06, "loss": 0.2389, "step": 79000 }, { "epoch": 0.27, "learning_rate": 5.0967725380038525e-06, "loss": 0.2774, "step": 79500 }, { "epoch": 0.27, "learning_rate": 5.084797432537388e-06, "loss": 0.2451, "step": 80000 }, { "epoch": 0.28, "learning_rate": 5.072822327070924e-06, "loss": 0.2227, "step": 80500 }, { "epoch": 0.28, "learning_rate": 5.060847221604459e-06, "loss": 0.2652, "step": 81000 }, { "epoch": 0.28, "learning_rate": 5.048872116137994e-06, "loss": 0.2727, "step": 81500 }, { "epoch": 0.28, "learning_rate": 5.036897010671529e-06, "loss": 0.257, "step": 82000 }, { "epoch": 0.28, "learning_rate": 5.024921905205065e-06, "loss": 0.209, "step": 82500 }, { "epoch": 0.28, "learning_rate": 5.012946799738601e-06, "loss": 0.2342, "step": 83000 }, { "epoch": 0.29, "learning_rate": 5.000971694272136e-06, "loss": 0.2429, "step": 83500 }, { "epoch": 0.29, "learning_rate": 4.989020539016604e-06, "loss": 0.2346, "step": 84000 }, { "epoch": 0.29, "learning_rate": 4.977045433550139e-06, "loss": 0.2521, "step": 84500 }, { "epoch": 0.29, "learning_rate": 4.965094278294608e-06, "loss": 0.2536, "step": 85000 }, { "epoch": 0.29, "learning_rate": 4.953119172828144e-06, "loss": 0.2448, "step": 85500 }, { "epoch": 0.29, "learning_rate": 4.9411440673616796e-06, "loss": 0.2265, "step": 86000 }, { "epoch": 0.3, "learning_rate": 4.929168961895214e-06, "loss": 0.2427, "step": 86500 }, { "epoch": 0.3, "learning_rate": 4.917193856428749e-06, "loss": 0.2626, "step": 87000 }, { "epoch": 0.3, "learning_rate": 4.905218750962285e-06, "loss": 0.2531, "step": 87500 }, { "epoch": 0.3, "learning_rate": 4.893267595706754e-06, "loss": 0.2344, "step": 88000 }, { "epoch": 0.3, "learning_rate": 4.8812924902402895e-06, "loss": 0.2213, "step": 88500 }, { "epoch": 0.3, "learning_rate": 4.869317384773824e-06, "loss": 0.2384, "step": 89000 }, { "epoch": 0.31, "learning_rate": 4.857342279307359e-06, "loss": 0.2676, "step": 89500 }, { "epoch": 0.31, "learning_rate": 4.845367173840895e-06, "loss": 0.271, "step": 90000 }, { "epoch": 0.31, "learning_rate": 4.833416018585364e-06, "loss": 0.2691, "step": 90500 }, { "epoch": 0.31, "learning_rate": 4.8214409131188995e-06, "loss": 0.2609, "step": 91000 }, { "epoch": 0.31, "learning_rate": 4.809465807652434e-06, "loss": 0.2414, "step": 91500 }, { "epoch": 0.31, "learning_rate": 4.797490702185969e-06, "loss": 0.2542, "step": 92000 }, { "epoch": 0.32, "learning_rate": 4.785539546930438e-06, "loss": 0.2575, "step": 92500 }, { "epoch": 0.32, "learning_rate": 4.773564441463974e-06, "loss": 0.2182, "step": 93000 }, { "epoch": 0.32, "learning_rate": 4.7615893359975094e-06, "loss": 0.2975, "step": 93500 }, { "epoch": 0.32, "learning_rate": 4.749614230531045e-06, "loss": 0.2542, "step": 94000 }, { "epoch": 0.32, "learning_rate": 4.73763912506458e-06, "loss": 0.2297, "step": 94500 }, { "epoch": 0.33, "learning_rate": 4.725664019598115e-06, "loss": 0.2704, "step": 95000 }, { "epoch": 0.33, "learning_rate": 4.713712864342584e-06, "loss": 0.2101, "step": 95500 }, { "epoch": 0.33, "learning_rate": 4.701737758876119e-06, "loss": 0.2597, "step": 96000 }, { "epoch": 0.33, "learning_rate": 4.689762653409655e-06, "loss": 0.2194, "step": 96500 }, { "epoch": 0.33, "learning_rate": 4.67778754794319e-06, "loss": 0.2235, "step": 97000 }, { "epoch": 0.33, "learning_rate": 4.665860342898592e-06, "loss": 0.2419, "step": 97500 }, { "epoch": 0.34, "learning_rate": 4.653885237432127e-06, "loss": 0.2434, "step": 98000 }, { "epoch": 0.34, "learning_rate": 4.641910131965662e-06, "loss": 0.2861, "step": 98500 }, { "epoch": 0.34, "learning_rate": 4.629935026499197e-06, "loss": 0.2311, "step": 99000 }, { "epoch": 0.34, "learning_rate": 4.617959921032733e-06, "loss": 0.2198, "step": 99500 }, { "epoch": 0.34, "learning_rate": 4.605984815566269e-06, "loss": 0.243, "step": 100000 }, { "epoch": 0.34, "learning_rate": 4.5940336603107375e-06, "loss": 0.2348, "step": 100500 }, { "epoch": 0.35, "learning_rate": 4.582058554844272e-06, "loss": 0.25, "step": 101000 }, { "epoch": 0.35, "learning_rate": 4.570083449377807e-06, "loss": 0.2267, "step": 101500 }, { "epoch": 0.35, "learning_rate": 4.558108343911343e-06, "loss": 0.2492, "step": 102000 }, { "epoch": 0.35, "learning_rate": 4.546133238444879e-06, "loss": 0.2534, "step": 102500 }, { "epoch": 0.35, "learning_rate": 4.5341581329784136e-06, "loss": 0.2082, "step": 103000 }, { "epoch": 0.35, "learning_rate": 4.522206977722882e-06, "loss": 0.263, "step": 103500 }, { "epoch": 0.36, "learning_rate": 4.510231872256417e-06, "loss": 0.2707, "step": 104000 }, { "epoch": 0.36, "learning_rate": 4.498256766789953e-06, "loss": 0.2593, "step": 104500 }, { "epoch": 0.36, "learning_rate": 4.486281661323489e-06, "loss": 0.2735, "step": 105000 }, { "epoch": 0.36, "learning_rate": 4.474306555857024e-06, "loss": 0.2743, "step": 105500 }, { "epoch": 0.36, "learning_rate": 4.462331450390559e-06, "loss": 0.2314, "step": 106000 }, { "epoch": 0.36, "learning_rate": 4.450356344924095e-06, "loss": 0.2241, "step": 106500 }, { "epoch": 0.37, "learning_rate": 4.438381239457631e-06, "loss": 0.2471, "step": 107000 }, { "epoch": 0.37, "learning_rate": 4.426430084202099e-06, "loss": 0.2347, "step": 107500 }, { "epoch": 0.37, "learning_rate": 4.414454978735634e-06, "loss": 0.2391, "step": 108000 }, { "epoch": 0.37, "learning_rate": 4.402479873269169e-06, "loss": 0.2819, "step": 108500 }, { "epoch": 0.37, "learning_rate": 4.390504767802705e-06, "loss": 0.2278, "step": 109000 }, { "epoch": 0.37, "learning_rate": 4.378529662336241e-06, "loss": 0.2467, "step": 109500 }, { "epoch": 0.38, "learning_rate": 4.366554556869776e-06, "loss": 0.2494, "step": 110000 }, { "epoch": 0.38, "learning_rate": 4.354579451403311e-06, "loss": 0.2059, "step": 110500 }, { "epoch": 0.38, "learning_rate": 4.342604345936846e-06, "loss": 0.2388, "step": 111000 }, { "epoch": 0.38, "learning_rate": 4.330653190681315e-06, "loss": 0.2286, "step": 111500 }, { "epoch": 0.38, "learning_rate": 4.318678085214851e-06, "loss": 0.2519, "step": 112000 }, { "epoch": 0.38, "learning_rate": 4.3067269299593185e-06, "loss": 0.2444, "step": 112500 }, { "epoch": 0.39, "learning_rate": 4.294751824492854e-06, "loss": 0.2278, "step": 113000 }, { "epoch": 0.39, "learning_rate": 4.28277671902639e-06, "loss": 0.2176, "step": 113500 }, { "epoch": 0.39, "learning_rate": 4.270801613559925e-06, "loss": 0.2382, "step": 114000 }, { "epoch": 0.39, "learning_rate": 4.258850458304393e-06, "loss": 0.2402, "step": 114500 }, { "epoch": 0.39, "learning_rate": 4.2468753528379285e-06, "loss": 0.2632, "step": 115000 }, { "epoch": 0.4, "learning_rate": 4.234924197582397e-06, "loss": 0.2324, "step": 115500 }, { "epoch": 0.4, "learning_rate": 4.222949092115933e-06, "loss": 0.2159, "step": 116000 }, { "epoch": 0.4, "learning_rate": 4.210973986649469e-06, "loss": 0.2862, "step": 116500 }, { "epoch": 0.4, "learning_rate": 4.198998881183003e-06, "loss": 0.2385, "step": 117000 }, { "epoch": 0.4, "learning_rate": 4.1870477259274715e-06, "loss": 0.2146, "step": 117500 }, { "epoch": 0.4, "learning_rate": 4.175072620461007e-06, "loss": 0.2749, "step": 118000 }, { "epoch": 0.41, "learning_rate": 4.163097514994543e-06, "loss": 0.2164, "step": 118500 }, { "epoch": 0.41, "learning_rate": 4.151122409528079e-06, "loss": 0.2521, "step": 119000 }, { "epoch": 0.41, "learning_rate": 4.1391473040616136e-06, "loss": 0.1924, "step": 119500 }, { "epoch": 0.41, "learning_rate": 4.1271721985951484e-06, "loss": 0.2564, "step": 120000 }, { "epoch": 0.41, "learning_rate": 4.115197093128684e-06, "loss": 0.1907, "step": 120500 }, { "epoch": 0.41, "learning_rate": 4.103245937873153e-06, "loss": 0.2629, "step": 121000 }, { "epoch": 0.42, "learning_rate": 4.091270832406689e-06, "loss": 0.1845, "step": 121500 }, { "epoch": 0.42, "learning_rate": 4.079295726940224e-06, "loss": 0.1999, "step": 122000 }, { "epoch": 0.42, "learning_rate": 4.067320621473758e-06, "loss": 0.2527, "step": 122500 }, { "epoch": 0.42, "learning_rate": 4.055345516007294e-06, "loss": 0.2153, "step": 123000 }, { "epoch": 0.42, "learning_rate": 4.04337041054083e-06, "loss": 0.2089, "step": 123500 }, { "epoch": 0.42, "learning_rate": 4.0313953050743655e-06, "loss": 0.2335, "step": 124000 }, { "epoch": 0.43, "learning_rate": 4.019420199607901e-06, "loss": 0.2252, "step": 124500 }, { "epoch": 0.43, "learning_rate": 4.007445094141436e-06, "loss": 0.2381, "step": 125000 }, { "epoch": 0.43, "learning_rate": 3.995469988674972e-06, "loss": 0.2327, "step": 125500 }, { "epoch": 0.43, "learning_rate": 3.983494883208507e-06, "loss": 0.247, "step": 126000 }, { "epoch": 0.43, "learning_rate": 3.9715197777420424e-06, "loss": 0.2659, "step": 126500 }, { "epoch": 0.43, "learning_rate": 3.959544672275577e-06, "loss": 0.2212, "step": 127000 }, { "epoch": 0.44, "learning_rate": 3.947569566809113e-06, "loss": 0.2265, "step": 127500 }, { "epoch": 0.44, "learning_rate": 3.935618411553582e-06, "loss": 0.2389, "step": 128000 }, { "epoch": 0.44, "learning_rate": 3.9236433060871175e-06, "loss": 0.2342, "step": 128500 }, { "epoch": 0.44, "learning_rate": 3.911668200620652e-06, "loss": 0.2181, "step": 129000 }, { "epoch": 0.44, "learning_rate": 3.899693095154188e-06, "loss": 0.2378, "step": 129500 }, { "epoch": 0.44, "learning_rate": 3.887717989687723e-06, "loss": 0.2397, "step": 130000 }, { "epoch": 0.45, "learning_rate": 3.875742884221259e-06, "loss": 0.2606, "step": 130500 }, { "epoch": 0.45, "learning_rate": 3.863767778754794e-06, "loss": 0.2198, "step": 131000 }, { "epoch": 0.45, "learning_rate": 3.851816623499262e-06, "loss": 0.2213, "step": 131500 }, { "epoch": 0.45, "learning_rate": 3.839841518032798e-06, "loss": 0.2663, "step": 132000 }, { "epoch": 0.45, "learning_rate": 3.827866412566333e-06, "loss": 0.2195, "step": 132500 }, { "epoch": 0.46, "learning_rate": 3.815891307099869e-06, "loss": 0.1806, "step": 133000 }, { "epoch": 0.46, "learning_rate": 3.803940151844337e-06, "loss": 0.2167, "step": 133500 }, { "epoch": 0.46, "learning_rate": 3.7919650463778727e-06, "loss": 0.2563, "step": 134000 }, { "epoch": 0.46, "learning_rate": 3.7799899409114085e-06, "loss": 0.2136, "step": 134500 }, { "epoch": 0.46, "learning_rate": 3.7680148354449438e-06, "loss": 0.2307, "step": 135000 }, { "epoch": 0.46, "learning_rate": 3.7560397299784786e-06, "loss": 0.2135, "step": 135500 }, { "epoch": 0.47, "learning_rate": 3.744088574722947e-06, "loss": 0.253, "step": 136000 }, { "epoch": 0.47, "learning_rate": 3.7321134692564827e-06, "loss": 0.2402, "step": 136500 }, { "epoch": 0.47, "learning_rate": 3.7201383637900184e-06, "loss": 0.2199, "step": 137000 }, { "epoch": 0.47, "learning_rate": 3.7081632583235537e-06, "loss": 0.2072, "step": 137500 }, { "epoch": 0.47, "learning_rate": 3.6961881528570886e-06, "loss": 0.2046, "step": 138000 }, { "epoch": 0.47, "learning_rate": 3.684236997601557e-06, "loss": 0.1959, "step": 138500 }, { "epoch": 0.48, "learning_rate": 3.6722618921350927e-06, "loss": 0.2218, "step": 139000 }, { "epoch": 0.48, "learning_rate": 3.6602867866686284e-06, "loss": 0.2931, "step": 139500 }, { "epoch": 0.48, "learning_rate": 3.648311681202164e-06, "loss": 0.2156, "step": 140000 }, { "epoch": 0.48, "learning_rate": 3.6363605259466325e-06, "loss": 0.2149, "step": 140500 }, { "epoch": 0.48, "learning_rate": 3.6243854204801673e-06, "loss": 0.234, "step": 141000 }, { "epoch": 0.48, "learning_rate": 3.6124103150137026e-06, "loss": 0.2632, "step": 141500 }, { "epoch": 0.49, "learning_rate": 3.6004352095472383e-06, "loss": 0.2561, "step": 142000 }, { "epoch": 0.49, "learning_rate": 3.5884840542917067e-06, "loss": 0.2184, "step": 142500 }, { "epoch": 0.49, "learning_rate": 3.5765089488252424e-06, "loss": 0.2336, "step": 143000 }, { "epoch": 0.49, "learning_rate": 3.5645338433587773e-06, "loss": 0.2321, "step": 143500 }, { "epoch": 0.49, "learning_rate": 3.5525587378923126e-06, "loss": 0.2539, "step": 144000 }, { "epoch": 0.49, "learning_rate": 3.540607582636781e-06, "loss": 0.2314, "step": 144500 }, { "epoch": 0.5, "learning_rate": 3.5286324771703167e-06, "loss": 0.2352, "step": 145000 }, { "epoch": 0.5, "learning_rate": 3.5166573717038524e-06, "loss": 0.2136, "step": 145500 }, { "epoch": 0.5, "learning_rate": 3.504682266237388e-06, "loss": 0.2662, "step": 146000 }, { "epoch": 0.5, "learning_rate": 3.492731110981856e-06, "loss": 0.2461, "step": 146500 }, { "epoch": 0.5, "learning_rate": 3.4807560055153918e-06, "loss": 0.1742, "step": 147000 }, { "epoch": 0.5, "learning_rate": 3.4687809000489266e-06, "loss": 0.1936, "step": 147500 }, { "epoch": 0.51, "learning_rate": 3.4568057945824623e-06, "loss": 0.1879, "step": 148000 }, { "epoch": 0.51, "learning_rate": 3.4448306891159976e-06, "loss": 0.24, "step": 148500 }, { "epoch": 0.51, "learning_rate": 3.432855583649533e-06, "loss": 0.2371, "step": 149000 }, { "epoch": 0.51, "learning_rate": 3.4208804781830682e-06, "loss": 0.253, "step": 149500 }, { "epoch": 0.51, "learning_rate": 3.408905372716604e-06, "loss": 0.1954, "step": 150000 }, { "epoch": 0.51, "learning_rate": 3.3969302672501397e-06, "loss": 0.2494, "step": 150500 }, { "epoch": 0.52, "learning_rate": 3.3849791119946076e-06, "loss": 0.1934, "step": 151000 }, { "epoch": 0.52, "learning_rate": 3.3730040065281433e-06, "loss": 0.2544, "step": 151500 }, { "epoch": 0.52, "learning_rate": 3.3610289010616786e-06, "loss": 0.2255, "step": 152000 }, { "epoch": 0.52, "learning_rate": 3.349053795595214e-06, "loss": 0.2103, "step": 152500 }, { "epoch": 0.52, "learning_rate": 3.3370786901287496e-06, "loss": 0.2033, "step": 153000 }, { "epoch": 0.53, "learning_rate": 3.325103584662285e-06, "loss": 0.1838, "step": 153500 }, { "epoch": 0.53, "learning_rate": 3.31312847919582e-06, "loss": 0.3, "step": 154000 }, { "epoch": 0.53, "learning_rate": 3.301153373729356e-06, "loss": 0.2067, "step": 154500 }, { "epoch": 0.53, "learning_rate": 3.289202218473824e-06, "loss": 0.2176, "step": 155000 }, { "epoch": 0.53, "learning_rate": 3.2772510632182922e-06, "loss": 0.2316, "step": 155500 }, { "epoch": 0.53, "learning_rate": 3.265275957751828e-06, "loss": 0.235, "step": 156000 }, { "epoch": 0.54, "learning_rate": 3.2533008522853632e-06, "loss": 0.2208, "step": 156500 }, { "epoch": 0.54, "learning_rate": 3.2413257468188985e-06, "loss": 0.2194, "step": 157000 }, { "epoch": 0.54, "learning_rate": 3.2293745915633673e-06, "loss": 0.2314, "step": 157500 }, { "epoch": 0.54, "learning_rate": 3.217399486096902e-06, "loss": 0.2367, "step": 158000 }, { "epoch": 0.54, "learning_rate": 3.205424380630438e-06, "loss": 0.184, "step": 158500 }, { "epoch": 0.54, "learning_rate": 3.1934492751639736e-06, "loss": 0.2172, "step": 159000 }, { "epoch": 0.55, "learning_rate": 3.1814981199084416e-06, "loss": 0.2203, "step": 159500 }, { "epoch": 0.55, "learning_rate": 3.1695230144419773e-06, "loss": 0.2066, "step": 160000 }, { "epoch": 0.55, "learning_rate": 3.1575479089755126e-06, "loss": 0.226, "step": 160500 }, { "epoch": 0.55, "learning_rate": 3.145572803509048e-06, "loss": 0.1993, "step": 161000 }, { "epoch": 0.55, "learning_rate": 3.1335976980425836e-06, "loss": 0.2209, "step": 161500 }, { "epoch": 0.55, "learning_rate": 3.121622592576119e-06, "loss": 0.2078, "step": 162000 }, { "epoch": 0.56, "learning_rate": 3.109647487109654e-06, "loss": 0.2263, "step": 162500 }, { "epoch": 0.56, "learning_rate": 3.0976723816431895e-06, "loss": 0.2194, "step": 163000 }, { "epoch": 0.56, "learning_rate": 3.085697276176725e-06, "loss": 0.2015, "step": 163500 }, { "epoch": 0.56, "learning_rate": 3.0737461209211936e-06, "loss": 0.2078, "step": 164000 }, { "epoch": 0.56, "learning_rate": 3.061771015454729e-06, "loss": 0.2465, "step": 164500 }, { "epoch": 0.56, "learning_rate": 3.049795909988264e-06, "loss": 0.2301, "step": 165000 }, { "epoch": 0.57, "learning_rate": 3.0378208045218e-06, "loss": 0.2014, "step": 165500 }, { "epoch": 0.57, "learning_rate": 3.025845699055335e-06, "loss": 0.1913, "step": 166000 }, { "epoch": 0.57, "learning_rate": 3.013870593588871e-06, "loss": 0.2305, "step": 166500 }, { "epoch": 0.57, "learning_rate": 3.0018954881224057e-06, "loss": 0.2185, "step": 167000 }, { "epoch": 0.57, "learning_rate": 2.9899443328668745e-06, "loss": 0.222, "step": 167500 }, { "epoch": 0.57, "learning_rate": 2.97796922740041e-06, "loss": 0.2073, "step": 168000 }, { "epoch": 0.58, "learning_rate": 2.965994121933945e-06, "loss": 0.189, "step": 168500 }, { "epoch": 0.58, "learning_rate": 2.954019016467481e-06, "loss": 0.205, "step": 169000 }, { "epoch": 0.58, "learning_rate": 2.942043911001016e-06, "loss": 0.211, "step": 169500 }, { "epoch": 0.58, "learning_rate": 2.9300688055345514e-06, "loss": 0.2355, "step": 170000 }, { "epoch": 0.58, "learning_rate": 2.918093700068087e-06, "loss": 0.2351, "step": 170500 }, { "epoch": 0.59, "learning_rate": 2.9061185946016224e-06, "loss": 0.2413, "step": 171000 }, { "epoch": 0.59, "learning_rate": 2.894167439346091e-06, "loss": 0.2304, "step": 171500 }, { "epoch": 0.59, "learning_rate": 2.8821923338796265e-06, "loss": 0.2138, "step": 172000 }, { "epoch": 0.59, "learning_rate": 2.8702172284131614e-06, "loss": 0.2223, "step": 172500 }, { "epoch": 0.59, "learning_rate": 2.858242122946697e-06, "loss": 0.2214, "step": 173000 }, { "epoch": 0.59, "learning_rate": 2.8462909676911655e-06, "loss": 0.2426, "step": 173500 }, { "epoch": 0.6, "learning_rate": 2.8343158622247008e-06, "loss": 0.2301, "step": 174000 }, { "epoch": 0.6, "learning_rate": 2.8223407567582365e-06, "loss": 0.2265, "step": 174500 }, { "epoch": 0.6, "learning_rate": 2.8103656512917713e-06, "loss": 0.2501, "step": 175000 }, { "epoch": 0.6, "learning_rate": 2.798390545825307e-06, "loss": 0.2074, "step": 175500 }, { "epoch": 0.6, "learning_rate": 2.7864154403588428e-06, "loss": 0.2511, "step": 176000 }, { "epoch": 0.6, "learning_rate": 2.774440334892378e-06, "loss": 0.2096, "step": 176500 }, { "epoch": 0.61, "learning_rate": 2.7624652294259134e-06, "loss": 0.222, "step": 177000 }, { "epoch": 0.61, "learning_rate": 2.7505140741703817e-06, "loss": 0.1944, "step": 177500 }, { "epoch": 0.61, "learning_rate": 2.738538968703917e-06, "loss": 0.2324, "step": 178000 }, { "epoch": 0.61, "learning_rate": 2.7265638632374527e-06, "loss": 0.229, "step": 178500 }, { "epoch": 0.61, "learning_rate": 2.714612707981921e-06, "loss": 0.249, "step": 179000 }, { "epoch": 0.61, "learning_rate": 2.7026376025154564e-06, "loss": 0.189, "step": 179500 }, { "epoch": 0.62, "learning_rate": 2.690662497048992e-06, "loss": 0.2328, "step": 180000 }, { "epoch": 0.62, "learning_rate": 2.678687391582527e-06, "loss": 0.2474, "step": 180500 }, { "epoch": 0.62, "learning_rate": 2.6667122861160627e-06, "loss": 0.1939, "step": 181000 }, { "epoch": 0.62, "learning_rate": 2.654737180649598e-06, "loss": 0.19, "step": 181500 }, { "epoch": 0.62, "learning_rate": 2.6427620751831337e-06, "loss": 0.2433, "step": 182000 }, { "epoch": 0.62, "learning_rate": 2.630786969716669e-06, "loss": 0.2171, "step": 182500 }, { "epoch": 0.63, "learning_rate": 2.618835814461137e-06, "loss": 0.1911, "step": 183000 }, { "epoch": 0.63, "learning_rate": 2.6068607089946727e-06, "loss": 0.2519, "step": 183500 }, { "epoch": 0.63, "learning_rate": 2.594909553739141e-06, "loss": 0.2094, "step": 184000 }, { "epoch": 0.63, "learning_rate": 2.5829344482726767e-06, "loss": 0.1911, "step": 184500 }, { "epoch": 0.63, "learning_rate": 2.570959342806212e-06, "loss": 0.218, "step": 185000 }, { "epoch": 0.63, "learning_rate": 2.5589842373397473e-06, "loss": 0.2081, "step": 185500 }, { "epoch": 0.64, "learning_rate": 2.547033082084216e-06, "loss": 0.2282, "step": 186000 }, { "epoch": 0.64, "learning_rate": 2.535057976617751e-06, "loss": 0.1888, "step": 186500 }, { "epoch": 0.64, "learning_rate": 2.5230828711512867e-06, "loss": 0.1858, "step": 187000 }, { "epoch": 0.64, "learning_rate": 2.511107765684822e-06, "loss": 0.218, "step": 187500 }, { "epoch": 0.64, "learning_rate": 2.4991326602183577e-06, "loss": 0.2614, "step": 188000 }, { "epoch": 0.64, "learning_rate": 2.4871575547518926e-06, "loss": 0.2407, "step": 188500 }, { "epoch": 0.65, "learning_rate": 2.475206399496361e-06, "loss": 0.2338, "step": 189000 }, { "epoch": 0.65, "learning_rate": 2.4632312940298967e-06, "loss": 0.1825, "step": 189500 }, { "epoch": 0.65, "learning_rate": 2.451256188563432e-06, "loss": 0.2095, "step": 190000 }, { "epoch": 0.65, "learning_rate": 2.4392810830969677e-06, "loss": 0.2295, "step": 190500 }, { "epoch": 0.65, "learning_rate": 2.427305977630503e-06, "loss": 0.2118, "step": 191000 }, { "epoch": 0.66, "learning_rate": 2.4153308721640383e-06, "loss": 0.2096, "step": 191500 }, { "epoch": 0.66, "learning_rate": 2.403355766697574e-06, "loss": 0.1916, "step": 192000 }, { "epoch": 0.66, "learning_rate": 2.3913806612311093e-06, "loss": 0.2059, "step": 192500 }, { "epoch": 0.66, "learning_rate": 2.3794055557646446e-06, "loss": 0.1891, "step": 193000 }, { "epoch": 0.66, "learning_rate": 2.367454400509113e-06, "loss": 0.2334, "step": 193500 }, { "epoch": 0.66, "learning_rate": 2.3554792950426482e-06, "loss": 0.2112, "step": 194000 }, { "epoch": 0.67, "learning_rate": 2.343504189576184e-06, "loss": 0.2117, "step": 194500 }, { "epoch": 0.67, "learning_rate": 2.3315290841097192e-06, "loss": 0.2576, "step": 195000 }, { "epoch": 0.67, "learning_rate": 2.3195539786432545e-06, "loss": 0.2264, "step": 195500 }, { "epoch": 0.67, "learning_rate": 2.3076028233877233e-06, "loss": 0.2078, "step": 196000 }, { "epoch": 0.67, "learning_rate": 2.295627717921258e-06, "loss": 0.2008, "step": 196500 }, { "epoch": 0.67, "learning_rate": 2.283652612454794e-06, "loss": 0.2493, "step": 197000 }, { "epoch": 0.68, "learning_rate": 2.2716775069883296e-06, "loss": 0.1625, "step": 197500 }, { "epoch": 0.68, "learning_rate": 2.259702401521865e-06, "loss": 0.2086, "step": 198000 }, { "epoch": 0.68, "learning_rate": 2.2477272960554e-06, "loss": 0.2326, "step": 198500 }, { "epoch": 0.68, "learning_rate": 2.2357761407998686e-06, "loss": 0.1936, "step": 199000 }, { "epoch": 0.68, "learning_rate": 2.223824985544337e-06, "loss": 0.2182, "step": 199500 }, { "epoch": 0.68, "learning_rate": 2.2118498800778722e-06, "loss": 0.2449, "step": 200000 }, { "epoch": 0.69, "learning_rate": 2.199874774611408e-06, "loss": 0.1762, "step": 200500 }, { "epoch": 0.69, "learning_rate": 2.1878996691449432e-06, "loss": 0.2033, "step": 201000 }, { "epoch": 0.69, "learning_rate": 2.1759245636784785e-06, "loss": 0.2165, "step": 201500 }, { "epoch": 0.69, "learning_rate": 2.163949458212014e-06, "loss": 0.1966, "step": 202000 }, { "epoch": 0.69, "learning_rate": 2.1519743527455495e-06, "loss": 0.207, "step": 202500 }, { "epoch": 0.69, "learning_rate": 2.1399992472790853e-06, "loss": 0.2306, "step": 203000 }, { "epoch": 0.7, "learning_rate": 2.12802414181262e-06, "loss": 0.2208, "step": 203500 }, { "epoch": 0.7, "learning_rate": 2.116072986557089e-06, "loss": 0.2058, "step": 204000 }, { "epoch": 0.7, "learning_rate": 2.104097881090624e-06, "loss": 0.1907, "step": 204500 }, { "epoch": 0.7, "learning_rate": 2.092146725835092e-06, "loss": 0.2182, "step": 205000 }, { "epoch": 0.7, "learning_rate": 2.080171620368628e-06, "loss": 0.2206, "step": 205500 }, { "epoch": 0.7, "learning_rate": 2.0681965149021636e-06, "loss": 0.1957, "step": 206000 }, { "epoch": 0.71, "learning_rate": 2.056221409435699e-06, "loss": 0.1911, "step": 206500 }, { "epoch": 0.71, "learning_rate": 2.044246303969234e-06, "loss": 0.2188, "step": 207000 }, { "epoch": 0.71, "learning_rate": 2.0322711985027695e-06, "loss": 0.2, "step": 207500 }, { "epoch": 0.71, "learning_rate": 2.020296093036305e-06, "loss": 0.1907, "step": 208000 }, { "epoch": 0.71, "learning_rate": 2.0083209875698405e-06, "loss": 0.2258, "step": 208500 }, { "epoch": 0.72, "learning_rate": 1.996369832314309e-06, "loss": 0.2048, "step": 209000 }, { "epoch": 0.72, "learning_rate": 1.984418677058777e-06, "loss": 0.213, "step": 209500 }, { "epoch": 0.72, "learning_rate": 1.972443571592313e-06, "loss": 0.2089, "step": 210000 }, { "epoch": 0.72, "learning_rate": 1.9604924163367813e-06, "loss": 0.2252, "step": 210500 }, { "epoch": 0.72, "learning_rate": 1.948517310870316e-06, "loss": 0.188, "step": 211000 }, { "epoch": 0.72, "learning_rate": 1.936542205403852e-06, "loss": 0.1943, "step": 211500 }, { "epoch": 0.73, "learning_rate": 1.924567099937387e-06, "loss": 0.1994, "step": 212000 }, { "epoch": 0.73, "learning_rate": 1.912591994470923e-06, "loss": 0.1892, "step": 212500 }, { "epoch": 0.73, "learning_rate": 1.9006168890044584e-06, "loss": 0.2104, "step": 213000 }, { "epoch": 0.73, "learning_rate": 1.8886417835379935e-06, "loss": 0.189, "step": 213500 }, { "epoch": 0.73, "learning_rate": 1.8766666780715292e-06, "loss": 0.203, "step": 214000 }, { "epoch": 0.73, "learning_rate": 1.8646915726050643e-06, "loss": 0.1794, "step": 214500 }, { "epoch": 0.74, "learning_rate": 1.8527164671386e-06, "loss": 0.2119, "step": 215000 }, { "epoch": 0.74, "learning_rate": 1.840741361672135e-06, "loss": 0.183, "step": 215500 }, { "epoch": 0.74, "learning_rate": 1.8287662562056708e-06, "loss": 0.1655, "step": 216000 }, { "epoch": 0.74, "learning_rate": 1.8167911507392063e-06, "loss": 0.1866, "step": 216500 }, { "epoch": 0.74, "learning_rate": 1.8048399954836742e-06, "loss": 0.202, "step": 217000 }, { "epoch": 0.74, "learning_rate": 1.79286489001721e-06, "loss": 0.2151, "step": 217500 }, { "epoch": 0.75, "learning_rate": 1.7808897845507454e-06, "loss": 0.1977, "step": 218000 }, { "epoch": 0.75, "learning_rate": 1.7689386292952136e-06, "loss": 0.2263, "step": 218500 }, { "epoch": 0.75, "learning_rate": 1.756963523828749e-06, "loss": 0.1919, "step": 219000 }, { "epoch": 0.75, "learning_rate": 1.7449884183622846e-06, "loss": 0.1726, "step": 219500 }, { "epoch": 0.75, "learning_rate": 1.73301331289582e-06, "loss": 0.198, "step": 220000 }, { "epoch": 0.75, "learning_rate": 1.7210382074293554e-06, "loss": 0.2128, "step": 220500 }, { "epoch": 0.76, "learning_rate": 1.709063101962891e-06, "loss": 0.2186, "step": 221000 }, { "epoch": 0.76, "learning_rate": 1.6970879964964262e-06, "loss": 0.2037, "step": 221500 }, { "epoch": 0.76, "learning_rate": 1.6851128910299617e-06, "loss": 0.1783, "step": 222000 }, { "epoch": 0.76, "learning_rate": 1.67316173577443e-06, "loss": 0.1906, "step": 222500 }, { "epoch": 0.76, "learning_rate": 1.6611866303079656e-06, "loss": 0.23, "step": 223000 }, { "epoch": 0.76, "learning_rate": 1.6492115248415009e-06, "loss": 0.2613, "step": 223500 }, { "epoch": 0.77, "learning_rate": 1.6372364193750364e-06, "loss": 0.2053, "step": 224000 }, { "epoch": 0.77, "learning_rate": 1.6252613139085717e-06, "loss": 0.2254, "step": 224500 }, { "epoch": 0.77, "learning_rate": 1.6133341088639731e-06, "loss": 0.185, "step": 225000 }, { "epoch": 0.77, "learning_rate": 1.6013590033975086e-06, "loss": 0.205, "step": 225500 }, { "epoch": 0.77, "learning_rate": 1.589383897931044e-06, "loss": 0.1897, "step": 226000 }, { "epoch": 0.77, "learning_rate": 1.5774327426755123e-06, "loss": 0.1755, "step": 226500 }, { "epoch": 0.78, "learning_rate": 1.5654576372090478e-06, "loss": 0.2278, "step": 227000 }, { "epoch": 0.78, "learning_rate": 1.553482531742583e-06, "loss": 0.1753, "step": 227500 }, { "epoch": 0.78, "learning_rate": 1.5415074262761186e-06, "loss": 0.207, "step": 228000 }, { "epoch": 0.78, "learning_rate": 1.5295323208096539e-06, "loss": 0.1999, "step": 228500 }, { "epoch": 0.78, "learning_rate": 1.5175572153431894e-06, "loss": 0.2763, "step": 229000 }, { "epoch": 0.79, "learning_rate": 1.5055821098767247e-06, "loss": 0.2363, "step": 229500 }, { "epoch": 0.79, "learning_rate": 1.4936070044102604e-06, "loss": 0.2022, "step": 230000 }, { "epoch": 0.79, "learning_rate": 1.4816318989437957e-06, "loss": 0.2565, "step": 230500 }, { "epoch": 0.79, "learning_rate": 1.4696567934773312e-06, "loss": 0.2224, "step": 231000 }, { "epoch": 0.79, "learning_rate": 1.4576816880108665e-06, "loss": 0.2018, "step": 231500 }, { "epoch": 0.79, "learning_rate": 1.445706582544402e-06, "loss": 0.1966, "step": 232000 }, { "epoch": 0.8, "learning_rate": 1.4337554272888703e-06, "loss": 0.2034, "step": 232500 }, { "epoch": 0.8, "learning_rate": 1.4217803218224056e-06, "loss": 0.2089, "step": 233000 }, { "epoch": 0.8, "learning_rate": 1.4098052163559411e-06, "loss": 0.1942, "step": 233500 }, { "epoch": 0.8, "learning_rate": 1.3978301108894764e-06, "loss": 0.1786, "step": 234000 }, { "epoch": 0.8, "learning_rate": 1.385878955633945e-06, "loss": 0.2404, "step": 234500 }, { "epoch": 0.8, "learning_rate": 1.3739038501674803e-06, "loss": 0.1703, "step": 235000 }, { "epoch": 0.81, "learning_rate": 1.3619526949119487e-06, "loss": 0.2025, "step": 235500 }, { "epoch": 0.81, "learning_rate": 1.3499775894454842e-06, "loss": 0.2186, "step": 236000 }, { "epoch": 0.81, "learning_rate": 1.3380024839790195e-06, "loss": 0.2175, "step": 236500 }, { "epoch": 0.81, "learning_rate": 1.326027378512555e-06, "loss": 0.2511, "step": 237000 }, { "epoch": 0.81, "learning_rate": 1.3140522730460905e-06, "loss": 0.2199, "step": 237500 }, { "epoch": 0.81, "learning_rate": 1.302077167579626e-06, "loss": 0.2199, "step": 238000 }, { "epoch": 0.82, "learning_rate": 1.2901020621131613e-06, "loss": 0.2085, "step": 238500 }, { "epoch": 0.82, "learning_rate": 1.2781269566466968e-06, "loss": 0.2038, "step": 239000 }, { "epoch": 0.82, "learning_rate": 1.2661758013911651e-06, "loss": 0.2175, "step": 239500 }, { "epoch": 0.82, "learning_rate": 1.2542006959247004e-06, "loss": 0.229, "step": 240000 }, { "epoch": 0.82, "learning_rate": 1.242225590458236e-06, "loss": 0.1929, "step": 240500 }, { "epoch": 0.82, "learning_rate": 1.2302504849917712e-06, "loss": 0.1896, "step": 241000 }, { "epoch": 0.83, "learning_rate": 1.2182753795253067e-06, "loss": 0.2221, "step": 241500 }, { "epoch": 0.83, "learning_rate": 1.2063002740588423e-06, "loss": 0.1957, "step": 242000 }, { "epoch": 0.83, "learning_rate": 1.1943251685923778e-06, "loss": 0.2127, "step": 242500 }, { "epoch": 0.83, "learning_rate": 1.182350063125913e-06, "loss": 0.1977, "step": 243000 }, { "epoch": 0.83, "learning_rate": 1.1703749576594486e-06, "loss": 0.1765, "step": 243500 }, { "epoch": 0.83, "learning_rate": 1.158423802403917e-06, "loss": 0.2475, "step": 244000 }, { "epoch": 0.84, "learning_rate": 1.1464486969374522e-06, "loss": 0.2178, "step": 244500 }, { "epoch": 0.84, "learning_rate": 1.1344735914709877e-06, "loss": 0.2157, "step": 245000 }, { "epoch": 0.84, "learning_rate": 1.122498486004523e-06, "loss": 0.2147, "step": 245500 }, { "epoch": 0.84, "learning_rate": 1.1105712809599244e-06, "loss": 0.1948, "step": 246000 }, { "epoch": 0.84, "learning_rate": 1.09859617549346e-06, "loss": 0.1968, "step": 246500 }, { "epoch": 0.85, "learning_rate": 1.0866210700269952e-06, "loss": 0.1725, "step": 247000 }, { "epoch": 0.85, "learning_rate": 1.0746459645605308e-06, "loss": 0.1864, "step": 247500 }, { "epoch": 0.85, "learning_rate": 1.062670859094066e-06, "loss": 0.2123, "step": 248000 }, { "epoch": 0.85, "learning_rate": 1.0506957536276015e-06, "loss": 0.1684, "step": 248500 }, { "epoch": 0.85, "learning_rate": 1.0387206481611368e-06, "loss": 0.138, "step": 249000 }, { "epoch": 0.85, "learning_rate": 1.0267455426946726e-06, "loss": 0.2054, "step": 249500 }, { "epoch": 0.86, "learning_rate": 1.0147704372282079e-06, "loss": 0.2042, "step": 250000 }, { "epoch": 0.86, "learning_rate": 1.0028192819726762e-06, "loss": 0.2019, "step": 250500 }, { "epoch": 0.86, "learning_rate": 9.908441765062117e-07, "loss": 0.2051, "step": 251000 }, { "epoch": 0.86, "learning_rate": 9.788930212506799e-07, "loss": 0.2206, "step": 251500 }, { "epoch": 0.86, "learning_rate": 9.669179157842154e-07, "loss": 0.1939, "step": 252000 }, { "epoch": 0.86, "learning_rate": 9.549428103177509e-07, "loss": 0.1783, "step": 252500 }, { "epoch": 0.87, "learning_rate": 9.429677048512863e-07, "loss": 0.2094, "step": 253000 }, { "epoch": 0.87, "learning_rate": 9.310165495957548e-07, "loss": 0.2094, "step": 253500 }, { "epoch": 0.87, "learning_rate": 9.190414441292902e-07, "loss": 0.2089, "step": 254000 }, { "epoch": 0.87, "learning_rate": 9.070663386628256e-07, "loss": 0.2105, "step": 254500 }, { "epoch": 0.87, "learning_rate": 8.95091233196361e-07, "loss": 0.2205, "step": 255000 }, { "epoch": 0.87, "learning_rate": 8.831161277298964e-07, "loss": 0.2192, "step": 255500 }, { "epoch": 0.88, "learning_rate": 8.711410222634319e-07, "loss": 0.2001, "step": 256000 }, { "epoch": 0.88, "learning_rate": 8.591659167969673e-07, "loss": 0.18, "step": 256500 }, { "epoch": 0.88, "learning_rate": 8.472147615414355e-07, "loss": 0.1814, "step": 257000 }, { "epoch": 0.88, "learning_rate": 8.35239656074971e-07, "loss": 0.2044, "step": 257500 }, { "epoch": 0.88, "learning_rate": 8.232645506085064e-07, "loss": 0.1876, "step": 258000 }, { "epoch": 0.88, "learning_rate": 8.112894451420418e-07, "loss": 0.1998, "step": 258500 }, { "epoch": 0.89, "learning_rate": 7.993143396755773e-07, "loss": 0.1667, "step": 259000 }, { "epoch": 0.89, "learning_rate": 7.873392342091127e-07, "loss": 0.2043, "step": 259500 }, { "epoch": 0.89, "learning_rate": 7.753641287426481e-07, "loss": 0.1759, "step": 260000 }, { "epoch": 0.89, "learning_rate": 7.633890232761835e-07, "loss": 0.1607, "step": 260500 }, { "epoch": 0.89, "learning_rate": 7.514378680206519e-07, "loss": 0.2327, "step": 261000 }, { "epoch": 0.89, "learning_rate": 7.394627625541873e-07, "loss": 0.205, "step": 261500 }, { "epoch": 0.9, "learning_rate": 7.274876570877228e-07, "loss": 0.202, "step": 262000 }, { "epoch": 0.9, "learning_rate": 7.155365018321912e-07, "loss": 0.1992, "step": 262500 }, { "epoch": 0.9, "learning_rate": 7.035613963657266e-07, "loss": 0.2099, "step": 263000 }, { "epoch": 0.9, "learning_rate": 6.915862908992621e-07, "loss": 0.225, "step": 263500 }, { "epoch": 0.9, "learning_rate": 6.796111854327975e-07, "loss": 0.1722, "step": 264000 }, { "epoch": 0.9, "learning_rate": 6.676360799663329e-07, "loss": 0.2016, "step": 264500 }, { "epoch": 0.91, "learning_rate": 6.556609744998684e-07, "loss": 0.193, "step": 265000 }, { "epoch": 0.91, "learning_rate": 6.436858690334037e-07, "loss": 0.222, "step": 265500 }, { "epoch": 0.91, "learning_rate": 6.317107635669391e-07, "loss": 0.1912, "step": 266000 }, { "epoch": 0.91, "learning_rate": 6.197356581004745e-07, "loss": 0.2108, "step": 266500 }, { "epoch": 0.91, "learning_rate": 6.0776055263401e-07, "loss": 0.1917, "step": 267000 }, { "epoch": 0.92, "learning_rate": 5.958093973784783e-07, "loss": 0.1795, "step": 267500 }, { "epoch": 0.92, "learning_rate": 5.838342919120137e-07, "loss": 0.2032, "step": 268000 }, { "epoch": 0.92, "learning_rate": 5.718591864455492e-07, "loss": 0.1946, "step": 268500 }, { "epoch": 0.92, "learning_rate": 5.598840809790846e-07, "loss": 0.1944, "step": 269000 }, { "epoch": 0.92, "learning_rate": 5.47932925723553e-07, "loss": 0.2188, "step": 269500 }, { "epoch": 0.92, "learning_rate": 5.359578202570884e-07, "loss": 0.2265, "step": 270000 }, { "epoch": 0.93, "learning_rate": 5.239827147906238e-07, "loss": 0.2165, "step": 270500 }, { "epoch": 0.93, "learning_rate": 5.120076093241592e-07, "loss": 0.1648, "step": 271000 }, { "epoch": 0.93, "learning_rate": 5.000325038576947e-07, "loss": 0.2164, "step": 271500 }, { "epoch": 0.93, "learning_rate": 4.880813486021631e-07, "loss": 0.2216, "step": 272000 }, { "epoch": 0.93, "learning_rate": 4.761062431356985e-07, "loss": 0.1969, "step": 272500 }, { "epoch": 0.93, "learning_rate": 4.641550878801668e-07, "loss": 0.1804, "step": 273000 }, { "epoch": 0.94, "learning_rate": 4.521799824137022e-07, "loss": 0.1979, "step": 273500 }, { "epoch": 0.94, "learning_rate": 4.4020487694723773e-07, "loss": 0.2244, "step": 274000 }, { "epoch": 0.94, "learning_rate": 4.2822977148077313e-07, "loss": 0.218, "step": 274500 }, { "epoch": 0.94, "learning_rate": 4.1625466601430853e-07, "loss": 0.2156, "step": 275000 }, { "epoch": 0.94, "learning_rate": 4.04279560547844e-07, "loss": 0.1865, "step": 275500 }, { "epoch": 0.94, "learning_rate": 3.9230445508137943e-07, "loss": 0.1838, "step": 276000 }, { "epoch": 0.95, "learning_rate": 3.8032934961491483e-07, "loss": 0.164, "step": 276500 }, { "epoch": 0.95, "learning_rate": 3.6835424414845023e-07, "loss": 0.1726, "step": 277000 }, { "epoch": 0.95, "learning_rate": 3.564030888929186e-07, "loss": 0.1883, "step": 277500 }, { "epoch": 0.95, "learning_rate": 3.44427983426454e-07, "loss": 0.1768, "step": 278000 }, { "epoch": 0.95, "learning_rate": 3.3245287795998945e-07, "loss": 0.2227, "step": 278500 }, { "epoch": 0.95, "learning_rate": 3.204777724935249e-07, "loss": 0.1388, "step": 279000 }, { "epoch": 0.96, "learning_rate": 3.085266172379932e-07, "loss": 0.2058, "step": 279500 }, { "epoch": 0.96, "learning_rate": 2.9655151177152866e-07, "loss": 0.2163, "step": 280000 }, { "epoch": 0.96, "learning_rate": 2.845764063050641e-07, "loss": 0.1807, "step": 280500 }, { "epoch": 0.96, "learning_rate": 2.726013008385995e-07, "loss": 0.1744, "step": 281000 }, { "epoch": 0.96, "learning_rate": 2.6062619537213497e-07, "loss": 0.1752, "step": 281500 }, { "epoch": 0.96, "learning_rate": 2.486510899056704e-07, "loss": 0.1851, "step": 282000 }, { "epoch": 0.97, "learning_rate": 2.366759844392058e-07, "loss": 0.194, "step": 282500 }, { "epoch": 0.97, "learning_rate": 2.2470087897274124e-07, "loss": 0.1932, "step": 283000 }, { "epoch": 0.97, "learning_rate": 2.1272577350627667e-07, "loss": 0.2132, "step": 283500 }, { "epoch": 0.97, "learning_rate": 2.0077461825074503e-07, "loss": 0.2121, "step": 284000 }, { "epoch": 0.97, "learning_rate": 1.8879951278428046e-07, "loss": 0.1818, "step": 284500 }, { "epoch": 0.98, "learning_rate": 1.7682440731781588e-07, "loss": 0.1572, "step": 285000 }, { "epoch": 0.98, "learning_rate": 1.648493018513513e-07, "loss": 0.1862, "step": 285500 }, { "epoch": 0.98, "learning_rate": 1.529220968067526e-07, "loss": 0.1985, "step": 286000 }, { "epoch": 0.98, "learning_rate": 1.4094699134028801e-07, "loss": 0.2008, "step": 286500 }, { "epoch": 0.98, "learning_rate": 1.2897188587382344e-07, "loss": 0.2292, "step": 287000 }, { "epoch": 0.98, "learning_rate": 1.1699678040735886e-07, "loss": 0.2061, "step": 287500 }, { "epoch": 0.99, "learning_rate": 1.050216749408943e-07, "loss": 0.2021, "step": 288000 }, { "epoch": 0.99, "learning_rate": 9.304656947442973e-08, "loss": 0.1685, "step": 288500 }, { "epoch": 0.99, "learning_rate": 8.107146400796515e-08, "loss": 0.1779, "step": 289000 }, { "epoch": 0.99, "learning_rate": 6.912030875243351e-08, "loss": 0.1905, "step": 289500 }, { "epoch": 0.99, "learning_rate": 5.7145203285968946e-08, "loss": 0.1863, "step": 290000 }, { "epoch": 0.99, "learning_rate": 4.5170097819504365e-08, "loss": 0.1859, "step": 290500 }, { "epoch": 1.0, "learning_rate": 3.3194992353039797e-08, "loss": 0.1752, "step": 291000 }, { "epoch": 1.0, "learning_rate": 2.1219886886575222e-08, "loss": 0.1982, "step": 291500 }, { "epoch": 1.0, "learning_rate": 9.244781420110651e-09, "loss": 0.1291, "step": 292000 }, { "epoch": 1.0, "eval_loss": 1.2412053346633911, "eval_rmse": 1.1140938997268677, "eval_runtime": 11.2425, "eval_samples_per_second": 136.18, "eval_steps_per_second": 17.078, "step": 292273 } ], "max_steps": 292273, "num_train_epochs": 1, "total_flos": 1.9031292466854525e+17, "trial_name": null, "trial_params": null }