diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,18106 +1,18136 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 0.9991450102399937, - "global_step": 301500, + "epoch": 0.9997153128579279, + "global_step": 302000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, - "learning_rate": 4.9983430431007635e-05, - "loss": 3.2342, + "learning_rate": 4.9983448421972554e-05, + "loss": 3.2257, "step": 100 }, { "epoch": 0.0, - "learning_rate": 4.996686086201526e-05, - "loss": 3.2296, + "learning_rate": 4.9966896843945106e-05, + "loss": 3.2217, "step": 200 }, { "epoch": 0.0, - "learning_rate": 4.995029129302289e-05, - "loss": 3.2473, + "learning_rate": 4.995034526591765e-05, + "loss": 3.2307, "step": 300 }, { "epoch": 0.0, - "learning_rate": 4.993372172403052e-05, - "loss": 3.2422, + "learning_rate": 4.993379368789021e-05, + "loss": 3.23, "step": 400 }, { "epoch": 0.0, - "learning_rate": 4.9917152155038145e-05, - "loss": 3.2386, + "learning_rate": 4.9917242109862754e-05, + "loss": 3.2364, "step": 500 }, { "epoch": 0.0, - "learning_rate": 4.990058258604578e-05, - "loss": 3.2347, + "learning_rate": 4.990069053183531e-05, + "loss": 3.2179, "step": 600 }, { "epoch": 0.0, - "learning_rate": 4.9884013017053403e-05, - "loss": 3.2354, + "learning_rate": 4.988413895380786e-05, + "loss": 3.2401, "step": 700 }, { "epoch": 0.0, - "learning_rate": 4.986744344806103e-05, - "loss": 3.2574, + "learning_rate": 4.986758737578041e-05, + "loss": 3.2259, "step": 800 }, { "epoch": 0.0, - "learning_rate": 4.985087387906866e-05, - "loss": 3.2561, + "learning_rate": 4.985103579775296e-05, + "loss": 3.2405, "step": 900 }, { "epoch": 0.0, - "learning_rate": 4.983430431007629e-05, - "loss": 3.2664, + "learning_rate": 4.983448421972551e-05, + "loss": 3.2286, "step": 1000 }, { "epoch": 0.0, - "learning_rate": 4.9817734741083913e-05, - "loss": 3.251, + "learning_rate": 4.981793264169806e-05, + "loss": 3.2355, "step": 1100 }, { "epoch": 0.0, - "learning_rate": 4.9801165172091546e-05, - "loss": 3.25, + "learning_rate": 4.980138106367061e-05, + "loss": 3.2333, "step": 1200 }, { "epoch": 0.0, - "learning_rate": 4.978459560309918e-05, - "loss": 3.245, + "learning_rate": 4.9784829485643166e-05, + "loss": 3.2257, "step": 1300 }, { "epoch": 0.0, - "learning_rate": 4.9768026034106804e-05, - "loss": 3.2417, + "learning_rate": 4.976827790761571e-05, + "loss": 3.2207, "step": 1400 }, { "epoch": 0.0, - "learning_rate": 4.975145646511443e-05, - "loss": 3.2543, + "learning_rate": 4.975172632958827e-05, + "loss": 3.2243, "step": 1500 }, { "epoch": 0.01, - "learning_rate": 4.973488689612206e-05, - "loss": 3.2517, + "learning_rate": 4.9735174751560814e-05, + "loss": 3.238, "step": 1600 }, { "epoch": 0.01, - "learning_rate": 4.971831732712969e-05, - "loss": 3.2528, + "learning_rate": 4.9718623173533366e-05, + "loss": 3.2202, "step": 1700 }, { "epoch": 0.01, - "learning_rate": 4.970174775813732e-05, - "loss": 3.245, + "learning_rate": 4.970207159550592e-05, + "loss": 3.2387, "step": 1800 }, { "epoch": 0.01, - "learning_rate": 4.968517818914495e-05, - "loss": 3.2543, + "learning_rate": 4.968552001747847e-05, + "loss": 3.234, "step": 1900 }, { "epoch": 0.01, - "learning_rate": 4.966860862015257e-05, - "loss": 3.2626, + "learning_rate": 4.966896843945102e-05, + "loss": 3.2363, "step": 2000 }, { "epoch": 0.01, - "learning_rate": 4.9652039051160206e-05, - "loss": 3.2535, + "learning_rate": 4.965241686142357e-05, + "loss": 3.2244, "step": 2100 }, { "epoch": 0.01, - "learning_rate": 4.963546948216783e-05, - "loss": 3.2511, + "learning_rate": 4.9635865283396124e-05, + "loss": 3.2496, "step": 2200 }, { "epoch": 0.01, - "learning_rate": 4.961889991317546e-05, - "loss": 3.2571, + "learning_rate": 4.961931370536867e-05, + "loss": 3.2291, "step": 2300 }, { "epoch": 0.01, - "learning_rate": 4.960233034418309e-05, - "loss": 3.2549, + "learning_rate": 4.960276212734122e-05, + "loss": 3.2286, "step": 2400 }, { "epoch": 0.01, - "learning_rate": 4.958576077519072e-05, - "loss": 3.2534, + "learning_rate": 4.958621054931377e-05, + "loss": 3.2343, "step": 2500 }, { "epoch": 0.01, - "learning_rate": 4.956919120619835e-05, - "loss": 3.2504, + "learning_rate": 4.9569658971286324e-05, + "loss": 3.2409, "step": 2600 }, { "epoch": 0.01, - "learning_rate": 4.9552621637205974e-05, - "loss": 3.2426, + "learning_rate": 4.9553107393258875e-05, + "loss": 3.2325, "step": 2700 }, { "epoch": 0.01, - "learning_rate": 4.9536052068213607e-05, - "loss": 3.2643, + "learning_rate": 4.953655581523143e-05, + "loss": 3.2311, "step": 2800 }, { "epoch": 0.01, - "learning_rate": 4.951948249922123e-05, - "loss": 3.2465, + "learning_rate": 4.952000423720398e-05, + "loss": 3.2293, "step": 2900 }, { "epoch": 0.01, - "learning_rate": 4.9502912930228865e-05, - "loss": 3.2441, + "learning_rate": 4.950345265917653e-05, + "loss": 3.2224, "step": 3000 }, { "epoch": 0.01, - "learning_rate": 4.948634336123649e-05, - "loss": 3.2632, + "learning_rate": 4.948690108114908e-05, + "loss": 3.2323, "step": 3100 }, { "epoch": 0.01, - "learning_rate": 4.946977379224412e-05, - "loss": 3.249, + "learning_rate": 4.947034950312163e-05, + "loss": 3.2349, "step": 3200 }, { "epoch": 0.01, - "learning_rate": 4.945320422325175e-05, - "loss": 3.2477, + "learning_rate": 4.945379792509418e-05, + "loss": 3.2474, "step": 3300 }, { "epoch": 0.01, - "learning_rate": 4.9436634654259375e-05, - "loss": 3.2559, + "learning_rate": 4.943724634706673e-05, + "loss": 3.2332, "step": 3400 }, { "epoch": 0.01, - "learning_rate": 4.9420065085267e-05, - "loss": 3.2625, + "learning_rate": 4.942069476903928e-05, + "loss": 3.2395, "step": 3500 }, { "epoch": 0.01, - "learning_rate": 4.9403495516274633e-05, - "loss": 3.2528, + "learning_rate": 4.940414319101183e-05, + "loss": 3.2282, "step": 3600 }, { "epoch": 0.01, - "learning_rate": 4.9386925947282266e-05, - "loss": 3.2534, + "learning_rate": 4.9387591612984384e-05, + "loss": 3.2328, "step": 3700 }, { "epoch": 0.01, - "learning_rate": 4.937035637828989e-05, - "loss": 3.2627, + "learning_rate": 4.9371040034956936e-05, + "loss": 3.2273, "step": 3800 }, { "epoch": 0.01, - "learning_rate": 4.935378680929752e-05, - "loss": 3.2487, + "learning_rate": 4.935448845692949e-05, + "loss": 3.2425, "step": 3900 }, { "epoch": 0.01, - "learning_rate": 4.933721724030515e-05, - "loss": 3.2441, + "learning_rate": 4.933793687890203e-05, + "loss": 3.2347, "step": 4000 }, { "epoch": 0.01, - "learning_rate": 4.9320647671312776e-05, - "loss": 3.2566, + "learning_rate": 4.932138530087459e-05, + "loss": 3.248, "step": 4100 }, { "epoch": 0.01, - "learning_rate": 4.930407810232041e-05, - "loss": 3.2602, + "learning_rate": 4.9304833722847136e-05, + "loss": 3.2292, "step": 4200 }, { "epoch": 0.01, - "learning_rate": 4.9287508533328035e-05, - "loss": 3.2599, + "learning_rate": 4.9288282144819694e-05, + "loss": 3.2293, "step": 4300 }, { "epoch": 0.01, - "learning_rate": 4.927093896433566e-05, - "loss": 3.2581, + "learning_rate": 4.927173056679224e-05, + "loss": 3.2343, "step": 4400 }, { "epoch": 0.01, - "learning_rate": 4.925436939534329e-05, - "loss": 3.245, + "learning_rate": 4.925517898876479e-05, + "loss": 3.2426, "step": 4500 }, { "epoch": 0.02, - "learning_rate": 4.923779982635092e-05, - "loss": 3.2707, + "learning_rate": 4.923862741073734e-05, + "loss": 3.2377, "step": 4600 }, { "epoch": 0.02, - "learning_rate": 4.9221230257358545e-05, - "loss": 3.2542, + "learning_rate": 4.9222075832709894e-05, + "loss": 3.225, "step": 4700 }, { "epoch": 0.02, - "learning_rate": 4.920466068836618e-05, - "loss": 3.2618, + "learning_rate": 4.9205524254682445e-05, + "loss": 3.2388, "step": 4800 }, { "epoch": 0.02, - "learning_rate": 4.91880911193738e-05, - "loss": 3.2384, + "learning_rate": 4.918897267665499e-05, + "loss": 3.2369, "step": 4900 }, { "epoch": 0.02, - "learning_rate": 4.9171521550381436e-05, - "loss": 3.2547, + "learning_rate": 4.917242109862755e-05, + "loss": 3.239, "step": 5000 }, { "epoch": 0.02, - "learning_rate": 4.915495198138906e-05, - "loss": 3.247, + "learning_rate": 4.915586952060009e-05, + "loss": 3.244, "step": 5100 }, { "epoch": 0.02, - "learning_rate": 4.913838241239669e-05, - "loss": 3.2497, + "learning_rate": 4.913931794257265e-05, + "loss": 3.2302, "step": 5200 }, { "epoch": 0.02, - "learning_rate": 4.912181284340432e-05, - "loss": 3.2488, + "learning_rate": 4.9122766364545197e-05, + "loss": 3.2378, "step": 5300 }, { "epoch": 0.02, - "learning_rate": 4.910524327441195e-05, - "loss": 3.2555, + "learning_rate": 4.910621478651775e-05, + "loss": 3.2281, "step": 5400 }, { "epoch": 0.02, - "learning_rate": 4.908867370541957e-05, - "loss": 3.2479, + "learning_rate": 4.90896632084903e-05, + "loss": 3.2336, "step": 5500 }, { "epoch": 0.02, - "learning_rate": 4.9072104136427204e-05, - "loss": 3.2523, + "learning_rate": 4.907311163046285e-05, + "loss": 3.2253, "step": 5600 }, { "epoch": 0.02, - "learning_rate": 4.905553456743484e-05, - "loss": 3.2423, + "learning_rate": 4.90565600524354e-05, + "loss": 3.2363, "step": 5700 }, { "epoch": 0.02, - "learning_rate": 4.903896499844246e-05, - "loss": 3.2508, + "learning_rate": 4.904000847440795e-05, + "loss": 3.2449, "step": 5800 }, { "epoch": 0.02, - "learning_rate": 4.902239542945009e-05, - "loss": 3.2563, + "learning_rate": 4.9023456896380506e-05, + "loss": 3.2388, "step": 5900 }, { "epoch": 0.02, - "learning_rate": 4.900582586045772e-05, - "loss": 3.2491, + "learning_rate": 4.900690531835305e-05, + "loss": 3.2311, "step": 6000 }, { "epoch": 0.02, - "learning_rate": 4.898925629146535e-05, - "loss": 3.2463, + "learning_rate": 4.899035374032561e-05, + "loss": 3.2261, "step": 6100 }, { "epoch": 0.02, - "learning_rate": 4.897268672247298e-05, - "loss": 3.2567, + "learning_rate": 4.8973802162298154e-05, + "loss": 3.2186, "step": 6200 }, { "epoch": 0.02, - "learning_rate": 4.8956117153480605e-05, - "loss": 3.2525, + "learning_rate": 4.8957250584270706e-05, + "loss": 3.2502, "step": 6300 }, { "epoch": 0.02, - "learning_rate": 4.893954758448823e-05, - "loss": 3.2581, + "learning_rate": 4.894069900624326e-05, + "loss": 3.2358, "step": 6400 }, { "epoch": 0.02, - "learning_rate": 4.8922978015495863e-05, - "loss": 3.2604, + "learning_rate": 4.892414742821581e-05, + "loss": 3.2307, "step": 6500 }, { "epoch": 0.02, - "learning_rate": 4.8906408446503496e-05, - "loss": 3.2602, + "learning_rate": 4.890759585018836e-05, + "loss": 3.221, "step": 6600 }, { "epoch": 0.02, - "learning_rate": 4.8889838877511115e-05, - "loss": 3.2515, + "learning_rate": 4.8891044272160905e-05, + "loss": 3.2406, "step": 6700 }, { "epoch": 0.02, - "learning_rate": 4.887326930851875e-05, - "loss": 3.258, + "learning_rate": 4.8874492694133464e-05, + "loss": 3.2378, "step": 6800 }, { "epoch": 0.02, - "learning_rate": 4.885669973952638e-05, - "loss": 3.2555, + "learning_rate": 4.885794111610601e-05, + "loss": 3.2395, "step": 6900 }, { "epoch": 0.02, - "learning_rate": 4.8840130170534006e-05, - "loss": 3.2389, + "learning_rate": 4.884138953807856e-05, + "loss": 3.2302, "step": 7000 }, { "epoch": 0.02, - "learning_rate": 4.882356060154163e-05, - "loss": 3.2564, + "learning_rate": 4.882483796005111e-05, + "loss": 3.2328, "step": 7100 }, { "epoch": 0.02, - "learning_rate": 4.8806991032549265e-05, - "loss": 3.2473, + "learning_rate": 4.8808286382023663e-05, + "loss": 3.2389, "step": 7200 }, { "epoch": 0.02, - "learning_rate": 4.879042146355689e-05, - "loss": 3.2543, + "learning_rate": 4.8791734803996215e-05, + "loss": 3.2375, "step": 7300 }, { "epoch": 0.02, - "learning_rate": 4.877385189456452e-05, - "loss": 3.2445, + "learning_rate": 4.8775183225968767e-05, + "loss": 3.2292, "step": 7400 }, { "epoch": 0.02, - "learning_rate": 4.875728232557215e-05, - "loss": 3.2538, + "learning_rate": 4.875863164794132e-05, + "loss": 3.2326, "step": 7500 }, { "epoch": 0.03, - "learning_rate": 4.8740712756579775e-05, - "loss": 3.2585, + "learning_rate": 4.874208006991387e-05, + "loss": 3.2364, "step": 7600 }, { "epoch": 0.03, - "learning_rate": 4.872414318758741e-05, - "loss": 3.2591, + "learning_rate": 4.872552849188642e-05, + "loss": 3.2421, "step": 7700 }, { "epoch": 0.03, - "learning_rate": 4.870757361859504e-05, - "loss": 3.2531, + "learning_rate": 4.8708976913858966e-05, + "loss": 3.2427, "step": 7800 }, { "epoch": 0.03, - "learning_rate": 4.869100404960266e-05, - "loss": 3.2597, + "learning_rate": 4.869242533583152e-05, + "loss": 3.2228, "step": 7900 }, { "epoch": 0.03, - "learning_rate": 4.867443448061029e-05, - "loss": 3.2583, + "learning_rate": 4.867587375780407e-05, + "loss": 3.2507, "step": 8000 }, { "epoch": 0.03, - "learning_rate": 4.8657864911617924e-05, - "loss": 3.2595, + "learning_rate": 4.865932217977662e-05, + "loss": 3.2225, "step": 8100 }, { "epoch": 0.03, - "learning_rate": 4.864129534262555e-05, - "loss": 3.2644, + "learning_rate": 4.864277060174917e-05, + "loss": 3.2415, "step": 8200 }, { "epoch": 0.03, - "learning_rate": 4.8624725773633176e-05, - "loss": 3.2493, + "learning_rate": 4.8626219023721724e-05, + "loss": 3.233, "step": 8300 }, { "epoch": 0.03, - "learning_rate": 4.860815620464081e-05, - "loss": 3.2591, + "learning_rate": 4.8609667445694276e-05, + "loss": 3.2325, "step": 8400 }, { "epoch": 0.03, - "learning_rate": 4.8591586635648434e-05, - "loss": 3.2501, + "learning_rate": 4.859311586766683e-05, + "loss": 3.2225, "step": 8500 }, { "epoch": 0.03, - "learning_rate": 4.857501706665607e-05, - "loss": 3.2634, + "learning_rate": 4.857656428963938e-05, + "loss": 3.2354, "step": 8600 }, { "epoch": 0.03, - "learning_rate": 4.855844749766369e-05, - "loss": 3.2509, + "learning_rate": 4.856001271161193e-05, + "loss": 3.2392, "step": 8700 }, { "epoch": 0.03, - "learning_rate": 4.854187792867132e-05, - "loss": 3.2621, + "learning_rate": 4.8543461133584475e-05, + "loss": 3.2396, "step": 8800 }, { "epoch": 0.03, - "learning_rate": 4.852530835967895e-05, - "loss": 3.2493, + "learning_rate": 4.8526909555557034e-05, + "loss": 3.2406, "step": 8900 }, { "epoch": 0.03, - "learning_rate": 4.8508738790686583e-05, - "loss": 3.2657, + "learning_rate": 4.851035797752958e-05, + "loss": 3.2257, "step": 9000 }, { "epoch": 0.03, - "learning_rate": 4.84921692216942e-05, - "loss": 3.2605, + "learning_rate": 4.849380639950213e-05, + "loss": 3.2407, "step": 9100 }, { "epoch": 0.03, - "learning_rate": 4.8475599652701835e-05, - "loss": 3.2619, + "learning_rate": 4.847725482147468e-05, + "loss": 3.2329, "step": 9200 }, { "epoch": 0.03, - "learning_rate": 4.845903008370947e-05, - "loss": 3.2539, + "learning_rate": 4.8460703243447233e-05, + "loss": 3.2203, "step": 9300 }, { "epoch": 0.03, - "learning_rate": 4.8442460514717094e-05, - "loss": 3.2475, + "learning_rate": 4.8444151665419785e-05, + "loss": 3.2381, "step": 9400 }, { "epoch": 0.03, - "learning_rate": 4.842589094572472e-05, - "loss": 3.2495, + "learning_rate": 4.842760008739233e-05, + "loss": 3.228, "step": 9500 }, { "epoch": 0.03, - "learning_rate": 4.840932137673235e-05, - "loss": 3.2457, + "learning_rate": 4.841104850936489e-05, + "loss": 3.2399, "step": 9600 }, { "epoch": 0.03, - "learning_rate": 4.839275180773998e-05, - "loss": 3.2514, + "learning_rate": 4.839449693133743e-05, + "loss": 3.2333, "step": 9700 }, { "epoch": 0.03, - "learning_rate": 4.837618223874761e-05, - "loss": 3.2583, + "learning_rate": 4.837794535330999e-05, + "loss": 3.221, "step": 9800 }, { "epoch": 0.03, - "learning_rate": 4.8359612669755236e-05, - "loss": 3.2539, + "learning_rate": 4.8361393775282536e-05, + "loss": 3.239, "step": 9900 }, { "epoch": 0.03, - "learning_rate": 4.834304310076286e-05, - "loss": 3.2715, + "learning_rate": 4.8344842197255095e-05, + "loss": 3.2276, "step": 10000 }, { "epoch": 0.03, - "learning_rate": 4.8326473531770495e-05, - "loss": 3.2632, + "learning_rate": 4.832829061922764e-05, + "loss": 3.2384, "step": 10100 }, { "epoch": 0.03, - "learning_rate": 4.830990396277813e-05, - "loss": 3.2663, + "learning_rate": 4.831173904120019e-05, + "loss": 3.2334, "step": 10200 }, { "epoch": 0.03, - "learning_rate": 4.829333439378575e-05, - "loss": 3.2465, + "learning_rate": 4.829518746317274e-05, + "loss": 3.2397, "step": 10300 }, { "epoch": 0.03, - "learning_rate": 4.827676482479338e-05, - "loss": 3.25, + "learning_rate": 4.827863588514529e-05, + "loss": 3.2406, "step": 10400 }, { "epoch": 0.03, - "learning_rate": 4.826019525580101e-05, - "loss": 3.2647, + "learning_rate": 4.8262084307117846e-05, + "loss": 3.2295, "step": 10500 }, { "epoch": 0.04, - "learning_rate": 4.824362568680864e-05, - "loss": 3.2457, + "learning_rate": 4.824553272909039e-05, + "loss": 3.238, "step": 10600 }, { "epoch": 0.04, - "learning_rate": 4.822705611781626e-05, - "loss": 3.2529, + "learning_rate": 4.822898115106295e-05, + "loss": 3.2331, "step": 10700 }, { "epoch": 0.04, - "learning_rate": 4.8210486548823896e-05, - "loss": 3.254, + "learning_rate": 4.8212429573035494e-05, + "loss": 3.2395, "step": 10800 }, { "epoch": 0.04, - "learning_rate": 4.819391697983152e-05, - "loss": 3.2404, + "learning_rate": 4.8195877995008045e-05, + "loss": 3.2228, "step": 10900 }, { "epoch": 0.04, - "learning_rate": 4.8177347410839154e-05, - "loss": 3.2372, + "learning_rate": 4.81793264169806e-05, + "loss": 3.2337, "step": 11000 }, { "epoch": 0.04, - "learning_rate": 4.816077784184678e-05, - "loss": 3.2519, + "learning_rate": 4.816277483895315e-05, + "loss": 3.237, "step": 11100 }, { "epoch": 0.04, - "learning_rate": 4.8144208272854406e-05, - "loss": 3.2537, + "learning_rate": 4.81462232609257e-05, + "loss": 3.2385, "step": 11200 }, { "epoch": 0.04, - "learning_rate": 4.812763870386204e-05, - "loss": 3.25, + "learning_rate": 4.8129671682898245e-05, + "loss": 3.2399, "step": 11300 }, { "epoch": 0.04, - "learning_rate": 4.811106913486967e-05, - "loss": 3.239, + "learning_rate": 4.8113120104870803e-05, + "loss": 3.2375, "step": 11400 }, { "epoch": 0.04, - "learning_rate": 4.80944995658773e-05, - "loss": 3.2504, + "learning_rate": 4.809656852684335e-05, + "loss": 3.2247, "step": 11500 }, { "epoch": 0.04, - "learning_rate": 4.807792999688492e-05, - "loss": 3.2594, + "learning_rate": 4.808001694881591e-05, + "loss": 3.2291, "step": 11600 }, { "epoch": 0.04, - "learning_rate": 4.8061360427892555e-05, - "loss": 3.2507, + "learning_rate": 4.806346537078845e-05, + "loss": 3.226, "step": 11700 }, { "epoch": 0.04, - "learning_rate": 4.804479085890018e-05, - "loss": 3.257, + "learning_rate": 4.8046913792761e-05, + "loss": 3.2363, "step": 11800 }, { "epoch": 0.04, - "learning_rate": 4.802822128990781e-05, - "loss": 3.2566, + "learning_rate": 4.8030362214733555e-05, + "loss": 3.2452, "step": 11900 }, { "epoch": 0.04, - "learning_rate": 4.801165172091544e-05, - "loss": 3.26, + "learning_rate": 4.8013810636706106e-05, + "loss": 3.2346, "step": 12000 }, { "epoch": 0.04, - "learning_rate": 4.7995082151923065e-05, - "loss": 3.2626, + "learning_rate": 4.799725905867866e-05, + "loss": 3.2284, "step": 12100 }, { "epoch": 0.04, - "learning_rate": 4.79785125829307e-05, - "loss": 3.2528, + "learning_rate": 4.798070748065121e-05, + "loss": 3.251, "step": 12200 }, { "epoch": 0.04, - "learning_rate": 4.7961943013938324e-05, - "loss": 3.2448, + "learning_rate": 4.796415590262376e-05, + "loss": 3.2408, "step": 12300 }, { "epoch": 0.04, - "learning_rate": 4.794537344494595e-05, - "loss": 3.2484, + "learning_rate": 4.7947604324596306e-05, + "loss": 3.2378, "step": 12400 }, { "epoch": 0.04, - "learning_rate": 4.792880387595358e-05, - "loss": 3.2451, + "learning_rate": 4.793105274656886e-05, + "loss": 3.2372, "step": 12500 }, { "epoch": 0.04, - "learning_rate": 4.7912234306961215e-05, - "loss": 3.253, + "learning_rate": 4.791450116854141e-05, + "loss": 3.2344, "step": 12600 }, { "epoch": 0.04, - "learning_rate": 4.789566473796884e-05, - "loss": 3.2487, + "learning_rate": 4.789794959051396e-05, + "loss": 3.2384, "step": 12700 }, { "epoch": 0.04, - "learning_rate": 4.7879095168976466e-05, - "loss": 3.2619, + "learning_rate": 4.788139801248651e-05, + "loss": 3.2208, "step": 12800 }, { "epoch": 0.04, - "learning_rate": 4.78625255999841e-05, - "loss": 3.2509, + "learning_rate": 4.7864846434459064e-05, + "loss": 3.2237, "step": 12900 }, { "epoch": 0.04, - "learning_rate": 4.7845956030991725e-05, - "loss": 3.2522, + "learning_rate": 4.7848294856431616e-05, + "loss": 3.2443, "step": 13000 }, { "epoch": 0.04, - "learning_rate": 4.782938646199935e-05, - "loss": 3.2639, + "learning_rate": 4.783174327840417e-05, + "loss": 3.2414, "step": 13100 }, { "epoch": 0.04, - "learning_rate": 4.7812816893006976e-05, - "loss": 3.2601, + "learning_rate": 4.781519170037672e-05, + "loss": 3.2334, "step": 13200 }, { "epoch": 0.04, - "learning_rate": 4.779624732401461e-05, - "loss": 3.2602, + "learning_rate": 4.779864012234927e-05, + "loss": 3.2411, "step": 13300 }, { "epoch": 0.04, - "learning_rate": 4.777967775502224e-05, - "loss": 3.2606, + "learning_rate": 4.7782088544321815e-05, + "loss": 3.2192, "step": 13400 }, { "epoch": 0.04, - "learning_rate": 4.776310818602987e-05, - "loss": 3.2578, + "learning_rate": 4.776553696629437e-05, + "loss": 3.2274, "step": 13500 }, { "epoch": 0.05, - "learning_rate": 4.774653861703749e-05, - "loss": 3.2527, + "learning_rate": 4.774898538826692e-05, + "loss": 3.2357, "step": 13600 }, { "epoch": 0.05, - "learning_rate": 4.7729969048045126e-05, - "loss": 3.2571, + "learning_rate": 4.773243381023947e-05, + "loss": 3.2324, "step": 13700 }, { "epoch": 0.05, - "learning_rate": 4.771339947905275e-05, - "loss": 3.2775, + "learning_rate": 4.771588223221202e-05, + "loss": 3.2423, "step": 13800 }, { "epoch": 0.05, - "learning_rate": 4.7696829910060384e-05, - "loss": 3.2545, + "learning_rate": 4.769933065418457e-05, + "loss": 3.2305, "step": 13900 }, { "epoch": 0.05, - "learning_rate": 4.768026034106801e-05, - "loss": 3.2583, + "learning_rate": 4.7682779076157125e-05, + "loss": 3.2262, "step": 14000 }, { "epoch": 0.05, - "learning_rate": 4.7663690772075636e-05, - "loss": 3.2569, + "learning_rate": 4.7666227498129676e-05, + "loss": 3.2279, "step": 14100 }, { "epoch": 0.05, - "learning_rate": 4.764712120308327e-05, - "loss": 3.2477, + "learning_rate": 4.764967592010223e-05, + "loss": 3.2422, "step": 14200 }, { "epoch": 0.05, - "learning_rate": 4.76305516340909e-05, - "loss": 3.2549, + "learning_rate": 4.763312434207477e-05, + "loss": 3.2209, "step": 14300 }, { "epoch": 0.05, - "learning_rate": 4.761398206509852e-05, - "loss": 3.2582, + "learning_rate": 4.761657276404733e-05, + "loss": 3.2252, "step": 14400 }, { "epoch": 0.05, - "learning_rate": 4.759741249610615e-05, - "loss": 3.2706, + "learning_rate": 4.7600021186019876e-05, + "loss": 3.23, "step": 14500 }, { "epoch": 0.05, - "learning_rate": 4.7580842927113785e-05, - "loss": 3.2634, + "learning_rate": 4.758346960799243e-05, + "loss": 3.2193, "step": 14600 }, { "epoch": 0.05, - "learning_rate": 4.756427335812141e-05, - "loss": 3.2478, + "learning_rate": 4.756691802996498e-05, + "loss": 3.2445, "step": 14700 }, { "epoch": 0.05, - "learning_rate": 4.754770378912904e-05, - "loss": 3.2444, + "learning_rate": 4.755036645193753e-05, + "loss": 3.2397, "step": 14800 }, { "epoch": 0.05, - "learning_rate": 4.753113422013667e-05, - "loss": 3.2506, + "learning_rate": 4.753381487391008e-05, + "loss": 3.2437, "step": 14900 }, { "epoch": 0.05, - "learning_rate": 4.7514564651144295e-05, - "loss": 3.2451, + "learning_rate": 4.751726329588263e-05, + "loss": 3.2306, "step": 15000 }, { "epoch": 0.05, - "learning_rate": 4.749799508215193e-05, - "loss": 3.2607, + "learning_rate": 4.7500711717855186e-05, + "loss": 3.2132, "step": 15100 }, { "epoch": 0.05, - "learning_rate": 4.7481425513159554e-05, - "loss": 3.2518, + "learning_rate": 4.748416013982773e-05, + "loss": 3.2296, "step": 15200 }, { "epoch": 0.05, - "learning_rate": 4.746485594416718e-05, - "loss": 3.2624, + "learning_rate": 4.746760856180029e-05, + "loss": 3.228, "step": 15300 }, { "epoch": 0.05, - "learning_rate": 4.744828637517481e-05, - "loss": 3.2715, + "learning_rate": 4.7451056983772834e-05, + "loss": 3.2401, "step": 15400 }, { "epoch": 0.05, - "learning_rate": 4.7431716806182445e-05, - "loss": 3.2487, + "learning_rate": 4.7434505405745385e-05, + "loss": 3.2338, "step": 15500 }, { "epoch": 0.05, - "learning_rate": 4.7415147237190064e-05, - "loss": 3.2365, + "learning_rate": 4.741795382771794e-05, + "loss": 3.2383, "step": 15600 }, { "epoch": 0.05, - "learning_rate": 4.7398577668197696e-05, - "loss": 3.2514, + "learning_rate": 4.740140224969049e-05, + "loss": 3.2377, "step": 15700 }, { "epoch": 0.05, - "learning_rate": 4.738200809920533e-05, - "loss": 3.2454, + "learning_rate": 4.738485067166304e-05, + "loss": 3.2291, "step": 15800 }, { "epoch": 0.05, - "learning_rate": 4.7365438530212955e-05, - "loss": 3.2505, + "learning_rate": 4.7368299093635585e-05, + "loss": 3.2338, "step": 15900 }, { "epoch": 0.05, - "learning_rate": 4.734886896122058e-05, - "loss": 3.2462, + "learning_rate": 4.735174751560814e-05, + "loss": 3.2571, "step": 16000 }, { "epoch": 0.05, - "learning_rate": 4.733229939222821e-05, - "loss": 3.2516, + "learning_rate": 4.733519593758069e-05, + "loss": 3.2434, "step": 16100 }, { "epoch": 0.05, - "learning_rate": 4.731572982323584e-05, - "loss": 3.26, + "learning_rate": 4.7318644359553246e-05, + "loss": 3.2513, "step": 16200 }, { "epoch": 0.05, - "learning_rate": 4.729916025424347e-05, - "loss": 3.2518, + "learning_rate": 4.730209278152579e-05, + "loss": 3.2262, "step": 16300 }, { "epoch": 0.05, - "learning_rate": 4.72825906852511e-05, - "loss": 3.261, + "learning_rate": 4.728554120349834e-05, + "loss": 3.2335, "step": 16400 }, { "epoch": 0.05, - "learning_rate": 4.726602111625872e-05, - "loss": 3.2619, + "learning_rate": 4.7268989625470894e-05, + "loss": 3.2375, "step": 16500 }, { - "epoch": 0.06, - "learning_rate": 4.7249451547266356e-05, - "loss": 3.2566, + "epoch": 0.05, + "learning_rate": 4.7252438047443446e-05, + "loss": 3.2351, "step": 16600 }, { "epoch": 0.06, - "learning_rate": 4.723288197827399e-05, - "loss": 3.259, + "learning_rate": 4.7235886469416e-05, + "loss": 3.2421, "step": 16700 }, { "epoch": 0.06, - "learning_rate": 4.721631240928161e-05, - "loss": 3.2601, + "learning_rate": 4.721933489138854e-05, + "loss": 3.2414, "step": 16800 }, { "epoch": 0.06, - "learning_rate": 4.719974284028924e-05, - "loss": 3.2565, + "learning_rate": 4.72027833133611e-05, + "loss": 3.2401, "step": 16900 }, { "epoch": 0.06, - "learning_rate": 4.718317327129687e-05, - "loss": 3.2467, + "learning_rate": 4.7186231735333646e-05, + "loss": 3.2273, "step": 17000 }, { "epoch": 0.06, - "learning_rate": 4.71666037023045e-05, - "loss": 3.251, + "learning_rate": 4.7169680157306204e-05, + "loss": 3.2189, "step": 17100 }, { "epoch": 0.06, - "learning_rate": 4.7150034133312124e-05, - "loss": 3.242, + "learning_rate": 4.715312857927875e-05, + "loss": 3.2305, "step": 17200 }, { "epoch": 0.06, - "learning_rate": 4.713346456431976e-05, - "loss": 3.2473, + "learning_rate": 4.71365770012513e-05, + "loss": 3.2238, "step": 17300 }, { "epoch": 0.06, - "learning_rate": 4.711689499532738e-05, - "loss": 3.2614, + "learning_rate": 4.712002542322385e-05, + "loss": 3.231, "step": 17400 }, { "epoch": 0.06, - "learning_rate": 4.7100325426335015e-05, - "loss": 3.2593, + "learning_rate": 4.7103473845196404e-05, + "loss": 3.2405, "step": 17500 }, { "epoch": 0.06, - "learning_rate": 4.708375585734264e-05, - "loss": 3.2489, + "learning_rate": 4.7086922267168955e-05, + "loss": 3.2297, "step": 17600 }, { "epoch": 0.06, - "learning_rate": 4.706718628835027e-05, - "loss": 3.2577, + "learning_rate": 4.707037068914151e-05, + "loss": 3.2231, "step": 17700 }, { "epoch": 0.06, - "learning_rate": 4.70506167193579e-05, - "loss": 3.2534, + "learning_rate": 4.705381911111406e-05, + "loss": 3.2413, "step": 17800 }, { "epoch": 0.06, - "learning_rate": 4.703404715036553e-05, - "loss": 3.2467, + "learning_rate": 4.70372675330866e-05, + "loss": 3.2268, "step": 17900 }, { "epoch": 0.06, - "learning_rate": 4.701747758137315e-05, - "loss": 3.2492, + "learning_rate": 4.7020715955059155e-05, + "loss": 3.2325, "step": 18000 }, { "epoch": 0.06, - "learning_rate": 4.7000908012380784e-05, - "loss": 3.2596, + "learning_rate": 4.7004164377031706e-05, + "loss": 3.2254, "step": 18100 }, { "epoch": 0.06, - "learning_rate": 4.6984338443388416e-05, - "loss": 3.2561, + "learning_rate": 4.698761279900426e-05, + "loss": 3.2287, "step": 18200 }, { "epoch": 0.06, - "learning_rate": 4.696776887439604e-05, - "loss": 3.2577, + "learning_rate": 4.697106122097681e-05, + "loss": 3.2558, "step": 18300 }, { "epoch": 0.06, - "learning_rate": 4.695119930540367e-05, - "loss": 3.2424, + "learning_rate": 4.695450964294936e-05, + "loss": 3.2299, "step": 18400 }, { "epoch": 0.06, - "learning_rate": 4.69346297364113e-05, - "loss": 3.2483, + "learning_rate": 4.693795806492191e-05, + "loss": 3.2292, "step": 18500 }, { "epoch": 0.06, - "learning_rate": 4.6918060167418926e-05, - "loss": 3.2533, + "learning_rate": 4.6921406486894465e-05, + "loss": 3.2299, "step": 18600 }, { "epoch": 0.06, - "learning_rate": 4.690149059842656e-05, - "loss": 3.2567, + "learning_rate": 4.6904854908867016e-05, + "loss": 3.243, "step": 18700 }, { "epoch": 0.06, - "learning_rate": 4.6884921029434185e-05, - "loss": 3.2664, + "learning_rate": 4.688830333083957e-05, + "loss": 3.244, "step": 18800 }, { "epoch": 0.06, - "learning_rate": 4.686835146044181e-05, - "loss": 3.2535, + "learning_rate": 4.687175175281211e-05, + "loss": 3.2359, "step": 18900 }, { "epoch": 0.06, - "learning_rate": 4.685178189144944e-05, - "loss": 3.259, + "learning_rate": 4.6855200174784664e-05, + "loss": 3.236, "step": 19000 }, { "epoch": 0.06, - "learning_rate": 4.6835212322457076e-05, - "loss": 3.2582, + "learning_rate": 4.6838648596757216e-05, + "loss": 3.2212, "step": 19100 }, { "epoch": 0.06, - "learning_rate": 4.6818642753464695e-05, - "loss": 3.2647, + "learning_rate": 4.682209701872977e-05, + "loss": 3.2376, "step": 19200 }, { "epoch": 0.06, - "learning_rate": 4.680207318447233e-05, - "loss": 3.2572, + "learning_rate": 4.680554544070232e-05, + "loss": 3.2421, "step": 19300 }, { "epoch": 0.06, - "learning_rate": 4.678550361547996e-05, - "loss": 3.2559, + "learning_rate": 4.678899386267487e-05, + "loss": 3.2435, "step": 19400 }, { "epoch": 0.06, - "learning_rate": 4.6768934046487586e-05, - "loss": 3.2551, + "learning_rate": 4.677244228464742e-05, + "loss": 3.2364, "step": 19500 }, { "epoch": 0.06, - "learning_rate": 4.675236447749521e-05, - "loss": 3.2399, + "learning_rate": 4.675589070661997e-05, + "loss": 3.2373, "step": 19600 }, { "epoch": 0.07, - "learning_rate": 4.6735794908502844e-05, - "loss": 3.2602, + "learning_rate": 4.6739339128592525e-05, + "loss": 3.2417, "step": 19700 }, { "epoch": 0.07, - "learning_rate": 4.671922533951047e-05, - "loss": 3.2517, + "learning_rate": 4.672278755056507e-05, + "loss": 3.2286, "step": 19800 }, { "epoch": 0.07, - "learning_rate": 4.67026557705181e-05, - "loss": 3.2398, + "learning_rate": 4.670623597253763e-05, + "loss": 3.2254, "step": 19900 }, { "epoch": 0.07, - "learning_rate": 4.668608620152573e-05, - "loss": 3.2424, + "learning_rate": 4.668968439451017e-05, + "loss": 3.2308, "step": 20000 }, { "epoch": 0.07, - "learning_rate": 4.6669516632533354e-05, - "loss": 3.2541, + "learning_rate": 4.6673132816482725e-05, + "loss": 3.2302, "step": 20100 }, { "epoch": 0.07, - "learning_rate": 4.665294706354099e-05, - "loss": 3.258, + "learning_rate": 4.6656581238455277e-05, + "loss": 3.2198, "step": 20200 }, { "epoch": 0.07, - "learning_rate": 4.663637749454862e-05, - "loss": 3.2599, + "learning_rate": 4.664002966042783e-05, + "loss": 3.2326, "step": 20300 }, { "epoch": 0.07, - "learning_rate": 4.661980792555624e-05, - "loss": 3.2378, + "learning_rate": 4.662347808240038e-05, + "loss": 3.2362, "step": 20400 }, { "epoch": 0.07, - "learning_rate": 4.660323835656387e-05, - "loss": 3.2651, + "learning_rate": 4.6606926504372925e-05, + "loss": 3.2449, "step": 20500 }, { "epoch": 0.07, - "learning_rate": 4.6586668787571504e-05, - "loss": 3.2447, + "learning_rate": 4.659037492634548e-05, + "loss": 3.223, "step": 20600 }, { "epoch": 0.07, - "learning_rate": 4.657009921857913e-05, - "loss": 3.2513, + "learning_rate": 4.657382334831803e-05, + "loss": 3.2264, "step": 20700 }, { "epoch": 0.07, - "learning_rate": 4.6553529649586755e-05, - "loss": 3.2463, + "learning_rate": 4.6557271770290586e-05, + "loss": 3.254, "step": 20800 }, { "epoch": 0.07, - "learning_rate": 4.653696008059439e-05, - "loss": 3.2531, + "learning_rate": 4.654072019226313e-05, + "loss": 3.2381, "step": 20900 }, { "epoch": 0.07, - "learning_rate": 4.6520390511602014e-05, - "loss": 3.2492, + "learning_rate": 4.652416861423568e-05, + "loss": 3.232, "step": 21000 }, { "epoch": 0.07, - "learning_rate": 4.6503820942609646e-05, - "loss": 3.2602, + "learning_rate": 4.6507617036208234e-05, + "loss": 3.2433, "step": 21100 }, { "epoch": 0.07, - "learning_rate": 4.648725137361727e-05, - "loss": 3.2471, + "learning_rate": 4.6491065458180786e-05, + "loss": 3.2282, "step": 21200 }, { "epoch": 0.07, - "learning_rate": 4.64706818046249e-05, - "loss": 3.2583, + "learning_rate": 4.647451388015334e-05, + "loss": 3.2348, "step": 21300 }, { "epoch": 0.07, - "learning_rate": 4.645411223563253e-05, - "loss": 3.2626, + "learning_rate": 4.645796230212588e-05, + "loss": 3.2254, "step": 21400 }, { "epoch": 0.07, - "learning_rate": 4.643754266664016e-05, - "loss": 3.249, + "learning_rate": 4.644141072409844e-05, + "loss": 3.226, "step": 21500 }, { "epoch": 0.07, - "learning_rate": 4.642097309764778e-05, - "loss": 3.2449, + "learning_rate": 4.6424859146070985e-05, + "loss": 3.2414, "step": 21600 }, { "epoch": 0.07, - "learning_rate": 4.6404403528655415e-05, - "loss": 3.2385, + "learning_rate": 4.6408307568043544e-05, + "loss": 3.2403, "step": 21700 }, { "epoch": 0.07, - "learning_rate": 4.638783395966305e-05, - "loss": 3.2672, + "learning_rate": 4.639175599001609e-05, + "loss": 3.236, "step": 21800 }, { "epoch": 0.07, - "learning_rate": 4.637126439067067e-05, - "loss": 3.2481, + "learning_rate": 4.637520441198864e-05, + "loss": 3.2257, "step": 21900 }, { "epoch": 0.07, - "learning_rate": 4.63546948216783e-05, - "loss": 3.2492, + "learning_rate": 4.635865283396119e-05, + "loss": 3.239, "step": 22000 }, { "epoch": 0.07, - "learning_rate": 4.6338125252685925e-05, - "loss": 3.2499, + "learning_rate": 4.6342101255933743e-05, + "loss": 3.2213, "step": 22100 }, { "epoch": 0.07, - "learning_rate": 4.632155568369356e-05, - "loss": 3.2543, + "learning_rate": 4.6325549677906295e-05, + "loss": 3.2377, "step": 22200 }, { "epoch": 0.07, - "learning_rate": 4.630498611470119e-05, - "loss": 3.2711, + "learning_rate": 4.630899809987884e-05, + "loss": 3.224, "step": 22300 }, { "epoch": 0.07, - "learning_rate": 4.6288416545708816e-05, - "loss": 3.2661, + "learning_rate": 4.62924465218514e-05, + "loss": 3.2245, "step": 22400 }, { "epoch": 0.07, - "learning_rate": 4.627184697671644e-05, - "loss": 3.249, + "learning_rate": 4.627589494382394e-05, + "loss": 3.226, "step": 22500 }, { "epoch": 0.07, - "learning_rate": 4.6255277407724074e-05, - "loss": 3.2482, + "learning_rate": 4.62593433657965e-05, + "loss": 3.2252, "step": 22600 }, { "epoch": 0.08, - "learning_rate": 4.62387078387317e-05, - "loss": 3.2607, + "learning_rate": 4.6242791787769046e-05, + "loss": 3.2373, "step": 22700 }, { "epoch": 0.08, - "learning_rate": 4.6222138269739326e-05, - "loss": 3.2485, + "learning_rate": 4.62262402097416e-05, + "loss": 3.2358, "step": 22800 }, { "epoch": 0.08, - "learning_rate": 4.620556870074696e-05, - "loss": 3.2489, + "learning_rate": 4.620968863171415e-05, + "loss": 3.2443, "step": 22900 }, { "epoch": 0.08, - "learning_rate": 4.6188999131754584e-05, - "loss": 3.2498, + "learning_rate": 4.61931370536867e-05, + "loss": 3.2412, "step": 23000 }, { "epoch": 0.08, - "learning_rate": 4.617242956276222e-05, - "loss": 3.2472, + "learning_rate": 4.617658547565925e-05, + "loss": 3.2382, "step": 23100 }, { "epoch": 0.08, - "learning_rate": 4.615585999376984e-05, - "loss": 3.2528, + "learning_rate": 4.6160033897631804e-05, + "loss": 3.2275, "step": 23200 }, { "epoch": 0.08, - "learning_rate": 4.613929042477747e-05, - "loss": 3.2614, + "learning_rate": 4.6143482319604356e-05, + "loss": 3.2253, "step": 23300 }, { "epoch": 0.08, - "learning_rate": 4.61227208557851e-05, - "loss": 3.2598, + "learning_rate": 4.61269307415769e-05, + "loss": 3.2343, "step": 23400 }, { "epoch": 0.08, - "learning_rate": 4.6106151286792734e-05, - "loss": 3.2525, + "learning_rate": 4.611037916354945e-05, + "loss": 3.2356, "step": 23500 }, { "epoch": 0.08, - "learning_rate": 4.608958171780036e-05, - "loss": 3.2625, + "learning_rate": 4.6093827585522004e-05, + "loss": 3.239, "step": 23600 }, { "epoch": 0.08, - "learning_rate": 4.6073012148807985e-05, - "loss": 3.2494, + "learning_rate": 4.6077276007494555e-05, + "loss": 3.2248, "step": 23700 }, { "epoch": 0.08, - "learning_rate": 4.605644257981562e-05, - "loss": 3.2526, + "learning_rate": 4.606072442946711e-05, + "loss": 3.229, "step": 23800 }, { "epoch": 0.08, - "learning_rate": 4.6039873010823244e-05, - "loss": 3.2595, + "learning_rate": 4.604417285143966e-05, + "loss": 3.2279, "step": 23900 }, { "epoch": 0.08, - "learning_rate": 4.6023303441830876e-05, - "loss": 3.2476, + "learning_rate": 4.602762127341221e-05, + "loss": 3.2392, "step": 24000 }, { "epoch": 0.08, - "learning_rate": 4.60067338728385e-05, - "loss": 3.2495, + "learning_rate": 4.601106969538476e-05, + "loss": 3.2323, "step": 24100 }, { "epoch": 0.08, - "learning_rate": 4.599016430384613e-05, - "loss": 3.2433, + "learning_rate": 4.5994518117357313e-05, + "loss": 3.2491, "step": 24200 }, { "epoch": 0.08, - "learning_rate": 4.597359473485376e-05, - "loss": 3.2597, + "learning_rate": 4.5977966539329865e-05, + "loss": 3.23, "step": 24300 }, { "epoch": 0.08, - "learning_rate": 4.5957025165861386e-05, - "loss": 3.2615, + "learning_rate": 4.596141496130241e-05, + "loss": 3.231, "step": 24400 }, { "epoch": 0.08, - "learning_rate": 4.594045559686901e-05, - "loss": 3.2369, + "learning_rate": 4.594486338327496e-05, + "loss": 3.2324, "step": 24500 }, { "epoch": 0.08, - "learning_rate": 4.5923886027876645e-05, - "loss": 3.2553, + "learning_rate": 4.592831180524751e-05, + "loss": 3.2435, "step": 24600 }, { "epoch": 0.08, - "learning_rate": 4.590731645888428e-05, - "loss": 3.2511, + "learning_rate": 4.5911760227220065e-05, + "loss": 3.2287, "step": 24700 }, { "epoch": 0.08, - "learning_rate": 4.58907468898919e-05, - "loss": 3.2486, + "learning_rate": 4.5895208649192616e-05, + "loss": 3.2269, "step": 24800 }, { "epoch": 0.08, - "learning_rate": 4.587417732089953e-05, - "loss": 3.2571, + "learning_rate": 4.587865707116517e-05, + "loss": 3.2269, "step": 24900 }, { "epoch": 0.08, - "learning_rate": 4.585760775190716e-05, - "loss": 3.252, + "learning_rate": 4.586210549313772e-05, + "loss": 3.2322, "step": 25000 }, { "epoch": 0.08, - "learning_rate": 4.584103818291479e-05, - "loss": 3.2458, + "learning_rate": 4.5845553915110264e-05, + "loss": 3.2333, "step": 25100 }, { "epoch": 0.08, - "learning_rate": 4.582446861392242e-05, - "loss": 3.2539, + "learning_rate": 4.582900233708282e-05, + "loss": 3.2278, "step": 25200 }, { "epoch": 0.08, - "learning_rate": 4.5807899044930046e-05, - "loss": 3.2525, + "learning_rate": 4.581245075905537e-05, + "loss": 3.2357, "step": 25300 }, { "epoch": 0.08, - "learning_rate": 4.579132947593767e-05, - "loss": 3.2467, + "learning_rate": 4.5795899181027926e-05, + "loss": 3.2285, "step": 25400 }, { "epoch": 0.08, - "learning_rate": 4.5774759906945304e-05, - "loss": 3.245, + "learning_rate": 4.577934760300047e-05, + "loss": 3.2239, "step": 25500 }, { "epoch": 0.08, - "learning_rate": 4.575819033795293e-05, - "loss": 3.255, + "learning_rate": 4.576279602497303e-05, + "loss": 3.239, "step": 25600 }, { "epoch": 0.09, - "learning_rate": 4.5741620768960556e-05, - "loss": 3.2572, + "learning_rate": 4.5746244446945574e-05, + "loss": 3.2165, "step": 25700 }, { "epoch": 0.09, - "learning_rate": 4.572505119996819e-05, - "loss": 3.2437, + "learning_rate": 4.5729692868918126e-05, + "loss": 3.2322, "step": 25800 }, { "epoch": 0.09, - "learning_rate": 4.570848163097582e-05, - "loss": 3.2539, + "learning_rate": 4.571314129089068e-05, + "loss": 3.2443, "step": 25900 }, { "epoch": 0.09, - "learning_rate": 4.569191206198345e-05, - "loss": 3.2452, + "learning_rate": 4.569658971286322e-05, + "loss": 3.228, "step": 26000 }, { "epoch": 0.09, - "learning_rate": 4.567534249299107e-05, - "loss": 3.2499, + "learning_rate": 4.568003813483578e-05, + "loss": 3.2367, "step": 26100 }, { "epoch": 0.09, - "learning_rate": 4.5658772923998705e-05, - "loss": 3.2532, + "learning_rate": 4.5663486556808325e-05, + "loss": 3.2208, "step": 26200 }, { "epoch": 0.09, - "learning_rate": 4.564220335500633e-05, - "loss": 3.2627, + "learning_rate": 4.5646934978780884e-05, + "loss": 3.2345, "step": 26300 }, { "epoch": 0.09, - "learning_rate": 4.5625633786013964e-05, - "loss": 3.254, + "learning_rate": 4.563038340075343e-05, + "loss": 3.2279, "step": 26400 }, { "epoch": 0.09, - "learning_rate": 4.560906421702159e-05, - "loss": 3.242, + "learning_rate": 4.561383182272598e-05, + "loss": 3.2287, "step": 26500 }, { "epoch": 0.09, - "learning_rate": 4.5592494648029215e-05, - "loss": 3.2456, + "learning_rate": 4.559728024469853e-05, + "loss": 3.2432, "step": 26600 }, { "epoch": 0.09, - "learning_rate": 4.557592507903685e-05, - "loss": 3.2566, + "learning_rate": 4.558072866667108e-05, + "loss": 3.2298, "step": 26700 }, { "epoch": 0.09, - "learning_rate": 4.5559355510044474e-05, - "loss": 3.2619, + "learning_rate": 4.5564177088643635e-05, + "loss": 3.237, "step": 26800 }, { "epoch": 0.09, - "learning_rate": 4.55427859410521e-05, - "loss": 3.2473, + "learning_rate": 4.554762551061618e-05, + "loss": 3.2274, "step": 26900 }, { "epoch": 0.09, - "learning_rate": 4.552621637205973e-05, - "loss": 3.2556, + "learning_rate": 4.553107393258874e-05, + "loss": 3.2149, "step": 27000 }, { "epoch": 0.09, - "learning_rate": 4.5509646803067365e-05, - "loss": 3.2482, + "learning_rate": 4.551452235456128e-05, + "loss": 3.2277, "step": 27100 }, { "epoch": 0.09, - "learning_rate": 4.549307723407499e-05, - "loss": 3.242, + "learning_rate": 4.549797077653384e-05, + "loss": 3.2431, "step": 27200 }, { "epoch": 0.09, - "learning_rate": 4.5476507665082616e-05, - "loss": 3.2364, + "learning_rate": 4.5481419198506386e-05, + "loss": 3.2247, "step": 27300 }, { "epoch": 0.09, - "learning_rate": 4.545993809609025e-05, - "loss": 3.2554, + "learning_rate": 4.546486762047894e-05, + "loss": 3.2261, "step": 27400 }, { "epoch": 0.09, - "learning_rate": 4.5443368527097875e-05, - "loss": 3.2623, + "learning_rate": 4.544831604245149e-05, + "loss": 3.2287, "step": 27500 }, { "epoch": 0.09, - "learning_rate": 4.542679895810551e-05, - "loss": 3.2509, + "learning_rate": 4.543176446442404e-05, + "loss": 3.2262, "step": 27600 }, { "epoch": 0.09, - "learning_rate": 4.541022938911313e-05, - "loss": 3.2505, + "learning_rate": 4.541521288639659e-05, + "loss": 3.2326, "step": 27700 }, { "epoch": 0.09, - "learning_rate": 4.539365982012076e-05, - "loss": 3.2444, + "learning_rate": 4.5398661308369144e-05, + "loss": 3.2415, "step": 27800 }, { "epoch": 0.09, - "learning_rate": 4.537709025112839e-05, - "loss": 3.2507, + "learning_rate": 4.5382109730341696e-05, + "loss": 3.2364, "step": 27900 }, { "epoch": 0.09, - "learning_rate": 4.536052068213602e-05, - "loss": 3.2601, + "learning_rate": 4.536555815231424e-05, + "loss": 3.2283, "step": 28000 }, { "epoch": 0.09, - "learning_rate": 4.534395111314364e-05, - "loss": 3.2567, + "learning_rate": 4.534900657428679e-05, + "loss": 3.2292, "step": 28100 }, { "epoch": 0.09, - "learning_rate": 4.5327381544151276e-05, - "loss": 3.2566, + "learning_rate": 4.5332454996259344e-05, + "loss": 3.2307, "step": 28200 }, { "epoch": 0.09, - "learning_rate": 4.531081197515891e-05, - "loss": 3.24, + "learning_rate": 4.5315903418231895e-05, + "loss": 3.2422, "step": 28300 }, { "epoch": 0.09, - "learning_rate": 4.5294242406166534e-05, - "loss": 3.2489, + "learning_rate": 4.529935184020445e-05, + "loss": 3.2398, "step": 28400 }, { "epoch": 0.09, - "learning_rate": 4.527767283717416e-05, - "loss": 3.2449, + "learning_rate": 4.5282800262177e-05, + "loss": 3.2222, "step": 28500 }, { "epoch": 0.09, - "learning_rate": 4.526110326818179e-05, - "loss": 3.2486, + "learning_rate": 4.526624868414955e-05, + "loss": 3.2243, "step": 28600 }, { "epoch": 0.1, - "learning_rate": 4.524453369918942e-05, - "loss": 3.25, + "learning_rate": 4.52496971061221e-05, + "loss": 3.2278, "step": 28700 }, { "epoch": 0.1, - "learning_rate": 4.522796413019705e-05, - "loss": 3.2477, + "learning_rate": 4.523314552809465e-05, + "loss": 3.223, "step": 28800 }, { "epoch": 0.1, - "learning_rate": 4.521139456120468e-05, - "loss": 3.2538, + "learning_rate": 4.5216593950067205e-05, + "loss": 3.2322, "step": 28900 }, { "epoch": 0.1, - "learning_rate": 4.51948249922123e-05, - "loss": 3.2463, + "learning_rate": 4.520004237203975e-05, + "loss": 3.2332, "step": 29000 }, { "epoch": 0.1, - "learning_rate": 4.5178255423219935e-05, - "loss": 3.2486, + "learning_rate": 4.51834907940123e-05, + "loss": 3.227, "step": 29100 }, { "epoch": 0.1, - "learning_rate": 4.516168585422757e-05, - "loss": 3.2608, + "learning_rate": 4.516693921598485e-05, + "loss": 3.2199, "step": 29200 }, { "epoch": 0.1, - "learning_rate": 4.514511628523519e-05, - "loss": 3.2619, + "learning_rate": 4.5150387637957404e-05, + "loss": 3.2298, "step": 29300 }, { "epoch": 0.1, - "learning_rate": 4.512854671624282e-05, - "loss": 3.2548, + "learning_rate": 4.5133836059929956e-05, + "loss": 3.2319, "step": 29400 }, { "epoch": 0.1, - "learning_rate": 4.511197714725045e-05, - "loss": 3.2464, + "learning_rate": 4.511728448190251e-05, + "loss": 3.2312, "step": 29500 }, { "epoch": 0.1, - "learning_rate": 4.509540757825808e-05, - "loss": 3.2335, + "learning_rate": 4.510073290387506e-05, + "loss": 3.2282, "step": 29600 }, { "epoch": 0.1, - "learning_rate": 4.5078838009265704e-05, - "loss": 3.2545, + "learning_rate": 4.508418132584761e-05, + "loss": 3.2379, "step": 29700 }, { "epoch": 0.1, - "learning_rate": 4.5062268440273336e-05, - "loss": 3.2472, + "learning_rate": 4.506762974782016e-05, + "loss": 3.2251, "step": 29800 }, { "epoch": 0.1, - "learning_rate": 4.504569887128096e-05, - "loss": 3.2478, + "learning_rate": 4.505107816979271e-05, + "loss": 3.2288, "step": 29900 }, { "epoch": 0.1, - "learning_rate": 4.5029129302288595e-05, - "loss": 3.2357, + "learning_rate": 4.5034526591765266e-05, + "loss": 3.243, "step": 30000 }, { "epoch": 0.1, - "learning_rate": 4.501255973329622e-05, - "loss": 3.247, + "learning_rate": 4.501797501373781e-05, + "loss": 3.2306, "step": 30100 }, { "epoch": 0.1, - "learning_rate": 4.4995990164303846e-05, - "loss": 3.2369, + "learning_rate": 4.500142343571036e-05, + "loss": 3.221, "step": 30200 }, { "epoch": 0.1, - "learning_rate": 4.497942059531148e-05, - "loss": 3.2581, + "learning_rate": 4.4984871857682914e-05, + "loss": 3.2394, "step": 30300 }, { "epoch": 0.1, - "learning_rate": 4.496285102631911e-05, - "loss": 3.2746, + "learning_rate": 4.4968320279655465e-05, + "loss": 3.2276, "step": 30400 }, { "epoch": 0.1, - "learning_rate": 4.494628145732673e-05, - "loss": 3.2517, + "learning_rate": 4.495176870162802e-05, + "loss": 3.2221, "step": 30500 }, { "epoch": 0.1, - "learning_rate": 4.492971188833436e-05, - "loss": 3.2565, + "learning_rate": 4.493521712360056e-05, + "loss": 3.2232, "step": 30600 }, { "epoch": 0.1, - "learning_rate": 4.491314231934199e-05, - "loss": 3.2539, + "learning_rate": 4.491866554557312e-05, + "loss": 3.2374, "step": 30700 }, { "epoch": 0.1, - "learning_rate": 4.489657275034962e-05, - "loss": 3.2528, + "learning_rate": 4.4902113967545665e-05, + "loss": 3.236, "step": 30800 }, { "epoch": 0.1, - "learning_rate": 4.488000318135725e-05, - "loss": 3.2485, + "learning_rate": 4.488556238951822e-05, + "loss": 3.2221, "step": 30900 }, { "epoch": 0.1, - "learning_rate": 4.486343361236487e-05, - "loss": 3.2504, + "learning_rate": 4.486901081149077e-05, + "loss": 3.2296, "step": 31000 }, { "epoch": 0.1, - "learning_rate": 4.4846864043372506e-05, - "loss": 3.2605, + "learning_rate": 4.4852459233463326e-05, + "loss": 3.235, "step": 31100 }, { "epoch": 0.1, - "learning_rate": 4.483029447438014e-05, - "loss": 3.2413, + "learning_rate": 4.483590765543587e-05, + "loss": 3.2331, "step": 31200 }, { "epoch": 0.1, - "learning_rate": 4.481372490538776e-05, - "loss": 3.2433, + "learning_rate": 4.481935607740842e-05, + "loss": 3.2392, "step": 31300 }, { "epoch": 0.1, - "learning_rate": 4.479715533639539e-05, - "loss": 3.2358, + "learning_rate": 4.4802804499380974e-05, + "loss": 3.2311, "step": 31400 }, { "epoch": 0.1, - "learning_rate": 4.478058576740302e-05, - "loss": 3.246, + "learning_rate": 4.478625292135352e-05, + "loss": 3.2463, "step": 31500 }, { "epoch": 0.1, - "learning_rate": 4.476401619841065e-05, - "loss": 3.2436, + "learning_rate": 4.476970134332608e-05, + "loss": 3.2239, "step": 31600 }, { - "epoch": 0.11, - "learning_rate": 4.4747446629418274e-05, - "loss": 3.2599, + "epoch": 0.1, + "learning_rate": 4.475314976529862e-05, + "loss": 3.233, "step": 31700 }, { "epoch": 0.11, - "learning_rate": 4.473087706042591e-05, - "loss": 3.2453, + "learning_rate": 4.473659818727118e-05, + "loss": 3.2518, "step": 31800 }, { "epoch": 0.11, - "learning_rate": 4.471430749143353e-05, - "loss": 3.2594, + "learning_rate": 4.4720046609243726e-05, + "loss": 3.228, "step": 31900 }, { "epoch": 0.11, - "learning_rate": 4.4697737922441165e-05, - "loss": 3.2583, + "learning_rate": 4.470349503121628e-05, + "loss": 3.2294, "step": 32000 }, { "epoch": 0.11, - "learning_rate": 4.468116835344879e-05, - "loss": 3.2433, + "learning_rate": 4.468694345318883e-05, + "loss": 3.2321, "step": 32100 }, { "epoch": 0.11, - "learning_rate": 4.466459878445642e-05, - "loss": 3.2487, + "learning_rate": 4.467039187516138e-05, + "loss": 3.2251, "step": 32200 }, { "epoch": 0.11, - "learning_rate": 4.464802921546405e-05, - "loss": 3.2464, + "learning_rate": 4.465384029713393e-05, + "loss": 3.23, "step": 32300 }, { "epoch": 0.11, - "learning_rate": 4.463145964647168e-05, - "loss": 3.25, + "learning_rate": 4.463728871910648e-05, + "loss": 3.2264, "step": 32400 }, { "epoch": 0.11, - "learning_rate": 4.46148900774793e-05, - "loss": 3.2461, + "learning_rate": 4.4620737141079035e-05, + "loss": 3.2287, "step": 32500 }, { "epoch": 0.11, - "learning_rate": 4.4598320508486934e-05, - "loss": 3.2463, + "learning_rate": 4.460418556305158e-05, + "loss": 3.2307, "step": 32600 }, { "epoch": 0.11, - "learning_rate": 4.4581750939494566e-05, - "loss": 3.256, + "learning_rate": 4.458763398502414e-05, + "loss": 3.2354, "step": 32700 }, { "epoch": 0.11, - "learning_rate": 4.456518137050219e-05, - "loss": 3.248, + "learning_rate": 4.457108240699668e-05, + "loss": 3.2303, "step": 32800 }, { "epoch": 0.11, - "learning_rate": 4.454861180150982e-05, - "loss": 3.2472, + "learning_rate": 4.4554530828969235e-05, + "loss": 3.2387, "step": 32900 }, { "epoch": 0.11, - "learning_rate": 4.453204223251745e-05, - "loss": 3.2433, + "learning_rate": 4.4537979250941787e-05, + "loss": 3.2231, "step": 33000 }, { "epoch": 0.11, - "learning_rate": 4.4515472663525076e-05, - "loss": 3.271, + "learning_rate": 4.452142767291434e-05, + "loss": 3.2442, "step": 33100 }, { "epoch": 0.11, - "learning_rate": 4.449890309453271e-05, - "loss": 3.2518, + "learning_rate": 4.450487609488689e-05, + "loss": 3.2325, "step": 33200 }, { "epoch": 0.11, - "learning_rate": 4.4482333525540335e-05, - "loss": 3.2536, + "learning_rate": 4.448832451685944e-05, + "loss": 3.2279, "step": 33300 }, { "epoch": 0.11, - "learning_rate": 4.446576395654796e-05, - "loss": 3.2317, + "learning_rate": 4.447177293883199e-05, + "loss": 3.2434, "step": 33400 }, { "epoch": 0.11, - "learning_rate": 4.444919438755559e-05, - "loss": 3.2532, + "learning_rate": 4.445522136080454e-05, + "loss": 3.228, "step": 33500 }, { "epoch": 0.11, - "learning_rate": 4.4432624818563226e-05, - "loss": 3.264, + "learning_rate": 4.443866978277709e-05, + "loss": 3.2217, "step": 33600 }, { "epoch": 0.11, - "learning_rate": 4.441605524957085e-05, - "loss": 3.2416, + "learning_rate": 4.442211820474964e-05, + "loss": 3.23, "step": 33700 }, { "epoch": 0.11, - "learning_rate": 4.439948568057848e-05, - "loss": 3.2655, + "learning_rate": 4.440556662672219e-05, + "loss": 3.2359, "step": 33800 }, { "epoch": 0.11, - "learning_rate": 4.438291611158611e-05, - "loss": 3.2467, + "learning_rate": 4.4389015048694744e-05, + "loss": 3.2337, "step": 33900 }, { "epoch": 0.11, - "learning_rate": 4.4366346542593736e-05, - "loss": 3.2454, + "learning_rate": 4.4372463470667296e-05, + "loss": 3.2243, "step": 34000 }, { "epoch": 0.11, - "learning_rate": 4.434977697360136e-05, - "loss": 3.2445, + "learning_rate": 4.435591189263985e-05, + "loss": 3.2295, "step": 34100 }, { "epoch": 0.11, - "learning_rate": 4.4333207404608994e-05, - "loss": 3.2569, + "learning_rate": 4.43393603146124e-05, + "loss": 3.2234, "step": 34200 }, { "epoch": 0.11, - "learning_rate": 4.431663783561662e-05, - "loss": 3.2527, + "learning_rate": 4.432280873658495e-05, + "loss": 3.2321, "step": 34300 }, { "epoch": 0.11, - "learning_rate": 4.430006826662425e-05, - "loss": 3.2508, + "learning_rate": 4.43062571585575e-05, + "loss": 3.2387, "step": 34400 }, { "epoch": 0.11, - "learning_rate": 4.428349869763188e-05, - "loss": 3.2663, + "learning_rate": 4.428970558053005e-05, + "loss": 3.2336, "step": 34500 }, { "epoch": 0.11, - "learning_rate": 4.4266929128639504e-05, - "loss": 3.2484, + "learning_rate": 4.42731540025026e-05, + "loss": 3.2237, "step": 34600 }, { "epoch": 0.11, - "learning_rate": 4.425035955964714e-05, - "loss": 3.2569, + "learning_rate": 4.425660242447515e-05, + "loss": 3.2277, "step": 34700 }, { "epoch": 0.12, - "learning_rate": 4.423378999065477e-05, - "loss": 3.252, + "learning_rate": 4.42400508464477e-05, + "loss": 3.2189, "step": 34800 }, { "epoch": 0.12, - "learning_rate": 4.4217220421662395e-05, - "loss": 3.2398, + "learning_rate": 4.422349926842025e-05, + "loss": 3.2294, "step": 34900 }, { "epoch": 0.12, - "learning_rate": 4.420065085267002e-05, - "loss": 3.2416, + "learning_rate": 4.4206947690392805e-05, + "loss": 3.2252, "step": 35000 }, { "epoch": 0.12, - "learning_rate": 4.4184081283677654e-05, - "loss": 3.2498, + "learning_rate": 4.4190396112365357e-05, + "loss": 3.2373, "step": 35100 }, { "epoch": 0.12, - "learning_rate": 4.416751171468528e-05, - "loss": 3.2529, + "learning_rate": 4.417384453433791e-05, + "loss": 3.2372, "step": 35200 }, { "epoch": 0.12, - "learning_rate": 4.4150942145692905e-05, - "loss": 3.2522, + "learning_rate": 4.415729295631046e-05, + "loss": 3.2401, "step": 35300 }, { "epoch": 0.12, - "learning_rate": 4.413437257670054e-05, - "loss": 3.2417, + "learning_rate": 4.4140741378283005e-05, + "loss": 3.2253, "step": 35400 }, { "epoch": 0.12, - "learning_rate": 4.4117803007708164e-05, - "loss": 3.2596, + "learning_rate": 4.412418980025556e-05, + "loss": 3.2226, "step": 35500 }, { "epoch": 0.12, - "learning_rate": 4.4101233438715796e-05, - "loss": 3.2585, + "learning_rate": 4.410763822222811e-05, + "loss": 3.2193, "step": 35600 }, { "epoch": 0.12, - "learning_rate": 4.408466386972342e-05, - "loss": 3.2546, + "learning_rate": 4.409108664420066e-05, + "loss": 3.2422, "step": 35700 }, { "epoch": 0.12, - "learning_rate": 4.406809430073105e-05, - "loss": 3.2534, + "learning_rate": 4.407453506617321e-05, + "loss": 3.2242, "step": 35800 }, { "epoch": 0.12, - "learning_rate": 4.405152473173868e-05, - "loss": 3.2497, + "learning_rate": 4.405798348814576e-05, + "loss": 3.2089, "step": 35900 }, { "epoch": 0.12, - "learning_rate": 4.403495516274631e-05, - "loss": 3.2471, + "learning_rate": 4.4041431910118314e-05, + "loss": 3.2331, "step": 36000 }, { "epoch": 0.12, - "learning_rate": 4.401838559375394e-05, - "loss": 3.2556, + "learning_rate": 4.402488033209086e-05, + "loss": 3.2368, "step": 36100 }, { "epoch": 0.12, - "learning_rate": 4.4001816024761565e-05, - "loss": 3.253, + "learning_rate": 4.400832875406342e-05, + "loss": 3.2214, "step": 36200 }, { "epoch": 0.12, - "learning_rate": 4.39852464557692e-05, - "loss": 3.2383, + "learning_rate": 4.399177717603596e-05, + "loss": 3.2286, "step": 36300 }, { "epoch": 0.12, - "learning_rate": 4.396867688677682e-05, - "loss": 3.2575, + "learning_rate": 4.397522559800852e-05, + "loss": 3.2174, "step": 36400 }, { "epoch": 0.12, - "learning_rate": 4.395210731778445e-05, - "loss": 3.2376, + "learning_rate": 4.3958674019981065e-05, + "loss": 3.239, "step": 36500 }, { "epoch": 0.12, - "learning_rate": 4.393553774879208e-05, - "loss": 3.2524, + "learning_rate": 4.394212244195362e-05, + "loss": 3.2291, "step": 36600 }, { "epoch": 0.12, - "learning_rate": 4.391896817979971e-05, - "loss": 3.2607, + "learning_rate": 4.392557086392617e-05, + "loss": 3.2342, "step": 36700 }, { "epoch": 0.12, - "learning_rate": 4.390239861080734e-05, - "loss": 3.2391, + "learning_rate": 4.390901928589872e-05, + "loss": 3.2233, "step": 36800 }, { "epoch": 0.12, - "learning_rate": 4.3885829041814966e-05, - "loss": 3.2546, + "learning_rate": 4.389246770787127e-05, + "loss": 3.221, "step": 36900 }, { "epoch": 0.12, - "learning_rate": 4.386925947282259e-05, - "loss": 3.2445, + "learning_rate": 4.387591612984382e-05, + "loss": 3.2212, "step": 37000 }, { "epoch": 0.12, - "learning_rate": 4.3852689903830224e-05, - "loss": 3.2477, + "learning_rate": 4.3859364551816375e-05, + "loss": 3.2249, "step": 37100 }, { "epoch": 0.12, - "learning_rate": 4.383612033483786e-05, - "loss": 3.2484, + "learning_rate": 4.384281297378892e-05, + "loss": 3.2197, "step": 37200 }, { "epoch": 0.12, - "learning_rate": 4.381955076584548e-05, - "loss": 3.2554, + "learning_rate": 4.382626139576148e-05, + "loss": 3.2327, "step": 37300 }, { "epoch": 0.12, - "learning_rate": 4.380298119685311e-05, - "loss": 3.2561, + "learning_rate": 4.380970981773402e-05, + "loss": 3.2335, "step": 37400 }, { "epoch": 0.12, - "learning_rate": 4.378641162786074e-05, - "loss": 3.2386, + "learning_rate": 4.3793158239706575e-05, + "loss": 3.2382, "step": 37500 }, { "epoch": 0.12, - "learning_rate": 4.376984205886837e-05, - "loss": 3.2467, + "learning_rate": 4.3776606661679126e-05, + "loss": 3.2364, "step": 37600 }, { "epoch": 0.12, - "learning_rate": 4.375327248987599e-05, - "loss": 3.2595, + "learning_rate": 4.376005508365168e-05, + "loss": 3.2344, "step": 37700 }, { "epoch": 0.13, - "learning_rate": 4.3736702920883625e-05, - "loss": 3.2485, + "learning_rate": 4.374350350562423e-05, + "loss": 3.2241, "step": 37800 }, { "epoch": 0.13, - "learning_rate": 4.372013335189125e-05, - "loss": 3.2467, + "learning_rate": 4.3726951927596774e-05, + "loss": 3.2368, "step": 37900 }, { "epoch": 0.13, - "learning_rate": 4.3703563782898884e-05, - "loss": 3.2477, + "learning_rate": 4.371040034956933e-05, + "loss": 3.2257, "step": 38000 }, { "epoch": 0.13, - "learning_rate": 4.368699421390651e-05, - "loss": 3.2461, + "learning_rate": 4.369384877154188e-05, + "loss": 3.2273, "step": 38100 }, { "epoch": 0.13, - "learning_rate": 4.3670424644914135e-05, - "loss": 3.2596, + "learning_rate": 4.3677297193514436e-05, + "loss": 3.2322, "step": 38200 }, { "epoch": 0.13, - "learning_rate": 4.365385507592177e-05, - "loss": 3.2514, + "learning_rate": 4.366074561548698e-05, + "loss": 3.2209, "step": 38300 }, { "epoch": 0.13, - "learning_rate": 4.36372855069294e-05, - "loss": 3.2442, + "learning_rate": 4.364419403745953e-05, + "loss": 3.2195, "step": 38400 }, { "epoch": 0.13, - "learning_rate": 4.3620715937937026e-05, - "loss": 3.2626, + "learning_rate": 4.3627642459432084e-05, + "loss": 3.2227, "step": 38500 }, { "epoch": 0.13, - "learning_rate": 4.360414636894465e-05, - "loss": 3.2347, + "learning_rate": 4.3611090881404635e-05, + "loss": 3.2196, "step": 38600 }, { "epoch": 0.13, - "learning_rate": 4.3587576799952285e-05, - "loss": 3.2471, + "learning_rate": 4.359453930337719e-05, + "loss": 3.2258, "step": 38700 }, { "epoch": 0.13, - "learning_rate": 4.357100723095991e-05, - "loss": 3.2518, + "learning_rate": 4.357798772534974e-05, + "loss": 3.2258, "step": 38800 }, { "epoch": 0.13, - "learning_rate": 4.355443766196754e-05, - "loss": 3.246, + "learning_rate": 4.356143614732229e-05, + "loss": 3.2172, "step": 38900 }, { "epoch": 0.13, - "learning_rate": 4.353786809297517e-05, - "loss": 3.2378, + "learning_rate": 4.3544884569294835e-05, + "loss": 3.2297, "step": 39000 }, { "epoch": 0.13, - "learning_rate": 4.3521298523982795e-05, - "loss": 3.255, + "learning_rate": 4.352833299126739e-05, + "loss": 3.2326, "step": 39100 }, { "epoch": 0.13, - "learning_rate": 4.350472895499043e-05, - "loss": 3.2643, + "learning_rate": 4.351178141323994e-05, + "loss": 3.2251, "step": 39200 }, { "epoch": 0.13, - "learning_rate": 4.348815938599805e-05, - "loss": 3.2521, + "learning_rate": 4.349522983521249e-05, + "loss": 3.2193, "step": 39300 }, { "epoch": 0.13, - "learning_rate": 4.347158981700568e-05, - "loss": 3.2459, + "learning_rate": 4.347867825718504e-05, + "loss": 3.2255, "step": 39400 }, { "epoch": 0.13, - "learning_rate": 4.345502024801331e-05, - "loss": 3.2469, + "learning_rate": 4.346212667915759e-05, + "loss": 3.2313, "step": 39500 }, { "epoch": 0.13, - "learning_rate": 4.343845067902094e-05, - "loss": 3.2438, + "learning_rate": 4.3445575101130145e-05, + "loss": 3.2326, "step": 39600 }, { "epoch": 0.13, - "learning_rate": 4.342188111002857e-05, - "loss": 3.2418, + "learning_rate": 4.3429023523102696e-05, + "loss": 3.2225, "step": 39700 }, { "epoch": 0.13, - "learning_rate": 4.3405311541036196e-05, - "loss": 3.2665, + "learning_rate": 4.341247194507525e-05, + "loss": 3.2157, "step": 39800 }, { "epoch": 0.13, - "learning_rate": 4.338874197204382e-05, - "loss": 3.2425, + "learning_rate": 4.33959203670478e-05, + "loss": 3.2213, "step": 39900 }, { "epoch": 0.13, - "learning_rate": 4.3372172403051454e-05, - "loss": 3.253, + "learning_rate": 4.3379368789020344e-05, + "loss": 3.2286, "step": 40000 }, { "epoch": 0.13, - "learning_rate": 4.335560283405909e-05, - "loss": 3.2465, + "learning_rate": 4.3362817210992896e-05, + "loss": 3.2452, "step": 40100 }, { "epoch": 0.13, - "learning_rate": 4.3339033265066706e-05, - "loss": 3.2541, + "learning_rate": 4.334626563296545e-05, + "loss": 3.2188, "step": 40200 }, { "epoch": 0.13, - "learning_rate": 4.332246369607434e-05, - "loss": 3.2447, + "learning_rate": 4.3329714054938e-05, + "loss": 3.2279, "step": 40300 }, { "epoch": 0.13, - "learning_rate": 4.330589412708197e-05, - "loss": 3.2481, + "learning_rate": 4.331316247691055e-05, + "loss": 3.2394, "step": 40400 }, { "epoch": 0.13, - "learning_rate": 4.32893245580896e-05, - "loss": 3.2491, + "learning_rate": 4.32966108988831e-05, + "loss": 3.2167, "step": 40500 }, { "epoch": 0.13, - "learning_rate": 4.327275498909722e-05, - "loss": 3.2468, + "learning_rate": 4.3280059320855654e-05, + "loss": 3.233, "step": 40600 }, { "epoch": 0.13, - "learning_rate": 4.3256185420104855e-05, - "loss": 3.2446, + "learning_rate": 4.32635077428282e-05, + "loss": 3.2217, "step": 40700 }, { "epoch": 0.14, - "learning_rate": 4.323961585111248e-05, - "loss": 3.2552, + "learning_rate": 4.324695616480076e-05, + "loss": 3.2317, "step": 40800 }, { "epoch": 0.14, - "learning_rate": 4.3223046282120114e-05, - "loss": 3.2511, + "learning_rate": 4.32304045867733e-05, + "loss": 3.2229, "step": 40900 }, { "epoch": 0.14, - "learning_rate": 4.320647671312774e-05, - "loss": 3.2463, + "learning_rate": 4.321385300874586e-05, + "loss": 3.2299, "step": 41000 }, { "epoch": 0.14, - "learning_rate": 4.3189907144135365e-05, - "loss": 3.253, + "learning_rate": 4.3197301430718405e-05, + "loss": 3.2177, "step": 41100 }, { "epoch": 0.14, - "learning_rate": 4.3173337575143e-05, - "loss": 3.2488, + "learning_rate": 4.318074985269096e-05, + "loss": 3.2237, "step": 41200 }, { "epoch": 0.14, - "learning_rate": 4.315676800615063e-05, - "loss": 3.2353, + "learning_rate": 4.316419827466351e-05, + "loss": 3.2304, "step": 41300 }, { "epoch": 0.14, - "learning_rate": 4.314019843715825e-05, - "loss": 3.2478, + "learning_rate": 4.314764669663606e-05, + "loss": 3.2418, "step": 41400 }, { "epoch": 0.14, - "learning_rate": 4.312362886816588e-05, - "loss": 3.2462, + "learning_rate": 4.313109511860861e-05, + "loss": 3.2326, "step": 41500 }, { "epoch": 0.14, - "learning_rate": 4.3107059299173515e-05, - "loss": 3.2454, + "learning_rate": 4.3114543540581156e-05, + "loss": 3.2331, "step": 41600 }, { "epoch": 0.14, - "learning_rate": 4.309048973018114e-05, - "loss": 3.257, + "learning_rate": 4.3097991962553715e-05, + "loss": 3.2251, "step": 41700 }, { "epoch": 0.14, - "learning_rate": 4.3073920161188766e-05, - "loss": 3.2524, + "learning_rate": 4.308144038452626e-05, + "loss": 3.2351, "step": 41800 }, { "epoch": 0.14, - "learning_rate": 4.30573505921964e-05, - "loss": 3.2396, + "learning_rate": 4.306488880649882e-05, + "loss": 3.2205, "step": 41900 }, { "epoch": 0.14, - "learning_rate": 4.3040781023204025e-05, - "loss": 3.2557, + "learning_rate": 4.304833722847136e-05, + "loss": 3.2284, "step": 42000 }, { "epoch": 0.14, - "learning_rate": 4.302421145421166e-05, - "loss": 3.252, + "learning_rate": 4.3031785650443914e-05, + "loss": 3.2255, "step": 42100 }, { "epoch": 0.14, - "learning_rate": 4.300764188521928e-05, - "loss": 3.2549, + "learning_rate": 4.3015234072416466e-05, + "loss": 3.2218, "step": 42200 }, { "epoch": 0.14, - "learning_rate": 4.299107231622691e-05, - "loss": 3.2609, + "learning_rate": 4.299868249438902e-05, + "loss": 3.2232, "step": 42300 }, { "epoch": 0.14, - "learning_rate": 4.297450274723454e-05, - "loss": 3.2527, + "learning_rate": 4.298213091636157e-05, + "loss": 3.2255, "step": 42400 }, { "epoch": 0.14, - "learning_rate": 4.2957933178242174e-05, - "loss": 3.235, + "learning_rate": 4.2965579338334114e-05, + "loss": 3.2329, "step": 42500 }, { "epoch": 0.14, - "learning_rate": 4.294136360924979e-05, - "loss": 3.2272, + "learning_rate": 4.294902776030667e-05, + "loss": 3.2362, "step": 42600 }, { "epoch": 0.14, - "learning_rate": 4.2924794040257426e-05, - "loss": 3.2437, + "learning_rate": 4.293247618227922e-05, + "loss": 3.2339, "step": 42700 }, { "epoch": 0.14, - "learning_rate": 4.290822447126506e-05, - "loss": 3.2629, + "learning_rate": 4.2915924604251776e-05, + "loss": 3.2127, "step": 42800 }, { "epoch": 0.14, - "learning_rate": 4.2891654902272684e-05, - "loss": 3.2478, + "learning_rate": 4.289937302622432e-05, + "loss": 3.2332, "step": 42900 }, { "epoch": 0.14, - "learning_rate": 4.287508533328031e-05, - "loss": 3.2512, + "learning_rate": 4.288282144819687e-05, + "loss": 3.2336, "step": 43000 }, { "epoch": 0.14, - "learning_rate": 4.285851576428794e-05, - "loss": 3.2496, + "learning_rate": 4.2866269870169424e-05, + "loss": 3.2425, "step": 43100 }, { "epoch": 0.14, - "learning_rate": 4.284194619529557e-05, - "loss": 3.2403, + "learning_rate": 4.2849718292141975e-05, + "loss": 3.2219, "step": 43200 }, { "epoch": 0.14, - "learning_rate": 4.28253766263032e-05, - "loss": 3.242, + "learning_rate": 4.283316671411453e-05, + "loss": 3.2378, "step": 43300 }, { "epoch": 0.14, - "learning_rate": 4.280880705731083e-05, - "loss": 3.243, + "learning_rate": 4.281661513608708e-05, + "loss": 3.2278, "step": 43400 }, { "epoch": 0.14, - "learning_rate": 4.279223748831845e-05, - "loss": 3.2471, + "learning_rate": 4.280006355805963e-05, + "loss": 3.2178, "step": 43500 }, { "epoch": 0.14, - "learning_rate": 4.2775667919326085e-05, - "loss": 3.2592, + "learning_rate": 4.2783511980032175e-05, + "loss": 3.2235, "step": 43600 }, { "epoch": 0.14, - "learning_rate": 4.275909835033372e-05, - "loss": 3.2476, + "learning_rate": 4.276696040200473e-05, + "loss": 3.2406, "step": 43700 }, { - "epoch": 0.15, - "learning_rate": 4.274252878134134e-05, - "loss": 3.248, + "epoch": 0.14, + "learning_rate": 4.275040882397728e-05, + "loss": 3.2458, "step": 43800 }, { "epoch": 0.15, - "learning_rate": 4.272595921234897e-05, - "loss": 3.2378, + "learning_rate": 4.273385724594983e-05, + "loss": 3.2276, "step": 43900 }, { "epoch": 0.15, - "learning_rate": 4.27093896433566e-05, - "loss": 3.2499, + "learning_rate": 4.271730566792238e-05, + "loss": 3.2279, "step": 44000 }, { "epoch": 0.15, - "learning_rate": 4.269282007436423e-05, - "loss": 3.2527, + "learning_rate": 4.270075408989493e-05, + "loss": 3.224, "step": 44100 }, { "epoch": 0.15, - "learning_rate": 4.2676250505371854e-05, - "loss": 3.2443, + "learning_rate": 4.2684202511867484e-05, + "loss": 3.2273, "step": 44200 }, { "epoch": 0.15, - "learning_rate": 4.2659680936379486e-05, - "loss": 3.2477, + "learning_rate": 4.2667650933840036e-05, + "loss": 3.2251, "step": 44300 }, { "epoch": 0.15, - "learning_rate": 4.264311136738711e-05, - "loss": 3.2495, + "learning_rate": 4.265109935581259e-05, + "loss": 3.2316, "step": 44400 }, { "epoch": 0.15, - "learning_rate": 4.2626541798394745e-05, - "loss": 3.245, + "learning_rate": 4.263454777778514e-05, + "loss": 3.2168, "step": 44500 }, { "epoch": 0.15, - "learning_rate": 4.260997222940237e-05, - "loss": 3.2449, + "learning_rate": 4.2617996199757684e-05, + "loss": 3.2252, "step": 44600 }, { "epoch": 0.15, - "learning_rate": 4.2593402660409996e-05, - "loss": 3.2511, + "learning_rate": 4.2601444621730236e-05, + "loss": 3.2334, "step": 44700 }, { "epoch": 0.15, - "learning_rate": 4.257683309141763e-05, - "loss": 3.2413, + "learning_rate": 4.258489304370279e-05, + "loss": 3.2356, "step": 44800 }, { "epoch": 0.15, - "learning_rate": 4.256026352242526e-05, - "loss": 3.2423, + "learning_rate": 4.256834146567534e-05, + "loss": 3.2336, "step": 44900 }, { "epoch": 0.15, - "learning_rate": 4.254369395343288e-05, - "loss": 3.2483, + "learning_rate": 4.255178988764789e-05, + "loss": 3.2092, "step": 45000 }, { "epoch": 0.15, - "learning_rate": 4.252712438444051e-05, - "loss": 3.2414, + "learning_rate": 4.253523830962044e-05, + "loss": 3.2301, "step": 45100 }, { "epoch": 0.15, - "learning_rate": 4.2510554815448146e-05, - "loss": 3.2552, + "learning_rate": 4.2518686731592994e-05, + "loss": 3.223, "step": 45200 }, { "epoch": 0.15, - "learning_rate": 4.249398524645577e-05, - "loss": 3.2474, + "learning_rate": 4.2502135153565545e-05, + "loss": 3.2343, "step": 45300 }, { "epoch": 0.15, - "learning_rate": 4.24774156774634e-05, - "loss": 3.2374, + "learning_rate": 4.24855835755381e-05, + "loss": 3.2362, "step": 45400 }, { "epoch": 0.15, - "learning_rate": 4.246084610847103e-05, - "loss": 3.2392, + "learning_rate": 4.246903199751064e-05, + "loss": 3.2124, "step": 45500 }, { "epoch": 0.15, - "learning_rate": 4.2444276539478656e-05, - "loss": 3.257, + "learning_rate": 4.24524804194832e-05, + "loss": 3.2291, "step": 45600 }, { "epoch": 0.15, - "learning_rate": 4.242770697048629e-05, - "loss": 3.2656, + "learning_rate": 4.2435928841455745e-05, + "loss": 3.2263, "step": 45700 }, { "epoch": 0.15, - "learning_rate": 4.2411137401493914e-05, - "loss": 3.2569, + "learning_rate": 4.2419377263428296e-05, + "loss": 3.2303, "step": 45800 }, { "epoch": 0.15, - "learning_rate": 4.239456783250154e-05, - "loss": 3.2466, + "learning_rate": 4.240282568540085e-05, + "loss": 3.2388, "step": 45900 }, { "epoch": 0.15, - "learning_rate": 4.237799826350917e-05, - "loss": 3.2382, + "learning_rate": 4.23862741073734e-05, + "loss": 3.2159, "step": 46000 }, { "epoch": 0.15, - "learning_rate": 4.2361428694516805e-05, - "loss": 3.2467, + "learning_rate": 4.236972252934595e-05, + "loss": 3.2127, "step": 46100 }, { "epoch": 0.15, - "learning_rate": 4.2344859125524424e-05, - "loss": 3.2501, + "learning_rate": 4.2353170951318496e-05, + "loss": 3.2191, "step": 46200 }, { "epoch": 0.15, - "learning_rate": 4.232828955653206e-05, - "loss": 3.2362, + "learning_rate": 4.2336619373291054e-05, + "loss": 3.2332, "step": 46300 }, { "epoch": 0.15, - "learning_rate": 4.231171998753969e-05, - "loss": 3.2499, + "learning_rate": 4.23200677952636e-05, + "loss": 3.2223, "step": 46400 }, { "epoch": 0.15, - "learning_rate": 4.2295150418547315e-05, - "loss": 3.2487, + "learning_rate": 4.230351621723616e-05, + "loss": 3.2246, "step": 46500 }, { "epoch": 0.15, - "learning_rate": 4.227858084955494e-05, - "loss": 3.252, + "learning_rate": 4.22869646392087e-05, + "loss": 3.2153, "step": 46600 }, { "epoch": 0.15, - "learning_rate": 4.2262011280562574e-05, - "loss": 3.2483, + "learning_rate": 4.227041306118126e-05, + "loss": 3.2131, "step": 46700 }, { - "epoch": 0.16, - "learning_rate": 4.22454417115702e-05, - "loss": 3.2438, + "epoch": 0.15, + "learning_rate": 4.2253861483153806e-05, + "loss": 3.2193, "step": 46800 }, { "epoch": 0.16, - "learning_rate": 4.222887214257783e-05, - "loss": 3.243, + "learning_rate": 4.223730990512636e-05, + "loss": 3.2299, "step": 46900 }, { "epoch": 0.16, - "learning_rate": 4.221230257358546e-05, - "loss": 3.2388, + "learning_rate": 4.222075832709891e-05, + "loss": 3.2321, "step": 47000 }, { "epoch": 0.16, - "learning_rate": 4.2195733004593084e-05, - "loss": 3.2444, + "learning_rate": 4.2204206749071454e-05, + "loss": 3.2386, "step": 47100 }, { "epoch": 0.16, - "learning_rate": 4.2179163435600716e-05, - "loss": 3.2319, + "learning_rate": 4.218765517104401e-05, + "loss": 3.2334, "step": 47200 }, { "epoch": 0.16, - "learning_rate": 4.216259386660835e-05, - "loss": 3.2342, + "learning_rate": 4.217110359301656e-05, + "loss": 3.2362, "step": 47300 }, { "epoch": 0.16, - "learning_rate": 4.2146024297615975e-05, - "loss": 3.2442, + "learning_rate": 4.2154552014989115e-05, + "loss": 3.2236, "step": 47400 }, { "epoch": 0.16, - "learning_rate": 4.21294547286236e-05, - "loss": 3.2393, + "learning_rate": 4.213800043696166e-05, + "loss": 3.2217, "step": 47500 }, { "epoch": 0.16, - "learning_rate": 4.211288515963123e-05, - "loss": 3.2367, + "learning_rate": 4.212144885893421e-05, + "loss": 3.2183, "step": 47600 }, { "epoch": 0.16, - "learning_rate": 4.209631559063886e-05, - "loss": 3.2501, + "learning_rate": 4.210489728090676e-05, + "loss": 3.22, "step": 47700 }, { "epoch": 0.16, - "learning_rate": 4.2079746021646485e-05, - "loss": 3.2452, + "learning_rate": 4.2088345702879315e-05, + "loss": 3.2311, "step": 47800 }, { "epoch": 0.16, - "learning_rate": 4.206317645265412e-05, - "loss": 3.2442, + "learning_rate": 4.2071794124851867e-05, + "loss": 3.2322, "step": 47900 }, { "epoch": 0.16, - "learning_rate": 4.204660688366174e-05, - "loss": 3.2376, + "learning_rate": 4.205524254682441e-05, + "loss": 3.2265, "step": 48000 }, { "epoch": 0.16, - "learning_rate": 4.2030037314669376e-05, - "loss": 3.2367, + "learning_rate": 4.203869096879697e-05, + "loss": 3.2196, "step": 48100 }, { "epoch": 0.16, - "learning_rate": 4.2013467745677e-05, - "loss": 3.2489, + "learning_rate": 4.2022139390769515e-05, + "loss": 3.2476, "step": 48200 }, { "epoch": 0.16, - "learning_rate": 4.199689817668463e-05, - "loss": 3.2521, + "learning_rate": 4.200558781274207e-05, + "loss": 3.2223, "step": 48300 }, { "epoch": 0.16, - "learning_rate": 4.198032860769226e-05, - "loss": 3.2567, + "learning_rate": 4.198903623471462e-05, + "loss": 3.2305, "step": 48400 }, { "epoch": 0.16, - "learning_rate": 4.1963759038699886e-05, - "loss": 3.2288, + "learning_rate": 4.197248465668717e-05, + "loss": 3.239, "step": 48500 }, { "epoch": 0.16, - "learning_rate": 4.194718946970752e-05, - "loss": 3.243, + "learning_rate": 4.195593307865972e-05, + "loss": 3.2237, "step": 48600 }, { "epoch": 0.16, - "learning_rate": 4.1930619900715144e-05, - "loss": 3.2426, + "learning_rate": 4.193938150063227e-05, + "loss": 3.2326, "step": 48700 }, { "epoch": 0.16, - "learning_rate": 4.191405033172277e-05, - "loss": 3.256, + "learning_rate": 4.1922829922604824e-05, + "loss": 3.2289, "step": 48800 }, { "epoch": 0.16, - "learning_rate": 4.18974807627304e-05, - "loss": 3.2583, + "learning_rate": 4.1906278344577376e-05, + "loss": 3.2099, "step": 48900 }, { "epoch": 0.16, - "learning_rate": 4.188091119373803e-05, - "loss": 3.2518, + "learning_rate": 4.188972676654993e-05, + "loss": 3.233, "step": 49000 }, { "epoch": 0.16, - "learning_rate": 4.1864341624745654e-05, - "loss": 3.2468, + "learning_rate": 4.187317518852247e-05, + "loss": 3.2154, "step": 49100 }, { "epoch": 0.16, - "learning_rate": 4.184777205575329e-05, - "loss": 3.2454, + "learning_rate": 4.1856623610495024e-05, + "loss": 3.2276, "step": 49200 }, { "epoch": 0.16, - "learning_rate": 4.183120248676092e-05, - "loss": 3.2491, + "learning_rate": 4.1840072032467575e-05, + "loss": 3.2334, "step": 49300 }, { "epoch": 0.16, - "learning_rate": 4.1814632917768545e-05, - "loss": 3.2646, + "learning_rate": 4.182352045444013e-05, + "loss": 3.2181, "step": 49400 }, { "epoch": 0.16, - "learning_rate": 4.179806334877617e-05, - "loss": 3.2585, + "learning_rate": 4.180696887641268e-05, + "loss": 3.2195, "step": 49500 }, { "epoch": 0.16, - "learning_rate": 4.1781493779783804e-05, - "loss": 3.2457, + "learning_rate": 4.179041729838523e-05, + "loss": 3.2245, "step": 49600 }, { "epoch": 0.16, - "learning_rate": 4.176492421079143e-05, - "loss": 3.2431, + "learning_rate": 4.177386572035778e-05, + "loss": 3.2155, "step": 49700 }, { - "epoch": 0.17, - "learning_rate": 4.174835464179906e-05, - "loss": 3.2433, + "epoch": 0.16, + "learning_rate": 4.175731414233033e-05, + "loss": 3.2247, "step": 49800 }, { "epoch": 0.17, - "learning_rate": 4.173178507280669e-05, - "loss": 3.2441, + "learning_rate": 4.1740762564302885e-05, + "loss": 3.2115, "step": 49900 }, { "epoch": 0.17, - "learning_rate": 4.1715215503814314e-05, - "loss": 3.254, + "learning_rate": 4.1724210986275437e-05, + "loss": 3.2295, "step": 50000 }, { "epoch": 0.17, - "learning_rate": 4.1698645934821946e-05, - "loss": 3.2404, + "learning_rate": 4.170765940824798e-05, + "loss": 3.2108, "step": 50100 }, { "epoch": 0.17, - "learning_rate": 4.168207636582957e-05, - "loss": 3.254, + "learning_rate": 4.169110783022053e-05, + "loss": 3.2176, "step": 50200 }, { "epoch": 0.17, - "learning_rate": 4.16655067968372e-05, - "loss": 3.2355, + "learning_rate": 4.1674556252193085e-05, + "loss": 3.2278, "step": 50300 }, { "epoch": 0.17, - "learning_rate": 4.164893722784483e-05, - "loss": 3.2509, + "learning_rate": 4.1658004674165636e-05, + "loss": 3.2191, "step": 50400 }, { "epoch": 0.17, - "learning_rate": 4.163236765885246e-05, - "loss": 3.2458, + "learning_rate": 4.164145309613819e-05, + "loss": 3.2167, "step": 50500 }, { "epoch": 0.17, - "learning_rate": 4.161579808986009e-05, - "loss": 3.2469, + "learning_rate": 4.162490151811074e-05, + "loss": 3.2384, "step": 50600 }, { "epoch": 0.17, - "learning_rate": 4.1599228520867715e-05, - "loss": 3.2565, + "learning_rate": 4.160834994008329e-05, + "loss": 3.2417, "step": 50700 }, { "epoch": 0.17, - "learning_rate": 4.158265895187535e-05, - "loss": 3.2405, + "learning_rate": 4.159179836205584e-05, + "loss": 3.2092, "step": 50800 }, { "epoch": 0.17, - "learning_rate": 4.156608938288297e-05, - "loss": 3.2361, + "learning_rate": 4.1575246784028394e-05, + "loss": 3.227, "step": 50900 }, { "epoch": 0.17, - "learning_rate": 4.1549519813890606e-05, - "loss": 3.2459, + "learning_rate": 4.155869520600094e-05, + "loss": 3.2181, "step": 51000 }, { "epoch": 0.17, - "learning_rate": 4.153295024489823e-05, - "loss": 3.2475, + "learning_rate": 4.15421436279735e-05, + "loss": 3.2421, "step": 51100 }, { "epoch": 0.17, - "learning_rate": 4.151638067590586e-05, - "loss": 3.2551, + "learning_rate": 4.152559204994604e-05, + "loss": 3.2312, "step": 51200 }, { "epoch": 0.17, - "learning_rate": 4.149981110691349e-05, - "loss": 3.2275, + "learning_rate": 4.1509040471918594e-05, + "loss": 3.2301, "step": 51300 }, { "epoch": 0.17, - "learning_rate": 4.1483241537921116e-05, - "loss": 3.2438, + "learning_rate": 4.1492488893891145e-05, + "loss": 3.2426, "step": 51400 }, { "epoch": 0.17, - "learning_rate": 4.146667196892874e-05, - "loss": 3.2507, + "learning_rate": 4.14759373158637e-05, + "loss": 3.2381, "step": 51500 }, { "epoch": 0.17, - "learning_rate": 4.1450102399936374e-05, - "loss": 3.2429, + "learning_rate": 4.145938573783625e-05, + "loss": 3.2318, "step": 51600 }, { "epoch": 0.17, - "learning_rate": 4.143353283094401e-05, - "loss": 3.2454, + "learning_rate": 4.1442834159808793e-05, + "loss": 3.2254, "step": 51700 }, { "epoch": 0.17, - "learning_rate": 4.141696326195163e-05, - "loss": 3.2471, + "learning_rate": 4.142628258178135e-05, + "loss": 3.2146, "step": 51800 }, { "epoch": 0.17, - "learning_rate": 4.140039369295926e-05, - "loss": 3.2453, + "learning_rate": 4.14097310037539e-05, + "loss": 3.2258, "step": 51900 }, { "epoch": 0.17, - "learning_rate": 4.138382412396689e-05, - "loss": 3.2384, + "learning_rate": 4.1393179425726455e-05, + "loss": 3.2322, "step": 52000 }, { "epoch": 0.17, - "learning_rate": 4.136725455497452e-05, - "loss": 3.2522, + "learning_rate": 4.1376627847699e-05, + "loss": 3.2397, "step": 52100 }, { "epoch": 0.17, - "learning_rate": 4.135068498598215e-05, - "loss": 3.243, + "learning_rate": 4.136007626967156e-05, + "loss": 3.2316, "step": 52200 }, { "epoch": 0.17, - "learning_rate": 4.1334115416989775e-05, - "loss": 3.2496, + "learning_rate": 4.13435246916441e-05, + "loss": 3.231, "step": 52300 }, { "epoch": 0.17, - "learning_rate": 4.13175458479974e-05, - "loss": 3.2456, + "learning_rate": 4.1326973113616655e-05, + "loss": 3.2242, "step": 52400 }, { "epoch": 0.17, - "learning_rate": 4.1300976279005034e-05, - "loss": 3.2445, + "learning_rate": 4.1310421535589206e-05, + "loss": 3.2256, "step": 52500 }, { "epoch": 0.17, - "learning_rate": 4.1284406710012666e-05, - "loss": 3.2577, + "learning_rate": 4.129386995756175e-05, + "loss": 3.2227, "step": 52600 }, { "epoch": 0.17, - "learning_rate": 4.1267837141020285e-05, - "loss": 3.2466, + "learning_rate": 4.127731837953431e-05, + "loss": 3.2128, "step": 52700 }, { "epoch": 0.17, - "learning_rate": 4.125126757202792e-05, - "loss": 3.2486, + "learning_rate": 4.1260766801506854e-05, + "loss": 3.22, "step": 52800 }, { "epoch": 0.18, - "learning_rate": 4.123469800303555e-05, - "loss": 3.2348, + "learning_rate": 4.124421522347941e-05, + "loss": 3.2227, "step": 52900 }, { "epoch": 0.18, - "learning_rate": 4.1218128434043176e-05, - "loss": 3.2439, + "learning_rate": 4.122766364545196e-05, + "loss": 3.2277, "step": 53000 }, { "epoch": 0.18, - "learning_rate": 4.12015588650508e-05, - "loss": 3.2449, + "learning_rate": 4.121111206742451e-05, + "loss": 3.2351, "step": 53100 }, { "epoch": 0.18, - "learning_rate": 4.1184989296058435e-05, - "loss": 3.2434, + "learning_rate": 4.119456048939706e-05, + "loss": 3.21, "step": 53200 }, { "epoch": 0.18, - "learning_rate": 4.116841972706606e-05, - "loss": 3.242, + "learning_rate": 4.117800891136961e-05, + "loss": 3.2246, "step": 53300 }, { "epoch": 0.18, - "learning_rate": 4.115185015807369e-05, - "loss": 3.2493, + "learning_rate": 4.1161457333342164e-05, + "loss": 3.2215, "step": 53400 }, { "epoch": 0.18, - "learning_rate": 4.113528058908132e-05, - "loss": 3.2387, + "learning_rate": 4.114490575531471e-05, + "loss": 3.2247, "step": 53500 }, { "epoch": 0.18, - "learning_rate": 4.1118711020088945e-05, - "loss": 3.2418, + "learning_rate": 4.112835417728727e-05, + "loss": 3.2347, "step": 53600 }, { "epoch": 0.18, - "learning_rate": 4.110214145109658e-05, - "loss": 3.2295, + "learning_rate": 4.111180259925981e-05, + "loss": 3.2127, "step": 53700 }, { "epoch": 0.18, - "learning_rate": 4.108557188210421e-05, - "loss": 3.2463, + "learning_rate": 4.109525102123237e-05, + "loss": 3.2264, "step": 53800 }, { "epoch": 0.18, - "learning_rate": 4.106900231311183e-05, - "loss": 3.2414, + "learning_rate": 4.1078699443204915e-05, + "loss": 3.235, "step": 53900 }, { "epoch": 0.18, - "learning_rate": 4.105243274411946e-05, - "loss": 3.2426, + "learning_rate": 4.106214786517747e-05, + "loss": 3.224, "step": 54000 }, { "epoch": 0.18, - "learning_rate": 4.1035863175127094e-05, - "loss": 3.258, + "learning_rate": 4.104559628715002e-05, + "loss": 3.2122, "step": 54100 }, { "epoch": 0.18, - "learning_rate": 4.101929360613472e-05, - "loss": 3.2583, + "learning_rate": 4.102904470912257e-05, + "loss": 3.2248, "step": 54200 }, { "epoch": 0.18, - "learning_rate": 4.1002724037142346e-05, - "loss": 3.2462, + "learning_rate": 4.101249313109512e-05, + "loss": 3.2246, "step": 54300 }, { "epoch": 0.18, - "learning_rate": 4.098615446814998e-05, - "loss": 3.2532, + "learning_rate": 4.099594155306767e-05, + "loss": 3.2112, "step": 54400 }, { "epoch": 0.18, - "learning_rate": 4.0969584899157604e-05, - "loss": 3.242, + "learning_rate": 4.0979389975040225e-05, + "loss": 3.2193, "step": 54500 }, { "epoch": 0.18, - "learning_rate": 4.095301533016524e-05, - "loss": 3.2382, + "learning_rate": 4.096283839701277e-05, + "loss": 3.2381, "step": 54600 }, { "epoch": 0.18, - "learning_rate": 4.093644576117286e-05, - "loss": 3.2551, + "learning_rate": 4.094628681898532e-05, + "loss": 3.2125, "step": 54700 }, { "epoch": 0.18, - "learning_rate": 4.091987619218049e-05, - "loss": 3.242, + "learning_rate": 4.092973524095787e-05, + "loss": 3.2167, "step": 54800 }, { "epoch": 0.18, - "learning_rate": 4.090330662318812e-05, - "loss": 3.2387, + "learning_rate": 4.0913183662930424e-05, + "loss": 3.2411, "step": 54900 }, { "epoch": 0.18, - "learning_rate": 4.0886737054195754e-05, - "loss": 3.2386, + "learning_rate": 4.0896632084902976e-05, + "loss": 3.2351, "step": 55000 }, { "epoch": 0.18, - "learning_rate": 4.087016748520337e-05, - "loss": 3.247, + "learning_rate": 4.088008050687553e-05, + "loss": 3.229, "step": 55100 }, { "epoch": 0.18, - "learning_rate": 4.0853597916211005e-05, - "loss": 3.2492, + "learning_rate": 4.086352892884808e-05, + "loss": 3.2242, "step": 55200 }, { "epoch": 0.18, - "learning_rate": 4.083702834721864e-05, - "loss": 3.2388, + "learning_rate": 4.084697735082063e-05, + "loss": 3.2375, "step": 55300 }, { "epoch": 0.18, - "learning_rate": 4.0820458778226264e-05, - "loss": 3.247, + "learning_rate": 4.083042577279318e-05, + "loss": 3.2275, "step": 55400 }, { "epoch": 0.18, - "learning_rate": 4.080388920923389e-05, - "loss": 3.2247, + "learning_rate": 4.0813874194765734e-05, + "loss": 3.2358, "step": 55500 }, { "epoch": 0.18, - "learning_rate": 4.078731964024152e-05, - "loss": 3.2509, + "learning_rate": 4.079732261673828e-05, + "loss": 3.2098, "step": 55600 }, { "epoch": 0.18, - "learning_rate": 4.077075007124915e-05, - "loss": 3.2441, + "learning_rate": 4.078077103871083e-05, + "loss": 3.2194, "step": 55700 }, { "epoch": 0.18, - "learning_rate": 4.075418050225678e-05, - "loss": 3.2363, + "learning_rate": 4.076421946068338e-05, + "loss": 3.2233, "step": 55800 }, { "epoch": 0.19, - "learning_rate": 4.0737610933264406e-05, - "loss": 3.2309, + "learning_rate": 4.0747667882655934e-05, + "loss": 3.2256, "step": 55900 }, { "epoch": 0.19, - "learning_rate": 4.072104136427203e-05, - "loss": 3.2455, + "learning_rate": 4.0731116304628485e-05, + "loss": 3.2315, "step": 56000 }, { "epoch": 0.19, - "learning_rate": 4.0704471795279665e-05, - "loss": 3.2337, + "learning_rate": 4.071456472660104e-05, + "loss": 3.231, "step": 56100 }, { "epoch": 0.19, - "learning_rate": 4.06879022262873e-05, - "loss": 3.2319, + "learning_rate": 4.069801314857359e-05, + "loss": 3.2246, "step": 56200 }, { "epoch": 0.19, - "learning_rate": 4.0671332657294916e-05, - "loss": 3.2311, + "learning_rate": 4.068146157054614e-05, + "loss": 3.2184, "step": 56300 }, { "epoch": 0.19, - "learning_rate": 4.065476308830255e-05, - "loss": 3.2484, + "learning_rate": 4.066490999251869e-05, + "loss": 3.2323, "step": 56400 }, { "epoch": 0.19, - "learning_rate": 4.063819351931018e-05, - "loss": 3.2382, + "learning_rate": 4.0648358414491236e-05, + "loss": 3.2269, "step": 56500 }, { "epoch": 0.19, - "learning_rate": 4.062162395031781e-05, - "loss": 3.2409, + "learning_rate": 4.0631806836463795e-05, + "loss": 3.228, "step": 56600 }, { "epoch": 0.19, - "learning_rate": 4.060505438132543e-05, - "loss": 3.2248, + "learning_rate": 4.061525525843634e-05, + "loss": 3.2091, "step": 56700 }, { "epoch": 0.19, - "learning_rate": 4.058848481233306e-05, - "loss": 3.2414, + "learning_rate": 4.059870368040889e-05, + "loss": 3.2117, "step": 56800 }, { "epoch": 0.19, - "learning_rate": 4.057191524334069e-05, - "loss": 3.233, + "learning_rate": 4.058215210238144e-05, + "loss": 3.231, "step": 56900 }, { "epoch": 0.19, - "learning_rate": 4.0555345674348324e-05, - "loss": 3.2484, + "learning_rate": 4.0565600524353994e-05, + "loss": 3.2189, "step": 57000 }, { "epoch": 0.19, - "learning_rate": 4.053877610535595e-05, - "loss": 3.2532, + "learning_rate": 4.0549048946326546e-05, + "loss": 3.2136, "step": 57100 }, { "epoch": 0.19, - "learning_rate": 4.0522206536363576e-05, - "loss": 3.2527, + "learning_rate": 4.053249736829909e-05, + "loss": 3.2382, "step": 57200 }, { "epoch": 0.19, - "learning_rate": 4.050563696737121e-05, - "loss": 3.2447, + "learning_rate": 4.051594579027165e-05, + "loss": 3.2172, "step": 57300 }, { "epoch": 0.19, - "learning_rate": 4.0489067398378834e-05, - "loss": 3.2393, + "learning_rate": 4.0499394212244194e-05, + "loss": 3.2328, "step": 57400 }, { "epoch": 0.19, - "learning_rate": 4.047249782938646e-05, - "loss": 3.2333, + "learning_rate": 4.048284263421675e-05, + "loss": 3.2226, "step": 57500 }, { "epoch": 0.19, - "learning_rate": 4.045592826039409e-05, - "loss": 3.2494, + "learning_rate": 4.04662910561893e-05, + "loss": 3.2263, "step": 57600 }, { "epoch": 0.19, - "learning_rate": 4.043935869140172e-05, - "loss": 3.2256, + "learning_rate": 4.044973947816185e-05, + "loss": 3.2245, "step": 57700 }, { "epoch": 0.19, - "learning_rate": 4.042278912240935e-05, - "loss": 3.2434, + "learning_rate": 4.04331879001344e-05, + "loss": 3.2293, "step": 57800 }, { "epoch": 0.19, - "learning_rate": 4.040621955341698e-05, - "loss": 3.2256, + "learning_rate": 4.041663632210695e-05, + "loss": 3.2203, "step": 57900 }, { "epoch": 0.19, - "learning_rate": 4.03896499844246e-05, - "loss": 3.2336, + "learning_rate": 4.0400084744079504e-05, + "loss": 3.2224, "step": 58000 }, { "epoch": 0.19, - "learning_rate": 4.0373080415432235e-05, - "loss": 3.2468, + "learning_rate": 4.038353316605205e-05, + "loss": 3.2303, "step": 58100 }, { "epoch": 0.19, - "learning_rate": 4.035651084643987e-05, - "loss": 3.2433, + "learning_rate": 4.036698158802461e-05, + "loss": 3.2189, "step": 58200 }, { "epoch": 0.19, - "learning_rate": 4.0339941277447494e-05, - "loss": 3.2476, + "learning_rate": 4.035043000999715e-05, + "loss": 3.2308, "step": 58300 }, { "epoch": 0.19, - "learning_rate": 4.032337170845512e-05, - "loss": 3.2488, + "learning_rate": 4.033387843196971e-05, + "loss": 3.2222, "step": 58400 }, { "epoch": 0.19, - "learning_rate": 4.030680213946275e-05, - "loss": 3.2495, + "learning_rate": 4.0317326853942255e-05, + "loss": 3.2363, "step": 58500 }, { "epoch": 0.19, - "learning_rate": 4.029023257047038e-05, - "loss": 3.234, + "learning_rate": 4.0300775275914806e-05, + "loss": 3.2252, "step": 58600 }, { "epoch": 0.19, - "learning_rate": 4.0273663001478004e-05, - "loss": 3.2345, + "learning_rate": 4.028422369788736e-05, + "loss": 3.2275, "step": 58700 }, { "epoch": 0.19, - "learning_rate": 4.0257093432485636e-05, - "loss": 3.2438, + "learning_rate": 4.026767211985991e-05, + "loss": 3.2232, "step": 58800 }, { - "epoch": 0.2, - "learning_rate": 4.024052386349326e-05, - "loss": 3.2477, + "epoch": 0.19, + "learning_rate": 4.025112054183246e-05, + "loss": 3.223, "step": 58900 }, { "epoch": 0.2, - "learning_rate": 4.0223954294500895e-05, - "loss": 3.2387, + "learning_rate": 4.023456896380501e-05, + "loss": 3.2184, "step": 59000 }, { "epoch": 0.2, - "learning_rate": 4.020738472550852e-05, - "loss": 3.2499, + "learning_rate": 4.0218017385777564e-05, + "loss": 3.2196, "step": 59100 }, { "epoch": 0.2, - "learning_rate": 4.0190815156516146e-05, - "loss": 3.2412, + "learning_rate": 4.020146580775011e-05, + "loss": 3.2299, "step": 59200 }, { "epoch": 0.2, - "learning_rate": 4.017424558752378e-05, - "loss": 3.2494, + "learning_rate": 4.018491422972267e-05, + "loss": 3.2119, "step": 59300 }, { "epoch": 0.2, - "learning_rate": 4.015767601853141e-05, - "loss": 3.2526, + "learning_rate": 4.016836265169521e-05, + "loss": 3.224, "step": 59400 }, { "epoch": 0.2, - "learning_rate": 4.014110644953904e-05, - "loss": 3.2332, + "learning_rate": 4.0151811073667764e-05, + "loss": 3.2295, "step": 59500 }, { "epoch": 0.2, - "learning_rate": 4.012453688054666e-05, - "loss": 3.2525, + "learning_rate": 4.0135259495640316e-05, + "loss": 3.2268, "step": 59600 }, { "epoch": 0.2, - "learning_rate": 4.0107967311554296e-05, - "loss": 3.2355, + "learning_rate": 4.011870791761287e-05, + "loss": 3.2104, "step": 59700 }, { "epoch": 0.2, - "learning_rate": 4.009139774256192e-05, - "loss": 3.2361, + "learning_rate": 4.010215633958542e-05, + "loss": 3.2356, "step": 59800 }, { "epoch": 0.2, - "learning_rate": 4.007482817356955e-05, - "loss": 3.2443, + "learning_rate": 4.008560476155797e-05, + "loss": 3.2117, "step": 59900 }, { "epoch": 0.2, - "learning_rate": 4.005825860457718e-05, - "loss": 3.2448, + "learning_rate": 4.006905318353052e-05, + "loss": 3.217, "step": 60000 }, { "epoch": 0.2, - "learning_rate": 4.0041689035584806e-05, - "loss": 3.2373, + "learning_rate": 4.0052501605503074e-05, + "loss": 3.2305, "step": 60100 }, { "epoch": 0.2, - "learning_rate": 4.002511946659244e-05, - "loss": 3.2407, + "learning_rate": 4.003595002747562e-05, + "loss": 3.2251, "step": 60200 }, { "epoch": 0.2, - "learning_rate": 4.0008549897600064e-05, - "loss": 3.249, + "learning_rate": 4.001939844944817e-05, + "loss": 3.2209, "step": 60300 }, { "epoch": 0.2, - "learning_rate": 3.999198032860769e-05, - "loss": 3.2453, + "learning_rate": 4.000284687142072e-05, + "loss": 3.2148, "step": 60400 }, { "epoch": 0.2, - "learning_rate": 3.997541075961532e-05, - "loss": 3.2505, + "learning_rate": 3.998629529339327e-05, + "loss": 3.2226, "step": 60500 }, { "epoch": 0.2, - "learning_rate": 3.9958841190622955e-05, - "loss": 3.2409, + "learning_rate": 3.9969743715365825e-05, + "loss": 3.2163, "step": 60600 }, { "epoch": 0.2, - "learning_rate": 3.994227162163058e-05, - "loss": 3.2438, + "learning_rate": 3.9953192137338376e-05, + "loss": 3.2369, "step": 60700 }, { "epoch": 0.2, - "learning_rate": 3.992570205263821e-05, - "loss": 3.2413, + "learning_rate": 3.993664055931093e-05, + "loss": 3.2164, "step": 60800 }, { "epoch": 0.2, - "learning_rate": 3.990913248364584e-05, - "loss": 3.2422, + "learning_rate": 3.992008898128348e-05, + "loss": 3.2144, "step": 60900 }, { "epoch": 0.2, - "learning_rate": 3.9892562914653465e-05, - "loss": 3.2408, + "learning_rate": 3.990353740325603e-05, + "loss": 3.2206, "step": 61000 }, { "epoch": 0.2, - "learning_rate": 3.987599334566109e-05, - "loss": 3.2549, + "learning_rate": 3.9886985825228576e-05, + "loss": 3.2236, "step": 61100 }, { "epoch": 0.2, - "learning_rate": 3.9859423776668724e-05, - "loss": 3.2536, + "learning_rate": 3.9870434247201134e-05, + "loss": 3.2361, "step": 61200 }, { "epoch": 0.2, - "learning_rate": 3.984285420767635e-05, - "loss": 3.2476, + "learning_rate": 3.985388266917368e-05, + "loss": 3.2302, "step": 61300 }, { "epoch": 0.2, - "learning_rate": 3.982628463868398e-05, - "loss": 3.2499, + "learning_rate": 3.983733109114623e-05, + "loss": 3.2151, "step": 61400 }, { "epoch": 0.2, - "learning_rate": 3.980971506969161e-05, - "loss": 3.2339, + "learning_rate": 3.982077951311878e-05, + "loss": 3.2323, "step": 61500 }, { "epoch": 0.2, - "learning_rate": 3.9793145500699234e-05, - "loss": 3.2456, + "learning_rate": 3.9804227935091334e-05, + "loss": 3.2227, "step": 61600 }, { "epoch": 0.2, - "learning_rate": 3.9776575931706866e-05, - "loss": 3.2148, + "learning_rate": 3.9787676357063886e-05, + "loss": 3.2192, "step": 61700 }, { "epoch": 0.2, - "learning_rate": 3.97600063627145e-05, - "loss": 3.2546, + "learning_rate": 3.977112477903643e-05, + "loss": 3.2176, "step": 61800 }, { - "epoch": 0.21, - "learning_rate": 3.9743436793722125e-05, - "loss": 3.2489, + "epoch": 0.2, + "learning_rate": 3.975457320100899e-05, + "loss": 3.2302, "step": 61900 }, { "epoch": 0.21, - "learning_rate": 3.972686722472975e-05, - "loss": 3.2425, + "learning_rate": 3.9738021622981534e-05, + "loss": 3.2133, "step": 62000 }, { "epoch": 0.21, - "learning_rate": 3.971029765573738e-05, - "loss": 3.243, + "learning_rate": 3.972147004495409e-05, + "loss": 3.2085, "step": 62100 }, { "epoch": 0.21, - "learning_rate": 3.969372808674501e-05, - "loss": 3.2491, + "learning_rate": 3.970491846692664e-05, + "loss": 3.2091, "step": 62200 }, { "epoch": 0.21, - "learning_rate": 3.967715851775264e-05, - "loss": 3.2368, + "learning_rate": 3.9688366888899195e-05, + "loss": 3.2252, "step": 62300 }, { "epoch": 0.21, - "learning_rate": 3.966058894876027e-05, - "loss": 3.2563, + "learning_rate": 3.967181531087174e-05, + "loss": 3.2102, "step": 62400 }, { "epoch": 0.21, - "learning_rate": 3.964401937976789e-05, - "loss": 3.2389, + "learning_rate": 3.965526373284429e-05, + "loss": 3.2291, "step": 62500 }, { "epoch": 0.21, - "learning_rate": 3.9627449810775526e-05, - "loss": 3.243, + "learning_rate": 3.963871215481684e-05, + "loss": 3.2343, "step": 62600 }, { "epoch": 0.21, - "learning_rate": 3.961088024178315e-05, - "loss": 3.2594, + "learning_rate": 3.962216057678939e-05, + "loss": 3.2171, "step": 62700 }, { "epoch": 0.21, - "learning_rate": 3.959431067279078e-05, - "loss": 3.2334, + "learning_rate": 3.9605608998761947e-05, + "loss": 3.2261, "step": 62800 }, { "epoch": 0.21, - "learning_rate": 3.957774110379841e-05, - "loss": 3.2215, + "learning_rate": 3.958905742073449e-05, + "loss": 3.203, "step": 62900 }, { "epoch": 0.21, - "learning_rate": 3.956117153480604e-05, - "loss": 3.2579, + "learning_rate": 3.957250584270705e-05, + "loss": 3.2202, "step": 63000 }, { "epoch": 0.21, - "learning_rate": 3.954460196581367e-05, - "loss": 3.2352, + "learning_rate": 3.9555954264679595e-05, + "loss": 3.2124, "step": 63100 }, { "epoch": 0.21, - "learning_rate": 3.9528032396821294e-05, - "loss": 3.2356, + "learning_rate": 3.9539402686652146e-05, + "loss": 3.2225, "step": 63200 }, { "epoch": 0.21, - "learning_rate": 3.951146282782893e-05, - "loss": 3.2423, + "learning_rate": 3.95228511086247e-05, + "loss": 3.2152, "step": 63300 }, { "epoch": 0.21, - "learning_rate": 3.949489325883655e-05, - "loss": 3.2382, + "learning_rate": 3.950629953059725e-05, + "loss": 3.2256, "step": 63400 }, { "epoch": 0.21, - "learning_rate": 3.9478323689844185e-05, - "loss": 3.2387, + "learning_rate": 3.94897479525698e-05, + "loss": 3.2302, "step": 63500 }, { "epoch": 0.21, - "learning_rate": 3.946175412085181e-05, - "loss": 3.2456, + "learning_rate": 3.9473196374542346e-05, + "loss": 3.2183, "step": 63600 }, { "epoch": 0.21, - "learning_rate": 3.944518455185944e-05, - "loss": 3.2462, + "learning_rate": 3.9456644796514904e-05, + "loss": 3.2141, "step": 63700 }, { "epoch": 0.21, - "learning_rate": 3.942861498286707e-05, - "loss": 3.236, + "learning_rate": 3.944009321848745e-05, + "loss": 3.2292, "step": 63800 }, { "epoch": 0.21, - "learning_rate": 3.9412045413874695e-05, - "loss": 3.2431, + "learning_rate": 3.942354164046001e-05, + "loss": 3.2087, "step": 63900 }, { "epoch": 0.21, - "learning_rate": 3.939547584488232e-05, - "loss": 3.2574, + "learning_rate": 3.940699006243255e-05, + "loss": 3.2305, "step": 64000 }, { "epoch": 0.21, - "learning_rate": 3.9378906275889954e-05, - "loss": 3.2494, + "learning_rate": 3.9390438484405104e-05, + "loss": 3.2297, "step": 64100 }, { "epoch": 0.21, - "learning_rate": 3.9362336706897586e-05, - "loss": 3.228, + "learning_rate": 3.9373886906377655e-05, + "loss": 3.2315, "step": 64200 }, { "epoch": 0.21, - "learning_rate": 3.934576713790521e-05, - "loss": 3.2459, + "learning_rate": 3.935733532835021e-05, + "loss": 3.2187, "step": 64300 }, { "epoch": 0.21, - "learning_rate": 3.932919756891284e-05, - "loss": 3.246, + "learning_rate": 3.934078375032276e-05, + "loss": 3.2354, "step": 64400 }, { "epoch": 0.21, - "learning_rate": 3.931262799992047e-05, - "loss": 3.2319, + "learning_rate": 3.932423217229531e-05, + "loss": 3.2133, "step": 64500 }, { "epoch": 0.21, - "learning_rate": 3.9296058430928096e-05, - "loss": 3.2416, + "learning_rate": 3.930768059426786e-05, + "loss": 3.205, "step": 64600 }, { "epoch": 0.21, - "learning_rate": 3.927948886193573e-05, - "loss": 3.2388, + "learning_rate": 3.9291129016240407e-05, + "loss": 3.2235, "step": 64700 }, { "epoch": 0.21, - "learning_rate": 3.9262919292943355e-05, - "loss": 3.2518, + "learning_rate": 3.9274577438212965e-05, + "loss": 3.2307, "step": 64800 }, { - "epoch": 0.22, - "learning_rate": 3.924634972395098e-05, - "loss": 3.2544, + "epoch": 0.21, + "learning_rate": 3.925802586018551e-05, + "loss": 3.2245, "step": 64900 }, { "epoch": 0.22, - "learning_rate": 3.922978015495861e-05, - "loss": 3.2276, + "learning_rate": 3.924147428215806e-05, + "loss": 3.2386, "step": 65000 }, { "epoch": 0.22, - "learning_rate": 3.921321058596624e-05, - "loss": 3.2407, + "learning_rate": 3.922492270413061e-05, + "loss": 3.2195, "step": 65100 }, { "epoch": 0.22, - "learning_rate": 3.9196641016973865e-05, - "loss": 3.2388, + "learning_rate": 3.9208371126103165e-05, + "loss": 3.2069, "step": 65200 }, { "epoch": 0.22, - "learning_rate": 3.91800714479815e-05, - "loss": 3.2347, + "learning_rate": 3.9191819548075716e-05, + "loss": 3.2237, "step": 65300 }, { "epoch": 0.22, - "learning_rate": 3.916350187898913e-05, - "loss": 3.23, + "learning_rate": 3.917526797004827e-05, + "loss": 3.2154, "step": 65400 }, { "epoch": 0.22, - "learning_rate": 3.9146932309996756e-05, - "loss": 3.256, + "learning_rate": 3.915871639202082e-05, + "loss": 3.226, "step": 65500 }, { "epoch": 0.22, - "learning_rate": 3.913036274100438e-05, - "loss": 3.2215, + "learning_rate": 3.914216481399337e-05, + "loss": 3.2138, "step": 65600 }, { "epoch": 0.22, - "learning_rate": 3.911379317201201e-05, - "loss": 3.2425, + "learning_rate": 3.9125613235965916e-05, + "loss": 3.2123, "step": 65700 }, { "epoch": 0.22, - "learning_rate": 3.909722360301964e-05, - "loss": 3.238, + "learning_rate": 3.910906165793847e-05, + "loss": 3.2206, "step": 65800 }, { "epoch": 0.22, - "learning_rate": 3.908065403402727e-05, - "loss": 3.2399, + "learning_rate": 3.909251007991102e-05, + "loss": 3.2263, "step": 65900 }, { "epoch": 0.22, - "learning_rate": 3.906408446503489e-05, - "loss": 3.2504, + "learning_rate": 3.907595850188357e-05, + "loss": 3.2236, "step": 66000 }, { "epoch": 0.22, - "learning_rate": 3.9047514896042524e-05, - "loss": 3.242, + "learning_rate": 3.905940692385612e-05, + "loss": 3.2258, "step": 66100 }, { "epoch": 0.22, - "learning_rate": 3.903094532705016e-05, - "loss": 3.227, + "learning_rate": 3.9042855345828674e-05, + "loss": 3.2201, "step": 66200 }, { "epoch": 0.22, - "learning_rate": 3.901437575805778e-05, - "loss": 3.2359, + "learning_rate": 3.9026303767801225e-05, + "loss": 3.2243, "step": 66300 }, { "epoch": 0.22, - "learning_rate": 3.899780618906541e-05, - "loss": 3.2384, + "learning_rate": 3.900975218977378e-05, + "loss": 3.2093, "step": 66400 }, { "epoch": 0.22, - "learning_rate": 3.898123662007304e-05, - "loss": 3.2398, + "learning_rate": 3.899320061174633e-05, + "loss": 3.2242, "step": 66500 }, { "epoch": 0.22, - "learning_rate": 3.896466705108067e-05, - "loss": 3.227, + "learning_rate": 3.8976649033718873e-05, + "loss": 3.2244, "step": 66600 }, { "epoch": 0.22, - "learning_rate": 3.89480974820883e-05, - "loss": 3.2451, + "learning_rate": 3.896009745569143e-05, + "loss": 3.2154, "step": 66700 }, { "epoch": 0.22, - "learning_rate": 3.8931527913095925e-05, - "loss": 3.2433, + "learning_rate": 3.894354587766398e-05, + "loss": 3.2336, "step": 66800 }, { "epoch": 0.22, - "learning_rate": 3.891495834410355e-05, - "loss": 3.2375, + "learning_rate": 3.892699429963653e-05, + "loss": 3.2193, "step": 66900 }, { "epoch": 0.22, - "learning_rate": 3.8898388775111184e-05, - "loss": 3.2454, + "learning_rate": 3.891044272160908e-05, + "loss": 3.2151, "step": 67000 }, { "epoch": 0.22, - "learning_rate": 3.8881819206118816e-05, - "loss": 3.2461, + "learning_rate": 3.889389114358163e-05, + "loss": 3.2257, "step": 67100 }, { "epoch": 0.22, - "learning_rate": 3.8865249637126435e-05, - "loss": 3.2302, + "learning_rate": 3.887733956555418e-05, + "loss": 3.2287, "step": 67200 }, { "epoch": 0.22, - "learning_rate": 3.884868006813407e-05, - "loss": 3.2354, + "learning_rate": 3.886078798752673e-05, + "loss": 3.233, "step": 67300 }, { "epoch": 0.22, - "learning_rate": 3.88321104991417e-05, - "loss": 3.2427, + "learning_rate": 3.8844236409499286e-05, + "loss": 3.2373, "step": 67400 }, { "epoch": 0.22, - "learning_rate": 3.8815540930149326e-05, - "loss": 3.2403, + "learning_rate": 3.882768483147183e-05, + "loss": 3.2168, "step": 67500 }, { "epoch": 0.22, - "learning_rate": 3.879897136115695e-05, - "loss": 3.2245, + "learning_rate": 3.881113325344439e-05, + "loss": 3.2128, "step": 67600 }, { "epoch": 0.22, - "learning_rate": 3.8782401792164585e-05, - "loss": 3.2394, + "learning_rate": 3.8794581675416934e-05, + "loss": 3.2286, "step": 67700 }, { "epoch": 0.22, - "learning_rate": 3.876583222317221e-05, - "loss": 3.2532, + "learning_rate": 3.877803009738949e-05, + "loss": 3.2202, "step": 67800 }, { - "epoch": 0.23, - "learning_rate": 3.874926265417984e-05, - "loss": 3.2535, + "epoch": 0.22, + "learning_rate": 3.876147851936204e-05, + "loss": 3.2161, "step": 67900 }, { "epoch": 0.23, - "learning_rate": 3.873269308518747e-05, - "loss": 3.2401, + "learning_rate": 3.874492694133459e-05, + "loss": 3.2183, "step": 68000 }, { "epoch": 0.23, - "learning_rate": 3.8716123516195095e-05, - "loss": 3.2349, + "learning_rate": 3.872837536330714e-05, + "loss": 3.2203, "step": 68100 }, { "epoch": 0.23, - "learning_rate": 3.869955394720273e-05, - "loss": 3.253, + "learning_rate": 3.8711823785279685e-05, + "loss": 3.2274, "step": 68200 }, { "epoch": 0.23, - "learning_rate": 3.868298437821036e-05, - "loss": 3.2332, + "learning_rate": 3.8695272207252244e-05, + "loss": 3.2185, "step": 68300 }, { "epoch": 0.23, - "learning_rate": 3.866641480921798e-05, - "loss": 3.2401, + "learning_rate": 3.867872062922479e-05, + "loss": 3.2274, "step": 68400 }, { "epoch": 0.23, - "learning_rate": 3.864984524022561e-05, - "loss": 3.2359, + "learning_rate": 3.866216905119735e-05, + "loss": 3.2088, "step": 68500 }, { "epoch": 0.23, - "learning_rate": 3.8633275671233244e-05, - "loss": 3.2458, + "learning_rate": 3.864561747316989e-05, + "loss": 3.2172, "step": 68600 }, { "epoch": 0.23, - "learning_rate": 3.861670610224087e-05, - "loss": 3.2493, + "learning_rate": 3.8629065895142443e-05, + "loss": 3.22, "step": 68700 }, { "epoch": 0.23, - "learning_rate": 3.8600136533248496e-05, - "loss": 3.2251, + "learning_rate": 3.8612514317114995e-05, + "loss": 3.2296, "step": 68800 }, { "epoch": 0.23, - "learning_rate": 3.858356696425613e-05, - "loss": 3.2484, + "learning_rate": 3.859596273908755e-05, + "loss": 3.2238, "step": 68900 }, { "epoch": 0.23, - "learning_rate": 3.8566997395263754e-05, - "loss": 3.2424, + "learning_rate": 3.85794111610601e-05, + "loss": 3.2144, "step": 69000 }, { "epoch": 0.23, - "learning_rate": 3.855042782627139e-05, - "loss": 3.2317, + "learning_rate": 3.856285958303264e-05, + "loss": 3.2282, "step": 69100 }, { "epoch": 0.23, - "learning_rate": 3.853385825727901e-05, - "loss": 3.2362, + "learning_rate": 3.85463080050052e-05, + "loss": 3.215, "step": 69200 }, { "epoch": 0.23, - "learning_rate": 3.851728868828664e-05, - "loss": 3.2435, + "learning_rate": 3.8529756426977746e-05, + "loss": 3.2107, "step": 69300 }, { "epoch": 0.23, - "learning_rate": 3.850071911929427e-05, - "loss": 3.2397, + "learning_rate": 3.8513204848950305e-05, + "loss": 3.2129, "step": 69400 }, { "epoch": 0.23, - "learning_rate": 3.8484149550301904e-05, - "loss": 3.2372, + "learning_rate": 3.849665327092285e-05, + "loss": 3.2153, "step": 69500 }, { "epoch": 0.23, - "learning_rate": 3.846757998130952e-05, - "loss": 3.2365, + "learning_rate": 3.84801016928954e-05, + "loss": 3.2096, "step": 69600 }, { "epoch": 0.23, - "learning_rate": 3.8451010412317155e-05, - "loss": 3.2557, + "learning_rate": 3.846355011486795e-05, + "loss": 3.2298, "step": 69700 }, { "epoch": 0.23, - "learning_rate": 3.843444084332479e-05, - "loss": 3.2363, + "learning_rate": 3.8446998536840504e-05, + "loss": 3.2375, "step": 69800 }, { "epoch": 0.23, - "learning_rate": 3.8417871274332414e-05, - "loss": 3.2406, + "learning_rate": 3.8430446958813056e-05, + "loss": 3.2142, "step": 69900 }, { "epoch": 0.23, - "learning_rate": 3.840130170534004e-05, - "loss": 3.2325, + "learning_rate": 3.841389538078561e-05, + "loss": 3.2231, "step": 70000 }, { "epoch": 0.23, - "learning_rate": 3.838473213634767e-05, - "loss": 3.2417, + "learning_rate": 3.839734380275816e-05, + "loss": 3.2332, "step": 70100 }, { "epoch": 0.23, - "learning_rate": 3.83681625673553e-05, - "loss": 3.2478, + "learning_rate": 3.8380792224730704e-05, + "loss": 3.2367, "step": 70200 }, { "epoch": 0.23, - "learning_rate": 3.835159299836293e-05, - "loss": 3.2409, + "learning_rate": 3.8364240646703256e-05, + "loss": 3.2115, "step": 70300 }, { "epoch": 0.23, - "learning_rate": 3.8335023429370556e-05, - "loss": 3.2449, + "learning_rate": 3.834768906867581e-05, + "loss": 3.2244, "step": 70400 }, { "epoch": 0.23, - "learning_rate": 3.831845386037818e-05, - "loss": 3.2395, + "learning_rate": 3.833113749064836e-05, + "loss": 3.2218, "step": 70500 }, { "epoch": 0.23, - "learning_rate": 3.8301884291385815e-05, - "loss": 3.2519, + "learning_rate": 3.831458591262091e-05, + "loss": 3.204, "step": 70600 }, { "epoch": 0.23, - "learning_rate": 3.828531472239345e-05, - "loss": 3.235, + "learning_rate": 3.829803433459346e-05, + "loss": 3.2202, "step": 70700 }, { "epoch": 0.23, - "learning_rate": 3.8268745153401067e-05, - "loss": 3.2414, + "learning_rate": 3.8281482756566014e-05, + "loss": 3.2192, "step": 70800 }, { "epoch": 0.23, - "learning_rate": 3.82521755844087e-05, - "loss": 3.2598, + "learning_rate": 3.8264931178538565e-05, + "loss": 3.224, "step": 70900 }, { "epoch": 0.24, - "learning_rate": 3.823560601541633e-05, - "loss": 3.2426, + "learning_rate": 3.824837960051112e-05, + "loss": 3.2117, "step": 71000 }, { "epoch": 0.24, - "learning_rate": 3.821903644642396e-05, - "loss": 3.2473, + "learning_rate": 3.823182802248367e-05, + "loss": 3.2212, "step": 71100 }, { "epoch": 0.24, - "learning_rate": 3.820246687743158e-05, - "loss": 3.2395, + "learning_rate": 3.821527644445621e-05, + "loss": 3.2228, "step": 71200 }, { "epoch": 0.24, - "learning_rate": 3.8185897308439216e-05, - "loss": 3.2264, + "learning_rate": 3.8198724866428765e-05, + "loss": 3.2269, "step": 71300 }, { "epoch": 0.24, - "learning_rate": 3.816932773944684e-05, - "loss": 3.2459, + "learning_rate": 3.8182173288401316e-05, + "loss": 3.2196, "step": 71400 }, { "epoch": 0.24, - "learning_rate": 3.8152758170454474e-05, - "loss": 3.2449, + "learning_rate": 3.816562171037387e-05, + "loss": 3.2253, "step": 71500 }, { "epoch": 0.24, - "learning_rate": 3.81361886014621e-05, - "loss": 3.2336, + "learning_rate": 3.814907013234642e-05, + "loss": 3.2346, "step": 71600 }, { "epoch": 0.24, - "learning_rate": 3.8119619032469726e-05, - "loss": 3.2412, + "learning_rate": 3.813251855431897e-05, + "loss": 3.2139, "step": 71700 }, { "epoch": 0.24, - "learning_rate": 3.810304946347736e-05, - "loss": 3.253, + "learning_rate": 3.811596697629152e-05, + "loss": 3.2337, "step": 71800 }, { "epoch": 0.24, - "learning_rate": 3.808647989448499e-05, - "loss": 3.2446, + "learning_rate": 3.8099415398264074e-05, + "loss": 3.2227, "step": 71900 }, { "epoch": 0.24, - "learning_rate": 3.806991032549262e-05, - "loss": 3.2455, + "learning_rate": 3.8082863820236626e-05, + "loss": 3.2295, "step": 72000 }, { "epoch": 0.24, - "learning_rate": 3.805334075650024e-05, - "loss": 3.2407, + "learning_rate": 3.806631224220917e-05, + "loss": 3.2226, "step": 72100 }, { "epoch": 0.24, - "learning_rate": 3.8036771187507875e-05, - "loss": 3.2333, + "learning_rate": 3.804976066418173e-05, + "loss": 3.2131, "step": 72200 }, { "epoch": 0.24, - "learning_rate": 3.80202016185155e-05, - "loss": 3.2358, + "learning_rate": 3.8033209086154274e-05, + "loss": 3.2247, "step": 72300 }, { "epoch": 0.24, - "learning_rate": 3.800363204952313e-05, - "loss": 3.24, + "learning_rate": 3.8016657508126826e-05, + "loss": 3.2186, "step": 72400 }, { "epoch": 0.24, - "learning_rate": 3.798706248053076e-05, - "loss": 3.2246, + "learning_rate": 3.800010593009938e-05, + "loss": 3.2117, "step": 72500 }, { "epoch": 0.24, - "learning_rate": 3.7970492911538385e-05, - "loss": 3.2363, + "learning_rate": 3.798355435207193e-05, + "loss": 3.2314, "step": 72600 }, { "epoch": 0.24, - "learning_rate": 3.795392334254602e-05, - "loss": 3.2273, + "learning_rate": 3.796700277404448e-05, + "loss": 3.2089, "step": 72700 }, { "epoch": 0.24, - "learning_rate": 3.7937353773553644e-05, - "loss": 3.2304, + "learning_rate": 3.7950451196017025e-05, + "loss": 3.226, "step": 72800 }, { "epoch": 0.24, - "learning_rate": 3.792078420456127e-05, - "loss": 3.2442, + "learning_rate": 3.7933899617989584e-05, + "loss": 3.2161, "step": 72900 }, { "epoch": 0.24, - "learning_rate": 3.79042146355689e-05, - "loss": 3.2451, + "learning_rate": 3.791734803996213e-05, + "loss": 3.2283, "step": 73000 }, { "epoch": 0.24, - "learning_rate": 3.7887645066576535e-05, - "loss": 3.2503, + "learning_rate": 3.790079646193469e-05, + "loss": 3.2215, "step": 73100 }, { "epoch": 0.24, - "learning_rate": 3.787107549758416e-05, - "loss": 3.2374, + "learning_rate": 3.788424488390723e-05, + "loss": 3.213, "step": 73200 }, { "epoch": 0.24, - "learning_rate": 3.7854505928591787e-05, - "loss": 3.228, + "learning_rate": 3.786769330587979e-05, + "loss": 3.2152, "step": 73300 }, { "epoch": 0.24, - "learning_rate": 3.783793635959942e-05, - "loss": 3.2312, + "learning_rate": 3.7851141727852335e-05, + "loss": 3.2219, "step": 73400 }, { "epoch": 0.24, - "learning_rate": 3.7821366790607045e-05, - "loss": 3.2332, + "learning_rate": 3.7834590149824886e-05, + "loss": 3.2307, "step": 73500 }, { "epoch": 0.24, - "learning_rate": 3.780479722161467e-05, - "loss": 3.2484, + "learning_rate": 3.781803857179744e-05, + "loss": 3.2132, "step": 73600 }, { "epoch": 0.24, - "learning_rate": 3.77882276526223e-05, - "loss": 3.2383, + "learning_rate": 3.780148699376998e-05, + "loss": 3.2082, "step": 73700 }, { "epoch": 0.24, - "learning_rate": 3.777165808362993e-05, - "loss": 3.2439, + "learning_rate": 3.778493541574254e-05, + "loss": 3.2206, "step": 73800 }, { "epoch": 0.24, - "learning_rate": 3.775508851463756e-05, - "loss": 3.2455, + "learning_rate": 3.7768383837715086e-05, + "loss": 3.228, "step": 73900 }, { - "epoch": 0.25, - "learning_rate": 3.773851894564519e-05, - "loss": 3.2369, + "epoch": 0.24, + "learning_rate": 3.7751832259687644e-05, + "loss": 3.2302, "step": 74000 }, { "epoch": 0.25, - "learning_rate": 3.772194937665281e-05, - "loss": 3.2377, + "learning_rate": 3.773528068166019e-05, + "loss": 3.2272, "step": 74100 }, { "epoch": 0.25, - "learning_rate": 3.7705379807660446e-05, - "loss": 3.2421, + "learning_rate": 3.771872910363274e-05, + "loss": 3.2328, "step": 74200 }, { "epoch": 0.25, - "learning_rate": 3.768881023866807e-05, - "loss": 3.244, + "learning_rate": 3.770217752560529e-05, + "loss": 3.2222, "step": 74300 }, { "epoch": 0.25, - "learning_rate": 3.7672240669675704e-05, - "loss": 3.2479, + "learning_rate": 3.7685625947577844e-05, + "loss": 3.2183, "step": 74400 }, { "epoch": 0.25, - "learning_rate": 3.765567110068333e-05, - "loss": 3.2367, + "learning_rate": 3.7669074369550396e-05, + "loss": 3.2262, "step": 74500 }, { "epoch": 0.25, - "learning_rate": 3.7639101531690956e-05, - "loss": 3.2384, + "learning_rate": 3.765252279152295e-05, + "loss": 3.2263, "step": 74600 }, { "epoch": 0.25, - "learning_rate": 3.762253196269859e-05, - "loss": 3.2461, + "learning_rate": 3.76359712134955e-05, + "loss": 3.2287, "step": 74700 }, { "epoch": 0.25, - "learning_rate": 3.7605962393706214e-05, - "loss": 3.2371, + "learning_rate": 3.7619419635468044e-05, + "loss": 3.2146, "step": 74800 }, { "epoch": 0.25, - "learning_rate": 3.758939282471384e-05, - "loss": 3.2354, + "learning_rate": 3.76028680574406e-05, + "loss": 3.2161, "step": 74900 }, { "epoch": 0.25, - "learning_rate": 3.757282325572147e-05, - "loss": 3.2274, + "learning_rate": 3.758631647941315e-05, + "loss": 3.2316, "step": 75000 }, { "epoch": 0.25, - "learning_rate": 3.7556253686729105e-05, - "loss": 3.2474, + "learning_rate": 3.75697649013857e-05, + "loss": 3.212, "step": 75100 }, { "epoch": 0.25, - "learning_rate": 3.753968411773673e-05, - "loss": 3.2328, + "learning_rate": 3.755321332335825e-05, + "loss": 3.228, "step": 75200 }, { "epoch": 0.25, - "learning_rate": 3.752311454874436e-05, - "loss": 3.248, + "learning_rate": 3.75366617453308e-05, + "loss": 3.2138, "step": 75300 }, { "epoch": 0.25, - "learning_rate": 3.750654497975199e-05, - "loss": 3.2355, + "learning_rate": 3.752011016730335e-05, + "loss": 3.2177, "step": 75400 }, { "epoch": 0.25, - "learning_rate": 3.7489975410759615e-05, - "loss": 3.2228, + "learning_rate": 3.7503558589275905e-05, + "loss": 3.2179, "step": 75500 }, { "epoch": 0.25, - "learning_rate": 3.747340584176725e-05, - "loss": 3.2439, + "learning_rate": 3.7487007011248456e-05, + "loss": 3.2271, "step": 75600 }, { "epoch": 0.25, - "learning_rate": 3.7456836272774874e-05, - "loss": 3.236, + "learning_rate": 3.747045543322101e-05, + "loss": 3.2057, "step": 75700 }, { "epoch": 0.25, - "learning_rate": 3.74402667037825e-05, - "loss": 3.2324, + "learning_rate": 3.745390385519355e-05, + "loss": 3.2261, "step": 75800 }, { "epoch": 0.25, - "learning_rate": 3.742369713479013e-05, - "loss": 3.2345, + "learning_rate": 3.7437352277166104e-05, + "loss": 3.2153, "step": 75900 }, { "epoch": 0.25, - "learning_rate": 3.7407127565797765e-05, - "loss": 3.2541, + "learning_rate": 3.7420800699138656e-05, + "loss": 3.2154, "step": 76000 }, { "epoch": 0.25, - "learning_rate": 3.7390557996805384e-05, - "loss": 3.2353, + "learning_rate": 3.740424912111121e-05, + "loss": 3.2243, "step": 76100 }, { "epoch": 0.25, - "learning_rate": 3.7373988427813017e-05, - "loss": 3.2357, + "learning_rate": 3.738769754308376e-05, + "loss": 3.2105, "step": 76200 }, { "epoch": 0.25, - "learning_rate": 3.735741885882065e-05, - "loss": 3.2395, + "learning_rate": 3.737114596505631e-05, + "loss": 3.2205, "step": 76300 }, { "epoch": 0.25, - "learning_rate": 3.7340849289828275e-05, - "loss": 3.2267, + "learning_rate": 3.735459438702886e-05, + "loss": 3.2251, "step": 76400 }, { "epoch": 0.25, - "learning_rate": 3.73242797208359e-05, - "loss": 3.2452, + "learning_rate": 3.7338042809001414e-05, + "loss": 3.2264, "step": 76500 }, { "epoch": 0.25, - "learning_rate": 3.730771015184353e-05, - "loss": 3.2364, + "learning_rate": 3.7321491230973966e-05, + "loss": 3.2178, "step": 76600 }, { "epoch": 0.25, - "learning_rate": 3.729114058285116e-05, - "loss": 3.236, + "learning_rate": 3.730493965294651e-05, + "loss": 3.2199, "step": 76700 }, { "epoch": 0.25, - "learning_rate": 3.727457101385879e-05, - "loss": 3.2322, + "learning_rate": 3.728838807491907e-05, + "loss": 3.233, "step": 76800 }, { "epoch": 0.25, - "learning_rate": 3.725800144486642e-05, - "loss": 3.2505, + "learning_rate": 3.7271836496891614e-05, + "loss": 3.2193, "step": 76900 }, { - "epoch": 0.26, - "learning_rate": 3.7241431875874043e-05, - "loss": 3.2449, + "epoch": 0.25, + "learning_rate": 3.7255284918864165e-05, + "loss": 3.2229, "step": 77000 }, { "epoch": 0.26, - "learning_rate": 3.7224862306881676e-05, - "loss": 3.241, + "learning_rate": 3.723873334083672e-05, + "loss": 3.2225, "step": 77100 }, { "epoch": 0.26, - "learning_rate": 3.720829273788931e-05, - "loss": 3.2367, + "learning_rate": 3.722218176280927e-05, + "loss": 3.2239, "step": 77200 }, { "epoch": 0.26, - "learning_rate": 3.719172316889693e-05, - "loss": 3.2389, + "learning_rate": 3.720563018478182e-05, + "loss": 3.2105, "step": 77300 }, { "epoch": 0.26, - "learning_rate": 3.717515359990456e-05, - "loss": 3.2345, + "learning_rate": 3.718907860675437e-05, + "loss": 3.2153, "step": 77400 }, { "epoch": 0.26, - "learning_rate": 3.715858403091219e-05, - "loss": 3.2427, + "learning_rate": 3.717252702872692e-05, + "loss": 3.2189, "step": 77500 }, { "epoch": 0.26, - "learning_rate": 3.714201446191982e-05, - "loss": 3.2475, + "learning_rate": 3.715597545069947e-05, + "loss": 3.2139, "step": 77600 }, { "epoch": 0.26, - "learning_rate": 3.7125444892927444e-05, - "loss": 3.2406, + "learning_rate": 3.7139423872672027e-05, + "loss": 3.2199, "step": 77700 }, { "epoch": 0.26, - "learning_rate": 3.710887532393508e-05, - "loss": 3.222, + "learning_rate": 3.712287229464457e-05, + "loss": 3.2219, "step": 77800 }, { "epoch": 0.26, - "learning_rate": 3.70923057549427e-05, - "loss": 3.2439, + "learning_rate": 3.710632071661713e-05, + "loss": 3.2273, "step": 77900 }, { "epoch": 0.26, - "learning_rate": 3.7075736185950335e-05, - "loss": 3.2342, + "learning_rate": 3.7089769138589675e-05, + "loss": 3.2283, "step": 78000 }, { "epoch": 0.26, - "learning_rate": 3.705916661695796e-05, - "loss": 3.2255, + "learning_rate": 3.7073217560562226e-05, + "loss": 3.2345, "step": 78100 }, { "epoch": 0.26, - "learning_rate": 3.704259704796559e-05, - "loss": 3.2257, + "learning_rate": 3.705666598253478e-05, + "loss": 3.2035, "step": 78200 }, { "epoch": 0.26, - "learning_rate": 3.702602747897322e-05, - "loss": 3.2324, + "learning_rate": 3.704011440450732e-05, + "loss": 3.2201, "step": 78300 }, { "epoch": 0.26, - "learning_rate": 3.700945790998085e-05, - "loss": 3.2483, + "learning_rate": 3.702356282647988e-05, + "loss": 3.2179, "step": 78400 }, { "epoch": 0.26, - "learning_rate": 3.699288834098847e-05, - "loss": 3.2338, + "learning_rate": 3.7007011248452426e-05, + "loss": 3.2245, "step": 78500 }, { "epoch": 0.26, - "learning_rate": 3.6976318771996104e-05, - "loss": 3.23, + "learning_rate": 3.6990459670424984e-05, + "loss": 3.2306, "step": 78600 }, { "epoch": 0.26, - "learning_rate": 3.6959749203003737e-05, - "loss": 3.2255, + "learning_rate": 3.697390809239753e-05, + "loss": 3.2271, "step": 78700 }, { "epoch": 0.26, - "learning_rate": 3.694317963401136e-05, - "loss": 3.2307, + "learning_rate": 3.695735651437008e-05, + "loss": 3.2302, "step": 78800 }, { "epoch": 0.26, - "learning_rate": 3.692661006501899e-05, - "loss": 3.2296, + "learning_rate": 3.694080493634263e-05, + "loss": 3.2168, "step": 78900 }, { "epoch": 0.26, - "learning_rate": 3.691004049602662e-05, - "loss": 3.2394, + "learning_rate": 3.6924253358315184e-05, + "loss": 3.2176, "step": 79000 }, { "epoch": 0.26, - "learning_rate": 3.6893470927034247e-05, - "loss": 3.2359, + "learning_rate": 3.6907701780287735e-05, + "loss": 3.2194, "step": 79100 }, { "epoch": 0.26, - "learning_rate": 3.687690135804188e-05, - "loss": 3.226, + "learning_rate": 3.689115020226028e-05, + "loss": 3.2331, "step": 79200 }, { "epoch": 0.26, - "learning_rate": 3.6860331789049505e-05, - "loss": 3.226, + "learning_rate": 3.687459862423284e-05, + "loss": 3.2143, "step": 79300 }, { "epoch": 0.26, - "learning_rate": 3.684376222005713e-05, - "loss": 3.2304, + "learning_rate": 3.6858047046205383e-05, + "loss": 3.2188, "step": 79400 }, { "epoch": 0.26, - "learning_rate": 3.682719265106476e-05, - "loss": 3.2466, + "learning_rate": 3.684149546817794e-05, + "loss": 3.2267, "step": 79500 }, { "epoch": 0.26, - "learning_rate": 3.6810623082072396e-05, - "loss": 3.2235, + "learning_rate": 3.6824943890150487e-05, + "loss": 3.2312, "step": 79600 }, { "epoch": 0.26, - "learning_rate": 3.6794053513080015e-05, - "loss": 3.2425, + "learning_rate": 3.680839231212304e-05, + "loss": 3.2214, "step": 79700 }, { "epoch": 0.26, - "learning_rate": 3.677748394408765e-05, - "loss": 3.2322, + "learning_rate": 3.679184073409559e-05, + "loss": 3.2317, "step": 79800 }, { "epoch": 0.26, - "learning_rate": 3.676091437509528e-05, - "loss": 3.2492, + "learning_rate": 3.677528915606814e-05, + "loss": 3.228, "step": 79900 }, { - "epoch": 0.27, - "learning_rate": 3.6744344806102906e-05, - "loss": 3.2154, + "epoch": 0.26, + "learning_rate": 3.675873757804069e-05, + "loss": 3.2051, "step": 80000 }, { "epoch": 0.27, - "learning_rate": 3.672777523711053e-05, - "loss": 3.2329, + "learning_rate": 3.6742186000013245e-05, + "loss": 3.228, "step": 80100 }, { "epoch": 0.27, - "learning_rate": 3.6711205668118164e-05, - "loss": 3.2245, + "learning_rate": 3.6725634421985796e-05, + "loss": 3.2225, "step": 80200 }, { "epoch": 0.27, - "learning_rate": 3.669463609912579e-05, - "loss": 3.2259, + "learning_rate": 3.670908284395834e-05, + "loss": 3.2061, "step": 80300 }, { "epoch": 0.27, - "learning_rate": 3.667806653013342e-05, - "loss": 3.2383, + "learning_rate": 3.66925312659309e-05, + "loss": 3.2151, "step": 80400 }, { "epoch": 0.27, - "learning_rate": 3.666149696114105e-05, - "loss": 3.2398, + "learning_rate": 3.6675979687903444e-05, + "loss": 3.2253, "step": 80500 }, { "epoch": 0.27, - "learning_rate": 3.6644927392148674e-05, - "loss": 3.238, + "learning_rate": 3.6659428109875996e-05, + "loss": 3.2066, "step": 80600 }, { "epoch": 0.27, - "learning_rate": 3.662835782315631e-05, - "loss": 3.2296, + "learning_rate": 3.664287653184855e-05, + "loss": 3.2188, "step": 80700 }, { "epoch": 0.27, - "learning_rate": 3.661178825416394e-05, - "loss": 3.2399, + "learning_rate": 3.66263249538211e-05, + "loss": 3.2215, "step": 80800 }, { "epoch": 0.27, - "learning_rate": 3.659521868517156e-05, - "loss": 3.2414, + "learning_rate": 3.660977337579365e-05, + "loss": 3.224, "step": 80900 }, { "epoch": 0.27, - "learning_rate": 3.657864911617919e-05, - "loss": 3.227, + "learning_rate": 3.65932217977662e-05, + "loss": 3.2102, "step": 81000 }, { "epoch": 0.27, - "learning_rate": 3.6562079547186824e-05, - "loss": 3.2409, + "learning_rate": 3.6576670219738754e-05, + "loss": 3.2209, "step": 81100 }, { "epoch": 0.27, - "learning_rate": 3.654550997819445e-05, - "loss": 3.2261, + "learning_rate": 3.6560118641711305e-05, + "loss": 3.2197, "step": 81200 }, { "epoch": 0.27, - "learning_rate": 3.6528940409202076e-05, - "loss": 3.2448, + "learning_rate": 3.654356706368385e-05, + "loss": 3.2199, "step": 81300 }, { "epoch": 0.27, - "learning_rate": 3.651237084020971e-05, - "loss": 3.2423, + "learning_rate": 3.65270154856564e-05, + "loss": 3.2185, "step": 81400 }, { "epoch": 0.27, - "learning_rate": 3.6495801271217334e-05, - "loss": 3.2332, + "learning_rate": 3.6510463907628953e-05, + "loss": 3.2099, "step": 81500 }, { "epoch": 0.27, - "learning_rate": 3.6479231702224967e-05, - "loss": 3.2424, + "learning_rate": 3.6493912329601505e-05, + "loss": 3.216, "step": 81600 }, { "epoch": 0.27, - "learning_rate": 3.646266213323259e-05, - "loss": 3.2406, + "learning_rate": 3.647736075157406e-05, + "loss": 3.2192, "step": 81700 }, { "epoch": 0.27, - "learning_rate": 3.644609256424022e-05, - "loss": 3.2445, + "learning_rate": 3.646080917354661e-05, + "loss": 3.2318, "step": 81800 }, { "epoch": 0.27, - "learning_rate": 3.642952299524785e-05, - "loss": 3.2361, + "learning_rate": 3.644425759551916e-05, + "loss": 3.2112, "step": 81900 }, { "epoch": 0.27, - "learning_rate": 3.641295342625548e-05, - "loss": 3.2543, + "learning_rate": 3.642770601749171e-05, + "loss": 3.2242, "step": 82000 }, { "epoch": 0.27, - "learning_rate": 3.63963838572631e-05, - "loss": 3.2461, + "learning_rate": 3.641115443946426e-05, + "loss": 3.2211, "step": 82100 }, { "epoch": 0.27, - "learning_rate": 3.6379814288270735e-05, + "learning_rate": 3.639460286143681e-05, "loss": 3.2281, "step": 82200 }, { "epoch": 0.27, - "learning_rate": 3.636324471927837e-05, - "loss": 3.2322, + "learning_rate": 3.6378051283409366e-05, + "loss": 3.2108, "step": 82300 }, { "epoch": 0.27, - "learning_rate": 3.6346675150285993e-05, - "loss": 3.2337, + "learning_rate": 3.636149970538191e-05, + "loss": 3.2417, "step": 82400 }, { "epoch": 0.27, - "learning_rate": 3.633010558129362e-05, - "loss": 3.2371, + "learning_rate": 3.634494812735446e-05, + "loss": 3.2018, "step": 82500 }, { "epoch": 0.27, - "learning_rate": 3.631353601230125e-05, - "loss": 3.2533, + "learning_rate": 3.6328396549327014e-05, + "loss": 3.2078, "step": 82600 }, { "epoch": 0.27, - "learning_rate": 3.629696644330888e-05, - "loss": 3.226, + "learning_rate": 3.6311844971299566e-05, + "loss": 3.2217, "step": 82700 }, { "epoch": 0.27, - "learning_rate": 3.628039687431651e-05, - "loss": 3.2352, + "learning_rate": 3.629529339327212e-05, + "loss": 3.2299, "step": 82800 }, { "epoch": 0.27, - "learning_rate": 3.6263827305324136e-05, - "loss": 3.2253, + "learning_rate": 3.627874181524466e-05, + "loss": 3.2122, "step": 82900 }, { - "epoch": 0.28, - "learning_rate": 3.624725773633176e-05, - "loss": 3.2402, + "epoch": 0.27, + "learning_rate": 3.626219023721722e-05, + "loss": 3.2012, "step": 83000 }, { "epoch": 0.28, - "learning_rate": 3.6230688167339394e-05, - "loss": 3.2427, + "learning_rate": 3.6245638659189765e-05, + "loss": 3.2202, "step": 83100 }, { "epoch": 0.28, - "learning_rate": 3.621411859834702e-05, - "loss": 3.235, + "learning_rate": 3.6229087081162324e-05, + "loss": 3.2196, "step": 83200 }, { "epoch": 0.28, - "learning_rate": 3.6197549029354646e-05, - "loss": 3.2475, + "learning_rate": 3.621253550313487e-05, + "loss": 3.2261, "step": 83300 }, { "epoch": 0.28, - "learning_rate": 3.618097946036228e-05, - "loss": 3.2205, + "learning_rate": 3.619598392510743e-05, + "loss": 3.2297, "step": 83400 }, { "epoch": 0.28, - "learning_rate": 3.6164409891369904e-05, - "loss": 3.2287, + "learning_rate": 3.617943234707997e-05, + "loss": 3.2122, "step": 83500 }, { "epoch": 0.28, - "learning_rate": 3.614784032237754e-05, - "loss": 3.2393, + "learning_rate": 3.6162880769052523e-05, + "loss": 3.2333, "step": 83600 }, { "epoch": 0.28, - "learning_rate": 3.613127075338516e-05, - "loss": 3.2321, + "learning_rate": 3.6146329191025075e-05, + "loss": 3.2289, "step": 83700 }, { "epoch": 0.28, - "learning_rate": 3.611470118439279e-05, - "loss": 3.235, + "learning_rate": 3.612977761299762e-05, + "loss": 3.2149, "step": 83800 }, { "epoch": 0.28, - "learning_rate": 3.609813161540042e-05, - "loss": 3.2487, + "learning_rate": 3.611322603497018e-05, + "loss": 3.2221, "step": 83900 }, { "epoch": 0.28, - "learning_rate": 3.6081562046408054e-05, - "loss": 3.2423, + "learning_rate": 3.609667445694272e-05, + "loss": 3.198, "step": 84000 }, { "epoch": 0.28, - "learning_rate": 3.606499247741568e-05, - "loss": 3.2177, + "learning_rate": 3.608012287891528e-05, + "loss": 3.222, "step": 84100 }, { "epoch": 0.28, - "learning_rate": 3.6048422908423306e-05, - "loss": 3.2359, + "learning_rate": 3.6063571300887826e-05, + "loss": 3.2223, "step": 84200 }, { "epoch": 0.28, - "learning_rate": 3.603185333943094e-05, - "loss": 3.235, + "learning_rate": 3.604701972286038e-05, + "loss": 3.2018, "step": 84300 }, { "epoch": 0.28, - "learning_rate": 3.6015283770438564e-05, - "loss": 3.236, + "learning_rate": 3.603046814483293e-05, + "loss": 3.2143, "step": 84400 }, { "epoch": 0.28, - "learning_rate": 3.599871420144619e-05, - "loss": 3.2437, + "learning_rate": 3.601391656680548e-05, + "loss": 3.2135, "step": 84500 }, { "epoch": 0.28, - "learning_rate": 3.598214463245382e-05, - "loss": 3.2359, + "learning_rate": 3.599736498877803e-05, + "loss": 3.2139, "step": 84600 }, { "epoch": 0.28, - "learning_rate": 3.596557506346145e-05, - "loss": 3.235, + "learning_rate": 3.598081341075058e-05, + "loss": 3.2271, "step": 84700 }, { "epoch": 0.28, - "learning_rate": 3.594900549446908e-05, - "loss": 3.2456, + "learning_rate": 3.5964261832723136e-05, + "loss": 3.2118, "step": 84800 }, { "epoch": 0.28, - "learning_rate": 3.5932435925476707e-05, - "loss": 3.2526, + "learning_rate": 3.594771025469568e-05, + "loss": 3.2201, "step": 84900 }, { "epoch": 0.28, - "learning_rate": 3.591586635648433e-05, - "loss": 3.2429, + "learning_rate": 3.593115867666824e-05, + "loss": 3.2079, "step": 85000 }, { "epoch": 0.28, - "learning_rate": 3.5899296787491965e-05, - "loss": 3.2268, + "learning_rate": 3.5914607098640784e-05, + "loss": 3.2088, "step": 85100 }, { "epoch": 0.28, - "learning_rate": 3.58827272184996e-05, - "loss": 3.2352, + "learning_rate": 3.5898055520613336e-05, + "loss": 3.2313, "step": 85200 }, { "epoch": 0.28, - "learning_rate": 3.5866157649507223e-05, - "loss": 3.2318, + "learning_rate": 3.588150394258589e-05, + "loss": 3.2058, "step": 85300 }, { "epoch": 0.28, - "learning_rate": 3.584958808051485e-05, - "loss": 3.2366, + "learning_rate": 3.586495236455844e-05, + "loss": 3.2212, "step": 85400 }, { "epoch": 0.28, - "learning_rate": 3.583301851152248e-05, - "loss": 3.2355, + "learning_rate": 3.584840078653099e-05, + "loss": 3.2098, "step": 85500 }, { "epoch": 0.28, - "learning_rate": 3.581644894253011e-05, - "loss": 3.236, + "learning_rate": 3.583184920850354e-05, + "loss": 3.2189, "step": 85600 }, { "epoch": 0.28, - "learning_rate": 3.579987937353774e-05, - "loss": 3.2272, + "learning_rate": 3.5815297630476094e-05, + "loss": 3.23, "step": 85700 }, { "epoch": 0.28, - "learning_rate": 3.5783309804545366e-05, - "loss": 3.2345, + "learning_rate": 3.579874605244864e-05, + "loss": 3.2242, "step": 85800 }, { "epoch": 0.28, - "learning_rate": 3.576674023555299e-05, - "loss": 3.2274, + "learning_rate": 3.57821944744212e-05, + "loss": 3.2118, "step": 85900 }, { "epoch": 0.28, - "learning_rate": 3.5750170666560624e-05, - "loss": 3.2409, + "learning_rate": 3.576564289639374e-05, + "loss": 3.2157, "step": 86000 }, { "epoch": 0.29, - "learning_rate": 3.573360109756825e-05, - "loss": 3.2405, + "learning_rate": 3.574909131836629e-05, + "loss": 3.2089, "step": 86100 }, { "epoch": 0.29, - "learning_rate": 3.5717031528575876e-05, - "loss": 3.2357, + "learning_rate": 3.5732539740338845e-05, + "loss": 3.2204, "step": 86200 }, { "epoch": 0.29, - "learning_rate": 3.570046195958351e-05, - "loss": 3.2326, + "learning_rate": 3.5715988162311396e-05, + "loss": 3.2208, "step": 86300 }, { "epoch": 0.29, - "learning_rate": 3.568389239059114e-05, - "loss": 3.2339, + "learning_rate": 3.569943658428395e-05, + "loss": 3.2122, "step": 86400 }, { "epoch": 0.29, - "learning_rate": 3.566732282159877e-05, - "loss": 3.229, + "learning_rate": 3.56828850062565e-05, + "loss": 3.2062, "step": 86500 }, { "epoch": 0.29, - "learning_rate": 3.565075325260639e-05, - "loss": 3.2422, + "learning_rate": 3.566633342822905e-05, + "loss": 3.2187, "step": 86600 }, { "epoch": 0.29, - "learning_rate": 3.5634183683614026e-05, - "loss": 3.2494, + "learning_rate": 3.56497818502016e-05, + "loss": 3.2318, "step": 86700 }, { "epoch": 0.29, - "learning_rate": 3.561761411462165e-05, - "loss": 3.2374, + "learning_rate": 3.563323027217415e-05, + "loss": 3.2082, "step": 86800 }, { "epoch": 0.29, - "learning_rate": 3.5601044545629284e-05, - "loss": 3.237, + "learning_rate": 3.56166786941467e-05, + "loss": 3.2205, "step": 86900 }, { "epoch": 0.29, - "learning_rate": 3.558447497663691e-05, - "loss": 3.2399, + "learning_rate": 3.560012711611925e-05, + "loss": 3.2252, "step": 87000 }, { "epoch": 0.29, - "learning_rate": 3.5567905407644536e-05, - "loss": 3.2357, + "learning_rate": 3.55835755380918e-05, + "loss": 3.2209, "step": 87100 }, { "epoch": 0.29, - "learning_rate": 3.555133583865217e-05, - "loss": 3.255, + "learning_rate": 3.5567023960064354e-05, + "loss": 3.2233, "step": 87200 }, { "epoch": 0.29, - "learning_rate": 3.5534766269659794e-05, - "loss": 3.2318, + "learning_rate": 3.5550472382036906e-05, + "loss": 3.218, "step": 87300 }, { "epoch": 0.29, - "learning_rate": 3.551819670066742e-05, - "loss": 3.2317, + "learning_rate": 3.553392080400946e-05, + "loss": 3.211, "step": 87400 }, { "epoch": 0.29, - "learning_rate": 3.550162713167505e-05, - "loss": 3.2398, + "learning_rate": 3.551736922598201e-05, + "loss": 3.2018, "step": 87500 }, { "epoch": 0.29, - "learning_rate": 3.5485057562682685e-05, - "loss": 3.2272, + "learning_rate": 3.550081764795456e-05, + "loss": 3.213, "step": 87600 }, { "epoch": 0.29, - "learning_rate": 3.546848799369031e-05, - "loss": 3.2349, + "learning_rate": 3.5484266069927105e-05, + "loss": 3.2091, "step": 87700 }, { "epoch": 0.29, - "learning_rate": 3.5451918424697937e-05, - "loss": 3.2279, + "learning_rate": 3.5467714491899664e-05, + "loss": 3.2159, "step": 87800 }, { "epoch": 0.29, - "learning_rate": 3.543534885570557e-05, - "loss": 3.2343, + "learning_rate": 3.545116291387221e-05, + "loss": 3.2204, "step": 87900 }, { "epoch": 0.29, - "learning_rate": 3.5418779286713195e-05, - "loss": 3.2399, + "learning_rate": 3.543461133584476e-05, + "loss": 3.2198, "step": 88000 }, { "epoch": 0.29, - "learning_rate": 3.540220971772083e-05, - "loss": 3.2443, + "learning_rate": 3.541805975781731e-05, + "loss": 3.203, "step": 88100 }, { "epoch": 0.29, - "learning_rate": 3.5385640148728453e-05, - "loss": 3.228, + "learning_rate": 3.540150817978986e-05, + "loss": 3.2139, "step": 88200 }, { "epoch": 0.29, - "learning_rate": 3.536907057973608e-05, - "loss": 3.2365, + "learning_rate": 3.5384956601762415e-05, + "loss": 3.2139, "step": 88300 }, { "epoch": 0.29, - "learning_rate": 3.535250101074371e-05, - "loss": 3.239, + "learning_rate": 3.536840502373496e-05, + "loss": 3.2211, "step": 88400 }, { "epoch": 0.29, - "learning_rate": 3.533593144175134e-05, - "loss": 3.2189, + "learning_rate": 3.535185344570752e-05, + "loss": 3.2154, "step": 88500 }, { "epoch": 0.29, - "learning_rate": 3.5319361872758963e-05, - "loss": 3.2397, + "learning_rate": 3.533530186768006e-05, + "loss": 3.2089, "step": 88600 }, { "epoch": 0.29, - "learning_rate": 3.5302792303766596e-05, - "loss": 3.232, + "learning_rate": 3.531875028965262e-05, + "loss": 3.2009, "step": 88700 }, { "epoch": 0.29, - "learning_rate": 3.528622273477423e-05, - "loss": 3.2339, + "learning_rate": 3.5302198711625166e-05, + "loss": 3.2066, "step": 88800 }, { "epoch": 0.29, - "learning_rate": 3.5269653165781854e-05, - "loss": 3.2358, + "learning_rate": 3.5285647133597724e-05, + "loss": 3.2157, "step": 88900 }, { "epoch": 0.29, - "learning_rate": 3.525308359678948e-05, - "loss": 3.2359, + "learning_rate": 3.526909555557027e-05, + "loss": 3.2104, "step": 89000 }, { - "epoch": 0.3, - "learning_rate": 3.523651402779711e-05, - "loss": 3.2325, + "epoch": 0.29, + "learning_rate": 3.525254397754282e-05, + "loss": 3.2152, "step": 89100 }, { "epoch": 0.3, - "learning_rate": 3.521994445880474e-05, - "loss": 3.2296, + "learning_rate": 3.523599239951537e-05, + "loss": 3.2114, "step": 89200 }, { "epoch": 0.3, - "learning_rate": 3.520337488981237e-05, - "loss": 3.2339, + "learning_rate": 3.521944082148792e-05, + "loss": 3.2181, "step": 89300 }, { "epoch": 0.3, - "learning_rate": 3.518680532082e-05, - "loss": 3.2216, + "learning_rate": 3.5202889243460476e-05, + "loss": 3.2101, "step": 89400 }, { "epoch": 0.3, - "learning_rate": 3.517023575182762e-05, - "loss": 3.2419, + "learning_rate": 3.518633766543302e-05, + "loss": 3.2122, "step": 89500 }, { "epoch": 0.3, - "learning_rate": 3.5153666182835256e-05, - "loss": 3.2348, + "learning_rate": 3.516978608740558e-05, + "loss": 3.2134, "step": 89600 }, { "epoch": 0.3, - "learning_rate": 3.513709661384289e-05, - "loss": 3.2378, + "learning_rate": 3.5153234509378124e-05, + "loss": 3.2231, "step": 89700 }, { "epoch": 0.3, - "learning_rate": 3.512052704485051e-05, - "loss": 3.2371, + "learning_rate": 3.5136682931350675e-05, + "loss": 3.2271, "step": 89800 }, { "epoch": 0.3, - "learning_rate": 3.510395747585814e-05, - "loss": 3.2262, + "learning_rate": 3.512013135332323e-05, + "loss": 3.2058, "step": 89900 }, { "epoch": 0.3, - "learning_rate": 3.508738790686577e-05, - "loss": 3.2282, + "learning_rate": 3.510357977529578e-05, + "loss": 3.2268, "step": 90000 }, { "epoch": 0.3, - "learning_rate": 3.50708183378734e-05, - "loss": 3.2506, + "learning_rate": 3.508702819726833e-05, + "loss": 3.2239, "step": 90100 }, { "epoch": 0.3, - "learning_rate": 3.5054248768881024e-05, - "loss": 3.2378, + "learning_rate": 3.5070476619240875e-05, + "loss": 3.2276, "step": 90200 }, { "epoch": 0.3, - "learning_rate": 3.5037679199888657e-05, - "loss": 3.2378, + "learning_rate": 3.505392504121343e-05, + "loss": 3.2156, "step": 90300 }, { "epoch": 0.3, - "learning_rate": 3.502110963089628e-05, - "loss": 3.2346, + "learning_rate": 3.503737346318598e-05, + "loss": 3.2178, "step": 90400 }, { "epoch": 0.3, - "learning_rate": 3.5004540061903915e-05, - "loss": 3.2204, + "learning_rate": 3.5020821885158536e-05, + "loss": 3.2145, "step": 90500 }, { "epoch": 0.3, - "learning_rate": 3.498797049291154e-05, - "loss": 3.222, + "learning_rate": 3.500427030713108e-05, + "loss": 3.2208, "step": 90600 }, { "epoch": 0.3, - "learning_rate": 3.497140092391917e-05, - "loss": 3.2352, + "learning_rate": 3.498771872910363e-05, + "loss": 3.2244, "step": 90700 }, { "epoch": 0.3, - "learning_rate": 3.49548313549268e-05, - "loss": 3.2203, + "learning_rate": 3.4971167151076184e-05, + "loss": 3.217, "step": 90800 }, { "epoch": 0.3, - "learning_rate": 3.493826178593443e-05, - "loss": 3.2452, + "learning_rate": 3.4954615573048736e-05, + "loss": 3.2144, "step": 90900 }, { "epoch": 0.3, - "learning_rate": 3.492169221694205e-05, - "loss": 3.2305, + "learning_rate": 3.493806399502129e-05, + "loss": 3.2113, "step": 91000 }, { "epoch": 0.3, - "learning_rate": 3.4905122647949683e-05, - "loss": 3.2408, + "learning_rate": 3.492151241699384e-05, + "loss": 3.1976, "step": 91100 }, { "epoch": 0.3, - "learning_rate": 3.4888553078957316e-05, - "loss": 3.2241, + "learning_rate": 3.490496083896639e-05, + "loss": 3.224, "step": 91200 }, { "epoch": 0.3, - "learning_rate": 3.487198350996494e-05, - "loss": 3.2287, + "learning_rate": 3.488840926093894e-05, + "loss": 3.2245, "step": 91300 }, { "epoch": 0.3, - "learning_rate": 3.485541394097257e-05, - "loss": 3.2359, + "learning_rate": 3.487185768291149e-05, + "loss": 3.2233, "step": 91400 }, { "epoch": 0.3, - "learning_rate": 3.48388443719802e-05, - "loss": 3.2272, + "learning_rate": 3.485530610488404e-05, + "loss": 3.2121, "step": 91500 }, { "epoch": 0.3, - "learning_rate": 3.4822274802987826e-05, - "loss": 3.2369, + "learning_rate": 3.483875452685659e-05, + "loss": 3.2212, "step": 91600 }, { "epoch": 0.3, - "learning_rate": 3.480570523399546e-05, - "loss": 3.219, + "learning_rate": 3.482220294882914e-05, + "loss": 3.212, "step": 91700 }, { "epoch": 0.3, - "learning_rate": 3.478913566500308e-05, - "loss": 3.232, + "learning_rate": 3.4805651370801694e-05, + "loss": 3.2157, "step": 91800 }, { "epoch": 0.3, - "learning_rate": 3.477256609601071e-05, - "loss": 3.2252, + "learning_rate": 3.4789099792774245e-05, + "loss": 3.2169, "step": 91900 }, { "epoch": 0.3, - "learning_rate": 3.475599652701834e-05, - "loss": 3.239, + "learning_rate": 3.47725482147468e-05, + "loss": 3.2216, "step": 92000 }, { - "epoch": 0.31, - "learning_rate": 3.473942695802597e-05, - "loss": 3.2355, + "epoch": 0.3, + "learning_rate": 3.475599663671935e-05, + "loss": 3.2198, "step": 92100 }, { "epoch": 0.31, - "learning_rate": 3.4722857389033595e-05, - "loss": 3.2359, + "learning_rate": 3.47394450586919e-05, + "loss": 3.2245, "step": 92200 }, { "epoch": 0.31, - "learning_rate": 3.470628782004123e-05, - "loss": 3.2358, + "learning_rate": 3.4722893480664445e-05, + "loss": 3.2115, "step": 92300 }, { "epoch": 0.31, - "learning_rate": 3.468971825104885e-05, - "loss": 3.2402, + "learning_rate": 3.4706341902637e-05, + "loss": 3.2278, "step": 92400 }, { "epoch": 0.31, - "learning_rate": 3.4673148682056486e-05, - "loss": 3.2411, + "learning_rate": 3.468979032460955e-05, + "loss": 3.2278, "step": 92500 }, { "epoch": 0.31, - "learning_rate": 3.465657911306411e-05, - "loss": 3.2427, + "learning_rate": 3.46732387465821e-05, + "loss": 3.2207, "step": 92600 }, { "epoch": 0.31, - "learning_rate": 3.464000954407174e-05, - "loss": 3.2437, + "learning_rate": 3.465668716855465e-05, + "loss": 3.2184, "step": 92700 }, { "epoch": 0.31, - "learning_rate": 3.462343997507937e-05, - "loss": 3.2219, + "learning_rate": 3.46401355905272e-05, + "loss": 3.2014, "step": 92800 }, { "epoch": 0.31, - "learning_rate": 3.4606870406087e-05, - "loss": 3.2291, + "learning_rate": 3.4623584012499755e-05, + "loss": 3.2174, "step": 92900 }, { "epoch": 0.31, - "learning_rate": 3.459030083709462e-05, - "loss": 3.2326, + "learning_rate": 3.4607032434472306e-05, + "loss": 3.2212, "step": 93000 }, { "epoch": 0.31, - "learning_rate": 3.4573731268102254e-05, - "loss": 3.2328, + "learning_rate": 3.459048085644486e-05, + "loss": 3.2134, "step": 93100 }, { "epoch": 0.31, - "learning_rate": 3.4557161699109887e-05, - "loss": 3.2412, + "learning_rate": 3.45739292784174e-05, + "loss": 3.2128, "step": 93200 }, { "epoch": 0.31, - "learning_rate": 3.454059213011751e-05, - "loss": 3.2331, + "learning_rate": 3.455737770038996e-05, + "loss": 3.2239, "step": 93300 }, { "epoch": 0.31, - "learning_rate": 3.452402256112514e-05, - "loss": 3.2408, + "learning_rate": 3.4540826122362506e-05, + "loss": 3.2155, "step": 93400 }, { "epoch": 0.31, - "learning_rate": 3.450745299213277e-05, - "loss": 3.2463, + "learning_rate": 3.4524274544335064e-05, + "loss": 3.2089, "step": 93500 }, { "epoch": 0.31, - "learning_rate": 3.44908834231404e-05, - "loss": 3.2193, + "learning_rate": 3.450772296630761e-05, + "loss": 3.2141, "step": 93600 }, { "epoch": 0.31, - "learning_rate": 3.447431385414803e-05, - "loss": 3.2362, + "learning_rate": 3.449117138828016e-05, + "loss": 3.2124, "step": 93700 }, { "epoch": 0.31, - "learning_rate": 3.4457744285155655e-05, - "loss": 3.2277, + "learning_rate": 3.447461981025271e-05, + "loss": 3.2081, "step": 93800 }, { "epoch": 0.31, - "learning_rate": 3.444117471616328e-05, - "loss": 3.2267, + "learning_rate": 3.445806823222526e-05, + "loss": 3.2224, "step": 93900 }, { "epoch": 0.31, - "learning_rate": 3.4424605147170913e-05, - "loss": 3.2432, + "learning_rate": 3.4441516654197815e-05, + "loss": 3.233, "step": 94000 }, { "epoch": 0.31, - "learning_rate": 3.4408035578178546e-05, - "loss": 3.2313, + "learning_rate": 3.442496507617036e-05, + "loss": 3.2112, "step": 94100 }, { "epoch": 0.31, - "learning_rate": 3.4391466009186165e-05, - "loss": 3.2453, + "learning_rate": 3.440841349814292e-05, + "loss": 3.2057, "step": 94200 }, { "epoch": 0.31, - "learning_rate": 3.43748964401938e-05, - "loss": 3.2433, + "learning_rate": 3.4391861920115463e-05, + "loss": 3.2134, "step": 94300 }, { "epoch": 0.31, - "learning_rate": 3.435832687120143e-05, - "loss": 3.2271, + "learning_rate": 3.437531034208802e-05, + "loss": 3.23, "step": 94400 }, { "epoch": 0.31, - "learning_rate": 3.4341757302209056e-05, - "loss": 3.2321, + "learning_rate": 3.4358758764060567e-05, + "loss": 3.2211, "step": 94500 }, { "epoch": 0.31, - "learning_rate": 3.432518773321668e-05, - "loss": 3.2307, + "learning_rate": 3.434220718603312e-05, + "loss": 3.2119, "step": 94600 }, { "epoch": 0.31, - "learning_rate": 3.4308618164224315e-05, - "loss": 3.2298, + "learning_rate": 3.432565560800567e-05, + "loss": 3.2151, "step": 94700 }, { "epoch": 0.31, - "learning_rate": 3.429204859523194e-05, - "loss": 3.2341, + "learning_rate": 3.4309104029978215e-05, + "loss": 3.2221, "step": 94800 }, { "epoch": 0.31, - "learning_rate": 3.427547902623957e-05, - "loss": 3.2277, + "learning_rate": 3.429255245195077e-05, + "loss": 3.2109, "step": 94900 }, { "epoch": 0.31, - "learning_rate": 3.42589094572472e-05, - "loss": 3.2243, + "learning_rate": 3.427600087392332e-05, + "loss": 3.2108, "step": 95000 }, { - "epoch": 0.32, - "learning_rate": 3.4242339888254825e-05, - "loss": 3.2252, + "epoch": 0.31, + "learning_rate": 3.4259449295895876e-05, + "loss": 3.2047, "step": 95100 }, { "epoch": 0.32, - "learning_rate": 3.422577031926246e-05, - "loss": 3.2373, + "learning_rate": 3.424289771786842e-05, + "loss": 3.2165, "step": 95200 }, { "epoch": 0.32, - "learning_rate": 3.420920075027009e-05, - "loss": 3.2315, + "learning_rate": 3.422634613984097e-05, + "loss": 3.2133, "step": 95300 }, { "epoch": 0.32, - "learning_rate": 3.4192631181277716e-05, - "loss": 3.2376, + "learning_rate": 3.4209794561813524e-05, + "loss": 3.2218, "step": 95400 }, { "epoch": 0.32, - "learning_rate": 3.417606161228534e-05, - "loss": 3.2266, + "learning_rate": 3.4193242983786076e-05, + "loss": 3.2102, "step": 95500 }, { "epoch": 0.32, - "learning_rate": 3.4159492043292974e-05, - "loss": 3.2262, + "learning_rate": 3.417669140575863e-05, + "loss": 3.2125, "step": 95600 }, { "epoch": 0.32, - "learning_rate": 3.41429224743006e-05, - "loss": 3.2466, + "learning_rate": 3.416013982773118e-05, + "loss": 3.2128, "step": 95700 }, { "epoch": 0.32, - "learning_rate": 3.4126352905308226e-05, - "loss": 3.2479, + "learning_rate": 3.414358824970373e-05, + "loss": 3.2139, "step": 95800 }, { "epoch": 0.32, - "learning_rate": 3.410978333631586e-05, - "loss": 3.2223, + "learning_rate": 3.4127036671676275e-05, + "loss": 3.227, "step": 95900 }, { "epoch": 0.32, - "learning_rate": 3.4093213767323484e-05, - "loss": 3.2395, + "learning_rate": 3.4110485093648834e-05, + "loss": 3.2102, "step": 96000 }, { "epoch": 0.32, - "learning_rate": 3.407664419833112e-05, - "loss": 3.2302, + "learning_rate": 3.409393351562138e-05, + "loss": 3.2076, "step": 96100 }, { "epoch": 0.32, - "learning_rate": 3.406007462933874e-05, - "loss": 3.2257, + "learning_rate": 3.407738193759393e-05, + "loss": 3.2113, "step": 96200 }, { "epoch": 0.32, - "learning_rate": 3.404350506034637e-05, - "loss": 3.2366, + "learning_rate": 3.406083035956648e-05, + "loss": 3.2022, "step": 96300 }, { "epoch": 0.32, - "learning_rate": 3.4026935491354e-05, - "loss": 3.2412, + "learning_rate": 3.4044278781539033e-05, + "loss": 3.2205, "step": 96400 }, { "epoch": 0.32, - "learning_rate": 3.4010365922361633e-05, - "loss": 3.2422, + "learning_rate": 3.4027727203511585e-05, + "loss": 3.219, "step": 96500 }, { "epoch": 0.32, - "learning_rate": 3.399379635336926e-05, - "loss": 3.2234, + "learning_rate": 3.401117562548414e-05, + "loss": 3.208, "step": 96600 }, { "epoch": 0.32, - "learning_rate": 3.3977226784376885e-05, - "loss": 3.2288, + "learning_rate": 3.399462404745669e-05, + "loss": 3.2122, "step": 96700 }, { "epoch": 0.32, - "learning_rate": 3.396065721538452e-05, - "loss": 3.2311, + "learning_rate": 3.397807246942924e-05, + "loss": 3.2184, "step": 96800 }, { "epoch": 0.32, - "learning_rate": 3.3944087646392143e-05, - "loss": 3.2405, + "learning_rate": 3.3961520891401785e-05, + "loss": 3.2141, "step": 96900 }, { "epoch": 0.32, - "learning_rate": 3.392751807739977e-05, - "loss": 3.22, + "learning_rate": 3.3944969313374336e-05, + "loss": 3.1999, "step": 97000 }, { "epoch": 0.32, - "learning_rate": 3.39109485084074e-05, - "loss": 3.2193, + "learning_rate": 3.392841773534689e-05, + "loss": 3.2156, "step": 97100 }, { "epoch": 0.32, - "learning_rate": 3.389437893941503e-05, - "loss": 3.2208, + "learning_rate": 3.391186615731944e-05, + "loss": 3.1978, "step": 97200 }, { "epoch": 0.32, - "learning_rate": 3.387780937042266e-05, - "loss": 3.2173, + "learning_rate": 3.389531457929199e-05, + "loss": 3.2225, "step": 97300 }, { "epoch": 0.32, - "learning_rate": 3.3861239801430286e-05, - "loss": 3.2119, + "learning_rate": 3.387876300126454e-05, + "loss": 3.2183, "step": 97400 }, { "epoch": 0.32, - "learning_rate": 3.384467023243791e-05, - "loss": 3.2322, + "learning_rate": 3.3862211423237094e-05, + "loss": 3.212, "step": 97500 }, { "epoch": 0.32, - "learning_rate": 3.3828100663445545e-05, - "loss": 3.2253, + "learning_rate": 3.3845659845209646e-05, + "loss": 3.2221, "step": 97600 }, { "epoch": 0.32, - "learning_rate": 3.381153109445318e-05, - "loss": 3.2345, + "learning_rate": 3.38291082671822e-05, + "loss": 3.233, "step": 97700 }, { "epoch": 0.32, - "learning_rate": 3.37949615254608e-05, - "loss": 3.2351, + "learning_rate": 3.381255668915474e-05, + "loss": 3.2255, "step": 97800 }, { "epoch": 0.32, - "learning_rate": 3.377839195646843e-05, - "loss": 3.2274, + "learning_rate": 3.37960051111273e-05, + "loss": 3.2232, "step": 97900 }, { "epoch": 0.32, - "learning_rate": 3.376182238747606e-05, - "loss": 3.2336, + "learning_rate": 3.3779453533099845e-05, + "loss": 3.2101, "step": 98000 }, { - "epoch": 0.33, - "learning_rate": 3.374525281848369e-05, - "loss": 3.2287, + "epoch": 0.32, + "learning_rate": 3.37629019550724e-05, + "loss": 3.2177, "step": 98100 }, { "epoch": 0.33, - "learning_rate": 3.372868324949131e-05, - "loss": 3.2335, + "learning_rate": 3.374635037704495e-05, + "loss": 3.232, "step": 98200 }, { "epoch": 0.33, - "learning_rate": 3.3712113680498946e-05, - "loss": 3.2347, + "learning_rate": 3.37297987990175e-05, + "loss": 3.2241, "step": 98300 }, { "epoch": 0.33, - "learning_rate": 3.369554411150657e-05, - "loss": 3.2256, + "learning_rate": 3.371324722099005e-05, + "loss": 3.2181, "step": 98400 }, { "epoch": 0.33, - "learning_rate": 3.3678974542514204e-05, - "loss": 3.2141, + "learning_rate": 3.3696695642962603e-05, + "loss": 3.2157, "step": 98500 }, { "epoch": 0.33, - "learning_rate": 3.366240497352183e-05, - "loss": 3.2306, + "learning_rate": 3.3680144064935155e-05, + "loss": 3.2139, "step": 98600 }, { "epoch": 0.33, - "learning_rate": 3.3645835404529456e-05, - "loss": 3.2361, + "learning_rate": 3.36635924869077e-05, + "loss": 3.2002, "step": 98700 }, { "epoch": 0.33, - "learning_rate": 3.362926583553709e-05, - "loss": 3.2326, + "learning_rate": 3.364704090888026e-05, + "loss": 3.2125, "step": 98800 }, { "epoch": 0.33, - "learning_rate": 3.361269626654472e-05, - "loss": 3.2227, + "learning_rate": 3.36304893308528e-05, + "loss": 3.2204, "step": 98900 }, { "epoch": 0.33, - "learning_rate": 3.359612669755235e-05, - "loss": 3.237, + "learning_rate": 3.361393775282536e-05, + "loss": 3.2045, "step": 99000 }, { "epoch": 0.33, - "learning_rate": 3.357955712855997e-05, - "loss": 3.2404, + "learning_rate": 3.3597386174797906e-05, + "loss": 3.2092, "step": 99100 }, { "epoch": 0.33, - "learning_rate": 3.3562987559567605e-05, - "loss": 3.2297, + "learning_rate": 3.358083459677046e-05, + "loss": 3.2169, "step": 99200 }, { "epoch": 0.33, - "learning_rate": 3.354641799057523e-05, - "loss": 3.2177, + "learning_rate": 3.356428301874301e-05, + "loss": 3.2236, "step": 99300 }, { "epoch": 0.33, - "learning_rate": 3.3529848421582863e-05, - "loss": 3.2255, + "learning_rate": 3.3547731440715554e-05, + "loss": 3.2094, "step": 99400 }, { "epoch": 0.33, - "learning_rate": 3.351327885259049e-05, - "loss": 3.229, + "learning_rate": 3.353117986268811e-05, + "loss": 3.2282, "step": 99500 }, { "epoch": 0.33, - "learning_rate": 3.3496709283598115e-05, - "loss": 3.2253, + "learning_rate": 3.351462828466066e-05, + "loss": 3.2174, "step": 99600 }, { "epoch": 0.33, - "learning_rate": 3.348013971460575e-05, - "loss": 3.219, + "learning_rate": 3.3498076706633216e-05, + "loss": 3.2173, "step": 99700 }, { "epoch": 0.33, - "learning_rate": 3.3463570145613374e-05, - "loss": 3.243, + "learning_rate": 3.348152512860576e-05, + "loss": 3.2206, "step": 99800 }, { "epoch": 0.33, - "learning_rate": 3.3447000576621e-05, - "loss": 3.2349, + "learning_rate": 3.346497355057832e-05, + "loss": 3.205, "step": 99900 }, { "epoch": 0.33, - "learning_rate": 3.343043100762863e-05, - "loss": 3.2488, + "learning_rate": 3.3448421972550864e-05, + "loss": 3.2302, "step": 100000 }, { "epoch": 0.33, - "learning_rate": 3.3413861438636265e-05, - "loss": 3.2385, + "learning_rate": 3.3431870394523416e-05, + "loss": 3.2069, "step": 100100 }, { "epoch": 0.33, - "learning_rate": 3.339729186964389e-05, - "loss": 3.2293, + "learning_rate": 3.341531881649597e-05, + "loss": 3.2128, "step": 100200 }, { "epoch": 0.33, - "learning_rate": 3.3380722300651516e-05, - "loss": 3.2342, + "learning_rate": 3.339876723846851e-05, + "loss": 3.2144, "step": 100300 }, { "epoch": 0.33, - "learning_rate": 3.336415273165915e-05, - "loss": 3.2411, + "learning_rate": 3.338221566044107e-05, + "loss": 3.221, "step": 100400 }, { "epoch": 0.33, - "learning_rate": 3.3347583162666775e-05, - "loss": 3.2371, + "learning_rate": 3.3365664082413615e-05, + "loss": 3.2181, "step": 100500 }, { "epoch": 0.33, - "learning_rate": 3.333101359367441e-05, - "loss": 3.2258, + "learning_rate": 3.3349112504386174e-05, + "loss": 3.2225, "step": 100600 }, { "epoch": 0.33, - "learning_rate": 3.3314444024682026e-05, - "loss": 3.2356, + "learning_rate": 3.333256092635872e-05, + "loss": 3.2134, "step": 100700 }, { "epoch": 0.33, - "learning_rate": 3.329787445568966e-05, - "loss": 3.229, + "learning_rate": 3.331600934833127e-05, + "loss": 3.22, "step": 100800 }, { "epoch": 0.33, - "learning_rate": 3.328130488669729e-05, - "loss": 3.2363, + "learning_rate": 3.329945777030382e-05, + "loss": 3.2056, "step": 100900 }, { "epoch": 0.33, - "learning_rate": 3.326473531770492e-05, - "loss": 3.226, + "learning_rate": 3.328290619227637e-05, + "loss": 3.2147, "step": 101000 }, { - "epoch": 0.34, - "learning_rate": 3.324816574871254e-05, - "loss": 3.2386, + "epoch": 0.33, + "learning_rate": 3.3266354614248925e-05, + "loss": 3.2266, "step": 101100 }, { "epoch": 0.34, - "learning_rate": 3.3231596179720176e-05, - "loss": 3.2363, + "learning_rate": 3.3249803036221476e-05, + "loss": 3.1922, "step": 101200 }, { "epoch": 0.34, - "learning_rate": 3.32150266107278e-05, - "loss": 3.2304, + "learning_rate": 3.323325145819403e-05, + "loss": 3.206, "step": 101300 }, { "epoch": 0.34, - "learning_rate": 3.3198457041735434e-05, - "loss": 3.2295, + "learning_rate": 3.321669988016657e-05, + "loss": 3.2208, "step": 101400 }, { "epoch": 0.34, - "learning_rate": 3.318188747274306e-05, - "loss": 3.2289, + "learning_rate": 3.320014830213913e-05, + "loss": 3.2202, "step": 101500 }, { "epoch": 0.34, - "learning_rate": 3.3165317903750686e-05, - "loss": 3.2365, + "learning_rate": 3.3183596724111676e-05, + "loss": 3.2122, "step": 101600 }, { "epoch": 0.34, - "learning_rate": 3.314874833475832e-05, - "loss": 3.2313, + "learning_rate": 3.316704514608423e-05, + "loss": 3.2116, "step": 101700 }, { "epoch": 0.34, - "learning_rate": 3.313217876576595e-05, - "loss": 3.2274, + "learning_rate": 3.315049356805678e-05, + "loss": 3.2134, "step": 101800 }, { "epoch": 0.34, - "learning_rate": 3.311560919677357e-05, - "loss": 3.2199, + "learning_rate": 3.313394199002933e-05, + "loss": 3.2103, "step": 101900 }, { "epoch": 0.34, - "learning_rate": 3.30990396277812e-05, - "loss": 3.2383, + "learning_rate": 3.311739041200188e-05, + "loss": 3.2068, "step": 102000 }, { "epoch": 0.34, - "learning_rate": 3.3082470058788835e-05, - "loss": 3.2247, + "learning_rate": 3.3100838833974434e-05, + "loss": 3.2104, "step": 102100 }, { "epoch": 0.34, - "learning_rate": 3.306590048979646e-05, - "loss": 3.2384, + "learning_rate": 3.3084287255946986e-05, + "loss": 3.2232, "step": 102200 }, { "epoch": 0.34, - "learning_rate": 3.304933092080409e-05, - "loss": 3.2346, + "learning_rate": 3.306773567791954e-05, + "loss": 3.2144, "step": 102300 }, { "epoch": 0.34, - "learning_rate": 3.303276135181172e-05, - "loss": 3.2464, + "learning_rate": 3.305118409989208e-05, + "loss": 3.2114, "step": 102400 }, { "epoch": 0.34, - "learning_rate": 3.3016191782819345e-05, - "loss": 3.2331, + "learning_rate": 3.3034632521864634e-05, + "loss": 3.2242, "step": 102500 }, { "epoch": 0.34, - "learning_rate": 3.299962221382698e-05, - "loss": 3.2337, + "learning_rate": 3.3018080943837185e-05, + "loss": 3.2113, "step": 102600 }, { "epoch": 0.34, - "learning_rate": 3.2983052644834604e-05, - "loss": 3.2389, + "learning_rate": 3.300152936580974e-05, + "loss": 3.2212, "step": 102700 }, { "epoch": 0.34, - "learning_rate": 3.296648307584223e-05, - "loss": 3.2324, + "learning_rate": 3.298497778778229e-05, + "loss": 3.2189, "step": 102800 }, { "epoch": 0.34, - "learning_rate": 3.294991350684986e-05, - "loss": 3.2205, + "learning_rate": 3.296842620975484e-05, + "loss": 3.2169, "step": 102900 }, { "epoch": 0.34, - "learning_rate": 3.2933343937857495e-05, - "loss": 3.2256, + "learning_rate": 3.295187463172739e-05, + "loss": 3.2197, "step": 103000 }, { "epoch": 0.34, - "learning_rate": 3.2916774368865114e-05, - "loss": 3.2269, + "learning_rate": 3.293532305369994e-05, + "loss": 3.216, "step": 103100 }, { "epoch": 0.34, - "learning_rate": 3.2900204799872746e-05, - "loss": 3.2183, + "learning_rate": 3.2918771475672495e-05, + "loss": 3.2166, "step": 103200 }, { "epoch": 0.34, - "learning_rate": 3.288363523088038e-05, - "loss": 3.2285, + "learning_rate": 3.290221989764504e-05, + "loss": 3.2132, "step": 103300 }, { "epoch": 0.34, - "learning_rate": 3.2867065661888005e-05, - "loss": 3.2214, + "learning_rate": 3.28856683196176e-05, + "loss": 3.2185, "step": 103400 }, { "epoch": 0.34, - "learning_rate": 3.285049609289563e-05, - "loss": 3.2273, + "learning_rate": 3.286911674159014e-05, + "loss": 3.2171, "step": 103500 }, { "epoch": 0.34, - "learning_rate": 3.283392652390326e-05, - "loss": 3.231, + "learning_rate": 3.2852565163562694e-05, + "loss": 3.2213, "step": 103600 }, { "epoch": 0.34, - "learning_rate": 3.281735695491089e-05, - "loss": 3.2162, + "learning_rate": 3.2836013585535246e-05, + "loss": 3.2184, "step": 103700 }, { "epoch": 0.34, - "learning_rate": 3.280078738591852e-05, - "loss": 3.2362, + "learning_rate": 3.28194620075078e-05, + "loss": 3.207, "step": 103800 }, { "epoch": 0.34, - "learning_rate": 3.278421781692615e-05, - "loss": 3.2199, + "learning_rate": 3.280291042948035e-05, + "loss": 3.2179, "step": 103900 }, { "epoch": 0.34, - "learning_rate": 3.276764824793377e-05, - "loss": 3.2301, + "learning_rate": 3.2786358851452894e-05, + "loss": 3.2106, "step": 104000 }, { "epoch": 0.34, - "learning_rate": 3.2751078678941406e-05, - "loss": 3.235, + "learning_rate": 3.276980727342545e-05, + "loss": 3.2138, "step": 104100 }, { - "epoch": 0.35, - "learning_rate": 3.273450910994904e-05, - "loss": 3.2261, + "epoch": 0.34, + "learning_rate": 3.2753255695398e-05, + "loss": 3.2092, "step": 104200 }, { "epoch": 0.35, - "learning_rate": 3.271793954095666e-05, - "loss": 3.2321, + "learning_rate": 3.2736704117370556e-05, + "loss": 3.2239, "step": 104300 }, { "epoch": 0.35, - "learning_rate": 3.270136997196429e-05, - "loss": 3.2355, + "learning_rate": 3.27201525393431e-05, + "loss": 3.2171, "step": 104400 }, { "epoch": 0.35, - "learning_rate": 3.268480040297192e-05, - "loss": 3.2353, + "learning_rate": 3.270360096131566e-05, + "loss": 3.2123, "step": 104500 }, { "epoch": 0.35, - "learning_rate": 3.266823083397955e-05, - "loss": 3.2207, + "learning_rate": 3.2687049383288204e-05, + "loss": 3.2178, "step": 104600 }, { "epoch": 0.35, - "learning_rate": 3.2651661264987174e-05, - "loss": 3.2329, + "learning_rate": 3.2670497805260755e-05, + "loss": 3.2123, "step": 104700 }, { "epoch": 0.35, - "learning_rate": 3.263509169599481e-05, - "loss": 3.2261, + "learning_rate": 3.265394622723331e-05, + "loss": 3.2263, "step": 104800 }, { "epoch": 0.35, - "learning_rate": 3.261852212700243e-05, - "loss": 3.2343, + "learning_rate": 3.263739464920585e-05, + "loss": 3.206, "step": 104900 }, { "epoch": 0.35, - "learning_rate": 3.2601952558010065e-05, - "loss": 3.225, + "learning_rate": 3.262084307117841e-05, + "loss": 3.2175, "step": 105000 }, { "epoch": 0.35, - "learning_rate": 3.258538298901769e-05, - "loss": 3.2261, + "learning_rate": 3.2604291493150955e-05, + "loss": 3.2182, "step": 105100 }, { "epoch": 0.35, - "learning_rate": 3.256881342002532e-05, - "loss": 3.233, + "learning_rate": 3.258773991512351e-05, + "loss": 3.2159, "step": 105200 }, { "epoch": 0.35, - "learning_rate": 3.255224385103295e-05, - "loss": 3.2243, + "learning_rate": 3.257118833709606e-05, + "loss": 3.2083, "step": 105300 }, { "epoch": 0.35, - "learning_rate": 3.253567428204058e-05, - "loss": 3.238, + "learning_rate": 3.255463675906861e-05, + "loss": 3.215, "step": 105400 }, { "epoch": 0.35, - "learning_rate": 3.25191047130482e-05, - "loss": 3.2217, + "learning_rate": 3.253808518104116e-05, + "loss": 3.2176, "step": 105500 }, { "epoch": 0.35, - "learning_rate": 3.2502535144055834e-05, - "loss": 3.2263, + "learning_rate": 3.252153360301371e-05, + "loss": 3.2174, "step": 105600 }, { "epoch": 0.35, - "learning_rate": 3.2485965575063466e-05, - "loss": 3.24, + "learning_rate": 3.2504982024986264e-05, + "loss": 3.2166, "step": 105700 }, { "epoch": 0.35, - "learning_rate": 3.246939600607109e-05, - "loss": 3.2362, + "learning_rate": 3.248843044695881e-05, + "loss": 3.2205, "step": 105800 }, { "epoch": 0.35, - "learning_rate": 3.245282643707872e-05, - "loss": 3.2442, + "learning_rate": 3.247187886893137e-05, + "loss": 3.2126, "step": 105900 }, { "epoch": 0.35, - "learning_rate": 3.243625686808635e-05, - "loss": 3.2427, + "learning_rate": 3.245532729090391e-05, + "loss": 3.2161, "step": 106000 }, { "epoch": 0.35, - "learning_rate": 3.2419687299093976e-05, - "loss": 3.2308, + "learning_rate": 3.243877571287647e-05, + "loss": 3.2172, "step": 106100 }, { "epoch": 0.35, - "learning_rate": 3.240311773010161e-05, - "loss": 3.2239, + "learning_rate": 3.2422224134849016e-05, + "loss": 3.2345, "step": 106200 }, { "epoch": 0.35, - "learning_rate": 3.2386548161109235e-05, - "loss": 3.2405, + "learning_rate": 3.240567255682157e-05, + "loss": 3.2015, "step": 106300 }, { "epoch": 0.35, - "learning_rate": 3.236997859211686e-05, - "loss": 3.2283, + "learning_rate": 3.238912097879412e-05, + "loss": 3.2203, "step": 106400 }, { "epoch": 0.35, - "learning_rate": 3.235340902312449e-05, - "loss": 3.2221, + "learning_rate": 3.237256940076667e-05, + "loss": 3.2063, "step": 106500 }, { "epoch": 0.35, - "learning_rate": 3.2336839454132126e-05, - "loss": 3.2467, + "learning_rate": 3.235601782273922e-05, + "loss": 3.2047, "step": 106600 }, { "epoch": 0.35, - "learning_rate": 3.2320269885139745e-05, - "loss": 3.2298, + "learning_rate": 3.2339466244711774e-05, + "loss": 3.2148, "step": 106700 }, { "epoch": 0.35, - "learning_rate": 3.230370031614738e-05, - "loss": 3.2264, + "learning_rate": 3.2322914666684325e-05, + "loss": 3.2131, "step": 106800 }, { "epoch": 0.35, - "learning_rate": 3.228713074715501e-05, - "loss": 3.2204, + "learning_rate": 3.230636308865687e-05, + "loss": 3.2055, "step": 106900 }, { "epoch": 0.35, - "learning_rate": 3.2270561178162636e-05, - "loss": 3.2318, + "learning_rate": 3.228981151062943e-05, + "loss": 3.2167, "step": 107000 }, { "epoch": 0.35, - "learning_rate": 3.225399160917026e-05, - "loss": 3.2317, + "learning_rate": 3.227325993260197e-05, + "loss": 3.2064, "step": 107100 }, { - "epoch": 0.36, - "learning_rate": 3.2237422040177894e-05, - "loss": 3.2323, + "epoch": 0.35, + "learning_rate": 3.2256708354574525e-05, + "loss": 3.2135, "step": 107200 }, { "epoch": 0.36, - "learning_rate": 3.222085247118552e-05, - "loss": 3.2188, + "learning_rate": 3.2240156776547077e-05, + "loss": 3.2032, "step": 107300 }, { "epoch": 0.36, - "learning_rate": 3.220428290219315e-05, - "loss": 3.2382, + "learning_rate": 3.222360519851963e-05, + "loss": 3.2125, "step": 107400 }, { "epoch": 0.36, - "learning_rate": 3.218771333320078e-05, - "loss": 3.2385, + "learning_rate": 3.220705362049218e-05, + "loss": 3.2259, "step": 107500 }, { "epoch": 0.36, - "learning_rate": 3.2171143764208404e-05, - "loss": 3.2225, + "learning_rate": 3.219050204246473e-05, + "loss": 3.2223, "step": 107600 }, { "epoch": 0.36, - "learning_rate": 3.215457419521604e-05, - "loss": 3.2201, + "learning_rate": 3.217395046443728e-05, + "loss": 3.2173, "step": 107700 }, { "epoch": 0.36, - "learning_rate": 3.213800462622367e-05, - "loss": 3.233, + "learning_rate": 3.2157398886409835e-05, + "loss": 3.2094, "step": 107800 }, { "epoch": 0.36, - "learning_rate": 3.212143505723129e-05, - "loss": 3.2328, + "learning_rate": 3.214084730838238e-05, + "loss": 3.2085, "step": 107900 }, { "epoch": 0.36, - "learning_rate": 3.210486548823892e-05, - "loss": 3.2275, + "learning_rate": 3.212429573035494e-05, + "loss": 3.2124, "step": 108000 }, { "epoch": 0.36, - "learning_rate": 3.2088295919246554e-05, - "loss": 3.2484, + "learning_rate": 3.210774415232748e-05, + "loss": 3.2167, "step": 108100 }, { "epoch": 0.36, - "learning_rate": 3.207172635025418e-05, - "loss": 3.2282, + "learning_rate": 3.2091192574300034e-05, + "loss": 3.2069, "step": 108200 }, { "epoch": 0.36, - "learning_rate": 3.2055156781261805e-05, - "loss": 3.2229, + "learning_rate": 3.2074640996272586e-05, + "loss": 3.2212, "step": 108300 }, { "epoch": 0.36, - "learning_rate": 3.203858721226944e-05, - "loss": 3.2231, + "learning_rate": 3.205808941824514e-05, + "loss": 3.2001, "step": 108400 }, { "epoch": 0.36, - "learning_rate": 3.2022017643277064e-05, - "loss": 3.2365, + "learning_rate": 3.204153784021769e-05, + "loss": 3.2189, "step": 108500 }, { "epoch": 0.36, - "learning_rate": 3.2005448074284696e-05, - "loss": 3.2248, + "learning_rate": 3.202498626219024e-05, + "loss": 3.2099, "step": 108600 }, { "epoch": 0.36, - "learning_rate": 3.198887850529232e-05, - "loss": 3.2227, + "learning_rate": 3.200843468416279e-05, + "loss": 3.2313, "step": 108700 }, { "epoch": 0.36, - "learning_rate": 3.197230893629995e-05, - "loss": 3.2154, + "learning_rate": 3.199188310613534e-05, + "loss": 3.2255, "step": 108800 }, { "epoch": 0.36, - "learning_rate": 3.195573936730758e-05, - "loss": 3.2262, + "learning_rate": 3.1975331528107895e-05, + "loss": 3.2169, "step": 108900 }, { "epoch": 0.36, - "learning_rate": 3.193916979831521e-05, - "loss": 3.2372, + "learning_rate": 3.195877995008044e-05, + "loss": 3.2065, "step": 109000 }, { "epoch": 0.36, - "learning_rate": 3.192260022932284e-05, - "loss": 3.2315, + "learning_rate": 3.1942228372053e-05, + "loss": 3.2056, "step": 109100 }, { "epoch": 0.36, - "learning_rate": 3.1906030660330465e-05, - "loss": 3.2385, + "learning_rate": 3.1925676794025543e-05, + "loss": 3.2181, "step": 109200 }, { "epoch": 0.36, - "learning_rate": 3.188946109133809e-05, - "loss": 3.2223, + "learning_rate": 3.1909125215998095e-05, + "loss": 3.21, "step": 109300 }, { "epoch": 0.36, - "learning_rate": 3.187289152234572e-05, - "loss": 3.2236, + "learning_rate": 3.1892573637970647e-05, + "loss": 3.2092, "step": 109400 }, { "epoch": 0.36, - "learning_rate": 3.185632195335335e-05, - "loss": 3.2245, + "learning_rate": 3.187602205994319e-05, + "loss": 3.2106, "step": 109500 }, { "epoch": 0.36, - "learning_rate": 3.1839752384360975e-05, - "loss": 3.2415, + "learning_rate": 3.185947048191575e-05, + "loss": 3.2285, "step": 109600 }, { "epoch": 0.36, - "learning_rate": 3.182318281536861e-05, - "loss": 3.227, + "learning_rate": 3.1842918903888295e-05, + "loss": 3.2064, "step": 109700 }, { "epoch": 0.36, - "learning_rate": 3.180661324637624e-05, - "loss": 3.222, + "learning_rate": 3.182636732586085e-05, + "loss": 3.2219, "step": 109800 }, { "epoch": 0.36, - "learning_rate": 3.1790043677383866e-05, - "loss": 3.2142, + "learning_rate": 3.18098157478334e-05, + "loss": 3.214, "step": 109900 }, { "epoch": 0.36, - "learning_rate": 3.177347410839149e-05, - "loss": 3.2194, + "learning_rate": 3.1793264169805956e-05, + "loss": 3.2125, "step": 110000 }, { "epoch": 0.36, - "learning_rate": 3.1756904539399124e-05, - "loss": 3.2304, + "learning_rate": 3.17767125917785e-05, + "loss": 3.2134, "step": 110100 }, { - "epoch": 0.37, - "learning_rate": 3.174033497040675e-05, - "loss": 3.2377, + "epoch": 0.36, + "learning_rate": 3.176016101375105e-05, + "loss": 3.2183, "step": 110200 }, { "epoch": 0.37, - "learning_rate": 3.172376540141438e-05, - "loss": 3.2376, + "learning_rate": 3.1743609435723604e-05, + "loss": 3.2137, "step": 110300 }, { "epoch": 0.37, - "learning_rate": 3.170719583242201e-05, - "loss": 3.232, + "learning_rate": 3.172705785769615e-05, + "loss": 3.2198, "step": 110400 }, { "epoch": 0.37, - "learning_rate": 3.1690626263429634e-05, - "loss": 3.2356, + "learning_rate": 3.171050627966871e-05, + "loss": 3.2033, "step": 110500 }, { "epoch": 0.37, - "learning_rate": 3.167405669443727e-05, - "loss": 3.223, + "learning_rate": 3.169395470164125e-05, + "loss": 3.2077, "step": 110600 }, { "epoch": 0.37, - "learning_rate": 3.165748712544489e-05, - "loss": 3.2433, + "learning_rate": 3.167740312361381e-05, + "loss": 3.2076, "step": 110700 }, { "epoch": 0.37, - "learning_rate": 3.164091755645252e-05, - "loss": 3.2333, + "learning_rate": 3.1660851545586355e-05, + "loss": 3.2198, "step": 110800 }, { "epoch": 0.37, - "learning_rate": 3.162434798746015e-05, - "loss": 3.2223, + "learning_rate": 3.164429996755891e-05, + "loss": 3.208, "step": 110900 }, { "epoch": 0.37, - "learning_rate": 3.1607778418467784e-05, - "loss": 3.2395, + "learning_rate": 3.162774838953146e-05, + "loss": 3.2236, "step": 111000 }, { "epoch": 0.37, - "learning_rate": 3.159120884947541e-05, - "loss": 3.2346, + "learning_rate": 3.161119681150401e-05, + "loss": 3.1924, "step": 111100 }, { "epoch": 0.37, - "learning_rate": 3.1574639280483035e-05, - "loss": 3.2348, + "learning_rate": 3.159464523347656e-05, + "loss": 3.2076, "step": 111200 }, { "epoch": 0.37, - "learning_rate": 3.155806971149067e-05, - "loss": 3.2257, + "learning_rate": 3.1578093655449113e-05, + "loss": 3.2083, "step": 111300 }, { "epoch": 0.37, - "learning_rate": 3.1541500142498294e-05, - "loss": 3.2289, + "learning_rate": 3.1561542077421665e-05, + "loss": 3.2161, "step": 111400 }, { "epoch": 0.37, - "learning_rate": 3.1524930573505926e-05, - "loss": 3.2265, + "learning_rate": 3.154499049939421e-05, + "loss": 3.2077, "step": 111500 }, { "epoch": 0.37, - "learning_rate": 3.150836100451355e-05, - "loss": 3.2324, + "learning_rate": 3.152843892136677e-05, + "loss": 3.2125, "step": 111600 }, { "epoch": 0.37, - "learning_rate": 3.149179143552118e-05, - "loss": 3.2251, + "learning_rate": 3.151188734333931e-05, + "loss": 3.2076, "step": 111700 }, { "epoch": 0.37, - "learning_rate": 3.147522186652881e-05, - "loss": 3.2295, + "learning_rate": 3.1495335765311865e-05, + "loss": 3.2141, "step": 111800 }, { "epoch": 0.37, - "learning_rate": 3.1458652297536436e-05, - "loss": 3.2176, + "learning_rate": 3.1478784187284416e-05, + "loss": 3.2007, "step": 111900 }, { "epoch": 0.37, - "learning_rate": 3.144208272854406e-05, - "loss": 3.2224, + "learning_rate": 3.146223260925697e-05, + "loss": 3.2117, "step": 112000 }, { "epoch": 0.37, - "learning_rate": 3.1425513159551695e-05, - "loss": 3.2243, + "learning_rate": 3.144568103122952e-05, + "loss": 3.2139, "step": 112100 }, { "epoch": 0.37, - "learning_rate": 3.140894359055933e-05, - "loss": 3.2256, + "learning_rate": 3.142912945320207e-05, + "loss": 3.2103, "step": 112200 }, { "epoch": 0.37, - "learning_rate": 3.139237402156695e-05, - "loss": 3.2403, + "learning_rate": 3.141257787517462e-05, + "loss": 3.2301, "step": 112300 }, { "epoch": 0.37, - "learning_rate": 3.137580445257458e-05, - "loss": 3.2341, + "learning_rate": 3.1396026297147174e-05, + "loss": 3.2093, "step": 112400 }, { "epoch": 0.37, - "learning_rate": 3.135923488358221e-05, - "loss": 3.2252, + "learning_rate": 3.137947471911972e-05, + "loss": 3.2164, "step": 112500 }, { "epoch": 0.37, - "learning_rate": 3.134266531458984e-05, - "loss": 3.2344, + "learning_rate": 3.136292314109227e-05, + "loss": 3.2135, "step": 112600 }, { "epoch": 0.37, - "learning_rate": 3.132609574559747e-05, - "loss": 3.2295, + "learning_rate": 3.134637156306482e-05, + "loss": 3.2134, "step": 112700 }, { "epoch": 0.37, - "learning_rate": 3.1309526176605096e-05, - "loss": 3.2217, + "learning_rate": 3.1329819985037374e-05, + "loss": 3.2188, "step": 112800 }, { "epoch": 0.37, - "learning_rate": 3.129295660761272e-05, - "loss": 3.2301, + "learning_rate": 3.1313268407009925e-05, + "loss": 3.2105, "step": 112900 }, { "epoch": 0.37, - "learning_rate": 3.1276387038620354e-05, - "loss": 3.2276, + "learning_rate": 3.129671682898248e-05, + "loss": 3.2104, "step": 113000 }, { "epoch": 0.37, - "learning_rate": 3.125981746962798e-05, - "loss": 3.2163, + "learning_rate": 3.128016525095503e-05, + "loss": 3.2033, "step": 113100 }, { - "epoch": 0.38, - "learning_rate": 3.1243247900635606e-05, - "loss": 3.2197, + "epoch": 0.37, + "learning_rate": 3.126361367292758e-05, + "loss": 3.2155, "step": 113200 }, { "epoch": 0.38, - "learning_rate": 3.122667833164324e-05, - "loss": 3.2331, + "learning_rate": 3.124706209490013e-05, + "loss": 3.1941, "step": 113300 }, { "epoch": 0.38, - "learning_rate": 3.121010876265087e-05, - "loss": 3.2393, + "learning_rate": 3.123051051687268e-05, + "loss": 3.219, "step": 113400 }, { "epoch": 0.38, - "learning_rate": 3.11935391936585e-05, - "loss": 3.2349, + "learning_rate": 3.1213958938845235e-05, + "loss": 3.1956, "step": 113500 }, { "epoch": 0.38, - "learning_rate": 3.117696962466612e-05, - "loss": 3.2398, + "learning_rate": 3.119740736081778e-05, + "loss": 3.2119, "step": 113600 }, { "epoch": 0.38, - "learning_rate": 3.1160400055673755e-05, - "loss": 3.2226, + "learning_rate": 3.118085578279033e-05, + "loss": 3.2063, "step": 113700 }, { "epoch": 0.38, - "learning_rate": 3.114383048668138e-05, - "loss": 3.235, + "learning_rate": 3.116430420476288e-05, + "loss": 3.2058, "step": 113800 }, { "epoch": 0.38, - "learning_rate": 3.1127260917689014e-05, - "loss": 3.2323, + "learning_rate": 3.1147752626735435e-05, + "loss": 3.2183, "step": 113900 }, { "epoch": 0.38, - "learning_rate": 3.111069134869664e-05, - "loss": 3.2148, + "learning_rate": 3.1131201048707986e-05, + "loss": 3.2157, "step": 114000 }, { "epoch": 0.38, - "learning_rate": 3.1094121779704265e-05, - "loss": 3.2374, + "learning_rate": 3.111464947068054e-05, + "loss": 3.2146, "step": 114100 }, { "epoch": 0.38, - "learning_rate": 3.10775522107119e-05, - "loss": 3.2386, + "learning_rate": 3.109809789265309e-05, + "loss": 3.2093, "step": 114200 }, { "epoch": 0.38, - "learning_rate": 3.106098264171953e-05, - "loss": 3.2384, + "learning_rate": 3.1081546314625634e-05, + "loss": 3.211, "step": 114300 }, { "epoch": 0.38, - "learning_rate": 3.104441307272715e-05, - "loss": 3.2152, + "learning_rate": 3.106499473659819e-05, + "loss": 3.2102, "step": 114400 }, { "epoch": 0.38, - "learning_rate": 3.102784350373478e-05, - "loss": 3.2395, + "learning_rate": 3.104844315857074e-05, + "loss": 3.2225, "step": 114500 }, { "epoch": 0.38, - "learning_rate": 3.1011273934742415e-05, - "loss": 3.2241, + "learning_rate": 3.1031891580543296e-05, + "loss": 3.2211, "step": 114600 }, { "epoch": 0.38, - "learning_rate": 3.099470436575004e-05, - "loss": 3.2374, + "learning_rate": 3.101534000251584e-05, + "loss": 3.2268, "step": 114700 }, { "epoch": 0.38, - "learning_rate": 3.0978134796757666e-05, - "loss": 3.2332, + "learning_rate": 3.099878842448839e-05, + "loss": 3.2043, "step": 114800 }, { "epoch": 0.38, - "learning_rate": 3.09615652277653e-05, - "loss": 3.222, + "learning_rate": 3.0982236846460944e-05, + "loss": 3.2144, "step": 114900 }, { "epoch": 0.38, - "learning_rate": 3.0944995658772925e-05, - "loss": 3.2152, + "learning_rate": 3.096568526843349e-05, + "loss": 3.2017, "step": 115000 }, { "epoch": 0.38, - "learning_rate": 3.092842608978056e-05, - "loss": 3.2408, + "learning_rate": 3.094913369040605e-05, + "loss": 3.2268, "step": 115100 }, { "epoch": 0.38, - "learning_rate": 3.091185652078818e-05, - "loss": 3.2377, + "learning_rate": 3.093258211237859e-05, + "loss": 3.2111, "step": 115200 }, { "epoch": 0.38, - "learning_rate": 3.089528695179581e-05, - "loss": 3.2156, + "learning_rate": 3.091603053435115e-05, + "loss": 3.2112, "step": 115300 }, { "epoch": 0.38, - "learning_rate": 3.087871738280344e-05, - "loss": 3.213, + "learning_rate": 3.0899478956323695e-05, + "loss": 3.2139, "step": 115400 }, { "epoch": 0.38, - "learning_rate": 3.0862147813811074e-05, - "loss": 3.2395, + "learning_rate": 3.0882927378296254e-05, + "loss": 3.2076, "step": 115500 }, { "epoch": 0.38, - "learning_rate": 3.084557824481869e-05, - "loss": 3.2366, + "learning_rate": 3.08663758002688e-05, + "loss": 3.2195, "step": 115600 }, { "epoch": 0.38, - "learning_rate": 3.0829008675826326e-05, - "loss": 3.2261, + "learning_rate": 3.084982422224135e-05, + "loss": 3.2077, "step": 115700 }, { "epoch": 0.38, - "learning_rate": 3.081243910683396e-05, - "loss": 3.2225, + "learning_rate": 3.08332726442139e-05, + "loss": 3.204, "step": 115800 }, { "epoch": 0.38, - "learning_rate": 3.0795869537841584e-05, - "loss": 3.2136, + "learning_rate": 3.0816721066186446e-05, + "loss": 3.195, "step": 115900 }, { "epoch": 0.38, - "learning_rate": 3.077929996884921e-05, - "loss": 3.2334, + "learning_rate": 3.0800169488159005e-05, + "loss": 3.2033, "step": 116000 }, { "epoch": 0.38, - "learning_rate": 3.076273039985684e-05, - "loss": 3.2375, + "learning_rate": 3.078361791013155e-05, + "loss": 3.2174, "step": 116100 }, { - "epoch": 0.39, - "learning_rate": 3.074616083086447e-05, - "loss": 3.2291, + "epoch": 0.38, + "learning_rate": 3.076706633210411e-05, + "loss": 3.206, "step": 116200 }, { - "epoch": 0.39, - "learning_rate": 3.07295912618721e-05, - "loss": 3.2267, + "epoch": 0.38, + "learning_rate": 3.075051475407665e-05, + "loss": 3.2081, "step": 116300 }, { "epoch": 0.39, - "learning_rate": 3.071302169287973e-05, - "loss": 3.2334, + "learning_rate": 3.0733963176049204e-05, + "loss": 3.2117, "step": 116400 }, { "epoch": 0.39, - "learning_rate": 3.069645212388735e-05, - "loss": 3.243, + "learning_rate": 3.0717411598021756e-05, + "loss": 3.2291, "step": 116500 }, { "epoch": 0.39, - "learning_rate": 3.0679882554894985e-05, - "loss": 3.2383, + "learning_rate": 3.070086001999431e-05, + "loss": 3.2169, "step": 116600 }, { "epoch": 0.39, - "learning_rate": 3.066331298590262e-05, - "loss": 3.2226, + "learning_rate": 3.068430844196686e-05, + "loss": 3.2108, "step": 116700 }, { "epoch": 0.39, - "learning_rate": 3.064674341691024e-05, - "loss": 3.2293, + "learning_rate": 3.066775686393941e-05, + "loss": 3.2212, "step": 116800 }, { "epoch": 0.39, - "learning_rate": 3.063017384791787e-05, - "loss": 3.2295, + "learning_rate": 3.065120528591196e-05, + "loss": 3.2008, "step": 116900 }, { "epoch": 0.39, - "learning_rate": 3.06136042789255e-05, - "loss": 3.2255, + "learning_rate": 3.063465370788451e-05, + "loss": 3.2144, "step": 117000 }, { "epoch": 0.39, - "learning_rate": 3.059703470993313e-05, - "loss": 3.2237, + "learning_rate": 3.0618102129857066e-05, + "loss": 3.2073, "step": 117100 }, { "epoch": 0.39, - "learning_rate": 3.0580465140940754e-05, - "loss": 3.2296, + "learning_rate": 3.060155055182961e-05, + "loss": 3.2153, "step": 117200 }, { "epoch": 0.39, - "learning_rate": 3.0563895571948386e-05, - "loss": 3.2146, + "learning_rate": 3.058499897380216e-05, + "loss": 3.211, "step": 117300 }, { "epoch": 0.39, - "learning_rate": 3.054732600295601e-05, - "loss": 3.233, + "learning_rate": 3.0568447395774714e-05, + "loss": 3.2168, "step": 117400 }, { "epoch": 0.39, - "learning_rate": 3.0530756433963645e-05, - "loss": 3.2368, + "learning_rate": 3.0551895817747265e-05, + "loss": 3.216, "step": 117500 }, { "epoch": 0.39, - "learning_rate": 3.0514186864971274e-05, - "loss": 3.2226, + "learning_rate": 3.053534423971982e-05, + "loss": 3.2004, "step": 117600 }, { "epoch": 0.39, - "learning_rate": 3.0497617295978896e-05, - "loss": 3.2194, + "learning_rate": 3.051879266169237e-05, + "loss": 3.2084, "step": 117700 }, { "epoch": 0.39, - "learning_rate": 3.048104772698653e-05, - "loss": 3.2265, + "learning_rate": 3.0502241083664917e-05, + "loss": 3.22, "step": 117800 }, { "epoch": 0.39, - "learning_rate": 3.046447815799415e-05, - "loss": 3.2417, + "learning_rate": 3.048568950563747e-05, + "loss": 3.2166, "step": 117900 }, { "epoch": 0.39, - "learning_rate": 3.0447908589001784e-05, - "loss": 3.2405, + "learning_rate": 3.046913792761002e-05, + "loss": 3.2222, "step": 118000 }, { "epoch": 0.39, - "learning_rate": 3.0431339020009413e-05, - "loss": 3.2319, + "learning_rate": 3.0452586349582568e-05, + "loss": 3.2117, "step": 118100 }, { "epoch": 0.39, - "learning_rate": 3.041476945101704e-05, - "loss": 3.2268, + "learning_rate": 3.0436034771555123e-05, + "loss": 3.2125, "step": 118200 }, { "epoch": 0.39, - "learning_rate": 3.0398199882024668e-05, - "loss": 3.2309, + "learning_rate": 3.041948319352767e-05, + "loss": 3.2137, "step": 118300 }, { "epoch": 0.39, - "learning_rate": 3.03816303130323e-05, - "loss": 3.2208, + "learning_rate": 3.0402931615500223e-05, + "loss": 3.215, "step": 118400 }, { "epoch": 0.39, - "learning_rate": 3.0365060744039927e-05, - "loss": 3.2245, + "learning_rate": 3.038638003747277e-05, + "loss": 3.218, "step": 118500 }, { "epoch": 0.39, - "learning_rate": 3.0348491175047556e-05, - "loss": 3.2487, + "learning_rate": 3.0369828459445326e-05, + "loss": 3.1974, "step": 118600 }, { "epoch": 0.39, - "learning_rate": 3.0331921606055185e-05, - "loss": 3.2202, + "learning_rate": 3.0353276881417874e-05, + "loss": 3.2126, "step": 118700 }, { "epoch": 0.39, - "learning_rate": 3.031535203706281e-05, - "loss": 3.2295, + "learning_rate": 3.033672530339043e-05, + "loss": 3.2139, "step": 118800 }, { "epoch": 0.39, - "learning_rate": 3.029878246807044e-05, - "loss": 3.2206, + "learning_rate": 3.0320173725362977e-05, + "loss": 3.2146, "step": 118900 }, { "epoch": 0.39, - "learning_rate": 3.0282212899078073e-05, - "loss": 3.2292, + "learning_rate": 3.0303622147335532e-05, + "loss": 3.2, "step": 119000 }, { "epoch": 0.39, - "learning_rate": 3.02656433300857e-05, - "loss": 3.2261, + "learning_rate": 3.028707056930808e-05, + "loss": 3.2269, "step": 119100 }, { - "epoch": 0.4, - "learning_rate": 3.0249073761093328e-05, - "loss": 3.2271, + "epoch": 0.39, + "learning_rate": 3.027051899128063e-05, + "loss": 3.2071, "step": 119200 }, { - "epoch": 0.4, - "learning_rate": 3.0232504192100957e-05, - "loss": 3.2221, + "epoch": 0.39, + "learning_rate": 3.025396741325318e-05, + "loss": 3.2145, "step": 119300 }, { "epoch": 0.4, - "learning_rate": 3.0215934623108583e-05, - "loss": 3.2278, + "learning_rate": 3.023741583522573e-05, + "loss": 3.2169, "step": 119400 }, { "epoch": 0.4, - "learning_rate": 3.0199365054116212e-05, - "loss": 3.2219, + "learning_rate": 3.0220864257198284e-05, + "loss": 3.2167, "step": 119500 }, { "epoch": 0.4, - "learning_rate": 3.0182795485123844e-05, - "loss": 3.2203, + "learning_rate": 3.0204312679170832e-05, + "loss": 3.2153, "step": 119600 }, { "epoch": 0.4, - "learning_rate": 3.016622591613147e-05, - "loss": 3.2124, + "learning_rate": 3.0187761101143387e-05, + "loss": 3.2135, "step": 119700 }, { "epoch": 0.4, - "learning_rate": 3.01496563471391e-05, - "loss": 3.2194, + "learning_rate": 3.0171209523115935e-05, + "loss": 3.1964, "step": 119800 }, { "epoch": 0.4, - "learning_rate": 3.013308677814673e-05, - "loss": 3.2409, + "learning_rate": 3.0154657945088487e-05, + "loss": 3.2092, "step": 119900 }, { "epoch": 0.4, - "learning_rate": 3.0116517209154354e-05, - "loss": 3.2318, + "learning_rate": 3.0138106367061035e-05, + "loss": 3.2155, "step": 120000 }, { "epoch": 0.4, - "learning_rate": 3.0099947640161984e-05, - "loss": 3.2093, + "learning_rate": 3.012155478903359e-05, + "loss": 3.2027, "step": 120100 }, { "epoch": 0.4, - "learning_rate": 3.0083378071169616e-05, - "loss": 3.2183, + "learning_rate": 3.0105003211006138e-05, + "loss": 3.207, "step": 120200 }, { "epoch": 0.4, - "learning_rate": 3.0066808502177242e-05, - "loss": 3.2256, + "learning_rate": 3.0088451632978686e-05, + "loss": 3.2054, "step": 120300 }, { "epoch": 0.4, - "learning_rate": 3.005023893318487e-05, - "loss": 3.227, + "learning_rate": 3.007190005495124e-05, + "loss": 3.2104, "step": 120400 }, { "epoch": 0.4, - "learning_rate": 3.00336693641925e-05, - "loss": 3.2367, + "learning_rate": 3.005534847692379e-05, + "loss": 3.2141, "step": 120500 }, { "epoch": 0.4, - "learning_rate": 3.0017099795200126e-05, - "loss": 3.2392, + "learning_rate": 3.0038796898896344e-05, + "loss": 3.2351, "step": 120600 }, { "epoch": 0.4, - "learning_rate": 3.0000530226207755e-05, - "loss": 3.2285, + "learning_rate": 3.0022245320868893e-05, + "loss": 3.2072, "step": 120700 }, { "epoch": 0.4, - "learning_rate": 2.9983960657215388e-05, - "loss": 3.2154, + "learning_rate": 3.0005693742841444e-05, + "loss": 3.2226, "step": 120800 }, { "epoch": 0.4, - "learning_rate": 2.9967391088223014e-05, - "loss": 3.2316, + "learning_rate": 2.9989142164813993e-05, + "loss": 3.2129, "step": 120900 }, { "epoch": 0.4, - "learning_rate": 2.9950821519230643e-05, - "loss": 3.2332, + "learning_rate": 2.9972590586786548e-05, + "loss": 3.2077, "step": 121000 }, { "epoch": 0.4, - "learning_rate": 2.9934251950238272e-05, - "loss": 3.2192, + "learning_rate": 2.9956039008759096e-05, + "loss": 3.2047, "step": 121100 }, { "epoch": 0.4, - "learning_rate": 2.9917682381245898e-05, - "loss": 3.2238, + "learning_rate": 2.993948743073165e-05, + "loss": 3.2231, "step": 121200 }, { "epoch": 0.4, - "learning_rate": 2.9901112812253527e-05, - "loss": 3.2334, + "learning_rate": 2.99229358527042e-05, + "loss": 3.2042, "step": 121300 }, { "epoch": 0.4, - "learning_rate": 2.988454324326116e-05, - "loss": 3.2313, + "learning_rate": 2.9906384274676747e-05, + "loss": 3.2102, "step": 121400 }, { "epoch": 0.4, - "learning_rate": 2.9867973674268786e-05, - "loss": 3.231, + "learning_rate": 2.98898326966493e-05, + "loss": 3.2076, "step": 121500 }, { "epoch": 0.4, - "learning_rate": 2.9851404105276415e-05, - "loss": 3.2317, + "learning_rate": 2.9873281118621847e-05, + "loss": 3.2117, "step": 121600 }, { "epoch": 0.4, - "learning_rate": 2.9834834536284044e-05, - "loss": 3.245, + "learning_rate": 2.9856729540594402e-05, + "loss": 3.2181, "step": 121700 }, { "epoch": 0.4, - "learning_rate": 2.981826496729167e-05, - "loss": 3.2195, + "learning_rate": 2.984017796256695e-05, + "loss": 3.2159, "step": 121800 }, { "epoch": 0.4, - "learning_rate": 2.98016953982993e-05, - "loss": 3.2271, + "learning_rate": 2.9823626384539505e-05, + "loss": 3.2139, "step": 121900 }, { "epoch": 0.4, - "learning_rate": 2.9785125829306932e-05, - "loss": 3.2187, + "learning_rate": 2.9807074806512053e-05, + "loss": 3.2215, "step": 122000 }, { "epoch": 0.4, - "learning_rate": 2.9768556260314558e-05, - "loss": 3.2208, + "learning_rate": 2.979052322848461e-05, + "loss": 3.2234, "step": 122100 }, { "epoch": 0.4, - "learning_rate": 2.9751986691322187e-05, - "loss": 3.2191, + "learning_rate": 2.9773971650457157e-05, + "loss": 3.2025, "step": 122200 }, { - "epoch": 0.41, - "learning_rate": 2.9735417122329816e-05, - "loss": 3.2307, + "epoch": 0.4, + "learning_rate": 2.9757420072429708e-05, + "loss": 3.2206, "step": 122300 }, { "epoch": 0.41, - "learning_rate": 2.9718847553337442e-05, - "loss": 3.2211, + "learning_rate": 2.9740868494402256e-05, + "loss": 3.2149, "step": 122400 }, { "epoch": 0.41, - "learning_rate": 2.970227798434507e-05, - "loss": 3.2381, + "learning_rate": 2.9724316916374805e-05, + "loss": 3.2153, "step": 122500 }, { "epoch": 0.41, - "learning_rate": 2.9685708415352704e-05, - "loss": 3.2402, + "learning_rate": 2.970776533834736e-05, + "loss": 3.2168, "step": 122600 }, { "epoch": 0.41, - "learning_rate": 2.966913884636033e-05, - "loss": 3.2266, + "learning_rate": 2.9691213760319908e-05, + "loss": 3.2086, "step": 122700 }, { "epoch": 0.41, - "learning_rate": 2.965256927736796e-05, - "loss": 3.2324, + "learning_rate": 2.9674662182292463e-05, + "loss": 3.2081, "step": 122800 }, { "epoch": 0.41, - "learning_rate": 2.9635999708375588e-05, - "loss": 3.2224, + "learning_rate": 2.965811060426501e-05, + "loss": 3.205, "step": 122900 }, { "epoch": 0.41, - "learning_rate": 2.9619430139383214e-05, - "loss": 3.2309, + "learning_rate": 2.9641559026237563e-05, + "loss": 3.2146, "step": 123000 }, { "epoch": 0.41, - "learning_rate": 2.9602860570390846e-05, - "loss": 3.2154, + "learning_rate": 2.9625007448210114e-05, + "loss": 3.2039, "step": 123100 }, { "epoch": 0.41, - "learning_rate": 2.9586291001398475e-05, - "loss": 3.2346, + "learning_rate": 2.9608455870182666e-05, + "loss": 3.1994, "step": 123200 }, { "epoch": 0.41, - "learning_rate": 2.95697214324061e-05, - "loss": 3.2175, + "learning_rate": 2.9591904292155214e-05, + "loss": 3.2157, "step": 123300 }, { "epoch": 0.41, - "learning_rate": 2.955315186341373e-05, - "loss": 3.2232, + "learning_rate": 2.957535271412777e-05, + "loss": 3.2073, "step": 123400 }, { "epoch": 0.41, - "learning_rate": 2.953658229442136e-05, - "loss": 3.2271, + "learning_rate": 2.9558801136100317e-05, + "loss": 3.2103, "step": 123500 }, { "epoch": 0.41, - "learning_rate": 2.9520012725428986e-05, - "loss": 3.2256, + "learning_rate": 2.9542249558072865e-05, + "loss": 3.2013, "step": 123600 }, { "epoch": 0.41, - "learning_rate": 2.9503443156436618e-05, - "loss": 3.2454, + "learning_rate": 2.952569798004542e-05, + "loss": 3.2066, "step": 123700 }, { "epoch": 0.41, - "learning_rate": 2.9486873587444247e-05, - "loss": 3.2222, + "learning_rate": 2.950914640201797e-05, + "loss": 3.2168, "step": 123800 }, { "epoch": 0.41, - "learning_rate": 2.9470304018451873e-05, - "loss": 3.2316, + "learning_rate": 2.949259482399052e-05, + "loss": 3.2092, "step": 123900 }, { "epoch": 0.41, - "learning_rate": 2.9453734449459502e-05, - "loss": 3.2242, + "learning_rate": 2.947604324596307e-05, + "loss": 3.2012, "step": 124000 }, { "epoch": 0.41, - "learning_rate": 2.943716488046713e-05, - "loss": 3.229, + "learning_rate": 2.9459491667935623e-05, + "loss": 3.2065, "step": 124100 }, { "epoch": 0.41, - "learning_rate": 2.9420595311474757e-05, - "loss": 3.2243, + "learning_rate": 2.944294008990817e-05, + "loss": 3.2076, "step": 124200 }, { "epoch": 0.41, - "learning_rate": 2.940402574248239e-05, - "loss": 3.2444, + "learning_rate": 2.9426388511880727e-05, + "loss": 3.2081, "step": 124300 }, { "epoch": 0.41, - "learning_rate": 2.938745617349002e-05, - "loss": 3.2197, + "learning_rate": 2.9409836933853275e-05, + "loss": 3.219, "step": 124400 }, { "epoch": 0.41, - "learning_rate": 2.9370886604497645e-05, - "loss": 3.2308, + "learning_rate": 2.9393285355825826e-05, + "loss": 3.2208, "step": 124500 }, { "epoch": 0.41, - "learning_rate": 2.9354317035505274e-05, - "loss": 3.2265, + "learning_rate": 2.9376733777798378e-05, + "loss": 3.211, "step": 124600 }, { "epoch": 0.41, - "learning_rate": 2.9337747466512903e-05, - "loss": 3.2085, + "learning_rate": 2.936018219977093e-05, + "loss": 3.2115, "step": 124700 }, { "epoch": 0.41, - "learning_rate": 2.932117789752053e-05, - "loss": 3.2301, + "learning_rate": 2.9343630621743478e-05, + "loss": 3.2179, "step": 124800 }, { "epoch": 0.41, - "learning_rate": 2.9304608328528162e-05, - "loss": 3.2408, + "learning_rate": 2.9327079043716026e-05, + "loss": 3.2032, "step": 124900 }, { "epoch": 0.41, - "learning_rate": 2.928803875953579e-05, - "loss": 3.2132, + "learning_rate": 2.931052746568858e-05, + "loss": 3.219, "step": 125000 }, { "epoch": 0.41, - "learning_rate": 2.9271469190543417e-05, - "loss": 3.2224, + "learning_rate": 2.929397588766113e-05, + "loss": 3.2159, "step": 125100 }, { "epoch": 0.41, - "learning_rate": 2.9254899621551046e-05, - "loss": 3.2286, + "learning_rate": 2.9277424309633684e-05, + "loss": 3.2126, "step": 125200 }, { - "epoch": 0.42, - "learning_rate": 2.9238330052558675e-05, - "loss": 3.2283, + "epoch": 0.41, + "learning_rate": 2.9260872731606232e-05, + "loss": 3.2035, "step": 125300 }, { "epoch": 0.42, - "learning_rate": 2.92217604835663e-05, - "loss": 3.2219, + "learning_rate": 2.9244321153578784e-05, + "loss": 3.2009, "step": 125400 }, { "epoch": 0.42, - "learning_rate": 2.9205190914573934e-05, - "loss": 3.2264, + "learning_rate": 2.9227769575551332e-05, + "loss": 3.2031, "step": 125500 }, { "epoch": 0.42, - "learning_rate": 2.9188621345581563e-05, - "loss": 3.2186, + "learning_rate": 2.9211217997523887e-05, + "loss": 3.1933, "step": 125600 }, { "epoch": 0.42, - "learning_rate": 2.917205177658919e-05, - "loss": 3.2227, + "learning_rate": 2.9194666419496435e-05, + "loss": 3.1983, "step": 125700 }, { "epoch": 0.42, - "learning_rate": 2.9155482207596818e-05, - "loss": 3.232, + "learning_rate": 2.917811484146899e-05, + "loss": 3.2197, "step": 125800 }, { "epoch": 0.42, - "learning_rate": 2.9138912638604447e-05, - "loss": 3.2313, + "learning_rate": 2.916156326344154e-05, + "loss": 3.1927, "step": 125900 }, { "epoch": 0.42, - "learning_rate": 2.9122343069612073e-05, - "loss": 3.2293, + "learning_rate": 2.9145011685414087e-05, + "loss": 3.2192, "step": 126000 }, { "epoch": 0.42, - "learning_rate": 2.9105773500619705e-05, - "loss": 3.2284, + "learning_rate": 2.9128460107386642e-05, + "loss": 3.2099, "step": 126100 }, { "epoch": 0.42, - "learning_rate": 2.9089203931627335e-05, - "loss": 3.2362, + "learning_rate": 2.911190852935919e-05, + "loss": 3.2108, "step": 126200 }, { "epoch": 0.42, - "learning_rate": 2.907263436263496e-05, - "loss": 3.2199, + "learning_rate": 2.909535695133174e-05, + "loss": 3.2101, "step": 126300 }, { "epoch": 0.42, - "learning_rate": 2.905606479364259e-05, - "loss": 3.2282, + "learning_rate": 2.907880537330429e-05, + "loss": 3.2059, "step": 126400 }, { "epoch": 0.42, - "learning_rate": 2.903949522465022e-05, - "loss": 3.2222, + "learning_rate": 2.9062253795276845e-05, + "loss": 3.2117, "step": 126500 }, { "epoch": 0.42, - "learning_rate": 2.9022925655657845e-05, - "loss": 3.2246, + "learning_rate": 2.9045702217249393e-05, + "loss": 3.2112, "step": 126600 }, { "epoch": 0.42, - "learning_rate": 2.9006356086665477e-05, - "loss": 3.2297, + "learning_rate": 2.9029150639221948e-05, + "loss": 3.2049, "step": 126700 }, { "epoch": 0.42, - "learning_rate": 2.89897865176731e-05, - "loss": 3.2119, + "learning_rate": 2.9012599061194496e-05, + "loss": 3.2065, "step": 126800 }, { "epoch": 0.42, - "learning_rate": 2.8973216948680732e-05, - "loss": 3.2196, + "learning_rate": 2.8996047483167048e-05, + "loss": 3.2086, "step": 126900 }, { "epoch": 0.42, - "learning_rate": 2.895664737968836e-05, - "loss": 3.2241, + "learning_rate": 2.8979495905139596e-05, + "loss": 3.2163, "step": 127000 }, { "epoch": 0.42, - "learning_rate": 2.8940077810695987e-05, - "loss": 3.2189, + "learning_rate": 2.8962944327112144e-05, + "loss": 3.2058, "step": 127100 }, { "epoch": 0.42, - "learning_rate": 2.8923508241703617e-05, - "loss": 3.2313, + "learning_rate": 2.89463927490847e-05, + "loss": 3.219, "step": 127200 }, { "epoch": 0.42, - "learning_rate": 2.890693867271125e-05, - "loss": 3.2264, + "learning_rate": 2.8929841171057247e-05, + "loss": 3.2101, "step": 127300 }, { "epoch": 0.42, - "learning_rate": 2.889036910371887e-05, - "loss": 3.2281, + "learning_rate": 2.8913289593029802e-05, + "loss": 3.1842, "step": 127400 }, { "epoch": 0.42, - "learning_rate": 2.8873799534726504e-05, - "loss": 3.2295, + "learning_rate": 2.889673801500235e-05, + "loss": 3.1933, "step": 127500 }, { "epoch": 0.42, - "learning_rate": 2.8857229965734133e-05, - "loss": 3.2186, + "learning_rate": 2.8880186436974906e-05, + "loss": 3.2216, "step": 127600 }, { "epoch": 0.42, - "learning_rate": 2.884066039674176e-05, - "loss": 3.2196, + "learning_rate": 2.8863634858947454e-05, + "loss": 3.1969, "step": 127700 }, { "epoch": 0.42, - "learning_rate": 2.882409082774939e-05, - "loss": 3.2222, + "learning_rate": 2.8847083280920005e-05, + "loss": 3.21, "step": 127800 }, { "epoch": 0.42, - "learning_rate": 2.880752125875702e-05, - "loss": 3.2249, + "learning_rate": 2.8830531702892554e-05, + "loss": 3.2159, "step": 127900 }, { "epoch": 0.42, - "learning_rate": 2.8790951689764643e-05, - "loss": 3.2254, + "learning_rate": 2.881398012486511e-05, + "loss": 3.2087, "step": 128000 }, { "epoch": 0.42, - "learning_rate": 2.8774382120772276e-05, - "loss": 3.2127, + "learning_rate": 2.8797428546837657e-05, + "loss": 3.2099, "step": 128100 }, { "epoch": 0.42, - "learning_rate": 2.8757812551779905e-05, - "loss": 3.2291, + "learning_rate": 2.8780876968810205e-05, + "loss": 3.207, "step": 128200 }, { - "epoch": 0.43, - "learning_rate": 2.874124298278753e-05, - "loss": 3.22, + "epoch": 0.42, + "learning_rate": 2.876432539078276e-05, + "loss": 3.2018, "step": 128300 }, { "epoch": 0.43, - "learning_rate": 2.872467341379516e-05, - "loss": 3.2345, + "learning_rate": 2.874777381275531e-05, + "loss": 3.2126, "step": 128400 }, { "epoch": 0.43, - "learning_rate": 2.8708103844802793e-05, - "loss": 3.2199, + "learning_rate": 2.873122223472786e-05, + "loss": 3.1857, "step": 128500 }, { "epoch": 0.43, - "learning_rate": 2.8691534275810415e-05, - "loss": 3.2286, + "learning_rate": 2.8714670656700408e-05, + "loss": 3.2049, "step": 128600 }, { "epoch": 0.43, - "learning_rate": 2.8674964706818048e-05, - "loss": 3.2335, + "learning_rate": 2.8698119078672963e-05, + "loss": 3.2024, "step": 128700 }, { "epoch": 0.43, - "learning_rate": 2.8658395137825677e-05, - "loss": 3.2214, + "learning_rate": 2.868156750064551e-05, + "loss": 3.1979, "step": 128800 }, { "epoch": 0.43, - "learning_rate": 2.8641825568833303e-05, - "loss": 3.221, + "learning_rate": 2.8665015922618066e-05, + "loss": 3.1877, "step": 128900 }, { "epoch": 0.43, - "learning_rate": 2.8625255999840932e-05, - "loss": 3.2138, + "learning_rate": 2.8648464344590615e-05, + "loss": 3.2119, "step": 129000 }, { "epoch": 0.43, - "learning_rate": 2.8608686430848565e-05, - "loss": 3.2296, + "learning_rate": 2.863191276656317e-05, + "loss": 3.2062, "step": 129100 }, { "epoch": 0.43, - "learning_rate": 2.8592116861856187e-05, - "loss": 3.2253, + "learning_rate": 2.8615361188535718e-05, + "loss": 3.2026, "step": 129200 }, { "epoch": 0.43, - "learning_rate": 2.857554729286382e-05, - "loss": 3.2294, + "learning_rate": 2.8598809610508266e-05, + "loss": 3.202, "step": 129300 }, { "epoch": 0.43, - "learning_rate": 2.855897772387145e-05, - "loss": 3.2132, + "learning_rate": 2.8582258032480818e-05, + "loss": 3.2093, "step": 129400 }, { "epoch": 0.43, - "learning_rate": 2.8542408154879075e-05, - "loss": 3.2269, + "learning_rate": 2.8565706454453366e-05, + "loss": 3.2128, "step": 129500 }, { "epoch": 0.43, - "learning_rate": 2.8525838585886704e-05, - "loss": 3.2239, + "learning_rate": 2.854915487642592e-05, + "loss": 3.2045, "step": 129600 }, { "epoch": 0.43, - "learning_rate": 2.8509269016894337e-05, - "loss": 3.2232, + "learning_rate": 2.853260329839847e-05, + "loss": 3.215, "step": 129700 }, { "epoch": 0.43, - "learning_rate": 2.849269944790196e-05, - "loss": 3.2173, + "learning_rate": 2.8516051720371024e-05, + "loss": 3.1955, "step": 129800 }, { "epoch": 0.43, - "learning_rate": 2.847612987890959e-05, - "loss": 3.2268, + "learning_rate": 2.8499500142343572e-05, + "loss": 3.1963, "step": 129900 }, { "epoch": 0.43, - "learning_rate": 2.845956030991722e-05, - "loss": 3.2327, + "learning_rate": 2.8482948564316124e-05, + "loss": 3.2093, "step": 130000 }, { "epoch": 0.43, - "learning_rate": 2.8442990740924847e-05, - "loss": 3.2153, + "learning_rate": 2.8466396986288675e-05, + "loss": 3.2118, "step": 130100 }, { "epoch": 0.43, - "learning_rate": 2.8426421171932476e-05, - "loss": 3.2188, + "learning_rate": 2.8449845408261227e-05, + "loss": 3.194, "step": 130200 }, { "epoch": 0.43, - "learning_rate": 2.840985160294011e-05, - "loss": 3.2433, + "learning_rate": 2.8433293830233775e-05, + "loss": 3.2017, "step": 130300 }, { "epoch": 0.43, - "learning_rate": 2.839328203394773e-05, - "loss": 3.2227, + "learning_rate": 2.8416742252206323e-05, + "loss": 3.211, "step": 130400 }, { "epoch": 0.43, - "learning_rate": 2.8376712464955363e-05, - "loss": 3.2353, + "learning_rate": 2.840019067417888e-05, + "loss": 3.2106, "step": 130500 }, { "epoch": 0.43, - "learning_rate": 2.8360142895962993e-05, - "loss": 3.2305, + "learning_rate": 2.8383639096151427e-05, + "loss": 3.2176, "step": 130600 }, { "epoch": 0.43, - "learning_rate": 2.834357332697062e-05, - "loss": 3.2248, + "learning_rate": 2.836708751812398e-05, + "loss": 3.2183, "step": 130700 }, { "epoch": 0.43, - "learning_rate": 2.8327003757978248e-05, - "loss": 3.235, + "learning_rate": 2.835053594009653e-05, + "loss": 3.2077, "step": 130800 }, { "epoch": 0.43, - "learning_rate": 2.831043418898588e-05, - "loss": 3.2387, + "learning_rate": 2.833398436206908e-05, + "loss": 3.2177, "step": 130900 }, { "epoch": 0.43, - "learning_rate": 2.8293864619993503e-05, - "loss": 3.2295, + "learning_rate": 2.831743278404163e-05, + "loss": 3.2055, "step": 131000 }, { "epoch": 0.43, - "learning_rate": 2.8277295051001135e-05, - "loss": 3.2201, + "learning_rate": 2.8300881206014185e-05, + "loss": 3.2004, "step": 131100 }, { "epoch": 0.43, - "learning_rate": 2.8260725482008764e-05, - "loss": 3.2156, + "learning_rate": 2.8284329627986733e-05, + "loss": 3.2067, "step": 131200 }, { - "epoch": 0.44, - "learning_rate": 2.824415591301639e-05, - "loss": 3.2252, + "epoch": 0.43, + "learning_rate": 2.8267778049959288e-05, + "loss": 3.2099, "step": 131300 }, { - "epoch": 0.44, - "learning_rate": 2.822758634402402e-05, - "loss": 3.2277, + "epoch": 0.43, + "learning_rate": 2.8251226471931836e-05, + "loss": 3.2169, "step": 131400 }, { "epoch": 0.44, - "learning_rate": 2.8211016775031652e-05, - "loss": 3.2286, + "learning_rate": 2.8234674893904384e-05, + "loss": 3.2089, "step": 131500 }, { "epoch": 0.44, - "learning_rate": 2.8194447206039275e-05, - "loss": 3.2298, + "learning_rate": 2.821812331587694e-05, + "loss": 3.2037, "step": 131600 }, { "epoch": 0.44, - "learning_rate": 2.8177877637046907e-05, - "loss": 3.2223, + "learning_rate": 2.8201571737849487e-05, + "loss": 3.205, "step": 131700 }, { "epoch": 0.44, - "learning_rate": 2.8161308068054536e-05, - "loss": 3.2411, + "learning_rate": 2.818502015982204e-05, + "loss": 3.2096, "step": 131800 }, { "epoch": 0.44, - "learning_rate": 2.8144738499062162e-05, - "loss": 3.2296, + "learning_rate": 2.8168468581794587e-05, + "loss": 3.1876, "step": 131900 }, { "epoch": 0.44, - "learning_rate": 2.812816893006979e-05, - "loss": 3.2354, + "learning_rate": 2.8151917003767142e-05, + "loss": 3.1992, "step": 132000 }, { "epoch": 0.44, - "learning_rate": 2.8111599361077424e-05, - "loss": 3.2113, + "learning_rate": 2.813536542573969e-05, + "loss": 3.2101, "step": 132100 }, { "epoch": 0.44, - "learning_rate": 2.8095029792085046e-05, - "loss": 3.2163, + "learning_rate": 2.8118813847712245e-05, + "loss": 3.2086, "step": 132200 }, { "epoch": 0.44, - "learning_rate": 2.807846022309268e-05, - "loss": 3.2109, + "learning_rate": 2.8102262269684794e-05, + "loss": 3.1936, "step": 132300 }, { "epoch": 0.44, - "learning_rate": 2.8061890654100308e-05, - "loss": 3.2313, + "learning_rate": 2.8085710691657345e-05, + "loss": 3.196, "step": 132400 }, { "epoch": 0.44, - "learning_rate": 2.8045321085107934e-05, - "loss": 3.2192, + "learning_rate": 2.8069159113629893e-05, + "loss": 3.2171, "step": 132500 }, { "epoch": 0.44, - "learning_rate": 2.8028751516115563e-05, - "loss": 3.2196, + "learning_rate": 2.805260753560244e-05, + "loss": 3.2095, "step": 132600 }, { "epoch": 0.44, - "learning_rate": 2.8012181947123196e-05, - "loss": 3.2198, + "learning_rate": 2.8036055957574997e-05, + "loss": 3.2239, "step": 132700 }, { "epoch": 0.44, - "learning_rate": 2.799561237813082e-05, - "loss": 3.2182, + "learning_rate": 2.8019504379547545e-05, + "loss": 3.212, "step": 132800 }, { "epoch": 0.44, - "learning_rate": 2.797904280913845e-05, - "loss": 3.2294, + "learning_rate": 2.80029528015201e-05, + "loss": 3.212, "step": 132900 }, { "epoch": 0.44, - "learning_rate": 2.796247324014608e-05, - "loss": 3.2133, + "learning_rate": 2.7986401223492648e-05, + "loss": 3.2108, "step": 133000 }, { "epoch": 0.44, - "learning_rate": 2.7945903671153706e-05, - "loss": 3.2242, + "learning_rate": 2.7969849645465203e-05, + "loss": 3.2177, "step": 133100 }, { "epoch": 0.44, - "learning_rate": 2.7929334102161335e-05, - "loss": 3.2268, + "learning_rate": 2.795329806743775e-05, + "loss": 3.1988, "step": 133200 }, { "epoch": 0.44, - "learning_rate": 2.7912764533168968e-05, - "loss": 3.2337, + "learning_rate": 2.7936746489410303e-05, + "loss": 3.2144, "step": 133300 }, { "epoch": 0.44, - "learning_rate": 2.7896194964176593e-05, - "loss": 3.215, + "learning_rate": 2.792019491138285e-05, + "loss": 3.2092, "step": 133400 }, { "epoch": 0.44, - "learning_rate": 2.7879625395184223e-05, - "loss": 3.2271, + "learning_rate": 2.7903643333355406e-05, + "loss": 3.1915, "step": 133500 }, { "epoch": 0.44, - "learning_rate": 2.7863055826191852e-05, - "loss": 3.2246, + "learning_rate": 2.7887091755327954e-05, + "loss": 3.2053, "step": 133600 }, { "epoch": 0.44, - "learning_rate": 2.7846486257199478e-05, - "loss": 3.2251, + "learning_rate": 2.7870540177300502e-05, + "loss": 3.2167, "step": 133700 }, { "epoch": 0.44, - "learning_rate": 2.7829916688207107e-05, - "loss": 3.2179, + "learning_rate": 2.7853988599273057e-05, + "loss": 3.2171, "step": 133800 }, { "epoch": 0.44, - "learning_rate": 2.781334711921474e-05, - "loss": 3.2296, + "learning_rate": 2.7837437021245606e-05, + "loss": 3.2031, "step": 133900 }, { "epoch": 0.44, - "learning_rate": 2.7796777550222365e-05, - "loss": 3.2174, + "learning_rate": 2.7820885443218157e-05, + "loss": 3.2153, "step": 134000 }, { "epoch": 0.44, - "learning_rate": 2.7780207981229994e-05, - "loss": 3.2197, + "learning_rate": 2.7804333865190705e-05, + "loss": 3.2145, "step": 134100 }, { "epoch": 0.44, - "learning_rate": 2.7763638412237624e-05, - "loss": 3.2132, + "learning_rate": 2.778778228716326e-05, + "loss": 3.214, "step": 134200 }, { - "epoch": 0.45, - "learning_rate": 2.774706884324525e-05, - "loss": 3.2248, + "epoch": 0.44, + "learning_rate": 2.777123070913581e-05, + "loss": 3.2285, "step": 134300 }, { - "epoch": 0.45, - "learning_rate": 2.773049927425288e-05, - "loss": 3.2264, + "epoch": 0.44, + "learning_rate": 2.7754679131108364e-05, + "loss": 3.2159, "step": 134400 }, { "epoch": 0.45, - "learning_rate": 2.771392970526051e-05, - "loss": 3.2295, + "learning_rate": 2.7738127553080912e-05, + "loss": 3.203, "step": 134500 }, { "epoch": 0.45, - "learning_rate": 2.7697360136268137e-05, - "loss": 3.2363, + "learning_rate": 2.7721575975053467e-05, + "loss": 3.1936, "step": 134600 }, { "epoch": 0.45, - "learning_rate": 2.7680790567275766e-05, - "loss": 3.2137, + "learning_rate": 2.7705024397026015e-05, + "loss": 3.2042, "step": 134700 }, { "epoch": 0.45, - "learning_rate": 2.7664220998283396e-05, - "loss": 3.2227, + "learning_rate": 2.7688472818998563e-05, + "loss": 3.2148, "step": 134800 }, { "epoch": 0.45, - "learning_rate": 2.764765142929102e-05, - "loss": 3.2089, + "learning_rate": 2.7671921240971115e-05, + "loss": 3.2011, "step": 134900 }, { "epoch": 0.45, - "learning_rate": 2.763108186029865e-05, - "loss": 3.2158, + "learning_rate": 2.7655369662943663e-05, + "loss": 3.1952, "step": 135000 }, { "epoch": 0.45, - "learning_rate": 2.7614512291306283e-05, - "loss": 3.2242, + "learning_rate": 2.7638818084916218e-05, + "loss": 3.1974, "step": 135100 }, { "epoch": 0.45, - "learning_rate": 2.759794272231391e-05, - "loss": 3.2298, + "learning_rate": 2.7622266506888766e-05, + "loss": 3.2046, "step": 135200 }, { "epoch": 0.45, - "learning_rate": 2.7581373153321538e-05, - "loss": 3.2311, + "learning_rate": 2.760571492886132e-05, + "loss": 3.221, "step": 135300 }, { "epoch": 0.45, - "learning_rate": 2.7564803584329164e-05, - "loss": 3.2269, + "learning_rate": 2.758916335083387e-05, + "loss": 3.2248, "step": 135400 }, { "epoch": 0.45, - "learning_rate": 2.7548234015336793e-05, - "loss": 3.2398, + "learning_rate": 2.757261177280642e-05, + "loss": 3.2217, "step": 135500 }, { "epoch": 0.45, - "learning_rate": 2.7531664446344422e-05, - "loss": 3.2279, + "learning_rate": 2.755606019477897e-05, + "loss": 3.1972, "step": 135600 }, { "epoch": 0.45, - "learning_rate": 2.7515094877352048e-05, - "loss": 3.2175, + "learning_rate": 2.7539508616751524e-05, + "loss": 3.1882, "step": 135700 }, { "epoch": 0.45, - "learning_rate": 2.749852530835968e-05, - "loss": 3.2316, + "learning_rate": 2.7522957038724073e-05, + "loss": 3.2127, "step": 135800 }, { "epoch": 0.45, - "learning_rate": 2.748195573936731e-05, - "loss": 3.2238, + "learning_rate": 2.750640546069662e-05, + "loss": 3.2023, "step": 135900 }, { "epoch": 0.45, - "learning_rate": 2.7465386170374936e-05, - "loss": 3.1977, + "learning_rate": 2.7489853882669176e-05, + "loss": 3.2077, "step": 136000 }, { "epoch": 0.45, - "learning_rate": 2.7448816601382565e-05, - "loss": 3.2147, + "learning_rate": 2.7473302304641724e-05, + "loss": 3.2066, "step": 136100 }, { "epoch": 0.45, - "learning_rate": 2.7432247032390194e-05, - "loss": 3.2307, + "learning_rate": 2.745675072661428e-05, + "loss": 3.2084, "step": 136200 }, { "epoch": 0.45, - "learning_rate": 2.741567746339782e-05, - "loss": 3.2341, + "learning_rate": 2.7440199148586827e-05, + "loss": 3.207, "step": 136300 }, { "epoch": 0.45, - "learning_rate": 2.7399107894405453e-05, - "loss": 3.2241, + "learning_rate": 2.742364757055938e-05, + "loss": 3.2051, "step": 136400 }, { "epoch": 0.45, - "learning_rate": 2.7382538325413082e-05, - "loss": 3.2129, + "learning_rate": 2.7407095992531927e-05, + "loss": 3.2136, "step": 136500 }, { "epoch": 0.45, - "learning_rate": 2.7365968756420708e-05, - "loss": 3.224, + "learning_rate": 2.7390544414504482e-05, + "loss": 3.2049, "step": 136600 }, { "epoch": 0.45, - "learning_rate": 2.7349399187428337e-05, - "loss": 3.2184, + "learning_rate": 2.737399283647703e-05, + "loss": 3.2035, "step": 136700 }, { "epoch": 0.45, - "learning_rate": 2.733282961843597e-05, - "loss": 3.2284, + "learning_rate": 2.7357441258449585e-05, + "loss": 3.2075, "step": 136800 }, { "epoch": 0.45, - "learning_rate": 2.7316260049443592e-05, - "loss": 3.2366, + "learning_rate": 2.7340889680422133e-05, + "loss": 3.2075, "step": 136900 }, { "epoch": 0.45, - "learning_rate": 2.7299690480451225e-05, - "loss": 3.2337, + "learning_rate": 2.732433810239468e-05, + "loss": 3.217, "step": 137000 }, { "epoch": 0.45, - "learning_rate": 2.7283120911458854e-05, - "loss": 3.2357, + "learning_rate": 2.7307786524367233e-05, + "loss": 3.2164, "step": 137100 }, { "epoch": 0.45, - "learning_rate": 2.726655134246648e-05, - "loss": 3.2118, + "learning_rate": 2.7291234946339785e-05, + "loss": 3.2113, "step": 137200 }, { - "epoch": 0.46, - "learning_rate": 2.724998177347411e-05, - "loss": 3.2289, + "epoch": 0.45, + "learning_rate": 2.7274683368312336e-05, + "loss": 3.2173, "step": 137300 }, { - "epoch": 0.46, - "learning_rate": 2.723341220448174e-05, - "loss": 3.2298, + "epoch": 0.45, + "learning_rate": 2.7258131790284885e-05, + "loss": 3.2006, "step": 137400 }, { "epoch": 0.46, - "learning_rate": 2.7216842635489364e-05, - "loss": 3.2182, + "learning_rate": 2.724158021225744e-05, + "loss": 3.2109, "step": 137500 }, { "epoch": 0.46, - "learning_rate": 2.7200273066496996e-05, - "loss": 3.2296, + "learning_rate": 2.7225028634229988e-05, + "loss": 3.2163, "step": 137600 }, { "epoch": 0.46, - "learning_rate": 2.7183703497504626e-05, - "loss": 3.2118, + "learning_rate": 2.7208477056202543e-05, + "loss": 3.2097, "step": 137700 }, { "epoch": 0.46, - "learning_rate": 2.716713392851225e-05, - "loss": 3.2149, + "learning_rate": 2.719192547817509e-05, + "loss": 3.2051, "step": 137800 }, { "epoch": 0.46, - "learning_rate": 2.715056435951988e-05, - "loss": 3.2249, + "learning_rate": 2.7175373900147643e-05, + "loss": 3.2144, "step": 137900 }, { "epoch": 0.46, - "learning_rate": 2.7133994790527513e-05, - "loss": 3.2382, + "learning_rate": 2.715882232212019e-05, + "loss": 3.2078, "step": 138000 }, { "epoch": 0.46, - "learning_rate": 2.7117425221535136e-05, - "loss": 3.217, + "learning_rate": 2.714227074409274e-05, + "loss": 3.2011, "step": 138100 }, { "epoch": 0.46, - "learning_rate": 2.7100855652542768e-05, - "loss": 3.2368, + "learning_rate": 2.7125719166065294e-05, + "loss": 3.2112, "step": 138200 }, { "epoch": 0.46, - "learning_rate": 2.7084286083550397e-05, - "loss": 3.2178, + "learning_rate": 2.7109167588037842e-05, + "loss": 3.2091, "step": 138300 }, { "epoch": 0.46, - "learning_rate": 2.7067716514558023e-05, - "loss": 3.2173, + "learning_rate": 2.7092616010010397e-05, + "loss": 3.2036, "step": 138400 }, { "epoch": 0.46, - "learning_rate": 2.7051146945565652e-05, - "loss": 3.2224, + "learning_rate": 2.7076064431982945e-05, + "loss": 3.2165, "step": 138500 }, { "epoch": 0.46, - "learning_rate": 2.7034577376573285e-05, - "loss": 3.2209, + "learning_rate": 2.70595128539555e-05, + "loss": 3.2103, "step": 138600 }, { "epoch": 0.46, - "learning_rate": 2.7018007807580907e-05, - "loss": 3.2192, + "learning_rate": 2.704296127592805e-05, + "loss": 3.2041, "step": 138700 }, { "epoch": 0.46, - "learning_rate": 2.700143823858854e-05, - "loss": 3.2266, + "learning_rate": 2.70264096979006e-05, + "loss": 3.2078, "step": 138800 }, { "epoch": 0.46, - "learning_rate": 2.698486866959617e-05, - "loss": 3.2137, + "learning_rate": 2.700985811987315e-05, + "loss": 3.2091, "step": 138900 }, { "epoch": 0.46, - "learning_rate": 2.6968299100603795e-05, - "loss": 3.2217, + "learning_rate": 2.6993306541845703e-05, + "loss": 3.2039, "step": 139000 }, { "epoch": 0.46, - "learning_rate": 2.6951729531611424e-05, - "loss": 3.2383, + "learning_rate": 2.697675496381825e-05, + "loss": 3.2062, "step": 139100 }, { "epoch": 0.46, - "learning_rate": 2.6935159962619057e-05, - "loss": 3.2284, + "learning_rate": 2.69602033857908e-05, + "loss": 3.2143, "step": 139200 }, { "epoch": 0.46, - "learning_rate": 2.691859039362668e-05, - "loss": 3.2103, + "learning_rate": 2.6943651807763355e-05, + "loss": 3.1957, "step": 139300 }, { "epoch": 0.46, - "learning_rate": 2.6902020824634312e-05, - "loss": 3.2048, + "learning_rate": 2.6927100229735903e-05, + "loss": 3.1922, "step": 139400 }, { "epoch": 0.46, - "learning_rate": 2.688545125564194e-05, - "loss": 3.2156, + "learning_rate": 2.6910548651708455e-05, + "loss": 3.1996, "step": 139500 }, { "epoch": 0.46, - "learning_rate": 2.6868881686649567e-05, - "loss": 3.2312, + "learning_rate": 2.6893997073681003e-05, + "loss": 3.2065, "step": 139600 }, { "epoch": 0.46, - "learning_rate": 2.6852312117657196e-05, - "loss": 3.2305, + "learning_rate": 2.6877445495653558e-05, + "loss": 3.2263, "step": 139700 }, { "epoch": 0.46, - "learning_rate": 2.683574254866483e-05, - "loss": 3.2263, + "learning_rate": 2.6860893917626106e-05, + "loss": 3.1938, "step": 139800 }, { "epoch": 0.46, - "learning_rate": 2.681917297967245e-05, - "loss": 3.22, + "learning_rate": 2.684434233959866e-05, + "loss": 3.2105, "step": 139900 }, { "epoch": 0.46, - "learning_rate": 2.6802603410680084e-05, - "loss": 3.2181, + "learning_rate": 2.682779076157121e-05, + "loss": 3.2109, "step": 140000 }, { "epoch": 0.46, - "learning_rate": 2.6786033841687713e-05, - "loss": 3.2224, + "learning_rate": 2.6811239183543764e-05, + "loss": 3.2005, "step": 140100 }, { "epoch": 0.46, - "learning_rate": 2.676946427269534e-05, - "loss": 3.2351, + "learning_rate": 2.6794687605516312e-05, + "loss": 3.1935, "step": 140200 }, { "epoch": 0.46, - "learning_rate": 2.6752894703702968e-05, - "loss": 3.2244, + "learning_rate": 2.677813602748886e-05, + "loss": 3.2168, "step": 140300 }, { - "epoch": 0.47, - "learning_rate": 2.67363251347106e-05, - "loss": 3.225, + "epoch": 0.46, + "learning_rate": 2.6761584449461412e-05, + "loss": 3.2128, "step": 140400 }, { "epoch": 0.47, - "learning_rate": 2.6719755565718223e-05, - "loss": 3.2308, + "learning_rate": 2.674503287143396e-05, + "loss": 3.2011, "step": 140500 }, { "epoch": 0.47, - "learning_rate": 2.6703185996725856e-05, - "loss": 3.2282, + "learning_rate": 2.6728481293406515e-05, + "loss": 3.2114, "step": 140600 }, { "epoch": 0.47, - "learning_rate": 2.6686616427733485e-05, - "loss": 3.2132, + "learning_rate": 2.6711929715379064e-05, + "loss": 3.1862, "step": 140700 }, { "epoch": 0.47, - "learning_rate": 2.667004685874111e-05, - "loss": 3.2157, + "learning_rate": 2.669537813735162e-05, + "loss": 3.1954, "step": 140800 }, { "epoch": 0.47, - "learning_rate": 2.665347728974874e-05, - "loss": 3.2119, + "learning_rate": 2.6678826559324167e-05, + "loss": 3.1993, "step": 140900 }, { "epoch": 0.47, - "learning_rate": 2.6636907720756372e-05, - "loss": 3.2202, + "learning_rate": 2.666227498129672e-05, + "loss": 3.2081, "step": 141000 }, { "epoch": 0.47, - "learning_rate": 2.6620338151763995e-05, - "loss": 3.2244, + "learning_rate": 2.6645723403269267e-05, + "loss": 3.1976, "step": 141100 }, { "epoch": 0.47, - "learning_rate": 2.6603768582771627e-05, - "loss": 3.2192, + "learning_rate": 2.662917182524182e-05, + "loss": 3.207, "step": 141200 }, { "epoch": 0.47, - "learning_rate": 2.6587199013779257e-05, - "loss": 3.2168, + "learning_rate": 2.661262024721437e-05, + "loss": 3.1961, "step": 141300 }, { "epoch": 0.47, - "learning_rate": 2.6570629444786882e-05, - "loss": 3.2163, + "learning_rate": 2.6596068669186925e-05, + "loss": 3.1978, "step": 141400 }, { "epoch": 0.47, - "learning_rate": 2.655405987579451e-05, - "loss": 3.2176, + "learning_rate": 2.6579517091159473e-05, + "loss": 3.2085, "step": 141500 }, { "epoch": 0.47, - "learning_rate": 2.6537490306802144e-05, - "loss": 3.2219, + "learning_rate": 2.656296551313202e-05, + "loss": 3.2127, "step": 141600 }, { "epoch": 0.47, - "learning_rate": 2.6520920737809767e-05, - "loss": 3.2229, + "learning_rate": 2.6546413935104576e-05, + "loss": 3.2028, "step": 141700 }, { "epoch": 0.47, - "learning_rate": 2.65043511688174e-05, - "loss": 3.2251, + "learning_rate": 2.6529862357077124e-05, + "loss": 3.2135, "step": 141800 }, { "epoch": 0.47, - "learning_rate": 2.648778159982503e-05, - "loss": 3.2147, + "learning_rate": 2.6513310779049676e-05, + "loss": 3.1982, "step": 141900 }, { "epoch": 0.47, - "learning_rate": 2.6471212030832654e-05, - "loss": 3.2329, + "learning_rate": 2.6496759201022224e-05, + "loss": 3.2079, "step": 142000 }, { "epoch": 0.47, - "learning_rate": 2.6454642461840283e-05, - "loss": 3.2006, + "learning_rate": 2.648020762299478e-05, + "loss": 3.2031, "step": 142100 }, { "epoch": 0.47, - "learning_rate": 2.6438072892847916e-05, - "loss": 3.2302, + "learning_rate": 2.6463656044967328e-05, + "loss": 3.1982, "step": 142200 }, { "epoch": 0.47, - "learning_rate": 2.642150332385554e-05, - "loss": 3.2187, + "learning_rate": 2.6447104466939882e-05, + "loss": 3.2098, "step": 142300 }, { "epoch": 0.47, - "learning_rate": 2.640493375486317e-05, - "loss": 3.2308, + "learning_rate": 2.643055288891243e-05, + "loss": 3.2032, "step": 142400 }, { "epoch": 0.47, - "learning_rate": 2.63883641858708e-05, - "loss": 3.2184, + "learning_rate": 2.6414001310884982e-05, + "loss": 3.2071, "step": 142500 }, { "epoch": 0.47, - "learning_rate": 2.6371794616878426e-05, - "loss": 3.2199, + "learning_rate": 2.639744973285753e-05, + "loss": 3.1982, "step": 142600 }, { "epoch": 0.47, - "learning_rate": 2.6355225047886055e-05, - "loss": 3.2249, + "learning_rate": 2.6380898154830082e-05, + "loss": 3.2055, "step": 142700 }, { "epoch": 0.47, - "learning_rate": 2.6338655478893688e-05, - "loss": 3.221, + "learning_rate": 2.6364346576802634e-05, + "loss": 3.2096, "step": 142800 }, { "epoch": 0.47, - "learning_rate": 2.632208590990131e-05, - "loss": 3.2254, + "learning_rate": 2.6347794998775182e-05, + "loss": 3.2036, "step": 142900 }, { "epoch": 0.47, - "learning_rate": 2.6305516340908943e-05, - "loss": 3.2197, + "learning_rate": 2.6331243420747737e-05, + "loss": 3.218, "step": 143000 }, { "epoch": 0.47, - "learning_rate": 2.6288946771916572e-05, - "loss": 3.2145, + "learning_rate": 2.6314691842720285e-05, + "loss": 3.2024, "step": 143100 }, { "epoch": 0.47, - "learning_rate": 2.6272377202924198e-05, - "loss": 3.2317, + "learning_rate": 2.629814026469284e-05, + "loss": 3.1902, "step": 143200 }, { "epoch": 0.47, - "learning_rate": 2.6255807633931827e-05, - "loss": 3.2097, + "learning_rate": 2.628158868666539e-05, + "loss": 3.2006, "step": 143300 }, { - "epoch": 0.48, - "learning_rate": 2.623923806493946e-05, - "loss": 3.2249, + "epoch": 0.47, + "learning_rate": 2.626503710863794e-05, + "loss": 3.2039, "step": 143400 }, { "epoch": 0.48, - "learning_rate": 2.6222668495947082e-05, - "loss": 3.2229, + "learning_rate": 2.6248485530610488e-05, + "loss": 3.2156, "step": 143500 }, { "epoch": 0.48, - "learning_rate": 2.6206098926954715e-05, - "loss": 3.2314, + "learning_rate": 2.6231933952583043e-05, + "loss": 3.2026, "step": 143600 }, { "epoch": 0.48, - "learning_rate": 2.6189529357962344e-05, - "loss": 3.2178, + "learning_rate": 2.621538237455559e-05, + "loss": 3.205, "step": 143700 }, { "epoch": 0.48, - "learning_rate": 2.617295978896997e-05, - "loss": 3.219, + "learning_rate": 2.619883079652814e-05, + "loss": 3.2073, "step": 143800 }, { "epoch": 0.48, - "learning_rate": 2.61563902199776e-05, - "loss": 3.2161, + "learning_rate": 2.6182279218500695e-05, + "loss": 3.2039, "step": 143900 }, { "epoch": 0.48, - "learning_rate": 2.613982065098523e-05, - "loss": 3.2139, + "learning_rate": 2.6165727640473243e-05, + "loss": 3.1997, "step": 144000 }, { "epoch": 0.48, - "learning_rate": 2.6123251081992854e-05, - "loss": 3.2303, + "learning_rate": 2.6149176062445794e-05, + "loss": 3.2027, "step": 144100 }, { "epoch": 0.48, - "learning_rate": 2.6106681513000487e-05, - "loss": 3.2213, + "learning_rate": 2.6132624484418346e-05, + "loss": 3.2095, "step": 144200 }, { "epoch": 0.48, - "learning_rate": 2.6090111944008112e-05, - "loss": 3.2237, + "learning_rate": 2.6116072906390898e-05, + "loss": 3.2036, "step": 144300 }, { "epoch": 0.48, - "learning_rate": 2.607354237501574e-05, - "loss": 3.2234, + "learning_rate": 2.6099521328363446e-05, + "loss": 3.2025, "step": 144400 }, { "epoch": 0.48, - "learning_rate": 2.605697280602337e-05, - "loss": 3.2243, + "learning_rate": 2.6082969750336e-05, + "loss": 3.2072, "step": 144500 }, { "epoch": 0.48, - "learning_rate": 2.6040403237030997e-05, - "loss": 3.2164, + "learning_rate": 2.606641817230855e-05, + "loss": 3.1967, "step": 144600 }, { "epoch": 0.48, - "learning_rate": 2.6023833668038626e-05, - "loss": 3.2225, + "learning_rate": 2.6049866594281104e-05, + "loss": 3.2063, "step": 144700 }, { "epoch": 0.48, - "learning_rate": 2.600726409904626e-05, - "loss": 3.2298, + "learning_rate": 2.6033315016253652e-05, + "loss": 3.2073, "step": 144800 }, { "epoch": 0.48, - "learning_rate": 2.5990694530053884e-05, - "loss": 3.2206, + "learning_rate": 2.60167634382262e-05, + "loss": 3.1927, "step": 144900 }, { "epoch": 0.48, - "learning_rate": 2.5974124961061514e-05, - "loss": 3.2198, + "learning_rate": 2.6000211860198752e-05, + "loss": 3.2024, "step": 145000 }, { "epoch": 0.48, - "learning_rate": 2.5957555392069143e-05, - "loss": 3.2283, + "learning_rate": 2.59836602821713e-05, + "loss": 3.197, "step": 145100 }, { "epoch": 0.48, - "learning_rate": 2.594098582307677e-05, - "loss": 3.2158, + "learning_rate": 2.5967108704143855e-05, + "loss": 3.2058, "step": 145200 }, { "epoch": 0.48, - "learning_rate": 2.5924416254084398e-05, - "loss": 3.2232, + "learning_rate": 2.5950557126116403e-05, + "loss": 3.2186, "step": 145300 }, { "epoch": 0.48, - "learning_rate": 2.590784668509203e-05, - "loss": 3.2186, + "learning_rate": 2.593400554808896e-05, + "loss": 3.2011, "step": 145400 }, { "epoch": 0.48, - "learning_rate": 2.5891277116099656e-05, - "loss": 3.2297, + "learning_rate": 2.5917453970061507e-05, + "loss": 3.2134, "step": 145500 }, { "epoch": 0.48, - "learning_rate": 2.5874707547107285e-05, - "loss": 3.23, + "learning_rate": 2.5900902392034058e-05, + "loss": 3.196, "step": 145600 }, { "epoch": 0.48, - "learning_rate": 2.5858137978114915e-05, - "loss": 3.2242, + "learning_rate": 2.588435081400661e-05, + "loss": 3.2026, "step": 145700 }, { "epoch": 0.48, - "learning_rate": 2.584156840912254e-05, - "loss": 3.2239, + "learning_rate": 2.586779923597916e-05, + "loss": 3.209, "step": 145800 }, { "epoch": 0.48, - "learning_rate": 2.582499884013017e-05, - "loss": 3.2156, + "learning_rate": 2.585124765795171e-05, + "loss": 3.1936, "step": 145900 }, { "epoch": 0.48, - "learning_rate": 2.5808429271137802e-05, - "loss": 3.2097, + "learning_rate": 2.5834696079924258e-05, + "loss": 3.2055, "step": 146000 }, { "epoch": 0.48, - "learning_rate": 2.5791859702145428e-05, - "loss": 3.2027, + "learning_rate": 2.5818144501896813e-05, + "loss": 3.1944, "step": 146100 }, { "epoch": 0.48, - "learning_rate": 2.5775290133153057e-05, - "loss": 3.2147, + "learning_rate": 2.580159292386936e-05, + "loss": 3.2079, "step": 146200 }, { "epoch": 0.48, - "learning_rate": 2.5758720564160686e-05, - "loss": 3.2159, + "learning_rate": 2.5785041345841916e-05, + "loss": 3.209, "step": 146300 }, { - "epoch": 0.49, - "learning_rate": 2.5742150995168312e-05, - "loss": 3.213, + "epoch": 0.48, + "learning_rate": 2.5768489767814464e-05, + "loss": 3.2054, "step": 146400 }, { - "epoch": 0.49, - "learning_rate": 2.5725581426175945e-05, - "loss": 3.2189, + "epoch": 0.48, + "learning_rate": 2.5751938189787016e-05, + "loss": 3.2042, "step": 146500 }, { "epoch": 0.49, - "learning_rate": 2.5709011857183574e-05, - "loss": 3.2198, + "learning_rate": 2.5735386611759564e-05, + "loss": 3.1991, "step": 146600 }, { "epoch": 0.49, - "learning_rate": 2.56924422881912e-05, - "loss": 3.2303, + "learning_rate": 2.571883503373212e-05, + "loss": 3.2101, "step": 146700 }, { "epoch": 0.49, - "learning_rate": 2.567587271919883e-05, - "loss": 3.2105, + "learning_rate": 2.5702283455704667e-05, + "loss": 3.1984, "step": 146800 }, { "epoch": 0.49, - "learning_rate": 2.5659303150206458e-05, - "loss": 3.2282, + "learning_rate": 2.5685731877677222e-05, + "loss": 3.2056, "step": 146900 }, { "epoch": 0.49, - "learning_rate": 2.5642733581214084e-05, - "loss": 3.2173, + "learning_rate": 2.566918029964977e-05, + "loss": 3.2, "step": 147000 }, { "epoch": 0.49, - "learning_rate": 2.5626164012221717e-05, - "loss": 3.2143, + "learning_rate": 2.565262872162232e-05, + "loss": 3.206, "step": 147100 }, { "epoch": 0.49, - "learning_rate": 2.5609594443229346e-05, - "loss": 3.2082, + "learning_rate": 2.5636077143594874e-05, + "loss": 3.1903, "step": 147200 }, { "epoch": 0.49, - "learning_rate": 2.559302487423697e-05, - "loss": 3.2274, + "learning_rate": 2.5619525565567422e-05, + "loss": 3.2069, "step": 147300 }, { "epoch": 0.49, - "learning_rate": 2.55764553052446e-05, - "loss": 3.2419, + "learning_rate": 2.5602973987539973e-05, + "loss": 3.2011, "step": 147400 }, { "epoch": 0.49, - "learning_rate": 2.555988573625223e-05, - "loss": 3.2227, + "learning_rate": 2.558642240951252e-05, + "loss": 3.2038, "step": 147500 }, { "epoch": 0.49, - "learning_rate": 2.5543316167259856e-05, - "loss": 3.2344, + "learning_rate": 2.5569870831485077e-05, + "loss": 3.2099, "step": 147600 }, { "epoch": 0.49, - "learning_rate": 2.552674659826749e-05, - "loss": 3.2287, + "learning_rate": 2.5553319253457625e-05, + "loss": 3.2028, "step": 147700 }, { "epoch": 0.49, - "learning_rate": 2.5510177029275118e-05, - "loss": 3.2179, + "learning_rate": 2.553676767543018e-05, + "loss": 3.2134, "step": 147800 }, { "epoch": 0.49, - "learning_rate": 2.5493607460282744e-05, - "loss": 3.2217, + "learning_rate": 2.5520216097402728e-05, + "loss": 3.196, "step": 147900 }, { "epoch": 0.49, - "learning_rate": 2.5477037891290373e-05, - "loss": 3.2359, + "learning_rate": 2.550366451937528e-05, + "loss": 3.2233, "step": 148000 }, { "epoch": 0.49, - "learning_rate": 2.5460468322298002e-05, - "loss": 3.2277, + "learning_rate": 2.5487112941347828e-05, + "loss": 3.1966, "step": 148100 }, { "epoch": 0.49, - "learning_rate": 2.5443898753305628e-05, - "loss": 3.2103, + "learning_rate": 2.5470561363320376e-05, + "loss": 3.2001, "step": 148200 }, { "epoch": 0.49, - "learning_rate": 2.542732918431326e-05, - "loss": 3.213, + "learning_rate": 2.545400978529293e-05, + "loss": 3.1996, "step": 148300 }, { "epoch": 0.49, - "learning_rate": 2.541075961532089e-05, - "loss": 3.2063, + "learning_rate": 2.543745820726548e-05, + "loss": 3.2018, "step": 148400 }, { "epoch": 0.49, - "learning_rate": 2.5394190046328515e-05, - "loss": 3.2153, + "learning_rate": 2.5420906629238034e-05, + "loss": 3.1989, "step": 148500 }, { "epoch": 0.49, - "learning_rate": 2.5377620477336145e-05, - "loss": 3.2187, + "learning_rate": 2.5404355051210582e-05, + "loss": 3.2076, "step": 148600 }, { "epoch": 0.49, - "learning_rate": 2.5361050908343774e-05, - "loss": 3.2132, + "learning_rate": 2.5387803473183137e-05, + "loss": 3.2128, "step": 148700 }, { "epoch": 0.49, - "learning_rate": 2.53444813393514e-05, - "loss": 3.2091, + "learning_rate": 2.5371251895155686e-05, + "loss": 3.2073, "step": 148800 }, { "epoch": 0.49, - "learning_rate": 2.5327911770359032e-05, - "loss": 3.2153, + "learning_rate": 2.5354700317128237e-05, + "loss": 3.1981, "step": 148900 }, { "epoch": 0.49, - "learning_rate": 2.531134220136666e-05, - "loss": 3.2265, + "learning_rate": 2.5338148739100785e-05, + "loss": 3.2092, "step": 149000 }, { "epoch": 0.49, - "learning_rate": 2.5294772632374287e-05, - "loss": 3.2141, + "learning_rate": 2.532159716107334e-05, + "loss": 3.2213, "step": 149100 }, { "epoch": 0.49, - "learning_rate": 2.5278203063381916e-05, - "loss": 3.2269, + "learning_rate": 2.530504558304589e-05, + "loss": 3.2147, "step": 149200 }, { "epoch": 0.49, - "learning_rate": 2.5261633494389546e-05, - "loss": 3.2248, + "learning_rate": 2.5288494005018437e-05, + "loss": 3.2079, "step": 149300 }, { - "epoch": 0.5, - "learning_rate": 2.524506392539717e-05, - "loss": 3.2274, + "epoch": 0.49, + "learning_rate": 2.5271942426990992e-05, + "loss": 3.2091, "step": 149400 }, { - "epoch": 0.5, - "learning_rate": 2.5228494356404804e-05, - "loss": 3.2308, + "epoch": 0.49, + "learning_rate": 2.525539084896354e-05, + "loss": 3.2003, "step": 149500 }, { "epoch": 0.5, - "learning_rate": 2.5211924787412433e-05, - "loss": 3.2069, + "learning_rate": 2.5238839270936092e-05, + "loss": 3.1978, "step": 149600 }, { "epoch": 0.5, - "learning_rate": 2.519535521842006e-05, - "loss": 3.2335, + "learning_rate": 2.522228769290864e-05, + "loss": 3.2132, "step": 149700 }, { "epoch": 0.5, - "learning_rate": 2.5178785649427688e-05, - "loss": 3.223, + "learning_rate": 2.5205736114881195e-05, + "loss": 3.1928, "step": 149800 }, { "epoch": 0.5, - "learning_rate": 2.5162216080435317e-05, - "loss": 3.23, + "learning_rate": 2.5189184536853743e-05, + "loss": 3.2015, "step": 149900 }, { "epoch": 0.5, - "learning_rate": 2.5145646511442943e-05, - "loss": 3.2203, + "learning_rate": 2.5172632958826298e-05, + "loss": 3.2106, "step": 150000 }, { "epoch": 0.5, - "learning_rate": 2.5129076942450576e-05, - "loss": 3.2192, + "learning_rate": 2.5156081380798846e-05, + "loss": 3.199, "step": 150100 }, { "epoch": 0.5, - "learning_rate": 2.5112507373458205e-05, - "loss": 3.2091, + "learning_rate": 2.51395298027714e-05, + "loss": 3.1951, "step": 150200 }, { "epoch": 0.5, - "learning_rate": 2.509593780446583e-05, - "loss": 3.2199, + "learning_rate": 2.512297822474395e-05, + "loss": 3.2051, "step": 150300 }, { "epoch": 0.5, - "learning_rate": 2.507936823547346e-05, - "loss": 3.2189, + "learning_rate": 2.5106426646716498e-05, + "loss": 3.2101, "step": 150400 }, { "epoch": 0.5, - "learning_rate": 2.506279866648109e-05, - "loss": 3.2123, + "learning_rate": 2.508987506868905e-05, + "loss": 3.2054, "step": 150500 }, { "epoch": 0.5, - "learning_rate": 2.5046229097488715e-05, - "loss": 3.2053, + "learning_rate": 2.5073323490661598e-05, + "loss": 3.2007, "step": 150600 }, { "epoch": 0.5, - "learning_rate": 2.5029659528496348e-05, - "loss": 3.2243, + "learning_rate": 2.5056771912634153e-05, + "loss": 3.2255, "step": 150700 }, { "epoch": 0.5, - "learning_rate": 2.5013089959503977e-05, - "loss": 3.2081, + "learning_rate": 2.50402203346067e-05, + "loss": 3.2011, "step": 150800 }, { "epoch": 0.5, - "learning_rate": 2.4996520390511603e-05, - "loss": 3.2182, + "learning_rate": 2.5023668756579256e-05, + "loss": 3.21, "step": 150900 }, { "epoch": 0.5, - "learning_rate": 2.4979950821519232e-05, - "loss": 3.2189, + "learning_rate": 2.5007117178551804e-05, + "loss": 3.206, "step": 151000 }, { "epoch": 0.5, - "learning_rate": 2.496338125252686e-05, - "loss": 3.2217, + "learning_rate": 2.4990565600524356e-05, + "loss": 3.2077, "step": 151100 }, { "epoch": 0.5, - "learning_rate": 2.4946811683534487e-05, - "loss": 3.2156, + "learning_rate": 2.4974014022496907e-05, + "loss": 3.2043, "step": 151200 }, { "epoch": 0.5, - "learning_rate": 2.493024211454212e-05, - "loss": 3.2229, + "learning_rate": 2.4957462444469455e-05, + "loss": 3.2054, "step": 151300 }, { "epoch": 0.5, - "learning_rate": 2.4913672545549745e-05, - "loss": 3.2108, + "learning_rate": 2.4940910866442007e-05, + "loss": 3.201, "step": 151400 }, { "epoch": 0.5, - "learning_rate": 2.4897102976557375e-05, - "loss": 3.2318, + "learning_rate": 2.492435928841456e-05, + "loss": 3.1775, "step": 151500 }, { "epoch": 0.5, - "learning_rate": 2.4880533407565004e-05, - "loss": 3.2274, + "learning_rate": 2.490780771038711e-05, + "loss": 3.1991, "step": 151600 }, { "epoch": 0.5, - "learning_rate": 2.4863963838572633e-05, - "loss": 3.212, + "learning_rate": 2.4891256132359662e-05, + "loss": 3.1855, "step": 151700 }, { "epoch": 0.5, - "learning_rate": 2.484739426958026e-05, - "loss": 3.2243, + "learning_rate": 2.4874704554332213e-05, + "loss": 3.2147, "step": 151800 }, { "epoch": 0.5, - "learning_rate": 2.483082470058789e-05, - "loss": 3.2059, + "learning_rate": 2.485815297630476e-05, + "loss": 3.2056, "step": 151900 }, { "epoch": 0.5, - "learning_rate": 2.4814255131595517e-05, - "loss": 3.2264, + "learning_rate": 2.4841601398277313e-05, + "loss": 3.1878, "step": 152000 }, { "epoch": 0.5, - "learning_rate": 2.4797685562603146e-05, - "loss": 3.2324, + "learning_rate": 2.482504982024986e-05, + "loss": 3.201, "step": 152100 }, { "epoch": 0.5, - "learning_rate": 2.4781115993610776e-05, - "loss": 3.2233, + "learning_rate": 2.4808498242222413e-05, + "loss": 3.1954, "step": 152200 }, { "epoch": 0.5, - "learning_rate": 2.4764546424618405e-05, - "loss": 3.2342, + "learning_rate": 2.4791946664194965e-05, + "loss": 3.208, "step": 152300 }, { - "epoch": 0.51, - "learning_rate": 2.474797685562603e-05, - "loss": 3.2193, + "epoch": 0.5, + "learning_rate": 2.4775395086167516e-05, + "loss": 3.2046, "step": 152400 }, { - "epoch": 0.51, - "learning_rate": 2.4731407286633663e-05, - "loss": 3.2501, + "epoch": 0.5, + "learning_rate": 2.4758843508140068e-05, + "loss": 3.2096, "step": 152500 }, { "epoch": 0.51, - "learning_rate": 2.471483771764129e-05, - "loss": 3.2225, + "learning_rate": 2.474229193011262e-05, + "loss": 3.1912, "step": 152600 }, { "epoch": 0.51, - "learning_rate": 2.4698268148648918e-05, - "loss": 3.2076, + "learning_rate": 2.472574035208517e-05, + "loss": 3.2087, "step": 152700 }, { "epoch": 0.51, - "learning_rate": 2.4681698579656547e-05, - "loss": 3.2151, + "learning_rate": 2.470918877405772e-05, + "loss": 3.2026, "step": 152800 }, { "epoch": 0.51, - "learning_rate": 2.4665129010664177e-05, - "loss": 3.2064, + "learning_rate": 2.469263719603027e-05, + "loss": 3.2028, "step": 152900 }, { "epoch": 0.51, - "learning_rate": 2.4648559441671803e-05, - "loss": 3.2132, + "learning_rate": 2.4676085618002822e-05, + "loss": 3.2052, "step": 153000 }, { "epoch": 0.51, - "learning_rate": 2.4631989872679435e-05, - "loss": 3.2306, + "learning_rate": 2.4659534039975374e-05, + "loss": 3.2224, "step": 153100 }, { "epoch": 0.51, - "learning_rate": 2.461542030368706e-05, - "loss": 3.2373, + "learning_rate": 2.4642982461947922e-05, + "loss": 3.2065, "step": 153200 }, { "epoch": 0.51, - "learning_rate": 2.459885073469469e-05, - "loss": 3.2166, + "learning_rate": 2.4626430883920474e-05, + "loss": 3.1843, "step": 153300 }, { "epoch": 0.51, - "learning_rate": 2.458228116570232e-05, - "loss": 3.2198, + "learning_rate": 2.4609879305893025e-05, + "loss": 3.2033, "step": 153400 }, { "epoch": 0.51, - "learning_rate": 2.456571159670995e-05, - "loss": 3.2135, + "learning_rate": 2.4593327727865577e-05, + "loss": 3.1906, "step": 153500 }, { "epoch": 0.51, - "learning_rate": 2.4549142027717574e-05, - "loss": 3.2008, + "learning_rate": 2.4576776149838125e-05, + "loss": 3.1975, "step": 153600 }, { "epoch": 0.51, - "learning_rate": 2.4532572458725207e-05, - "loss": 3.215, + "learning_rate": 2.4560224571810677e-05, + "loss": 3.1931, "step": 153700 }, { "epoch": 0.51, - "learning_rate": 2.4516002889732833e-05, - "loss": 3.2426, + "learning_rate": 2.454367299378323e-05, + "loss": 3.2084, "step": 153800 }, { "epoch": 0.51, - "learning_rate": 2.4499433320740462e-05, - "loss": 3.2137, + "learning_rate": 2.452712141575578e-05, + "loss": 3.2089, "step": 153900 }, { "epoch": 0.51, - "learning_rate": 2.448286375174809e-05, - "loss": 3.2177, + "learning_rate": 2.451056983772833e-05, + "loss": 3.2076, "step": 154000 }, { "epoch": 0.51, - "learning_rate": 2.446629418275572e-05, - "loss": 3.2256, + "learning_rate": 2.4494018259700883e-05, + "loss": 3.2131, "step": 154100 }, { "epoch": 0.51, - "learning_rate": 2.4449724613763346e-05, - "loss": 3.2111, + "learning_rate": 2.4477466681673435e-05, + "loss": 3.185, "step": 154200 }, { "epoch": 0.51, - "learning_rate": 2.443315504477098e-05, - "loss": 3.2284, + "learning_rate": 2.4460915103645983e-05, + "loss": 3.2189, "step": 154300 }, { "epoch": 0.51, - "learning_rate": 2.4416585475778605e-05, - "loss": 3.2174, + "learning_rate": 2.444436352561853e-05, + "loss": 3.2003, "step": 154400 }, { "epoch": 0.51, - "learning_rate": 2.4400015906786234e-05, - "loss": 3.2156, + "learning_rate": 2.4427811947591083e-05, + "loss": 3.206, "step": 154500 }, { "epoch": 0.51, - "learning_rate": 2.4383446337793863e-05, - "loss": 3.2307, + "learning_rate": 2.4411260369563634e-05, + "loss": 3.2072, "step": 154600 }, { "epoch": 0.51, - "learning_rate": 2.4366876768801492e-05, - "loss": 3.2055, + "learning_rate": 2.4394708791536186e-05, + "loss": 3.1948, "step": 154700 }, { "epoch": 0.51, - "learning_rate": 2.4350307199809118e-05, - "loss": 3.2108, + "learning_rate": 2.4378157213508738e-05, + "loss": 3.2002, "step": 154800 }, { "epoch": 0.51, - "learning_rate": 2.433373763081675e-05, - "loss": 3.2131, + "learning_rate": 2.436160563548129e-05, + "loss": 3.201, "step": 154900 }, { "epoch": 0.51, - "learning_rate": 2.4317168061824376e-05, - "loss": 3.212, + "learning_rate": 2.434505405745384e-05, + "loss": 3.1999, "step": 155000 }, { "epoch": 0.51, - "learning_rate": 2.4300598492832006e-05, - "loss": 3.2146, + "learning_rate": 2.432850247942639e-05, + "loss": 3.2012, "step": 155100 }, { "epoch": 0.51, - "learning_rate": 2.428402892383963e-05, - "loss": 3.2176, + "learning_rate": 2.431195090139894e-05, + "loss": 3.2057, "step": 155200 }, { "epoch": 0.51, - "learning_rate": 2.4267459354847264e-05, - "loss": 3.2155, + "learning_rate": 2.4295399323371492e-05, + "loss": 3.2004, "step": 155300 }, { "epoch": 0.51, - "learning_rate": 2.425088978585489e-05, - "loss": 3.2257, + "learning_rate": 2.427884774534404e-05, + "loss": 3.2138, "step": 155400 }, { - "epoch": 0.52, - "learning_rate": 2.423432021686252e-05, - "loss": 3.2212, + "epoch": 0.51, + "learning_rate": 2.4262296167316592e-05, + "loss": 3.1942, "step": 155500 }, { "epoch": 0.52, - "learning_rate": 2.421775064787015e-05, - "loss": 3.2313, + "learning_rate": 2.4245744589289144e-05, + "loss": 3.2087, "step": 155600 }, { "epoch": 0.52, - "learning_rate": 2.4201181078877778e-05, - "loss": 3.2174, + "learning_rate": 2.4229193011261695e-05, + "loss": 3.2001, "step": 155700 }, { "epoch": 0.52, - "learning_rate": 2.4184611509885403e-05, - "loss": 3.2207, + "learning_rate": 2.4212641433234247e-05, + "loss": 3.1938, "step": 155800 }, { "epoch": 0.52, - "learning_rate": 2.4168041940893036e-05, - "loss": 3.2239, + "learning_rate": 2.4196089855206795e-05, + "loss": 3.2153, "step": 155900 }, { "epoch": 0.52, - "learning_rate": 2.4151472371900662e-05, - "loss": 3.2188, + "learning_rate": 2.4179538277179347e-05, + "loss": 3.2044, "step": 156000 }, { "epoch": 0.52, - "learning_rate": 2.413490280290829e-05, - "loss": 3.2222, + "learning_rate": 2.4162986699151898e-05, + "loss": 3.1884, "step": 156100 }, { "epoch": 0.52, - "learning_rate": 2.411833323391592e-05, - "loss": 3.2209, + "learning_rate": 2.414643512112445e-05, + "loss": 3.1998, "step": 156200 }, { "epoch": 0.52, - "learning_rate": 2.410176366492355e-05, - "loss": 3.2226, + "learning_rate": 2.4129883543097e-05, + "loss": 3.2015, "step": 156300 }, { "epoch": 0.52, - "learning_rate": 2.4085194095931175e-05, - "loss": 3.2146, + "learning_rate": 2.4113331965069553e-05, + "loss": 3.1976, "step": 156400 }, { "epoch": 0.52, - "learning_rate": 2.4068624526938808e-05, - "loss": 3.2019, + "learning_rate": 2.40967803870421e-05, + "loss": 3.1984, "step": 156500 }, { "epoch": 0.52, - "learning_rate": 2.4052054957946434e-05, - "loss": 3.213, + "learning_rate": 2.4080228809014653e-05, + "loss": 3.2004, "step": 156600 }, { "epoch": 0.52, - "learning_rate": 2.4035485388954063e-05, - "loss": 3.2051, + "learning_rate": 2.40636772309872e-05, + "loss": 3.1966, "step": 156700 }, { "epoch": 0.52, - "learning_rate": 2.4018915819961692e-05, - "loss": 3.2262, + "learning_rate": 2.4047125652959753e-05, + "loss": 3.2148, "step": 156800 }, { "epoch": 0.52, - "learning_rate": 2.400234625096932e-05, - "loss": 3.2098, + "learning_rate": 2.4030574074932304e-05, + "loss": 3.2191, "step": 156900 }, { "epoch": 0.52, - "learning_rate": 2.3985776681976947e-05, - "loss": 3.2209, + "learning_rate": 2.4014022496904856e-05, + "loss": 3.2158, "step": 157000 }, { "epoch": 0.52, - "learning_rate": 2.396920711298458e-05, - "loss": 3.2172, + "learning_rate": 2.3997470918877408e-05, + "loss": 3.1973, "step": 157100 }, { "epoch": 0.52, - "learning_rate": 2.3952637543992205e-05, - "loss": 3.2234, + "learning_rate": 2.398091934084996e-05, + "loss": 3.2051, "step": 157200 }, { "epoch": 0.52, - "learning_rate": 2.3936067974999835e-05, - "loss": 3.2136, + "learning_rate": 2.396436776282251e-05, + "loss": 3.203, "step": 157300 }, { "epoch": 0.52, - "learning_rate": 2.3919498406007464e-05, - "loss": 3.2271, + "learning_rate": 2.394781618479506e-05, + "loss": 3.2064, "step": 157400 }, { "epoch": 0.52, - "learning_rate": 2.3902928837015093e-05, - "loss": 3.2114, + "learning_rate": 2.393126460676761e-05, + "loss": 3.2014, "step": 157500 }, { "epoch": 0.52, - "learning_rate": 2.388635926802272e-05, - "loss": 3.2014, + "learning_rate": 2.391471302874016e-05, + "loss": 3.2021, "step": 157600 }, { "epoch": 0.52, - "learning_rate": 2.386978969903035e-05, - "loss": 3.2182, + "learning_rate": 2.389816145071271e-05, + "loss": 3.2059, "step": 157700 }, { "epoch": 0.52, - "learning_rate": 2.3853220130037977e-05, - "loss": 3.2097, + "learning_rate": 2.3881609872685262e-05, + "loss": 3.2054, "step": 157800 }, { "epoch": 0.52, - "learning_rate": 2.3836650561045606e-05, - "loss": 3.222, + "learning_rate": 2.3865058294657814e-05, + "loss": 3.2024, "step": 157900 }, { "epoch": 0.52, - "learning_rate": 2.3820080992053236e-05, - "loss": 3.2259, + "learning_rate": 2.3848506716630365e-05, + "loss": 3.2089, "step": 158000 }, { "epoch": 0.52, - "learning_rate": 2.3803511423060865e-05, - "loss": 3.2167, + "learning_rate": 2.3831955138602917e-05, + "loss": 3.1962, "step": 158100 }, { "epoch": 0.52, - "learning_rate": 2.378694185406849e-05, - "loss": 3.2333, + "learning_rate": 2.3815403560575465e-05, + "loss": 3.2032, "step": 158200 }, { "epoch": 0.52, - "learning_rate": 2.3770372285076123e-05, - "loss": 3.2201, + "learning_rate": 2.3798851982548017e-05, + "loss": 3.1959, "step": 158300 }, { "epoch": 0.52, - "learning_rate": 2.375380271608375e-05, - "loss": 3.2387, + "learning_rate": 2.3782300404520568e-05, + "loss": 3.205, "step": 158400 }, { - "epoch": 0.53, - "learning_rate": 2.373723314709138e-05, - "loss": 3.2158, + "epoch": 0.52, + "learning_rate": 2.376574882649312e-05, + "loss": 3.2005, "step": 158500 }, { "epoch": 0.53, - "learning_rate": 2.3720663578099008e-05, - "loss": 3.2183, + "learning_rate": 2.374919724846567e-05, + "loss": 3.1979, "step": 158600 }, { "epoch": 0.53, - "learning_rate": 2.3704094009106637e-05, - "loss": 3.2102, + "learning_rate": 2.373264567043822e-05, + "loss": 3.2002, "step": 158700 }, { "epoch": 0.53, - "learning_rate": 2.3687524440114266e-05, - "loss": 3.2226, + "learning_rate": 2.371609409241077e-05, + "loss": 3.1889, "step": 158800 }, { "epoch": 0.53, - "learning_rate": 2.3670954871121895e-05, - "loss": 3.21, + "learning_rate": 2.3699542514383323e-05, + "loss": 3.2065, "step": 158900 }, { "epoch": 0.53, - "learning_rate": 2.365438530212952e-05, - "loss": 3.1934, + "learning_rate": 2.3682990936355874e-05, + "loss": 3.2198, "step": 159000 }, { "epoch": 0.53, - "learning_rate": 2.363781573313715e-05, - "loss": 3.2183, + "learning_rate": 2.3666439358328423e-05, + "loss": 3.1924, "step": 159100 }, { "epoch": 0.53, - "learning_rate": 2.362124616414478e-05, - "loss": 3.2046, + "learning_rate": 2.3649887780300974e-05, + "loss": 3.2031, "step": 159200 }, { "epoch": 0.53, - "learning_rate": 2.360467659515241e-05, - "loss": 3.2182, + "learning_rate": 2.3633336202273526e-05, + "loss": 3.2186, "step": 159300 }, { "epoch": 0.53, - "learning_rate": 2.3588107026160038e-05, - "loss": 3.2251, + "learning_rate": 2.3616784624246077e-05, + "loss": 3.1983, "step": 159400 }, { "epoch": 0.53, - "learning_rate": 2.3571537457167664e-05, - "loss": 3.2097, + "learning_rate": 2.360023304621863e-05, + "loss": 3.1825, "step": 159500 }, { "epoch": 0.53, - "learning_rate": 2.3554967888175293e-05, - "loss": 3.2196, + "learning_rate": 2.358368146819118e-05, + "loss": 3.2078, "step": 159600 }, { "epoch": 0.53, - "learning_rate": 2.3538398319182922e-05, - "loss": 3.2091, + "learning_rate": 2.3567129890163732e-05, + "loss": 3.2212, "step": 159700 }, { "epoch": 0.53, - "learning_rate": 2.352182875019055e-05, - "loss": 3.2071, + "learning_rate": 2.355057831213628e-05, + "loss": 3.2122, "step": 159800 }, { "epoch": 0.53, - "learning_rate": 2.350525918119818e-05, - "loss": 3.2071, + "learning_rate": 2.353402673410883e-05, + "loss": 3.2066, "step": 159900 }, { "epoch": 0.53, - "learning_rate": 2.348868961220581e-05, - "loss": 3.2082, + "learning_rate": 2.351747515608138e-05, + "loss": 3.2083, "step": 160000 }, { "epoch": 0.53, - "learning_rate": 2.3472120043213435e-05, - "loss": 3.2178, + "learning_rate": 2.3500923578053932e-05, + "loss": 3.209, "step": 160100 }, { "epoch": 0.53, - "learning_rate": 2.3455550474221065e-05, - "loss": 3.2252, + "learning_rate": 2.3484372000026483e-05, + "loss": 3.1902, "step": 160200 }, { "epoch": 0.53, - "learning_rate": 2.3438980905228694e-05, - "loss": 3.2326, + "learning_rate": 2.3467820421999035e-05, + "loss": 3.2105, "step": 160300 }, { "epoch": 0.53, - "learning_rate": 2.3422411336236323e-05, - "loss": 3.2149, + "learning_rate": 2.3451268843971587e-05, + "loss": 3.207, "step": 160400 }, { "epoch": 0.53, - "learning_rate": 2.3405841767243952e-05, - "loss": 3.2187, + "learning_rate": 2.3434717265944138e-05, + "loss": 3.2011, "step": 160500 }, { "epoch": 0.53, - "learning_rate": 2.338927219825158e-05, - "loss": 3.2216, + "learning_rate": 2.3418165687916686e-05, + "loss": 3.2104, "step": 160600 }, { "epoch": 0.53, - "learning_rate": 2.3372702629259207e-05, - "loss": 3.2157, + "learning_rate": 2.3401614109889238e-05, + "loss": 3.1891, "step": 160700 }, { "epoch": 0.53, - "learning_rate": 2.335613306026684e-05, - "loss": 3.2188, + "learning_rate": 2.338506253186179e-05, + "loss": 3.2032, "step": 160800 }, { "epoch": 0.53, - "learning_rate": 2.3339563491274466e-05, - "loss": 3.2099, + "learning_rate": 2.3368510953834338e-05, + "loss": 3.2063, "step": 160900 }, { "epoch": 0.53, - "learning_rate": 2.3322993922282095e-05, - "loss": 3.2184, + "learning_rate": 2.335195937580689e-05, + "loss": 3.1922, "step": 161000 }, { "epoch": 0.53, - "learning_rate": 2.3306424353289724e-05, - "loss": 3.2162, + "learning_rate": 2.333540779777944e-05, + "loss": 3.2114, "step": 161100 }, { "epoch": 0.53, - "learning_rate": 2.3289854784297353e-05, - "loss": 3.2167, + "learning_rate": 2.3318856219751993e-05, + "loss": 3.2012, "step": 161200 }, { "epoch": 0.53, - "learning_rate": 2.327328521530498e-05, - "loss": 3.2164, + "learning_rate": 2.3302304641724544e-05, + "loss": 3.2058, "step": 161300 }, { "epoch": 0.53, - "learning_rate": 2.3256715646312612e-05, - "loss": 3.2222, + "learning_rate": 2.3285753063697092e-05, + "loss": 3.2105, "step": 161400 }, { - "epoch": 0.54, - "learning_rate": 2.3240146077320238e-05, - "loss": 3.2174, + "epoch": 0.53, + "learning_rate": 2.3269201485669644e-05, + "loss": 3.1976, "step": 161500 }, { - "epoch": 0.54, - "learning_rate": 2.3223576508327867e-05, - "loss": 3.2111, + "epoch": 0.53, + "learning_rate": 2.3252649907642196e-05, + "loss": 3.1885, "step": 161600 }, { "epoch": 0.54, - "learning_rate": 2.3207006939335496e-05, - "loss": 3.2132, + "learning_rate": 2.3236098329614747e-05, + "loss": 3.2004, "step": 161700 }, { "epoch": 0.54, - "learning_rate": 2.3190437370343125e-05, - "loss": 3.2218, + "learning_rate": 2.32195467515873e-05, + "loss": 3.212, "step": 161800 }, { "epoch": 0.54, - "learning_rate": 2.317386780135075e-05, - "loss": 3.2056, + "learning_rate": 2.320299517355985e-05, + "loss": 3.1956, "step": 161900 }, { "epoch": 0.54, - "learning_rate": 2.3157298232358384e-05, - "loss": 3.2133, + "learning_rate": 2.3186443595532402e-05, + "loss": 3.1999, "step": 162000 }, { "epoch": 0.54, - "learning_rate": 2.314072866336601e-05, - "loss": 3.2275, + "learning_rate": 2.316989201750495e-05, + "loss": 3.2216, "step": 162100 }, { "epoch": 0.54, - "learning_rate": 2.312415909437364e-05, - "loss": 3.2189, + "learning_rate": 2.31533404394775e-05, + "loss": 3.2131, "step": 162200 }, { "epoch": 0.54, - "learning_rate": 2.3107589525381268e-05, - "loss": 3.2206, + "learning_rate": 2.313678886145005e-05, + "loss": 3.2127, "step": 162300 }, { "epoch": 0.54, - "learning_rate": 2.3091019956388897e-05, - "loss": 3.2203, + "learning_rate": 2.31202372834226e-05, + "loss": 3.1974, "step": 162400 }, { "epoch": 0.54, - "learning_rate": 2.3074450387396523e-05, - "loss": 3.2114, + "learning_rate": 2.3103685705395153e-05, + "loss": 3.2005, "step": 162500 }, { "epoch": 0.54, - "learning_rate": 2.3057880818404155e-05, - "loss": 3.2298, + "learning_rate": 2.3087134127367705e-05, + "loss": 3.21, "step": 162600 }, { "epoch": 0.54, - "learning_rate": 2.304131124941178e-05, - "loss": 3.2187, + "learning_rate": 2.3070582549340256e-05, + "loss": 3.2029, "step": 162700 }, { "epoch": 0.54, - "learning_rate": 2.302474168041941e-05, - "loss": 3.2125, + "learning_rate": 2.3054030971312808e-05, + "loss": 3.2006, "step": 162800 }, { "epoch": 0.54, - "learning_rate": 2.300817211142704e-05, - "loss": 3.2196, + "learning_rate": 2.3037479393285356e-05, + "loss": 3.2076, "step": 162900 }, { "epoch": 0.54, - "learning_rate": 2.299160254243467e-05, - "loss": 3.2183, + "learning_rate": 2.3020927815257908e-05, + "loss": 3.2036, "step": 163000 }, { "epoch": 0.54, - "learning_rate": 2.2975032973442295e-05, - "loss": 3.2161, + "learning_rate": 2.300437623723046e-05, + "loss": 3.2021, "step": 163100 }, { "epoch": 0.54, - "learning_rate": 2.2958463404449927e-05, - "loss": 3.2134, + "learning_rate": 2.2987824659203008e-05, + "loss": 3.1863, "step": 163200 }, { "epoch": 0.54, - "learning_rate": 2.2941893835457553e-05, - "loss": 3.2221, + "learning_rate": 2.297127308117556e-05, + "loss": 3.2187, "step": 163300 }, { "epoch": 0.54, - "learning_rate": 2.2925324266465182e-05, - "loss": 3.2096, + "learning_rate": 2.295472150314811e-05, + "loss": 3.2038, "step": 163400 }, { "epoch": 0.54, - "learning_rate": 2.290875469747281e-05, - "loss": 3.2248, + "learning_rate": 2.2938169925120662e-05, + "loss": 3.2033, "step": 163500 }, { "epoch": 0.54, - "learning_rate": 2.289218512848044e-05, - "loss": 3.2274, + "learning_rate": 2.2921618347093214e-05, + "loss": 3.207, "step": 163600 }, { "epoch": 0.54, - "learning_rate": 2.2875615559488067e-05, - "loss": 3.226, + "learning_rate": 2.2905066769065762e-05, + "loss": 3.1917, "step": 163700 }, { "epoch": 0.54, - "learning_rate": 2.2859045990495696e-05, - "loss": 3.2257, + "learning_rate": 2.2888515191038314e-05, + "loss": 3.1845, "step": 163800 }, { "epoch": 0.54, - "learning_rate": 2.2842476421503325e-05, - "loss": 3.2302, + "learning_rate": 2.2871963613010865e-05, + "loss": 3.1897, "step": 163900 }, { "epoch": 0.54, - "learning_rate": 2.2825906852510954e-05, - "loss": 3.2168, + "learning_rate": 2.2855412034983417e-05, + "loss": 3.1998, "step": 164000 }, { "epoch": 0.54, - "learning_rate": 2.280933728351858e-05, - "loss": 3.2274, + "learning_rate": 2.283886045695597e-05, + "loss": 3.1936, "step": 164100 }, { "epoch": 0.54, - "learning_rate": 2.2792767714526213e-05, - "loss": 3.2094, + "learning_rate": 2.282230887892852e-05, + "loss": 3.2005, "step": 164200 }, { "epoch": 0.54, - "learning_rate": 2.277619814553384e-05, - "loss": 3.222, + "learning_rate": 2.280575730090107e-05, + "loss": 3.1998, "step": 164300 }, { "epoch": 0.54, - "learning_rate": 2.2759628576541468e-05, - "loss": 3.225, + "learning_rate": 2.278920572287362e-05, + "loss": 3.2058, "step": 164400 }, { - "epoch": 0.55, - "learning_rate": 2.2743059007549097e-05, - "loss": 3.2139, + "epoch": 0.54, + "learning_rate": 2.277265414484617e-05, + "loss": 3.2058, "step": 164500 }, { - "epoch": 0.55, - "learning_rate": 2.2726489438556726e-05, - "loss": 3.2275, + "epoch": 0.54, + "learning_rate": 2.275610256681872e-05, + "loss": 3.2025, "step": 164600 }, { "epoch": 0.55, - "learning_rate": 2.2709919869564352e-05, - "loss": 3.217, + "learning_rate": 2.273955098879127e-05, + "loss": 3.205, "step": 164700 }, { "epoch": 0.55, - "learning_rate": 2.2693350300571984e-05, - "loss": 3.2205, + "learning_rate": 2.2722999410763823e-05, + "loss": 3.1912, "step": 164800 }, { "epoch": 0.55, - "learning_rate": 2.267678073157961e-05, - "loss": 3.2178, + "learning_rate": 2.2706447832736375e-05, + "loss": 3.1995, "step": 164900 }, { "epoch": 0.55, - "learning_rate": 2.266021116258724e-05, - "loss": 3.2022, + "learning_rate": 2.2689896254708926e-05, + "loss": 3.1941, "step": 165000 }, { "epoch": 0.55, - "learning_rate": 2.264364159359487e-05, - "loss": 3.2236, + "learning_rate": 2.2673344676681478e-05, + "loss": 3.2027, "step": 165100 }, { "epoch": 0.55, - "learning_rate": 2.2627072024602498e-05, - "loss": 3.2191, + "learning_rate": 2.2656793098654026e-05, + "loss": 3.2062, "step": 165200 }, { "epoch": 0.55, - "learning_rate": 2.2610502455610124e-05, - "loss": 3.2038, + "learning_rate": 2.2640241520626578e-05, + "loss": 3.2064, "step": 165300 }, { "epoch": 0.55, - "learning_rate": 2.2593932886617756e-05, - "loss": 3.2108, + "learning_rate": 2.2623689942599126e-05, + "loss": 3.185, "step": 165400 }, { "epoch": 0.55, - "learning_rate": 2.2577363317625382e-05, - "loss": 3.2065, + "learning_rate": 2.2607138364571678e-05, + "loss": 3.2034, "step": 165500 }, { "epoch": 0.55, - "learning_rate": 2.256079374863301e-05, - "loss": 3.2168, + "learning_rate": 2.259058678654423e-05, + "loss": 3.1962, "step": 165600 }, { "epoch": 0.55, - "learning_rate": 2.254422417964064e-05, - "loss": 3.222, + "learning_rate": 2.257403520851678e-05, + "loss": 3.2138, "step": 165700 }, { "epoch": 0.55, - "learning_rate": 2.252765461064827e-05, - "loss": 3.2179, + "learning_rate": 2.2557483630489332e-05, + "loss": 3.2043, "step": 165800 }, { "epoch": 0.55, - "learning_rate": 2.2511085041655895e-05, - "loss": 3.2166, + "learning_rate": 2.2540932052461884e-05, + "loss": 3.1944, "step": 165900 }, { "epoch": 0.55, - "learning_rate": 2.2494515472663528e-05, - "loss": 3.2093, + "learning_rate": 2.2524380474434436e-05, + "loss": 3.2045, "step": 166000 }, { "epoch": 0.55, - "learning_rate": 2.2477945903671154e-05, - "loss": 3.238, + "learning_rate": 2.2507828896406984e-05, + "loss": 3.2019, "step": 166100 }, { "epoch": 0.55, - "learning_rate": 2.2461376334678783e-05, - "loss": 3.2243, + "learning_rate": 2.2491277318379535e-05, + "loss": 3.2008, "step": 166200 }, { "epoch": 0.55, - "learning_rate": 2.2444806765686412e-05, - "loss": 3.2205, + "learning_rate": 2.2474725740352087e-05, + "loss": 3.2056, "step": 166300 }, { "epoch": 0.55, - "learning_rate": 2.242823719669404e-05, - "loss": 3.2243, + "learning_rate": 2.245817416232464e-05, + "loss": 3.2127, "step": 166400 }, { "epoch": 0.55, - "learning_rate": 2.2411667627701667e-05, - "loss": 3.2148, + "learning_rate": 2.2441622584297187e-05, + "loss": 3.2155, "step": 166500 }, { "epoch": 0.55, - "learning_rate": 2.23950980587093e-05, - "loss": 3.214, + "learning_rate": 2.242507100626974e-05, + "loss": 3.1889, "step": 166600 }, { "epoch": 0.55, - "learning_rate": 2.2378528489716926e-05, - "loss": 3.2244, + "learning_rate": 2.240851942824229e-05, + "loss": 3.1998, "step": 166700 }, { "epoch": 0.55, - "learning_rate": 2.2361958920724555e-05, - "loss": 3.2258, + "learning_rate": 2.239196785021484e-05, + "loss": 3.1955, "step": 166800 }, { "epoch": 0.55, - "learning_rate": 2.2345389351732184e-05, - "loss": 3.2191, + "learning_rate": 2.237541627218739e-05, + "loss": 3.1883, "step": 166900 }, { "epoch": 0.55, - "learning_rate": 2.2328819782739813e-05, - "loss": 3.2106, + "learning_rate": 2.235886469415994e-05, + "loss": 3.2105, "step": 167000 }, { "epoch": 0.55, - "learning_rate": 2.231225021374744e-05, - "loss": 3.2171, + "learning_rate": 2.2342313116132493e-05, + "loss": 3.1922, "step": 167100 }, { "epoch": 0.55, - "learning_rate": 2.2295680644755072e-05, - "loss": 3.2075, + "learning_rate": 2.2325761538105045e-05, + "loss": 3.2084, "step": 167200 }, { "epoch": 0.55, - "learning_rate": 2.2279111075762698e-05, - "loss": 3.211, + "learning_rate": 2.2309209960077596e-05, + "loss": 3.1992, "step": 167300 }, { "epoch": 0.55, - "learning_rate": 2.2262541506770327e-05, - "loss": 3.2132, + "learning_rate": 2.2292658382050148e-05, + "loss": 3.1982, "step": 167400 }, { - "epoch": 0.56, - "learning_rate": 2.2245971937777956e-05, - "loss": 3.23, + "epoch": 0.55, + "learning_rate": 2.22761068040227e-05, + "loss": 3.2015, "step": 167500 }, { - "epoch": 0.56, - "learning_rate": 2.2229402368785585e-05, - "loss": 3.2116, + "epoch": 0.55, + "learning_rate": 2.2259555225995248e-05, + "loss": 3.1835, "step": 167600 }, { "epoch": 0.56, - "learning_rate": 2.221283279979321e-05, - "loss": 3.224, + "learning_rate": 2.2243003647967796e-05, + "loss": 3.2006, "step": 167700 }, { "epoch": 0.56, - "learning_rate": 2.2196263230800844e-05, - "loss": 3.2222, + "learning_rate": 2.2226452069940347e-05, + "loss": 3.2041, "step": 167800 }, { "epoch": 0.56, - "learning_rate": 2.217969366180847e-05, - "loss": 3.2164, + "learning_rate": 2.22099004919129e-05, + "loss": 3.204, "step": 167900 }, { "epoch": 0.56, - "learning_rate": 2.21631240928161e-05, - "loss": 3.2285, + "learning_rate": 2.219334891388545e-05, + "loss": 3.2042, "step": 168000 }, { "epoch": 0.56, - "learning_rate": 2.2146554523823724e-05, - "loss": 3.2157, + "learning_rate": 2.2176797335858002e-05, + "loss": 3.1964, "step": 168100 }, { "epoch": 0.56, - "learning_rate": 2.2129984954831357e-05, - "loss": 3.2168, + "learning_rate": 2.2160245757830554e-05, + "loss": 3.2025, "step": 168200 }, { "epoch": 0.56, - "learning_rate": 2.2113415385838983e-05, - "loss": 3.2078, + "learning_rate": 2.2143694179803105e-05, + "loss": 3.1967, "step": 168300 }, { "epoch": 0.56, - "learning_rate": 2.2096845816846612e-05, - "loss": 3.1972, + "learning_rate": 2.2127142601775654e-05, + "loss": 3.2051, "step": 168400 }, { "epoch": 0.56, - "learning_rate": 2.208027624785424e-05, - "loss": 3.2122, + "learning_rate": 2.2110591023748205e-05, + "loss": 3.1978, "step": 168500 }, { "epoch": 0.56, - "learning_rate": 2.206370667886187e-05, - "loss": 3.208, + "learning_rate": 2.2094039445720757e-05, + "loss": 3.2102, "step": 168600 }, { "epoch": 0.56, - "learning_rate": 2.2047137109869496e-05, - "loss": 3.2052, + "learning_rate": 2.2077487867693305e-05, + "loss": 3.1967, "step": 168700 }, { "epoch": 0.56, - "learning_rate": 2.203056754087713e-05, - "loss": 3.2134, + "learning_rate": 2.2060936289665857e-05, + "loss": 3.1871, "step": 168800 }, { "epoch": 0.56, - "learning_rate": 2.2013997971884755e-05, - "loss": 3.2198, + "learning_rate": 2.2044384711638408e-05, + "loss": 3.1997, "step": 168900 }, { "epoch": 0.56, - "learning_rate": 2.1997428402892384e-05, - "loss": 3.2389, + "learning_rate": 2.202783313361096e-05, + "loss": 3.1969, "step": 169000 }, { "epoch": 0.56, - "learning_rate": 2.1980858833900013e-05, - "loss": 3.2038, + "learning_rate": 2.201128155558351e-05, + "loss": 3.2053, "step": 169100 }, { "epoch": 0.56, - "learning_rate": 2.1964289264907642e-05, - "loss": 3.2153, + "learning_rate": 2.199472997755606e-05, + "loss": 3.2068, "step": 169200 }, { "epoch": 0.56, - "learning_rate": 2.1947719695915268e-05, - "loss": 3.218, + "learning_rate": 2.197817839952861e-05, + "loss": 3.205, "step": 169300 }, { "epoch": 0.56, - "learning_rate": 2.19311501269229e-05, - "loss": 3.2073, + "learning_rate": 2.1961626821501163e-05, + "loss": 3.2104, "step": 169400 }, { "epoch": 0.56, - "learning_rate": 2.1914580557930527e-05, - "loss": 3.2081, + "learning_rate": 2.1945075243473714e-05, + "loss": 3.2003, "step": 169500 }, { "epoch": 0.56, - "learning_rate": 2.1898010988938156e-05, - "loss": 3.2194, + "learning_rate": 2.1928523665446266e-05, + "loss": 3.2045, "step": 169600 }, { "epoch": 0.56, - "learning_rate": 2.1881441419945785e-05, - "loss": 3.2059, + "learning_rate": 2.1911972087418818e-05, + "loss": 3.2116, "step": 169700 }, { "epoch": 0.56, - "learning_rate": 2.1864871850953414e-05, - "loss": 3.2232, + "learning_rate": 2.189542050939137e-05, + "loss": 3.1815, "step": 169800 }, { "epoch": 0.56, - "learning_rate": 2.184830228196104e-05, - "loss": 3.2131, + "learning_rate": 2.1878868931363917e-05, + "loss": 3.1922, "step": 169900 }, { "epoch": 0.56, - "learning_rate": 2.1831732712968673e-05, - "loss": 3.2144, + "learning_rate": 2.1862317353336466e-05, + "loss": 3.2027, "step": 170000 }, { "epoch": 0.56, - "learning_rate": 2.18151631439763e-05, - "loss": 3.2059, + "learning_rate": 2.1845765775309017e-05, + "loss": 3.1976, "step": 170100 }, { "epoch": 0.56, - "learning_rate": 2.1798593574983928e-05, - "loss": 3.2204, + "learning_rate": 2.182921419728157e-05, + "loss": 3.2115, "step": 170200 }, { "epoch": 0.56, - "learning_rate": 2.1782024005991557e-05, - "loss": 3.2271, + "learning_rate": 2.181266261925412e-05, + "loss": 3.2026, "step": 170300 }, { "epoch": 0.56, - "learning_rate": 2.1765454436999186e-05, - "loss": 3.2162, + "learning_rate": 2.1796111041226672e-05, + "loss": 3.2009, "step": 170400 }, { - "epoch": 0.57, - "learning_rate": 2.1748884868006815e-05, - "loss": 3.2095, + "epoch": 0.56, + "learning_rate": 2.1779559463199224e-05, + "loss": 3.185, "step": 170500 }, { - "epoch": 0.57, - "learning_rate": 2.1732315299014444e-05, - "loss": 3.2096, + "epoch": 0.56, + "learning_rate": 2.1763007885171775e-05, + "loss": 3.1971, "step": 170600 }, { "epoch": 0.57, - "learning_rate": 2.171574573002207e-05, - "loss": 3.2119, + "learning_rate": 2.1746456307144323e-05, + "loss": 3.1998, "step": 170700 }, { "epoch": 0.57, - "learning_rate": 2.16991761610297e-05, - "loss": 3.2224, + "learning_rate": 2.1729904729116875e-05, + "loss": 3.1945, "step": 170800 }, { "epoch": 0.57, - "learning_rate": 2.168260659203733e-05, - "loss": 3.2099, + "learning_rate": 2.1713353151089427e-05, + "loss": 3.2063, "step": 170900 }, { "epoch": 0.57, - "learning_rate": 2.1666037023044958e-05, - "loss": 3.2122, + "learning_rate": 2.1696801573061975e-05, + "loss": 3.1947, "step": 171000 }, { "epoch": 0.57, - "learning_rate": 2.1649467454052587e-05, - "loss": 3.2208, + "learning_rate": 2.1680249995034526e-05, + "loss": 3.1923, "step": 171100 }, { "epoch": 0.57, - "learning_rate": 2.1632897885060216e-05, - "loss": 3.207, + "learning_rate": 2.1663698417007078e-05, + "loss": 3.1909, "step": 171200 }, { "epoch": 0.57, - "learning_rate": 2.1616328316067842e-05, - "loss": 3.2111, + "learning_rate": 2.164714683897963e-05, + "loss": 3.2091, "step": 171300 }, { "epoch": 0.57, - "learning_rate": 2.159975874707547e-05, - "loss": 3.2171, + "learning_rate": 2.163059526095218e-05, + "loss": 3.2042, "step": 171400 }, { "epoch": 0.57, - "learning_rate": 2.15831891780831e-05, - "loss": 3.2098, + "learning_rate": 2.161404368292473e-05, + "loss": 3.1955, "step": 171500 }, { "epoch": 0.57, - "learning_rate": 2.156661960909073e-05, - "loss": 3.2209, + "learning_rate": 2.159749210489728e-05, + "loss": 3.1915, "step": 171600 }, { "epoch": 0.57, - "learning_rate": 2.155005004009836e-05, - "loss": 3.2129, + "learning_rate": 2.1580940526869833e-05, + "loss": 3.1964, "step": 171700 }, { "epoch": 0.57, - "learning_rate": 2.1533480471105988e-05, - "loss": 3.2184, + "learning_rate": 2.1564388948842384e-05, + "loss": 3.1965, "step": 171800 }, { "epoch": 0.57, - "learning_rate": 2.1516910902113614e-05, - "loss": 3.2078, + "learning_rate": 2.1547837370814936e-05, + "loss": 3.2048, "step": 171900 }, { "epoch": 0.57, - "learning_rate": 2.1500341333121243e-05, - "loss": 3.1978, + "learning_rate": 2.1531285792787488e-05, + "loss": 3.204, "step": 172000 }, { "epoch": 0.57, - "learning_rate": 2.1483771764128872e-05, - "loss": 3.2174, + "learning_rate": 2.1514734214760036e-05, + "loss": 3.1971, "step": 172100 }, { "epoch": 0.57, - "learning_rate": 2.14672021951365e-05, - "loss": 3.2091, + "learning_rate": 2.1498182636732587e-05, + "loss": 3.1966, "step": 172200 }, { "epoch": 0.57, - "learning_rate": 2.145063262614413e-05, - "loss": 3.2273, + "learning_rate": 2.148163105870514e-05, + "loss": 3.1991, "step": 172300 }, { "epoch": 0.57, - "learning_rate": 2.143406305715176e-05, - "loss": 3.2248, + "learning_rate": 2.1465079480677687e-05, + "loss": 3.1876, "step": 172400 }, { "epoch": 0.57, - "learning_rate": 2.141749348815939e-05, - "loss": 3.2139, + "learning_rate": 2.144852790265024e-05, + "loss": 3.1985, "step": 172500 }, { "epoch": 0.57, - "learning_rate": 2.1400923919167015e-05, - "loss": 3.2183, + "learning_rate": 2.143197632462279e-05, + "loss": 3.1869, "step": 172600 }, { "epoch": 0.57, - "learning_rate": 2.1384354350174644e-05, - "loss": 3.2161, + "learning_rate": 2.1415424746595342e-05, + "loss": 3.2055, "step": 172700 }, { "epoch": 0.57, - "learning_rate": 2.1367784781182273e-05, - "loss": 3.2103, + "learning_rate": 2.1398873168567894e-05, + "loss": 3.1982, "step": 172800 }, { "epoch": 0.57, - "learning_rate": 2.1351215212189903e-05, - "loss": 3.2244, + "learning_rate": 2.1382321590540445e-05, + "loss": 3.1976, "step": 172900 }, { "epoch": 0.57, - "learning_rate": 2.133464564319753e-05, - "loss": 3.2045, + "learning_rate": 2.1365770012512993e-05, + "loss": 3.1843, "step": 173000 }, { "epoch": 0.57, - "learning_rate": 2.131807607420516e-05, - "loss": 3.2181, + "learning_rate": 2.1349218434485545e-05, + "loss": 3.2011, "step": 173100 }, { "epoch": 0.57, - "learning_rate": 2.1301506505212787e-05, - "loss": 3.2184, + "learning_rate": 2.1332666856458093e-05, + "loss": 3.2063, "step": 173200 }, { "epoch": 0.57, - "learning_rate": 2.1284936936220416e-05, - "loss": 3.2278, + "learning_rate": 2.1316115278430645e-05, + "loss": 3.2047, "step": 173300 }, { "epoch": 0.57, - "learning_rate": 2.1268367367228045e-05, - "loss": 3.2055, + "learning_rate": 2.1299563700403196e-05, + "loss": 3.1998, "step": 173400 }, { "epoch": 0.57, - "learning_rate": 2.1251797798235674e-05, - "loss": 3.2179, + "learning_rate": 2.1283012122375748e-05, + "loss": 3.2016, "step": 173500 }, { - "epoch": 0.58, - "learning_rate": 2.12352282292433e-05, - "loss": 3.2125, + "epoch": 0.57, + "learning_rate": 2.12664605443483e-05, + "loss": 3.1933, "step": 173600 }, { "epoch": 0.58, - "learning_rate": 2.1218658660250933e-05, - "loss": 3.2107, + "learning_rate": 2.124990896632085e-05, + "loss": 3.2167, "step": 173700 }, { "epoch": 0.58, - "learning_rate": 2.120208909125856e-05, - "loss": 3.2069, + "learning_rate": 2.1233357388293403e-05, + "loss": 3.1986, "step": 173800 }, { "epoch": 0.58, - "learning_rate": 2.1185519522266188e-05, - "loss": 3.2293, + "learning_rate": 2.121680581026595e-05, + "loss": 3.2004, "step": 173900 }, { "epoch": 0.58, - "learning_rate": 2.1168949953273817e-05, - "loss": 3.2222, + "learning_rate": 2.1200254232238503e-05, + "loss": 3.1998, "step": 174000 }, { "epoch": 0.58, - "learning_rate": 2.1152380384281446e-05, - "loss": 3.2199, + "learning_rate": 2.1183702654211054e-05, + "loss": 3.2064, "step": 174100 }, { "epoch": 0.58, - "learning_rate": 2.1135810815289072e-05, - "loss": 3.2056, + "learning_rate": 2.1167151076183606e-05, + "loss": 3.2091, "step": 174200 }, { "epoch": 0.58, - "learning_rate": 2.1119241246296705e-05, - "loss": 3.2268, + "learning_rate": 2.1150599498156154e-05, + "loss": 3.2021, "step": 174300 }, { "epoch": 0.58, - "learning_rate": 2.110267167730433e-05, - "loss": 3.2109, + "learning_rate": 2.1134047920128706e-05, + "loss": 3.2037, "step": 174400 }, { "epoch": 0.58, - "learning_rate": 2.108610210831196e-05, - "loss": 3.2206, + "learning_rate": 2.1117496342101257e-05, + "loss": 3.1959, "step": 174500 }, { "epoch": 0.58, - "learning_rate": 2.106953253931959e-05, - "loss": 3.2069, + "learning_rate": 2.110094476407381e-05, + "loss": 3.1948, "step": 174600 }, { "epoch": 0.58, - "learning_rate": 2.1052962970327218e-05, - "loss": 3.2137, + "learning_rate": 2.1084393186046357e-05, + "loss": 3.1958, "step": 174700 }, { "epoch": 0.58, - "learning_rate": 2.1036393401334844e-05, - "loss": 3.2231, + "learning_rate": 2.106784160801891e-05, + "loss": 3.1991, "step": 174800 }, { "epoch": 0.58, - "learning_rate": 2.1019823832342477e-05, - "loss": 3.2157, + "learning_rate": 2.105129002999146e-05, + "loss": 3.2047, "step": 174900 }, { "epoch": 0.58, - "learning_rate": 2.1003254263350102e-05, - "loss": 3.2173, + "learning_rate": 2.1034738451964012e-05, + "loss": 3.1995, "step": 175000 }, { "epoch": 0.58, - "learning_rate": 2.098668469435773e-05, - "loss": 3.2336, + "learning_rate": 2.1018186873936563e-05, + "loss": 3.1888, "step": 175100 }, { "epoch": 0.58, - "learning_rate": 2.097011512536536e-05, - "loss": 3.219, + "learning_rate": 2.1001635295909115e-05, + "loss": 3.2027, "step": 175200 }, { "epoch": 0.58, - "learning_rate": 2.095354555637299e-05, - "loss": 3.2058, + "learning_rate": 2.0985083717881667e-05, + "loss": 3.1948, "step": 175300 }, { "epoch": 0.58, - "learning_rate": 2.0936975987380616e-05, - "loss": 3.2108, + "learning_rate": 2.0968532139854215e-05, + "loss": 3.2079, "step": 175400 }, { "epoch": 0.58, - "learning_rate": 2.092040641838825e-05, - "loss": 3.2162, + "learning_rate": 2.0951980561826763e-05, + "loss": 3.1925, "step": 175500 }, { "epoch": 0.58, - "learning_rate": 2.0903836849395874e-05, - "loss": 3.2056, + "learning_rate": 2.0935428983799315e-05, + "loss": 3.1986, "step": 175600 }, { "epoch": 0.58, - "learning_rate": 2.0887267280403503e-05, - "loss": 3.2143, + "learning_rate": 2.0918877405771866e-05, + "loss": 3.1992, "step": 175700 }, { "epoch": 0.58, - "learning_rate": 2.0870697711411133e-05, - "loss": 3.2066, + "learning_rate": 2.0902325827744418e-05, + "loss": 3.207, "step": 175800 }, { "epoch": 0.58, - "learning_rate": 2.0854128142418762e-05, - "loss": 3.2056, + "learning_rate": 2.088577424971697e-05, + "loss": 3.2053, "step": 175900 }, { "epoch": 0.58, - "learning_rate": 2.0837558573426388e-05, - "loss": 3.2122, + "learning_rate": 2.086922267168952e-05, + "loss": 3.2022, "step": 176000 }, { "epoch": 0.58, - "learning_rate": 2.082098900443402e-05, - "loss": 3.2139, + "learning_rate": 2.0852671093662073e-05, + "loss": 3.2019, "step": 176100 }, { "epoch": 0.58, - "learning_rate": 2.0804419435441646e-05, - "loss": 3.2123, + "learning_rate": 2.083611951563462e-05, + "loss": 3.1908, "step": 176200 }, { "epoch": 0.58, - "learning_rate": 2.0787849866449275e-05, - "loss": 3.2147, + "learning_rate": 2.0819567937607172e-05, + "loss": 3.2079, "step": 176300 }, { "epoch": 0.58, - "learning_rate": 2.0771280297456904e-05, - "loss": 3.2279, + "learning_rate": 2.0803016359579724e-05, + "loss": 3.1879, "step": 176400 }, { "epoch": 0.58, - "learning_rate": 2.0754710728464534e-05, - "loss": 3.2111, + "learning_rate": 2.0786464781552272e-05, + "loss": 3.1965, "step": 176500 }, { - "epoch": 0.59, - "learning_rate": 2.073814115947216e-05, - "loss": 3.2211, + "epoch": 0.58, + "learning_rate": 2.0769913203524824e-05, + "loss": 3.1913, "step": 176600 }, { - "epoch": 0.59, - "learning_rate": 2.0721571590479792e-05, - "loss": 3.2094, + "epoch": 0.58, + "learning_rate": 2.0753361625497375e-05, + "loss": 3.2077, "step": 176700 }, { "epoch": 0.59, - "learning_rate": 2.0705002021487418e-05, - "loss": 3.2107, + "learning_rate": 2.0736810047469927e-05, + "loss": 3.1967, "step": 176800 }, { "epoch": 0.59, - "learning_rate": 2.0688432452495047e-05, - "loss": 3.2158, + "learning_rate": 2.072025846944248e-05, + "loss": 3.2053, "step": 176900 }, { "epoch": 0.59, - "learning_rate": 2.0671862883502673e-05, - "loss": 3.2056, + "learning_rate": 2.0703706891415027e-05, + "loss": 3.1999, "step": 177000 }, { "epoch": 0.59, - "learning_rate": 2.0655293314510306e-05, - "loss": 3.2228, + "learning_rate": 2.068715531338758e-05, + "loss": 3.2043, "step": 177100 }, { "epoch": 0.59, - "learning_rate": 2.063872374551793e-05, - "loss": 3.2119, + "learning_rate": 2.067060373536013e-05, + "loss": 3.1981, "step": 177200 }, { "epoch": 0.59, - "learning_rate": 2.062215417652556e-05, - "loss": 3.2208, + "learning_rate": 2.065405215733268e-05, + "loss": 3.1962, "step": 177300 }, { "epoch": 0.59, - "learning_rate": 2.060558460753319e-05, - "loss": 3.2222, + "learning_rate": 2.0637500579305233e-05, + "loss": 3.1939, "step": 177400 }, { "epoch": 0.59, - "learning_rate": 2.058901503854082e-05, - "loss": 3.2195, + "learning_rate": 2.0620949001277785e-05, + "loss": 3.2171, "step": 177500 }, { "epoch": 0.59, - "learning_rate": 2.0572445469548445e-05, - "loss": 3.221, + "learning_rate": 2.0604397423250333e-05, + "loss": 3.2081, "step": 177600 }, { "epoch": 0.59, - "learning_rate": 2.0555875900556077e-05, - "loss": 3.2316, + "learning_rate": 2.0587845845222885e-05, + "loss": 3.1993, "step": 177700 }, { "epoch": 0.59, - "learning_rate": 2.0539306331563703e-05, - "loss": 3.2149, + "learning_rate": 2.0571294267195433e-05, + "loss": 3.1957, "step": 177800 }, { "epoch": 0.59, - "learning_rate": 2.0522736762571332e-05, - "loss": 3.2003, + "learning_rate": 2.0554742689167984e-05, + "loss": 3.2016, "step": 177900 }, { "epoch": 0.59, - "learning_rate": 2.050616719357896e-05, - "loss": 3.2055, + "learning_rate": 2.0538191111140536e-05, + "loss": 3.2018, "step": 178000 }, { "epoch": 0.59, - "learning_rate": 2.048959762458659e-05, - "loss": 3.2178, + "learning_rate": 2.0521639533113088e-05, + "loss": 3.2035, "step": 178100 }, { "epoch": 0.59, - "learning_rate": 2.0473028055594217e-05, - "loss": 3.2139, + "learning_rate": 2.050508795508564e-05, + "loss": 3.2024, "step": 178200 }, { "epoch": 0.59, - "learning_rate": 2.045645848660185e-05, - "loss": 3.2057, + "learning_rate": 2.048853637705819e-05, + "loss": 3.2026, "step": 178300 }, { "epoch": 0.59, - "learning_rate": 2.0439888917609475e-05, - "loss": 3.2186, + "learning_rate": 2.0471984799030742e-05, + "loss": 3.1915, "step": 178400 }, { "epoch": 0.59, - "learning_rate": 2.0423319348617104e-05, - "loss": 3.2105, + "learning_rate": 2.045543322100329e-05, + "loss": 3.1941, "step": 178500 }, { "epoch": 0.59, - "learning_rate": 2.0406749779624733e-05, - "loss": 3.2051, + "learning_rate": 2.0438881642975842e-05, + "loss": 3.1902, "step": 178600 }, { "epoch": 0.59, - "learning_rate": 2.0390180210632363e-05, - "loss": 3.2133, + "learning_rate": 2.0422330064948394e-05, + "loss": 3.1926, "step": 178700 }, { "epoch": 0.59, - "learning_rate": 2.037361064163999e-05, - "loss": 3.2348, + "learning_rate": 2.0405778486920942e-05, + "loss": 3.1957, "step": 178800 }, { "epoch": 0.59, - "learning_rate": 2.035704107264762e-05, - "loss": 3.2199, + "learning_rate": 2.0389226908893494e-05, + "loss": 3.2077, "step": 178900 }, { "epoch": 0.59, - "learning_rate": 2.0340471503655247e-05, - "loss": 3.2118, + "learning_rate": 2.0372675330866045e-05, + "loss": 3.1984, "step": 179000 }, { "epoch": 0.59, - "learning_rate": 2.0323901934662876e-05, - "loss": 3.206, + "learning_rate": 2.0356123752838597e-05, + "loss": 3.1861, "step": 179100 }, { "epoch": 0.59, - "learning_rate": 2.0307332365670505e-05, - "loss": 3.2025, + "learning_rate": 2.033957217481115e-05, + "loss": 3.2034, "step": 179200 }, { "epoch": 0.59, - "learning_rate": 2.0290762796678134e-05, - "loss": 3.2123, + "learning_rate": 2.0323020596783697e-05, + "loss": 3.2005, "step": 179300 }, { "epoch": 0.59, - "learning_rate": 2.027419322768576e-05, - "loss": 3.2126, + "learning_rate": 2.030646901875625e-05, + "loss": 3.2005, "step": 179400 }, { "epoch": 0.59, - "learning_rate": 2.0257623658693393e-05, - "loss": 3.2246, + "learning_rate": 2.02899174407288e-05, + "loss": 3.2006, "step": 179500 }, { - "epoch": 0.6, - "learning_rate": 2.024105408970102e-05, - "loss": 3.2044, + "epoch": 0.59, + "learning_rate": 2.027336586270135e-05, + "loss": 3.2097, "step": 179600 }, { - "epoch": 0.6, - "learning_rate": 2.0224484520708648e-05, - "loss": 3.2238, + "epoch": 0.59, + "learning_rate": 2.0256814284673903e-05, + "loss": 3.194, "step": 179700 }, { "epoch": 0.6, - "learning_rate": 2.0207914951716277e-05, - "loss": 3.2209, + "learning_rate": 2.0240262706646455e-05, + "loss": 3.2067, "step": 179800 }, { "epoch": 0.6, - "learning_rate": 2.0191345382723906e-05, - "loss": 3.2077, + "learning_rate": 2.0223711128619003e-05, + "loss": 3.2058, "step": 179900 }, { "epoch": 0.6, - "learning_rate": 2.0174775813731532e-05, - "loss": 3.2099, + "learning_rate": 2.0207159550591555e-05, + "loss": 3.2136, "step": 180000 }, { "epoch": 0.6, - "learning_rate": 2.0158206244739165e-05, - "loss": 3.2346, + "learning_rate": 2.0190607972564106e-05, + "loss": 3.189, "step": 180100 }, { "epoch": 0.6, - "learning_rate": 2.014163667574679e-05, - "loss": 3.2103, + "learning_rate": 2.0174056394536654e-05, + "loss": 3.1893, "step": 180200 }, { "epoch": 0.6, - "learning_rate": 2.012506710675442e-05, - "loss": 3.2181, + "learning_rate": 2.0157504816509206e-05, + "loss": 3.2046, "step": 180300 }, { "epoch": 0.6, - "learning_rate": 2.010849753776205e-05, - "loss": 3.2152, + "learning_rate": 2.0140953238481758e-05, + "loss": 3.1953, "step": 180400 }, { "epoch": 0.6, - "learning_rate": 2.0091927968769678e-05, - "loss": 3.2175, + "learning_rate": 2.012440166045431e-05, + "loss": 3.201, "step": 180500 }, { "epoch": 0.6, - "learning_rate": 2.0075358399777304e-05, - "loss": 3.2149, + "learning_rate": 2.010785008242686e-05, + "loss": 3.2157, "step": 180600 }, { "epoch": 0.6, - "learning_rate": 2.0058788830784937e-05, - "loss": 3.2166, + "learning_rate": 2.0091298504399412e-05, + "loss": 3.1992, "step": 180700 }, { "epoch": 0.6, - "learning_rate": 2.0042219261792562e-05, - "loss": 3.2107, + "learning_rate": 2.0074746926371964e-05, + "loss": 3.1929, "step": 180800 }, { "epoch": 0.6, - "learning_rate": 2.002564969280019e-05, - "loss": 3.2124, + "learning_rate": 2.0058195348344512e-05, + "loss": 3.2006, "step": 180900 }, { "epoch": 0.6, - "learning_rate": 2.000908012380782e-05, - "loss": 3.2106, + "learning_rate": 2.004164377031706e-05, + "loss": 3.1947, "step": 181000 }, { "epoch": 0.6, - "learning_rate": 1.999251055481545e-05, - "loss": 3.2197, + "learning_rate": 2.0025092192289612e-05, + "loss": 3.1953, "step": 181100 }, { "epoch": 0.6, - "learning_rate": 1.9975940985823076e-05, - "loss": 3.2246, + "learning_rate": 2.0008540614262164e-05, + "loss": 3.1981, "step": 181200 }, { "epoch": 0.6, - "learning_rate": 1.9959371416830705e-05, - "loss": 3.2074, + "learning_rate": 1.9991989036234715e-05, + "loss": 3.1958, "step": 181300 }, { "epoch": 0.6, - "learning_rate": 1.9942801847838334e-05, - "loss": 3.2075, + "learning_rate": 1.9975437458207267e-05, + "loss": 3.2149, "step": 181400 }, { "epoch": 0.6, - "learning_rate": 1.9926232278845963e-05, - "loss": 3.211, + "learning_rate": 1.995888588017982e-05, + "loss": 3.1982, "step": 181500 }, { "epoch": 0.6, - "learning_rate": 1.990966270985359e-05, - "loss": 3.2053, + "learning_rate": 1.994233430215237e-05, + "loss": 3.2088, "step": 181600 }, { "epoch": 0.6, - "learning_rate": 1.9893093140861222e-05, - "loss": 3.2205, + "learning_rate": 1.9925782724124918e-05, + "loss": 3.2016, "step": 181700 }, { "epoch": 0.6, - "learning_rate": 1.9876523571868848e-05, - "loss": 3.199, + "learning_rate": 1.990923114609747e-05, + "loss": 3.2023, "step": 181800 }, { "epoch": 0.6, - "learning_rate": 1.9859954002876477e-05, - "loss": 3.2271, + "learning_rate": 1.989267956807002e-05, + "loss": 3.1883, "step": 181900 }, { "epoch": 0.6, - "learning_rate": 1.9843384433884106e-05, - "loss": 3.2162, + "learning_rate": 1.9876127990042573e-05, + "loss": 3.2048, "step": 182000 }, { "epoch": 0.6, - "learning_rate": 1.9826814864891735e-05, - "loss": 3.2215, + "learning_rate": 1.985957641201512e-05, + "loss": 3.196, "step": 182100 }, { "epoch": 0.6, - "learning_rate": 1.9810245295899365e-05, - "loss": 3.1948, + "learning_rate": 1.9843024833987673e-05, + "loss": 3.1875, "step": 182200 }, { "epoch": 0.6, - "learning_rate": 1.9793675726906994e-05, - "loss": 3.23, + "learning_rate": 1.9826473255960224e-05, + "loss": 3.2023, "step": 182300 }, { "epoch": 0.6, - "learning_rate": 1.977710615791462e-05, - "loss": 3.2102, + "learning_rate": 1.9809921677932776e-05, + "loss": 3.2036, "step": 182400 }, { "epoch": 0.6, - "learning_rate": 1.976053658892225e-05, - "loss": 3.1882, + "learning_rate": 1.9793370099905324e-05, + "loss": 3.2086, "step": 182500 }, { - "epoch": 0.61, - "learning_rate": 1.9743967019929878e-05, - "loss": 3.2112, + "epoch": 0.6, + "learning_rate": 1.9776818521877876e-05, + "loss": 3.189, "step": 182600 }, { - "epoch": 0.61, - "learning_rate": 1.9727397450937507e-05, - "loss": 3.2204, + "epoch": 0.6, + "learning_rate": 1.9760266943850427e-05, + "loss": 3.2058, "step": 182700 }, { "epoch": 0.61, - "learning_rate": 1.9710827881945136e-05, - "loss": 3.2033, + "learning_rate": 1.974371536582298e-05, + "loss": 3.1888, "step": 182800 }, { "epoch": 0.61, - "learning_rate": 1.9694258312952766e-05, - "loss": 3.2034, + "learning_rate": 1.972716378779553e-05, + "loss": 3.1813, "step": 182900 }, { "epoch": 0.61, - "learning_rate": 1.967768874396039e-05, - "loss": 3.2138, + "learning_rate": 1.9710612209768082e-05, + "loss": 3.2135, "step": 183000 }, { "epoch": 0.61, - "learning_rate": 1.966111917496802e-05, - "loss": 3.2213, + "learning_rate": 1.9694060631740634e-05, + "loss": 3.1972, "step": 183100 }, { "epoch": 0.61, - "learning_rate": 1.964454960597565e-05, - "loss": 3.2022, + "learning_rate": 1.9677509053713182e-05, + "loss": 3.2116, "step": 183200 }, { "epoch": 0.61, - "learning_rate": 1.962798003698328e-05, - "loss": 3.2096, + "learning_rate": 1.966095747568573e-05, + "loss": 3.1999, "step": 183300 }, { "epoch": 0.61, - "learning_rate": 1.9611410467990908e-05, - "loss": 3.2053, + "learning_rate": 1.9644405897658282e-05, + "loss": 3.1968, "step": 183400 }, { "epoch": 0.61, - "learning_rate": 1.9594840898998537e-05, - "loss": 3.2069, + "learning_rate": 1.9627854319630833e-05, + "loss": 3.1951, "step": 183500 }, { "epoch": 0.61, - "learning_rate": 1.9578271330006163e-05, - "loss": 3.2051, + "learning_rate": 1.9611302741603385e-05, + "loss": 3.1993, "step": 183600 }, { "epoch": 0.61, - "learning_rate": 1.9561701761013792e-05, - "loss": 3.2068, + "learning_rate": 1.9594751163575937e-05, + "loss": 3.2, "step": 183700 }, { "epoch": 0.61, - "learning_rate": 1.954513219202142e-05, - "loss": 3.2107, + "learning_rate": 1.9578199585548488e-05, + "loss": 3.2064, "step": 183800 }, { "epoch": 0.61, - "learning_rate": 1.952856262302905e-05, - "loss": 3.2082, + "learning_rate": 1.956164800752104e-05, + "loss": 3.2108, "step": 183900 }, { "epoch": 0.61, - "learning_rate": 1.951199305403668e-05, - "loss": 3.2135, + "learning_rate": 1.9545096429493588e-05, + "loss": 3.1979, "step": 184000 }, { "epoch": 0.61, - "learning_rate": 1.949542348504431e-05, - "loss": 3.2131, + "learning_rate": 1.952854485146614e-05, + "loss": 3.1987, "step": 184100 }, { "epoch": 0.61, - "learning_rate": 1.947885391605194e-05, - "loss": 3.217, + "learning_rate": 1.951199327343869e-05, + "loss": 3.2007, "step": 184200 }, { "epoch": 0.61, - "learning_rate": 1.9462284347059564e-05, - "loss": 3.2085, + "learning_rate": 1.949544169541124e-05, + "loss": 3.198, "step": 184300 }, { "epoch": 0.61, - "learning_rate": 1.9445714778067193e-05, - "loss": 3.2023, + "learning_rate": 1.947889011738379e-05, + "loss": 3.2051, "step": 184400 }, { "epoch": 0.61, - "learning_rate": 1.9429145209074823e-05, - "loss": 3.2041, + "learning_rate": 1.9462338539356343e-05, + "loss": 3.192, "step": 184500 }, { "epoch": 0.61, - "learning_rate": 1.9412575640082452e-05, - "loss": 3.1917, + "learning_rate": 1.9445786961328894e-05, + "loss": 3.2129, "step": 184600 }, { "epoch": 0.61, - "learning_rate": 1.939600607109008e-05, - "loss": 3.2282, + "learning_rate": 1.9429235383301446e-05, + "loss": 3.2072, "step": 184700 }, { "epoch": 0.61, - "learning_rate": 1.937943650209771e-05, - "loss": 3.2208, + "learning_rate": 1.9412683805273994e-05, + "loss": 3.1932, "step": 184800 }, { "epoch": 0.61, - "learning_rate": 1.9362866933105336e-05, - "loss": 3.1997, + "learning_rate": 1.9396132227246546e-05, + "loss": 3.2124, "step": 184900 }, { "epoch": 0.61, - "learning_rate": 1.9346297364112965e-05, - "loss": 3.2031, + "learning_rate": 1.9379580649219097e-05, + "loss": 3.1987, "step": 185000 }, { "epoch": 0.61, - "learning_rate": 1.9329727795120595e-05, - "loss": 3.209, + "learning_rate": 1.936302907119165e-05, + "loss": 3.199, "step": 185100 }, { "epoch": 0.61, - "learning_rate": 1.9313158226128224e-05, - "loss": 3.2041, + "learning_rate": 1.93464774931642e-05, + "loss": 3.203, "step": 185200 }, { "epoch": 0.61, - "learning_rate": 1.9296588657135853e-05, - "loss": 3.2266, + "learning_rate": 1.9329925915136752e-05, + "loss": 3.2016, "step": 185300 }, { "epoch": 0.61, - "learning_rate": 1.9280019088143482e-05, - "loss": 3.2112, + "learning_rate": 1.93133743371093e-05, + "loss": 3.2168, "step": 185400 }, { "epoch": 0.61, - "learning_rate": 1.9263449519151108e-05, - "loss": 3.203, + "learning_rate": 1.9296822759081852e-05, + "loss": 3.1985, "step": 185500 }, { - "epoch": 0.62, - "learning_rate": 1.9246879950158737e-05, - "loss": 3.1993, + "epoch": 0.61, + "learning_rate": 1.92802711810544e-05, + "loss": 3.189, "step": 185600 }, { - "epoch": 0.62, - "learning_rate": 1.9230310381166366e-05, - "loss": 3.2096, + "epoch": 0.61, + "learning_rate": 1.9263719603026952e-05, + "loss": 3.1951, "step": 185700 }, { "epoch": 0.62, - "learning_rate": 1.9213740812173996e-05, - "loss": 3.2016, + "learning_rate": 1.9247168024999503e-05, + "loss": 3.212, "step": 185800 }, { "epoch": 0.62, - "learning_rate": 1.919717124318162e-05, - "loss": 3.2328, + "learning_rate": 1.9230616446972055e-05, + "loss": 3.1964, "step": 185900 }, { "epoch": 0.62, - "learning_rate": 1.9180601674189254e-05, - "loss": 3.2087, + "learning_rate": 1.9214064868944607e-05, + "loss": 3.1895, "step": 186000 }, { "epoch": 0.62, - "learning_rate": 1.916403210519688e-05, - "loss": 3.2094, + "learning_rate": 1.9197513290917158e-05, + "loss": 3.2004, "step": 186100 }, { "epoch": 0.62, - "learning_rate": 1.914746253620451e-05, - "loss": 3.2157, + "learning_rate": 1.918096171288971e-05, + "loss": 3.203, "step": 186200 }, { "epoch": 0.62, - "learning_rate": 1.9130892967212138e-05, - "loss": 3.2215, + "learning_rate": 1.9164410134862258e-05, + "loss": 3.2075, "step": 186300 }, { "epoch": 0.62, - "learning_rate": 1.9114323398219767e-05, - "loss": 3.2244, + "learning_rate": 1.914785855683481e-05, + "loss": 3.1911, "step": 186400 }, { "epoch": 0.62, - "learning_rate": 1.9097753829227393e-05, - "loss": 3.2091, + "learning_rate": 1.913130697880736e-05, + "loss": 3.2001, "step": 186500 }, { "epoch": 0.62, - "learning_rate": 1.9081184260235026e-05, - "loss": 3.218, + "learning_rate": 1.911475540077991e-05, + "loss": 3.2045, "step": 186600 }, { "epoch": 0.62, - "learning_rate": 1.906461469124265e-05, - "loss": 3.2123, + "learning_rate": 1.909820382275246e-05, + "loss": 3.1983, "step": 186700 }, { "epoch": 0.62, - "learning_rate": 1.904804512225028e-05, - "loss": 3.1967, + "learning_rate": 1.9081652244725013e-05, + "loss": 3.2046, "step": 186800 }, { "epoch": 0.62, - "learning_rate": 1.903147555325791e-05, - "loss": 3.1944, + "learning_rate": 1.9065100666697564e-05, + "loss": 3.2096, "step": 186900 }, { "epoch": 0.62, - "learning_rate": 1.901490598426554e-05, - "loss": 3.2196, + "learning_rate": 1.9048549088670116e-05, + "loss": 3.2003, "step": 187000 }, { "epoch": 0.62, - "learning_rate": 1.8998336415273165e-05, - "loss": 3.2202, + "learning_rate": 1.9031997510642667e-05, + "loss": 3.1881, "step": 187100 }, { "epoch": 0.62, - "learning_rate": 1.8981766846280798e-05, - "loss": 3.2133, + "learning_rate": 1.9015445932615216e-05, + "loss": 3.1904, "step": 187200 }, { "epoch": 0.62, - "learning_rate": 1.8965197277288423e-05, - "loss": 3.2015, + "learning_rate": 1.8998894354587767e-05, + "loss": 3.1982, "step": 187300 }, { "epoch": 0.62, - "learning_rate": 1.8948627708296053e-05, - "loss": 3.2106, + "learning_rate": 1.898234277656032e-05, + "loss": 3.2091, "step": 187400 }, { "epoch": 0.62, - "learning_rate": 1.8932058139303682e-05, - "loss": 3.213, + "learning_rate": 1.896579119853287e-05, + "loss": 3.1938, "step": 187500 }, { "epoch": 0.62, - "learning_rate": 1.891548857031131e-05, - "loss": 3.2015, + "learning_rate": 1.8949239620505422e-05, + "loss": 3.2024, "step": 187600 }, { "epoch": 0.62, - "learning_rate": 1.8898919001318937e-05, - "loss": 3.195, + "learning_rate": 1.893268804247797e-05, + "loss": 3.1934, "step": 187700 }, { "epoch": 0.62, - "learning_rate": 1.888234943232657e-05, - "loss": 3.202, + "learning_rate": 1.8916136464450522e-05, + "loss": 3.1933, "step": 187800 }, { "epoch": 0.62, - "learning_rate": 1.8865779863334195e-05, - "loss": 3.2147, + "learning_rate": 1.8899584886423073e-05, + "loss": 3.1882, "step": 187900 }, { "epoch": 0.62, - "learning_rate": 1.8849210294341825e-05, - "loss": 3.2094, + "learning_rate": 1.888303330839562e-05, + "loss": 3.1962, "step": 188000 }, { "epoch": 0.62, - "learning_rate": 1.8832640725349454e-05, - "loss": 3.2107, + "learning_rate": 1.8866481730368173e-05, + "loss": 3.2101, "step": 188100 }, { "epoch": 0.62, - "learning_rate": 1.8816071156357083e-05, - "loss": 3.2142, + "learning_rate": 1.8849930152340725e-05, + "loss": 3.1973, "step": 188200 }, { "epoch": 0.62, - "learning_rate": 1.879950158736471e-05, - "loss": 3.1991, + "learning_rate": 1.8833378574313276e-05, + "loss": 3.2004, "step": 188300 }, { "epoch": 0.62, - "learning_rate": 1.878293201837234e-05, - "loss": 3.2112, + "learning_rate": 1.8816826996285828e-05, + "loss": 3.1943, "step": 188400 }, { "epoch": 0.62, - "learning_rate": 1.8766362449379967e-05, - "loss": 3.217, + "learning_rate": 1.880027541825838e-05, + "loss": 3.192, "step": 188500 }, { - "epoch": 0.63, - "learning_rate": 1.8749792880387596e-05, - "loss": 3.2094, + "epoch": 0.62, + "learning_rate": 1.878372384023093e-05, + "loss": 3.1939, "step": 188600 }, { - "epoch": 0.63, - "learning_rate": 1.8733223311395226e-05, - "loss": 3.2199, + "epoch": 0.62, + "learning_rate": 1.876717226220348e-05, + "loss": 3.1928, "step": 188700 }, { - "epoch": 0.63, - "learning_rate": 1.8716653742402855e-05, - "loss": 3.2165, + "epoch": 0.62, + "learning_rate": 1.8750620684176028e-05, + "loss": 3.1936, "step": 188800 }, { "epoch": 0.63, - "learning_rate": 1.870008417341048e-05, - "loss": 3.2216, + "learning_rate": 1.873406910614858e-05, + "loss": 3.1858, "step": 188900 }, { "epoch": 0.63, - "learning_rate": 1.8683514604418113e-05, - "loss": 3.2022, + "learning_rate": 1.871751752812113e-05, + "loss": 3.2005, "step": 189000 }, { "epoch": 0.63, - "learning_rate": 1.866694503542574e-05, - "loss": 3.2169, + "learning_rate": 1.8700965950093682e-05, + "loss": 3.1904, "step": 189100 }, { "epoch": 0.63, - "learning_rate": 1.8650375466433368e-05, - "loss": 3.2172, + "learning_rate": 1.8684414372066234e-05, + "loss": 3.1912, "step": 189200 }, { "epoch": 0.63, - "learning_rate": 1.8633805897440997e-05, - "loss": 3.1992, + "learning_rate": 1.8667862794038786e-05, + "loss": 3.1979, "step": 189300 }, { "epoch": 0.63, - "learning_rate": 1.8617236328448627e-05, - "loss": 3.2133, + "learning_rate": 1.8651311216011337e-05, + "loss": 3.202, "step": 189400 }, { "epoch": 0.63, - "learning_rate": 1.8600666759456252e-05, - "loss": 3.2031, + "learning_rate": 1.8634759637983885e-05, + "loss": 3.1932, "step": 189500 }, { "epoch": 0.63, - "learning_rate": 1.8584097190463885e-05, - "loss": 3.2065, + "learning_rate": 1.8618208059956437e-05, + "loss": 3.1855, "step": 189600 }, { "epoch": 0.63, - "learning_rate": 1.856752762147151e-05, - "loss": 3.2336, + "learning_rate": 1.860165648192899e-05, + "loss": 3.1816, "step": 189700 }, { "epoch": 0.63, - "learning_rate": 1.855095805247914e-05, - "loss": 3.2006, + "learning_rate": 1.858510490390154e-05, + "loss": 3.2059, "step": 189800 }, { "epoch": 0.63, - "learning_rate": 1.853438848348677e-05, - "loss": 3.218, + "learning_rate": 1.856855332587409e-05, + "loss": 3.1834, "step": 189900 }, { "epoch": 0.63, - "learning_rate": 1.85178189144944e-05, - "loss": 3.2102, + "learning_rate": 1.855200174784664e-05, + "loss": 3.2076, "step": 190000 }, { "epoch": 0.63, - "learning_rate": 1.8501249345502024e-05, - "loss": 3.2073, + "learning_rate": 1.853545016981919e-05, + "loss": 3.2002, "step": 190100 }, { "epoch": 0.63, - "learning_rate": 1.8484679776509654e-05, - "loss": 3.2091, + "learning_rate": 1.8518898591791743e-05, + "loss": 3.205, "step": 190200 }, { "epoch": 0.63, - "learning_rate": 1.8468110207517283e-05, - "loss": 3.2118, + "learning_rate": 1.850234701376429e-05, + "loss": 3.1938, "step": 190300 }, { "epoch": 0.63, - "learning_rate": 1.8451540638524912e-05, - "loss": 3.2146, + "learning_rate": 1.8485795435736843e-05, + "loss": 3.1829, "step": 190400 }, { "epoch": 0.63, - "learning_rate": 1.8434971069532538e-05, - "loss": 3.2176, + "learning_rate": 1.8469243857709395e-05, + "loss": 3.2003, "step": 190500 }, { "epoch": 0.63, - "learning_rate": 1.841840150054017e-05, - "loss": 3.2038, + "learning_rate": 1.8452692279681946e-05, + "loss": 3.1954, "step": 190600 }, { "epoch": 0.63, - "learning_rate": 1.8401831931547796e-05, - "loss": 3.2063, + "learning_rate": 1.8436140701654498e-05, + "loss": 3.1973, "step": 190700 }, { "epoch": 0.63, - "learning_rate": 1.8385262362555425e-05, - "loss": 3.2042, + "learning_rate": 1.841958912362705e-05, + "loss": 3.1997, "step": 190800 }, { "epoch": 0.63, - "learning_rate": 1.8368692793563055e-05, - "loss": 3.2107, + "learning_rate": 1.84030375455996e-05, + "loss": 3.1949, "step": 190900 }, { "epoch": 0.63, - "learning_rate": 1.8352123224570684e-05, - "loss": 3.2044, + "learning_rate": 1.838648596757215e-05, + "loss": 3.1931, "step": 191000 }, { "epoch": 0.63, - "learning_rate": 1.833555365557831e-05, - "loss": 3.2205, + "learning_rate": 1.8369934389544697e-05, + "loss": 3.1955, "step": 191100 }, { "epoch": 0.63, - "learning_rate": 1.8318984086585942e-05, - "loss": 3.2036, + "learning_rate": 1.835338281151725e-05, + "loss": 3.2073, "step": 191200 }, { "epoch": 0.63, - "learning_rate": 1.8302414517593568e-05, - "loss": 3.2105, + "learning_rate": 1.83368312334898e-05, + "loss": 3.2062, "step": 191300 }, { "epoch": 0.63, - "learning_rate": 1.8285844948601197e-05, - "loss": 3.2051, + "learning_rate": 1.8320279655462352e-05, + "loss": 3.2038, "step": 191400 }, { "epoch": 0.63, - "learning_rate": 1.8269275379608826e-05, - "loss": 3.2023, + "learning_rate": 1.8303728077434904e-05, + "loss": 3.182, "step": 191500 }, { "epoch": 0.63, - "learning_rate": 1.8252705810616456e-05, - "loss": 3.2084, + "learning_rate": 1.8287176499407455e-05, + "loss": 3.1976, "step": 191600 }, { - "epoch": 0.64, - "learning_rate": 1.823613624162408e-05, - "loss": 3.2098, + "epoch": 0.63, + "learning_rate": 1.8270624921380007e-05, + "loss": 3.1961, "step": 191700 }, { - "epoch": 0.64, - "learning_rate": 1.8219566672631714e-05, - "loss": 3.216, + "epoch": 0.63, + "learning_rate": 1.8254073343352555e-05, + "loss": 3.2065, "step": 191800 }, { "epoch": 0.64, - "learning_rate": 1.820299710363934e-05, - "loss": 3.2113, + "learning_rate": 1.8237521765325107e-05, + "loss": 3.2159, "step": 191900 }, { "epoch": 0.64, - "learning_rate": 1.818642753464697e-05, - "loss": 3.2106, + "learning_rate": 1.822097018729766e-05, + "loss": 3.1905, "step": 192000 }, { "epoch": 0.64, - "learning_rate": 1.8169857965654598e-05, - "loss": 3.2105, + "learning_rate": 1.8204418609270207e-05, + "loss": 3.191, "step": 192100 }, { "epoch": 0.64, - "learning_rate": 1.8153288396662227e-05, - "loss": 3.2169, + "learning_rate": 1.8187867031242758e-05, + "loss": 3.2008, "step": 192200 }, { "epoch": 0.64, - "learning_rate": 1.8136718827669853e-05, - "loss": 3.2081, + "learning_rate": 1.817131545321531e-05, + "loss": 3.1912, "step": 192300 }, { "epoch": 0.64, - "learning_rate": 1.8120149258677486e-05, - "loss": 3.2154, + "learning_rate": 1.815476387518786e-05, + "loss": 3.1873, "step": 192400 }, { "epoch": 0.64, - "learning_rate": 1.810357968968511e-05, - "loss": 3.2097, + "learning_rate": 1.8138212297160413e-05, + "loss": 3.1873, "step": 192500 }, { "epoch": 0.64, - "learning_rate": 1.808701012069274e-05, - "loss": 3.2035, + "learning_rate": 1.812166071913296e-05, + "loss": 3.1907, "step": 192600 }, { "epoch": 0.64, - "learning_rate": 1.807044055170037e-05, - "loss": 3.2127, + "learning_rate": 1.8105109141105513e-05, + "loss": 3.1979, "step": 192700 }, { "epoch": 0.64, - "learning_rate": 1.8053870982708e-05, - "loss": 3.2086, + "learning_rate": 1.8088557563078064e-05, + "loss": 3.1918, "step": 192800 }, { "epoch": 0.64, - "learning_rate": 1.8037301413715625e-05, - "loss": 3.2048, + "learning_rate": 1.8072005985050616e-05, + "loss": 3.2026, "step": 192900 }, { "epoch": 0.64, - "learning_rate": 1.8020731844723258e-05, - "loss": 3.2162, + "learning_rate": 1.8055454407023168e-05, + "loss": 3.1904, "step": 193000 }, { "epoch": 0.64, - "learning_rate": 1.8004162275730884e-05, - "loss": 3.2113, + "learning_rate": 1.803890282899572e-05, + "loss": 3.1928, "step": 193100 }, { "epoch": 0.64, - "learning_rate": 1.7987592706738513e-05, - "loss": 3.2067, + "learning_rate": 1.8022351250968268e-05, + "loss": 3.1923, "step": 193200 }, { "epoch": 0.64, - "learning_rate": 1.7971023137746142e-05, - "loss": 3.2054, + "learning_rate": 1.800579967294082e-05, + "loss": 3.1909, "step": 193300 }, { "epoch": 0.64, - "learning_rate": 1.795445356875377e-05, - "loss": 3.2263, + "learning_rate": 1.798924809491337e-05, + "loss": 3.2021, "step": 193400 }, { "epoch": 0.64, - "learning_rate": 1.7937883999761397e-05, - "loss": 3.2259, + "learning_rate": 1.797269651688592e-05, + "loss": 3.178, "step": 193500 }, { "epoch": 0.64, - "learning_rate": 1.792131443076903e-05, - "loss": 3.209, + "learning_rate": 1.795614493885847e-05, + "loss": 3.1929, "step": 193600 }, { "epoch": 0.64, - "learning_rate": 1.7904744861776655e-05, - "loss": 3.2209, + "learning_rate": 1.7939593360831022e-05, + "loss": 3.2002, "step": 193700 }, { "epoch": 0.64, - "learning_rate": 1.7888175292784285e-05, - "loss": 3.196, + "learning_rate": 1.7923041782803574e-05, + "loss": 3.1994, "step": 193800 }, { "epoch": 0.64, - "learning_rate": 1.7871605723791914e-05, - "loss": 3.2132, + "learning_rate": 1.7906490204776125e-05, + "loss": 3.1891, "step": 193900 }, { "epoch": 0.64, - "learning_rate": 1.7855036154799543e-05, - "loss": 3.2047, + "learning_rate": 1.7889938626748677e-05, + "loss": 3.1899, "step": 194000 }, { "epoch": 0.64, - "learning_rate": 1.783846658580717e-05, - "loss": 3.1997, + "learning_rate": 1.787338704872123e-05, + "loss": 3.2039, "step": 194100 }, { "epoch": 0.64, - "learning_rate": 1.78218970168148e-05, - "loss": 3.2146, + "learning_rate": 1.7856835470693777e-05, + "loss": 3.1978, "step": 194200 }, { "epoch": 0.64, - "learning_rate": 1.7805327447822427e-05, - "loss": 3.2159, + "learning_rate": 1.784028389266633e-05, + "loss": 3.2101, "step": 194300 }, { "epoch": 0.64, - "learning_rate": 1.7788757878830056e-05, - "loss": 3.218, + "learning_rate": 1.7823732314638877e-05, + "loss": 3.1848, "step": 194400 }, { "epoch": 0.64, - "learning_rate": 1.7772188309837686e-05, - "loss": 3.2143, + "learning_rate": 1.7807180736611428e-05, + "loss": 3.1949, "step": 194500 }, { "epoch": 0.64, - "learning_rate": 1.7755618740845315e-05, - "loss": 3.2165, + "learning_rate": 1.779062915858398e-05, + "loss": 3.1983, "step": 194600 }, { - "epoch": 0.65, - "learning_rate": 1.773904917185294e-05, - "loss": 3.2065, + "epoch": 0.64, + "learning_rate": 1.777407758055653e-05, + "loss": 3.1847, "step": 194700 }, { - "epoch": 0.65, - "learning_rate": 1.772247960286057e-05, - "loss": 3.209, + "epoch": 0.64, + "learning_rate": 1.7757526002529083e-05, + "loss": 3.1959, "step": 194800 }, { "epoch": 0.65, - "learning_rate": 1.77059100338682e-05, - "loss": 3.1997, + "learning_rate": 1.7740974424501635e-05, + "loss": 3.2126, "step": 194900 }, { "epoch": 0.65, - "learning_rate": 1.7689340464875828e-05, - "loss": 3.2126, + "learning_rate": 1.7724422846474183e-05, + "loss": 3.2048, "step": 195000 }, { "epoch": 0.65, - "learning_rate": 1.7672770895883457e-05, - "loss": 3.2111, + "learning_rate": 1.7707871268446734e-05, + "loss": 3.1869, "step": 195100 }, { "epoch": 0.65, - "learning_rate": 1.7656201326891087e-05, - "loss": 3.213, + "learning_rate": 1.7691319690419286e-05, + "loss": 3.1921, "step": 195200 }, { "epoch": 0.65, - "learning_rate": 1.7639631757898713e-05, - "loss": 3.1941, + "learning_rate": 1.7674768112391838e-05, + "loss": 3.1892, "step": 195300 }, { "epoch": 0.65, - "learning_rate": 1.7623062188906342e-05, - "loss": 3.2127, + "learning_rate": 1.765821653436439e-05, + "loss": 3.1968, "step": 195400 }, { "epoch": 0.65, - "learning_rate": 1.760649261991397e-05, - "loss": 3.2127, + "learning_rate": 1.7641664956336937e-05, + "loss": 3.1988, "step": 195500 }, { "epoch": 0.65, - "learning_rate": 1.75899230509216e-05, - "loss": 3.1989, + "learning_rate": 1.762511337830949e-05, + "loss": 3.2126, "step": 195600 }, { "epoch": 0.65, - "learning_rate": 1.757335348192923e-05, - "loss": 3.2102, + "learning_rate": 1.760856180028204e-05, + "loss": 3.1923, "step": 195700 }, { "epoch": 0.65, - "learning_rate": 1.755678391293686e-05, - "loss": 3.2103, + "learning_rate": 1.759201022225459e-05, + "loss": 3.2019, "step": 195800 }, { "epoch": 0.65, - "learning_rate": 1.7540214343944484e-05, - "loss": 3.2125, + "learning_rate": 1.757545864422714e-05, + "loss": 3.194, "step": 195900 }, { "epoch": 0.65, - "learning_rate": 1.7523644774952114e-05, - "loss": 3.2185, + "learning_rate": 1.7558907066199692e-05, + "loss": 3.1736, "step": 196000 }, { "epoch": 0.65, - "learning_rate": 1.7507075205959743e-05, - "loss": 3.2028, + "learning_rate": 1.7542355488172244e-05, + "loss": 3.2077, "step": 196100 }, { "epoch": 0.65, - "learning_rate": 1.7490505636967372e-05, - "loss": 3.1988, + "learning_rate": 1.7525803910144795e-05, + "loss": 3.1971, "step": 196200 }, { "epoch": 0.65, - "learning_rate": 1.7473936067975e-05, - "loss": 3.2054, + "learning_rate": 1.7509252332117347e-05, + "loss": 3.2082, "step": 196300 }, { "epoch": 0.65, - "learning_rate": 1.745736649898263e-05, - "loss": 3.2123, + "learning_rate": 1.74927007540899e-05, + "loss": 3.193, "step": 196400 }, { "epoch": 0.65, - "learning_rate": 1.744079692999026e-05, - "loss": 3.2197, + "learning_rate": 1.7476149176062447e-05, + "loss": 3.1967, "step": 196500 }, { "epoch": 0.65, - "learning_rate": 1.7424227360997885e-05, - "loss": 3.2052, + "learning_rate": 1.7459597598034995e-05, + "loss": 3.1989, "step": 196600 }, { "epoch": 0.65, - "learning_rate": 1.7407657792005515e-05, - "loss": 3.213, + "learning_rate": 1.7443046020007546e-05, + "loss": 3.2095, "step": 196700 }, { "epoch": 0.65, - "learning_rate": 1.7391088223013144e-05, - "loss": 3.2339, + "learning_rate": 1.7426494441980098e-05, + "loss": 3.2008, "step": 196800 }, { "epoch": 0.65, - "learning_rate": 1.7374518654020773e-05, - "loss": 3.2103, + "learning_rate": 1.740994286395265e-05, + "loss": 3.1905, "step": 196900 }, { "epoch": 0.65, - "learning_rate": 1.7357949085028402e-05, - "loss": 3.2076, + "learning_rate": 1.73933912859252e-05, + "loss": 3.186, "step": 197000 }, { "epoch": 0.65, - "learning_rate": 1.734137951603603e-05, - "loss": 3.2111, + "learning_rate": 1.7376839707897753e-05, + "loss": 3.2015, "step": 197100 }, { "epoch": 0.65, - "learning_rate": 1.7324809947043657e-05, - "loss": 3.2042, + "learning_rate": 1.7360288129870304e-05, + "loss": 3.2075, "step": 197200 }, { "epoch": 0.65, - "learning_rate": 1.7308240378051286e-05, - "loss": 3.2044, + "learning_rate": 1.7343736551842853e-05, + "loss": 3.2102, "step": 197300 }, { "epoch": 0.65, - "learning_rate": 1.7291670809058916e-05, - "loss": 3.2034, + "learning_rate": 1.7327184973815404e-05, + "loss": 3.2194, "step": 197400 }, { "epoch": 0.65, - "learning_rate": 1.7275101240066545e-05, - "loss": 3.2202, + "learning_rate": 1.7310633395787956e-05, + "loss": 3.18, "step": 197500 }, { "epoch": 0.65, - "learning_rate": 1.7258531671074174e-05, - "loss": 3.2144, + "learning_rate": 1.7294081817760507e-05, + "loss": 3.1919, "step": 197600 }, { - "epoch": 0.66, - "learning_rate": 1.7241962102081803e-05, - "loss": 3.2129, + "epoch": 0.65, + "learning_rate": 1.7277530239733056e-05, + "loss": 3.1882, "step": 197700 }, { - "epoch": 0.66, - "learning_rate": 1.722539253308943e-05, - "loss": 3.2161, + "epoch": 0.65, + "learning_rate": 1.7260978661705607e-05, + "loss": 3.2027, "step": 197800 }, { "epoch": 0.66, - "learning_rate": 1.7208822964097058e-05, - "loss": 3.1943, + "learning_rate": 1.724442708367816e-05, + "loss": 3.1725, "step": 197900 }, { "epoch": 0.66, - "learning_rate": 1.7192253395104687e-05, - "loss": 3.2116, + "learning_rate": 1.722787550565071e-05, + "loss": 3.1862, "step": 198000 }, { "epoch": 0.66, - "learning_rate": 1.7175683826112317e-05, - "loss": 3.2197, + "learning_rate": 1.721132392762326e-05, + "loss": 3.2106, "step": 198100 }, { "epoch": 0.66, - "learning_rate": 1.7159114257119946e-05, - "loss": 3.2022, + "learning_rate": 1.719477234959581e-05, + "loss": 3.1998, "step": 198200 }, { "epoch": 0.66, - "learning_rate": 1.7142544688127575e-05, - "loss": 3.2089, + "learning_rate": 1.7178220771568362e-05, + "loss": 3.2036, "step": 198300 }, { "epoch": 0.66, - "learning_rate": 1.71259751191352e-05, - "loss": 3.2023, + "learning_rate": 1.7161669193540913e-05, + "loss": 3.1837, "step": 198400 }, { "epoch": 0.66, - "learning_rate": 1.7109405550142834e-05, - "loss": 3.2181, + "learning_rate": 1.7145117615513465e-05, + "loss": 3.2088, "step": 198500 }, { "epoch": 0.66, - "learning_rate": 1.709283598115046e-05, - "loss": 3.205, + "learning_rate": 1.7128566037486017e-05, + "loss": 3.2003, "step": 198600 }, { "epoch": 0.66, - "learning_rate": 1.707626641215809e-05, - "loss": 3.2179, + "learning_rate": 1.7112014459458568e-05, + "loss": 3.1863, "step": 198700 }, { "epoch": 0.66, - "learning_rate": 1.7059696843165714e-05, - "loss": 3.201, + "learning_rate": 1.7095462881431116e-05, + "loss": 3.1906, "step": 198800 }, { "epoch": 0.66, - "learning_rate": 1.7043127274173347e-05, - "loss": 3.2126, + "learning_rate": 1.7078911303403665e-05, + "loss": 3.2116, "step": 198900 }, { "epoch": 0.66, - "learning_rate": 1.7026557705180973e-05, - "loss": 3.1959, + "learning_rate": 1.7062359725376216e-05, + "loss": 3.1982, "step": 199000 }, { "epoch": 0.66, - "learning_rate": 1.7009988136188602e-05, - "loss": 3.1999, + "learning_rate": 1.7045808147348768e-05, + "loss": 3.1876, "step": 199100 }, { "epoch": 0.66, - "learning_rate": 1.699341856719623e-05, - "loss": 3.2214, + "learning_rate": 1.702925656932132e-05, + "loss": 3.1977, "step": 199200 }, { "epoch": 0.66, - "learning_rate": 1.697684899820386e-05, - "loss": 3.2283, + "learning_rate": 1.701270499129387e-05, + "loss": 3.2028, "step": 199300 }, { "epoch": 0.66, - "learning_rate": 1.6960279429211486e-05, - "loss": 3.2203, + "learning_rate": 1.6996153413266423e-05, + "loss": 3.1859, "step": 199400 }, { "epoch": 0.66, - "learning_rate": 1.694370986021912e-05, - "loss": 3.1907, + "learning_rate": 1.6979601835238974e-05, + "loss": 3.1904, "step": 199500 }, { "epoch": 0.66, - "learning_rate": 1.6927140291226745e-05, - "loss": 3.1986, + "learning_rate": 1.6963050257211522e-05, + "loss": 3.1979, "step": 199600 }, { "epoch": 0.66, - "learning_rate": 1.6910570722234374e-05, - "loss": 3.1994, + "learning_rate": 1.6946498679184074e-05, + "loss": 3.1961, "step": 199700 }, { "epoch": 0.66, - "learning_rate": 1.6894001153242003e-05, - "loss": 3.1981, + "learning_rate": 1.6929947101156626e-05, + "loss": 3.1784, "step": 199800 }, { "epoch": 0.66, - "learning_rate": 1.6877431584249632e-05, - "loss": 3.2137, + "learning_rate": 1.6913395523129174e-05, + "loss": 3.2019, "step": 199900 }, { "epoch": 0.66, - "learning_rate": 1.6860862015257258e-05, - "loss": 3.204, + "learning_rate": 1.6896843945101725e-05, + "loss": 3.21, "step": 200000 }, { "epoch": 0.66, - "learning_rate": 1.684429244626489e-05, - "loss": 3.2166, + "learning_rate": 1.6880292367074277e-05, + "loss": 3.1996, "step": 200100 }, { "epoch": 0.66, - "learning_rate": 1.6827722877272516e-05, - "loss": 3.2157, + "learning_rate": 1.686374078904683e-05, + "loss": 3.2104, "step": 200200 }, { "epoch": 0.66, - "learning_rate": 1.6811153308280146e-05, - "loss": 3.2037, + "learning_rate": 1.684718921101938e-05, + "loss": 3.1973, "step": 200300 }, { "epoch": 0.66, - "learning_rate": 1.6794583739287775e-05, - "loss": 3.2089, + "learning_rate": 1.683063763299193e-05, + "loss": 3.1861, "step": 200400 }, { "epoch": 0.66, - "learning_rate": 1.6778014170295404e-05, - "loss": 3.2135, + "learning_rate": 1.681408605496448e-05, + "loss": 3.1908, "step": 200500 }, { "epoch": 0.66, - "learning_rate": 1.676144460130303e-05, - "loss": 3.2092, + "learning_rate": 1.6797534476937032e-05, + "loss": 3.1923, "step": 200600 }, { - "epoch": 0.67, - "learning_rate": 1.6744875032310662e-05, - "loss": 3.2038, + "epoch": 0.66, + "learning_rate": 1.6780982898909583e-05, + "loss": 3.1873, "step": 200700 }, { - "epoch": 0.67, - "learning_rate": 1.672830546331829e-05, - "loss": 3.2133, + "epoch": 0.66, + "learning_rate": 1.6764431320882135e-05, + "loss": 3.1916, "step": 200800 }, { "epoch": 0.67, - "learning_rate": 1.6711735894325918e-05, - "loss": 3.2193, + "learning_rate": 1.6747879742854687e-05, + "loss": 3.1892, "step": 200900 }, { "epoch": 0.67, - "learning_rate": 1.6695166325333547e-05, - "loss": 3.2117, + "learning_rate": 1.6731328164827235e-05, + "loss": 3.189, "step": 201000 }, { "epoch": 0.67, - "learning_rate": 1.6678596756341176e-05, - "loss": 3.2155, + "learning_rate": 1.6714776586799786e-05, + "loss": 3.1985, "step": 201100 }, { "epoch": 0.67, - "learning_rate": 1.6662027187348802e-05, - "loss": 3.1926, + "learning_rate": 1.6698225008772338e-05, + "loss": 3.1946, "step": 201200 }, { "epoch": 0.67, - "learning_rate": 1.6645457618356434e-05, - "loss": 3.2177, + "learning_rate": 1.6681673430744886e-05, + "loss": 3.1988, "step": 201300 }, { "epoch": 0.67, - "learning_rate": 1.662888804936406e-05, - "loss": 3.2024, + "learning_rate": 1.6665121852717438e-05, + "loss": 3.1992, "step": 201400 }, { "epoch": 0.67, - "learning_rate": 1.661231848037169e-05, - "loss": 3.2102, + "learning_rate": 1.664857027468999e-05, + "loss": 3.1898, "step": 201500 }, { "epoch": 0.67, - "learning_rate": 1.659574891137932e-05, - "loss": 3.2033, + "learning_rate": 1.663201869666254e-05, + "loss": 3.2034, "step": 201600 }, { "epoch": 0.67, - "learning_rate": 1.6579179342386948e-05, - "loss": 3.2061, + "learning_rate": 1.6615467118635093e-05, + "loss": 3.1876, "step": 201700 }, { "epoch": 0.67, - "learning_rate": 1.6562609773394574e-05, - "loss": 3.2203, + "learning_rate": 1.6598915540607644e-05, + "loss": 3.1985, "step": 201800 }, { "epoch": 0.67, - "learning_rate": 1.6546040204402206e-05, - "loss": 3.2093, + "learning_rate": 1.6582363962580196e-05, + "loss": 3.1994, "step": 201900 }, { "epoch": 0.67, - "learning_rate": 1.6529470635409832e-05, - "loss": 3.2131, + "learning_rate": 1.6565812384552744e-05, + "loss": 3.2095, "step": 202000 }, { "epoch": 0.67, - "learning_rate": 1.651290106641746e-05, - "loss": 3.1958, + "learning_rate": 1.6549260806525292e-05, + "loss": 3.1894, "step": 202100 }, { "epoch": 0.67, - "learning_rate": 1.649633149742509e-05, - "loss": 3.1999, + "learning_rate": 1.6532709228497844e-05, + "loss": 3.1941, "step": 202200 }, { "epoch": 0.67, - "learning_rate": 1.647976192843272e-05, - "loss": 3.2168, + "learning_rate": 1.6516157650470395e-05, + "loss": 3.1958, "step": 202300 }, { "epoch": 0.67, - "learning_rate": 1.6463192359440345e-05, - "loss": 3.2204, + "learning_rate": 1.6499606072442947e-05, + "loss": 3.1884, "step": 202400 }, { "epoch": 0.67, - "learning_rate": 1.6446622790447978e-05, - "loss": 3.1891, + "learning_rate": 1.64830544944155e-05, + "loss": 3.1787, "step": 202500 }, { "epoch": 0.67, - "learning_rate": 1.6430053221455604e-05, - "loss": 3.2116, + "learning_rate": 1.646650291638805e-05, + "loss": 3.194, "step": 202600 }, { "epoch": 0.67, - "learning_rate": 1.6413483652463233e-05, - "loss": 3.2116, + "learning_rate": 1.6449951338360602e-05, + "loss": 3.1915, "step": 202700 }, { "epoch": 0.67, - "learning_rate": 1.6396914083470862e-05, - "loss": 3.2156, + "learning_rate": 1.643339976033315e-05, + "loss": 3.1968, "step": 202800 }, { "epoch": 0.67, - "learning_rate": 1.638034451447849e-05, - "loss": 3.2012, + "learning_rate": 1.64168481823057e-05, + "loss": 3.1891, "step": 202900 }, { "epoch": 0.67, - "learning_rate": 1.6363774945486117e-05, - "loss": 3.2175, + "learning_rate": 1.6400296604278253e-05, + "loss": 3.2048, "step": 203000 }, { "epoch": 0.67, - "learning_rate": 1.6347205376493746e-05, - "loss": 3.2165, + "learning_rate": 1.6383745026250805e-05, + "loss": 3.184, "step": 203100 }, { "epoch": 0.67, - "learning_rate": 1.6330635807501376e-05, - "loss": 3.2112, + "learning_rate": 1.6367193448223356e-05, + "loss": 3.1904, "step": 203200 }, { "epoch": 0.67, - "learning_rate": 1.6314066238509005e-05, - "loss": 3.2194, + "learning_rate": 1.6350641870195905e-05, + "loss": 3.189, "step": 203300 }, { "epoch": 0.67, - "learning_rate": 1.629749666951663e-05, - "loss": 3.217, + "learning_rate": 1.6334090292168456e-05, + "loss": 3.1874, "step": 203400 }, { "epoch": 0.67, - "learning_rate": 1.6280927100524263e-05, - "loss": 3.2142, + "learning_rate": 1.6317538714141008e-05, + "loss": 3.1954, "step": 203500 }, { "epoch": 0.67, - "learning_rate": 1.626435753153189e-05, - "loss": 3.2103, + "learning_rate": 1.6300987136113556e-05, + "loss": 3.1799, "step": 203600 }, { - "epoch": 0.68, - "learning_rate": 1.624778796253952e-05, - "loss": 3.2168, + "epoch": 0.67, + "learning_rate": 1.6284435558086108e-05, + "loss": 3.1936, "step": 203700 }, { - "epoch": 0.68, - "learning_rate": 1.6231218393547148e-05, - "loss": 3.2153, + "epoch": 0.67, + "learning_rate": 1.626788398005866e-05, + "loss": 3.1993, "step": 203800 }, { - "epoch": 0.68, - "learning_rate": 1.6214648824554777e-05, - "loss": 3.2123, + "epoch": 0.67, + "learning_rate": 1.625133240203121e-05, + "loss": 3.2068, "step": 203900 }, { "epoch": 0.68, - "learning_rate": 1.6198079255562403e-05, - "loss": 3.2171, + "learning_rate": 1.6234780824003762e-05, + "loss": 3.1989, "step": 204000 }, { "epoch": 0.68, - "learning_rate": 1.6181509686570035e-05, - "loss": 3.2188, + "learning_rate": 1.6218229245976314e-05, + "loss": 3.1956, "step": 204100 }, { "epoch": 0.68, - "learning_rate": 1.616494011757766e-05, - "loss": 3.2026, + "learning_rate": 1.6201677667948866e-05, + "loss": 3.196, "step": 204200 }, { "epoch": 0.68, - "learning_rate": 1.614837054858529e-05, - "loss": 3.1926, + "learning_rate": 1.6185126089921414e-05, + "loss": 3.1879, "step": 204300 }, { "epoch": 0.68, - "learning_rate": 1.613180097959292e-05, - "loss": 3.2184, + "learning_rate": 1.6168574511893962e-05, + "loss": 3.186, "step": 204400 }, { "epoch": 0.68, - "learning_rate": 1.611523141060055e-05, - "loss": 3.2056, + "learning_rate": 1.6152022933866514e-05, + "loss": 3.1977, "step": 204500 }, { "epoch": 0.68, - "learning_rate": 1.6098661841608174e-05, - "loss": 3.2104, + "learning_rate": 1.6135471355839065e-05, + "loss": 3.2032, "step": 204600 }, { "epoch": 0.68, - "learning_rate": 1.6082092272615807e-05, - "loss": 3.2201, + "learning_rate": 1.6118919777811617e-05, + "loss": 3.1901, "step": 204700 }, { "epoch": 0.68, - "learning_rate": 1.6065522703623433e-05, - "loss": 3.2007, + "learning_rate": 1.610236819978417e-05, + "loss": 3.2021, "step": 204800 }, { "epoch": 0.68, - "learning_rate": 1.6048953134631062e-05, - "loss": 3.2181, + "learning_rate": 1.608581662175672e-05, + "loss": 3.1837, "step": 204900 }, { "epoch": 0.68, - "learning_rate": 1.603238356563869e-05, - "loss": 3.1903, + "learning_rate": 1.606926504372927e-05, + "loss": 3.1848, "step": 205000 }, { "epoch": 0.68, - "learning_rate": 1.601581399664632e-05, - "loss": 3.2141, + "learning_rate": 1.605271346570182e-05, + "loss": 3.1979, "step": 205100 }, { "epoch": 0.68, - "learning_rate": 1.5999244427653946e-05, - "loss": 3.2096, + "learning_rate": 1.603616188767437e-05, + "loss": 3.2023, "step": 205200 }, { "epoch": 0.68, - "learning_rate": 1.598267485866158e-05, - "loss": 3.205, + "learning_rate": 1.6019610309646923e-05, + "loss": 3.1872, "step": 205300 }, { "epoch": 0.68, - "learning_rate": 1.5966105289669205e-05, - "loss": 3.2026, + "learning_rate": 1.6003058731619475e-05, + "loss": 3.212, "step": 205400 }, { "epoch": 0.68, - "learning_rate": 1.5949535720676834e-05, - "loss": 3.2046, + "learning_rate": 1.5986507153592023e-05, + "loss": 3.1928, "step": 205500 }, { "epoch": 0.68, - "learning_rate": 1.5932966151684463e-05, - "loss": 3.2164, + "learning_rate": 1.5969955575564574e-05, + "loss": 3.1859, "step": 205600 }, { "epoch": 0.68, - "learning_rate": 1.5916396582692092e-05, - "loss": 3.2124, + "learning_rate": 1.5953403997537126e-05, + "loss": 3.1967, "step": 205700 }, { "epoch": 0.68, - "learning_rate": 1.5899827013699718e-05, - "loss": 3.2063, + "learning_rate": 1.5936852419509678e-05, + "loss": 3.1958, "step": 205800 }, { "epoch": 0.68, - "learning_rate": 1.588325744470735e-05, - "loss": 3.22, + "learning_rate": 1.5920300841482226e-05, + "loss": 3.1918, "step": 205900 }, { "epoch": 0.68, - "learning_rate": 1.5866687875714977e-05, - "loss": 3.2044, + "learning_rate": 1.5903749263454777e-05, + "loss": 3.1804, "step": 206000 }, { "epoch": 0.68, - "learning_rate": 1.5850118306722606e-05, - "loss": 3.2041, + "learning_rate": 1.588719768542733e-05, + "loss": 3.2003, "step": 206100 }, { "epoch": 0.68, - "learning_rate": 1.5833548737730235e-05, - "loss": 3.2142, + "learning_rate": 1.587064610739988e-05, + "loss": 3.187, "step": 206200 }, { "epoch": 0.68, - "learning_rate": 1.5816979168737864e-05, - "loss": 3.2063, + "learning_rate": 1.5854094529372432e-05, + "loss": 3.1814, "step": 206300 }, { "epoch": 0.68, - "learning_rate": 1.580040959974549e-05, - "loss": 3.2229, + "learning_rate": 1.5837542951344984e-05, + "loss": 3.1863, "step": 206400 }, { "epoch": 0.68, - "learning_rate": 1.5783840030753123e-05, - "loss": 3.2208, + "learning_rate": 1.5820991373317535e-05, + "loss": 3.1852, "step": 206500 }, { "epoch": 0.68, - "learning_rate": 1.576727046176075e-05, - "loss": 3.2127, + "learning_rate": 1.5804439795290084e-05, + "loss": 3.1979, "step": 206600 }, { "epoch": 0.68, - "learning_rate": 1.5750700892768378e-05, - "loss": 3.2129, + "learning_rate": 1.5787888217262632e-05, + "loss": 3.2016, "step": 206700 }, { - "epoch": 0.69, - "learning_rate": 1.5734131323776007e-05, - "loss": 3.2164, + "epoch": 0.68, + "learning_rate": 1.5771336639235183e-05, + "loss": 3.1792, "step": 206800 }, { - "epoch": 0.69, - "learning_rate": 1.5717561754783636e-05, - "loss": 3.2164, + "epoch": 0.68, + "learning_rate": 1.5754785061207735e-05, + "loss": 3.1935, "step": 206900 }, { "epoch": 0.69, - "learning_rate": 1.5700992185791262e-05, - "loss": 3.2027, + "learning_rate": 1.5738233483180287e-05, + "loss": 3.1911, "step": 207000 }, { "epoch": 0.69, - "learning_rate": 1.5684422616798894e-05, - "loss": 3.206, + "learning_rate": 1.5721681905152838e-05, + "loss": 3.1977, "step": 207100 }, { "epoch": 0.69, - "learning_rate": 1.566785304780652e-05, - "loss": 3.2023, + "learning_rate": 1.570513032712539e-05, + "loss": 3.1976, "step": 207200 }, { "epoch": 0.69, - "learning_rate": 1.565128347881415e-05, - "loss": 3.2103, + "learning_rate": 1.568857874909794e-05, + "loss": 3.1924, "step": 207300 }, { "epoch": 0.69, - "learning_rate": 1.563471390982178e-05, - "loss": 3.217, + "learning_rate": 1.567202717107049e-05, + "loss": 3.1993, "step": 207400 }, { "epoch": 0.69, - "learning_rate": 1.5618144340829408e-05, - "loss": 3.2069, + "learning_rate": 1.565547559304304e-05, + "loss": 3.1924, "step": 207500 }, { "epoch": 0.69, - "learning_rate": 1.5601574771837034e-05, - "loss": 3.2172, + "learning_rate": 1.5638924015015593e-05, + "loss": 3.1846, "step": 207600 }, { "epoch": 0.69, - "learning_rate": 1.5585005202844663e-05, - "loss": 3.213, + "learning_rate": 1.562237243698814e-05, + "loss": 3.1987, "step": 207700 }, { "epoch": 0.69, - "learning_rate": 1.5568435633852292e-05, - "loss": 3.1998, + "learning_rate": 1.5605820858960693e-05, + "loss": 3.1848, "step": 207800 }, { "epoch": 0.69, - "learning_rate": 1.555186606485992e-05, - "loss": 3.2063, + "learning_rate": 1.5589269280933244e-05, + "loss": 3.2008, "step": 207900 }, { "epoch": 0.69, - "learning_rate": 1.553529649586755e-05, - "loss": 3.2105, + "learning_rate": 1.5572717702905796e-05, + "loss": 3.1752, "step": 208000 }, { "epoch": 0.69, - "learning_rate": 1.551872692687518e-05, - "loss": 3.2186, + "learning_rate": 1.5556166124878348e-05, + "loss": 3.2012, "step": 208100 }, { "epoch": 0.69, - "learning_rate": 1.550215735788281e-05, - "loss": 3.2136, + "learning_rate": 1.55396145468509e-05, + "loss": 3.1953, "step": 208200 }, { "epoch": 0.69, - "learning_rate": 1.5485587788890435e-05, - "loss": 3.1979, + "learning_rate": 1.5523062968823447e-05, + "loss": 3.1911, "step": 208300 }, { "epoch": 0.69, - "learning_rate": 1.5469018219898064e-05, - "loss": 3.2201, + "learning_rate": 1.5506511390796e-05, + "loss": 3.1937, "step": 208400 }, { "epoch": 0.69, - "learning_rate": 1.5452448650905693e-05, - "loss": 3.2041, + "learning_rate": 1.548995981276855e-05, + "loss": 3.2045, "step": 208500 }, { "epoch": 0.69, - "learning_rate": 1.5435879081913322e-05, - "loss": 3.2177, + "learning_rate": 1.5473408234741102e-05, + "loss": 3.1828, "step": 208600 }, { "epoch": 0.69, - "learning_rate": 1.541930951292095e-05, - "loss": 3.2171, + "learning_rate": 1.5456856656713654e-05, + "loss": 3.1918, "step": 208700 }, { "epoch": 0.69, - "learning_rate": 1.540273994392858e-05, - "loss": 3.2134, + "learning_rate": 1.5440305078686202e-05, + "loss": 3.1808, "step": 208800 }, { "epoch": 0.69, - "learning_rate": 1.5386170374936207e-05, - "loss": 3.2089, + "learning_rate": 1.5423753500658754e-05, + "loss": 3.2055, "step": 208900 }, { "epoch": 0.69, - "learning_rate": 1.5369600805943836e-05, - "loss": 3.2007, + "learning_rate": 1.5407201922631305e-05, + "loss": 3.19, "step": 209000 }, { "epoch": 0.69, - "learning_rate": 1.5353031236951465e-05, - "loss": 3.2131, + "learning_rate": 1.5390650344603853e-05, + "loss": 3.1914, "step": 209100 }, { "epoch": 0.69, - "learning_rate": 1.5336461667959094e-05, - "loss": 3.2048, + "learning_rate": 1.5374098766576405e-05, + "loss": 3.1888, "step": 209200 }, { "epoch": 0.69, - "learning_rate": 1.5319892098966723e-05, - "loss": 3.2046, + "learning_rate": 1.5357547188548957e-05, + "loss": 3.1941, "step": 209300 }, { "epoch": 0.69, - "learning_rate": 1.5303322529974353e-05, - "loss": 3.2242, + "learning_rate": 1.5340995610521508e-05, + "loss": 3.1995, "step": 209400 }, { "epoch": 0.69, - "learning_rate": 1.528675296098198e-05, - "loss": 3.2035, + "learning_rate": 1.532444403249406e-05, + "loss": 3.1932, "step": 209500 }, { "epoch": 0.69, - "learning_rate": 1.5270183391989608e-05, - "loss": 3.2067, + "learning_rate": 1.530789245446661e-05, + "loss": 3.1977, "step": 209600 }, { "epoch": 0.69, - "learning_rate": 1.5253613822997237e-05, - "loss": 3.2158, + "learning_rate": 1.5291340876439163e-05, + "loss": 3.186, "step": 209700 }, { - "epoch": 0.7, - "learning_rate": 1.5237044254004864e-05, - "loss": 3.2135, + "epoch": 0.69, + "learning_rate": 1.527478929841171e-05, + "loss": 3.1783, "step": 209800 }, { - "epoch": 0.7, - "learning_rate": 1.5220474685012495e-05, - "loss": 3.21, + "epoch": 0.69, + "learning_rate": 1.5258237720384261e-05, + "loss": 3.1956, "step": 209900 }, { "epoch": 0.7, - "learning_rate": 1.5203905116020123e-05, - "loss": 3.2142, + "learning_rate": 1.5241686142356813e-05, + "loss": 3.1779, "step": 210000 }, { "epoch": 0.7, - "learning_rate": 1.518733554702775e-05, - "loss": 3.2031, + "learning_rate": 1.5225134564329363e-05, + "loss": 3.1904, "step": 210100 }, { "epoch": 0.7, - "learning_rate": 1.5170765978035381e-05, - "loss": 3.2151, + "learning_rate": 1.5208582986301914e-05, + "loss": 3.1958, "step": 210200 }, { "epoch": 0.7, - "learning_rate": 1.5154196409043009e-05, - "loss": 3.2074, + "learning_rate": 1.5192031408274466e-05, + "loss": 3.181, "step": 210300 }, { "epoch": 0.7, - "learning_rate": 1.5137626840050636e-05, - "loss": 3.2047, + "learning_rate": 1.5175479830247016e-05, + "loss": 3.1934, "step": 210400 }, { "epoch": 0.7, - "learning_rate": 1.5121057271058267e-05, - "loss": 3.2033, + "learning_rate": 1.5158928252219567e-05, + "loss": 3.2074, "step": 210500 }, { "epoch": 0.7, - "learning_rate": 1.5104487702065895e-05, - "loss": 3.2055, + "learning_rate": 1.5142376674192119e-05, + "loss": 3.1848, "step": 210600 }, { "epoch": 0.7, - "learning_rate": 1.5087918133073522e-05, - "loss": 3.222, + "learning_rate": 1.512582509616467e-05, + "loss": 3.1855, "step": 210700 }, { "epoch": 0.7, - "learning_rate": 1.5071348564081153e-05, - "loss": 3.2139, + "learning_rate": 1.510927351813722e-05, + "loss": 3.1973, "step": 210800 }, { "epoch": 0.7, - "learning_rate": 1.505477899508878e-05, - "loss": 3.2039, + "learning_rate": 1.5092721940109772e-05, + "loss": 3.1893, "step": 210900 }, { "epoch": 0.7, - "learning_rate": 1.5038209426096408e-05, - "loss": 3.2032, + "learning_rate": 1.5076170362082324e-05, + "loss": 3.1896, "step": 211000 }, { "epoch": 0.7, - "learning_rate": 1.5021639857104039e-05, - "loss": 3.2188, + "learning_rate": 1.5059618784054872e-05, + "loss": 3.205, "step": 211100 }, { "epoch": 0.7, - "learning_rate": 1.5005070288111666e-05, - "loss": 3.2164, + "learning_rate": 1.5043067206027422e-05, + "loss": 3.1947, "step": 211200 }, { "epoch": 0.7, - "learning_rate": 1.4988500719119294e-05, - "loss": 3.1936, + "learning_rate": 1.5026515627999973e-05, + "loss": 3.1914, "step": 211300 }, { "epoch": 0.7, - "learning_rate": 1.4971931150126925e-05, - "loss": 3.2153, + "learning_rate": 1.5009964049972525e-05, + "loss": 3.1995, "step": 211400 }, { "epoch": 0.7, - "learning_rate": 1.4955361581134552e-05, - "loss": 3.2276, + "learning_rate": 1.4993412471945076e-05, + "loss": 3.1803, "step": 211500 }, { "epoch": 0.7, - "learning_rate": 1.493879201214218e-05, - "loss": 3.2091, + "learning_rate": 1.4976860893917626e-05, + "loss": 3.1847, "step": 211600 }, { "epoch": 0.7, - "learning_rate": 1.492222244314981e-05, - "loss": 3.2166, + "learning_rate": 1.4960309315890178e-05, + "loss": 3.1987, "step": 211700 }, { "epoch": 0.7, - "learning_rate": 1.4905652874157438e-05, - "loss": 3.2097, + "learning_rate": 1.494375773786273e-05, + "loss": 3.1945, "step": 211800 }, { "epoch": 0.7, - "learning_rate": 1.4889083305165066e-05, - "loss": 3.2009, + "learning_rate": 1.492720615983528e-05, + "loss": 3.193, "step": 211900 }, { "epoch": 0.7, - "learning_rate": 1.4872513736172693e-05, - "loss": 3.2078, + "learning_rate": 1.4910654581807831e-05, + "loss": 3.1861, "step": 212000 }, { "epoch": 0.7, - "learning_rate": 1.4855944167180324e-05, - "loss": 3.1974, + "learning_rate": 1.4894103003780383e-05, + "loss": 3.1931, "step": 212100 }, { "epoch": 0.7, - "learning_rate": 1.4839374598187952e-05, - "loss": 3.2081, + "learning_rate": 1.4877551425752931e-05, + "loss": 3.1948, "step": 212200 }, { "epoch": 0.7, - "learning_rate": 1.482280502919558e-05, - "loss": 3.2127, + "learning_rate": 1.4860999847725483e-05, + "loss": 3.1972, "step": 212300 }, { "epoch": 0.7, - "learning_rate": 1.480623546020321e-05, - "loss": 3.2013, + "learning_rate": 1.4844448269698032e-05, + "loss": 3.2017, "step": 212400 }, { "epoch": 0.7, - "learning_rate": 1.4789665891210838e-05, - "loss": 3.198, + "learning_rate": 1.4827896691670584e-05, + "loss": 3.1915, "step": 212500 }, { "epoch": 0.7, - "learning_rate": 1.4773096322218467e-05, - "loss": 3.213, + "learning_rate": 1.4811345113643136e-05, + "loss": 3.1818, "step": 212600 }, { "epoch": 0.7, - "learning_rate": 1.4756526753226096e-05, - "loss": 3.217, + "learning_rate": 1.4794793535615686e-05, + "loss": 3.1902, "step": 212700 }, { - "epoch": 0.71, - "learning_rate": 1.4739957184233724e-05, - "loss": 3.2223, + "epoch": 0.7, + "learning_rate": 1.4778241957588237e-05, + "loss": 3.1895, "step": 212800 }, { - "epoch": 0.71, - "learning_rate": 1.4723387615241353e-05, - "loss": 3.2084, + "epoch": 0.7, + "learning_rate": 1.4761690379560789e-05, + "loss": 3.1919, "step": 212900 }, { "epoch": 0.71, - "learning_rate": 1.4706818046248982e-05, - "loss": 3.2058, + "learning_rate": 1.474513880153334e-05, + "loss": 3.1967, "step": 213000 }, { "epoch": 0.71, - "learning_rate": 1.469024847725661e-05, - "loss": 3.2136, + "learning_rate": 1.472858722350589e-05, + "loss": 3.1891, "step": 213100 }, { "epoch": 0.71, - "learning_rate": 1.4673678908264239e-05, - "loss": 3.2128, + "learning_rate": 1.4712035645478442e-05, + "loss": 3.1758, "step": 213200 }, { "epoch": 0.71, - "learning_rate": 1.4657109339271868e-05, - "loss": 3.2026, + "learning_rate": 1.469548406745099e-05, + "loss": 3.2071, "step": 213300 }, { "epoch": 0.71, - "learning_rate": 1.4640539770279495e-05, - "loss": 3.2095, + "learning_rate": 1.4678932489423542e-05, + "loss": 3.2125, "step": 213400 }, { "epoch": 0.71, - "learning_rate": 1.4623970201287125e-05, - "loss": 3.2105, + "learning_rate": 1.4662380911396093e-05, + "loss": 3.1862, "step": 213500 }, { "epoch": 0.71, - "learning_rate": 1.4607400632294754e-05, - "loss": 3.2065, + "learning_rate": 1.4645829333368643e-05, + "loss": 3.1975, "step": 213600 }, { "epoch": 0.71, - "learning_rate": 1.4590831063302381e-05, - "loss": 3.2127, + "learning_rate": 1.4629277755341195e-05, + "loss": 3.1916, "step": 213700 }, { "epoch": 0.71, - "learning_rate": 1.457426149431001e-05, - "loss": 3.2109, + "learning_rate": 1.4612726177313746e-05, + "loss": 3.1908, "step": 213800 }, { "epoch": 0.71, - "learning_rate": 1.455769192531764e-05, - "loss": 3.2129, + "learning_rate": 1.4596174599286296e-05, + "loss": 3.1773, "step": 213900 }, { "epoch": 0.71, - "learning_rate": 1.4541122356325267e-05, - "loss": 3.2073, + "learning_rate": 1.4579623021258848e-05, + "loss": 3.2031, "step": 214000 }, { "epoch": 0.71, - "learning_rate": 1.4524552787332896e-05, - "loss": 3.204, + "learning_rate": 1.45630714432314e-05, + "loss": 3.1875, "step": 214100 }, { "epoch": 0.71, - "learning_rate": 1.4507983218340526e-05, - "loss": 3.1946, + "learning_rate": 1.4546519865203951e-05, + "loss": 3.1997, "step": 214200 }, { "epoch": 0.71, - "learning_rate": 1.4491413649348153e-05, - "loss": 3.1985, + "learning_rate": 1.4529968287176501e-05, + "loss": 3.2021, "step": 214300 }, { "epoch": 0.71, - "learning_rate": 1.4474844080355782e-05, - "loss": 3.2131, + "learning_rate": 1.451341670914905e-05, + "loss": 3.178, "step": 214400 }, { "epoch": 0.71, - "learning_rate": 1.4458274511363412e-05, - "loss": 3.205, + "learning_rate": 1.44968651311216e-05, + "loss": 3.1976, "step": 214500 }, { "epoch": 0.71, - "learning_rate": 1.4441704942371039e-05, - "loss": 3.21, + "learning_rate": 1.4480313553094152e-05, + "loss": 3.2022, "step": 214600 }, { "epoch": 0.71, - "learning_rate": 1.4425135373378668e-05, - "loss": 3.1882, + "learning_rate": 1.4463761975066702e-05, + "loss": 3.1962, "step": 214700 }, { "epoch": 0.71, - "learning_rate": 1.4408565804386297e-05, - "loss": 3.2093, + "learning_rate": 1.4447210397039254e-05, + "loss": 3.1908, "step": 214800 }, { "epoch": 0.71, - "learning_rate": 1.4391996235393927e-05, - "loss": 3.1959, + "learning_rate": 1.4430658819011805e-05, + "loss": 3.189, "step": 214900 }, { "epoch": 0.71, - "learning_rate": 1.4375426666401554e-05, - "loss": 3.2058, + "learning_rate": 1.4414107240984357e-05, + "loss": 3.1929, "step": 215000 }, { "epoch": 0.71, - "learning_rate": 1.4358857097409183e-05, - "loss": 3.2058, + "learning_rate": 1.4397555662956907e-05, + "loss": 3.2004, "step": 215100 }, { "epoch": 0.71, - "learning_rate": 1.4342287528416813e-05, - "loss": 3.1981, + "learning_rate": 1.4381004084929459e-05, + "loss": 3.1882, "step": 215200 }, { "epoch": 0.71, - "learning_rate": 1.432571795942444e-05, - "loss": 3.2173, + "learning_rate": 1.436445250690201e-05, + "loss": 3.1882, "step": 215300 }, { "epoch": 0.71, - "learning_rate": 1.430914839043207e-05, - "loss": 3.1971, + "learning_rate": 1.434790092887456e-05, + "loss": 3.1888, "step": 215400 }, { "epoch": 0.71, - "learning_rate": 1.4292578821439699e-05, - "loss": 3.2072, + "learning_rate": 1.433134935084711e-05, + "loss": 3.1907, "step": 215500 }, { "epoch": 0.71, - "learning_rate": 1.4276009252447326e-05, - "loss": 3.2008, + "learning_rate": 1.431479777281966e-05, + "loss": 3.1913, "step": 215600 }, { "epoch": 0.71, - "learning_rate": 1.4259439683454955e-05, - "loss": 3.1914, + "learning_rate": 1.4298246194792212e-05, + "loss": 3.1941, "step": 215700 }, { - "epoch": 0.72, - "learning_rate": 1.4242870114462584e-05, - "loss": 3.1974, + "epoch": 0.71, + "learning_rate": 1.4281694616764763e-05, + "loss": 3.1988, "step": 215800 }, { - "epoch": 0.72, - "learning_rate": 1.4226300545470212e-05, - "loss": 3.1991, + "epoch": 0.71, + "learning_rate": 1.4265143038737313e-05, + "loss": 3.1936, "step": 215900 }, { "epoch": 0.72, - "learning_rate": 1.4209730976477841e-05, - "loss": 3.1959, + "learning_rate": 1.4248591460709865e-05, + "loss": 3.1952, "step": 216000 }, { "epoch": 0.72, - "learning_rate": 1.419316140748547e-05, - "loss": 3.2113, + "learning_rate": 1.4232039882682416e-05, + "loss": 3.1973, "step": 216100 }, { "epoch": 0.72, - "learning_rate": 1.4176591838493098e-05, - "loss": 3.1974, + "learning_rate": 1.4215488304654966e-05, + "loss": 3.1929, "step": 216200 }, { "epoch": 0.72, - "learning_rate": 1.4160022269500725e-05, - "loss": 3.2075, + "learning_rate": 1.4198936726627518e-05, + "loss": 3.1899, "step": 216300 }, { "epoch": 0.72, - "learning_rate": 1.4143452700508356e-05, - "loss": 3.2106, + "learning_rate": 1.418238514860007e-05, + "loss": 3.2022, "step": 216400 }, { "epoch": 0.72, - "learning_rate": 1.4126883131515984e-05, - "loss": 3.2003, + "learning_rate": 1.4165833570572621e-05, + "loss": 3.1831, "step": 216500 }, { "epoch": 0.72, - "learning_rate": 1.4110313562523611e-05, - "loss": 3.1879, + "learning_rate": 1.4149281992545169e-05, + "loss": 3.1919, "step": 216600 }, { "epoch": 0.72, - "learning_rate": 1.4093743993531242e-05, - "loss": 3.2126, + "learning_rate": 1.4132730414517719e-05, + "loss": 3.1754, "step": 216700 }, { "epoch": 0.72, - "learning_rate": 1.407717442453887e-05, - "loss": 3.2016, + "learning_rate": 1.411617883649027e-05, + "loss": 3.2042, "step": 216800 }, { "epoch": 0.72, - "learning_rate": 1.4060604855546497e-05, - "loss": 3.211, + "learning_rate": 1.4099627258462822e-05, + "loss": 3.1876, "step": 216900 }, { "epoch": 0.72, - "learning_rate": 1.4044035286554128e-05, - "loss": 3.1997, + "learning_rate": 1.4083075680435374e-05, + "loss": 3.1844, "step": 217000 }, { "epoch": 0.72, - "learning_rate": 1.4027465717561756e-05, - "loss": 3.2103, + "learning_rate": 1.4066524102407924e-05, + "loss": 3.1868, "step": 217100 }, { "epoch": 0.72, - "learning_rate": 1.4010896148569383e-05, - "loss": 3.196, + "learning_rate": 1.4049972524380475e-05, + "loss": 3.1826, "step": 217200 }, { "epoch": 0.72, - "learning_rate": 1.3994326579577014e-05, - "loss": 3.2021, + "learning_rate": 1.4033420946353027e-05, + "loss": 3.1919, "step": 217300 }, { "epoch": 0.72, - "learning_rate": 1.3977757010584642e-05, - "loss": 3.2191, + "learning_rate": 1.4016869368325577e-05, + "loss": 3.1802, "step": 217400 }, { "epoch": 0.72, - "learning_rate": 1.3961187441592269e-05, - "loss": 3.2132, + "learning_rate": 1.4000317790298128e-05, + "loss": 3.1847, "step": 217500 }, { "epoch": 0.72, - "learning_rate": 1.39446178725999e-05, - "loss": 3.2086, + "learning_rate": 1.398376621227068e-05, + "loss": 3.194, "step": 217600 }, { "epoch": 0.72, - "learning_rate": 1.3928048303607527e-05, - "loss": 3.2059, + "learning_rate": 1.3967214634243228e-05, + "loss": 3.1859, "step": 217700 }, { "epoch": 0.72, - "learning_rate": 1.3911478734615155e-05, - "loss": 3.1954, + "learning_rate": 1.395066305621578e-05, + "loss": 3.1873, "step": 217800 }, { "epoch": 0.72, - "learning_rate": 1.3894909165622786e-05, - "loss": 3.2142, + "learning_rate": 1.393411147818833e-05, + "loss": 3.2053, "step": 217900 }, { "epoch": 0.72, - "learning_rate": 1.3878339596630413e-05, - "loss": 3.2026, + "learning_rate": 1.3917559900160881e-05, + "loss": 3.2018, "step": 218000 }, { "epoch": 0.72, - "learning_rate": 1.3861770027638041e-05, - "loss": 3.2073, + "learning_rate": 1.3901008322133433e-05, + "loss": 3.1998, "step": 218100 }, { "epoch": 0.72, - "learning_rate": 1.3845200458645672e-05, - "loss": 3.212, + "learning_rate": 1.3884456744105983e-05, + "loss": 3.204, "step": 218200 }, { "epoch": 0.72, - "learning_rate": 1.38286308896533e-05, - "loss": 3.1912, + "learning_rate": 1.3867905166078534e-05, + "loss": 3.1859, "step": 218300 }, { "epoch": 0.72, - "learning_rate": 1.3812061320660927e-05, - "loss": 3.211, + "learning_rate": 1.3851353588051086e-05, + "loss": 3.1933, "step": 218400 }, { "epoch": 0.72, - "learning_rate": 1.3795491751668558e-05, - "loss": 3.1964, + "learning_rate": 1.3834802010023638e-05, + "loss": 3.1858, "step": 218500 }, { "epoch": 0.72, - "learning_rate": 1.3778922182676185e-05, - "loss": 3.2132, + "learning_rate": 1.3818250431996188e-05, + "loss": 3.1976, "step": 218600 }, { "epoch": 0.72, - "learning_rate": 1.3762352613683813e-05, - "loss": 3.1995, + "learning_rate": 1.380169885396874e-05, + "loss": 3.1973, "step": 218700 }, { - "epoch": 0.73, - "learning_rate": 1.3745783044691444e-05, - "loss": 3.2109, + "epoch": 0.72, + "learning_rate": 1.3785147275941287e-05, + "loss": 3.1992, "step": 218800 }, { - "epoch": 0.73, - "learning_rate": 1.3729213475699071e-05, - "loss": 3.2125, + "epoch": 0.72, + "learning_rate": 1.3768595697913839e-05, + "loss": 3.192, "step": 218900 }, { - "epoch": 0.73, - "learning_rate": 1.3712643906706699e-05, - "loss": 3.2031, + "epoch": 0.72, + "learning_rate": 1.3752044119886389e-05, + "loss": 3.1931, "step": 219000 }, { "epoch": 0.73, - "learning_rate": 1.369607433771433e-05, - "loss": 3.1986, + "learning_rate": 1.373549254185894e-05, + "loss": 3.1723, "step": 219100 }, { "epoch": 0.73, - "learning_rate": 1.3679504768721957e-05, - "loss": 3.1981, + "learning_rate": 1.3718940963831492e-05, + "loss": 3.195, "step": 219200 }, { "epoch": 0.73, - "learning_rate": 1.3662935199729585e-05, - "loss": 3.2263, + "learning_rate": 1.3702389385804044e-05, + "loss": 3.1847, "step": 219300 }, { "epoch": 0.73, - "learning_rate": 1.3646365630737216e-05, - "loss": 3.2184, + "learning_rate": 1.3685837807776594e-05, + "loss": 3.1779, "step": 219400 }, { "epoch": 0.73, - "learning_rate": 1.3629796061744843e-05, - "loss": 3.2163, + "learning_rate": 1.3669286229749145e-05, + "loss": 3.1967, "step": 219500 }, { "epoch": 0.73, - "learning_rate": 1.361322649275247e-05, - "loss": 3.1977, + "learning_rate": 1.3652734651721697e-05, + "loss": 3.1947, "step": 219600 }, { "epoch": 0.73, - "learning_rate": 1.3596656923760101e-05, - "loss": 3.2052, + "learning_rate": 1.3636183073694247e-05, + "loss": 3.2029, "step": 219700 }, { "epoch": 0.73, - "learning_rate": 1.3580087354767729e-05, - "loss": 3.197, + "learning_rate": 1.3619631495666798e-05, + "loss": 3.1816, "step": 219800 }, { "epoch": 0.73, - "learning_rate": 1.3563517785775356e-05, - "loss": 3.2158, + "learning_rate": 1.360307991763935e-05, + "loss": 3.1978, "step": 219900 }, { "epoch": 0.73, - "learning_rate": 1.3546948216782987e-05, - "loss": 3.2057, + "learning_rate": 1.3586528339611898e-05, + "loss": 3.1977, "step": 220000 }, { "epoch": 0.73, - "learning_rate": 1.3530378647790615e-05, - "loss": 3.2018, + "learning_rate": 1.356997676158445e-05, + "loss": 3.189, "step": 220100 }, { "epoch": 0.73, - "learning_rate": 1.3513809078798242e-05, - "loss": 3.2021, + "learning_rate": 1.3553425183557e-05, + "loss": 3.1977, "step": 220200 }, { "epoch": 0.73, - "learning_rate": 1.3497239509805873e-05, - "loss": 3.2095, + "learning_rate": 1.3536873605529551e-05, + "loss": 3.1867, "step": 220300 }, { "epoch": 0.73, - "learning_rate": 1.34806699408135e-05, - "loss": 3.2058, + "learning_rate": 1.3520322027502103e-05, + "loss": 3.1839, "step": 220400 }, { "epoch": 0.73, - "learning_rate": 1.3464100371821128e-05, - "loss": 3.2061, + "learning_rate": 1.3503770449474654e-05, + "loss": 3.2075, "step": 220500 }, { "epoch": 0.73, - "learning_rate": 1.3447530802828756e-05, - "loss": 3.2059, + "learning_rate": 1.3487218871447204e-05, + "loss": 3.1827, "step": 220600 }, { "epoch": 0.73, - "learning_rate": 1.3430961233836387e-05, - "loss": 3.2033, + "learning_rate": 1.3470667293419756e-05, + "loss": 3.2037, "step": 220700 }, { "epoch": 0.73, - "learning_rate": 1.3414391664844014e-05, - "loss": 3.2032, + "learning_rate": 1.3454115715392308e-05, + "loss": 3.1921, "step": 220800 }, { "epoch": 0.73, - "learning_rate": 1.3397822095851642e-05, - "loss": 3.1968, + "learning_rate": 1.3437564137364857e-05, + "loss": 3.2114, "step": 220900 }, { "epoch": 0.73, - "learning_rate": 1.3381252526859273e-05, - "loss": 3.1994, + "learning_rate": 1.3421012559337409e-05, + "loss": 3.1957, "step": 221000 }, { "epoch": 0.73, - "learning_rate": 1.33646829578669e-05, - "loss": 3.2166, + "learning_rate": 1.3404460981309957e-05, + "loss": 3.1848, "step": 221100 }, { "epoch": 0.73, - "learning_rate": 1.3348113388874528e-05, - "loss": 3.2152, + "learning_rate": 1.3387909403282509e-05, + "loss": 3.1892, "step": 221200 }, { "epoch": 0.73, - "learning_rate": 1.3331543819882159e-05, - "loss": 3.1944, + "learning_rate": 1.337135782525506e-05, + "loss": 3.1872, "step": 221300 }, { "epoch": 0.73, - "learning_rate": 1.3314974250889786e-05, - "loss": 3.1912, + "learning_rate": 1.335480624722761e-05, + "loss": 3.1875, "step": 221400 }, { "epoch": 0.73, - "learning_rate": 1.3298404681897414e-05, - "loss": 3.2152, + "learning_rate": 1.3338254669200162e-05, + "loss": 3.1792, "step": 221500 }, { "epoch": 0.73, - "learning_rate": 1.3281835112905044e-05, - "loss": 3.2086, + "learning_rate": 1.3321703091172714e-05, + "loss": 3.1944, "step": 221600 }, { "epoch": 0.73, - "learning_rate": 1.3265265543912672e-05, - "loss": 3.2133, + "learning_rate": 1.3305151513145263e-05, + "loss": 3.1959, "step": 221700 }, { - "epoch": 0.74, - "learning_rate": 1.32486959749203e-05, - "loss": 3.2056, + "epoch": 0.73, + "learning_rate": 1.3288599935117815e-05, + "loss": 3.2025, "step": 221800 }, { - "epoch": 0.74, - "learning_rate": 1.323212640592793e-05, - "loss": 3.2106, + "epoch": 0.73, + "learning_rate": 1.3272048357090367e-05, + "loss": 3.1946, "step": 221900 }, { - "epoch": 0.74, - "learning_rate": 1.3215556836935558e-05, - "loss": 3.2022, + "epoch": 0.73, + "learning_rate": 1.3255496779062918e-05, + "loss": 3.189, "step": 222000 }, { "epoch": 0.74, - "learning_rate": 1.3198987267943185e-05, - "loss": 3.2117, + "learning_rate": 1.3238945201035468e-05, + "loss": 3.1839, "step": 222100 }, { "epoch": 0.74, - "learning_rate": 1.3182417698950816e-05, - "loss": 3.1989, + "learning_rate": 1.3222393623008016e-05, + "loss": 3.1827, "step": 222200 }, { "epoch": 0.74, - "learning_rate": 1.3165848129958444e-05, - "loss": 3.208, + "learning_rate": 1.3205842044980568e-05, + "loss": 3.2012, "step": 222300 }, { "epoch": 0.74, - "learning_rate": 1.3149278560966071e-05, - "loss": 3.1975, + "learning_rate": 1.318929046695312e-05, + "loss": 3.187, "step": 222400 }, { "epoch": 0.74, - "learning_rate": 1.3132708991973702e-05, - "loss": 3.1923, + "learning_rate": 1.317273888892567e-05, + "loss": 3.1799, "step": 222500 }, { "epoch": 0.74, - "learning_rate": 1.311613942298133e-05, - "loss": 3.2061, + "learning_rate": 1.3156187310898221e-05, + "loss": 3.1919, "step": 222600 }, { "epoch": 0.74, - "learning_rate": 1.3099569853988957e-05, - "loss": 3.2101, + "learning_rate": 1.3139635732870773e-05, + "loss": 3.1891, "step": 222700 }, { "epoch": 0.74, - "learning_rate": 1.3083000284996588e-05, - "loss": 3.2026, + "learning_rate": 1.3123084154843324e-05, + "loss": 3.1861, "step": 222800 }, { "epoch": 0.74, - "learning_rate": 1.3066430716004216e-05, - "loss": 3.2158, + "learning_rate": 1.3106532576815874e-05, + "loss": 3.1962, "step": 222900 }, { "epoch": 0.74, - "learning_rate": 1.3049861147011843e-05, - "loss": 3.1983, + "learning_rate": 1.3089980998788426e-05, + "loss": 3.1951, "step": 223000 }, { "epoch": 0.74, - "learning_rate": 1.3033291578019474e-05, - "loss": 3.2061, + "learning_rate": 1.3073429420760977e-05, + "loss": 3.1878, "step": 223100 }, { "epoch": 0.74, - "learning_rate": 1.3016722009027102e-05, - "loss": 3.2016, + "learning_rate": 1.3056877842733527e-05, + "loss": 3.1796, "step": 223200 }, { "epoch": 0.74, - "learning_rate": 1.3000152440034729e-05, - "loss": 3.21, + "learning_rate": 1.3040326264706077e-05, + "loss": 3.1973, "step": 223300 }, { "epoch": 0.74, - "learning_rate": 1.298358287104236e-05, - "loss": 3.2083, + "learning_rate": 1.3023774686678627e-05, + "loss": 3.1867, "step": 223400 }, { "epoch": 0.74, - "learning_rate": 1.2967013302049988e-05, - "loss": 3.2064, + "learning_rate": 1.3007223108651179e-05, + "loss": 3.1891, "step": 223500 }, { "epoch": 0.74, - "learning_rate": 1.2950443733057615e-05, - "loss": 3.2008, + "learning_rate": 1.299067153062373e-05, + "loss": 3.1867, "step": 223600 }, { "epoch": 0.74, - "learning_rate": 1.2933874164065246e-05, - "loss": 3.1965, + "learning_rate": 1.297411995259628e-05, + "loss": 3.1877, "step": 223700 }, { "epoch": 0.74, - "learning_rate": 1.2917304595072873e-05, - "loss": 3.206, + "learning_rate": 1.2957568374568832e-05, + "loss": 3.1976, "step": 223800 }, { "epoch": 0.74, - "learning_rate": 1.2900735026080501e-05, - "loss": 3.2057, + "learning_rate": 1.2941016796541383e-05, + "loss": 3.1989, "step": 223900 }, { "epoch": 0.74, - "learning_rate": 1.2884165457088132e-05, - "loss": 3.2018, + "learning_rate": 1.2924465218513935e-05, + "loss": 3.1826, "step": 224000 }, { "epoch": 0.74, - "learning_rate": 1.286759588809576e-05, - "loss": 3.1939, + "learning_rate": 1.2907913640486485e-05, + "loss": 3.2061, "step": 224100 }, { "epoch": 0.74, - "learning_rate": 1.2851026319103387e-05, - "loss": 3.2039, + "learning_rate": 1.2891362062459037e-05, + "loss": 3.2034, "step": 224200 }, { "epoch": 0.74, - "learning_rate": 1.2834456750111018e-05, - "loss": 3.2135, + "learning_rate": 1.2874810484431588e-05, + "loss": 3.1899, "step": 224300 }, { "epoch": 0.74, - "learning_rate": 1.2817887181118645e-05, - "loss": 3.2111, + "learning_rate": 1.2858258906404136e-05, + "loss": 3.1986, "step": 224400 }, { "epoch": 0.74, - "learning_rate": 1.2801317612126273e-05, - "loss": 3.204, + "learning_rate": 1.2841707328376686e-05, + "loss": 3.2004, "step": 224500 }, { "epoch": 0.74, - "learning_rate": 1.2784748043133904e-05, - "loss": 3.2038, + "learning_rate": 1.2825155750349238e-05, + "loss": 3.1919, "step": 224600 }, { "epoch": 0.74, - "learning_rate": 1.2768178474141531e-05, - "loss": 3.2013, + "learning_rate": 1.280860417232179e-05, + "loss": 3.1889, "step": 224700 }, { "epoch": 0.74, - "learning_rate": 1.2751608905149159e-05, - "loss": 3.2112, + "learning_rate": 1.2792052594294341e-05, + "loss": 3.1987, "step": 224800 }, { - "epoch": 0.75, - "learning_rate": 1.2735039336156788e-05, - "loss": 3.195, + "epoch": 0.74, + "learning_rate": 1.2775501016266891e-05, + "loss": 3.1908, "step": 224900 }, { - "epoch": 0.75, - "learning_rate": 1.2718469767164417e-05, - "loss": 3.2133, + "epoch": 0.74, + "learning_rate": 1.2758949438239443e-05, + "loss": 3.1835, "step": 225000 }, { "epoch": 0.75, - "learning_rate": 1.2701900198172045e-05, - "loss": 3.1925, + "learning_rate": 1.2742397860211994e-05, + "loss": 3.1899, "step": 225100 }, { "epoch": 0.75, - "learning_rate": 1.2685330629179674e-05, - "loss": 3.206, + "learning_rate": 1.2725846282184544e-05, + "loss": 3.1985, "step": 225200 }, { "epoch": 0.75, - "learning_rate": 1.2668761060187303e-05, - "loss": 3.2129, + "learning_rate": 1.2709294704157096e-05, + "loss": 3.1937, "step": 225300 }, { "epoch": 0.75, - "learning_rate": 1.265219149119493e-05, - "loss": 3.2173, + "learning_rate": 1.2692743126129647e-05, + "loss": 3.1911, "step": 225400 }, { "epoch": 0.75, - "learning_rate": 1.263562192220256e-05, - "loss": 3.2037, + "learning_rate": 1.2676191548102195e-05, + "loss": 3.1832, "step": 225500 }, { "epoch": 0.75, - "learning_rate": 1.2619052353210189e-05, - "loss": 3.2033, + "learning_rate": 1.2659639970074747e-05, + "loss": 3.1976, "step": 225600 }, { "epoch": 0.75, - "learning_rate": 1.2602482784217816e-05, - "loss": 3.2127, + "learning_rate": 1.2643088392047297e-05, + "loss": 3.2007, "step": 225700 }, { "epoch": 0.75, - "learning_rate": 1.2585913215225446e-05, - "loss": 3.2027, + "learning_rate": 1.2626536814019849e-05, + "loss": 3.1932, "step": 225800 }, { "epoch": 0.75, - "learning_rate": 1.2569343646233075e-05, - "loss": 3.2037, + "learning_rate": 1.26099852359924e-05, + "loss": 3.1821, "step": 225900 }, { "epoch": 0.75, - "learning_rate": 1.2552774077240702e-05, - "loss": 3.2007, + "learning_rate": 1.259343365796495e-05, + "loss": 3.1778, "step": 226000 }, { "epoch": 0.75, - "learning_rate": 1.2536204508248332e-05, - "loss": 3.2014, + "learning_rate": 1.2576882079937502e-05, + "loss": 3.1822, "step": 226100 }, { "epoch": 0.75, - "learning_rate": 1.251963493925596e-05, - "loss": 3.1889, + "learning_rate": 1.2560330501910053e-05, + "loss": 3.1887, "step": 226200 }, { "epoch": 0.75, - "learning_rate": 1.2503065370263588e-05, - "loss": 3.2099, + "learning_rate": 1.2543778923882605e-05, + "loss": 3.1937, "step": 226300 }, { "epoch": 0.75, - "learning_rate": 1.2486495801271218e-05, - "loss": 3.2096, + "learning_rate": 1.2527227345855155e-05, + "loss": 3.1879, "step": 226400 }, { "epoch": 0.75, - "learning_rate": 1.2469926232278847e-05, - "loss": 3.2107, + "learning_rate": 1.2510675767827706e-05, + "loss": 3.1846, "step": 226500 }, { "epoch": 0.75, - "learning_rate": 1.2453356663286474e-05, - "loss": 3.2204, + "learning_rate": 1.2494124189800256e-05, + "loss": 3.1813, "step": 226600 }, { "epoch": 0.75, - "learning_rate": 1.2436787094294103e-05, - "loss": 3.2084, + "learning_rate": 1.2477572611772808e-05, + "loss": 3.1891, "step": 226700 }, { "epoch": 0.75, - "learning_rate": 1.2420217525301733e-05, - "loss": 3.2124, + "learning_rate": 1.2461021033745358e-05, + "loss": 3.2106, "step": 226800 }, { "epoch": 0.75, - "learning_rate": 1.2403647956309362e-05, - "loss": 3.194, + "learning_rate": 1.2444469455717908e-05, + "loss": 3.2068, "step": 226900 }, { "epoch": 0.75, - "learning_rate": 1.238707838731699e-05, - "loss": 3.2007, + "learning_rate": 1.242791787769046e-05, + "loss": 3.188, "step": 227000 }, { "epoch": 0.75, - "learning_rate": 1.2370508818324619e-05, - "loss": 3.2026, + "learning_rate": 1.2411366299663011e-05, + "loss": 3.1852, "step": 227100 }, { "epoch": 0.75, - "learning_rate": 1.2353939249332248e-05, - "loss": 3.2027, + "learning_rate": 1.239481472163556e-05, + "loss": 3.2014, "step": 227200 }, { "epoch": 0.75, - "learning_rate": 1.2337369680339875e-05, - "loss": 3.2051, + "learning_rate": 1.2378263143608112e-05, + "loss": 3.1816, "step": 227300 }, { "epoch": 0.75, - "learning_rate": 1.2320800111347505e-05, - "loss": 3.2089, + "learning_rate": 1.2361711565580664e-05, + "loss": 3.1997, "step": 227400 }, { "epoch": 0.75, - "learning_rate": 1.2304230542355134e-05, - "loss": 3.2059, + "learning_rate": 1.2345159987553214e-05, + "loss": 3.1861, "step": 227500 }, { "epoch": 0.75, - "learning_rate": 1.2287660973362761e-05, - "loss": 3.2139, + "learning_rate": 1.2328608409525764e-05, + "loss": 3.1985, "step": 227600 }, { "epoch": 0.75, - "learning_rate": 1.227109140437039e-05, - "loss": 3.2041, + "learning_rate": 1.2312056831498315e-05, + "loss": 3.1919, "step": 227700 }, { "epoch": 0.75, - "learning_rate": 1.225452183537802e-05, - "loss": 3.1896, + "learning_rate": 1.2295505253470867e-05, + "loss": 3.1901, "step": 227800 }, { - "epoch": 0.76, - "learning_rate": 1.2237952266385649e-05, - "loss": 3.1921, + "epoch": 0.75, + "learning_rate": 1.2278953675443419e-05, + "loss": 3.1833, "step": 227900 }, { - "epoch": 0.76, - "learning_rate": 1.2221382697393276e-05, - "loss": 3.1886, + "epoch": 0.75, + "learning_rate": 1.2262402097415967e-05, + "loss": 3.1935, "step": 228000 }, { "epoch": 0.76, - "learning_rate": 1.2204813128400906e-05, - "loss": 3.2056, + "learning_rate": 1.2245850519388518e-05, + "loss": 3.1952, "step": 228100 }, { "epoch": 0.76, - "learning_rate": 1.2188243559408533e-05, - "loss": 3.2103, + "learning_rate": 1.222929894136107e-05, + "loss": 3.1885, "step": 228200 }, { "epoch": 0.76, - "learning_rate": 1.2171673990416162e-05, - "loss": 3.2052, + "learning_rate": 1.2212747363333622e-05, + "loss": 3.2013, "step": 228300 }, { "epoch": 0.76, - "learning_rate": 1.2155104421423791e-05, - "loss": 3.1899, + "learning_rate": 1.2196195785306172e-05, + "loss": 3.1977, "step": 228400 }, { "epoch": 0.76, - "learning_rate": 1.2138534852431419e-05, - "loss": 3.19, + "learning_rate": 1.2179644207278723e-05, + "loss": 3.1771, "step": 228500 }, { "epoch": 0.76, - "learning_rate": 1.2121965283439048e-05, - "loss": 3.2068, + "learning_rate": 1.2163092629251273e-05, + "loss": 3.2004, "step": 228600 }, { "epoch": 0.76, - "learning_rate": 1.2105395714446677e-05, - "loss": 3.2082, + "learning_rate": 1.2146541051223825e-05, + "loss": 3.196, "step": 228700 }, { "epoch": 0.76, - "learning_rate": 1.2088826145454305e-05, - "loss": 3.1911, + "learning_rate": 1.2129989473196375e-05, + "loss": 3.1955, "step": 228800 }, { "epoch": 0.76, - "learning_rate": 1.2072256576461934e-05, - "loss": 3.1928, + "learning_rate": 1.2113437895168926e-05, + "loss": 3.1922, "step": 228900 }, { "epoch": 0.76, - "learning_rate": 1.2055687007469563e-05, - "loss": 3.1964, + "learning_rate": 1.2096886317141478e-05, + "loss": 3.1923, "step": 229000 }, { "epoch": 0.76, - "learning_rate": 1.203911743847719e-05, - "loss": 3.1941, + "learning_rate": 1.2080334739114028e-05, + "loss": 3.1893, "step": 229100 }, { "epoch": 0.76, - "learning_rate": 1.202254786948482e-05, - "loss": 3.2056, + "learning_rate": 1.2063783161086578e-05, + "loss": 3.1857, "step": 229200 }, { "epoch": 0.76, - "learning_rate": 1.200597830049245e-05, - "loss": 3.1963, + "learning_rate": 1.204723158305913e-05, + "loss": 3.1973, "step": 229300 }, { "epoch": 0.76, - "learning_rate": 1.1989408731500077e-05, - "loss": 3.1977, + "learning_rate": 1.203068000503168e-05, + "loss": 3.1987, "step": 229400 }, { "epoch": 0.76, - "learning_rate": 1.1972839162507706e-05, - "loss": 3.2055, + "learning_rate": 1.201412842700423e-05, + "loss": 3.1907, "step": 229500 }, { "epoch": 0.76, - "learning_rate": 1.1956269593515335e-05, - "loss": 3.208, + "learning_rate": 1.1997576848976782e-05, + "loss": 3.1904, "step": 229600 }, { "epoch": 0.76, - "learning_rate": 1.1939700024522963e-05, - "loss": 3.1937, + "learning_rate": 1.1981025270949332e-05, + "loss": 3.1822, "step": 229700 }, { "epoch": 0.76, - "learning_rate": 1.1923130455530592e-05, - "loss": 3.2012, + "learning_rate": 1.1964473692921884e-05, + "loss": 3.1966, "step": 229800 }, { "epoch": 0.76, - "learning_rate": 1.1906560886538221e-05, - "loss": 3.2016, + "learning_rate": 1.1947922114894434e-05, + "loss": 3.1882, "step": 229900 }, { "epoch": 0.76, - "learning_rate": 1.1889991317545849e-05, - "loss": 3.1975, + "learning_rate": 1.1931370536866985e-05, + "loss": 3.1804, "step": 230000 }, { "epoch": 0.76, - "learning_rate": 1.1873421748553478e-05, - "loss": 3.2078, + "learning_rate": 1.1914818958839537e-05, + "loss": 3.1778, "step": 230100 }, { "epoch": 0.76, - "learning_rate": 1.1856852179561107e-05, - "loss": 3.1885, + "learning_rate": 1.1898267380812089e-05, + "loss": 3.1946, "step": 230200 }, { "epoch": 0.76, - "learning_rate": 1.1840282610568735e-05, - "loss": 3.2109, + "learning_rate": 1.1881715802784638e-05, + "loss": 3.1835, "step": 230300 }, { "epoch": 0.76, - "learning_rate": 1.1823713041576364e-05, - "loss": 3.2004, + "learning_rate": 1.1865164224757188e-05, + "loss": 3.1823, "step": 230400 }, { "epoch": 0.76, - "learning_rate": 1.1807143472583991e-05, - "loss": 3.1954, + "learning_rate": 1.184861264672974e-05, + "loss": 3.2011, "step": 230500 }, { "epoch": 0.76, - "learning_rate": 1.179057390359162e-05, - "loss": 3.2114, + "learning_rate": 1.1832061068702292e-05, + "loss": 3.1936, "step": 230600 }, { "epoch": 0.76, - "learning_rate": 1.177400433459925e-05, - "loss": 3.2114, + "learning_rate": 1.1815509490674841e-05, + "loss": 3.1975, "step": 230700 }, { "epoch": 0.76, - "learning_rate": 1.1757434765606877e-05, - "loss": 3.2104, + "learning_rate": 1.1798957912647391e-05, + "loss": 3.1941, "step": 230800 }, { - "epoch": 0.77, - "learning_rate": 1.1740865196614506e-05, - "loss": 3.2037, + "epoch": 0.76, + "learning_rate": 1.1782406334619943e-05, + "loss": 3.1938, "step": 230900 }, { - "epoch": 0.77, - "learning_rate": 1.1724295627622136e-05, - "loss": 3.1939, + "epoch": 0.76, + "learning_rate": 1.1765854756592495e-05, + "loss": 3.1927, "step": 231000 }, { "epoch": 0.77, - "learning_rate": 1.1707726058629763e-05, - "loss": 3.1934, + "learning_rate": 1.1749303178565044e-05, + "loss": 3.2104, "step": 231100 }, { "epoch": 0.77, - "learning_rate": 1.1691156489637392e-05, - "loss": 3.2031, + "learning_rate": 1.1732751600537596e-05, + "loss": 3.1699, "step": 231200 }, { "epoch": 0.77, - "learning_rate": 1.1674586920645022e-05, - "loss": 3.1987, + "learning_rate": 1.1716200022510148e-05, + "loss": 3.1897, "step": 231300 }, { "epoch": 0.77, - "learning_rate": 1.1658017351652649e-05, - "loss": 3.2036, + "learning_rate": 1.1699648444482698e-05, + "loss": 3.1816, "step": 231400 }, { "epoch": 0.77, - "learning_rate": 1.1641447782660278e-05, - "loss": 3.2034, + "learning_rate": 1.1683096866455247e-05, + "loss": 3.1894, "step": 231500 }, { "epoch": 0.77, - "learning_rate": 1.1624878213667907e-05, - "loss": 3.1989, + "learning_rate": 1.1666545288427799e-05, + "loss": 3.1849, "step": 231600 }, { "epoch": 0.77, - "learning_rate": 1.1608308644675535e-05, - "loss": 3.2002, + "learning_rate": 1.164999371040035e-05, + "loss": 3.2012, "step": 231700 }, { "epoch": 0.77, - "learning_rate": 1.1591739075683164e-05, - "loss": 3.2198, + "learning_rate": 1.1633442132372902e-05, + "loss": 3.1898, "step": 231800 }, { "epoch": 0.77, - "learning_rate": 1.1575169506690793e-05, - "loss": 3.1994, + "learning_rate": 1.161689055434545e-05, + "loss": 3.1975, "step": 231900 }, { "epoch": 0.77, - "learning_rate": 1.1558599937698421e-05, - "loss": 3.1982, + "learning_rate": 1.1600338976318002e-05, + "loss": 3.1934, "step": 232000 }, { "epoch": 0.77, - "learning_rate": 1.154203036870605e-05, - "loss": 3.1939, + "learning_rate": 1.1583787398290554e-05, + "loss": 3.184, "step": 232100 }, { "epoch": 0.77, - "learning_rate": 1.152546079971368e-05, - "loss": 3.2011, + "learning_rate": 1.1567235820263105e-05, + "loss": 3.1918, "step": 232200 }, { "epoch": 0.77, - "learning_rate": 1.1508891230721307e-05, - "loss": 3.2023, + "learning_rate": 1.1550684242235655e-05, + "loss": 3.1757, "step": 232300 }, { "epoch": 0.77, - "learning_rate": 1.1492321661728936e-05, - "loss": 3.1956, + "learning_rate": 1.1534132664208207e-05, + "loss": 3.2003, "step": 232400 }, { "epoch": 0.77, - "learning_rate": 1.1475752092736563e-05, - "loss": 3.1954, + "learning_rate": 1.1517581086180757e-05, + "loss": 3.1875, "step": 232500 }, { "epoch": 0.77, - "learning_rate": 1.1459182523744193e-05, - "loss": 3.2009, + "learning_rate": 1.1501029508153308e-05, + "loss": 3.1961, "step": 232600 }, { "epoch": 0.77, - "learning_rate": 1.1442612954751822e-05, - "loss": 3.2081, + "learning_rate": 1.1484477930125858e-05, + "loss": 3.1907, "step": 232700 }, { "epoch": 0.77, - "learning_rate": 1.142604338575945e-05, - "loss": 3.202, + "learning_rate": 1.146792635209841e-05, + "loss": 3.1728, "step": 232800 }, { "epoch": 0.77, - "learning_rate": 1.1409473816767079e-05, - "loss": 3.1957, + "learning_rate": 1.1451374774070961e-05, + "loss": 3.1846, "step": 232900 }, { "epoch": 0.77, - "learning_rate": 1.1392904247774708e-05, - "loss": 3.1923, + "learning_rate": 1.1434823196043511e-05, + "loss": 3.1877, "step": 233000 }, { "epoch": 0.77, - "learning_rate": 1.1376334678782335e-05, - "loss": 3.1985, + "learning_rate": 1.1418271618016061e-05, + "loss": 3.1948, "step": 233100 }, { "epoch": 0.77, - "learning_rate": 1.1359765109789965e-05, - "loss": 3.1888, + "learning_rate": 1.1401720039988613e-05, + "loss": 3.1981, "step": 233200 }, { "epoch": 0.77, - "learning_rate": 1.1343195540797594e-05, - "loss": 3.2072, + "learning_rate": 1.1385168461961164e-05, + "loss": 3.1909, "step": 233300 }, { "epoch": 0.77, - "learning_rate": 1.1326625971805221e-05, - "loss": 3.198, + "learning_rate": 1.1368616883933714e-05, + "loss": 3.1941, "step": 233400 }, { "epoch": 0.77, - "learning_rate": 1.131005640281285e-05, - "loss": 3.2095, + "learning_rate": 1.1352065305906266e-05, + "loss": 3.1931, "step": 233500 }, { "epoch": 0.77, - "learning_rate": 1.129348683382048e-05, - "loss": 3.211, + "learning_rate": 1.1335513727878816e-05, + "loss": 3.203, "step": 233600 }, { "epoch": 0.77, - "learning_rate": 1.1276917264828107e-05, - "loss": 3.1971, + "learning_rate": 1.1318962149851367e-05, + "loss": 3.1858, "step": 233700 }, { "epoch": 0.77, - "learning_rate": 1.1260347695835736e-05, - "loss": 3.2054, + "learning_rate": 1.1302410571823917e-05, + "loss": 3.1904, "step": 233800 }, { - "epoch": 0.78, - "learning_rate": 1.1243778126843366e-05, - "loss": 3.2044, + "epoch": 0.77, + "learning_rate": 1.1285858993796469e-05, + "loss": 3.1833, "step": 233900 }, { - "epoch": 0.78, - "learning_rate": 1.1227208557850993e-05, - "loss": 3.1993, + "epoch": 0.77, + "learning_rate": 1.126930741576902e-05, + "loss": 3.1736, "step": 234000 }, { - "epoch": 0.78, - "learning_rate": 1.1210638988858622e-05, - "loss": 3.2091, + "epoch": 0.77, + "learning_rate": 1.1252755837741572e-05, + "loss": 3.1842, "step": 234100 }, { "epoch": 0.78, - "learning_rate": 1.1194069419866252e-05, - "loss": 3.2097, + "learning_rate": 1.1236204259714122e-05, + "loss": 3.1914, "step": 234200 }, { "epoch": 0.78, - "learning_rate": 1.1177499850873879e-05, - "loss": 3.2031, + "learning_rate": 1.1219652681686672e-05, + "loss": 3.1958, "step": 234300 }, { "epoch": 0.78, - "learning_rate": 1.1160930281881508e-05, - "loss": 3.1867, + "learning_rate": 1.1203101103659224e-05, + "loss": 3.1869, "step": 234400 }, { "epoch": 0.78, - "learning_rate": 1.1144360712889137e-05, - "loss": 3.203, + "learning_rate": 1.1186549525631775e-05, + "loss": 3.1938, "step": 234500 }, { "epoch": 0.78, - "learning_rate": 1.1127791143896765e-05, - "loss": 3.2104, + "learning_rate": 1.1169997947604325e-05, + "loss": 3.2019, "step": 234600 }, { "epoch": 0.78, - "learning_rate": 1.1111221574904394e-05, - "loss": 3.1894, + "learning_rate": 1.1153446369576875e-05, + "loss": 3.1884, "step": 234700 }, { "epoch": 0.78, - "learning_rate": 1.1094652005912022e-05, - "loss": 3.2143, + "learning_rate": 1.1136894791549427e-05, + "loss": 3.1818, "step": 234800 }, { "epoch": 0.78, - "learning_rate": 1.1078082436919651e-05, - "loss": 3.2056, + "learning_rate": 1.1120343213521978e-05, + "loss": 3.1933, "step": 234900 }, { "epoch": 0.78, - "learning_rate": 1.106151286792728e-05, - "loss": 3.2047, + "learning_rate": 1.1103791635494528e-05, + "loss": 3.1952, "step": 235000 }, { "epoch": 0.78, - "learning_rate": 1.1044943298934908e-05, - "loss": 3.1941, + "learning_rate": 1.108724005746708e-05, + "loss": 3.1888, "step": 235100 }, { "epoch": 0.78, - "learning_rate": 1.1028373729942537e-05, - "loss": 3.202, + "learning_rate": 1.1070688479439631e-05, + "loss": 3.1884, "step": 235200 }, { "epoch": 0.78, - "learning_rate": 1.1011804160950166e-05, - "loss": 3.2181, + "learning_rate": 1.1054136901412181e-05, + "loss": 3.188, "step": 235300 }, { "epoch": 0.78, - "learning_rate": 1.0995234591957794e-05, - "loss": 3.2038, + "learning_rate": 1.1037585323384731e-05, + "loss": 3.1928, "step": 235400 }, { "epoch": 0.78, - "learning_rate": 1.0978665022965423e-05, - "loss": 3.1839, + "learning_rate": 1.1021033745357283e-05, + "loss": 3.1925, "step": 235500 }, { "epoch": 0.78, - "learning_rate": 1.0962095453973052e-05, - "loss": 3.1914, + "learning_rate": 1.1004482167329834e-05, + "loss": 3.1943, "step": 235600 }, { "epoch": 0.78, - "learning_rate": 1.094552588498068e-05, - "loss": 3.202, + "learning_rate": 1.0987930589302386e-05, + "loss": 3.2029, "step": 235700 }, { "epoch": 0.78, - "learning_rate": 1.0928956315988309e-05, - "loss": 3.2015, + "learning_rate": 1.0971379011274934e-05, + "loss": 3.1857, "step": 235800 }, { "epoch": 0.78, - "learning_rate": 1.0912386746995938e-05, - "loss": 3.2038, + "learning_rate": 1.0954827433247486e-05, + "loss": 3.1852, "step": 235900 }, { "epoch": 0.78, - "learning_rate": 1.0895817178003565e-05, - "loss": 3.2038, + "learning_rate": 1.0938275855220037e-05, + "loss": 3.1967, "step": 236000 }, { "epoch": 0.78, - "learning_rate": 1.0879247609011195e-05, - "loss": 3.1973, + "learning_rate": 1.0921724277192589e-05, + "loss": 3.2004, "step": 236100 }, { "epoch": 0.78, - "learning_rate": 1.0862678040018824e-05, - "loss": 3.2014, + "learning_rate": 1.0905172699165139e-05, + "loss": 3.1926, "step": 236200 }, { "epoch": 0.78, - "learning_rate": 1.0846108471026451e-05, - "loss": 3.1948, + "learning_rate": 1.088862112113769e-05, + "loss": 3.1796, "step": 236300 }, { "epoch": 0.78, - "learning_rate": 1.082953890203408e-05, - "loss": 3.2121, + "learning_rate": 1.087206954311024e-05, + "loss": 3.1866, "step": 236400 }, { "epoch": 0.78, - "learning_rate": 1.081296933304171e-05, - "loss": 3.1987, + "learning_rate": 1.0855517965082792e-05, + "loss": 3.1899, "step": 236500 }, { "epoch": 0.78, - "learning_rate": 1.0796399764049337e-05, - "loss": 3.2045, + "learning_rate": 1.0838966387055342e-05, + "loss": 3.1899, "step": 236600 }, { "epoch": 0.78, - "learning_rate": 1.0779830195056966e-05, - "loss": 3.1962, + "learning_rate": 1.0822414809027893e-05, + "loss": 3.1853, "step": 236700 }, { "epoch": 0.78, - "learning_rate": 1.0763260626064596e-05, - "loss": 3.2013, + "learning_rate": 1.0805863231000445e-05, + "loss": 3.1913, "step": 236800 }, { - "epoch": 0.79, - "learning_rate": 1.0746691057072223e-05, - "loss": 3.2051, + "epoch": 0.78, + "learning_rate": 1.0789311652972995e-05, + "loss": 3.1891, "step": 236900 }, { - "epoch": 0.79, - "learning_rate": 1.0730121488079852e-05, - "loss": 3.2003, + "epoch": 0.78, + "learning_rate": 1.0772760074945545e-05, + "loss": 3.186, "step": 237000 }, { - "epoch": 0.79, - "learning_rate": 1.071355191908748e-05, - "loss": 3.2019, + "epoch": 0.78, + "learning_rate": 1.0756208496918096e-05, + "loss": 3.1869, "step": 237100 }, { "epoch": 0.79, - "learning_rate": 1.0696982350095109e-05, - "loss": 3.2067, + "learning_rate": 1.0739656918890648e-05, + "loss": 3.1974, "step": 237200 }, { "epoch": 0.79, - "learning_rate": 1.0680412781102738e-05, - "loss": 3.2017, + "learning_rate": 1.0723105340863198e-05, + "loss": 3.1878, "step": 237300 }, { "epoch": 0.79, - "learning_rate": 1.0663843212110366e-05, - "loss": 3.2005, + "learning_rate": 1.070655376283575e-05, + "loss": 3.1812, "step": 237400 }, { "epoch": 0.79, - "learning_rate": 1.0647273643117995e-05, - "loss": 3.2052, + "learning_rate": 1.06900021848083e-05, + "loss": 3.185, "step": 237500 }, { "epoch": 0.79, - "learning_rate": 1.0630704074125624e-05, - "loss": 3.2038, + "learning_rate": 1.0673450606780851e-05, + "loss": 3.2023, "step": 237600 }, { "epoch": 0.79, - "learning_rate": 1.0614134505133252e-05, - "loss": 3.2004, + "learning_rate": 1.0656899028753403e-05, + "loss": 3.1726, "step": 237700 }, { "epoch": 0.79, - "learning_rate": 1.0597564936140881e-05, - "loss": 3.1898, + "learning_rate": 1.0640347450725953e-05, + "loss": 3.1907, "step": 237800 }, { "epoch": 0.79, - "learning_rate": 1.058099536714851e-05, - "loss": 3.2144, + "learning_rate": 1.0623795872698504e-05, + "loss": 3.1871, "step": 237900 }, { "epoch": 0.79, - "learning_rate": 1.0564425798156138e-05, - "loss": 3.2156, + "learning_rate": 1.0607244294671056e-05, + "loss": 3.1937, "step": 238000 }, { "epoch": 0.79, - "learning_rate": 1.0547856229163767e-05, - "loss": 3.1812, + "learning_rate": 1.0590692716643606e-05, + "loss": 3.1822, "step": 238100 }, { "epoch": 0.79, - "learning_rate": 1.0531286660171396e-05, - "loss": 3.1975, + "learning_rate": 1.0574141138616156e-05, + "loss": 3.2023, "step": 238200 }, { "epoch": 0.79, - "learning_rate": 1.0514717091179024e-05, - "loss": 3.1936, + "learning_rate": 1.0557589560588707e-05, + "loss": 3.1785, "step": 238300 }, { "epoch": 0.79, - "learning_rate": 1.0498147522186653e-05, - "loss": 3.1991, + "learning_rate": 1.0541037982561259e-05, + "loss": 3.1752, "step": 238400 }, { "epoch": 0.79, - "learning_rate": 1.0481577953194282e-05, - "loss": 3.2074, + "learning_rate": 1.0524486404533809e-05, + "loss": 3.1812, "step": 238500 }, { "epoch": 0.79, - "learning_rate": 1.0465008384201911e-05, - "loss": 3.1967, + "learning_rate": 1.0507934826506359e-05, + "loss": 3.1884, "step": 238600 }, { "epoch": 0.79, - "learning_rate": 1.0448438815209539e-05, - "loss": 3.1987, + "learning_rate": 1.049138324847891e-05, + "loss": 3.1816, "step": 238700 }, { "epoch": 0.79, - "learning_rate": 1.0431869246217168e-05, - "loss": 3.2024, + "learning_rate": 1.0474831670451462e-05, + "loss": 3.1862, "step": 238800 }, { "epoch": 0.79, - "learning_rate": 1.0415299677224797e-05, - "loss": 3.2069, + "learning_rate": 1.0458280092424012e-05, + "loss": 3.1897, "step": 238900 }, { "epoch": 0.79, - "learning_rate": 1.0398730108232425e-05, - "loss": 3.2106, + "learning_rate": 1.0441728514396563e-05, + "loss": 3.1998, "step": 239000 }, { "epoch": 0.79, - "learning_rate": 1.0382160539240054e-05, - "loss": 3.2127, + "learning_rate": 1.0425176936369115e-05, + "loss": 3.189, "step": 239100 }, { "epoch": 0.79, - "learning_rate": 1.0365590970247683e-05, - "loss": 3.2007, + "learning_rate": 1.0408625358341665e-05, + "loss": 3.1833, "step": 239200 }, { "epoch": 0.79, - "learning_rate": 1.034902140125531e-05, - "loss": 3.1959, + "learning_rate": 1.0392073780314215e-05, + "loss": 3.2012, "step": 239300 }, { "epoch": 0.79, - "learning_rate": 1.033245183226294e-05, - "loss": 3.181, + "learning_rate": 1.0375522202286766e-05, + "loss": 3.1875, "step": 239400 }, { "epoch": 0.79, - "learning_rate": 1.0315882263270569e-05, - "loss": 3.2124, + "learning_rate": 1.0358970624259318e-05, + "loss": 3.1949, "step": 239500 }, { "epoch": 0.79, - "learning_rate": 1.0299312694278198e-05, - "loss": 3.2178, + "learning_rate": 1.034241904623187e-05, + "loss": 3.1907, "step": 239600 }, { "epoch": 0.79, - "learning_rate": 1.0282743125285826e-05, - "loss": 3.202, + "learning_rate": 1.0325867468204418e-05, + "loss": 3.178, "step": 239700 }, { "epoch": 0.79, - "learning_rate": 1.0266173556293455e-05, - "loss": 3.1981, + "learning_rate": 1.030931589017697e-05, + "loss": 3.1887, "step": 239800 }, { - "epoch": 0.8, - "learning_rate": 1.0249603987301084e-05, - "loss": 3.2119, + "epoch": 0.79, + "learning_rate": 1.0292764312149521e-05, + "loss": 3.1819, "step": 239900 }, { - "epoch": 0.8, - "learning_rate": 1.0233034418308712e-05, - "loss": 3.1918, + "epoch": 0.79, + "learning_rate": 1.0276212734122072e-05, + "loss": 3.1772, "step": 240000 }, { - "epoch": 0.8, - "learning_rate": 1.021646484931634e-05, - "loss": 3.1887, + "epoch": 0.79, + "learning_rate": 1.0259661156094622e-05, + "loss": 3.1903, "step": 240100 }, { "epoch": 0.8, - "learning_rate": 1.019989528032397e-05, - "loss": 3.2138, + "learning_rate": 1.0243109578067174e-05, + "loss": 3.1884, "step": 240200 }, { "epoch": 0.8, - "learning_rate": 1.0183325711331597e-05, - "loss": 3.1969, + "learning_rate": 1.0226558000039724e-05, + "loss": 3.1779, "step": 240300 }, { "epoch": 0.8, - "learning_rate": 1.0166756142339227e-05, - "loss": 3.2009, + "learning_rate": 1.0210006422012275e-05, + "loss": 3.1919, "step": 240400 }, { "epoch": 0.8, - "learning_rate": 1.0150186573346856e-05, - "loss": 3.2071, + "learning_rate": 1.0193454843984825e-05, + "loss": 3.1895, "step": 240500 }, { "epoch": 0.8, - "learning_rate": 1.0133617004354483e-05, - "loss": 3.2043, + "learning_rate": 1.0176903265957377e-05, + "loss": 3.1949, "step": 240600 }, { "epoch": 0.8, - "learning_rate": 1.0117047435362113e-05, - "loss": 3.1884, + "learning_rate": 1.0160351687929929e-05, + "loss": 3.1916, "step": 240700 }, { "epoch": 0.8, - "learning_rate": 1.0100477866369742e-05, - "loss": 3.1934, + "learning_rate": 1.0143800109902479e-05, + "loss": 3.1864, "step": 240800 }, { "epoch": 0.8, - "learning_rate": 1.008390829737737e-05, - "loss": 3.2103, + "learning_rate": 1.0127248531875028e-05, + "loss": 3.1842, "step": 240900 }, { "epoch": 0.8, - "learning_rate": 1.0067338728384999e-05, - "loss": 3.1946, + "learning_rate": 1.011069695384758e-05, + "loss": 3.1872, "step": 241000 }, { "epoch": 0.8, - "learning_rate": 1.0050769159392628e-05, - "loss": 3.195, + "learning_rate": 1.0094145375820132e-05, + "loss": 3.191, "step": 241100 }, { "epoch": 0.8, - "learning_rate": 1.0034199590400255e-05, - "loss": 3.198, + "learning_rate": 1.0077593797792683e-05, + "loss": 3.1852, "step": 241200 }, { "epoch": 0.8, - "learning_rate": 1.0017630021407884e-05, - "loss": 3.2096, + "learning_rate": 1.0061042219765233e-05, + "loss": 3.1924, "step": 241300 }, { "epoch": 0.8, - "learning_rate": 1.0001060452415512e-05, - "loss": 3.2068, + "learning_rate": 1.0044490641737783e-05, + "loss": 3.1867, "step": 241400 }, { "epoch": 0.8, - "learning_rate": 9.984490883423141e-06, - "loss": 3.194, + "learning_rate": 1.0027939063710335e-05, + "loss": 3.1861, "step": 241500 }, { "epoch": 0.8, - "learning_rate": 9.96792131443077e-06, - "loss": 3.1972, + "learning_rate": 1.0011387485682886e-05, + "loss": 3.1871, "step": 241600 }, { "epoch": 0.8, - "learning_rate": 9.951351745438398e-06, - "loss": 3.2035, + "learning_rate": 9.994835907655436e-06, + "loss": 3.1935, "step": 241700 }, { "epoch": 0.8, - "learning_rate": 9.934782176446027e-06, - "loss": 3.2039, + "learning_rate": 9.978284329627988e-06, + "loss": 3.1879, "step": 241800 }, { "epoch": 0.8, - "learning_rate": 9.918212607453656e-06, - "loss": 3.2024, + "learning_rate": 9.96173275160054e-06, + "loss": 3.1782, "step": 241900 }, { "epoch": 0.8, - "learning_rate": 9.901643038461284e-06, - "loss": 3.199, + "learning_rate": 9.94518117357309e-06, + "loss": 3.185, "step": 242000 }, { "epoch": 0.8, - "learning_rate": 9.885073469468913e-06, - "loss": 3.2126, + "learning_rate": 9.928629595545639e-06, + "loss": 3.1837, "step": 242100 }, { "epoch": 0.8, - "learning_rate": 9.868503900476542e-06, + "learning_rate": 9.91207801751819e-06, "loss": 3.1901, "step": 242200 }, { "epoch": 0.8, - "learning_rate": 9.85193433148417e-06, - "loss": 3.1887, + "learning_rate": 9.895526439490742e-06, + "loss": 3.1836, "step": 242300 }, { "epoch": 0.8, - "learning_rate": 9.835364762491799e-06, - "loss": 3.194, + "learning_rate": 9.878974861463292e-06, + "loss": 3.178, "step": 242400 }, { "epoch": 0.8, - "learning_rate": 9.818795193499428e-06, - "loss": 3.2044, + "learning_rate": 9.862423283435842e-06, + "loss": 3.1922, "step": 242500 }, { "epoch": 0.8, - "learning_rate": 9.802225624507056e-06, - "loss": 3.1921, + "learning_rate": 9.845871705408394e-06, + "loss": 3.1933, "step": 242600 }, { "epoch": 0.8, - "learning_rate": 9.785656055514685e-06, - "loss": 3.1993, + "learning_rate": 9.829320127380945e-06, + "loss": 3.1893, "step": 242700 }, { "epoch": 0.8, - "learning_rate": 9.769086486522314e-06, - "loss": 3.2003, + "learning_rate": 9.812768549353495e-06, + "loss": 3.1908, "step": 242800 }, { "epoch": 0.8, - "learning_rate": 9.752516917529942e-06, - "loss": 3.2048, + "learning_rate": 9.796216971326047e-06, + "loss": 3.1915, "step": 242900 }, { - "epoch": 0.81, - "learning_rate": 9.73594734853757e-06, - "loss": 3.1987, + "epoch": 0.8, + "learning_rate": 9.779665393298598e-06, + "loss": 3.1817, "step": 243000 }, { - "epoch": 0.81, - "learning_rate": 9.7193777795452e-06, - "loss": 3.1816, + "epoch": 0.8, + "learning_rate": 9.763113815271148e-06, + "loss": 3.1827, "step": 243100 }, { "epoch": 0.81, - "learning_rate": 9.702808210552828e-06, - "loss": 3.199, + "learning_rate": 9.746562237243698e-06, + "loss": 3.1925, "step": 243200 }, { "epoch": 0.81, - "learning_rate": 9.686238641560457e-06, - "loss": 3.1944, + "learning_rate": 9.73001065921625e-06, + "loss": 3.1802, "step": 243300 }, { "epoch": 0.81, - "learning_rate": 9.669669072568084e-06, - "loss": 3.2134, + "learning_rate": 9.713459081188801e-06, + "loss": 3.1794, "step": 243400 }, { "epoch": 0.81, - "learning_rate": 9.653099503575713e-06, - "loss": 3.1945, + "learning_rate": 9.696907503161353e-06, + "loss": 3.1776, "step": 243500 }, { "epoch": 0.81, - "learning_rate": 9.636529934583343e-06, - "loss": 3.1955, + "learning_rate": 9.680355925133901e-06, + "loss": 3.1893, "step": 243600 }, { "epoch": 0.81, - "learning_rate": 9.61996036559097e-06, - "loss": 3.2001, + "learning_rate": 9.663804347106453e-06, + "loss": 3.1881, "step": 243700 }, { "epoch": 0.81, - "learning_rate": 9.6033907965986e-06, - "loss": 3.2, + "learning_rate": 9.647252769079004e-06, + "loss": 3.186, "step": 243800 }, { "epoch": 0.81, - "learning_rate": 9.586821227606229e-06, - "loss": 3.2009, + "learning_rate": 9.630701191051556e-06, + "loss": 3.1937, "step": 243900 }, { "epoch": 0.81, - "learning_rate": 9.570251658613856e-06, - "loss": 3.202, + "learning_rate": 9.614149613024106e-06, + "loss": 3.1825, "step": 244000 }, { "epoch": 0.81, - "learning_rate": 9.553682089621485e-06, - "loss": 3.1903, + "learning_rate": 9.597598034996658e-06, + "loss": 3.1933, "step": 244100 }, { "epoch": 0.81, - "learning_rate": 9.537112520629114e-06, - "loss": 3.205, + "learning_rate": 9.581046456969208e-06, + "loss": 3.188, "step": 244200 }, { "epoch": 0.81, - "learning_rate": 9.520542951636742e-06, - "loss": 3.193, + "learning_rate": 9.564494878941759e-06, + "loss": 3.1816, "step": 244300 }, { "epoch": 0.81, - "learning_rate": 9.503973382644371e-06, - "loss": 3.1997, + "learning_rate": 9.547943300914309e-06, + "loss": 3.1957, "step": 244400 }, { "epoch": 0.81, - "learning_rate": 9.487403813652e-06, - "loss": 3.1954, + "learning_rate": 9.53139172288686e-06, + "loss": 3.1714, "step": 244500 }, { "epoch": 0.81, - "learning_rate": 9.470834244659628e-06, - "loss": 3.2054, + "learning_rate": 9.514840144859412e-06, + "loss": 3.1947, "step": 244600 }, { "epoch": 0.81, - "learning_rate": 9.454264675667257e-06, - "loss": 3.2179, + "learning_rate": 9.498288566831962e-06, + "loss": 3.1893, "step": 244700 }, { "epoch": 0.81, - "learning_rate": 9.437695106674886e-06, - "loss": 3.1996, + "learning_rate": 9.481736988804512e-06, + "loss": 3.1828, "step": 244800 }, { "epoch": 0.81, - "learning_rate": 9.421125537682514e-06, - "loss": 3.1986, + "learning_rate": 9.465185410777064e-06, + "loss": 3.1897, "step": 244900 }, { "epoch": 0.81, - "learning_rate": 9.404555968690143e-06, - "loss": 3.2045, + "learning_rate": 9.448633832749615e-06, + "loss": 3.1992, "step": 245000 }, { "epoch": 0.81, - "learning_rate": 9.387986399697772e-06, - "loss": 3.2094, + "learning_rate": 9.432082254722167e-06, + "loss": 3.1762, "step": 245100 }, { "epoch": 0.81, - "learning_rate": 9.3714168307054e-06, - "loss": 3.189, + "learning_rate": 9.415530676694717e-06, + "loss": 3.1735, "step": 245200 }, { "epoch": 0.81, - "learning_rate": 9.354847261713029e-06, - "loss": 3.1997, + "learning_rate": 9.398979098667267e-06, + "loss": 3.1873, "step": 245300 }, { "epoch": 0.81, - "learning_rate": 9.338277692720658e-06, - "loss": 3.208, + "learning_rate": 9.382427520639818e-06, + "loss": 3.2034, "step": 245400 }, { "epoch": 0.81, - "learning_rate": 9.321708123728286e-06, - "loss": 3.2134, + "learning_rate": 9.36587594261237e-06, + "loss": 3.1891, "step": 245500 }, { "epoch": 0.81, - "learning_rate": 9.305138554735915e-06, - "loss": 3.2009, + "learning_rate": 9.34932436458492e-06, + "loss": 3.1915, "step": 245600 }, { "epoch": 0.81, - "learning_rate": 9.288568985743542e-06, - "loss": 3.1935, + "learning_rate": 9.332772786557471e-06, + "loss": 3.1867, "step": 245700 }, { "epoch": 0.81, - "learning_rate": 9.271999416751172e-06, - "loss": 3.198, + "learning_rate": 9.316221208530021e-06, + "loss": 3.1941, "step": 245800 }, { "epoch": 0.81, - "learning_rate": 9.2554298477588e-06, - "loss": 3.2074, + "learning_rate": 9.299669630502573e-06, + "loss": 3.1953, "step": 245900 }, { - "epoch": 0.82, - "learning_rate": 9.238860278766428e-06, - "loss": 3.2067, + "epoch": 0.81, + "learning_rate": 9.283118052475123e-06, + "loss": 3.1898, "step": 246000 }, { - "epoch": 0.82, - "learning_rate": 9.222290709774058e-06, - "loss": 3.2029, + "epoch": 0.81, + "learning_rate": 9.266566474447674e-06, + "loss": 3.1872, "step": 246100 }, { - "epoch": 0.82, - "learning_rate": 9.205721140781687e-06, - "loss": 3.1951, + "epoch": 0.81, + "learning_rate": 9.250014896420226e-06, + "loss": 3.2021, "step": 246200 }, { "epoch": 0.82, - "learning_rate": 9.189151571789314e-06, - "loss": 3.1994, + "learning_rate": 9.233463318392776e-06, + "loss": 3.2002, "step": 246300 }, { "epoch": 0.82, - "learning_rate": 9.172582002796943e-06, - "loss": 3.2009, + "learning_rate": 9.216911740365326e-06, + "loss": 3.1856, "step": 246400 }, { "epoch": 0.82, - "learning_rate": 9.156012433804573e-06, - "loss": 3.2079, + "learning_rate": 9.200360162337877e-06, + "loss": 3.1775, "step": 246500 }, { "epoch": 0.82, - "learning_rate": 9.1394428648122e-06, - "loss": 3.2066, + "learning_rate": 9.183808584310429e-06, + "loss": 3.1816, "step": 246600 }, { "epoch": 0.82, - "learning_rate": 9.12287329581983e-06, - "loss": 3.2019, + "learning_rate": 9.167257006282979e-06, + "loss": 3.1818, "step": 246700 }, { "epoch": 0.82, - "learning_rate": 9.106303726827459e-06, - "loss": 3.2203, + "learning_rate": 9.15070542825553e-06, + "loss": 3.1901, "step": 246800 }, { "epoch": 0.82, - "learning_rate": 9.089734157835086e-06, - "loss": 3.2037, + "learning_rate": 9.134153850228082e-06, + "loss": 3.1884, "step": 246900 }, { "epoch": 0.82, - "learning_rate": 9.073164588842715e-06, - "loss": 3.209, + "learning_rate": 9.117602272200632e-06, + "loss": 3.1903, "step": 247000 }, { "epoch": 0.82, - "learning_rate": 9.056595019850344e-06, - "loss": 3.2121, + "learning_rate": 9.101050694173182e-06, + "loss": 3.1834, "step": 247100 }, { "epoch": 0.82, - "learning_rate": 9.040025450857972e-06, - "loss": 3.2017, + "learning_rate": 9.084499116145733e-06, + "loss": 3.1866, "step": 247200 }, { "epoch": 0.82, - "learning_rate": 9.023455881865601e-06, - "loss": 3.2235, + "learning_rate": 9.067947538118285e-06, + "loss": 3.1875, "step": 247300 }, { "epoch": 0.82, - "learning_rate": 9.00688631287323e-06, - "loss": 3.2089, + "learning_rate": 9.051395960090837e-06, + "loss": 3.1894, "step": 247400 }, { "epoch": 0.82, - "learning_rate": 8.990316743880858e-06, - "loss": 3.1986, + "learning_rate": 9.034844382063385e-06, + "loss": 3.1651, "step": 247500 }, { "epoch": 0.82, - "learning_rate": 8.973747174888487e-06, - "loss": 3.2099, + "learning_rate": 9.018292804035936e-06, + "loss": 3.1904, "step": 247600 }, { "epoch": 0.82, - "learning_rate": 8.957177605896116e-06, - "loss": 3.1863, + "learning_rate": 9.001741226008488e-06, + "loss": 3.1786, "step": 247700 }, { "epoch": 0.82, - "learning_rate": 8.940608036903744e-06, - "loss": 3.2018, + "learning_rate": 8.98518964798104e-06, + "loss": 3.1867, "step": 247800 }, { "epoch": 0.82, - "learning_rate": 8.924038467911373e-06, - "loss": 3.201, + "learning_rate": 8.96863806995359e-06, + "loss": 3.1903, "step": 247900 }, { "epoch": 0.82, - "learning_rate": 8.907468898919e-06, - "loss": 3.1937, + "learning_rate": 8.952086491926141e-06, + "loss": 3.1798, "step": 248000 }, { "epoch": 0.82, - "learning_rate": 8.89089932992663e-06, - "loss": 3.1958, + "learning_rate": 8.935534913898691e-06, + "loss": 3.1833, "step": 248100 }, { "epoch": 0.82, - "learning_rate": 8.874329760934259e-06, - "loss": 3.1989, + "learning_rate": 8.918983335871243e-06, + "loss": 3.1716, "step": 248200 }, { "epoch": 0.82, - "learning_rate": 8.857760191941886e-06, - "loss": 3.2101, + "learning_rate": 8.902431757843793e-06, + "loss": 3.1831, "step": 248300 }, { "epoch": 0.82, - "learning_rate": 8.841190622949516e-06, - "loss": 3.1967, + "learning_rate": 8.885880179816344e-06, + "loss": 3.1886, "step": 248400 }, { "epoch": 0.82, - "learning_rate": 8.824621053957145e-06, - "loss": 3.201, + "learning_rate": 8.869328601788896e-06, + "loss": 3.1785, "step": 248500 }, { "epoch": 0.82, - "learning_rate": 8.808051484964772e-06, - "loss": 3.2023, + "learning_rate": 8.852777023761446e-06, + "loss": 3.1986, "step": 248600 }, { "epoch": 0.82, - "learning_rate": 8.791481915972402e-06, - "loss": 3.2087, + "learning_rate": 8.836225445733996e-06, + "loss": 3.1952, "step": 248700 }, { "epoch": 0.82, - "learning_rate": 8.77491234698003e-06, - "loss": 3.1992, + "learning_rate": 8.819673867706547e-06, + "loss": 3.177, "step": 248800 }, { "epoch": 0.82, - "learning_rate": 8.758342777987658e-06, - "loss": 3.1887, + "learning_rate": 8.803122289679099e-06, + "loss": 3.1782, "step": 248900 }, { - "epoch": 0.83, - "learning_rate": 8.741773208995288e-06, - "loss": 3.1964, + "epoch": 0.82, + "learning_rate": 8.78657071165165e-06, + "loss": 3.1952, "step": 249000 }, { - "epoch": 0.83, - "learning_rate": 8.725203640002917e-06, - "loss": 3.2034, + "epoch": 0.82, + "learning_rate": 8.7700191336242e-06, + "loss": 3.1952, "step": 249100 }, { - "epoch": 0.83, - "learning_rate": 8.708634071010544e-06, - "loss": 3.1985, + "epoch": 0.82, + "learning_rate": 8.75346755559675e-06, + "loss": 3.189, "step": 249200 }, { "epoch": 0.83, - "learning_rate": 8.692064502018173e-06, - "loss": 3.2018, + "learning_rate": 8.736915977569302e-06, + "loss": 3.1787, "step": 249300 }, { "epoch": 0.83, - "learning_rate": 8.675494933025803e-06, - "loss": 3.2133, + "learning_rate": 8.720364399541853e-06, + "loss": 3.1852, "step": 249400 }, { "epoch": 0.83, - "learning_rate": 8.65892536403343e-06, - "loss": 3.1963, + "learning_rate": 8.703812821514403e-06, + "loss": 3.1992, "step": 249500 }, { "epoch": 0.83, - "learning_rate": 8.64235579504106e-06, - "loss": 3.1949, + "learning_rate": 8.687261243486955e-06, + "loss": 3.1881, "step": 249600 }, { "epoch": 0.83, - "learning_rate": 8.625786226048689e-06, - "loss": 3.2099, + "learning_rate": 8.670709665459505e-06, + "loss": 3.1877, "step": 249700 }, { "epoch": 0.83, - "learning_rate": 8.609216657056316e-06, - "loss": 3.2079, + "learning_rate": 8.654158087432056e-06, + "loss": 3.2009, "step": 249800 }, { "epoch": 0.83, - "learning_rate": 8.592647088063945e-06, - "loss": 3.1977, + "learning_rate": 8.637606509404606e-06, + "loss": 3.1878, "step": 249900 }, { "epoch": 0.83, - "learning_rate": 8.576077519071573e-06, - "loss": 3.1937, + "learning_rate": 8.621054931377158e-06, + "loss": 3.2031, "step": 250000 }, { "epoch": 0.83, - "learning_rate": 8.559507950079202e-06, - "loss": 3.2079, + "learning_rate": 8.60450335334971e-06, + "loss": 3.17, "step": 250100 }, { "epoch": 0.83, - "learning_rate": 8.542938381086831e-06, - "loss": 3.2087, + "learning_rate": 8.58795177532226e-06, + "loss": 3.1851, "step": 250200 }, { "epoch": 0.83, - "learning_rate": 8.52636881209446e-06, - "loss": 3.1957, + "learning_rate": 8.57140019729481e-06, + "loss": 3.1726, "step": 250300 }, { "epoch": 0.83, - "learning_rate": 8.509799243102088e-06, - "loss": 3.2, + "learning_rate": 8.554848619267361e-06, + "loss": 3.1813, "step": 250400 }, { "epoch": 0.83, - "learning_rate": 8.493229674109717e-06, - "loss": 3.1944, + "learning_rate": 8.538297041239913e-06, + "loss": 3.1961, "step": 250500 }, { "epoch": 0.83, - "learning_rate": 8.476660105117346e-06, - "loss": 3.1983, + "learning_rate": 8.521745463212462e-06, + "loss": 3.1915, "step": 250600 }, { "epoch": 0.83, - "learning_rate": 8.460090536124974e-06, - "loss": 3.2095, + "learning_rate": 8.505193885185014e-06, + "loss": 3.1872, "step": 250700 }, { "epoch": 0.83, - "learning_rate": 8.443520967132603e-06, - "loss": 3.1867, + "learning_rate": 8.488642307157566e-06, + "loss": 3.1696, "step": 250800 }, { "epoch": 0.83, - "learning_rate": 8.426951398140232e-06, - "loss": 3.1876, + "learning_rate": 8.472090729130116e-06, + "loss": 3.189, "step": 250900 }, { "epoch": 0.83, - "learning_rate": 8.41038182914786e-06, - "loss": 3.1878, + "learning_rate": 8.455539151102665e-06, + "loss": 3.1898, "step": 251000 }, { "epoch": 0.83, - "learning_rate": 8.393812260155489e-06, - "loss": 3.204, + "learning_rate": 8.438987573075217e-06, + "loss": 3.1839, "step": 251100 }, { "epoch": 0.83, - "learning_rate": 8.377242691163118e-06, - "loss": 3.1925, + "learning_rate": 8.422435995047769e-06, + "loss": 3.1821, "step": 251200 }, { "epoch": 0.83, - "learning_rate": 8.360673122170746e-06, - "loss": 3.1958, + "learning_rate": 8.40588441702032e-06, + "loss": 3.1936, "step": 251300 }, { "epoch": 0.83, - "learning_rate": 8.344103553178375e-06, - "loss": 3.1978, + "learning_rate": 8.38933283899287e-06, + "loss": 3.1867, "step": 251400 }, { "epoch": 0.83, - "learning_rate": 8.327533984186004e-06, - "loss": 3.1858, + "learning_rate": 8.37278126096542e-06, + "loss": 3.1925, "step": 251500 }, { "epoch": 0.83, - "learning_rate": 8.310964415193633e-06, - "loss": 3.2066, + "learning_rate": 8.356229682937972e-06, + "loss": 3.189, "step": 251600 }, { "epoch": 0.83, - "learning_rate": 8.29439484620126e-06, - "loss": 3.2071, + "learning_rate": 8.339678104910523e-06, + "loss": 3.1953, "step": 251700 }, { "epoch": 0.83, - "learning_rate": 8.27782527720889e-06, - "loss": 3.1957, + "learning_rate": 8.323126526883073e-06, + "loss": 3.1857, "step": 251800 }, { "epoch": 0.83, - "learning_rate": 8.26125570821652e-06, - "loss": 3.1972, + "learning_rate": 8.306574948855625e-06, + "loss": 3.1825, "step": 251900 }, { - "epoch": 0.84, - "learning_rate": 8.244686139224147e-06, - "loss": 3.1925, + "epoch": 0.83, + "learning_rate": 8.290023370828175e-06, + "loss": 3.1743, "step": 252000 }, { - "epoch": 0.84, - "learning_rate": 8.228116570231776e-06, - "loss": 3.1924, + "epoch": 0.83, + "learning_rate": 8.273471792800726e-06, + "loss": 3.1875, "step": 252100 }, { - "epoch": 0.84, - "learning_rate": 8.211547001239405e-06, - "loss": 3.196, + "epoch": 0.83, + "learning_rate": 8.256920214773276e-06, + "loss": 3.181, "step": 252200 }, { "epoch": 0.84, - "learning_rate": 8.194977432247033e-06, - "loss": 3.1984, + "learning_rate": 8.240368636745828e-06, + "loss": 3.1896, "step": 252300 }, { "epoch": 0.84, - "learning_rate": 8.178407863254662e-06, - "loss": 3.1963, + "learning_rate": 8.22381705871838e-06, + "loss": 3.1853, "step": 252400 }, { "epoch": 0.84, - "learning_rate": 8.161838294262291e-06, - "loss": 3.1956, + "learning_rate": 8.20726548069093e-06, + "loss": 3.1857, "step": 252500 }, { "epoch": 0.84, - "learning_rate": 8.145268725269919e-06, - "loss": 3.2056, + "learning_rate": 8.19071390266348e-06, + "loss": 3.1808, "step": 252600 }, { "epoch": 0.84, - "learning_rate": 8.128699156277548e-06, - "loss": 3.204, + "learning_rate": 8.17416232463603e-06, + "loss": 3.1771, "step": 252700 }, { "epoch": 0.84, - "learning_rate": 8.112129587285177e-06, - "loss": 3.1987, + "learning_rate": 8.157610746608582e-06, + "loss": 3.2018, "step": 252800 }, { "epoch": 0.84, - "learning_rate": 8.095560018292805e-06, - "loss": 3.206, + "learning_rate": 8.141059168581134e-06, + "loss": 3.1917, "step": 252900 }, { "epoch": 0.84, - "learning_rate": 8.078990449300434e-06, - "loss": 3.21, + "learning_rate": 8.124507590553684e-06, + "loss": 3.1882, "step": 253000 }, { "epoch": 0.84, - "learning_rate": 8.062420880308063e-06, - "loss": 3.1935, + "learning_rate": 8.107956012526234e-06, + "loss": 3.1986, "step": 253100 }, { "epoch": 0.84, - "learning_rate": 8.04585131131569e-06, - "loss": 3.2134, + "learning_rate": 8.091404434498785e-06, + "loss": 3.1932, "step": 253200 }, { "epoch": 0.84, - "learning_rate": 8.02928174232332e-06, - "loss": 3.2063, + "learning_rate": 8.074852856471337e-06, + "loss": 3.1961, "step": 253300 }, { "epoch": 0.84, - "learning_rate": 8.012712173330949e-06, - "loss": 3.2013, + "learning_rate": 8.058301278443887e-06, + "loss": 3.1845, "step": 253400 }, { "epoch": 0.84, - "learning_rate": 7.996142604338576e-06, - "loss": 3.2077, + "learning_rate": 8.041749700416439e-06, + "loss": 3.1815, "step": 253500 }, { "epoch": 0.84, - "learning_rate": 7.979573035346206e-06, - "loss": 3.206, + "learning_rate": 8.025198122388988e-06, + "loss": 3.1863, "step": 253600 }, { "epoch": 0.84, - "learning_rate": 7.963003466353835e-06, - "loss": 3.1939, + "learning_rate": 8.00864654436154e-06, + "loss": 3.1886, "step": 253700 }, { "epoch": 0.84, - "learning_rate": 7.946433897361462e-06, - "loss": 3.191, + "learning_rate": 7.99209496633409e-06, + "loss": 3.1878, "step": 253800 }, { "epoch": 0.84, - "learning_rate": 7.929864328369092e-06, - "loss": 3.1991, + "learning_rate": 7.975543388306642e-06, + "loss": 3.1726, "step": 253900 }, { "epoch": 0.84, - "learning_rate": 7.91329475937672e-06, - "loss": 3.2004, + "learning_rate": 7.958991810279193e-06, + "loss": 3.2059, "step": 254000 }, { "epoch": 0.84, - "learning_rate": 7.896725190384348e-06, - "loss": 3.1892, + "learning_rate": 7.942440232251743e-06, + "loss": 3.1758, "step": 254100 }, { "epoch": 0.84, - "learning_rate": 7.880155621391977e-06, - "loss": 3.1907, + "learning_rate": 7.925888654224293e-06, + "loss": 3.1719, "step": 254200 }, { "epoch": 0.84, - "learning_rate": 7.863586052399607e-06, - "loss": 3.2009, + "learning_rate": 7.909337076196845e-06, + "loss": 3.1998, "step": 254300 }, { "epoch": 0.84, - "learning_rate": 7.847016483407234e-06, - "loss": 3.1993, + "learning_rate": 7.892785498169396e-06, + "loss": 3.1951, "step": 254400 }, { "epoch": 0.84, - "learning_rate": 7.830446914414863e-06, - "loss": 3.2089, + "learning_rate": 7.876233920141946e-06, + "loss": 3.1734, "step": 254500 }, { "epoch": 0.84, - "learning_rate": 7.813877345422491e-06, - "loss": 3.1968, + "learning_rate": 7.859682342114498e-06, + "loss": 3.1689, "step": 254600 }, { "epoch": 0.84, - "learning_rate": 7.79730777643012e-06, - "loss": 3.2019, + "learning_rate": 7.84313076408705e-06, + "loss": 3.192, "step": 254700 }, { "epoch": 0.84, - "learning_rate": 7.78073820743775e-06, - "loss": 3.2021, + "learning_rate": 7.8265791860596e-06, + "loss": 3.1949, "step": 254800 }, { "epoch": 0.84, - "learning_rate": 7.764168638445377e-06, - "loss": 3.2017, + "learning_rate": 7.81002760803215e-06, + "loss": 3.1914, "step": 254900 }, { - "epoch": 0.85, - "learning_rate": 7.747599069453006e-06, - "loss": 3.2069, + "epoch": 0.84, + "learning_rate": 7.7934760300047e-06, + "loss": 3.1821, "step": 255000 }, { - "epoch": 0.85, - "learning_rate": 7.731029500460635e-06, - "loss": 3.2048, + "epoch": 0.84, + "learning_rate": 7.776924451977252e-06, + "loss": 3.1854, "step": 255100 }, { - "epoch": 0.85, - "learning_rate": 7.714459931468263e-06, - "loss": 3.2125, + "epoch": 0.84, + "learning_rate": 7.760372873949804e-06, + "loss": 3.1878, "step": 255200 }, { "epoch": 0.85, - "learning_rate": 7.697890362475892e-06, - "loss": 3.2086, + "learning_rate": 7.743821295922354e-06, + "loss": 3.1763, "step": 255300 }, { "epoch": 0.85, - "learning_rate": 7.681320793483521e-06, - "loss": 3.2043, + "learning_rate": 7.727269717894904e-06, + "loss": 3.1903, "step": 255400 }, { "epoch": 0.85, - "learning_rate": 7.664751224491149e-06, - "loss": 3.1995, + "learning_rate": 7.710718139867455e-06, + "loss": 3.1911, "step": 255500 }, { "epoch": 0.85, - "learning_rate": 7.648181655498778e-06, - "loss": 3.2046, + "learning_rate": 7.694166561840007e-06, + "loss": 3.1826, "step": 255600 }, { "epoch": 0.85, - "learning_rate": 7.631612086506407e-06, - "loss": 3.2028, + "learning_rate": 7.677614983812557e-06, + "loss": 3.1733, "step": 255700 }, { "epoch": 0.85, - "learning_rate": 7.6150425175140345e-06, - "loss": 3.2075, + "learning_rate": 7.661063405785108e-06, + "loss": 3.1917, "step": 255800 }, { "epoch": 0.85, - "learning_rate": 7.598472948521664e-06, - "loss": 3.1995, + "learning_rate": 7.644511827757658e-06, + "loss": 3.1704, "step": 255900 }, { "epoch": 0.85, - "learning_rate": 7.581903379529293e-06, - "loss": 3.211, + "learning_rate": 7.627960249730209e-06, + "loss": 3.1866, "step": 256000 }, { "epoch": 0.85, - "learning_rate": 7.5653338105369205e-06, - "loss": 3.1842, + "learning_rate": 7.611408671702761e-06, + "loss": 3.1873, "step": 256100 }, { "epoch": 0.85, - "learning_rate": 7.54876424154455e-06, - "loss": 3.1958, + "learning_rate": 7.5948570936753114e-06, + "loss": 3.1857, "step": 256200 }, { "epoch": 0.85, - "learning_rate": 7.532194672552179e-06, - "loss": 3.2064, + "learning_rate": 7.578305515647863e-06, + "loss": 3.1886, "step": 256300 }, { "epoch": 0.85, - "learning_rate": 7.515625103559806e-06, - "loss": 3.1934, + "learning_rate": 7.561753937620412e-06, + "loss": 3.1761, "step": 256400 }, { "epoch": 0.85, - "learning_rate": 7.499055534567436e-06, - "loss": 3.1988, + "learning_rate": 7.545202359592964e-06, + "loss": 3.1766, "step": 256500 }, { "epoch": 0.85, - "learning_rate": 7.482485965575063e-06, - "loss": 3.2002, + "learning_rate": 7.5286507815655144e-06, + "loss": 3.1841, "step": 256600 }, { "epoch": 0.85, - "learning_rate": 7.465916396582692e-06, - "loss": 3.2069, + "learning_rate": 7.512099203538066e-06, + "loss": 3.1859, "step": 256700 }, { "epoch": 0.85, - "learning_rate": 7.4493468275903215e-06, - "loss": 3.1969, + "learning_rate": 7.495547625510617e-06, + "loss": 3.1783, "step": 256800 }, { "epoch": 0.85, - "learning_rate": 7.432777258597949e-06, - "loss": 3.2161, + "learning_rate": 7.478996047483168e-06, + "loss": 3.1809, "step": 256900 }, { "epoch": 0.85, - "learning_rate": 7.416207689605578e-06, - "loss": 3.1883, + "learning_rate": 7.4624444694557175e-06, + "loss": 3.1788, "step": 257000 }, { "epoch": 0.85, - "learning_rate": 7.3996381206132074e-06, - "loss": 3.1967, + "learning_rate": 7.445892891428269e-06, + "loss": 3.1835, "step": 257100 }, { "epoch": 0.85, - "learning_rate": 7.383068551620835e-06, - "loss": 3.1958, + "learning_rate": 7.42934131340082e-06, + "loss": 3.1904, "step": 257200 }, { "epoch": 0.85, - "learning_rate": 7.366498982628464e-06, - "loss": 3.2047, + "learning_rate": 7.412789735373371e-06, + "loss": 3.1845, "step": 257300 }, { "epoch": 0.85, - "learning_rate": 7.349929413636093e-06, - "loss": 3.2122, + "learning_rate": 7.396238157345922e-06, + "loss": 3.1843, "step": 257400 }, { "epoch": 0.85, - "learning_rate": 7.333359844643721e-06, - "loss": 3.1884, + "learning_rate": 7.379686579318472e-06, + "loss": 3.1718, "step": 257500 }, { "epoch": 0.85, - "learning_rate": 7.31679027565135e-06, - "loss": 3.198, + "learning_rate": 7.363135001291023e-06, + "loss": 3.1828, "step": 257600 }, { "epoch": 0.85, - "learning_rate": 7.300220706658979e-06, - "loss": 3.1932, + "learning_rate": 7.346583423263574e-06, + "loss": 3.1854, "step": 257700 }, { "epoch": 0.85, - "learning_rate": 7.283651137666607e-06, - "loss": 3.1862, + "learning_rate": 7.330031845236125e-06, + "loss": 3.187, "step": 257800 }, { "epoch": 0.85, - "learning_rate": 7.267081568674236e-06, - "loss": 3.211, + "learning_rate": 7.313480267208677e-06, + "loss": 3.1744, "step": 257900 }, { "epoch": 0.85, - "learning_rate": 7.250511999681865e-06, - "loss": 3.2244, + "learning_rate": 7.2969286891812275e-06, + "loss": 3.1657, "step": 258000 }, { - "epoch": 0.86, - "learning_rate": 7.233942430689493e-06, - "loss": 3.1907, + "epoch": 0.85, + "learning_rate": 7.2803771111537774e-06, + "loss": 3.1939, "step": 258100 }, { - "epoch": 0.86, - "learning_rate": 7.217372861697122e-06, - "loss": 3.2034, + "epoch": 0.85, + "learning_rate": 7.263825533126328e-06, + "loss": 3.1844, "step": 258200 }, { "epoch": 0.86, - "learning_rate": 7.200803292704751e-06, - "loss": 3.1948, + "learning_rate": 7.24727395509888e-06, + "loss": 3.1878, "step": 258300 }, { "epoch": 0.86, - "learning_rate": 7.184233723712379e-06, - "loss": 3.2051, + "learning_rate": 7.2307223770714305e-06, + "loss": 3.1892, "step": 258400 }, { "epoch": 0.86, - "learning_rate": 7.167664154720008e-06, - "loss": 3.2098, + "learning_rate": 7.214170799043981e-06, + "loss": 3.1698, "step": 258500 }, { "epoch": 0.86, - "learning_rate": 7.151094585727637e-06, - "loss": 3.1924, + "learning_rate": 7.197619221016533e-06, + "loss": 3.1632, "step": 258600 }, { "epoch": 0.86, - "learning_rate": 7.1345250167352646e-06, - "loss": 3.2036, + "learning_rate": 7.181067642989083e-06, + "loss": 3.1843, "step": 258700 }, { "epoch": 0.86, - "learning_rate": 7.117955447742894e-06, - "loss": 3.187, + "learning_rate": 7.1645160649616336e-06, + "loss": 3.1959, "step": 258800 }, { "epoch": 0.86, - "learning_rate": 7.101385878750521e-06, - "loss": 3.1963, + "learning_rate": 7.147964486934184e-06, + "loss": 3.1903, "step": 258900 }, { "epoch": 0.86, - "learning_rate": 7.0848163097581505e-06, - "loss": 3.198, + "learning_rate": 7.131412908906736e-06, + "loss": 3.1829, "step": 259000 }, { "epoch": 0.86, - "learning_rate": 7.06824674076578e-06, - "loss": 3.2008, + "learning_rate": 7.114861330879287e-06, + "loss": 3.1839, "step": 259100 }, { "epoch": 0.86, - "learning_rate": 7.051677171773407e-06, - "loss": 3.1906, + "learning_rate": 7.0983097528518366e-06, + "loss": 3.1945, "step": 259200 }, { "epoch": 0.86, - "learning_rate": 7.035107602781036e-06, - "loss": 3.1933, + "learning_rate": 7.081758174824388e-06, + "loss": 3.1974, "step": 259300 }, { "epoch": 0.86, - "learning_rate": 7.018538033788666e-06, - "loss": 3.187, + "learning_rate": 7.065206596796939e-06, + "loss": 3.1901, "step": 259400 }, { "epoch": 0.86, - "learning_rate": 7.001968464796293e-06, - "loss": 3.2086, + "learning_rate": 7.04865501876949e-06, + "loss": 3.199, "step": 259500 }, { "epoch": 0.86, - "learning_rate": 6.985398895803922e-06, - "loss": 3.1764, + "learning_rate": 7.032103440742041e-06, + "loss": 3.1789, "step": 259600 }, { "epoch": 0.86, - "learning_rate": 6.9688293268115515e-06, - "loss": 3.2072, + "learning_rate": 7.015551862714592e-06, + "loss": 3.1926, "step": 259700 }, { "epoch": 0.86, - "learning_rate": 6.95225975781918e-06, - "loss": 3.1944, + "learning_rate": 6.999000284687142e-06, + "loss": 3.1913, "step": 259800 }, { "epoch": 0.86, - "learning_rate": 6.935690188826808e-06, - "loss": 3.2033, + "learning_rate": 6.982448706659693e-06, + "loss": 3.1772, "step": 259900 }, { "epoch": 0.86, - "learning_rate": 6.9191206198344375e-06, - "loss": 3.1849, + "learning_rate": 6.965897128632244e-06, + "loss": 3.1949, "step": 260000 }, { "epoch": 0.86, - "learning_rate": 6.902551050842066e-06, - "loss": 3.2032, + "learning_rate": 6.949345550604795e-06, + "loss": 3.198, "step": 260100 }, { "epoch": 0.86, - "learning_rate": 6.885981481849694e-06, - "loss": 3.1968, + "learning_rate": 6.932793972577347e-06, + "loss": 3.1874, "step": 260200 }, { "epoch": 0.86, - "learning_rate": 6.869411912857323e-06, - "loss": 3.1946, + "learning_rate": 6.916242394549896e-06, + "loss": 3.1878, "step": 260300 }, { "epoch": 0.86, - "learning_rate": 6.852842343864952e-06, - "loss": 3.2021, + "learning_rate": 6.899690816522447e-06, + "loss": 3.1917, "step": 260400 }, { "epoch": 0.86, - "learning_rate": 6.83627277487258e-06, - "loss": 3.1977, + "learning_rate": 6.883139238494998e-06, + "loss": 3.1871, "step": 260500 }, { "epoch": 0.86, - "learning_rate": 6.819703205880209e-06, - "loss": 3.1991, + "learning_rate": 6.86658766046755e-06, + "loss": 3.1729, "step": 260600 }, { "epoch": 0.86, - "learning_rate": 6.803133636887838e-06, - "loss": 3.188, + "learning_rate": 6.8500360824401e-06, + "loss": 3.1989, "step": 260700 }, { "epoch": 0.86, - "learning_rate": 6.786564067895466e-06, - "loss": 3.1872, + "learning_rate": 6.833484504412652e-06, + "loss": 3.1959, "step": 260800 }, { "epoch": 0.86, - "learning_rate": 6.769994498903094e-06, - "loss": 3.2008, + "learning_rate": 6.816932926385201e-06, + "loss": 3.1952, "step": 260900 }, { "epoch": 0.86, - "learning_rate": 6.753424929910724e-06, - "loss": 3.2057, + "learning_rate": 6.800381348357753e-06, + "loss": 3.1985, "step": 261000 }, { - "epoch": 0.87, - "learning_rate": 6.736855360918353e-06, - "loss": 3.1991, + "epoch": 0.86, + "learning_rate": 6.783829770330303e-06, + "loss": 3.1762, "step": 261100 }, { - "epoch": 0.87, - "learning_rate": 6.72028579192598e-06, - "loss": 3.204, + "epoch": 0.86, + "learning_rate": 6.767278192302855e-06, + "loss": 3.1956, "step": 261200 }, { - "epoch": 0.87, - "learning_rate": 6.7037162229336095e-06, - "loss": 3.2068, + "epoch": 0.86, + "learning_rate": 6.750726614275406e-06, + "loss": 3.1893, "step": 261300 }, { "epoch": 0.87, - "learning_rate": 6.687146653941239e-06, - "loss": 3.1978, + "learning_rate": 6.734175036247956e-06, + "loss": 3.1752, "step": 261400 }, { "epoch": 0.87, - "learning_rate": 6.670577084948866e-06, - "loss": 3.2118, + "learning_rate": 6.7176234582205064e-06, + "loss": 3.1878, "step": 261500 }, { "epoch": 0.87, - "learning_rate": 6.6540075159564954e-06, - "loss": 3.2004, + "learning_rate": 6.701071880193058e-06, + "loss": 3.1834, "step": 261600 }, { "epoch": 0.87, - "learning_rate": 6.637437946964125e-06, - "loss": 3.2003, + "learning_rate": 6.684520302165609e-06, + "loss": 3.1879, "step": 261700 }, { "epoch": 0.87, - "learning_rate": 6.620868377971752e-06, - "loss": 3.1993, + "learning_rate": 6.66796872413816e-06, + "loss": 3.1865, "step": 261800 }, { "epoch": 0.87, - "learning_rate": 6.604298808979381e-06, - "loss": 3.1891, + "learning_rate": 6.651417146110711e-06, + "loss": 3.1738, "step": 261900 }, { "epoch": 0.87, - "learning_rate": 6.5877292399870106e-06, - "loss": 3.205, + "learning_rate": 6.634865568083261e-06, + "loss": 3.1809, "step": 262000 }, { "epoch": 0.87, - "learning_rate": 6.571159670994638e-06, - "loss": 3.1891, + "learning_rate": 6.618313990055812e-06, + "loss": 3.1829, "step": 262100 }, { "epoch": 0.87, - "learning_rate": 6.554590102002267e-06, - "loss": 3.2069, + "learning_rate": 6.601762412028363e-06, + "loss": 3.1961, "step": 262200 }, { "epoch": 0.87, - "learning_rate": 6.5380205330098965e-06, - "loss": 3.1997, + "learning_rate": 6.585210834000914e-06, + "loss": 3.1817, "step": 262300 }, { "epoch": 0.87, - "learning_rate": 6.521450964017524e-06, - "loss": 3.1968, + "learning_rate": 6.568659255973465e-06, + "loss": 3.1887, "step": 262400 }, { "epoch": 0.87, - "learning_rate": 6.504881395025153e-06, - "loss": 3.2007, + "learning_rate": 6.5521076779460165e-06, + "loss": 3.1741, "step": 262500 }, { "epoch": 0.87, - "learning_rate": 6.488311826032782e-06, - "loss": 3.2007, + "learning_rate": 6.535556099918566e-06, + "loss": 3.1958, "step": 262600 }, { "epoch": 0.87, - "learning_rate": 6.47174225704041e-06, - "loss": 3.1845, + "learning_rate": 6.519004521891117e-06, + "loss": 3.1814, "step": 262700 }, { "epoch": 0.87, - "learning_rate": 6.455172688048039e-06, - "loss": 3.2023, + "learning_rate": 6.502452943863668e-06, + "loss": 3.1725, "step": 262800 }, { "epoch": 0.87, - "learning_rate": 6.438603119055668e-06, - "loss": 3.2095, + "learning_rate": 6.4859013658362195e-06, + "loss": 3.1868, "step": 262900 }, { "epoch": 0.87, - "learning_rate": 6.422033550063296e-06, - "loss": 3.2095, + "learning_rate": 6.46934978780877e-06, + "loss": 3.1795, "step": 263000 }, { "epoch": 0.87, - "learning_rate": 6.405463981070925e-06, - "loss": 3.1914, + "learning_rate": 6.45279820978132e-06, + "loss": 3.1872, "step": 263100 }, { "epoch": 0.87, - "learning_rate": 6.3888944120785526e-06, - "loss": 3.1991, + "learning_rate": 6.436246631753872e-06, + "loss": 3.1832, "step": 263200 }, { "epoch": 0.87, - "learning_rate": 6.372324843086182e-06, - "loss": 3.1961, + "learning_rate": 6.4196950537264225e-06, + "loss": 3.1798, "step": 263300 }, { "epoch": 0.87, - "learning_rate": 6.355755274093811e-06, - "loss": 3.1998, + "learning_rate": 6.403143475698973e-06, + "loss": 3.1852, "step": 263400 }, { "epoch": 0.87, - "learning_rate": 6.3391857051014385e-06, - "loss": 3.1975, + "learning_rate": 6.386591897671525e-06, + "loss": 3.1785, "step": 263500 }, { "epoch": 0.87, - "learning_rate": 6.322616136109068e-06, - "loss": 3.1991, + "learning_rate": 6.370040319644076e-06, + "loss": 3.188, "step": 263600 }, { "epoch": 0.87, - "learning_rate": 6.306046567116697e-06, - "loss": 3.2056, + "learning_rate": 6.3534887416166255e-06, + "loss": 3.1724, "step": 263700 }, { "epoch": 0.87, - "learning_rate": 6.289476998124324e-06, - "loss": 3.2045, + "learning_rate": 6.336937163589176e-06, + "loss": 3.1956, "step": 263800 }, { "epoch": 0.87, - "learning_rate": 6.272907429131954e-06, - "loss": 3.1925, + "learning_rate": 6.320385585561728e-06, + "loss": 3.1808, "step": 263900 }, { "epoch": 0.87, - "learning_rate": 6.256337860139583e-06, - "loss": 3.2032, + "learning_rate": 6.303834007534279e-06, + "loss": 3.1782, "step": 264000 }, { - "epoch": 0.88, - "learning_rate": 6.239768291147211e-06, - "loss": 3.193, + "epoch": 0.87, + "learning_rate": 6.28728242950683e-06, + "loss": 3.1882, "step": 264100 }, { - "epoch": 0.88, - "learning_rate": 6.2231987221548395e-06, - "loss": 3.2059, + "epoch": 0.87, + "learning_rate": 6.270730851479379e-06, + "loss": 3.2035, "step": 264200 }, { - "epoch": 0.88, - "learning_rate": 6.206629153162468e-06, - "loss": 3.1985, + "epoch": 0.87, + "learning_rate": 6.254179273451931e-06, + "loss": 3.1898, "step": 264300 }, { "epoch": 0.88, - "learning_rate": 6.190059584170097e-06, - "loss": 3.2031, + "learning_rate": 6.237627695424482e-06, + "loss": 3.166, "step": 264400 }, { "epoch": 0.88, - "learning_rate": 6.1734900151777255e-06, - "loss": 3.2033, + "learning_rate": 6.221076117397033e-06, + "loss": 3.1913, "step": 264500 }, { "epoch": 0.88, - "learning_rate": 6.156920446185354e-06, - "loss": 3.1953, + "learning_rate": 6.204524539369583e-06, + "loss": 3.1954, "step": 264600 }, { "epoch": 0.88, - "learning_rate": 6.140350877192982e-06, - "loss": 3.2069, + "learning_rate": 6.187972961342135e-06, + "loss": 3.2031, "step": 264700 }, { "epoch": 0.88, - "learning_rate": 6.123781308200611e-06, - "loss": 3.2004, + "learning_rate": 6.1714213833146855e-06, + "loss": 3.1892, "step": 264800 }, { "epoch": 0.88, - "learning_rate": 6.10721173920824e-06, - "loss": 3.1999, + "learning_rate": 6.154869805287236e-06, + "loss": 3.1832, "step": 264900 }, { "epoch": 0.88, - "learning_rate": 6.090642170215868e-06, - "loss": 3.2048, + "learning_rate": 6.138318227259787e-06, + "loss": 3.1861, "step": 265000 }, { "epoch": 0.88, - "learning_rate": 6.074072601223497e-06, - "loss": 3.2061, + "learning_rate": 6.121766649232339e-06, + "loss": 3.1859, "step": 265100 }, { "epoch": 0.88, - "learning_rate": 6.057503032231126e-06, - "loss": 3.1851, + "learning_rate": 6.1052150712048885e-06, + "loss": 3.1758, "step": 265200 }, { "epoch": 0.88, - "learning_rate": 6.040933463238754e-06, - "loss": 3.201, + "learning_rate": 6.08866349317744e-06, + "loss": 3.1898, "step": 265300 }, { "epoch": 0.88, - "learning_rate": 6.024363894246383e-06, - "loss": 3.2028, + "learning_rate": 6.072111915149991e-06, + "loss": 3.1844, "step": 265400 }, { "epoch": 0.88, - "learning_rate": 6.007794325254012e-06, - "loss": 3.2002, + "learning_rate": 6.055560337122542e-06, + "loss": 3.1839, "step": 265500 }, { "epoch": 0.88, - "learning_rate": 5.99122475626164e-06, - "loss": 3.1904, + "learning_rate": 6.039008759095092e-06, + "loss": 3.1746, "step": 265600 }, { "epoch": 0.88, - "learning_rate": 5.974655187269269e-06, - "loss": 3.1885, + "learning_rate": 6.022457181067644e-06, + "loss": 3.1839, "step": 265700 }, { "epoch": 0.88, - "learning_rate": 5.9580856182768975e-06, - "loss": 3.1876, + "learning_rate": 6.005905603040194e-06, + "loss": 3.1822, "step": 265800 }, { "epoch": 0.88, - "learning_rate": 5.941516049284526e-06, - "loss": 3.2017, + "learning_rate": 5.9893540250127455e-06, + "loss": 3.1824, "step": 265900 }, { "epoch": 0.88, - "learning_rate": 5.924946480292154e-06, - "loss": 3.1939, + "learning_rate": 5.972802446985295e-06, + "loss": 3.1711, "step": 266000 }, { "epoch": 0.88, - "learning_rate": 5.9083769112997834e-06, - "loss": 3.1861, + "learning_rate": 5.956250868957847e-06, + "loss": 3.183, "step": 266100 }, { "epoch": 0.88, - "learning_rate": 5.891807342307412e-06, - "loss": 3.2075, + "learning_rate": 5.939699290930398e-06, + "loss": 3.1901, "step": 266200 }, { "epoch": 0.88, - "learning_rate": 5.875237773315041e-06, - "loss": 3.2062, + "learning_rate": 5.9231477129029485e-06, + "loss": 3.1891, "step": 266300 }, { "epoch": 0.88, - "learning_rate": 5.858668204322669e-06, - "loss": 3.2042, + "learning_rate": 5.906596134875499e-06, + "loss": 3.1877, "step": 266400 }, { "epoch": 0.88, - "learning_rate": 5.842098635330298e-06, - "loss": 3.1906, + "learning_rate": 5.89004455684805e-06, + "loss": 3.1856, "step": 266500 }, { "epoch": 0.88, - "learning_rate": 5.825529066337927e-06, - "loss": 3.1885, + "learning_rate": 5.873492978820601e-06, + "loss": 3.1934, "step": 266600 }, { "epoch": 0.88, - "learning_rate": 5.808959497345555e-06, - "loss": 3.2018, + "learning_rate": 5.856941400793152e-06, + "loss": 3.1746, "step": 266700 }, { "epoch": 0.88, - "learning_rate": 5.7923899283531845e-06, - "loss": 3.1924, + "learning_rate": 5.840389822765703e-06, + "loss": 3.192, "step": 266800 }, { "epoch": 0.88, - "learning_rate": 5.775820359360813e-06, - "loss": 3.1831, + "learning_rate": 5.823838244738254e-06, + "loss": 3.2034, "step": 266900 }, { "epoch": 0.88, - "learning_rate": 5.759250790368441e-06, - "loss": 3.1926, + "learning_rate": 5.807286666710805e-06, + "loss": 3.1895, "step": 267000 }, { - "epoch": 0.89, - "learning_rate": 5.74268122137607e-06, - "loss": 3.1895, + "epoch": 0.88, + "learning_rate": 5.790735088683355e-06, + "loss": 3.1784, "step": 267100 }, { - "epoch": 0.89, - "learning_rate": 5.726111652383699e-06, - "loss": 3.2005, + "epoch": 0.88, + "learning_rate": 5.774183510655906e-06, + "loss": 3.1842, "step": 267200 }, { - "epoch": 0.89, - "learning_rate": 5.709542083391327e-06, - "loss": 3.199, + "epoch": 0.88, + "learning_rate": 5.757631932628457e-06, + "loss": 3.1878, "step": 267300 }, { "epoch": 0.89, - "learning_rate": 5.692972514398956e-06, - "loss": 3.1953, + "learning_rate": 5.741080354601008e-06, + "loss": 3.1832, "step": 267400 }, { "epoch": 0.89, - "learning_rate": 5.676402945406585e-06, - "loss": 3.2068, + "learning_rate": 5.724528776573558e-06, + "loss": 3.1797, "step": 267500 }, { "epoch": 0.89, - "learning_rate": 5.659833376414213e-06, - "loss": 3.2019, + "learning_rate": 5.70797719854611e-06, + "loss": 3.1818, "step": 267600 }, { "epoch": 0.89, - "learning_rate": 5.643263807421842e-06, - "loss": 3.1942, + "learning_rate": 5.69142562051866e-06, + "loss": 3.1838, "step": 267700 }, { "epoch": 0.89, - "learning_rate": 5.626694238429471e-06, - "loss": 3.2005, + "learning_rate": 5.6748740424912115e-06, + "loss": 3.1873, "step": 267800 }, { "epoch": 0.89, - "learning_rate": 5.610124669437099e-06, - "loss": 3.1976, + "learning_rate": 5.658322464463762e-06, + "loss": 3.1933, "step": 267900 }, { "epoch": 0.89, - "learning_rate": 5.593555100444727e-06, - "loss": 3.1944, + "learning_rate": 5.641770886436313e-06, + "loss": 3.1921, "step": 268000 }, { "epoch": 0.89, - "learning_rate": 5.5769855314523565e-06, - "loss": 3.2012, + "learning_rate": 5.625219308408864e-06, + "loss": 3.1796, "step": 268100 }, { "epoch": 0.89, - "learning_rate": 5.560415962459985e-06, - "loss": 3.2054, + "learning_rate": 5.608667730381415e-06, + "loss": 3.1771, "step": 268200 }, { "epoch": 0.89, - "learning_rate": 5.543846393467613e-06, - "loss": 3.1957, + "learning_rate": 5.592116152353965e-06, + "loss": 3.1847, "step": 268300 }, { "epoch": 0.89, - "learning_rate": 5.5272768244752424e-06, - "loss": 3.2021, + "learning_rate": 5.575564574326517e-06, + "loss": 3.1846, "step": 268400 }, { "epoch": 0.89, - "learning_rate": 5.510707255482871e-06, - "loss": 3.1878, + "learning_rate": 5.559012996299067e-06, + "loss": 3.2039, "step": 268500 }, { "epoch": 0.89, - "learning_rate": 5.494137686490499e-06, - "loss": 3.2068, + "learning_rate": 5.542461418271618e-06, + "loss": 3.1901, "step": 268600 }, { "epoch": 0.89, - "learning_rate": 5.477568117498128e-06, - "loss": 3.1908, + "learning_rate": 5.525909840244169e-06, + "loss": 3.1852, "step": 268700 }, { "epoch": 0.89, - "learning_rate": 5.460998548505757e-06, - "loss": 3.2027, + "learning_rate": 5.50935826221672e-06, + "loss": 3.1933, "step": 268800 }, { "epoch": 0.89, - "learning_rate": 5.444428979513385e-06, - "loss": 3.1964, + "learning_rate": 5.492806684189271e-06, + "loss": 3.1888, "step": 268900 }, { "epoch": 0.89, - "learning_rate": 5.427859410521014e-06, - "loss": 3.1848, + "learning_rate": 5.476255106161822e-06, + "loss": 3.1913, "step": 269000 }, { "epoch": 0.89, - "learning_rate": 5.411289841528643e-06, - "loss": 3.1923, + "learning_rate": 5.459703528134372e-06, + "loss": 3.1714, "step": 269100 }, { "epoch": 0.89, - "learning_rate": 5.394720272536271e-06, - "loss": 3.188, + "learning_rate": 5.443151950106924e-06, + "loss": 3.1775, "step": 269200 }, { "epoch": 0.89, - "learning_rate": 5.378150703543899e-06, - "loss": 3.1933, + "learning_rate": 5.4266003720794745e-06, + "loss": 3.1899, "step": 269300 }, { "epoch": 0.89, - "learning_rate": 5.3615811345515286e-06, - "loss": 3.2027, + "learning_rate": 5.410048794052025e-06, + "loss": 3.1866, "step": 269400 }, { "epoch": 0.89, - "learning_rate": 5.345011565559157e-06, - "loss": 3.1905, + "learning_rate": 5.393497216024576e-06, + "loss": 3.1793, "step": 269500 }, { "epoch": 0.89, - "learning_rate": 5.328441996566785e-06, - "loss": 3.1919, + "learning_rate": 5.376945637997128e-06, + "loss": 3.1914, "step": 269600 }, { "epoch": 0.89, - "learning_rate": 5.3118724275744145e-06, - "loss": 3.1936, + "learning_rate": 5.3603940599696775e-06, + "loss": 3.1872, "step": 269700 }, { "epoch": 0.89, - "learning_rate": 5.295302858582043e-06, - "loss": 3.1943, + "learning_rate": 5.343842481942229e-06, + "loss": 3.19, "step": 269800 }, { "epoch": 0.89, - "learning_rate": 5.278733289589671e-06, - "loss": 3.1764, + "learning_rate": 5.327290903914779e-06, + "loss": 3.1703, "step": 269900 }, { "epoch": 0.89, - "learning_rate": 5.2621637205973e-06, - "loss": 3.1938, + "learning_rate": 5.310739325887331e-06, + "loss": 3.1746, "step": 270000 }, { - "epoch": 0.9, - "learning_rate": 5.245594151604929e-06, - "loss": 3.2053, + "epoch": 0.89, + "learning_rate": 5.294187747859881e-06, + "loss": 3.1909, "step": 270100 }, { - "epoch": 0.9, - "learning_rate": 5.229024582612557e-06, - "loss": 3.1941, + "epoch": 0.89, + "learning_rate": 5.277636169832432e-06, + "loss": 3.1892, "step": 270200 }, { - "epoch": 0.9, - "learning_rate": 5.2124550136201855e-06, - "loss": 3.1898, + "epoch": 0.89, + "learning_rate": 5.261084591804983e-06, + "loss": 3.1793, "step": 270300 }, { "epoch": 0.9, - "learning_rate": 5.195885444627815e-06, - "loss": 3.1886, + "learning_rate": 5.2445330137775345e-06, + "loss": 3.2009, "step": 270400 }, { "epoch": 0.9, - "learning_rate": 5.179315875635443e-06, - "loss": 3.2037, + "learning_rate": 5.227981435750084e-06, + "loss": 3.1837, "step": 270500 }, { "epoch": 0.9, - "learning_rate": 5.162746306643071e-06, - "loss": 3.1957, + "learning_rate": 5.211429857722636e-06, + "loss": 3.177, "step": 270600 }, { "epoch": 0.9, - "learning_rate": 5.146176737650701e-06, - "loss": 3.1859, + "learning_rate": 5.194878279695187e-06, + "loss": 3.1822, "step": 270700 }, { "epoch": 0.9, - "learning_rate": 5.129607168658329e-06, - "loss": 3.2039, + "learning_rate": 5.1783267016677375e-06, + "loss": 3.1855, "step": 270800 }, { "epoch": 0.9, - "learning_rate": 5.113037599665957e-06, - "loss": 3.1869, + "learning_rate": 5.161775123640288e-06, + "loss": 3.1925, "step": 270900 }, { "epoch": 0.9, - "learning_rate": 5.0964680306735865e-06, - "loss": 3.2138, + "learning_rate": 5.145223545612839e-06, + "loss": 3.1637, "step": 271000 }, { "epoch": 0.9, - "learning_rate": 5.079898461681215e-06, - "loss": 3.1947, + "learning_rate": 5.12867196758539e-06, + "loss": 3.1903, "step": 271100 }, { "epoch": 0.9, - "learning_rate": 5.063328892688843e-06, - "loss": 3.1938, + "learning_rate": 5.1121203895579405e-06, + "loss": 3.1913, "step": 271200 }, { "epoch": 0.9, - "learning_rate": 5.046759323696472e-06, - "loss": 3.2019, + "learning_rate": 5.095568811530491e-06, + "loss": 3.1871, "step": 271300 }, { "epoch": 0.9, - "learning_rate": 5.030189754704101e-06, - "loss": 3.1861, + "learning_rate": 5.079017233503042e-06, + "loss": 3.1893, "step": 271400 }, { "epoch": 0.9, - "learning_rate": 5.013620185711729e-06, - "loss": 3.1945, + "learning_rate": 5.062465655475594e-06, + "loss": 3.1862, "step": 271500 }, { "epoch": 0.9, - "learning_rate": 4.9970506167193575e-06, - "loss": 3.2061, + "learning_rate": 5.045914077448144e-06, + "loss": 3.1725, "step": 271600 }, { "epoch": 0.9, - "learning_rate": 4.980481047726987e-06, - "loss": 3.1892, + "learning_rate": 5.029362499420695e-06, + "loss": 3.1741, "step": 271700 }, { "epoch": 0.9, - "learning_rate": 4.963911478734615e-06, - "loss": 3.2042, + "learning_rate": 5.012810921393246e-06, + "loss": 3.189, "step": 271800 }, { "epoch": 0.9, - "learning_rate": 4.9473419097422435e-06, - "loss": 3.1973, + "learning_rate": 4.996259343365797e-06, + "loss": 3.184, "step": 271900 }, { "epoch": 0.9, - "learning_rate": 4.930772340749873e-06, - "loss": 3.1865, + "learning_rate": 4.979707765338347e-06, + "loss": 3.1772, "step": 272000 }, { "epoch": 0.9, - "learning_rate": 4.914202771757501e-06, - "loss": 3.2016, + "learning_rate": 4.963156187310899e-06, + "loss": 3.187, "step": 272100 }, { "epoch": 0.9, - "learning_rate": 4.897633202765129e-06, - "loss": 3.1844, + "learning_rate": 4.946604609283449e-06, + "loss": 3.194, "step": 272200 }, { "epoch": 0.9, - "learning_rate": 4.881063633772759e-06, - "loss": 3.1993, + "learning_rate": 4.9300530312560005e-06, + "loss": 3.1719, "step": 272300 }, { "epoch": 0.9, - "learning_rate": 4.864494064780387e-06, - "loss": 3.1829, + "learning_rate": 4.91350145322855e-06, + "loss": 3.1788, "step": 272400 }, { "epoch": 0.9, - "learning_rate": 4.847924495788015e-06, - "loss": 3.1932, + "learning_rate": 4.896949875201102e-06, + "loss": 3.1842, "step": 272500 }, { "epoch": 0.9, - "learning_rate": 4.8313549267956445e-06, - "loss": 3.1942, + "learning_rate": 4.880398297173653e-06, + "loss": 3.1952, "step": 272600 }, { "epoch": 0.9, - "learning_rate": 4.814785357803273e-06, - "loss": 3.2129, + "learning_rate": 4.8638467191462035e-06, + "loss": 3.1831, "step": 272700 }, { "epoch": 0.9, - "learning_rate": 4.798215788810902e-06, - "loss": 3.1984, + "learning_rate": 4.847295141118754e-06, + "loss": 3.1689, "step": 272800 }, { "epoch": 0.9, - "learning_rate": 4.7816462198185304e-06, - "loss": 3.1943, + "learning_rate": 4.830743563091306e-06, + "loss": 3.1826, "step": 272900 }, { "epoch": 0.9, - "learning_rate": 4.765076650826159e-06, - "loss": 3.2095, + "learning_rate": 4.814191985063856e-06, + "loss": 3.1887, "step": 273000 }, { - "epoch": 0.91, - "learning_rate": 4.748507081833788e-06, - "loss": 3.2085, + "epoch": 0.9, + "learning_rate": 4.797640407036407e-06, + "loss": 3.1833, "step": 273100 }, { - "epoch": 0.91, - "learning_rate": 4.731937512841416e-06, - "loss": 3.2091, + "epoch": 0.9, + "learning_rate": 4.781088829008958e-06, + "loss": 3.1937, "step": 273200 }, { - "epoch": 0.91, - "learning_rate": 4.7153679438490456e-06, - "loss": 3.2097, + "epoch": 0.9, + "learning_rate": 4.764537250981509e-06, + "loss": 3.1956, "step": 273300 }, { "epoch": 0.91, - "learning_rate": 4.698798374856674e-06, - "loss": 3.1987, + "learning_rate": 4.74798567295406e-06, + "loss": 3.1764, "step": 273400 }, { "epoch": 0.91, - "learning_rate": 4.682228805864302e-06, - "loss": 3.1736, + "learning_rate": 4.73143409492661e-06, + "loss": 3.1858, "step": 273500 }, { "epoch": 0.91, - "learning_rate": 4.665659236871931e-06, - "loss": 3.1976, + "learning_rate": 4.714882516899161e-06, + "loss": 3.1754, "step": 273600 }, { "epoch": 0.91, - "learning_rate": 4.64908966787956e-06, - "loss": 3.2155, + "learning_rate": 4.698330938871713e-06, + "loss": 3.1942, "step": 273700 }, { "epoch": 0.91, - "learning_rate": 4.632520098887188e-06, - "loss": 3.1932, + "learning_rate": 4.681779360844263e-06, + "loss": 3.1874, "step": 273800 }, { "epoch": 0.91, - "learning_rate": 4.6159505298948166e-06, - "loss": 3.2084, + "learning_rate": 4.665227782816814e-06, + "loss": 3.181, "step": 273900 }, { "epoch": 0.91, - "learning_rate": 4.599380960902446e-06, - "loss": 3.2019, + "learning_rate": 4.648676204789365e-06, + "loss": 3.1783, "step": 274000 }, { "epoch": 0.91, - "learning_rate": 4.582811391910074e-06, - "loss": 3.1943, + "learning_rate": 4.632124626761916e-06, + "loss": 3.1984, "step": 274100 }, { "epoch": 0.91, - "learning_rate": 4.5662418229177025e-06, - "loss": 3.1962, + "learning_rate": 4.6155730487344665e-06, + "loss": 3.1851, "step": 274200 }, { "epoch": 0.91, - "learning_rate": 4.549672253925332e-06, - "loss": 3.1974, + "learning_rate": 4.599021470707018e-06, + "loss": 3.1763, "step": 274300 }, { "epoch": 0.91, - "learning_rate": 4.53310268493296e-06, - "loss": 3.1936, + "learning_rate": 4.582469892679568e-06, + "loss": 3.1728, "step": 274400 }, { "epoch": 0.91, - "learning_rate": 4.516533115940588e-06, - "loss": 3.2041, + "learning_rate": 4.56591831465212e-06, + "loss": 3.1656, "step": 274500 }, { "epoch": 0.91, - "learning_rate": 4.499963546948217e-06, - "loss": 3.2056, + "learning_rate": 4.54936673662467e-06, + "loss": 3.1856, "step": 274600 }, { "epoch": 0.91, - "learning_rate": 4.483393977955846e-06, - "loss": 3.2052, + "learning_rate": 4.532815158597221e-06, + "loss": 3.1828, "step": 274700 }, { "epoch": 0.91, - "learning_rate": 4.466824408963474e-06, - "loss": 3.1982, + "learning_rate": 4.516263580569772e-06, + "loss": 3.1954, "step": 274800 }, { "epoch": 0.91, - "learning_rate": 4.450254839971103e-06, - "loss": 3.1906, + "learning_rate": 4.499712002542323e-06, + "loss": 3.2046, "step": 274900 }, { "epoch": 0.91, - "learning_rate": 4.433685270978732e-06, - "loss": 3.1926, + "learning_rate": 4.483160424514873e-06, + "loss": 3.1887, "step": 275000 }, { "epoch": 0.91, - "learning_rate": 4.41711570198636e-06, - "loss": 3.1982, + "learning_rate": 4.466608846487424e-06, + "loss": 3.1919, "step": 275100 }, { "epoch": 0.91, - "learning_rate": 4.400546132993989e-06, - "loss": 3.1937, + "learning_rate": 4.450057268459975e-06, + "loss": 3.1823, "step": 275200 }, { "epoch": 0.91, - "learning_rate": 4.383976564001618e-06, - "loss": 3.1874, + "learning_rate": 4.4335056904325265e-06, + "loss": 3.1906, "step": 275300 }, { "epoch": 0.91, - "learning_rate": 4.367406995009246e-06, - "loss": 3.1878, + "learning_rate": 4.416954112405077e-06, + "loss": 3.1869, "step": 275400 }, { "epoch": 0.91, - "learning_rate": 4.3508374260168745e-06, - "loss": 3.2009, + "learning_rate": 4.400402534377628e-06, + "loss": 3.1924, "step": 275500 }, { "epoch": 0.91, - "learning_rate": 4.334267857024503e-06, - "loss": 3.2132, + "learning_rate": 4.383850956350179e-06, + "loss": 3.1899, "step": 275600 }, { "epoch": 0.91, - "learning_rate": 4.317698288032132e-06, - "loss": 3.1897, + "learning_rate": 4.3672993783227295e-06, + "loss": 3.1717, "step": 275700 }, { "epoch": 0.91, - "learning_rate": 4.3011287190397605e-06, - "loss": 3.1978, + "learning_rate": 4.35074780029528e-06, + "loss": 3.1914, "step": 275800 }, { "epoch": 0.91, - "learning_rate": 4.284559150047389e-06, - "loss": 3.2, + "learning_rate": 4.334196222267831e-06, + "loss": 3.1886, "step": 275900 }, { "epoch": 0.91, - "learning_rate": 4.267989581055018e-06, - "loss": 3.1906, + "learning_rate": 4.3176446442403826e-06, + "loss": 3.1902, "step": 276000 }, { "epoch": 0.91, - "learning_rate": 4.251420012062646e-06, - "loss": 3.1906, + "learning_rate": 4.3010930662129325e-06, + "loss": 3.1709, "step": 276100 }, { - "epoch": 0.92, - "learning_rate": 4.234850443070275e-06, - "loss": 3.1991, + "epoch": 0.91, + "learning_rate": 4.284541488185484e-06, + "loss": 3.1831, "step": 276200 }, { - "epoch": 0.92, - "learning_rate": 4.218280874077904e-06, - "loss": 3.1945, + "epoch": 0.91, + "learning_rate": 4.267989910158034e-06, + "loss": 3.1794, "step": 276300 }, { - "epoch": 0.92, - "learning_rate": 4.201711305085532e-06, - "loss": 3.2049, + "epoch": 0.91, + "learning_rate": 4.251438332130586e-06, + "loss": 3.174, "step": 276400 }, { "epoch": 0.92, - "learning_rate": 4.185141736093161e-06, - "loss": 3.194, + "learning_rate": 4.234886754103136e-06, + "loss": 3.1802, "step": 276500 }, { "epoch": 0.92, - "learning_rate": 4.16857216710079e-06, - "loss": 3.194, + "learning_rate": 4.218335176075687e-06, + "loss": 3.1848, "step": 276600 }, { "epoch": 0.92, - "learning_rate": 4.152002598108418e-06, - "loss": 3.1953, + "learning_rate": 4.201783598048238e-06, + "loss": 3.1882, "step": 276700 }, { "epoch": 0.92, - "learning_rate": 4.135433029116047e-06, - "loss": 3.1893, + "learning_rate": 4.1852320200207894e-06, + "loss": 3.1911, "step": 276800 }, { "epoch": 0.92, - "learning_rate": 4.118863460123675e-06, - "loss": 3.2006, + "learning_rate": 4.168680441993339e-06, + "loss": 3.1806, "step": 276900 }, { "epoch": 0.92, - "learning_rate": 4.102293891131304e-06, - "loss": 3.2029, + "learning_rate": 4.152128863965891e-06, + "loss": 3.1612, "step": 277000 }, { "epoch": 0.92, - "learning_rate": 4.0857243221389325e-06, - "loss": 3.2134, + "learning_rate": 4.135577285938442e-06, + "loss": 3.1932, "step": 277100 }, { "epoch": 0.92, - "learning_rate": 4.069154753146561e-06, - "loss": 3.1961, + "learning_rate": 4.1190257079109925e-06, + "loss": 3.1678, "step": 277200 }, { "epoch": 0.92, - "learning_rate": 4.05258518415419e-06, - "loss": 3.1829, + "learning_rate": 4.102474129883543e-06, + "loss": 3.1769, "step": 277300 }, { "epoch": 0.92, - "learning_rate": 4.0360156151618184e-06, - "loss": 3.1846, + "learning_rate": 4.085922551856094e-06, + "loss": 3.1743, "step": 277400 }, { "epoch": 0.92, - "learning_rate": 4.019446046169447e-06, - "loss": 3.2041, + "learning_rate": 4.069370973828645e-06, + "loss": 3.1766, "step": 277500 }, { "epoch": 0.92, - "learning_rate": 4.002876477177076e-06, - "loss": 3.1943, + "learning_rate": 4.052819395801196e-06, + "loss": 3.1754, "step": 277600 }, { "epoch": 0.92, - "learning_rate": 3.986306908184704e-06, - "loss": 3.208, + "learning_rate": 4.036267817773746e-06, + "loss": 3.182, "step": 277700 }, { "epoch": 0.92, - "learning_rate": 3.969737339192333e-06, - "loss": 3.1927, + "learning_rate": 4.019716239746298e-06, + "loss": 3.1811, "step": 277800 }, { "epoch": 0.92, - "learning_rate": 3.953167770199961e-06, - "loss": 3.2091, + "learning_rate": 4.0031646617188486e-06, + "loss": 3.1834, "step": 277900 }, { "epoch": 0.92, - "learning_rate": 3.93659820120759e-06, - "loss": 3.2018, + "learning_rate": 3.986613083691399e-06, + "loss": 3.1959, "step": 278000 }, { "epoch": 0.92, - "learning_rate": 3.920028632215219e-06, - "loss": 3.1928, + "learning_rate": 3.97006150566395e-06, + "loss": 3.1807, "step": 278100 }, { "epoch": 0.92, - "learning_rate": 3.903459063222847e-06, - "loss": 3.1958, + "learning_rate": 3.953509927636502e-06, + "loss": 3.1873, "step": 278200 }, { "epoch": 0.92, - "learning_rate": 3.886889494230476e-06, - "loss": 3.1915, + "learning_rate": 3.936958349609052e-06, + "loss": 3.1841, "step": 278300 }, { "epoch": 0.92, - "learning_rate": 3.8703199252381046e-06, - "loss": 3.184, + "learning_rate": 3.920406771581603e-06, + "loss": 3.172, "step": 278400 }, { "epoch": 0.92, - "learning_rate": 3.853750356245733e-06, - "loss": 3.1804, + "learning_rate": 3.903855193554154e-06, + "loss": 3.1787, "step": 278500 }, { "epoch": 0.92, - "learning_rate": 3.837180787253362e-06, - "loss": 3.2093, + "learning_rate": 3.887303615526705e-06, + "loss": 3.17, "step": 278600 }, { "epoch": 0.92, - "learning_rate": 3.8206112182609905e-06, - "loss": 3.1918, + "learning_rate": 3.8707520374992554e-06, + "loss": 3.1921, "step": 278700 }, { "epoch": 0.92, - "learning_rate": 3.8040416492686193e-06, - "loss": 3.1972, + "learning_rate": 3.854200459471806e-06, + "loss": 3.1826, "step": 278800 }, { "epoch": 0.92, - "learning_rate": 3.7874720802762476e-06, - "loss": 3.1872, + "learning_rate": 3.837648881444357e-06, + "loss": 3.1794, "step": 278900 }, { "epoch": 0.92, - "learning_rate": 3.770902511283877e-06, - "loss": 3.1887, + "learning_rate": 3.8210973034169086e-06, + "loss": 3.171, "step": 279000 }, { "epoch": 0.92, - "learning_rate": 3.754332942291505e-06, - "loss": 3.2183, + "learning_rate": 3.8045457253894585e-06, + "loss": 3.185, "step": 279100 }, { - "epoch": 0.93, - "learning_rate": 3.7377633732991335e-06, - "loss": 3.186, + "epoch": 0.92, + "learning_rate": 3.7879941473620096e-06, + "loss": 3.1912, "step": 279200 }, { - "epoch": 0.93, - "learning_rate": 3.7211938043067627e-06, - "loss": 3.2088, + "epoch": 0.92, + "learning_rate": 3.771442569334561e-06, + "loss": 3.1905, "step": 279300 }, { - "epoch": 0.93, - "learning_rate": 3.704624235314391e-06, - "loss": 3.2052, + "epoch": 0.92, + "learning_rate": 3.754890991307111e-06, + "loss": 3.178, "step": 279400 }, { "epoch": 0.93, - "learning_rate": 3.6880546663220195e-06, - "loss": 3.185, + "learning_rate": 3.7383394132796623e-06, + "loss": 3.1956, "step": 279500 }, { "epoch": 0.93, - "learning_rate": 3.6714850973296487e-06, - "loss": 3.187, + "learning_rate": 3.7217878352522135e-06, + "loss": 3.1887, "step": 279600 }, { "epoch": 0.93, - "learning_rate": 3.654915528337277e-06, - "loss": 3.196, + "learning_rate": 3.705236257224764e-06, + "loss": 3.1717, "step": 279700 }, { "epoch": 0.93, - "learning_rate": 3.6383459593449054e-06, - "loss": 3.1924, + "learning_rate": 3.688684679197315e-06, + "loss": 3.1801, "step": 279800 }, { "epoch": 0.93, - "learning_rate": 3.6217763903525346e-06, - "loss": 3.1811, + "learning_rate": 3.6721331011698653e-06, + "loss": 3.1833, "step": 279900 }, { "epoch": 0.93, - "learning_rate": 3.605206821360163e-06, - "loss": 3.2053, + "learning_rate": 3.6555815231424165e-06, + "loss": 3.1928, "step": 280000 }, { "epoch": 0.93, - "learning_rate": 3.5886372523677913e-06, - "loss": 3.2049, + "learning_rate": 3.6390299451149677e-06, + "loss": 3.1696, "step": 280100 }, { "epoch": 0.93, - "learning_rate": 3.57206768337542e-06, - "loss": 3.2003, + "learning_rate": 3.622478367087518e-06, + "loss": 3.1782, "step": 280200 }, { "epoch": 0.93, - "learning_rate": 3.555498114383049e-06, - "loss": 3.18, + "learning_rate": 3.605926789060069e-06, + "loss": 3.1934, "step": 280300 }, { "epoch": 0.93, - "learning_rate": 3.5389285453906776e-06, - "loss": 3.1911, + "learning_rate": 3.5893752110326204e-06, + "loss": 3.1831, "step": 280400 }, { "epoch": 0.93, - "learning_rate": 3.522358976398306e-06, - "loss": 3.1912, + "learning_rate": 3.5728236330051707e-06, + "loss": 3.1734, "step": 280500 }, { "epoch": 0.93, - "learning_rate": 3.505789407405935e-06, - "loss": 3.1971, + "learning_rate": 3.556272054977722e-06, + "loss": 3.1858, "step": 280600 }, { "epoch": 0.93, - "learning_rate": 3.4892198384135636e-06, - "loss": 3.1857, + "learning_rate": 3.539720476950273e-06, + "loss": 3.1986, "step": 280700 }, { "epoch": 0.93, - "learning_rate": 3.472650269421192e-06, - "loss": 3.2056, + "learning_rate": 3.5231688989228234e-06, + "loss": 3.1827, "step": 280800 }, { "epoch": 0.93, - "learning_rate": 3.456080700428821e-06, - "loss": 3.198, + "learning_rate": 3.5066173208953746e-06, + "loss": 3.166, "step": 280900 }, { "epoch": 0.93, - "learning_rate": 3.4395111314364495e-06, - "loss": 3.1944, + "learning_rate": 3.4900657428679253e-06, + "loss": 3.1994, "step": 281000 }, { "epoch": 0.93, - "learning_rate": 3.422941562444078e-06, - "loss": 3.1959, + "learning_rate": 3.473514164840476e-06, + "loss": 3.1865, "step": 281100 }, { "epoch": 0.93, - "learning_rate": 3.406371993451706e-06, - "loss": 3.1845, + "learning_rate": 3.4569625868130272e-06, + "loss": 3.1823, "step": 281200 }, { "epoch": 0.93, - "learning_rate": 3.3898024244593354e-06, - "loss": 3.1892, + "learning_rate": 3.4404110087855776e-06, + "loss": 3.1765, "step": 281300 }, { "epoch": 0.93, - "learning_rate": 3.3732328554669638e-06, - "loss": 3.177, + "learning_rate": 3.4238594307581287e-06, + "loss": 3.1878, "step": 281400 }, { "epoch": 0.93, - "learning_rate": 3.356663286474592e-06, - "loss": 3.212, + "learning_rate": 3.4073078527306795e-06, + "loss": 3.1765, "step": 281500 }, { "epoch": 0.93, - "learning_rate": 3.3400937174822213e-06, - "loss": 3.2007, + "learning_rate": 3.3907562747032303e-06, + "loss": 3.1966, "step": 281600 }, { "epoch": 0.93, - "learning_rate": 3.3235241484898497e-06, - "loss": 3.2081, + "learning_rate": 3.374204696675781e-06, + "loss": 3.1724, "step": 281700 }, { "epoch": 0.93, - "learning_rate": 3.306954579497478e-06, - "loss": 3.1967, + "learning_rate": 3.357653118648332e-06, + "loss": 3.189, "step": 281800 }, { "epoch": 0.93, - "learning_rate": 3.2903850105051073e-06, - "loss": 3.2081, + "learning_rate": 3.341101540620883e-06, + "loss": 3.1818, "step": 281900 }, { "epoch": 0.93, - "learning_rate": 3.2738154415127356e-06, - "loss": 3.2023, + "learning_rate": 3.3245499625934337e-06, + "loss": 3.1764, "step": 282000 }, { "epoch": 0.93, - "learning_rate": 3.257245872520364e-06, - "loss": 3.2075, + "learning_rate": 3.307998384565985e-06, + "loss": 3.1795, "step": 282100 }, { - "epoch": 0.94, - "learning_rate": 3.2406763035279923e-06, - "loss": 3.1768, + "epoch": 0.93, + "learning_rate": 3.291446806538535e-06, + "loss": 3.1749, "step": 282200 }, { - "epoch": 0.94, - "learning_rate": 3.2241067345356215e-06, - "loss": 3.197, + "epoch": 0.93, + "learning_rate": 3.2748952285110864e-06, + "loss": 3.1797, "step": 282300 }, { - "epoch": 0.94, - "learning_rate": 3.20753716554325e-06, - "loss": 3.1984, + "epoch": 0.93, + "learning_rate": 3.2583436504836375e-06, + "loss": 3.197, "step": 282400 }, { "epoch": 0.94, - "learning_rate": 3.1909675965508783e-06, - "loss": 3.2127, + "learning_rate": 3.241792072456188e-06, + "loss": 3.1891, "step": 282500 }, { "epoch": 0.94, - "learning_rate": 3.1743980275585075e-06, - "loss": 3.1937, + "learning_rate": 3.225240494428739e-06, + "loss": 3.1814, "step": 282600 }, { "epoch": 0.94, - "learning_rate": 3.157828458566136e-06, - "loss": 3.1999, + "learning_rate": 3.2086889164012894e-06, + "loss": 3.1746, "step": 282700 }, { "epoch": 0.94, - "learning_rate": 3.141258889573764e-06, - "loss": 3.1962, + "learning_rate": 3.1921373383738406e-06, + "loss": 3.1839, "step": 282800 }, { "epoch": 0.94, - "learning_rate": 3.124689320581393e-06, - "loss": 3.1872, + "learning_rate": 3.1755857603463917e-06, + "loss": 3.1831, "step": 282900 }, { "epoch": 0.94, - "learning_rate": 3.1081197515890217e-06, - "loss": 3.2094, + "learning_rate": 3.159034182318942e-06, + "loss": 3.1646, "step": 283000 }, { "epoch": 0.94, - "learning_rate": 3.09155018259665e-06, - "loss": 3.2024, + "learning_rate": 3.1424826042914932e-06, + "loss": 3.1741, "step": 283100 }, { "epoch": 0.94, - "learning_rate": 3.074980613604279e-06, - "loss": 3.2066, + "learning_rate": 3.1259310262640444e-06, + "loss": 3.1727, "step": 283200 }, { "epoch": 0.94, - "learning_rate": 3.0584110446119077e-06, - "loss": 3.1938, + "learning_rate": 3.109379448236595e-06, + "loss": 3.1849, "step": 283300 }, { "epoch": 0.94, - "learning_rate": 3.0418414756195365e-06, - "loss": 3.1987, + "learning_rate": 3.092827870209146e-06, + "loss": 3.1839, "step": 283400 }, { "epoch": 0.94, - "learning_rate": 3.025271906627165e-06, - "loss": 3.1939, + "learning_rate": 3.0762762921816967e-06, + "loss": 3.18, "step": 283500 }, { "epoch": 0.94, - "learning_rate": 3.0087023376347936e-06, - "loss": 3.1908, + "learning_rate": 3.0597247141542474e-06, + "loss": 3.1742, "step": 283600 }, { "epoch": 0.94, - "learning_rate": 2.9921327686424224e-06, - "loss": 3.1876, + "learning_rate": 3.0431731361267986e-06, + "loss": 3.1774, "step": 283700 }, { "epoch": 0.94, - "learning_rate": 2.975563199650051e-06, - "loss": 3.1957, + "learning_rate": 3.0266215580993494e-06, + "loss": 3.1843, "step": 283800 }, { "epoch": 0.94, - "learning_rate": 2.9589936306576795e-06, - "loss": 3.1796, + "learning_rate": 3.0100699800719e-06, + "loss": 3.1766, "step": 283900 }, { "epoch": 0.94, - "learning_rate": 2.9424240616653083e-06, - "loss": 3.188, + "learning_rate": 2.9935184020444513e-06, + "loss": 3.1777, "step": 284000 }, { "epoch": 0.94, - "learning_rate": 2.9258544926729367e-06, - "loss": 3.2003, + "learning_rate": 2.976966824017002e-06, + "loss": 3.1794, "step": 284100 }, { "epoch": 0.94, - "learning_rate": 2.9092849236805654e-06, - "loss": 3.1939, + "learning_rate": 2.960415245989553e-06, + "loss": 3.1821, "step": 284200 }, { "epoch": 0.94, - "learning_rate": 2.8927153546881942e-06, - "loss": 3.1908, + "learning_rate": 2.9438636679621036e-06, + "loss": 3.1864, "step": 284300 }, { "epoch": 0.94, - "learning_rate": 2.8761457856958226e-06, - "loss": 3.1916, + "learning_rate": 2.9273120899346547e-06, + "loss": 3.1804, "step": 284400 }, { "epoch": 0.94, - "learning_rate": 2.8595762167034514e-06, - "loss": 3.2058, + "learning_rate": 2.9107605119072055e-06, + "loss": 3.1666, "step": 284500 }, { "epoch": 0.94, - "learning_rate": 2.8430066477110797e-06, - "loss": 3.1948, + "learning_rate": 2.8942089338797562e-06, + "loss": 3.1827, "step": 284600 }, { "epoch": 0.94, - "learning_rate": 2.8264370787187085e-06, - "loss": 3.2074, + "learning_rate": 2.8776573558523074e-06, + "loss": 3.1742, "step": 284700 }, { "epoch": 0.94, - "learning_rate": 2.8098675097263373e-06, - "loss": 3.1944, + "learning_rate": 2.861105777824858e-06, + "loss": 3.1797, "step": 284800 }, { "epoch": 0.94, - "learning_rate": 2.7932979407339656e-06, - "loss": 3.2124, + "learning_rate": 2.844554199797409e-06, + "loss": 3.1792, "step": 284900 }, { "epoch": 0.94, - "learning_rate": 2.7767283717415944e-06, - "loss": 3.1756, + "learning_rate": 2.8280026217699597e-06, + "loss": 3.1884, "step": 285000 }, { "epoch": 0.94, - "learning_rate": 2.760158802749223e-06, - "loss": 3.1963, + "learning_rate": 2.811451043742511e-06, + "loss": 3.1918, "step": 285100 }, { - "epoch": 0.95, - "learning_rate": 2.7435892337568516e-06, - "loss": 3.207, + "epoch": 0.94, + "learning_rate": 2.7948994657150616e-06, + "loss": 3.1677, "step": 285200 }, { - "epoch": 0.95, - "learning_rate": 2.7270196647644803e-06, - "loss": 3.1815, + "epoch": 0.94, + "learning_rate": 2.7783478876876124e-06, + "loss": 3.1802, "step": 285300 }, { - "epoch": 0.95, - "learning_rate": 2.7104500957721087e-06, - "loss": 3.1843, + "epoch": 0.94, + "learning_rate": 2.761796309660163e-06, + "loss": 3.189, "step": 285400 }, { "epoch": 0.95, - "learning_rate": 2.6938805267797375e-06, - "loss": 3.19, + "learning_rate": 2.7452447316327143e-06, + "loss": 3.1809, "step": 285500 }, { "epoch": 0.95, - "learning_rate": 2.6773109577873663e-06, - "loss": 3.1823, + "learning_rate": 2.728693153605265e-06, + "loss": 3.1774, "step": 285600 }, { "epoch": 0.95, - "learning_rate": 2.6607413887949946e-06, - "loss": 3.1977, + "learning_rate": 2.7121415755778158e-06, + "loss": 3.1808, "step": 285700 }, { "epoch": 0.95, - "learning_rate": 2.6441718198026234e-06, - "loss": 3.2004, + "learning_rate": 2.6955899975503665e-06, + "loss": 3.1772, "step": 285800 }, { "epoch": 0.95, - "learning_rate": 2.6276022508102518e-06, - "loss": 3.2022, + "learning_rate": 2.6790384195229173e-06, + "loss": 3.183, "step": 285900 }, { "epoch": 0.95, - "learning_rate": 2.6110326818178805e-06, - "loss": 3.1907, + "learning_rate": 2.662486841495468e-06, + "loss": 3.1674, "step": 286000 }, { "epoch": 0.95, - "learning_rate": 2.5944631128255093e-06, - "loss": 3.1913, + "learning_rate": 2.645935263468019e-06, + "loss": 3.1804, "step": 286100 }, { "epoch": 0.95, - "learning_rate": 2.5778935438331377e-06, - "loss": 3.1965, + "learning_rate": 2.62938368544057e-06, + "loss": 3.1645, "step": 286200 }, { "epoch": 0.95, - "learning_rate": 2.5613239748407665e-06, - "loss": 3.2009, + "learning_rate": 2.6128321074131207e-06, + "loss": 3.1831, "step": 286300 }, { "epoch": 0.95, - "learning_rate": 2.5447544058483953e-06, - "loss": 3.1979, + "learning_rate": 2.5962805293856715e-06, + "loss": 3.1914, "step": 286400 }, { "epoch": 0.95, - "learning_rate": 2.528184836856024e-06, - "loss": 3.2045, + "learning_rate": 2.5797289513582227e-06, + "loss": 3.1885, "step": 286500 }, { "epoch": 0.95, - "learning_rate": 2.5116152678636524e-06, - "loss": 3.216, + "learning_rate": 2.5631773733307734e-06, + "loss": 3.1687, "step": 286600 }, { "epoch": 0.95, - "learning_rate": 2.495045698871281e-06, - "loss": 3.1947, + "learning_rate": 2.546625795303324e-06, + "loss": 3.1774, "step": 286700 }, { "epoch": 0.95, - "learning_rate": 2.47847612987891e-06, - "loss": 3.2021, + "learning_rate": 2.530074217275875e-06, + "loss": 3.1806, "step": 286800 }, { "epoch": 0.95, - "learning_rate": 2.4619065608865383e-06, - "loss": 3.2067, + "learning_rate": 2.513522639248426e-06, + "loss": 3.1848, "step": 286900 }, { "epoch": 0.95, - "learning_rate": 2.445336991894167e-06, - "loss": 3.2126, + "learning_rate": 2.496971061220977e-06, + "loss": 3.1876, "step": 287000 }, { "epoch": 0.95, - "learning_rate": 2.428767422901796e-06, - "loss": 3.1981, + "learning_rate": 2.4804194831935276e-06, + "loss": 3.1861, "step": 287100 }, { "epoch": 0.95, - "learning_rate": 2.4121978539094242e-06, - "loss": 3.2215, + "learning_rate": 2.4638679051660788e-06, + "loss": 3.1778, "step": 287200 }, { "epoch": 0.95, - "learning_rate": 2.395628284917053e-06, - "loss": 3.1964, + "learning_rate": 2.4473163271386295e-06, + "loss": 3.1881, "step": 287300 }, { "epoch": 0.95, - "learning_rate": 2.3790587159246814e-06, - "loss": 3.1968, + "learning_rate": 2.4307647491111803e-06, + "loss": 3.1748, "step": 287400 }, { "epoch": 0.95, - "learning_rate": 2.36248914693231e-06, - "loss": 3.1969, + "learning_rate": 2.414213171083731e-06, + "loss": 3.1889, "step": 287500 }, { "epoch": 0.95, - "learning_rate": 2.345919577939939e-06, - "loss": 3.186, + "learning_rate": 2.3976615930562822e-06, + "loss": 3.1885, "step": 287600 }, { "epoch": 0.95, - "learning_rate": 2.3293500089475673e-06, - "loss": 3.1977, + "learning_rate": 2.381110015028833e-06, + "loss": 3.1869, "step": 287700 }, { "epoch": 0.95, - "learning_rate": 2.312780439955196e-06, - "loss": 3.1927, + "learning_rate": 2.3645584370013837e-06, + "loss": 3.1853, "step": 287800 }, { "epoch": 0.95, - "learning_rate": 2.2962108709628244e-06, - "loss": 3.1928, + "learning_rate": 2.348006858973935e-06, + "loss": 3.1835, "step": 287900 }, { "epoch": 0.95, - "learning_rate": 2.2796413019704532e-06, - "loss": 3.1832, + "learning_rate": 2.3314552809464857e-06, + "loss": 3.1781, "step": 288000 }, { "epoch": 0.95, - "learning_rate": 2.263071732978082e-06, - "loss": 3.1958, + "learning_rate": 2.3149037029190364e-06, + "loss": 3.174, "step": 288100 }, { - "epoch": 0.96, - "learning_rate": 2.2465021639857104e-06, - "loss": 3.1934, + "epoch": 0.95, + "learning_rate": 2.298352124891587e-06, + "loss": 3.1868, "step": 288200 }, { - "epoch": 0.96, - "learning_rate": 2.229932594993339e-06, - "loss": 3.1973, + "epoch": 0.95, + "learning_rate": 2.2818005468641383e-06, + "loss": 3.1725, "step": 288300 }, { - "epoch": 0.96, - "learning_rate": 2.213363026000968e-06, - "loss": 3.2021, + "epoch": 0.95, + "learning_rate": 2.265248968836689e-06, + "loss": 3.1727, "step": 288400 }, { "epoch": 0.96, - "learning_rate": 2.1967934570085963e-06, - "loss": 3.2052, + "learning_rate": 2.24869739080924e-06, + "loss": 3.1856, "step": 288500 }, { "epoch": 0.96, - "learning_rate": 2.180223888016225e-06, - "loss": 3.205, + "learning_rate": 2.2321458127817906e-06, + "loss": 3.1698, "step": 288600 }, { "epoch": 0.96, - "learning_rate": 2.1636543190238534e-06, - "loss": 3.1919, + "learning_rate": 2.2155942347543418e-06, + "loss": 3.1837, "step": 288700 }, { "epoch": 0.96, - "learning_rate": 2.147084750031482e-06, - "loss": 3.1802, + "learning_rate": 2.1990426567268925e-06, + "loss": 3.1693, "step": 288800 }, { "epoch": 0.96, - "learning_rate": 2.130515181039111e-06, - "loss": 3.1896, + "learning_rate": 2.1824910786994433e-06, + "loss": 3.1833, "step": 288900 }, { "epoch": 0.96, - "learning_rate": 2.1139456120467393e-06, - "loss": 3.1952, + "learning_rate": 2.1659395006719945e-06, + "loss": 3.1834, "step": 289000 }, { "epoch": 0.96, - "learning_rate": 2.097376043054368e-06, - "loss": 3.193, + "learning_rate": 2.149387922644545e-06, + "loss": 3.1817, "step": 289100 }, { "epoch": 0.96, - "learning_rate": 2.0808064740619965e-06, - "loss": 3.1995, + "learning_rate": 2.132836344617096e-06, + "loss": 3.1702, "step": 289200 }, { "epoch": 0.96, - "learning_rate": 2.0642369050696253e-06, - "loss": 3.1722, + "learning_rate": 2.1162847665896467e-06, + "loss": 3.1801, "step": 289300 }, { "epoch": 0.96, - "learning_rate": 2.047667336077254e-06, - "loss": 3.1898, + "learning_rate": 2.099733188562198e-06, + "loss": 3.185, "step": 289400 }, { "epoch": 0.96, - "learning_rate": 2.031097767084883e-06, - "loss": 3.1856, + "learning_rate": 2.0831816105347486e-06, + "loss": 3.1787, "step": 289500 }, { "epoch": 0.96, - "learning_rate": 2.014528198092511e-06, - "loss": 3.1907, + "learning_rate": 2.0666300325072994e-06, + "loss": 3.1936, "step": 289600 }, { "epoch": 0.96, - "learning_rate": 1.99795862910014e-06, - "loss": 3.2043, + "learning_rate": 2.05007845447985e-06, + "loss": 3.1712, "step": 289700 }, { "epoch": 0.96, - "learning_rate": 1.9813890601077688e-06, - "loss": 3.1981, + "learning_rate": 2.0335268764524013e-06, + "loss": 3.1812, "step": 289800 }, { "epoch": 0.96, - "learning_rate": 1.9648194911153975e-06, - "loss": 3.1953, + "learning_rate": 2.016975298424952e-06, + "loss": 3.1807, "step": 289900 }, { "epoch": 0.96, - "learning_rate": 1.948249922123026e-06, - "loss": 3.1966, + "learning_rate": 2.000423720397503e-06, + "loss": 3.1812, "step": 290000 }, { "epoch": 0.96, - "learning_rate": 1.9316803531306547e-06, - "loss": 3.195, + "learning_rate": 1.9838721423700536e-06, + "loss": 3.1756, "step": 290100 }, { "epoch": 0.96, - "learning_rate": 1.915110784138283e-06, - "loss": 3.2012, + "learning_rate": 1.9673205643426043e-06, + "loss": 3.1735, "step": 290200 }, { "epoch": 0.96, - "learning_rate": 1.8985412151459116e-06, - "loss": 3.187, + "learning_rate": 1.950768986315155e-06, + "loss": 3.1803, "step": 290300 }, { "epoch": 0.96, - "learning_rate": 1.8819716461535404e-06, - "loss": 3.1955, + "learning_rate": 1.9342174082877063e-06, + "loss": 3.1893, "step": 290400 }, { "epoch": 0.96, - "learning_rate": 1.865402077161169e-06, - "loss": 3.2055, + "learning_rate": 1.917665830260257e-06, + "loss": 3.1775, "step": 290500 }, { "epoch": 0.96, - "learning_rate": 1.8488325081687977e-06, - "loss": 3.188, + "learning_rate": 1.901114252232808e-06, + "loss": 3.1824, "step": 290600 }, { "epoch": 0.96, - "learning_rate": 1.832262939176426e-06, - "loss": 3.1897, + "learning_rate": 1.8845626742053587e-06, + "loss": 3.1943, "step": 290700 }, { "epoch": 0.96, - "learning_rate": 1.8156933701840549e-06, - "loss": 3.1816, + "learning_rate": 1.8680110961779097e-06, + "loss": 3.1825, "step": 290800 }, { "epoch": 0.96, - "learning_rate": 1.7991238011916837e-06, - "loss": 3.1946, + "learning_rate": 1.8514595181504607e-06, + "loss": 3.1727, "step": 290900 }, { "epoch": 0.96, - "learning_rate": 1.782554232199312e-06, - "loss": 3.2138, + "learning_rate": 1.8349079401230114e-06, + "loss": 3.1731, "step": 291000 }, { "epoch": 0.96, - "learning_rate": 1.7659846632069408e-06, - "loss": 3.2028, + "learning_rate": 1.8183563620955624e-06, + "loss": 3.1667, "step": 291100 }, { - "epoch": 0.97, - "learning_rate": 1.7494150942145692e-06, - "loss": 3.1968, + "epoch": 0.96, + "learning_rate": 1.8018047840681131e-06, + "loss": 3.1719, "step": 291200 }, { - "epoch": 0.97, - "learning_rate": 1.732845525222198e-06, - "loss": 3.1996, + "epoch": 0.96, + "learning_rate": 1.7852532060406639e-06, + "loss": 3.1885, "step": 291300 }, { - "epoch": 0.97, - "learning_rate": 1.7162759562298267e-06, - "loss": 3.1971, + "epoch": 0.96, + "learning_rate": 1.7687016280132146e-06, + "loss": 3.1889, "step": 291400 }, { - "epoch": 0.97, - "learning_rate": 1.699706387237455e-06, - "loss": 3.1903, + "epoch": 0.96, + "learning_rate": 1.7521500499857658e-06, + "loss": 3.1978, "step": 291500 }, { "epoch": 0.97, - "learning_rate": 1.6831368182450839e-06, - "loss": 3.2047, + "learning_rate": 1.7355984719583166e-06, + "loss": 3.1771, "step": 291600 }, { "epoch": 0.97, - "learning_rate": 1.6665672492527124e-06, - "loss": 3.198, + "learning_rate": 1.7190468939308673e-06, + "loss": 3.1727, "step": 291700 }, { "epoch": 0.97, - "learning_rate": 1.649997680260341e-06, - "loss": 3.1874, + "learning_rate": 1.7024953159034185e-06, + "loss": 3.1841, "step": 291800 }, { "epoch": 0.97, - "learning_rate": 1.6334281112679698e-06, - "loss": 3.1945, + "learning_rate": 1.6859437378759693e-06, + "loss": 3.1956, "step": 291900 }, { "epoch": 0.97, - "learning_rate": 1.6168585422755984e-06, - "loss": 3.1789, + "learning_rate": 1.66939215984852e-06, + "loss": 3.1708, "step": 292000 }, { "epoch": 0.97, - "learning_rate": 1.6002889732832271e-06, - "loss": 3.1932, + "learning_rate": 1.6528405818210708e-06, + "loss": 3.1776, "step": 292100 }, { "epoch": 0.97, - "learning_rate": 1.583719404290856e-06, - "loss": 3.1847, + "learning_rate": 1.636289003793622e-06, + "loss": 3.1812, "step": 292200 }, { "epoch": 0.97, - "learning_rate": 1.5671498352984843e-06, - "loss": 3.2007, + "learning_rate": 1.6197374257661727e-06, + "loss": 3.1849, "step": 292300 }, { "epoch": 0.97, - "learning_rate": 1.5505802663061129e-06, - "loss": 3.2008, + "learning_rate": 1.6031858477387234e-06, + "loss": 3.186, "step": 292400 }, { "epoch": 0.97, - "learning_rate": 1.5340106973137416e-06, - "loss": 3.1925, + "learning_rate": 1.5866342697112742e-06, + "loss": 3.1821, "step": 292500 }, { "epoch": 0.97, - "learning_rate": 1.5174411283213702e-06, - "loss": 3.191, + "learning_rate": 1.5700826916838254e-06, + "loss": 3.1837, "step": 292600 }, { "epoch": 0.97, - "learning_rate": 1.5008715593289988e-06, - "loss": 3.205, + "learning_rate": 1.5535311136563761e-06, + "loss": 3.176, "step": 292700 }, { "epoch": 0.97, - "learning_rate": 1.4843019903366273e-06, - "loss": 3.1892, + "learning_rate": 1.536979535628927e-06, + "loss": 3.1906, "step": 292800 }, { "epoch": 0.97, - "learning_rate": 1.4677324213442561e-06, - "loss": 3.1991, + "learning_rate": 1.5204279576014778e-06, + "loss": 3.1814, "step": 292900 }, { "epoch": 0.97, - "learning_rate": 1.4511628523518847e-06, - "loss": 3.1787, + "learning_rate": 1.5038763795740286e-06, + "loss": 3.1792, "step": 293000 }, { "epoch": 0.97, - "learning_rate": 1.4345932833595133e-06, - "loss": 3.189, + "learning_rate": 1.4873248015465796e-06, + "loss": 3.181, "step": 293100 }, { "epoch": 0.97, - "learning_rate": 1.4180237143671418e-06, - "loss": 3.1957, + "learning_rate": 1.4707732235191303e-06, + "loss": 3.1924, "step": 293200 }, { "epoch": 0.97, - "learning_rate": 1.4014541453747706e-06, - "loss": 3.1977, + "learning_rate": 1.454221645491681e-06, + "loss": 3.1859, "step": 293300 }, { "epoch": 0.97, - "learning_rate": 1.3848845763823992e-06, - "loss": 3.1947, + "learning_rate": 1.437670067464232e-06, + "loss": 3.1868, "step": 293400 }, { "epoch": 0.97, - "learning_rate": 1.368315007390028e-06, - "loss": 3.192, + "learning_rate": 1.421118489436783e-06, + "loss": 3.1936, "step": 293500 }, { "epoch": 0.97, - "learning_rate": 1.3517454383976565e-06, - "loss": 3.1893, + "learning_rate": 1.4045669114093338e-06, + "loss": 3.1698, "step": 293600 }, { "epoch": 0.97, - "learning_rate": 1.3351758694052851e-06, - "loss": 3.195, + "learning_rate": 1.3880153333818847e-06, + "loss": 3.1745, "step": 293700 }, { "epoch": 0.97, - "learning_rate": 1.3186063004129137e-06, - "loss": 3.2036, + "learning_rate": 1.3714637553544355e-06, + "loss": 3.1815, "step": 293800 }, { "epoch": 0.97, - "learning_rate": 1.3020367314205425e-06, - "loss": 3.1751, + "learning_rate": 1.3549121773269864e-06, + "loss": 3.1744, "step": 293900 }, { "epoch": 0.97, - "learning_rate": 1.285467162428171e-06, - "loss": 3.1862, + "learning_rate": 1.3383605992995372e-06, + "loss": 3.164, "step": 294000 }, { "epoch": 0.97, - "learning_rate": 1.2688975934357996e-06, - "loss": 3.2041, + "learning_rate": 1.3218090212720882e-06, + "loss": 3.1744, "step": 294100 }, { "epoch": 0.97, - "learning_rate": 1.2523280244434282e-06, - "loss": 3.2073, + "learning_rate": 1.3052574432446391e-06, + "loss": 3.1882, "step": 294200 }, { - "epoch": 0.98, - "learning_rate": 1.2357584554510567e-06, - "loss": 3.1847, + "epoch": 0.97, + "learning_rate": 1.2887058652171899e-06, + "loss": 3.174, "step": 294300 }, { - "epoch": 0.98, - "learning_rate": 1.2191888864586855e-06, - "loss": 3.2026, + "epoch": 0.97, + "learning_rate": 1.2721542871897408e-06, + "loss": 3.1899, "step": 294400 }, { - "epoch": 0.98, - "learning_rate": 1.202619317466314e-06, - "loss": 3.1919, + "epoch": 0.97, + "learning_rate": 1.2556027091622916e-06, + "loss": 3.1791, "step": 294500 }, { "epoch": 0.98, - "learning_rate": 1.1860497484739427e-06, - "loss": 3.1985, + "learning_rate": 1.2390511311348426e-06, + "loss": 3.1678, "step": 294600 }, { "epoch": 0.98, - "learning_rate": 1.1694801794815712e-06, - "loss": 3.2101, + "learning_rate": 1.2224995531073933e-06, + "loss": 3.1793, "step": 294700 }, { "epoch": 0.98, - "learning_rate": 1.1529106104892e-06, - "loss": 3.1899, + "learning_rate": 1.2059479750799443e-06, + "loss": 3.1826, "step": 294800 }, { "epoch": 0.98, - "learning_rate": 1.1363410414968286e-06, - "loss": 3.1927, + "learning_rate": 1.189396397052495e-06, + "loss": 3.1821, "step": 294900 }, { "epoch": 0.98, - "learning_rate": 1.1197714725044574e-06, - "loss": 3.1931, + "learning_rate": 1.172844819025046e-06, + "loss": 3.1752, "step": 295000 }, { "epoch": 0.98, - "learning_rate": 1.103201903512086e-06, - "loss": 3.1946, + "learning_rate": 1.1562932409975967e-06, + "loss": 3.167, "step": 295100 }, { "epoch": 0.98, - "learning_rate": 1.0866323345197145e-06, - "loss": 3.1989, + "learning_rate": 1.1397416629701475e-06, + "loss": 3.1934, "step": 295200 }, { "epoch": 0.98, - "learning_rate": 1.0700627655273433e-06, - "loss": 3.1924, + "learning_rate": 1.1231900849426985e-06, + "loss": 3.1686, "step": 295300 }, { "epoch": 0.98, - "learning_rate": 1.0534931965349719e-06, - "loss": 3.2012, + "learning_rate": 1.1066385069152492e-06, + "loss": 3.1914, "step": 295400 }, { "epoch": 0.98, - "learning_rate": 1.0369236275426004e-06, - "loss": 3.1935, + "learning_rate": 1.0900869288878002e-06, + "loss": 3.1883, "step": 295500 }, { "epoch": 0.98, - "learning_rate": 1.020354058550229e-06, - "loss": 3.1971, + "learning_rate": 1.073535350860351e-06, + "loss": 3.1797, "step": 295600 }, { "epoch": 0.98, - "learning_rate": 1.0037844895578576e-06, - "loss": 3.182, + "learning_rate": 1.056983772832902e-06, + "loss": 3.1655, "step": 295700 }, { "epoch": 0.98, - "learning_rate": 9.872149205654864e-07, - "loss": 3.2003, + "learning_rate": 1.0404321948054529e-06, + "loss": 3.1817, "step": 295800 }, { "epoch": 0.98, - "learning_rate": 9.70645351573115e-07, - "loss": 3.1981, + "learning_rate": 1.0238806167780036e-06, + "loss": 3.1788, "step": 295900 }, { "epoch": 0.98, - "learning_rate": 9.540757825807435e-07, - "loss": 3.2116, + "learning_rate": 1.0073290387505546e-06, + "loss": 3.1789, "step": 296000 }, { "epoch": 0.98, - "learning_rate": 9.375062135883722e-07, - "loss": 3.1974, + "learning_rate": 9.907774607231053e-07, + "loss": 3.1745, "step": 296100 }, { "epoch": 0.98, - "learning_rate": 9.209366445960007e-07, - "loss": 3.1994, + "learning_rate": 9.742258826956563e-07, + "loss": 3.1784, "step": 296200 }, { "epoch": 0.98, - "learning_rate": 9.043670756036295e-07, - "loss": 3.2025, + "learning_rate": 9.57674304668207e-07, + "loss": 3.1881, "step": 296300 }, { "epoch": 0.98, - "learning_rate": 8.877975066112581e-07, - "loss": 3.1962, + "learning_rate": 9.41122726640758e-07, + "loss": 3.1753, "step": 296400 }, { "epoch": 0.98, - "learning_rate": 8.712279376188867e-07, - "loss": 3.1907, + "learning_rate": 9.245711486133088e-07, + "loss": 3.1879, "step": 296500 }, { "epoch": 0.98, - "learning_rate": 8.546583686265152e-07, - "loss": 3.1928, + "learning_rate": 9.080195705858597e-07, + "loss": 3.1751, "step": 296600 }, { "epoch": 0.98, - "learning_rate": 8.38088799634144e-07, - "loss": 3.1951, + "learning_rate": 8.914679925584106e-07, + "loss": 3.1598, "step": 296700 }, { "epoch": 0.98, - "learning_rate": 8.215192306417726e-07, - "loss": 3.1842, + "learning_rate": 8.749164145309613e-07, + "loss": 3.1756, "step": 296800 }, { "epoch": 0.98, - "learning_rate": 8.049496616494013e-07, - "loss": 3.1921, + "learning_rate": 8.583648365035123e-07, + "loss": 3.1813, "step": 296900 }, { "epoch": 0.98, - "learning_rate": 7.883800926570298e-07, - "loss": 3.1984, + "learning_rate": 8.418132584760631e-07, + "loss": 3.181, "step": 297000 }, { "epoch": 0.98, - "learning_rate": 7.718105236646585e-07, - "loss": 3.1898, + "learning_rate": 8.25261680448614e-07, + "loss": 3.1955, "step": 297100 }, { "epoch": 0.98, - "learning_rate": 7.552409546722871e-07, - "loss": 3.2005, + "learning_rate": 8.087101024211648e-07, + "loss": 3.1831, "step": 297200 }, { - "epoch": 0.99, - "learning_rate": 7.386713856799158e-07, - "loss": 3.1964, + "epoch": 0.98, + "learning_rate": 7.921585243937158e-07, + "loss": 3.1818, "step": 297300 }, { - "epoch": 0.99, - "learning_rate": 7.221018166875443e-07, - "loss": 3.1889, + "epoch": 0.98, + "learning_rate": 7.756069463662666e-07, + "loss": 3.165, "step": 297400 }, { - "epoch": 0.99, - "learning_rate": 7.055322476951729e-07, - "loss": 3.2061, + "epoch": 0.98, + "learning_rate": 7.590553683388175e-07, + "loss": 3.1697, "step": 297500 }, { "epoch": 0.99, - "learning_rate": 6.889626787028016e-07, - "loss": 3.1963, + "learning_rate": 7.425037903113683e-07, + "loss": 3.1783, "step": 297600 }, { "epoch": 0.99, - "learning_rate": 6.723931097104303e-07, - "loss": 3.1858, + "learning_rate": 7.259522122839192e-07, + "loss": 3.1876, "step": 297700 }, { "epoch": 0.99, - "learning_rate": 6.558235407180589e-07, - "loss": 3.1937, + "learning_rate": 7.0940063425647e-07, + "loss": 3.1694, "step": 297800 }, { "epoch": 0.99, - "learning_rate": 6.392539717256875e-07, - "loss": 3.1931, + "learning_rate": 6.928490562290209e-07, + "loss": 3.1809, "step": 297900 }, { "epoch": 0.99, - "learning_rate": 6.226844027333162e-07, - "loss": 3.1911, + "learning_rate": 6.762974782015718e-07, + "loss": 3.1672, "step": 298000 }, { "epoch": 0.99, - "learning_rate": 6.061148337409447e-07, - "loss": 3.1961, + "learning_rate": 6.597459001741226e-07, + "loss": 3.187, "step": 298100 }, { "epoch": 0.99, - "learning_rate": 5.895452647485733e-07, - "loss": 3.2042, + "learning_rate": 6.431943221466735e-07, + "loss": 3.1807, "step": 298200 }, { "epoch": 0.99, - "learning_rate": 5.72975695756202e-07, - "loss": 3.1891, + "learning_rate": 6.266427441192243e-07, + "loss": 3.1856, "step": 298300 }, { "epoch": 0.99, - "learning_rate": 5.564061267638307e-07, - "loss": 3.1903, + "learning_rate": 6.100911660917752e-07, + "loss": 3.17, "step": 298400 }, { "epoch": 0.99, - "learning_rate": 5.398365577714593e-07, - "loss": 3.202, + "learning_rate": 5.935395880643261e-07, + "loss": 3.1838, "step": 298500 }, { "epoch": 0.99, - "learning_rate": 5.232669887790879e-07, - "loss": 3.1893, + "learning_rate": 5.76988010036877e-07, + "loss": 3.1819, "step": 298600 }, { "epoch": 0.99, - "learning_rate": 5.066974197867166e-07, - "loss": 3.1945, + "learning_rate": 5.604364320094279e-07, + "loss": 3.1716, "step": 298700 }, { "epoch": 0.99, - "learning_rate": 4.901278507943452e-07, - "loss": 3.1845, + "learning_rate": 5.438848539819786e-07, + "loss": 3.1929, "step": 298800 }, { "epoch": 0.99, - "learning_rate": 4.735582818019738e-07, - "loss": 3.1887, + "learning_rate": 5.273332759545295e-07, + "loss": 3.1804, "step": 298900 }, { "epoch": 0.99, - "learning_rate": 4.5698871280960246e-07, - "loss": 3.1914, + "learning_rate": 5.107816979270804e-07, + "loss": 3.1826, "step": 299000 }, { "epoch": 0.99, - "learning_rate": 4.4041914381723103e-07, - "loss": 3.1897, + "learning_rate": 4.942301198996312e-07, + "loss": 3.1774, "step": 299100 }, { "epoch": 0.99, - "learning_rate": 4.238495748248597e-07, - "loss": 3.1971, + "learning_rate": 4.776785418721821e-07, + "loss": 3.1805, "step": 299200 }, { "epoch": 0.99, - "learning_rate": 4.072800058324883e-07, - "loss": 3.1771, + "learning_rate": 4.6112696384473293e-07, + "loss": 3.1867, "step": 299300 }, { "epoch": 0.99, - "learning_rate": 3.907104368401169e-07, - "loss": 3.2013, + "learning_rate": 4.445753858172839e-07, + "loss": 3.1791, "step": 299400 }, { "epoch": 0.99, - "learning_rate": 3.741408678477456e-07, - "loss": 3.2098, + "learning_rate": 4.280238077898347e-07, + "loss": 3.1744, "step": 299500 }, { "epoch": 0.99, - "learning_rate": 3.575712988553742e-07, - "loss": 3.2141, + "learning_rate": 4.1147222976238556e-07, + "loss": 3.1709, "step": 299600 }, { "epoch": 0.99, - "learning_rate": 3.410017298630028e-07, - "loss": 3.1915, + "learning_rate": 3.949206517349364e-07, + "loss": 3.1803, "step": 299700 }, { "epoch": 0.99, - "learning_rate": 3.2443216087063145e-07, - "loss": 3.1944, + "learning_rate": 3.783690737074873e-07, + "loss": 3.1865, "step": 299800 }, { "epoch": 0.99, - "learning_rate": 3.0786259187826007e-07, - "loss": 3.2052, + "learning_rate": 3.6181749568003814e-07, + "loss": 3.1713, "step": 299900 }, { "epoch": 0.99, - "learning_rate": 2.912930228858887e-07, - "loss": 3.1782, + "learning_rate": 3.4526591765258905e-07, + "loss": 3.1753, "step": 300000 }, { "epoch": 0.99, - "learning_rate": 2.747234538935173e-07, - "loss": 3.2006, + "learning_rate": 3.2871433962513986e-07, + "loss": 3.1801, "step": 300100 }, { "epoch": 0.99, - "learning_rate": 2.58153884901146e-07, - "loss": 3.2034, + "learning_rate": 3.121627615976907e-07, + "loss": 3.1985, "step": 300200 }, { - "epoch": 1.0, - "learning_rate": 2.415843159087746e-07, - "loss": 3.1802, + "epoch": 0.99, + "learning_rate": 2.9561118357024157e-07, + "loss": 3.1769, "step": 300300 }, { - "epoch": 1.0, - "learning_rate": 2.250147469164032e-07, - "loss": 3.1951, + "epoch": 0.99, + "learning_rate": 2.790596055427925e-07, + "loss": 3.1824, "step": 300400 }, { - "epoch": 1.0, - "learning_rate": 2.0844517792403183e-07, - "loss": 3.2002, + "epoch": 0.99, + "learning_rate": 2.6250802751534334e-07, + "loss": 3.1864, "step": 300500 }, { "epoch": 1.0, - "learning_rate": 1.9187560893166048e-07, - "loss": 3.2057, + "learning_rate": 2.459564494878942e-07, + "loss": 3.1831, "step": 300600 }, { "epoch": 1.0, - "learning_rate": 1.753060399392891e-07, - "loss": 3.1817, + "learning_rate": 2.2940487146044504e-07, + "loss": 3.1947, "step": 300700 }, { "epoch": 1.0, - "learning_rate": 1.5873647094691776e-07, - "loss": 3.1965, + "learning_rate": 2.1285329343299592e-07, + "loss": 3.1761, "step": 300800 }, { "epoch": 1.0, - "learning_rate": 1.4216690195454635e-07, - "loss": 3.1806, + "learning_rate": 1.9630171540554678e-07, + "loss": 3.1751, "step": 300900 }, { "epoch": 1.0, - "learning_rate": 1.25597332962175e-07, - "loss": 3.2019, + "learning_rate": 1.7975013737809764e-07, + "loss": 3.1802, "step": 301000 }, { "epoch": 1.0, - "learning_rate": 1.0902776396980363e-07, - "loss": 3.1854, + "learning_rate": 1.631985593506485e-07, + "loss": 3.1669, "step": 301100 }, { "epoch": 1.0, - "learning_rate": 9.245819497743225e-08, - "loss": 3.1878, + "learning_rate": 1.4664698132319936e-07, + "loss": 3.1814, "step": 301200 }, { "epoch": 1.0, - "learning_rate": 7.588862598506089e-08, - "loss": 3.1899, + "learning_rate": 1.3009540329575022e-07, + "loss": 3.1754, "step": 301300 }, { "epoch": 1.0, - "learning_rate": 5.93190569926895e-08, - "loss": 3.1923, + "learning_rate": 1.1354382526830108e-07, + "loss": 3.1674, "step": 301400 }, { "epoch": 1.0, - "learning_rate": 4.274948800031814e-08, - "loss": 3.2046, + "learning_rate": 9.699224724085195e-08, + "loss": 3.1877, "step": 301500 + }, + { + "epoch": 1.0, + "learning_rate": 8.044066921340281e-08, + "loss": 3.163, + "step": 301600 + }, + { + "epoch": 1.0, + "learning_rate": 6.388909118595368e-08, + "loss": 3.1852, + "step": 301700 + }, + { + "epoch": 1.0, + "learning_rate": 4.733751315850453e-08, + "loss": 3.1737, + "step": 301800 + }, + { + "epoch": 1.0, + "learning_rate": 3.07859351310554e-08, + "loss": 3.1886, + "step": 301900 + }, + { + "epoch": 1.0, + "learning_rate": 1.423435710360626e-08, + "loss": 3.1663, + "step": 302000 } ], - "max_steps": 301758, + "max_steps": 302086, "num_train_epochs": 1, - "total_flos": 2.575848645328896e+18, + "total_flos": 2.580120367792128e+18, "trial_name": null, "trial_params": null }