herbert-kgr10 / trainer_state.json
Łukasz Augustyniak
an initial model data
14b918d
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.2764453465140333,
"global_step": 381200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.2129437283437784e-05,
"loss": 1.2379,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 1.4256027417280164e-05,
"loss": 0.7257,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 1.546522956610944e-05,
"loss": 0.5796,
"step": 1500
},
{
"epoch": 0.01,
"learning_rate": 1.6333453908680466e-05,
"loss": 0.4975,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 1.6994513492146576e-05,
"loss": 0.4446,
"step": 2500
},
{
"epoch": 0.02,
"learning_rate": 1.7542591486498363e-05,
"loss": 0.4094,
"step": 3000
},
{
"epoch": 0.02,
"learning_rate": 1.799812583904253e-05,
"loss": 0.3847,
"step": 3500
},
{
"epoch": 0.02,
"learning_rate": 1.8398814018207687e-05,
"loss": 0.3704,
"step": 4000
},
{
"epoch": 0.03,
"learning_rate": 1.8746422335824573e-05,
"loss": 0.3564,
"step": 4500
},
{
"epoch": 0.03,
"learning_rate": 1.9062252153159553e-05,
"loss": 0.3467,
"step": 5000
},
{
"epoch": 0.03,
"learning_rate": 1.9343310044481473e-05,
"loss": 0.3388,
"step": 5500
},
{
"epoch": 0.04,
"learning_rate": 1.9603961801645213e-05,
"loss": 0.3315,
"step": 6000
},
{
"epoch": 0.04,
"learning_rate": 1.9839868300683366e-05,
"loss": 0.324,
"step": 6500
},
{
"epoch": 0.04,
"learning_rate": 2.0061762356282882e-05,
"loss": 0.32,
"step": 7000
},
{
"epoch": 0.04,
"learning_rate": 2.0265021385111326e-05,
"loss": 0.3137,
"step": 7500
},
{
"epoch": 0.05,
"learning_rate": 2.0458195441776583e-05,
"loss": 0.3098,
"step": 8000
},
{
"epoch": 0.05,
"learning_rate": 2.0636747154117713e-05,
"loss": 0.3046,
"step": 8500
},
{
"epoch": 0.05,
"learning_rate": 2.0807785578565834e-05,
"loss": 0.3027,
"step": 9000
},
{
"epoch": 0.06,
"learning_rate": 2.0966986891262083e-05,
"loss": 0.299,
"step": 9500
},
{
"epoch": 0.06,
"learning_rate": 2.1120442156381144e-05,
"loss": 0.2949,
"step": 10000
},
{
"epoch": 0.06,
"learning_rate": 2.126407788311574e-05,
"loss": 0.293,
"step": 10500
},
{
"epoch": 0.07,
"learning_rate": 2.1403228768808362e-05,
"loss": 0.2912,
"step": 11000
},
{
"epoch": 0.07,
"learning_rate": 2.153407205313307e-05,
"loss": 0.2882,
"step": 11500
},
{
"epoch": 0.07,
"learning_rate": 2.1661358320726367e-05,
"loss": 0.2863,
"step": 12000
},
{
"epoch": 0.07,
"learning_rate": 2.1781501739847258e-05,
"loss": 0.2854,
"step": 12500
},
{
"epoch": 0.08,
"learning_rate": 2.1896962056408874e-05,
"loss": 0.2832,
"step": 13000
},
{
"epoch": 0.08,
"learning_rate": 2.2008090702477508e-05,
"loss": 0.2792,
"step": 13500
},
{
"epoch": 0.08,
"learning_rate": 2.211689721953673e-05,
"loss": 0.2778,
"step": 14000
},
{
"epoch": 0.09,
"learning_rate": 2.2218573375603127e-05,
"loss": 0.2761,
"step": 14500
},
{
"epoch": 0.09,
"learning_rate": 2.2320043800379274e-05,
"loss": 0.2753,
"step": 15000
},
{
"epoch": 0.09,
"learning_rate": 2.2416621287798108e-05,
"loss": 0.2733,
"step": 15500
},
{
"epoch": 0.1,
"learning_rate": 2.2511634063520386e-05,
"loss": 0.2734,
"step": 16000
},
{
"epoch": 0.1,
"learning_rate": 2.2602254900427203e-05,
"loss": 0.2704,
"step": 16500
},
{
"epoch": 0.1,
"learning_rate": 2.2691582845312714e-05,
"loss": 0.2686,
"step": 17000
},
{
"epoch": 0.1,
"learning_rate": 2.2776939174648062e-05,
"loss": 0.2677,
"step": 17500
},
{
"epoch": 0.11,
"learning_rate": 2.2861224200309637e-05,
"loss": 0.2662,
"step": 18000
},
{
"epoch": 0.11,
"learning_rate": 2.2941894144885526e-05,
"loss": 0.2646,
"step": 18500
},
{
"epoch": 0.11,
"learning_rate": 2.3021675243341383e-05,
"loss": 0.2632,
"step": 19000
},
{
"epoch": 0.12,
"learning_rate": 2.3098146647661528e-05,
"loss": 0.2633,
"step": 19500
},
{
"epoch": 0.12,
"learning_rate": 2.3173880778124947e-05,
"loss": 0.2614,
"step": 20000
},
{
"epoch": 0.12,
"learning_rate": 2.3246569076131993e-05,
"loss": 0.2613,
"step": 20500
},
{
"epoch": 0.13,
"learning_rate": 2.3318647008867292e-05,
"loss": 0.26,
"step": 21000
},
{
"epoch": 0.13,
"learning_rate": 2.338790887946114e-05,
"loss": 0.2589,
"step": 21500
},
{
"epoch": 0.13,
"learning_rate": 2.3456667390552165e-05,
"loss": 0.2573,
"step": 22000
},
{
"epoch": 0.13,
"learning_rate": 2.352281133888646e-05,
"loss": 0.2566,
"step": 22500
},
{
"epoch": 0.14,
"learning_rate": 2.3588542720076777e-05,
"loss": 0.2564,
"step": 23000
},
{
"epoch": 0.14,
"learning_rate": 2.365183737938829e-05,
"loss": 0.2544,
"step": 23500
},
{
"epoch": 0.14,
"learning_rate": 2.371479694247017e-05,
"loss": 0.2541,
"step": 24000
},
{
"epoch": 0.15,
"learning_rate": 2.3775477661384013e-05,
"loss": 0.2529,
"step": 24500
},
{
"epoch": 0.15,
"learning_rate": 2.3835889724110435e-05,
"loss": 0.2528,
"step": 25000
},
{
"epoch": 0.15,
"learning_rate": 2.389416384748746e-05,
"loss": 0.2526,
"step": 25500
},
{
"epoch": 0.16,
"learning_rate": 2.3952226555385424e-05,
"loss": 0.2493,
"step": 26000
},
{
"epoch": 0.16,
"learning_rate": 2.40082776977891e-05,
"loss": 0.2495,
"step": 26500
},
{
"epoch": 0.16,
"learning_rate": 2.406416694337435e-05,
"loss": 0.2512,
"step": 27000
},
{
"epoch": 0.16,
"learning_rate": 2.4118158477291394e-05,
"loss": 0.2479,
"step": 27500
},
{
"epoch": 0.17,
"learning_rate": 2.4172031112122994e-05,
"loss": 0.2485,
"step": 28000
},
{
"epoch": 0.17,
"learning_rate": 2.4224109037950676e-05,
"loss": 0.2477,
"step": 28500
},
{
"epoch": 0.17,
"learning_rate": 2.427610552531118e-05,
"loss": 0.2468,
"step": 29000
},
{
"epoch": 0.18,
"learning_rate": 2.43264008500998e-05,
"loss": 0.2459,
"step": 29500
},
{
"epoch": 0.18,
"learning_rate": 2.43766474712664e-05,
"loss": 0.2447,
"step": 30000
},
{
"epoch": 0.18,
"learning_rate": 2.4425278193780763e-05,
"loss": 0.2448,
"step": 30500
},
{
"epoch": 0.19,
"learning_rate": 2.4473888895103195e-05,
"loss": 0.2452,
"step": 31000
},
{
"epoch": 0.19,
"learning_rate": 2.452096167288451e-05,
"loss": 0.243,
"step": 31500
},
{
"epoch": 0.19,
"learning_rate": 2.4568039621632712e-05,
"loss": 0.2429,
"step": 32000
},
{
"epoch": 0.19,
"learning_rate": 2.4613651179295147e-05,
"loss": 0.2413,
"step": 32500
},
{
"epoch": 0.2,
"learning_rate": 2.465857111901344e-05,
"loss": 0.242,
"step": 33000
},
{
"epoch": 0.2,
"learning_rate": 2.470282010219007e-05,
"loss": 0.241,
"step": 33500
},
{
"epoch": 0.2,
"learning_rate": 2.4747115836685183e-05,
"loss": 0.2446,
"step": 34000
},
{
"epoch": 0.21,
"learning_rate": 2.479007124651486e-05,
"loss": 0.2419,
"step": 34500
},
{
"epoch": 0.21,
"learning_rate": 2.4833090695589105e-05,
"loss": 0.2401,
"step": 35000
},
{
"epoch": 0.21,
"learning_rate": 2.487482601761183e-05,
"loss": 0.2405,
"step": 35500
},
{
"epoch": 0.21,
"learning_rate": 2.4916640669495123e-05,
"loss": 0.2388,
"step": 36000
},
{
"epoch": 0.22,
"learning_rate": 2.4957223300236813e-05,
"loss": 0.239,
"step": 36500
},
{
"epoch": 0.22,
"learning_rate": 2.4997898800324933e-05,
"loss": 0.2376,
"step": 37000
},
{
"epoch": 0.22,
"learning_rate": 2.5037390701940674e-05,
"loss": 0.2379,
"step": 37500
},
{
"epoch": 0.23,
"learning_rate": 2.5076987472641913e-05,
"loss": 0.2358,
"step": 38000
},
{
"epoch": 0.23,
"learning_rate": 2.511544574188309e-05,
"loss": 0.2364,
"step": 38500
},
{
"epoch": 0.23,
"learning_rate": 2.5154019522390574e-05,
"loss": 0.2358,
"step": 39000
},
{
"epoch": 0.24,
"learning_rate": 2.5191496887008284e-05,
"loss": 0.2363,
"step": 39500
},
{
"epoch": 0.24,
"learning_rate": 2.522909920509883e-05,
"loss": 0.2348,
"step": 40000
},
{
"epoch": 0.24,
"learning_rate": 2.5265644458512783e-05,
"loss": 0.2361,
"step": 40500
},
{
"epoch": 0.24,
"learning_rate": 2.5302323044391743e-05,
"loss": 0.235,
"step": 41000
},
{
"epoch": 0.25,
"learning_rate": 2.533798142761435e-05,
"loss": 0.2342,
"step": 41500
},
{
"epoch": 0.25,
"learning_rate": 2.5373780578144523e-05,
"loss": 0.2324,
"step": 42000
},
{
"epoch": 0.25,
"learning_rate": 2.540859411645845e-05,
"loss": 0.234,
"step": 42500
},
{
"epoch": 0.26,
"learning_rate": 2.5443555016744024e-05,
"loss": 0.2324,
"step": 43000
},
{
"epoch": 0.26,
"learning_rate": 2.5477562817417014e-05,
"loss": 0.2327,
"step": 43500
},
{
"epoch": 0.26,
"learning_rate": 2.5511723825597137e-05,
"loss": 0.2326,
"step": 44000
},
{
"epoch": 0.27,
"learning_rate": 2.5544962341922467e-05,
"loss": 0.2312,
"step": 44500
},
{
"epoch": 0.27,
"learning_rate": 2.557783206251906e-05,
"loss": 0.2307,
"step": 45000
},
{
"epoch": 0.27,
"learning_rate": 2.561034108155725e-05,
"loss": 0.2308,
"step": 45500
},
{
"epoch": 0.27,
"learning_rate": 2.5643013027610686e-05,
"loss": 0.2308,
"step": 46000
},
{
"epoch": 0.28,
"learning_rate": 2.5674818374560964e-05,
"loss": 0.2293,
"step": 46500
},
{
"epoch": 0.28,
"learning_rate": 2.5706790693478524e-05,
"loss": 0.2298,
"step": 47000
},
{
"epoch": 0.28,
"learning_rate": 2.5737922185796036e-05,
"loss": 0.2285,
"step": 47500
},
{
"epoch": 0.29,
"learning_rate": 2.5769224212885376e-05,
"loss": 0.2287,
"step": 48000
},
{
"epoch": 0.29,
"learning_rate": 2.5799709812099402e-05,
"loss": 0.2285,
"step": 48500
},
{
"epoch": 0.29,
"learning_rate": 2.583036907549842e-05,
"loss": 0.2267,
"step": 49000
},
{
"epoch": 0.3,
"learning_rate": 2.5860235038107347e-05,
"loss": 0.2285,
"step": 49500
},
{
"epoch": 0.3,
"learning_rate": 2.5890277404236973e-05,
"loss": 0.2265,
"step": 50000
},
{
"epoch": 0.3,
"learning_rate": 2.5919548417573063e-05,
"loss": 0.2265,
"step": 50500
},
{
"epoch": 0.3,
"learning_rate": 2.5948998222244765e-05,
"loss": 0.2267,
"step": 51000
},
{
"epoch": 0.31,
"learning_rate": 2.597769752707028e-05,
"loss": 0.2257,
"step": 51500
},
{
"epoch": 0.31,
"learning_rate": 2.6006577693913388e-05,
"loss": 0.2256,
"step": 52000
},
{
"epoch": 0.31,
"learning_rate": 2.6034727195273174e-05,
"loss": 0.2262,
"step": 52500
},
{
"epoch": 0.32,
"learning_rate": 2.6063059342925614e-05,
"loss": 0.2251,
"step": 53000
},
{
"epoch": 0.32,
"learning_rate": 2.6090679710580784e-05,
"loss": 0.2241,
"step": 53500
},
{
"epoch": 0.32,
"learning_rate": 2.6118484249898836e-05,
"loss": 0.2263,
"step": 54000
},
{
"epoch": 0.33,
"learning_rate": 2.614559500949493e-05,
"loss": 0.225,
"step": 54500
},
{
"epoch": 0.33,
"learning_rate": 2.6172891231876906e-05,
"loss": 0.2244,
"step": 55000
},
{
"epoch": 0.33,
"learning_rate": 2.6199510847853688e-05,
"loss": 0.2241,
"step": 55500
},
{
"epoch": 0.33,
"learning_rate": 2.6226317005634724e-05,
"loss": 0.2231,
"step": 56000
},
{
"epoch": 0.34,
"learning_rate": 2.6252462956759424e-05,
"loss": 0.224,
"step": 56500
},
{
"epoch": 0.34,
"learning_rate": 2.6278796336516485e-05,
"loss": 0.2231,
"step": 57000
},
{
"epoch": 0.34,
"learning_rate": 2.6304485184814167e-05,
"loss": 0.2223,
"step": 57500
},
{
"epoch": 0.35,
"learning_rate": 2.6330362174318602e-05,
"loss": 0.223,
"step": 58000
},
{
"epoch": 0.35,
"learning_rate": 2.635560962808044e-05,
"loss": 0.2221,
"step": 58500
},
{
"epoch": 0.35,
"learning_rate": 2.638104577754729e-05,
"loss": 0.2214,
"step": 59000
},
{
"epoch": 0.36,
"learning_rate": 2.640586674901711e-05,
"loss": 0.2215,
"step": 59500
},
{
"epoch": 0.36,
"learning_rate": 2.6430481486499792e-05,
"loss": 0.2221,
"step": 60000
},
{
"epoch": 0.36,
"learning_rate": 2.6454893388912424e-05,
"loss": 0.2208,
"step": 60500
},
{
"epoch": 0.36,
"learning_rate": 2.647949467707987e-05,
"loss": 0.2205,
"step": 61000
},
{
"epoch": 0.37,
"learning_rate": 2.65035076356444e-05,
"loss": 0.2195,
"step": 61500
},
{
"epoch": 0.37,
"learning_rate": 2.6527710143352714e-05,
"loss": 0.2206,
"step": 62000
},
{
"epoch": 0.37,
"learning_rate": 2.655133698770308e-05,
"loss": 0.22,
"step": 62500
},
{
"epoch": 0.38,
"learning_rate": 2.657515343705422e-05,
"loss": 0.2199,
"step": 63000
},
{
"epoch": 0.38,
"learning_rate": 2.659840638773283e-05,
"loss": 0.22,
"step": 63500
},
{
"epoch": 0.38,
"learning_rate": 2.6621848901583615e-05,
"loss": 0.22,
"step": 64000
},
{
"epoch": 0.39,
"learning_rate": 2.664473960799668e-05,
"loss": 0.2199,
"step": 64500
},
{
"epoch": 0.39,
"learning_rate": 2.6667819747011933e-05,
"loss": 0.2192,
"step": 65000
},
{
"epoch": 0.39,
"learning_rate": 2.6690359322473682e-05,
"loss": 0.2198,
"step": 65500
},
{
"epoch": 0.39,
"learning_rate": 2.6713088119359103e-05,
"loss": 0.2186,
"step": 66000
},
{
"epoch": 0.4,
"learning_rate": 2.6735287173488718e-05,
"loss": 0.2181,
"step": 66500
},
{
"epoch": 0.4,
"learning_rate": 2.6757675164657182e-05,
"loss": 0.2186,
"step": 67000
},
{
"epoch": 0.4,
"learning_rate": 2.6779543833364954e-05,
"loss": 0.2184,
"step": 67500
},
{
"epoch": 0.41,
"learning_rate": 2.6801601088263703e-05,
"loss": 0.2178,
"step": 68000
},
{
"epoch": 0.41,
"learning_rate": 2.6823149061538402e-05,
"loss": 0.2163,
"step": 68500
},
{
"epoch": 0.41,
"learning_rate": 2.6844885209841567e-05,
"loss": 0.2168,
"step": 69000
},
{
"epoch": 0.42,
"learning_rate": 2.6866121757529833e-05,
"loss": 0.2164,
"step": 69500
},
{
"epoch": 0.42,
"learning_rate": 2.6887207154131734e-05,
"loss": 0.2176,
"step": 70000
},
{
"epoch": 0.42,
"learning_rate": 2.6908143536085277e-05,
"loss": 0.2167,
"step": 70500
},
{
"epoch": 0.42,
"learning_rate": 2.6929267116061277e-05,
"loss": 0.2165,
"step": 71000
},
{
"epoch": 0.43,
"learning_rate": 2.694990937921598e-05,
"loss": 0.2159,
"step": 71500
},
{
"epoch": 0.43,
"learning_rate": 2.697073828038998e-05,
"loss": 0.2149,
"step": 72000
},
{
"epoch": 0.43,
"learning_rate": 2.699109457398446e-05,
"loss": 0.2169,
"step": 72500
},
{
"epoch": 0.44,
"learning_rate": 2.7011636904946913e-05,
"loss": 0.2161,
"step": 73000
},
{
"epoch": 0.44,
"learning_rate": 2.7031715044156344e-05,
"loss": 0.2145,
"step": 73500
},
{
"epoch": 0.44,
"learning_rate": 2.7051978583356027e-05,
"loss": 0.2156,
"step": 74000
},
{
"epoch": 0.44,
"learning_rate": 2.7071786067305193e-05,
"loss": 0.2159,
"step": 74500
},
{
"epoch": 0.45,
"learning_rate": 2.7091778280731625e-05,
"loss": 0.2153,
"step": 75000
},
{
"epoch": 0.45,
"learning_rate": 2.711132230931001e-05,
"loss": 0.2154,
"step": 75500
},
{
"epoch": 0.45,
"learning_rate": 2.713105036700763e-05,
"loss": 0.2151,
"step": 76000
},
{
"epoch": 0.46,
"learning_rate": 2.7150337856580877e-05,
"loss": 0.215,
"step": 76500
},
{
"epoch": 0.46,
"learning_rate": 2.716980864808648e-05,
"loss": 0.2137,
"step": 77000
},
{
"epoch": 0.46,
"learning_rate": 2.718884624619005e-05,
"loss": 0.213,
"step": 77500
},
{
"epoch": 0.47,
"learning_rate": 2.7208066394976544e-05,
"loss": 0.2134,
"step": 78000
},
{
"epoch": 0.47,
"learning_rate": 2.7226860494069692e-05,
"loss": 0.2138,
"step": 78500
},
{
"epoch": 0.47,
"learning_rate": 2.7245836371072047e-05,
"loss": 0.2139,
"step": 79000
},
{
"epoch": 0.47,
"learning_rate": 2.7264094739420033e-05,
"loss": 0.2131,
"step": 79500
},
{
"epoch": 0.48,
"learning_rate": 2.7282834357118275e-05,
"loss": 0.2136,
"step": 80000
},
{
"epoch": 0.48,
"learning_rate": 2.7301161507408316e-05,
"loss": 0.2132,
"step": 80500
},
{
"epoch": 0.48,
"learning_rate": 2.73196688411515e-05,
"loss": 0.2141,
"step": 81000
},
{
"epoch": 0.49,
"learning_rate": 2.7337770219476417e-05,
"loss": 0.2132,
"step": 81500
},
{
"epoch": 0.49,
"learning_rate": 2.7355761666135546e-05,
"loss": 0.2131,
"step": 82000
},
{
"epoch": 0.49,
"learning_rate": 2.737364450832697e-05,
"loss": 0.2131,
"step": 82500
},
{
"epoch": 0.5,
"learning_rate": 2.7391705879424115e-05,
"loss": 0.2128,
"step": 83000
},
{
"epoch": 0.5,
"learning_rate": 2.7409373699625777e-05,
"loss": 0.2109,
"step": 83500
},
{
"epoch": 0.5,
"learning_rate": 2.7427219199888326e-05,
"loss": 0.2121,
"step": 84000
},
{
"epoch": 0.5,
"learning_rate": 2.7444677107497597e-05,
"loss": 0.2122,
"step": 84500
},
{
"epoch": 0.51,
"learning_rate": 2.746231183620202e-05,
"loss": 0.2129,
"step": 85000
},
{
"epoch": 0.51,
"learning_rate": 2.7479564760638262e-05,
"loss": 0.2134,
"step": 85500
},
{
"epoch": 0.51,
"learning_rate": 2.749671778898659e-05,
"loss": 0.2118,
"step": 86000
},
{
"epoch": 0.52,
"learning_rate": 2.751377207140654e-05,
"loss": 0.2125,
"step": 86500
},
{
"epoch": 0.52,
"learning_rate": 2.7531001439160817e-05,
"loss": 0.2119,
"step": 87000
},
{
"epoch": 0.52,
"learning_rate": 2.7547860054130076e-05,
"loss": 0.213,
"step": 87500
},
{
"epoch": 0.53,
"learning_rate": 2.7564892873136608e-05,
"loss": 0.212,
"step": 88000
},
{
"epoch": 0.53,
"learning_rate": 2.7581560259607478e-05,
"loss": 0.2161,
"step": 88500
},
{
"epoch": 0.53,
"learning_rate": 2.759840096366627e-05,
"loss": 0.2147,
"step": 89000
},
{
"epoch": 0.53,
"learning_rate": 2.7614881411230366e-05,
"loss": 0.2118,
"step": 89500
},
{
"epoch": 0.54,
"learning_rate": 2.7631534285786048e-05,
"loss": 0.2116,
"step": 90000
},
{
"epoch": 0.54,
"learning_rate": 2.76478319413009e-05,
"loss": 0.2126,
"step": 90500
},
{
"epoch": 0.54,
"learning_rate": 2.766430112998838e-05,
"loss": 0.2114,
"step": 91000
},
{
"epoch": 0.55,
"learning_rate": 2.7680420003840493e-05,
"loss": 0.2099,
"step": 91500
},
{
"epoch": 0.55,
"learning_rate": 2.7696709514673566e-05,
"loss": 0.2093,
"step": 92000
},
{
"epoch": 0.55,
"learning_rate": 2.771265348670174e-05,
"loss": 0.2111,
"step": 92500
},
{
"epoch": 0.56,
"learning_rate": 2.772876719792772e-05,
"loss": 0.21,
"step": 93000
},
{
"epoch": 0.56,
"learning_rate": 2.7744540023028418e-05,
"loss": 0.2099,
"step": 93500
},
{
"epoch": 0.56,
"learning_rate": 2.776048168867023e-05,
"loss": 0.209,
"step": 94000
},
{
"epoch": 0.56,
"learning_rate": 2.777608700210528e-05,
"loss": 0.209,
"step": 94500
},
{
"epoch": 0.57,
"learning_rate": 2.7791860257210812e-05,
"loss": 0.2089,
"step": 95000
},
{
"epoch": 0.57,
"learning_rate": 2.7807301579636298e-05,
"loss": 0.2097,
"step": 95500
},
{
"epoch": 0.57,
"learning_rate": 2.7822909945253365e-05,
"loss": 0.2084,
"step": 96000
},
{
"epoch": 0.58,
"learning_rate": 2.783819068748691e-05,
"loss": 0.208,
"step": 96500
},
{
"epoch": 0.58,
"learning_rate": 2.7853637575380904e-05,
"loss": 0.2081,
"step": 97000
},
{
"epoch": 0.58,
"learning_rate": 2.786876104292373e-05,
"loss": 0.2092,
"step": 97500
},
{
"epoch": 0.59,
"learning_rate": 2.788404976005368e-05,
"loss": 0.2074,
"step": 98000
},
{
"epoch": 0.59,
"learning_rate": 2.7899019157382252e-05,
"loss": 0.2077,
"step": 98500
},
{
"epoch": 0.59,
"learning_rate": 2.7914152910150078e-05,
"loss": 0.2089,
"step": 99000
},
{
"epoch": 0.59,
"learning_rate": 2.792897134479138e-05,
"loss": 0.2079,
"step": 99500
},
{
"epoch": 0.6,
"learning_rate": 2.7943953243077938e-05,
"loss": 0.2086,
"step": 100000
},
{
"epoch": 0.6,
"learning_rate": 2.795862372948129e-05,
"loss": 0.2085,
"step": 100500
},
{
"epoch": 0.6,
"learning_rate": 2.7973456790481943e-05,
"loss": 0.2066,
"step": 101000
},
{
"epoch": 0.61,
"learning_rate": 2.798798225369947e-05,
"loss": 0.2073,
"step": 101500
},
{
"epoch": 0.61,
"learning_rate": 2.800243684398857e-05,
"loss": 0.2064,
"step": 102000
},
{
"epoch": 0.61,
"learning_rate": 2.8016821249601656e-05,
"loss": 0.2066,
"step": 102500
},
{
"epoch": 0.62,
"learning_rate": 2.803136646840342e-05,
"loss": 0.2066,
"step": 103000
},
{
"epoch": 0.62,
"learning_rate": 2.8045611424841357e-05,
"loss": 0.2068,
"step": 103500
},
{
"epoch": 0.62,
"learning_rate": 2.8060016315657188e-05,
"loss": 0.2067,
"step": 104000
},
{
"epoch": 0.62,
"learning_rate": 2.807412450073651e-05,
"loss": 0.2071,
"step": 104500
},
{
"epoch": 0.63,
"learning_rate": 2.8088391745384398e-05,
"loss": 0.2048,
"step": 105000
},
{
"epoch": 0.63,
"learning_rate": 2.81023657605226e-05,
"loss": 0.2061,
"step": 105500
},
{
"epoch": 0.63,
"learning_rate": 2.8116497964669418e-05,
"loss": 0.2064,
"step": 106000
},
{
"epoch": 0.64,
"learning_rate": 2.8130340337763864e-05,
"loss": 0.2049,
"step": 106500
},
{
"epoch": 0.64,
"learning_rate": 2.8144340033781484e-05,
"loss": 0.2057,
"step": 107000
},
{
"epoch": 0.64,
"learning_rate": 2.8158053221953934e-05,
"loss": 0.2063,
"step": 107500
},
{
"epoch": 0.64,
"learning_rate": 2.8171922871642636e-05,
"loss": 0.2051,
"step": 108000
},
{
"epoch": 0.65,
"learning_rate": 2.818550926385693e-05,
"loss": 0.2052,
"step": 108500
},
{
"epoch": 0.65,
"learning_rate": 2.8199251261043525e-05,
"loss": 0.2052,
"step": 109000
},
{
"epoch": 0.65,
"learning_rate": 2.8212713180603268e-05,
"loss": 0.2052,
"step": 109500
},
{
"epoch": 0.66,
"learning_rate": 2.822632985362071e-05,
"loss": 0.2044,
"step": 110000
},
{
"epoch": 0.66,
"learning_rate": 2.8239669560553714e-05,
"loss": 0.2051,
"step": 110500
},
{
"epoch": 0.66,
"learning_rate": 2.8253163174608688e-05,
"loss": 0.2046,
"step": 111000
},
{
"epoch": 0.67,
"learning_rate": 2.826638286794405e-05,
"loss": 0.2051,
"step": 111500
},
{
"epoch": 0.67,
"learning_rate": 2.8279543832152957e-05,
"loss": 0.2047,
"step": 112000
},
{
"epoch": 0.67,
"learning_rate": 2.829264658674229e-05,
"loss": 0.2048,
"step": 112500
},
{
"epoch": 0.67,
"learning_rate": 2.8305901578503227e-05,
"loss": 0.2038,
"step": 113000
},
{
"epoch": 0.68,
"learning_rate": 2.831888852671534e-05,
"loss": 0.2042,
"step": 113500
},
{
"epoch": 0.68,
"learning_rate": 2.833202688200269e-05,
"loss": 0.2035,
"step": 114000
},
{
"epoch": 0.68,
"learning_rate": 2.834490005297497e-05,
"loss": 0.2032,
"step": 114500
},
{
"epoch": 0.69,
"learning_rate": 2.835792380655797e-05,
"loss": 0.2037,
"step": 115000
},
{
"epoch": 0.69,
"learning_rate": 2.8370685176559642e-05,
"loss": 0.2032,
"step": 115500
},
{
"epoch": 0.69,
"learning_rate": 2.8383596310421844e-05,
"loss": 0.2039,
"step": 116000
},
{
"epoch": 0.7,
"learning_rate": 2.8396247804674794e-05,
"loss": 0.2038,
"step": 116500
},
{
"epoch": 0.7,
"learning_rate": 2.8409048249824243e-05,
"loss": 0.2042,
"step": 117000
},
{
"epoch": 0.7,
"learning_rate": 2.842159174424607e-05,
"loss": 0.2025,
"step": 117500
},
{
"epoch": 0.7,
"learning_rate": 2.843428338244851e-05,
"loss": 0.2037,
"step": 118000
},
{
"epoch": 0.71,
"learning_rate": 2.8446720705321826e-05,
"loss": 0.2028,
"step": 118500
},
{
"epoch": 0.71,
"learning_rate": 2.8459305370760914e-05,
"loss": 0.2039,
"step": 119000
},
{
"epoch": 0.71,
"learning_rate": 2.8471638304332623e-05,
"loss": 0.2042,
"step": 119500
},
{
"epoch": 0.72,
"learning_rate": 2.8484117785200688e-05,
"loss": 0.2032,
"step": 120000
},
{
"epoch": 0.72,
"learning_rate": 2.8496348067214675e-05,
"loss": 0.2034,
"step": 120500
},
{
"epoch": 0.72,
"learning_rate": 2.8508724107237616e-05,
"loss": 0.2031,
"step": 121000
},
{
"epoch": 0.73,
"learning_rate": 2.8520853432404158e-05,
"loss": 0.2038,
"step": 121500
},
{
"epoch": 0.73,
"learning_rate": 2.8533127732303632e-05,
"loss": 0.2019,
"step": 122000
},
{
"epoch": 0.73,
"learning_rate": 2.8545157753708722e-05,
"loss": 0.2027,
"step": 122500
},
{
"epoch": 0.73,
"learning_rate": 2.8557331972604735e-05,
"loss": 0.2029,
"step": 123000
},
{
"epoch": 0.74,
"learning_rate": 2.8569264303062103e-05,
"loss": 0.2025,
"step": 123500
},
{
"epoch": 0.74,
"learning_rate": 2.8581340059818852e-05,
"loss": 0.2026,
"step": 124000
},
{
"epoch": 0.74,
"learning_rate": 2.859298574123735e-05,
"loss": 0.2035,
"step": 124500
},
{
"epoch": 0.75,
"learning_rate": 2.8604965384644176e-05,
"loss": 0.2023,
"step": 125000
},
{
"epoch": 0.75,
"learning_rate": 2.8616707767644272e-05,
"loss": 0.2023,
"step": 125500
},
{
"epoch": 0.75,
"learning_rate": 2.8628592058798022e-05,
"loss": 0.2016,
"step": 126000
},
{
"epoch": 0.76,
"learning_rate": 2.8640241348522744e-05,
"loss": 0.2022,
"step": 126500
},
{
"epoch": 0.76,
"learning_rate": 2.8652031793355915e-05,
"loss": 0.2014,
"step": 127000
},
{
"epoch": 0.76,
"learning_rate": 2.8663589454278458e-05,
"loss": 0.202,
"step": 127500
},
{
"epoch": 0.76,
"learning_rate": 2.867528752332742e-05,
"loss": 0.2032,
"step": 128000
},
{
"epoch": 0.77,
"learning_rate": 2.8686754985633652e-05,
"loss": 0.2017,
"step": 128500
},
{
"epoch": 0.77,
"learning_rate": 2.8698362115139278e-05,
"loss": 0.2025,
"step": 129000
},
{
"epoch": 0.77,
"learning_rate": 2.8709740775789806e-05,
"loss": 0.2005,
"step": 129500
},
{
"epoch": 0.78,
"learning_rate": 2.8721258368755737e-05,
"loss": 0.2017,
"step": 130000
},
{
"epoch": 0.78,
"learning_rate": 2.8732549592507123e-05,
"loss": 0.2002,
"step": 130500
},
{
"epoch": 0.78,
"learning_rate": 2.8743979019717454e-05,
"loss": 0.2013,
"step": 131000
},
{
"epoch": 0.79,
"learning_rate": 2.8755184140104564e-05,
"loss": 0.2012,
"step": 131500
},
{
"epoch": 0.79,
"learning_rate": 2.8766526741102906e-05,
"loss": 0.2001,
"step": 132000
},
{
"epoch": 0.79,
"learning_rate": 2.877764706138406e-05,
"loss": 0.2006,
"step": 132500
},
{
"epoch": 0.79,
"learning_rate": 2.8788904145415675e-05,
"loss": 0.2002,
"step": 133000
},
{
"epoch": 0.8,
"learning_rate": 2.879994093948226e-05,
"loss": 0.2006,
"step": 133500
},
{
"epoch": 0.8,
"learning_rate": 2.8811113786400982e-05,
"loss": 0.2008,
"step": 134000
},
{
"epoch": 0.8,
"learning_rate": 2.882206829965323e-05,
"loss": 0.2004,
"step": 134500
},
{
"epoch": 0.81,
"learning_rate": 2.8833158160794665e-05,
"loss": 0.2006,
"step": 135000
},
{
"epoch": 0.81,
"learning_rate": 2.884403161098495e-05,
"loss": 0.2005,
"step": 135500
},
{
"epoch": 0.81,
"learning_rate": 2.8855039710007507e-05,
"loss": 0.2005,
"step": 136000
},
{
"epoch": 0.82,
"learning_rate": 2.8865833288052765e-05,
"loss": 0.2001,
"step": 136500
},
{
"epoch": 0.82,
"learning_rate": 2.88767608217479e-05,
"loss": 0.2012,
"step": 137000
},
{
"epoch": 0.82,
"learning_rate": 2.8887475692512324e-05,
"loss": 0.2,
"step": 137500
},
{
"epoch": 0.82,
"learning_rate": 2.8898151948801743e-05,
"loss": 0.2047,
"step": 138000
},
{
"epoch": 0.83,
"learning_rate": 2.8908789867936345e-05,
"loss": 0.201,
"step": 138500
},
{
"epoch": 0.83,
"learning_rate": 2.8919560379273633e-05,
"loss": 0.2001,
"step": 139000
},
{
"epoch": 0.83,
"learning_rate": 2.893012183686383e-05,
"loss": 0.1997,
"step": 139500
},
{
"epoch": 0.84,
"learning_rate": 2.8940815210844637e-05,
"loss": 0.1999,
"step": 140000
},
{
"epoch": 0.84,
"learning_rate": 2.895130129820388e-05,
"loss": 0.2006,
"step": 140500
},
{
"epoch": 0.84,
"learning_rate": 2.8961918631872983e-05,
"loss": 0.1989,
"step": 141000
},
{
"epoch": 0.85,
"learning_rate": 2.8972330417116244e-05,
"loss": 0.1994,
"step": 141500
},
{
"epoch": 0.85,
"learning_rate": 2.8982872784280433e-05,
"loss": 0.1983,
"step": 142000
},
{
"epoch": 0.85,
"learning_rate": 2.8993211312977118e-05,
"loss": 0.1993,
"step": 142500
},
{
"epoch": 0.85,
"learning_rate": 2.9003679764856915e-05,
"loss": 0.1992,
"step": 143000
},
{
"epoch": 0.86,
"learning_rate": 2.9013946060660928e-05,
"loss": 0.1994,
"step": 143500
},
{
"epoch": 0.86,
"learning_rate": 2.9024341626519623e-05,
"loss": 0.1985,
"step": 144000
},
{
"epoch": 0.86,
"learning_rate": 2.9034372533313795e-05,
"loss": 0.2008,
"step": 144500
},
{
"epoch": 0.87,
"learning_rate": 2.9044696792145252e-05,
"loss": 0.2002,
"step": 145000
},
{
"epoch": 0.87,
"learning_rate": 2.9054822166633558e-05,
"loss": 0.2006,
"step": 145500
},
{
"epoch": 0.87,
"learning_rate": 2.9065075526690717e-05,
"loss": 0.2001,
"step": 146000
},
{
"epoch": 0.87,
"learning_rate": 2.9075131606120165e-05,
"loss": 0.1993,
"step": 146500
},
{
"epoch": 0.88,
"learning_rate": 2.908531503451507e-05,
"loss": 0.1991,
"step": 147000
},
{
"epoch": 0.88,
"learning_rate": 2.909530276090928e-05,
"loss": 0.1993,
"step": 147500
},
{
"epoch": 0.88,
"learning_rate": 2.910541720509983e-05,
"loss": 0.1982,
"step": 148000
},
{
"epoch": 0.89,
"learning_rate": 2.9115337501402732e-05,
"loss": 0.1986,
"step": 148500
},
{
"epoch": 0.89,
"learning_rate": 2.912538388972165e-05,
"loss": 0.1986,
"step": 149000
},
{
"epoch": 0.89,
"learning_rate": 2.9135237660309318e-05,
"loss": 0.1987,
"step": 149500
},
{
"epoch": 0.9,
"learning_rate": 2.914521690247543e-05,
"loss": 0.1985,
"step": 150000
},
{
"epoch": 0.9,
"learning_rate": 2.915500503365078e-05,
"loss": 0.1989,
"step": 150500
},
{
"epoch": 0.9,
"learning_rate": 2.9164918021263375e-05,
"loss": 0.1978,
"step": 151000
},
{
"epoch": 0.9,
"learning_rate": 2.91746413817346e-05,
"loss": 0.1992,
"step": 151500
},
{
"epoch": 0.91,
"learning_rate": 2.9184488988751434e-05,
"loss": 0.1988,
"step": 152000
},
{
"epoch": 0.91,
"learning_rate": 2.9194148430094623e-05,
"loss": 0.1981,
"step": 152500
},
{
"epoch": 0.91,
"learning_rate": 2.9203931513294304e-05,
"loss": 0.1985,
"step": 153000
},
{
"epoch": 0.92,
"learning_rate": 2.9213527870401e-05,
"loss": 0.1983,
"step": 153500
},
{
"epoch": 0.92,
"learning_rate": 2.9223247269830284e-05,
"loss": 0.2006,
"step": 154000
},
{
"epoch": 0.92,
"learning_rate": 2.9232781361340522e-05,
"loss": 0.1987,
"step": 154500
},
{
"epoch": 0.93,
"learning_rate": 2.924243790074719e-05,
"loss": 0.1989,
"step": 155000
},
{
"epoch": 0.93,
"learning_rate": 2.925191052946856e-05,
"loss": 0.1972,
"step": 155500
},
{
"epoch": 0.93,
"learning_rate": 2.9261505016720347e-05,
"loss": 0.1981,
"step": 156000
},
{
"epoch": 0.93,
"learning_rate": 2.927091697003365e-05,
"loss": 0.1976,
"step": 156500
},
{
"epoch": 0.94,
"learning_rate": 2.928045019752382e-05,
"loss": 0.1973,
"step": 157000
},
{
"epoch": 0.94,
"learning_rate": 2.9289802247775793e-05,
"loss": 0.1989,
"step": 157500
},
{
"epoch": 0.94,
"learning_rate": 2.9299274992815847e-05,
"loss": 0.1965,
"step": 158000
},
{
"epoch": 0.95,
"learning_rate": 2.9308567897699503e-05,
"loss": 0.1964,
"step": 158500
},
{
"epoch": 0.95,
"learning_rate": 2.93179809228995e-05,
"loss": 0.1973,
"step": 159000
},
{
"epoch": 0.95,
"learning_rate": 2.9327215425822497e-05,
"loss": 0.1974,
"step": 159500
},
{
"epoch": 0.96,
"learning_rate": 2.933656947945947e-05,
"loss": 0.1968,
"step": 160000
},
{
"epoch": 0.96,
"learning_rate": 2.934574630990096e-05,
"loss": 0.1977,
"step": 160500
},
{
"epoch": 0.96,
"learning_rate": 2.9355042126275852e-05,
"loss": 0.1973,
"step": 161000
},
{
"epoch": 0.96,
"learning_rate": 2.936416200013231e-05,
"loss": 0.1975,
"step": 161500
},
{
"epoch": 0.97,
"learning_rate": 2.9373400299915887e-05,
"loss": 0.1974,
"step": 162000
},
{
"epoch": 0.97,
"learning_rate": 2.9382463919836192e-05,
"loss": 0.1978,
"step": 162500
},
{
"epoch": 0.97,
"learning_rate": 2.939164541040431e-05,
"loss": 0.1967,
"step": 163000
},
{
"epoch": 0.98,
"learning_rate": 2.9400653466114648e-05,
"loss": 0.1959,
"step": 163500
},
{
"epoch": 0.98,
"learning_rate": 2.940977884187325e-05,
"loss": 0.1964,
"step": 164000
},
{
"epoch": 0.98,
"learning_rate": 2.941873201049204e-05,
"loss": 0.1972,
"step": 164500
},
{
"epoch": 0.99,
"learning_rate": 2.9427801953192338e-05,
"loss": 0.1956,
"step": 165000
},
{
"epoch": 0.99,
"learning_rate": 2.9436700899535667e-05,
"loss": 0.1962,
"step": 165500
},
{
"epoch": 0.99,
"learning_rate": 2.9445716078579753e-05,
"loss": 0.1953,
"step": 166000
},
{
"epoch": 0.99,
"learning_rate": 2.9454561455457596e-05,
"loss": 0.1966,
"step": 166500
},
{
"epoch": 1.0,
"learning_rate": 2.946352252819492e-05,
"loss": 0.1964,
"step": 167000
},
{
"epoch": 1.0,
"learning_rate": 2.9472314976698527e-05,
"loss": 0.1954,
"step": 167500
},
{
"epoch": 1.0,
"learning_rate": 2.9481222588713497e-05,
"loss": 0.1967,
"step": 168000
},
{
"epoch": 1.01,
"learning_rate": 2.9489962738494186e-05,
"loss": 0.1955,
"step": 168500
},
{
"epoch": 1.01,
"learning_rate": 2.9498677178255942e-05,
"loss": 0.1961,
"step": 169000
},
{
"epoch": 1.01,
"learning_rate": 2.950736605881239e-05,
"loss": 0.1961,
"step": 169500
},
{
"epoch": 1.02,
"learning_rate": 2.951616905565036e-05,
"loss": 0.1958,
"step": 170000
},
{
"epoch": 1.02,
"learning_rate": 2.952480685872313e-05,
"loss": 0.1963,
"step": 170500
},
{
"epoch": 1.02,
"learning_rate": 2.9533558258899208e-05,
"loss": 0.196,
"step": 171000
},
{
"epoch": 1.02,
"learning_rate": 2.9542145581495995e-05,
"loss": 0.1965,
"step": 171500
},
{
"epoch": 1.03,
"learning_rate": 2.955084598632913e-05,
"loss": 0.196,
"step": 172000
},
{
"epoch": 1.03,
"learning_rate": 2.955938341505148e-05,
"loss": 0.1949,
"step": 172500
},
{
"epoch": 1.03,
"learning_rate": 2.9568033415409656e-05,
"loss": 0.196,
"step": 173000
},
{
"epoch": 1.04,
"learning_rate": 2.957652152669337e-05,
"loss": 0.1961,
"step": 173500
},
{
"epoch": 1.04,
"learning_rate": 2.958512170323439e-05,
"loss": 0.1969,
"step": 174000
},
{
"epoch": 1.04,
"learning_rate": 2.9593561063583085e-05,
"loss": 0.1965,
"step": 174500
},
{
"epoch": 1.05,
"learning_rate": 2.9602111986988488e-05,
"loss": 0.1965,
"step": 175000
},
{
"epoch": 1.05,
"learning_rate": 2.9610503153200486e-05,
"loss": 0.1964,
"step": 175500
},
{
"epoch": 1.05,
"learning_rate": 2.9619005384402748e-05,
"loss": 0.1956,
"step": 176000
},
{
"epoch": 1.05,
"learning_rate": 2.9627348903791495e-05,
"loss": 0.197,
"step": 176500
},
{
"epoch": 1.06,
"learning_rate": 2.9635802994194856e-05,
"loss": 0.1958,
"step": 177000
},
{
"epoch": 1.06,
"learning_rate": 2.9644099404803134e-05,
"loss": 0.1978,
"step": 177500
},
{
"epoch": 1.06,
"learning_rate": 2.9652505896498182e-05,
"loss": 0.1966,
"step": 178000
},
{
"epoch": 1.07,
"learning_rate": 2.9660755727306327e-05,
"loss": 0.1968,
"step": 178500
},
{
"epoch": 1.07,
"learning_rate": 2.966911515327857e-05,
"loss": 0.1962,
"step": 179000
},
{
"epoch": 1.07,
"learning_rate": 2.9677318924406836e-05,
"loss": 0.1966,
"step": 179500
},
{
"epoch": 1.07,
"learning_rate": 2.968563180873947e-05,
"loss": 0.1966,
"step": 180000
},
{
"epoch": 1.08,
"learning_rate": 2.9693790031644822e-05,
"loss": 0.1975,
"step": 180500
},
{
"epoch": 1.08,
"learning_rate": 2.97020568897159e-05,
"loss": 0.1964,
"step": 181000
},
{
"epoch": 1.08,
"learning_rate": 2.9710170067383318e-05,
"loss": 0.1962,
"step": 181500
},
{
"epoch": 1.09,
"learning_rate": 2.9718391406057494e-05,
"loss": 0.1967,
"step": 182000
},
{
"epoch": 1.09,
"learning_rate": 2.9726460033186095e-05,
"loss": 0.1962,
"step": 182500
},
{
"epoch": 1.09,
"learning_rate": 2.9734636351001065e-05,
"loss": 0.1957,
"step": 183000
},
{
"epoch": 1.1,
"learning_rate": 2.9742660914185072e-05,
"loss": 0.1966,
"step": 183500
},
{
"epoch": 1.1,
"learning_rate": 2.975079270153302e-05,
"loss": 0.1973,
"step": 184000
},
{
"epoch": 1.1,
"learning_rate": 2.9758773679437866e-05,
"loss": 0.1962,
"step": 184500
},
{
"epoch": 1.1,
"learning_rate": 2.9766861418741936e-05,
"loss": 0.1962,
"step": 185000
},
{
"epoch": 1.11,
"learning_rate": 2.9774799282275585e-05,
"loss": 0.1956,
"step": 185500
},
{
"epoch": 1.11,
"learning_rate": 2.9782843448161612e-05,
"loss": 0.1963,
"step": 186000
},
{
"epoch": 1.11,
"learning_rate": 2.9790738660641294e-05,
"loss": 0.1961,
"step": 186500
},
{
"epoch": 1.12,
"learning_rate": 2.979873972010495e-05,
"loss": 0.1975,
"step": 187000
},
{
"epoch": 1.12,
"learning_rate": 2.9806592737419435e-05,
"loss": 0.1966,
"step": 187500
},
{
"epoch": 1.12,
"learning_rate": 2.9814551149988898e-05,
"loss": 0.1973,
"step": 188000
},
{
"epoch": 1.13,
"learning_rate": 2.982236242075644e-05,
"loss": 0.1968,
"step": 188500
},
{
"epoch": 1.13,
"learning_rate": 2.983027863865077e-05,
"loss": 0.1972,
"step": 189000
},
{
"epoch": 1.13,
"learning_rate": 2.9838048604372908e-05,
"loss": 0.1965,
"step": 189500
},
{
"epoch": 1.13,
"learning_rate": 2.9845923072656245e-05,
"loss": 0.197,
"step": 190000
},
{
"epoch": 1.14,
"learning_rate": 2.9853652167867524e-05,
"loss": 0.1962,
"step": 190500
},
{
"epoch": 1.14,
"learning_rate": 2.9861485324599208e-05,
"loss": 0.1966,
"step": 191000
},
{
"epoch": 1.14,
"learning_rate": 2.9869173977013007e-05,
"loss": 0.1967,
"step": 191500
},
{
"epoch": 1.15,
"learning_rate": 2.9876966253393842e-05,
"loss": 0.196,
"step": 192000
},
{
"epoch": 1.15,
"learning_rate": 2.988461488404441e-05,
"loss": 0.1964,
"step": 192500
},
{
"epoch": 1.15,
"learning_rate": 2.989236670455906e-05,
"loss": 0.1961,
"step": 193000
},
{
"epoch": 1.16,
"learning_rate": 2.9899975727939854e-05,
"loss": 0.1959,
"step": 193500
},
{
"epoch": 1.16,
"learning_rate": 2.990768751049564e-05,
"loss": 0.1959,
"step": 194000
},
{
"epoch": 1.16,
"learning_rate": 2.9915257334694092e-05,
"loss": 0.196,
"step": 194500
},
{
"epoch": 1.16,
"learning_rate": 2.992292949075614e-05,
"loss": 0.1966,
"step": 195000
},
{
"epoch": 1.17,
"learning_rate": 2.993046051758501e-05,
"loss": 0.1969,
"step": 195500
},
{
"epoch": 1.17,
"learning_rate": 2.9938093452308026e-05,
"loss": 0.1957,
"step": 196000
},
{
"epoch": 1.17,
"learning_rate": 2.994558607743339e-05,
"loss": 0.1967,
"step": 196500
},
{
"epoch": 1.18,
"learning_rate": 2.9953180189789992e-05,
"loss": 0.1963,
"step": 197000
},
{
"epoch": 1.18,
"learning_rate": 2.9960634802855956e-05,
"loss": 0.195,
"step": 197500
},
{
"epoch": 1.18,
"learning_rate": 2.9968190485761867e-05,
"loss": 0.1963,
"step": 198000
},
{
"epoch": 1.19,
"learning_rate": 2.9975607470512163e-05,
"loss": 0.1966,
"step": 198500
},
{
"epoch": 1.19,
"learning_rate": 2.9983125110948153e-05,
"loss": 0.1963,
"step": 199000
},
{
"epoch": 1.19,
"learning_rate": 2.9990504845344676e-05,
"loss": 0.195,
"step": 199500
},
{
"epoch": 1.19,
"learning_rate": 2.9997984824475517e-05,
"loss": 0.1968,
"step": 200000
},
{
"epoch": 1.2,
"learning_rate": 3e-05,
"loss": 0.1959,
"step": 200500
},
{
"epoch": 1.2,
"learning_rate": 3e-05,
"loss": 0.1959,
"step": 201000
},
{
"epoch": 1.2,
"learning_rate": 3e-05,
"loss": 0.1959,
"step": 201500
},
{
"epoch": 1.21,
"learning_rate": 3e-05,
"loss": 0.1956,
"step": 202000
},
{
"epoch": 1.21,
"learning_rate": 3e-05,
"loss": 0.1955,
"step": 202500
},
{
"epoch": 1.21,
"learning_rate": 3e-05,
"loss": 0.1966,
"step": 203000
},
{
"epoch": 1.22,
"learning_rate": 3e-05,
"loss": 0.196,
"step": 203500
},
{
"epoch": 1.22,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 204000
},
{
"epoch": 1.22,
"learning_rate": 3e-05,
"loss": 0.1966,
"step": 204500
},
{
"epoch": 1.22,
"learning_rate": 3e-05,
"loss": 0.1965,
"step": 205000
},
{
"epoch": 1.23,
"learning_rate": 3e-05,
"loss": 0.1955,
"step": 205500
},
{
"epoch": 1.23,
"learning_rate": 3e-05,
"loss": 0.195,
"step": 206000
},
{
"epoch": 1.23,
"learning_rate": 3e-05,
"loss": 0.1962,
"step": 206500
},
{
"epoch": 1.24,
"learning_rate": 3e-05,
"loss": 0.1963,
"step": 207000
},
{
"epoch": 1.24,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 207500
},
{
"epoch": 1.24,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 208000
},
{
"epoch": 1.25,
"learning_rate": 3e-05,
"loss": 0.1957,
"step": 208500
},
{
"epoch": 1.25,
"learning_rate": 3e-05,
"loss": 0.1958,
"step": 209000
},
{
"epoch": 1.25,
"learning_rate": 3e-05,
"loss": 0.1958,
"step": 209500
},
{
"epoch": 1.25,
"learning_rate": 3e-05,
"loss": 0.1962,
"step": 210000
},
{
"epoch": 1.26,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 210500
},
{
"epoch": 1.26,
"learning_rate": 3e-05,
"loss": 0.195,
"step": 211000
},
{
"epoch": 1.26,
"learning_rate": 3e-05,
"loss": 0.1955,
"step": 211500
},
{
"epoch": 1.27,
"learning_rate": 3e-05,
"loss": 0.1962,
"step": 212000
},
{
"epoch": 1.27,
"learning_rate": 3e-05,
"loss": 0.1959,
"step": 212500
},
{
"epoch": 1.27,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 213000
},
{
"epoch": 1.27,
"learning_rate": 3e-05,
"loss": 0.1944,
"step": 213500
},
{
"epoch": 1.28,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 214000
},
{
"epoch": 1.28,
"learning_rate": 3e-05,
"loss": 0.1958,
"step": 214500
},
{
"epoch": 1.28,
"learning_rate": 3e-05,
"loss": 0.1952,
"step": 215000
},
{
"epoch": 1.29,
"learning_rate": 3e-05,
"loss": 0.1945,
"step": 215500
},
{
"epoch": 1.29,
"learning_rate": 3e-05,
"loss": 0.196,
"step": 216000
},
{
"epoch": 1.29,
"learning_rate": 3e-05,
"loss": 0.196,
"step": 216500
},
{
"epoch": 1.3,
"learning_rate": 3e-05,
"loss": 0.1957,
"step": 217000
},
{
"epoch": 1.3,
"learning_rate": 3e-05,
"loss": 0.1956,
"step": 217500
},
{
"epoch": 1.3,
"learning_rate": 3e-05,
"loss": 0.1956,
"step": 218000
},
{
"epoch": 1.3,
"learning_rate": 3e-05,
"loss": 0.196,
"step": 218500
},
{
"epoch": 1.31,
"learning_rate": 3e-05,
"loss": 0.1952,
"step": 219000
},
{
"epoch": 1.31,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 219500
},
{
"epoch": 1.31,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 220000
},
{
"epoch": 1.32,
"learning_rate": 3e-05,
"loss": 0.1955,
"step": 220500
},
{
"epoch": 1.32,
"learning_rate": 3e-05,
"loss": 0.1953,
"step": 221000
},
{
"epoch": 1.32,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 221500
},
{
"epoch": 1.33,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 222000
},
{
"epoch": 1.33,
"learning_rate": 3e-05,
"loss": 0.1948,
"step": 222500
},
{
"epoch": 1.33,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 223000
},
{
"epoch": 1.33,
"learning_rate": 3e-05,
"loss": 0.1957,
"step": 223500
},
{
"epoch": 1.34,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 224000
},
{
"epoch": 1.34,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 224500
},
{
"epoch": 1.34,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 225000
},
{
"epoch": 1.35,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 225500
},
{
"epoch": 1.35,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 226000
},
{
"epoch": 1.35,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 226500
},
{
"epoch": 1.36,
"learning_rate": 3e-05,
"loss": 0.1952,
"step": 227000
},
{
"epoch": 1.36,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 227500
},
{
"epoch": 1.36,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 228000
},
{
"epoch": 1.36,
"learning_rate": 3e-05,
"loss": 0.194,
"step": 228500
},
{
"epoch": 1.37,
"learning_rate": 3e-05,
"loss": 0.1939,
"step": 229000
},
{
"epoch": 1.37,
"learning_rate": 3e-05,
"loss": 0.1948,
"step": 229500
},
{
"epoch": 1.37,
"learning_rate": 3e-05,
"loss": 0.1944,
"step": 230000
},
{
"epoch": 1.38,
"learning_rate": 3e-05,
"loss": 0.1946,
"step": 230500
},
{
"epoch": 1.38,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 231000
},
{
"epoch": 1.38,
"learning_rate": 3e-05,
"loss": 0.1935,
"step": 231500
},
{
"epoch": 1.39,
"learning_rate": 3e-05,
"loss": 0.1944,
"step": 232000
},
{
"epoch": 1.39,
"learning_rate": 3e-05,
"loss": 0.1941,
"step": 232500
},
{
"epoch": 1.39,
"learning_rate": 3e-05,
"loss": 0.1952,
"step": 233000
},
{
"epoch": 1.39,
"learning_rate": 3e-05,
"loss": 0.1936,
"step": 233500
},
{
"epoch": 1.4,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 234000
},
{
"epoch": 1.4,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 234500
},
{
"epoch": 1.4,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 235000
},
{
"epoch": 1.41,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 235500
},
{
"epoch": 1.41,
"learning_rate": 3e-05,
"loss": 0.1936,
"step": 236000
},
{
"epoch": 1.41,
"learning_rate": 3e-05,
"loss": 0.1936,
"step": 236500
},
{
"epoch": 1.42,
"learning_rate": 3e-05,
"loss": 0.1946,
"step": 237000
},
{
"epoch": 1.42,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 237500
},
{
"epoch": 1.42,
"learning_rate": 3e-05,
"loss": 0.1942,
"step": 238000
},
{
"epoch": 1.42,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 238500
},
{
"epoch": 1.43,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 239000
},
{
"epoch": 1.43,
"learning_rate": 3e-05,
"loss": 0.1939,
"step": 239500
},
{
"epoch": 1.43,
"learning_rate": 3e-05,
"loss": 0.1947,
"step": 240000
},
{
"epoch": 1.44,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 240500
},
{
"epoch": 1.44,
"learning_rate": 3e-05,
"loss": 0.1936,
"step": 241000
},
{
"epoch": 1.44,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 241500
},
{
"epoch": 1.45,
"learning_rate": 3e-05,
"loss": 0.1942,
"step": 242000
},
{
"epoch": 1.45,
"learning_rate": 3e-05,
"loss": 0.1931,
"step": 242500
},
{
"epoch": 1.45,
"learning_rate": 3e-05,
"loss": 0.1932,
"step": 243000
},
{
"epoch": 1.45,
"learning_rate": 3e-05,
"loss": 0.1938,
"step": 243500
},
{
"epoch": 1.46,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 244000
},
{
"epoch": 1.46,
"learning_rate": 3e-05,
"loss": 0.1941,
"step": 244500
},
{
"epoch": 1.46,
"learning_rate": 3e-05,
"loss": 0.1941,
"step": 245000
},
{
"epoch": 1.47,
"learning_rate": 3e-05,
"loss": 0.1935,
"step": 245500
},
{
"epoch": 1.47,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 246000
},
{
"epoch": 1.47,
"learning_rate": 3e-05,
"loss": 0.1931,
"step": 246500
},
{
"epoch": 1.48,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 247000
},
{
"epoch": 1.48,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 247500
},
{
"epoch": 1.48,
"learning_rate": 3e-05,
"loss": 0.1925,
"step": 248000
},
{
"epoch": 1.48,
"learning_rate": 3e-05,
"loss": 0.1929,
"step": 248500
},
{
"epoch": 1.49,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 249000
},
{
"epoch": 1.49,
"learning_rate": 3e-05,
"loss": 0.1932,
"step": 249500
},
{
"epoch": 1.49,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 250000
},
{
"epoch": 1.5,
"learning_rate": 3e-05,
"loss": 0.1938,
"step": 250500
},
{
"epoch": 1.5,
"learning_rate": 3e-05,
"loss": 0.1942,
"step": 251000
},
{
"epoch": 1.5,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 251500
},
{
"epoch": 1.5,
"learning_rate": 3e-05,
"loss": 0.1945,
"step": 252000
},
{
"epoch": 1.51,
"learning_rate": 3e-05,
"loss": 0.1926,
"step": 252500
},
{
"epoch": 1.51,
"learning_rate": 3e-05,
"loss": 0.1935,
"step": 253000
},
{
"epoch": 1.51,
"learning_rate": 3e-05,
"loss": 0.1931,
"step": 253500
},
{
"epoch": 1.52,
"learning_rate": 3e-05,
"loss": 0.1925,
"step": 254000
},
{
"epoch": 1.52,
"learning_rate": 3e-05,
"loss": 0.193,
"step": 254500
},
{
"epoch": 1.52,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 255000
},
{
"epoch": 1.53,
"learning_rate": 3e-05,
"loss": 0.1933,
"step": 255500
},
{
"epoch": 1.53,
"learning_rate": 3e-05,
"loss": 0.1927,
"step": 256000
},
{
"epoch": 1.53,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 256500
},
{
"epoch": 1.53,
"learning_rate": 3e-05,
"loss": 0.1933,
"step": 257000
},
{
"epoch": 1.54,
"learning_rate": 3e-05,
"loss": 0.1933,
"step": 257500
},
{
"epoch": 1.54,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 258000
},
{
"epoch": 1.54,
"learning_rate": 3e-05,
"loss": 0.1912,
"step": 258500
},
{
"epoch": 1.55,
"learning_rate": 3e-05,
"loss": 0.1926,
"step": 259000
},
{
"epoch": 1.55,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 259500
},
{
"epoch": 1.55,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 260000
},
{
"epoch": 1.56,
"learning_rate": 3e-05,
"loss": 0.1929,
"step": 260500
},
{
"epoch": 1.56,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 261000
},
{
"epoch": 1.56,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 261500
},
{
"epoch": 1.56,
"learning_rate": 3e-05,
"loss": 0.193,
"step": 262000
},
{
"epoch": 1.57,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 262500
},
{
"epoch": 1.57,
"learning_rate": 3e-05,
"loss": 0.1935,
"step": 263000
},
{
"epoch": 1.57,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 263500
},
{
"epoch": 1.58,
"learning_rate": 3e-05,
"loss": 0.1922,
"step": 264000
},
{
"epoch": 1.58,
"learning_rate": 3e-05,
"loss": 0.193,
"step": 264500
},
{
"epoch": 1.58,
"learning_rate": 3e-05,
"loss": 0.1931,
"step": 265000
},
{
"epoch": 1.59,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 265500
},
{
"epoch": 1.59,
"learning_rate": 3e-05,
"loss": 0.1929,
"step": 266000
},
{
"epoch": 1.59,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 266500
},
{
"epoch": 1.59,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 267000
},
{
"epoch": 1.6,
"learning_rate": 3e-05,
"loss": 0.1919,
"step": 267500
},
{
"epoch": 1.6,
"learning_rate": 3e-05,
"loss": 0.1927,
"step": 268000
},
{
"epoch": 1.6,
"learning_rate": 3e-05,
"loss": 0.1914,
"step": 268500
},
{
"epoch": 1.61,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 269000
},
{
"epoch": 1.61,
"learning_rate": 3e-05,
"loss": 0.1928,
"step": 269500
},
{
"epoch": 1.61,
"learning_rate": 3e-05,
"loss": 0.1929,
"step": 270000
},
{
"epoch": 1.62,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 270500
},
{
"epoch": 1.62,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 271000
},
{
"epoch": 1.62,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 271500
},
{
"epoch": 1.62,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 272000
},
{
"epoch": 1.63,
"learning_rate": 3e-05,
"loss": 0.1926,
"step": 272500
},
{
"epoch": 1.63,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 273000
},
{
"epoch": 1.63,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 273500
},
{
"epoch": 1.64,
"learning_rate": 3e-05,
"loss": 0.1932,
"step": 274000
},
{
"epoch": 1.64,
"learning_rate": 3e-05,
"loss": 0.1919,
"step": 274500
},
{
"epoch": 1.64,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 275000
},
{
"epoch": 1.65,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 275500
},
{
"epoch": 1.65,
"learning_rate": 3e-05,
"loss": 0.1919,
"step": 276000
},
{
"epoch": 1.65,
"learning_rate": 3e-05,
"loss": 0.191,
"step": 276500
},
{
"epoch": 1.65,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 277000
},
{
"epoch": 1.66,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 277500
},
{
"epoch": 1.66,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 278000
},
{
"epoch": 1.66,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 278500
},
{
"epoch": 1.67,
"learning_rate": 3e-05,
"loss": 0.1919,
"step": 279000
},
{
"epoch": 1.67,
"learning_rate": 3e-05,
"loss": 0.1914,
"step": 279500
},
{
"epoch": 1.67,
"learning_rate": 3e-05,
"loss": 0.1917,
"step": 280000
},
{
"epoch": 1.68,
"learning_rate": 3e-05,
"loss": 0.1919,
"step": 280500
},
{
"epoch": 1.68,
"learning_rate": 3e-05,
"loss": 0.1913,
"step": 281000
},
{
"epoch": 1.68,
"learning_rate": 3e-05,
"loss": 0.1915,
"step": 281500
},
{
"epoch": 1.68,
"learning_rate": 3e-05,
"loss": 0.1912,
"step": 282000
},
{
"epoch": 1.69,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 282500
},
{
"epoch": 1.69,
"learning_rate": 3e-05,
"loss": 0.1918,
"step": 283000
},
{
"epoch": 1.69,
"learning_rate": 3e-05,
"loss": 0.191,
"step": 283500
},
{
"epoch": 1.7,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 284000
},
{
"epoch": 1.7,
"learning_rate": 3e-05,
"loss": 0.1915,
"step": 284500
},
{
"epoch": 1.7,
"learning_rate": 3e-05,
"loss": 0.1917,
"step": 285000
},
{
"epoch": 1.7,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 285500
},
{
"epoch": 1.71,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 286000
},
{
"epoch": 1.71,
"learning_rate": 3e-05,
"loss": 0.1908,
"step": 286500
},
{
"epoch": 1.71,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 287000
},
{
"epoch": 1.72,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 287500
},
{
"epoch": 1.72,
"learning_rate": 3e-05,
"loss": 0.1925,
"step": 288000
},
{
"epoch": 1.72,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 288500
},
{
"epoch": 1.73,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 289000
},
{
"epoch": 1.73,
"learning_rate": 3e-05,
"loss": 0.1913,
"step": 289500
},
{
"epoch": 1.73,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 290000
},
{
"epoch": 1.73,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 290500
},
{
"epoch": 1.74,
"learning_rate": 3e-05,
"loss": 0.191,
"step": 291000
},
{
"epoch": 1.74,
"learning_rate": 3e-05,
"loss": 0.1912,
"step": 291500
},
{
"epoch": 1.74,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 292000
},
{
"epoch": 1.75,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 292500
},
{
"epoch": 1.75,
"learning_rate": 3e-05,
"loss": 0.1923,
"step": 293000
},
{
"epoch": 1.75,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 293500
},
{
"epoch": 1.76,
"learning_rate": 3e-05,
"loss": 0.1914,
"step": 294000
},
{
"epoch": 1.76,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 294500
},
{
"epoch": 1.76,
"learning_rate": 3e-05,
"loss": 0.1908,
"step": 295000
},
{
"epoch": 1.76,
"learning_rate": 3e-05,
"loss": 0.1897,
"step": 295500
},
{
"epoch": 1.77,
"learning_rate": 3e-05,
"loss": 0.1913,
"step": 296000
},
{
"epoch": 1.77,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 296500
},
{
"epoch": 1.77,
"learning_rate": 3e-05,
"loss": 0.1912,
"step": 297000
},
{
"epoch": 1.78,
"learning_rate": 3e-05,
"loss": 0.1908,
"step": 297500
},
{
"epoch": 1.78,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 298000
},
{
"epoch": 1.78,
"learning_rate": 3e-05,
"loss": 0.1914,
"step": 298500
},
{
"epoch": 1.79,
"learning_rate": 3e-05,
"loss": 0.1907,
"step": 299000
},
{
"epoch": 1.79,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 299500
},
{
"epoch": 1.79,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 300000
},
{
"epoch": 1.79,
"learning_rate": 3e-05,
"loss": 0.1899,
"step": 300500
},
{
"epoch": 1.8,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 301000
},
{
"epoch": 1.8,
"learning_rate": 3e-05,
"loss": 0.1908,
"step": 301500
},
{
"epoch": 1.8,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 302000
},
{
"epoch": 1.81,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 302500
},
{
"epoch": 1.81,
"learning_rate": 3e-05,
"loss": 0.1904,
"step": 303000
},
{
"epoch": 1.81,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 303500
},
{
"epoch": 1.82,
"learning_rate": 3e-05,
"loss": 0.1896,
"step": 304000
},
{
"epoch": 1.82,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 304500
},
{
"epoch": 1.82,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 305000
},
{
"epoch": 1.82,
"learning_rate": 3e-05,
"loss": 0.1899,
"step": 305500
},
{
"epoch": 1.83,
"learning_rate": 3e-05,
"loss": 0.1913,
"step": 306000
},
{
"epoch": 1.83,
"learning_rate": 3e-05,
"loss": 0.1907,
"step": 306500
},
{
"epoch": 1.83,
"learning_rate": 3e-05,
"loss": 0.1904,
"step": 307000
},
{
"epoch": 1.84,
"learning_rate": 3e-05,
"loss": 0.1901,
"step": 307500
},
{
"epoch": 1.84,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 308000
},
{
"epoch": 1.84,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 308500
},
{
"epoch": 1.85,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 309000
},
{
"epoch": 1.85,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 309500
},
{
"epoch": 1.85,
"learning_rate": 3e-05,
"loss": 0.19,
"step": 310000
},
{
"epoch": 1.85,
"learning_rate": 3e-05,
"loss": 0.19,
"step": 310500
},
{
"epoch": 1.86,
"learning_rate": 3e-05,
"loss": 0.191,
"step": 311000
},
{
"epoch": 1.86,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 311500
},
{
"epoch": 1.86,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 312000
},
{
"epoch": 1.87,
"learning_rate": 3e-05,
"loss": 0.1897,
"step": 312500
},
{
"epoch": 1.87,
"learning_rate": 3e-05,
"loss": 0.1902,
"step": 313000
},
{
"epoch": 1.87,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 313500
},
{
"epoch": 1.88,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 314000
},
{
"epoch": 1.88,
"learning_rate": 3e-05,
"loss": 0.1886,
"step": 314500
},
{
"epoch": 1.88,
"learning_rate": 3e-05,
"loss": 0.189,
"step": 315000
},
{
"epoch": 1.88,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 315500
},
{
"epoch": 1.89,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 316000
},
{
"epoch": 1.89,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 316500
},
{
"epoch": 1.89,
"learning_rate": 3e-05,
"loss": 0.1899,
"step": 317000
},
{
"epoch": 1.9,
"learning_rate": 3e-05,
"loss": 0.1891,
"step": 317500
},
{
"epoch": 1.9,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 318000
},
{
"epoch": 1.9,
"learning_rate": 3e-05,
"loss": 0.1892,
"step": 318500
},
{
"epoch": 1.9,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 319000
},
{
"epoch": 1.91,
"learning_rate": 3e-05,
"loss": 0.189,
"step": 319500
},
{
"epoch": 1.91,
"learning_rate": 3e-05,
"loss": 0.1904,
"step": 320000
},
{
"epoch": 1.91,
"learning_rate": 3e-05,
"loss": 0.1901,
"step": 320500
},
{
"epoch": 1.92,
"learning_rate": 3e-05,
"loss": 0.1894,
"step": 321000
},
{
"epoch": 1.92,
"learning_rate": 3e-05,
"loss": 0.1904,
"step": 321500
},
{
"epoch": 1.92,
"learning_rate": 3e-05,
"loss": 0.1905,
"step": 322000
},
{
"epoch": 1.93,
"learning_rate": 3e-05,
"loss": 0.1896,
"step": 322500
},
{
"epoch": 1.93,
"learning_rate": 3e-05,
"loss": 0.1886,
"step": 323000
},
{
"epoch": 1.93,
"learning_rate": 3e-05,
"loss": 0.1907,
"step": 323500
},
{
"epoch": 1.93,
"learning_rate": 3e-05,
"loss": 0.1891,
"step": 324000
},
{
"epoch": 1.94,
"learning_rate": 3e-05,
"loss": 0.1893,
"step": 324500
},
{
"epoch": 1.94,
"learning_rate": 3e-05,
"loss": 0.1889,
"step": 325000
},
{
"epoch": 1.94,
"learning_rate": 3e-05,
"loss": 0.1895,
"step": 325500
},
{
"epoch": 1.95,
"learning_rate": 3e-05,
"loss": 0.1894,
"step": 326000
},
{
"epoch": 1.95,
"learning_rate": 3e-05,
"loss": 0.1893,
"step": 326500
},
{
"epoch": 1.95,
"learning_rate": 3e-05,
"loss": 0.1899,
"step": 327000
},
{
"epoch": 1.96,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 327500
},
{
"epoch": 1.96,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 328000
},
{
"epoch": 1.96,
"learning_rate": 3e-05,
"loss": 0.1894,
"step": 328500
},
{
"epoch": 1.96,
"learning_rate": 3e-05,
"loss": 0.1893,
"step": 329000
},
{
"epoch": 1.97,
"learning_rate": 3e-05,
"loss": 0.1891,
"step": 329500
},
{
"epoch": 1.97,
"learning_rate": 3e-05,
"loss": 0.1895,
"step": 330000
},
{
"epoch": 1.97,
"learning_rate": 3e-05,
"loss": 0.1903,
"step": 330500
},
{
"epoch": 1.98,
"learning_rate": 3e-05,
"loss": 0.19,
"step": 331000
},
{
"epoch": 1.98,
"learning_rate": 3e-05,
"loss": 0.1895,
"step": 331500
},
{
"epoch": 1.98,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 332000
},
{
"epoch": 1.99,
"learning_rate": 3e-05,
"loss": 0.1897,
"step": 332500
},
{
"epoch": 1.99,
"learning_rate": 3e-05,
"loss": 0.188,
"step": 333000
},
{
"epoch": 1.99,
"learning_rate": 3e-05,
"loss": 0.189,
"step": 333500
},
{
"epoch": 1.99,
"learning_rate": 3e-05,
"loss": 0.1894,
"step": 334000
},
{
"epoch": 2.0,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 334500
},
{
"epoch": 2.0,
"learning_rate": 3e-05,
"loss": 0.19,
"step": 335000
},
{
"epoch": 2.0,
"learning_rate": 3e-05,
"loss": 0.1888,
"step": 335500
},
{
"epoch": 2.01,
"learning_rate": 3e-05,
"loss": 0.1896,
"step": 336000
},
{
"epoch": 2.01,
"learning_rate": 3e-05,
"loss": 0.1893,
"step": 336500
},
{
"epoch": 2.01,
"learning_rate": 3e-05,
"loss": 0.1899,
"step": 337000
},
{
"epoch": 2.02,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 337500
},
{
"epoch": 2.02,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 338000
},
{
"epoch": 2.02,
"learning_rate": 3e-05,
"loss": 0.19,
"step": 338500
},
{
"epoch": 2.02,
"learning_rate": 3e-05,
"loss": 0.1915,
"step": 339000
},
{
"epoch": 2.03,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 339500
},
{
"epoch": 2.03,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 340000
},
{
"epoch": 2.03,
"learning_rate": 3e-05,
"loss": 0.1902,
"step": 340500
},
{
"epoch": 2.04,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 341000
},
{
"epoch": 2.04,
"learning_rate": 3e-05,
"loss": 0.1898,
"step": 341500
},
{
"epoch": 2.04,
"learning_rate": 3e-05,
"loss": 0.1896,
"step": 342000
},
{
"epoch": 2.05,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 342500
},
{
"epoch": 2.05,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 343000
},
{
"epoch": 2.05,
"learning_rate": 3e-05,
"loss": 0.1906,
"step": 343500
},
{
"epoch": 2.05,
"learning_rate": 3e-05,
"loss": 0.192,
"step": 344000
},
{
"epoch": 2.06,
"learning_rate": 3e-05,
"loss": 0.1918,
"step": 344500
},
{
"epoch": 2.06,
"learning_rate": 3e-05,
"loss": 0.1909,
"step": 345000
},
{
"epoch": 2.06,
"learning_rate": 3e-05,
"loss": 0.1916,
"step": 345500
},
{
"epoch": 2.07,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 346000
},
{
"epoch": 2.07,
"learning_rate": 3e-05,
"loss": 0.1911,
"step": 346500
},
{
"epoch": 2.07,
"learning_rate": 3e-05,
"loss": 0.1915,
"step": 347000
},
{
"epoch": 2.08,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 347500
},
{
"epoch": 2.08,
"learning_rate": 3e-05,
"loss": 0.1921,
"step": 348000
},
{
"epoch": 2.08,
"learning_rate": 3e-05,
"loss": 0.1927,
"step": 348500
},
{
"epoch": 2.08,
"learning_rate": 3e-05,
"loss": 0.1924,
"step": 349000
},
{
"epoch": 2.09,
"learning_rate": 3e-05,
"loss": 0.1936,
"step": 349500
},
{
"epoch": 2.09,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 350000
},
{
"epoch": 2.09,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 350500
},
{
"epoch": 2.1,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 351000
},
{
"epoch": 2.1,
"learning_rate": 3e-05,
"loss": 0.1934,
"step": 351500
},
{
"epoch": 2.1,
"learning_rate": 3e-05,
"loss": 0.1937,
"step": 352000
},
{
"epoch": 2.11,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 352500
},
{
"epoch": 2.11,
"learning_rate": 3e-05,
"loss": 0.1925,
"step": 353000
},
{
"epoch": 2.11,
"learning_rate": 3e-05,
"loss": 0.1942,
"step": 353500
},
{
"epoch": 2.11,
"learning_rate": 3e-05,
"loss": 0.1946,
"step": 354000
},
{
"epoch": 2.12,
"learning_rate": 3e-05,
"loss": 0.1949,
"step": 354500
},
{
"epoch": 2.12,
"learning_rate": 3e-05,
"loss": 0.1946,
"step": 355000
},
{
"epoch": 2.12,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 355500
},
{
"epoch": 2.13,
"learning_rate": 3e-05,
"loss": 0.1944,
"step": 356000
},
{
"epoch": 2.13,
"learning_rate": 3e-05,
"loss": 0.1945,
"step": 356500
},
{
"epoch": 2.13,
"learning_rate": 3e-05,
"loss": 0.1941,
"step": 357000
},
{
"epoch": 2.13,
"learning_rate": 3e-05,
"loss": 0.1943,
"step": 357500
},
{
"epoch": 2.14,
"learning_rate": 3e-05,
"loss": 0.1955,
"step": 358000
},
{
"epoch": 2.14,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 358500
},
{
"epoch": 2.14,
"learning_rate": 3e-05,
"loss": 0.1951,
"step": 359000
},
{
"epoch": 2.15,
"learning_rate": 3e-05,
"loss": 0.1956,
"step": 359500
},
{
"epoch": 2.15,
"learning_rate": 3e-05,
"loss": 0.1956,
"step": 360000
},
{
"epoch": 2.15,
"learning_rate": 3e-05,
"loss": 0.1967,
"step": 360500
},
{
"epoch": 2.16,
"learning_rate": 3e-05,
"loss": 0.1954,
"step": 361000
},
{
"epoch": 2.16,
"learning_rate": 3e-05,
"loss": 0.1959,
"step": 361500
},
{
"epoch": 2.16,
"learning_rate": 3e-05,
"loss": 0.1958,
"step": 362000
},
{
"epoch": 2.16,
"learning_rate": 3e-05,
"loss": 0.1953,
"step": 362500
},
{
"epoch": 2.17,
"learning_rate": 3e-05,
"loss": 0.1962,
"step": 363000
},
{
"epoch": 2.17,
"learning_rate": 3e-05,
"loss": 0.1967,
"step": 363500
},
{
"epoch": 2.17,
"learning_rate": 3e-05,
"loss": 0.1958,
"step": 364000
},
{
"epoch": 2.18,
"learning_rate": 3e-05,
"loss": 0.1962,
"step": 364500
},
{
"epoch": 2.18,
"learning_rate": 3e-05,
"loss": 0.1965,
"step": 365000
},
{
"epoch": 2.18,
"learning_rate": 3e-05,
"loss": 0.1963,
"step": 365500
},
{
"epoch": 2.19,
"learning_rate": 3e-05,
"loss": 0.1967,
"step": 366000
},
{
"epoch": 2.19,
"learning_rate": 3e-05,
"loss": 0.1969,
"step": 366500
},
{
"epoch": 2.19,
"learning_rate": 3e-05,
"loss": 0.1964,
"step": 367000
},
{
"epoch": 2.19,
"learning_rate": 3e-05,
"loss": 0.1964,
"step": 367500
},
{
"epoch": 2.2,
"learning_rate": 3e-05,
"loss": 0.196,
"step": 368000
},
{
"epoch": 2.2,
"learning_rate": 3e-05,
"loss": 0.1974,
"step": 368500
},
{
"epoch": 2.2,
"learning_rate": 3e-05,
"loss": 0.1966,
"step": 369000
},
{
"epoch": 2.21,
"learning_rate": 3e-05,
"loss": 0.1977,
"step": 369500
},
{
"epoch": 2.21,
"learning_rate": 3e-05,
"loss": 0.1964,
"step": 370000
},
{
"epoch": 2.21,
"learning_rate": 3e-05,
"loss": 0.1971,
"step": 370500
},
{
"epoch": 2.22,
"learning_rate": 3e-05,
"loss": 0.198,
"step": 371000
},
{
"epoch": 2.22,
"learning_rate": 3e-05,
"loss": 0.1974,
"step": 371500
},
{
"epoch": 2.22,
"learning_rate": 3e-05,
"loss": 0.1979,
"step": 372000
},
{
"epoch": 2.22,
"learning_rate": 3e-05,
"loss": 0.1972,
"step": 372500
},
{
"epoch": 2.23,
"learning_rate": 3e-05,
"loss": 0.1973,
"step": 373000
},
{
"epoch": 2.23,
"learning_rate": 3e-05,
"loss": 0.1975,
"step": 373500
},
{
"epoch": 2.23,
"learning_rate": 3e-05,
"loss": 0.1977,
"step": 374000
},
{
"epoch": 2.24,
"learning_rate": 3e-05,
"loss": 0.1964,
"step": 374500
},
{
"epoch": 2.24,
"learning_rate": 3e-05,
"loss": 0.1982,
"step": 375000
},
{
"epoch": 2.24,
"learning_rate": 3e-05,
"loss": 0.1978,
"step": 375500
},
{
"epoch": 2.25,
"learning_rate": 3e-05,
"loss": 0.1982,
"step": 376000
},
{
"epoch": 2.25,
"learning_rate": 3e-05,
"loss": 0.1978,
"step": 376500
},
{
"epoch": 2.25,
"learning_rate": 3e-05,
"loss": 0.1981,
"step": 377000
},
{
"epoch": 2.25,
"learning_rate": 3e-05,
"loss": 0.1981,
"step": 377500
},
{
"epoch": 2.26,
"learning_rate": 3e-05,
"loss": 0.1986,
"step": 378000
},
{
"epoch": 2.26,
"learning_rate": 3e-05,
"loss": 0.1986,
"step": 378500
},
{
"epoch": 2.26,
"learning_rate": 3e-05,
"loss": 0.1979,
"step": 379000
},
{
"epoch": 2.27,
"learning_rate": 3e-05,
"loss": 0.1975,
"step": 379500
},
{
"epoch": 2.27,
"learning_rate": 3e-05,
"loss": 0.1985,
"step": 380000
},
{
"epoch": 2.27,
"learning_rate": 3e-05,
"loss": 0.199,
"step": 380500
},
{
"epoch": 2.28,
"learning_rate": 3e-05,
"loss": 0.1975,
"step": 381000
},
{
"epoch": 2.28,
"step": 381200,
"total_flos": 2.6616833547962417e+19,
"train_runtime": 9.7313,
"train_samples_per_second": 34415.435
}
],
"max_steps": 334908,
"num_train_epochs": 2,
"total_flos": 2.6616833547962417e+19,
"trial_name": null,
"trial_params": null
}