diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,18136 +1,18106 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 0.9991860934470597, - "global_step": 302000, + "epoch": 0.9991450102399937, + "global_step": 301500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, - "learning_rate": 4.9983457183883334e-05, - "loss": 3.2639, + "learning_rate": 4.9983430431007635e-05, + "loss": 3.2342, "step": 100 }, { "epoch": 0.0, - "learning_rate": 4.996691436776665e-05, - "loss": 3.2781, + "learning_rate": 4.996686086201526e-05, + "loss": 3.2296, "step": 200 }, { "epoch": 0.0, - "learning_rate": 4.995037155164998e-05, - "loss": 3.2758, + "learning_rate": 4.995029129302289e-05, + "loss": 3.2473, "step": 300 }, { "epoch": 0.0, - "learning_rate": 4.9933828735533314e-05, - "loss": 3.2775, + "learning_rate": 4.993372172403052e-05, + "loss": 3.2422, "step": 400 }, { "epoch": 0.0, - "learning_rate": 4.991728591941663e-05, - "loss": 3.2774, + "learning_rate": 4.9917152155038145e-05, + "loss": 3.2386, "step": 500 }, { "epoch": 0.0, - "learning_rate": 4.990074310329996e-05, - "loss": 3.2595, + "learning_rate": 4.990058258604578e-05, + "loss": 3.2347, "step": 600 }, { "epoch": 0.0, - "learning_rate": 4.9884200287183294e-05, - "loss": 3.2909, + "learning_rate": 4.9884013017053403e-05, + "loss": 3.2354, "step": 700 }, { "epoch": 0.0, - "learning_rate": 4.986765747106661e-05, - "loss": 3.2913, + "learning_rate": 4.986744344806103e-05, + "loss": 3.2574, "step": 800 }, { "epoch": 0.0, - "learning_rate": 4.9851114654949944e-05, - "loss": 3.2938, + "learning_rate": 4.985087387906866e-05, + "loss": 3.2561, "step": 900 }, { "epoch": 0.0, - "learning_rate": 4.9834571838833275e-05, - "loss": 3.2852, + "learning_rate": 4.983430431007629e-05, + "loss": 3.2664, "step": 1000 }, { "epoch": 0.0, - "learning_rate": 4.98180290227166e-05, - "loss": 3.2939, + "learning_rate": 4.9817734741083913e-05, + "loss": 3.251, "step": 1100 }, { "epoch": 0.0, - "learning_rate": 4.9801486206599924e-05, - "loss": 3.2833, + "learning_rate": 4.9801165172091546e-05, + "loss": 3.25, "step": 1200 }, { "epoch": 0.0, - "learning_rate": 4.9784943390483255e-05, - "loss": 3.2919, + "learning_rate": 4.978459560309918e-05, + "loss": 3.245, "step": 1300 }, { "epoch": 0.0, - "learning_rate": 4.976840057436658e-05, - "loss": 3.2771, + "learning_rate": 4.9768026034106804e-05, + "loss": 3.2417, "step": 1400 }, { "epoch": 0.0, - "learning_rate": 4.9751857758249904e-05, - "loss": 3.2949, + "learning_rate": 4.975145646511443e-05, + "loss": 3.2543, "step": 1500 }, { "epoch": 0.01, - "learning_rate": 4.973531494213323e-05, - "loss": 3.2974, + "learning_rate": 4.973488689612206e-05, + "loss": 3.2517, "step": 1600 }, { "epoch": 0.01, - "learning_rate": 4.971877212601656e-05, - "loss": 3.307, + "learning_rate": 4.971831732712969e-05, + "loss": 3.2528, "step": 1700 }, { "epoch": 0.01, - "learning_rate": 4.9702229309899885e-05, - "loss": 3.2939, + "learning_rate": 4.970174775813732e-05, + "loss": 3.245, "step": 1800 }, { "epoch": 0.01, - "learning_rate": 4.968568649378321e-05, - "loss": 3.2917, + "learning_rate": 4.968517818914495e-05, + "loss": 3.2543, "step": 1900 }, { "epoch": 0.01, - "learning_rate": 4.966914367766654e-05, - "loss": 3.2832, + "learning_rate": 4.966860862015257e-05, + "loss": 3.2626, "step": 2000 }, { "epoch": 0.01, - "learning_rate": 4.9652600861549865e-05, - "loss": 3.2845, + "learning_rate": 4.9652039051160206e-05, + "loss": 3.2535, "step": 2100 }, { "epoch": 0.01, - "learning_rate": 4.963605804543319e-05, - "loss": 3.3021, + "learning_rate": 4.963546948216783e-05, + "loss": 3.2511, "step": 2200 }, { "epoch": 0.01, - "learning_rate": 4.961951522931652e-05, - "loss": 3.2918, + "learning_rate": 4.961889991317546e-05, + "loss": 3.2571, "step": 2300 }, { "epoch": 0.01, - "learning_rate": 4.9602972413199845e-05, - "loss": 3.2982, + "learning_rate": 4.960233034418309e-05, + "loss": 3.2549, "step": 2400 }, { "epoch": 0.01, - "learning_rate": 4.958642959708317e-05, - "loss": 3.2903, + "learning_rate": 4.958576077519072e-05, + "loss": 3.2534, "step": 2500 }, { "epoch": 0.01, - "learning_rate": 4.95698867809665e-05, - "loss": 3.2898, + "learning_rate": 4.956919120619835e-05, + "loss": 3.2504, "step": 2600 }, { "epoch": 0.01, - "learning_rate": 4.9553343964849826e-05, - "loss": 3.297, + "learning_rate": 4.9552621637205974e-05, + "loss": 3.2426, "step": 2700 }, { "epoch": 0.01, - "learning_rate": 4.953680114873315e-05, - "loss": 3.2864, + "learning_rate": 4.9536052068213607e-05, + "loss": 3.2643, "step": 2800 }, { "epoch": 0.01, - "learning_rate": 4.952025833261648e-05, - "loss": 3.2827, + "learning_rate": 4.951948249922123e-05, + "loss": 3.2465, "step": 2900 }, { "epoch": 0.01, - "learning_rate": 4.9503715516499806e-05, - "loss": 3.2932, + "learning_rate": 4.9502912930228865e-05, + "loss": 3.2441, "step": 3000 }, { "epoch": 0.01, - "learning_rate": 4.948717270038313e-05, - "loss": 3.2809, + "learning_rate": 4.948634336123649e-05, + "loss": 3.2632, "step": 3100 }, { "epoch": 0.01, - "learning_rate": 4.947062988426646e-05, - "loss": 3.2943, + "learning_rate": 4.946977379224412e-05, + "loss": 3.249, "step": 3200 }, { "epoch": 0.01, - "learning_rate": 4.945408706814979e-05, - "loss": 3.2932, + "learning_rate": 4.945320422325175e-05, + "loss": 3.2477, "step": 3300 }, { "epoch": 0.01, - "learning_rate": 4.943754425203311e-05, - "loss": 3.3063, + "learning_rate": 4.9436634654259375e-05, + "loss": 3.2559, "step": 3400 }, { "epoch": 0.01, - "learning_rate": 4.942100143591644e-05, - "loss": 3.2854, + "learning_rate": 4.9420065085267e-05, + "loss": 3.2625, "step": 3500 }, { "epoch": 0.01, - "learning_rate": 4.9404458619799774e-05, - "loss": 3.2995, + "learning_rate": 4.9403495516274633e-05, + "loss": 3.2528, "step": 3600 }, { "epoch": 0.01, - "learning_rate": 4.938791580368309e-05, - "loss": 3.2967, + "learning_rate": 4.9386925947282266e-05, + "loss": 3.2534, "step": 3700 }, { "epoch": 0.01, - "learning_rate": 4.937137298756642e-05, - "loss": 3.3016, + "learning_rate": 4.937035637828989e-05, + "loss": 3.2627, "step": 3800 }, { "epoch": 0.01, - "learning_rate": 4.9354830171449754e-05, - "loss": 3.2916, + "learning_rate": 4.935378680929752e-05, + "loss": 3.2487, "step": 3900 }, { "epoch": 0.01, - "learning_rate": 4.933828735533307e-05, - "loss": 3.2958, + "learning_rate": 4.933721724030515e-05, + "loss": 3.2441, "step": 4000 }, { "epoch": 0.01, - "learning_rate": 4.93217445392164e-05, - "loss": 3.3011, + "learning_rate": 4.9320647671312776e-05, + "loss": 3.2566, "step": 4100 }, { "epoch": 0.01, - "learning_rate": 4.930520172309973e-05, - "loss": 3.2951, + "learning_rate": 4.930407810232041e-05, + "loss": 3.2602, "step": 4200 }, { "epoch": 0.01, - "learning_rate": 4.928865890698305e-05, - "loss": 3.2985, + "learning_rate": 4.9287508533328035e-05, + "loss": 3.2599, "step": 4300 }, { "epoch": 0.01, - "learning_rate": 4.9272116090866384e-05, - "loss": 3.2887, + "learning_rate": 4.927093896433566e-05, + "loss": 3.2581, "step": 4400 }, { "epoch": 0.01, - "learning_rate": 4.925557327474971e-05, - "loss": 3.2952, + "learning_rate": 4.925436939534329e-05, + "loss": 3.245, "step": 4500 }, { "epoch": 0.02, - "learning_rate": 4.923903045863303e-05, - "loss": 3.2845, + "learning_rate": 4.923779982635092e-05, + "loss": 3.2707, "step": 4600 }, { "epoch": 0.02, - "learning_rate": 4.9222487642516364e-05, - "loss": 3.2851, + "learning_rate": 4.9221230257358545e-05, + "loss": 3.2542, "step": 4700 }, { "epoch": 0.02, - "learning_rate": 4.920594482639969e-05, - "loss": 3.2916, + "learning_rate": 4.920466068836618e-05, + "loss": 3.2618, "step": 4800 }, { "epoch": 0.02, - "learning_rate": 4.918940201028301e-05, - "loss": 3.2851, + "learning_rate": 4.91880911193738e-05, + "loss": 3.2384, "step": 4900 }, { "epoch": 0.02, - "learning_rate": 4.9172859194166344e-05, - "loss": 3.2833, + "learning_rate": 4.9171521550381436e-05, + "loss": 3.2547, "step": 5000 }, { "epoch": 0.02, - "learning_rate": 4.915631637804967e-05, - "loss": 3.2786, + "learning_rate": 4.915495198138906e-05, + "loss": 3.247, "step": 5100 }, { "epoch": 0.02, - "learning_rate": 4.9139773561932993e-05, - "loss": 3.2954, + "learning_rate": 4.913838241239669e-05, + "loss": 3.2497, "step": 5200 }, { "epoch": 0.02, - "learning_rate": 4.9123230745816325e-05, - "loss": 3.282, + "learning_rate": 4.912181284340432e-05, + "loss": 3.2488, "step": 5300 }, { "epoch": 0.02, - "learning_rate": 4.910668792969965e-05, - "loss": 3.2972, + "learning_rate": 4.910524327441195e-05, + "loss": 3.2555, "step": 5400 }, { "epoch": 0.02, - "learning_rate": 4.909014511358298e-05, - "loss": 3.3043, + "learning_rate": 4.908867370541957e-05, + "loss": 3.2479, "step": 5500 }, { "epoch": 0.02, - "learning_rate": 4.9073602297466305e-05, - "loss": 3.2883, + "learning_rate": 4.9072104136427204e-05, + "loss": 3.2523, "step": 5600 }, { "epoch": 0.02, - "learning_rate": 4.905705948134963e-05, - "loss": 3.2923, + "learning_rate": 4.905553456743484e-05, + "loss": 3.2423, "step": 5700 }, { "epoch": 0.02, - "learning_rate": 4.904051666523296e-05, - "loss": 3.2822, + "learning_rate": 4.903896499844246e-05, + "loss": 3.2508, "step": 5800 }, { "epoch": 0.02, - "learning_rate": 4.9023973849116285e-05, - "loss": 3.2934, + "learning_rate": 4.902239542945009e-05, + "loss": 3.2563, "step": 5900 }, { "epoch": 0.02, - "learning_rate": 4.900743103299961e-05, - "loss": 3.2926, + "learning_rate": 4.900582586045772e-05, + "loss": 3.2491, "step": 6000 }, { "epoch": 0.02, - "learning_rate": 4.899088821688294e-05, - "loss": 3.2956, + "learning_rate": 4.898925629146535e-05, + "loss": 3.2463, "step": 6100 }, { "epoch": 0.02, - "learning_rate": 4.8974345400766266e-05, - "loss": 3.2989, + "learning_rate": 4.897268672247298e-05, + "loss": 3.2567, "step": 6200 }, { "epoch": 0.02, - "learning_rate": 4.895780258464959e-05, - "loss": 3.2896, + "learning_rate": 4.8956117153480605e-05, + "loss": 3.2525, "step": 6300 }, { "epoch": 0.02, - "learning_rate": 4.894125976853292e-05, - "loss": 3.2996, + "learning_rate": 4.893954758448823e-05, + "loss": 3.2581, "step": 6400 }, { "epoch": 0.02, - "learning_rate": 4.8924716952416246e-05, - "loss": 3.2976, + "learning_rate": 4.8922978015495863e-05, + "loss": 3.2604, "step": 6500 }, { "epoch": 0.02, - "learning_rate": 4.890817413629957e-05, - "loss": 3.2935, + "learning_rate": 4.8906408446503496e-05, + "loss": 3.2602, "step": 6600 }, { "epoch": 0.02, - "learning_rate": 4.88916313201829e-05, - "loss": 3.2942, + "learning_rate": 4.8889838877511115e-05, + "loss": 3.2515, "step": 6700 }, { "epoch": 0.02, - "learning_rate": 4.8875088504066227e-05, - "loss": 3.2969, + "learning_rate": 4.887326930851875e-05, + "loss": 3.258, "step": 6800 }, { "epoch": 0.02, - "learning_rate": 4.885854568794955e-05, - "loss": 3.2932, + "learning_rate": 4.885669973952638e-05, + "loss": 3.2555, "step": 6900 }, { "epoch": 0.02, - "learning_rate": 4.884200287183288e-05, - "loss": 3.3085, + "learning_rate": 4.8840130170534006e-05, + "loss": 3.2389, "step": 7000 }, { "epoch": 0.02, - "learning_rate": 4.882546005571621e-05, - "loss": 3.2937, + "learning_rate": 4.882356060154163e-05, + "loss": 3.2564, "step": 7100 }, { "epoch": 0.02, - "learning_rate": 4.880891723959953e-05, - "loss": 3.295, + "learning_rate": 4.8806991032549265e-05, + "loss": 3.2473, "step": 7200 }, { "epoch": 0.02, - "learning_rate": 4.879237442348286e-05, - "loss": 3.2826, + "learning_rate": 4.879042146355689e-05, + "loss": 3.2543, "step": 7300 }, { "epoch": 0.02, - "learning_rate": 4.877583160736619e-05, - "loss": 3.2794, + "learning_rate": 4.877385189456452e-05, + "loss": 3.2445, "step": 7400 }, { "epoch": 0.02, - "learning_rate": 4.875928879124951e-05, - "loss": 3.2947, + "learning_rate": 4.875728232557215e-05, + "loss": 3.2538, "step": 7500 }, { "epoch": 0.03, - "learning_rate": 4.874274597513284e-05, - "loss": 3.2777, + "learning_rate": 4.8740712756579775e-05, + "loss": 3.2585, "step": 7600 }, { "epoch": 0.03, - "learning_rate": 4.872620315901617e-05, - "loss": 3.2978, + "learning_rate": 4.872414318758741e-05, + "loss": 3.2591, "step": 7700 }, { "epoch": 0.03, - "learning_rate": 4.870966034289949e-05, - "loss": 3.2885, + "learning_rate": 4.870757361859504e-05, + "loss": 3.2531, "step": 7800 }, { "epoch": 0.03, - "learning_rate": 4.8693117526782824e-05, - "loss": 3.2839, + "learning_rate": 4.869100404960266e-05, + "loss": 3.2597, "step": 7900 }, { "epoch": 0.03, - "learning_rate": 4.867657471066615e-05, - "loss": 3.2922, + "learning_rate": 4.867443448061029e-05, + "loss": 3.2583, "step": 8000 }, { "epoch": 0.03, - "learning_rate": 4.866003189454947e-05, - "loss": 3.2874, + "learning_rate": 4.8657864911617924e-05, + "loss": 3.2595, "step": 8100 }, { "epoch": 0.03, - "learning_rate": 4.8643489078432804e-05, - "loss": 3.2901, + "learning_rate": 4.864129534262555e-05, + "loss": 3.2644, "step": 8200 }, { "epoch": 0.03, - "learning_rate": 4.862694626231613e-05, - "loss": 3.2914, + "learning_rate": 4.8624725773633176e-05, + "loss": 3.2493, "step": 8300 }, { "epoch": 0.03, - "learning_rate": 4.861040344619945e-05, - "loss": 3.291, + "learning_rate": 4.860815620464081e-05, + "loss": 3.2591, "step": 8400 }, { "epoch": 0.03, - "learning_rate": 4.8593860630082784e-05, - "loss": 3.2921, + "learning_rate": 4.8591586635648434e-05, + "loss": 3.2501, "step": 8500 }, { "epoch": 0.03, - "learning_rate": 4.857731781396611e-05, - "loss": 3.3034, + "learning_rate": 4.857501706665607e-05, + "loss": 3.2634, "step": 8600 }, { "epoch": 0.03, - "learning_rate": 4.8560774997849433e-05, - "loss": 3.2853, + "learning_rate": 4.855844749766369e-05, + "loss": 3.2509, "step": 8700 }, { "epoch": 0.03, - "learning_rate": 4.8544232181732765e-05, - "loss": 3.2932, + "learning_rate": 4.854187792867132e-05, + "loss": 3.2621, "step": 8800 }, { "epoch": 0.03, - "learning_rate": 4.852768936561609e-05, - "loss": 3.2956, + "learning_rate": 4.852530835967895e-05, + "loss": 3.2493, "step": 8900 }, { "epoch": 0.03, - "learning_rate": 4.8511146549499414e-05, - "loss": 3.2974, + "learning_rate": 4.8508738790686583e-05, + "loss": 3.2657, "step": 9000 }, { "epoch": 0.03, - "learning_rate": 4.8494603733382745e-05, - "loss": 3.3028, + "learning_rate": 4.84921692216942e-05, + "loss": 3.2605, "step": 9100 }, { "epoch": 0.03, - "learning_rate": 4.847806091726607e-05, - "loss": 3.2898, + "learning_rate": 4.8475599652701835e-05, + "loss": 3.2619, "step": 9200 }, { "epoch": 0.03, - "learning_rate": 4.8461518101149394e-05, - "loss": 3.2808, + "learning_rate": 4.845903008370947e-05, + "loss": 3.2539, "step": 9300 }, { "epoch": 0.03, - "learning_rate": 4.8444975285032725e-05, - "loss": 3.2858, + "learning_rate": 4.8442460514717094e-05, + "loss": 3.2475, "step": 9400 }, { "epoch": 0.03, - "learning_rate": 4.842843246891605e-05, - "loss": 3.2769, + "learning_rate": 4.842589094572472e-05, + "loss": 3.2495, "step": 9500 }, { "epoch": 0.03, - "learning_rate": 4.841188965279938e-05, - "loss": 3.2756, + "learning_rate": 4.840932137673235e-05, + "loss": 3.2457, "step": 9600 }, { "epoch": 0.03, - "learning_rate": 4.8395346836682706e-05, - "loss": 3.2888, + "learning_rate": 4.839275180773998e-05, + "loss": 3.2514, "step": 9700 }, { "epoch": 0.03, - "learning_rate": 4.837880402056603e-05, - "loss": 3.2892, + "learning_rate": 4.837618223874761e-05, + "loss": 3.2583, "step": 9800 }, { "epoch": 0.03, - "learning_rate": 4.836226120444936e-05, - "loss": 3.2951, + "learning_rate": 4.8359612669755236e-05, + "loss": 3.2539, "step": 9900 }, { "epoch": 0.03, - "learning_rate": 4.8345718388332686e-05, - "loss": 3.2864, + "learning_rate": 4.834304310076286e-05, + "loss": 3.2715, "step": 10000 }, { "epoch": 0.03, - "learning_rate": 4.832917557221601e-05, - "loss": 3.3114, + "learning_rate": 4.8326473531770495e-05, + "loss": 3.2632, "step": 10100 }, { "epoch": 0.03, - "learning_rate": 4.831263275609934e-05, - "loss": 3.2875, + "learning_rate": 4.830990396277813e-05, + "loss": 3.2663, "step": 10200 }, { "epoch": 0.03, - "learning_rate": 4.829608993998267e-05, - "loss": 3.2978, + "learning_rate": 4.829333439378575e-05, + "loss": 3.2465, "step": 10300 }, { "epoch": 0.03, - "learning_rate": 4.827954712386599e-05, - "loss": 3.295, + "learning_rate": 4.827676482479338e-05, + "loss": 3.25, "step": 10400 }, { "epoch": 0.03, - "learning_rate": 4.826300430774932e-05, - "loss": 3.301, + "learning_rate": 4.826019525580101e-05, + "loss": 3.2647, "step": 10500 }, { "epoch": 0.04, - "learning_rate": 4.824646149163265e-05, - "loss": 3.2969, + "learning_rate": 4.824362568680864e-05, + "loss": 3.2457, "step": 10600 }, { "epoch": 0.04, - "learning_rate": 4.822991867551597e-05, - "loss": 3.2677, + "learning_rate": 4.822705611781626e-05, + "loss": 3.2529, "step": 10700 }, { "epoch": 0.04, - "learning_rate": 4.82133758593993e-05, - "loss": 3.2916, + "learning_rate": 4.8210486548823896e-05, + "loss": 3.254, "step": 10800 }, { "epoch": 0.04, - "learning_rate": 4.819683304328263e-05, - "loss": 3.2874, + "learning_rate": 4.819391697983152e-05, + "loss": 3.2404, "step": 10900 }, { "epoch": 0.04, - "learning_rate": 4.818029022716595e-05, - "loss": 3.2896, + "learning_rate": 4.8177347410839154e-05, + "loss": 3.2372, "step": 11000 }, { "epoch": 0.04, - "learning_rate": 4.816374741104928e-05, - "loss": 3.2944, + "learning_rate": 4.816077784184678e-05, + "loss": 3.2519, "step": 11100 }, { "epoch": 0.04, - "learning_rate": 4.814720459493261e-05, - "loss": 3.2915, + "learning_rate": 4.8144208272854406e-05, + "loss": 3.2537, "step": 11200 }, { "epoch": 0.04, - "learning_rate": 4.813066177881593e-05, - "loss": 3.3023, + "learning_rate": 4.812763870386204e-05, + "loss": 3.25, "step": 11300 }, { "epoch": 0.04, - "learning_rate": 4.8114118962699264e-05, - "loss": 3.2946, + "learning_rate": 4.811106913486967e-05, + "loss": 3.239, "step": 11400 }, { "epoch": 0.04, - "learning_rate": 4.809757614658258e-05, - "loss": 3.2983, + "learning_rate": 4.80944995658773e-05, + "loss": 3.2504, "step": 11500 }, { "epoch": 0.04, - "learning_rate": 4.808103333046591e-05, - "loss": 3.3081, + "learning_rate": 4.807792999688492e-05, + "loss": 3.2594, "step": 11600 }, { "epoch": 0.04, - "learning_rate": 4.8064490514349244e-05, - "loss": 3.2932, + "learning_rate": 4.8061360427892555e-05, + "loss": 3.2507, "step": 11700 }, { "epoch": 0.04, - "learning_rate": 4.804794769823257e-05, - "loss": 3.2931, + "learning_rate": 4.804479085890018e-05, + "loss": 3.257, "step": 11800 }, { "epoch": 0.04, - "learning_rate": 4.803140488211589e-05, - "loss": 3.3013, + "learning_rate": 4.802822128990781e-05, + "loss": 3.2566, "step": 11900 }, { "epoch": 0.04, - "learning_rate": 4.8014862065999224e-05, - "loss": 3.2959, + "learning_rate": 4.801165172091544e-05, + "loss": 3.26, "step": 12000 }, { "epoch": 0.04, - "learning_rate": 4.799831924988255e-05, - "loss": 3.2952, + "learning_rate": 4.7995082151923065e-05, + "loss": 3.2626, "step": 12100 }, { "epoch": 0.04, - "learning_rate": 4.7981776433765873e-05, - "loss": 3.2949, + "learning_rate": 4.79785125829307e-05, + "loss": 3.2528, "step": 12200 }, { "epoch": 0.04, - "learning_rate": 4.7965233617649205e-05, - "loss": 3.2953, + "learning_rate": 4.7961943013938324e-05, + "loss": 3.2448, "step": 12300 }, { "epoch": 0.04, - "learning_rate": 4.794869080153253e-05, - "loss": 3.289, + "learning_rate": 4.794537344494595e-05, + "loss": 3.2484, "step": 12400 }, { "epoch": 0.04, - "learning_rate": 4.7932147985415854e-05, - "loss": 3.2867, + "learning_rate": 4.792880387595358e-05, + "loss": 3.2451, "step": 12500 }, { "epoch": 0.04, - "learning_rate": 4.7915605169299185e-05, - "loss": 3.2901, + "learning_rate": 4.7912234306961215e-05, + "loss": 3.253, "step": 12600 }, { "epoch": 0.04, - "learning_rate": 4.789906235318251e-05, - "loss": 3.2829, + "learning_rate": 4.789566473796884e-05, + "loss": 3.2487, "step": 12700 }, { "epoch": 0.04, - "learning_rate": 4.7882519537065834e-05, - "loss": 3.2903, + "learning_rate": 4.7879095168976466e-05, + "loss": 3.2619, "step": 12800 }, { "epoch": 0.04, - "learning_rate": 4.7865976720949166e-05, - "loss": 3.2918, + "learning_rate": 4.78625255999841e-05, + "loss": 3.2509, "step": 12900 }, { "epoch": 0.04, - "learning_rate": 4.784943390483249e-05, - "loss": 3.284, + "learning_rate": 4.7845956030991725e-05, + "loss": 3.2522, "step": 13000 }, { "epoch": 0.04, - "learning_rate": 4.7832891088715815e-05, - "loss": 3.2858, + "learning_rate": 4.782938646199935e-05, + "loss": 3.2639, "step": 13100 }, { "epoch": 0.04, - "learning_rate": 4.7816348272599146e-05, - "loss": 3.2846, + "learning_rate": 4.7812816893006976e-05, + "loss": 3.2601, "step": 13200 }, { "epoch": 0.04, - "learning_rate": 4.779980545648247e-05, - "loss": 3.2948, + "learning_rate": 4.779624732401461e-05, + "loss": 3.2602, "step": 13300 }, { "epoch": 0.04, - "learning_rate": 4.7783262640365795e-05, - "loss": 3.2962, + "learning_rate": 4.777967775502224e-05, + "loss": 3.2606, "step": 13400 }, { "epoch": 0.04, - "learning_rate": 4.7766719824249126e-05, - "loss": 3.3008, + "learning_rate": 4.776310818602987e-05, + "loss": 3.2578, "step": 13500 }, { - "epoch": 0.04, - "learning_rate": 4.775017700813245e-05, - "loss": 3.2893, + "epoch": 0.05, + "learning_rate": 4.774653861703749e-05, + "loss": 3.2527, "step": 13600 }, { "epoch": 0.05, - "learning_rate": 4.7733634192015775e-05, - "loss": 3.2871, + "learning_rate": 4.7729969048045126e-05, + "loss": 3.2571, "step": 13700 }, { "epoch": 0.05, - "learning_rate": 4.771709137589911e-05, - "loss": 3.2983, + "learning_rate": 4.771339947905275e-05, + "loss": 3.2775, "step": 13800 }, { "epoch": 0.05, - "learning_rate": 4.770054855978243e-05, - "loss": 3.2774, + "learning_rate": 4.7696829910060384e-05, + "loss": 3.2545, "step": 13900 }, { "epoch": 0.05, - "learning_rate": 4.768400574366576e-05, - "loss": 3.2899, + "learning_rate": 4.768026034106801e-05, + "loss": 3.2583, "step": 14000 }, { "epoch": 0.05, - "learning_rate": 4.766746292754908e-05, - "loss": 3.2957, + "learning_rate": 4.7663690772075636e-05, + "loss": 3.2569, "step": 14100 }, { "epoch": 0.05, - "learning_rate": 4.765092011143241e-05, - "loss": 3.2904, + "learning_rate": 4.764712120308327e-05, + "loss": 3.2477, "step": 14200 }, { "epoch": 0.05, - "learning_rate": 4.763437729531574e-05, - "loss": 3.286, + "learning_rate": 4.76305516340909e-05, + "loss": 3.2549, "step": 14300 }, { "epoch": 0.05, - "learning_rate": 4.761783447919906e-05, - "loss": 3.284, + "learning_rate": 4.761398206509852e-05, + "loss": 3.2582, "step": 14400 }, { "epoch": 0.05, - "learning_rate": 4.760129166308239e-05, - "loss": 3.2834, + "learning_rate": 4.759741249610615e-05, + "loss": 3.2706, "step": 14500 }, { "epoch": 0.05, - "learning_rate": 4.758474884696572e-05, - "loss": 3.2954, + "learning_rate": 4.7580842927113785e-05, + "loss": 3.2634, "step": 14600 }, { "epoch": 0.05, - "learning_rate": 4.756820603084904e-05, - "loss": 3.286, + "learning_rate": 4.756427335812141e-05, + "loss": 3.2478, "step": 14700 }, { "epoch": 0.05, - "learning_rate": 4.755166321473237e-05, - "loss": 3.2783, + "learning_rate": 4.754770378912904e-05, + "loss": 3.2444, "step": 14800 }, { "epoch": 0.05, - "learning_rate": 4.7535120398615704e-05, - "loss": 3.2939, + "learning_rate": 4.753113422013667e-05, + "loss": 3.2506, "step": 14900 }, { "epoch": 0.05, - "learning_rate": 4.751857758249902e-05, - "loss": 3.301, + "learning_rate": 4.7514564651144295e-05, + "loss": 3.2451, "step": 15000 }, { "epoch": 0.05, - "learning_rate": 4.750203476638235e-05, - "loss": 3.3021, + "learning_rate": 4.749799508215193e-05, + "loss": 3.2607, "step": 15100 }, { "epoch": 0.05, - "learning_rate": 4.7485491950265684e-05, - "loss": 3.2916, + "learning_rate": 4.7481425513159554e-05, + "loss": 3.2518, "step": 15200 }, { "epoch": 0.05, - "learning_rate": 4.7468949134149e-05, - "loss": 3.2896, + "learning_rate": 4.746485594416718e-05, + "loss": 3.2624, "step": 15300 }, { "epoch": 0.05, - "learning_rate": 4.745240631803233e-05, - "loss": 3.295, + "learning_rate": 4.744828637517481e-05, + "loss": 3.2715, "step": 15400 }, { "epoch": 0.05, - "learning_rate": 4.7435863501915664e-05, - "loss": 3.2956, + "learning_rate": 4.7431716806182445e-05, + "loss": 3.2487, "step": 15500 }, { "epoch": 0.05, - "learning_rate": 4.741932068579898e-05, - "loss": 3.292, + "learning_rate": 4.7415147237190064e-05, + "loss": 3.2365, "step": 15600 }, { "epoch": 0.05, - "learning_rate": 4.7402777869682313e-05, - "loss": 3.289, + "learning_rate": 4.7398577668197696e-05, + "loss": 3.2514, "step": 15700 }, { "epoch": 0.05, - "learning_rate": 4.7386235053565645e-05, - "loss": 3.284, + "learning_rate": 4.738200809920533e-05, + "loss": 3.2454, "step": 15800 }, { "epoch": 0.05, - "learning_rate": 4.736969223744897e-05, - "loss": 3.291, + "learning_rate": 4.7365438530212955e-05, + "loss": 3.2505, "step": 15900 }, { "epoch": 0.05, - "learning_rate": 4.7353149421332294e-05, - "loss": 3.2793, + "learning_rate": 4.734886896122058e-05, + "loss": 3.2462, "step": 16000 }, { "epoch": 0.05, - "learning_rate": 4.7336606605215625e-05, - "loss": 3.2924, + "learning_rate": 4.733229939222821e-05, + "loss": 3.2516, "step": 16100 }, { "epoch": 0.05, - "learning_rate": 4.732006378909895e-05, - "loss": 3.2953, + "learning_rate": 4.731572982323584e-05, + "loss": 3.26, "step": 16200 }, { "epoch": 0.05, - "learning_rate": 4.7303520972982274e-05, - "loss": 3.2964, + "learning_rate": 4.729916025424347e-05, + "loss": 3.2518, "step": 16300 }, { "epoch": 0.05, - "learning_rate": 4.7286978156865606e-05, - "loss": 3.2916, + "learning_rate": 4.72825906852511e-05, + "loss": 3.261, "step": 16400 }, { "epoch": 0.05, - "learning_rate": 4.727043534074893e-05, - "loss": 3.2854, + "learning_rate": 4.726602111625872e-05, + "loss": 3.2619, "step": 16500 }, { - "epoch": 0.05, - "learning_rate": 4.7253892524632255e-05, - "loss": 3.2949, + "epoch": 0.06, + "learning_rate": 4.7249451547266356e-05, + "loss": 3.2566, "step": 16600 }, { "epoch": 0.06, - "learning_rate": 4.723734970851558e-05, - "loss": 3.289, + "learning_rate": 4.723288197827399e-05, + "loss": 3.259, "step": 16700 }, { "epoch": 0.06, - "learning_rate": 4.722080689239891e-05, - "loss": 3.2721, + "learning_rate": 4.721631240928161e-05, + "loss": 3.2601, "step": 16800 }, { "epoch": 0.06, - "learning_rate": 4.7204264076282235e-05, - "loss": 3.2848, + "learning_rate": 4.719974284028924e-05, + "loss": 3.2565, "step": 16900 }, { "epoch": 0.06, - "learning_rate": 4.718772126016556e-05, - "loss": 3.2939, + "learning_rate": 4.718317327129687e-05, + "loss": 3.2467, "step": 17000 }, { "epoch": 0.06, - "learning_rate": 4.717117844404889e-05, - "loss": 3.289, + "learning_rate": 4.71666037023045e-05, + "loss": 3.251, "step": 17100 }, { "epoch": 0.06, - "learning_rate": 4.7154635627932215e-05, - "loss": 3.2877, + "learning_rate": 4.7150034133312124e-05, + "loss": 3.242, "step": 17200 }, { "epoch": 0.06, - "learning_rate": 4.713809281181554e-05, - "loss": 3.2747, + "learning_rate": 4.713346456431976e-05, + "loss": 3.2473, "step": 17300 }, { "epoch": 0.06, - "learning_rate": 4.712154999569887e-05, - "loss": 3.2915, + "learning_rate": 4.711689499532738e-05, + "loss": 3.2614, "step": 17400 }, { "epoch": 0.06, - "learning_rate": 4.7105007179582196e-05, - "loss": 3.2763, + "learning_rate": 4.7100325426335015e-05, + "loss": 3.2593, "step": 17500 }, { "epoch": 0.06, - "learning_rate": 4.708846436346552e-05, - "loss": 3.2881, + "learning_rate": 4.708375585734264e-05, + "loss": 3.2489, "step": 17600 }, { "epoch": 0.06, - "learning_rate": 4.707192154734885e-05, - "loss": 3.2975, + "learning_rate": 4.706718628835027e-05, + "loss": 3.2577, "step": 17700 }, { "epoch": 0.06, - "learning_rate": 4.7055378731232176e-05, - "loss": 3.294, + "learning_rate": 4.70506167193579e-05, + "loss": 3.2534, "step": 17800 }, { "epoch": 0.06, - "learning_rate": 4.70388359151155e-05, - "loss": 3.2951, + "learning_rate": 4.703404715036553e-05, + "loss": 3.2467, "step": 17900 }, { "epoch": 0.06, - "learning_rate": 4.702229309899883e-05, - "loss": 3.2806, + "learning_rate": 4.701747758137315e-05, + "loss": 3.2492, "step": 18000 }, { "epoch": 0.06, - "learning_rate": 4.700575028288216e-05, - "loss": 3.2991, + "learning_rate": 4.7000908012380784e-05, + "loss": 3.2596, "step": 18100 }, { "epoch": 0.06, - "learning_rate": 4.698920746676548e-05, - "loss": 3.2838, + "learning_rate": 4.6984338443388416e-05, + "loss": 3.2561, "step": 18200 }, { "epoch": 0.06, - "learning_rate": 4.697266465064881e-05, - "loss": 3.2859, + "learning_rate": 4.696776887439604e-05, + "loss": 3.2577, "step": 18300 }, { "epoch": 0.06, - "learning_rate": 4.6956121834532144e-05, - "loss": 3.2875, + "learning_rate": 4.695119930540367e-05, + "loss": 3.2424, "step": 18400 }, { "epoch": 0.06, - "learning_rate": 4.693957901841546e-05, - "loss": 3.2801, + "learning_rate": 4.69346297364113e-05, + "loss": 3.2483, "step": 18500 }, { "epoch": 0.06, - "learning_rate": 4.692303620229879e-05, - "loss": 3.2839, + "learning_rate": 4.6918060167418926e-05, + "loss": 3.2533, "step": 18600 }, { "epoch": 0.06, - "learning_rate": 4.6906493386182124e-05, - "loss": 3.2893, + "learning_rate": 4.690149059842656e-05, + "loss": 3.2567, "step": 18700 }, { "epoch": 0.06, - "learning_rate": 4.688995057006544e-05, - "loss": 3.2755, + "learning_rate": 4.6884921029434185e-05, + "loss": 3.2664, "step": 18800 }, { "epoch": 0.06, - "learning_rate": 4.687340775394877e-05, - "loss": 3.2954, + "learning_rate": 4.686835146044181e-05, + "loss": 3.2535, "step": 18900 }, { "epoch": 0.06, - "learning_rate": 4.6856864937832104e-05, - "loss": 3.2875, + "learning_rate": 4.685178189144944e-05, + "loss": 3.259, "step": 19000 }, { "epoch": 0.06, - "learning_rate": 4.684032212171542e-05, - "loss": 3.2911, + "learning_rate": 4.6835212322457076e-05, + "loss": 3.2582, "step": 19100 }, { "epoch": 0.06, - "learning_rate": 4.6823779305598753e-05, - "loss": 3.287, + "learning_rate": 4.6818642753464695e-05, + "loss": 3.2647, "step": 19200 }, { "epoch": 0.06, - "learning_rate": 4.680723648948208e-05, - "loss": 3.2809, + "learning_rate": 4.680207318447233e-05, + "loss": 3.2572, "step": 19300 }, { "epoch": 0.06, - "learning_rate": 4.67906936733654e-05, - "loss": 3.2948, + "learning_rate": 4.678550361547996e-05, + "loss": 3.2559, "step": 19400 }, { "epoch": 0.06, - "learning_rate": 4.6774150857248734e-05, - "loss": 3.2868, + "learning_rate": 4.6768934046487586e-05, + "loss": 3.2551, "step": 19500 }, { "epoch": 0.06, - "learning_rate": 4.675760804113206e-05, - "loss": 3.2931, + "learning_rate": 4.675236447749521e-05, + "loss": 3.2399, "step": 19600 }, { "epoch": 0.07, - "learning_rate": 4.674106522501538e-05, - "loss": 3.2881, + "learning_rate": 4.6735794908502844e-05, + "loss": 3.2602, "step": 19700 }, { "epoch": 0.07, - "learning_rate": 4.6724522408898714e-05, - "loss": 3.2942, + "learning_rate": 4.671922533951047e-05, + "loss": 3.2517, "step": 19800 }, { "epoch": 0.07, - "learning_rate": 4.670797959278204e-05, - "loss": 3.2834, + "learning_rate": 4.67026557705181e-05, + "loss": 3.2398, "step": 19900 }, { "epoch": 0.07, - "learning_rate": 4.669143677666536e-05, - "loss": 3.2865, + "learning_rate": 4.668608620152573e-05, + "loss": 3.2424, "step": 20000 }, { "epoch": 0.07, - "learning_rate": 4.6674893960548695e-05, - "loss": 3.2815, + "learning_rate": 4.6669516632533354e-05, + "loss": 3.2541, "step": 20100 }, { "epoch": 0.07, - "learning_rate": 4.665835114443202e-05, - "loss": 3.3033, + "learning_rate": 4.665294706354099e-05, + "loss": 3.258, "step": 20200 }, { "epoch": 0.07, - "learning_rate": 4.664180832831535e-05, - "loss": 3.2943, + "learning_rate": 4.663637749454862e-05, + "loss": 3.2599, "step": 20300 }, { "epoch": 0.07, - "learning_rate": 4.6625265512198675e-05, - "loss": 3.2785, + "learning_rate": 4.661980792555624e-05, + "loss": 3.2378, "step": 20400 }, { "epoch": 0.07, - "learning_rate": 4.6608722696082e-05, - "loss": 3.2879, + "learning_rate": 4.660323835656387e-05, + "loss": 3.2651, "step": 20500 }, { "epoch": 0.07, - "learning_rate": 4.659217987996533e-05, - "loss": 3.2918, + "learning_rate": 4.6586668787571504e-05, + "loss": 3.2447, "step": 20600 }, { "epoch": 0.07, - "learning_rate": 4.6575637063848655e-05, - "loss": 3.2842, + "learning_rate": 4.657009921857913e-05, + "loss": 3.2513, "step": 20700 }, { "epoch": 0.07, - "learning_rate": 4.655909424773198e-05, - "loss": 3.2816, + "learning_rate": 4.6553529649586755e-05, + "loss": 3.2463, "step": 20800 }, { "epoch": 0.07, - "learning_rate": 4.654255143161531e-05, - "loss": 3.2917, + "learning_rate": 4.653696008059439e-05, + "loss": 3.2531, "step": 20900 }, { "epoch": 0.07, - "learning_rate": 4.6526008615498636e-05, - "loss": 3.2821, + "learning_rate": 4.6520390511602014e-05, + "loss": 3.2492, "step": 21000 }, { "epoch": 0.07, - "learning_rate": 4.650946579938196e-05, - "loss": 3.2816, + "learning_rate": 4.6503820942609646e-05, + "loss": 3.2602, "step": 21100 }, { "epoch": 0.07, - "learning_rate": 4.649292298326529e-05, - "loss": 3.276, + "learning_rate": 4.648725137361727e-05, + "loss": 3.2471, "step": 21200 }, { "epoch": 0.07, - "learning_rate": 4.6476380167148616e-05, - "loss": 3.2749, + "learning_rate": 4.64706818046249e-05, + "loss": 3.2583, "step": 21300 }, { "epoch": 0.07, - "learning_rate": 4.645983735103194e-05, - "loss": 3.3036, + "learning_rate": 4.645411223563253e-05, + "loss": 3.2626, "step": 21400 }, { "epoch": 0.07, - "learning_rate": 4.644329453491527e-05, - "loss": 3.2723, + "learning_rate": 4.643754266664016e-05, + "loss": 3.249, "step": 21500 }, { "epoch": 0.07, - "learning_rate": 4.6426751718798597e-05, - "loss": 3.2959, + "learning_rate": 4.642097309764778e-05, + "loss": 3.2449, "step": 21600 }, { "epoch": 0.07, - "learning_rate": 4.641020890268192e-05, - "loss": 3.2839, + "learning_rate": 4.6404403528655415e-05, + "loss": 3.2385, "step": 21700 }, { "epoch": 0.07, - "learning_rate": 4.639366608656525e-05, - "loss": 3.2925, + "learning_rate": 4.638783395966305e-05, + "loss": 3.2672, "step": 21800 }, { "epoch": 0.07, - "learning_rate": 4.637712327044858e-05, - "loss": 3.3013, + "learning_rate": 4.637126439067067e-05, + "loss": 3.2481, "step": 21900 }, { "epoch": 0.07, - "learning_rate": 4.63605804543319e-05, - "loss": 3.2799, + "learning_rate": 4.63546948216783e-05, + "loss": 3.2492, "step": 22000 }, { "epoch": 0.07, - "learning_rate": 4.634403763821523e-05, - "loss": 3.288, + "learning_rate": 4.6338125252685925e-05, + "loss": 3.2499, "step": 22100 }, { "epoch": 0.07, - "learning_rate": 4.632749482209856e-05, - "loss": 3.3072, + "learning_rate": 4.632155568369356e-05, + "loss": 3.2543, "step": 22200 }, { "epoch": 0.07, - "learning_rate": 4.631095200598188e-05, - "loss": 3.2815, + "learning_rate": 4.630498611470119e-05, + "loss": 3.2711, "step": 22300 }, { "epoch": 0.07, - "learning_rate": 4.629440918986521e-05, - "loss": 3.2871, + "learning_rate": 4.6288416545708816e-05, + "loss": 3.2661, "step": 22400 }, { "epoch": 0.07, - "learning_rate": 4.627786637374854e-05, - "loss": 3.2812, + "learning_rate": 4.627184697671644e-05, + "loss": 3.249, "step": 22500 }, { "epoch": 0.07, - "learning_rate": 4.626132355763186e-05, - "loss": 3.2976, + "learning_rate": 4.6255277407724074e-05, + "loss": 3.2482, "step": 22600 }, { "epoch": 0.08, - "learning_rate": 4.6244780741515194e-05, - "loss": 3.2819, + "learning_rate": 4.62387078387317e-05, + "loss": 3.2607, "step": 22700 }, { "epoch": 0.08, - "learning_rate": 4.622823792539852e-05, - "loss": 3.2883, + "learning_rate": 4.6222138269739326e-05, + "loss": 3.2485, "step": 22800 }, { "epoch": 0.08, - "learning_rate": 4.621169510928184e-05, - "loss": 3.2844, + "learning_rate": 4.620556870074696e-05, + "loss": 3.2489, "step": 22900 }, { "epoch": 0.08, - "learning_rate": 4.6195152293165174e-05, - "loss": 3.2909, + "learning_rate": 4.6188999131754584e-05, + "loss": 3.2498, "step": 23000 }, { "epoch": 0.08, - "learning_rate": 4.61786094770485e-05, - "loss": 3.2894, + "learning_rate": 4.617242956276222e-05, + "loss": 3.2472, "step": 23100 }, { "epoch": 0.08, - "learning_rate": 4.616206666093182e-05, - "loss": 3.2877, + "learning_rate": 4.615585999376984e-05, + "loss": 3.2528, "step": 23200 }, { "epoch": 0.08, - "learning_rate": 4.6145523844815154e-05, - "loss": 3.2877, + "learning_rate": 4.613929042477747e-05, + "loss": 3.2614, "step": 23300 }, { "epoch": 0.08, - "learning_rate": 4.612898102869848e-05, - "loss": 3.2899, + "learning_rate": 4.61227208557851e-05, + "loss": 3.2598, "step": 23400 }, { "epoch": 0.08, - "learning_rate": 4.61124382125818e-05, - "loss": 3.2926, + "learning_rate": 4.6106151286792734e-05, + "loss": 3.2525, "step": 23500 }, { "epoch": 0.08, - "learning_rate": 4.6095895396465135e-05, - "loss": 3.2819, + "learning_rate": 4.608958171780036e-05, + "loss": 3.2625, "step": 23600 }, { "epoch": 0.08, - "learning_rate": 4.607935258034846e-05, - "loss": 3.2827, + "learning_rate": 4.6073012148807985e-05, + "loss": 3.2494, "step": 23700 }, { "epoch": 0.08, - "learning_rate": 4.6062809764231784e-05, - "loss": 3.2924, + "learning_rate": 4.605644257981562e-05, + "loss": 3.2526, "step": 23800 }, { "epoch": 0.08, - "learning_rate": 4.6046266948115115e-05, - "loss": 3.287, + "learning_rate": 4.6039873010823244e-05, + "loss": 3.2595, "step": 23900 }, { "epoch": 0.08, - "learning_rate": 4.602972413199844e-05, - "loss": 3.2746, + "learning_rate": 4.6023303441830876e-05, + "loss": 3.2476, "step": 24000 }, { "epoch": 0.08, - "learning_rate": 4.6013181315881764e-05, - "loss": 3.2971, + "learning_rate": 4.60067338728385e-05, + "loss": 3.2495, "step": 24100 }, { "epoch": 0.08, - "learning_rate": 4.5996638499765095e-05, - "loss": 3.2789, + "learning_rate": 4.599016430384613e-05, + "loss": 3.2433, "step": 24200 }, { "epoch": 0.08, - "learning_rate": 4.598009568364842e-05, - "loss": 3.2857, + "learning_rate": 4.597359473485376e-05, + "loss": 3.2597, "step": 24300 }, { "epoch": 0.08, - "learning_rate": 4.596355286753175e-05, - "loss": 3.2808, + "learning_rate": 4.5957025165861386e-05, + "loss": 3.2615, "step": 24400 }, { "epoch": 0.08, - "learning_rate": 4.5947010051415076e-05, - "loss": 3.2932, + "learning_rate": 4.594045559686901e-05, + "loss": 3.2369, "step": 24500 }, { "epoch": 0.08, - "learning_rate": 4.59304672352984e-05, - "loss": 3.2946, + "learning_rate": 4.5923886027876645e-05, + "loss": 3.2553, "step": 24600 }, { "epoch": 0.08, - "learning_rate": 4.591392441918173e-05, - "loss": 3.2957, + "learning_rate": 4.590731645888428e-05, + "loss": 3.2511, "step": 24700 }, { "epoch": 0.08, - "learning_rate": 4.5897381603065056e-05, - "loss": 3.2578, + "learning_rate": 4.58907468898919e-05, + "loss": 3.2486, "step": 24800 }, { "epoch": 0.08, - "learning_rate": 4.588083878694838e-05, - "loss": 3.3015, + "learning_rate": 4.587417732089953e-05, + "loss": 3.2571, "step": 24900 }, { "epoch": 0.08, - "learning_rate": 4.586429597083171e-05, - "loss": 3.292, + "learning_rate": 4.585760775190716e-05, + "loss": 3.252, "step": 25000 }, { "epoch": 0.08, - "learning_rate": 4.5847753154715037e-05, - "loss": 3.2771, + "learning_rate": 4.584103818291479e-05, + "loss": 3.2458, "step": 25100 }, { "epoch": 0.08, - "learning_rate": 4.583121033859836e-05, - "loss": 3.2868, + "learning_rate": 4.582446861392242e-05, + "loss": 3.2539, "step": 25200 }, { "epoch": 0.08, - "learning_rate": 4.581466752248169e-05, - "loss": 3.2923, + "learning_rate": 4.5807899044930046e-05, + "loss": 3.2525, "step": 25300 }, { "epoch": 0.08, - "learning_rate": 4.579812470636502e-05, - "loss": 3.2885, + "learning_rate": 4.579132947593767e-05, + "loss": 3.2467, "step": 25400 }, { "epoch": 0.08, - "learning_rate": 4.578158189024834e-05, - "loss": 3.2929, + "learning_rate": 4.5774759906945304e-05, + "loss": 3.245, "step": 25500 }, { "epoch": 0.08, - "learning_rate": 4.576503907413167e-05, - "loss": 3.2829, + "learning_rate": 4.575819033795293e-05, + "loss": 3.255, "step": 25600 }, { "epoch": 0.09, - "learning_rate": 4.5748496258015e-05, - "loss": 3.2922, + "learning_rate": 4.5741620768960556e-05, + "loss": 3.2572, "step": 25700 }, { "epoch": 0.09, - "learning_rate": 4.573195344189832e-05, - "loss": 3.2905, + "learning_rate": 4.572505119996819e-05, + "loss": 3.2437, "step": 25800 }, { "epoch": 0.09, - "learning_rate": 4.571541062578165e-05, - "loss": 3.2845, + "learning_rate": 4.570848163097582e-05, + "loss": 3.2539, "step": 25900 }, { "epoch": 0.09, - "learning_rate": 4.569886780966498e-05, - "loss": 3.297, + "learning_rate": 4.569191206198345e-05, + "loss": 3.2452, "step": 26000 }, { "epoch": 0.09, - "learning_rate": 4.56823249935483e-05, - "loss": 3.281, + "learning_rate": 4.567534249299107e-05, + "loss": 3.2499, "step": 26100 }, { "epoch": 0.09, - "learning_rate": 4.5665782177431634e-05, - "loss": 3.2909, + "learning_rate": 4.5658772923998705e-05, + "loss": 3.2532, "step": 26200 }, { "epoch": 0.09, - "learning_rate": 4.564923936131496e-05, - "loss": 3.2849, + "learning_rate": 4.564220335500633e-05, + "loss": 3.2627, "step": 26300 }, { "epoch": 0.09, - "learning_rate": 4.563269654519828e-05, - "loss": 3.2719, + "learning_rate": 4.5625633786013964e-05, + "loss": 3.254, "step": 26400 }, { "epoch": 0.09, - "learning_rate": 4.5616153729081614e-05, - "loss": 3.2892, + "learning_rate": 4.560906421702159e-05, + "loss": 3.242, "step": 26500 }, { "epoch": 0.09, - "learning_rate": 4.559961091296494e-05, - "loss": 3.2945, + "learning_rate": 4.5592494648029215e-05, + "loss": 3.2456, "step": 26600 }, { "epoch": 0.09, - "learning_rate": 4.558306809684826e-05, - "loss": 3.275, + "learning_rate": 4.557592507903685e-05, + "loss": 3.2566, "step": 26700 }, { "epoch": 0.09, - "learning_rate": 4.5566525280731594e-05, - "loss": 3.2765, + "learning_rate": 4.5559355510044474e-05, + "loss": 3.2619, "step": 26800 }, { "epoch": 0.09, - "learning_rate": 4.554998246461492e-05, - "loss": 3.2737, + "learning_rate": 4.55427859410521e-05, + "loss": 3.2473, "step": 26900 }, { "epoch": 0.09, - "learning_rate": 4.553343964849824e-05, - "loss": 3.2916, + "learning_rate": 4.552621637205973e-05, + "loss": 3.2556, "step": 27000 }, { "epoch": 0.09, - "learning_rate": 4.5516896832381575e-05, - "loss": 3.2736, + "learning_rate": 4.5509646803067365e-05, + "loss": 3.2482, "step": 27100 }, { "epoch": 0.09, - "learning_rate": 4.55003540162649e-05, - "loss": 3.2818, + "learning_rate": 4.549307723407499e-05, + "loss": 3.242, "step": 27200 }, { "epoch": 0.09, - "learning_rate": 4.5483811200148224e-05, - "loss": 3.2877, + "learning_rate": 4.5476507665082616e-05, + "loss": 3.2364, "step": 27300 }, { "epoch": 0.09, - "learning_rate": 4.5467268384031555e-05, - "loss": 3.2904, + "learning_rate": 4.545993809609025e-05, + "loss": 3.2554, "step": 27400 }, { "epoch": 0.09, - "learning_rate": 4.545072556791488e-05, - "loss": 3.2939, + "learning_rate": 4.5443368527097875e-05, + "loss": 3.2623, "step": 27500 }, { "epoch": 0.09, - "learning_rate": 4.5434182751798204e-05, - "loss": 3.2877, + "learning_rate": 4.542679895810551e-05, + "loss": 3.2509, "step": 27600 }, { "epoch": 0.09, - "learning_rate": 4.5417639935681535e-05, - "loss": 3.2849, + "learning_rate": 4.541022938911313e-05, + "loss": 3.2505, "step": 27700 }, { "epoch": 0.09, - "learning_rate": 4.540109711956486e-05, - "loss": 3.2945, + "learning_rate": 4.539365982012076e-05, + "loss": 3.2444, "step": 27800 }, { "epoch": 0.09, - "learning_rate": 4.5384554303448185e-05, - "loss": 3.2906, + "learning_rate": 4.537709025112839e-05, + "loss": 3.2507, "step": 27900 }, { "epoch": 0.09, - "learning_rate": 4.5368011487331516e-05, - "loss": 3.2866, + "learning_rate": 4.536052068213602e-05, + "loss": 3.2601, "step": 28000 }, { "epoch": 0.09, - "learning_rate": 4.535146867121484e-05, - "loss": 3.2704, + "learning_rate": 4.534395111314364e-05, + "loss": 3.2567, "step": 28100 }, { "epoch": 0.09, - "learning_rate": 4.5334925855098165e-05, - "loss": 3.3005, + "learning_rate": 4.5327381544151276e-05, + "loss": 3.2566, "step": 28200 }, { "epoch": 0.09, - "learning_rate": 4.5318383038981496e-05, - "loss": 3.272, + "learning_rate": 4.531081197515891e-05, + "loss": 3.24, "step": 28300 }, { "epoch": 0.09, - "learning_rate": 4.530184022286482e-05, - "loss": 3.2867, + "learning_rate": 4.5294242406166534e-05, + "loss": 3.2489, "step": 28400 }, { "epoch": 0.09, - "learning_rate": 4.5285297406748145e-05, - "loss": 3.3054, + "learning_rate": 4.527767283717416e-05, + "loss": 3.2449, "step": 28500 }, { "epoch": 0.09, - "learning_rate": 4.5268754590631477e-05, - "loss": 3.2861, + "learning_rate": 4.526110326818179e-05, + "loss": 3.2486, "step": 28600 }, { - "epoch": 0.09, - "learning_rate": 4.52522117745148e-05, - "loss": 3.2856, + "epoch": 0.1, + "learning_rate": 4.524453369918942e-05, + "loss": 3.25, "step": 28700 }, { "epoch": 0.1, - "learning_rate": 4.523566895839813e-05, - "loss": 3.2965, + "learning_rate": 4.522796413019705e-05, + "loss": 3.2477, "step": 28800 }, { "epoch": 0.1, - "learning_rate": 4.521912614228146e-05, - "loss": 3.2931, + "learning_rate": 4.521139456120468e-05, + "loss": 3.2538, "step": 28900 }, { "epoch": 0.1, - "learning_rate": 4.520258332616478e-05, - "loss": 3.2858, + "learning_rate": 4.51948249922123e-05, + "loss": 3.2463, "step": 29000 }, { "epoch": 0.1, - "learning_rate": 4.518604051004811e-05, - "loss": 3.2665, + "learning_rate": 4.5178255423219935e-05, + "loss": 3.2486, "step": 29100 }, { "epoch": 0.1, - "learning_rate": 4.516949769393144e-05, - "loss": 3.2821, + "learning_rate": 4.516168585422757e-05, + "loss": 3.2608, "step": 29200 }, { "epoch": 0.1, - "learning_rate": 4.515295487781476e-05, - "loss": 3.2909, + "learning_rate": 4.514511628523519e-05, + "loss": 3.2619, "step": 29300 }, { "epoch": 0.1, - "learning_rate": 4.513641206169809e-05, - "loss": 3.271, + "learning_rate": 4.512854671624282e-05, + "loss": 3.2548, "step": 29400 }, { "epoch": 0.1, - "learning_rate": 4.511986924558141e-05, - "loss": 3.2822, + "learning_rate": 4.511197714725045e-05, + "loss": 3.2464, "step": 29500 }, { "epoch": 0.1, - "learning_rate": 4.510332642946474e-05, - "loss": 3.2736, + "learning_rate": 4.509540757825808e-05, + "loss": 3.2335, "step": 29600 }, { "epoch": 0.1, - "learning_rate": 4.5086783613348074e-05, - "loss": 3.2868, + "learning_rate": 4.5078838009265704e-05, + "loss": 3.2545, "step": 29700 }, { "epoch": 0.1, - "learning_rate": 4.507024079723139e-05, - "loss": 3.2943, + "learning_rate": 4.5062268440273336e-05, + "loss": 3.2472, "step": 29800 }, { "epoch": 0.1, - "learning_rate": 4.505369798111472e-05, - "loss": 3.3031, + "learning_rate": 4.504569887128096e-05, + "loss": 3.2478, "step": 29900 }, { "epoch": 0.1, - "learning_rate": 4.5037155164998054e-05, - "loss": 3.2958, + "learning_rate": 4.5029129302288595e-05, + "loss": 3.2357, "step": 30000 }, { "epoch": 0.1, - "learning_rate": 4.502061234888137e-05, - "loss": 3.2868, + "learning_rate": 4.501255973329622e-05, + "loss": 3.247, "step": 30100 }, { "epoch": 0.1, - "learning_rate": 4.50040695327647e-05, - "loss": 3.2876, + "learning_rate": 4.4995990164303846e-05, + "loss": 3.2369, "step": 30200 }, { "epoch": 0.1, - "learning_rate": 4.4987526716648034e-05, - "loss": 3.2898, + "learning_rate": 4.497942059531148e-05, + "loss": 3.2581, "step": 30300 }, { "epoch": 0.1, - "learning_rate": 4.497098390053135e-05, - "loss": 3.2959, + "learning_rate": 4.496285102631911e-05, + "loss": 3.2746, "step": 30400 }, { "epoch": 0.1, - "learning_rate": 4.4954441084414683e-05, - "loss": 3.2966, + "learning_rate": 4.494628145732673e-05, + "loss": 3.2517, "step": 30500 }, { "epoch": 0.1, - "learning_rate": 4.4937898268298015e-05, - "loss": 3.2712, + "learning_rate": 4.492971188833436e-05, + "loss": 3.2565, "step": 30600 }, { "epoch": 0.1, - "learning_rate": 4.492135545218133e-05, - "loss": 3.2904, + "learning_rate": 4.491314231934199e-05, + "loss": 3.2539, "step": 30700 }, { "epoch": 0.1, - "learning_rate": 4.4904812636064664e-05, - "loss": 3.2859, + "learning_rate": 4.489657275034962e-05, + "loss": 3.2528, "step": 30800 }, { "epoch": 0.1, - "learning_rate": 4.4888269819947995e-05, - "loss": 3.2782, + "learning_rate": 4.488000318135725e-05, + "loss": 3.2485, "step": 30900 }, { "epoch": 0.1, - "learning_rate": 4.487172700383132e-05, - "loss": 3.2856, + "learning_rate": 4.486343361236487e-05, + "loss": 3.2504, "step": 31000 }, { "epoch": 0.1, - "learning_rate": 4.4855184187714644e-05, - "loss": 3.2989, + "learning_rate": 4.4846864043372506e-05, + "loss": 3.2605, "step": 31100 }, { "epoch": 0.1, - "learning_rate": 4.4838641371597975e-05, - "loss": 3.2831, + "learning_rate": 4.483029447438014e-05, + "loss": 3.2413, "step": 31200 }, { "epoch": 0.1, - "learning_rate": 4.48220985554813e-05, - "loss": 3.2765, + "learning_rate": 4.481372490538776e-05, + "loss": 3.2433, "step": 31300 }, { "epoch": 0.1, - "learning_rate": 4.4805555739364625e-05, - "loss": 3.2854, + "learning_rate": 4.479715533639539e-05, + "loss": 3.2358, "step": 31400 }, { "epoch": 0.1, - "learning_rate": 4.4789012923247956e-05, - "loss": 3.2868, + "learning_rate": 4.478058576740302e-05, + "loss": 3.246, "step": 31500 }, { "epoch": 0.1, - "learning_rate": 4.477247010713128e-05, - "loss": 3.2819, + "learning_rate": 4.476401619841065e-05, + "loss": 3.2436, "step": 31600 }, { - "epoch": 0.1, - "learning_rate": 4.4755927291014605e-05, - "loss": 3.2786, + "epoch": 0.11, + "learning_rate": 4.4747446629418274e-05, + "loss": 3.2599, "step": 31700 }, { "epoch": 0.11, - "learning_rate": 4.4739384474897936e-05, - "loss": 3.2863, + "learning_rate": 4.473087706042591e-05, + "loss": 3.2453, "step": 31800 }, { "epoch": 0.11, - "learning_rate": 4.472284165878126e-05, - "loss": 3.2992, + "learning_rate": 4.471430749143353e-05, + "loss": 3.2594, "step": 31900 }, { "epoch": 0.11, - "learning_rate": 4.4706298842664585e-05, - "loss": 3.3031, + "learning_rate": 4.4697737922441165e-05, + "loss": 3.2583, "step": 32000 }, { "epoch": 0.11, - "learning_rate": 4.468975602654791e-05, - "loss": 3.2771, + "learning_rate": 4.468116835344879e-05, + "loss": 3.2433, "step": 32100 }, { "epoch": 0.11, - "learning_rate": 4.467321321043124e-05, - "loss": 3.2902, + "learning_rate": 4.466459878445642e-05, + "loss": 3.2487, "step": 32200 }, { "epoch": 0.11, - "learning_rate": 4.4656670394314566e-05, - "loss": 3.2804, + "learning_rate": 4.464802921546405e-05, + "loss": 3.2464, "step": 32300 }, { "epoch": 0.11, - "learning_rate": 4.464012757819789e-05, - "loss": 3.2853, + "learning_rate": 4.463145964647168e-05, + "loss": 3.25, "step": 32400 }, { "epoch": 0.11, - "learning_rate": 4.462358476208122e-05, - "loss": 3.2879, + "learning_rate": 4.46148900774793e-05, + "loss": 3.2461, "step": 32500 }, { "epoch": 0.11, - "learning_rate": 4.4607041945964546e-05, - "loss": 3.2883, + "learning_rate": 4.4598320508486934e-05, + "loss": 3.2463, "step": 32600 }, { "epoch": 0.11, - "learning_rate": 4.459049912984787e-05, - "loss": 3.2902, + "learning_rate": 4.4581750939494566e-05, + "loss": 3.256, "step": 32700 }, { "epoch": 0.11, - "learning_rate": 4.45739563137312e-05, - "loss": 3.2852, + "learning_rate": 4.456518137050219e-05, + "loss": 3.248, "step": 32800 }, { "epoch": 0.11, - "learning_rate": 4.455741349761453e-05, - "loss": 3.2832, + "learning_rate": 4.454861180150982e-05, + "loss": 3.2472, "step": 32900 }, { "epoch": 0.11, - "learning_rate": 4.454087068149785e-05, - "loss": 3.2793, + "learning_rate": 4.453204223251745e-05, + "loss": 3.2433, "step": 33000 }, { "epoch": 0.11, - "learning_rate": 4.452432786538118e-05, - "loss": 3.275, + "learning_rate": 4.4515472663525076e-05, + "loss": 3.271, "step": 33100 }, { "epoch": 0.11, - "learning_rate": 4.4507785049264514e-05, - "loss": 3.281, + "learning_rate": 4.449890309453271e-05, + "loss": 3.2518, "step": 33200 }, { "epoch": 0.11, - "learning_rate": 4.449124223314783e-05, - "loss": 3.284, + "learning_rate": 4.4482333525540335e-05, + "loss": 3.2536, "step": 33300 }, { "epoch": 0.11, - "learning_rate": 4.447469941703116e-05, - "loss": 3.2824, + "learning_rate": 4.446576395654796e-05, + "loss": 3.2317, "step": 33400 }, { "epoch": 0.11, - "learning_rate": 4.4458156600914494e-05, - "loss": 3.2664, + "learning_rate": 4.444919438755559e-05, + "loss": 3.2532, "step": 33500 }, { "epoch": 0.11, - "learning_rate": 4.444161378479781e-05, - "loss": 3.2768, + "learning_rate": 4.4432624818563226e-05, + "loss": 3.264, "step": 33600 }, { "epoch": 0.11, - "learning_rate": 4.442507096868114e-05, - "loss": 3.2952, + "learning_rate": 4.441605524957085e-05, + "loss": 3.2416, "step": 33700 }, { "epoch": 0.11, - "learning_rate": 4.4408528152564474e-05, - "loss": 3.2902, + "learning_rate": 4.439948568057848e-05, + "loss": 3.2655, "step": 33800 }, { "epoch": 0.11, - "learning_rate": 4.439198533644779e-05, - "loss": 3.2989, + "learning_rate": 4.438291611158611e-05, + "loss": 3.2467, "step": 33900 }, { "epoch": 0.11, - "learning_rate": 4.4375442520331123e-05, - "loss": 3.2766, + "learning_rate": 4.4366346542593736e-05, + "loss": 3.2454, "step": 34000 }, { "epoch": 0.11, - "learning_rate": 4.4358899704214455e-05, - "loss": 3.276, + "learning_rate": 4.434977697360136e-05, + "loss": 3.2445, "step": 34100 }, { "epoch": 0.11, - "learning_rate": 4.434235688809777e-05, - "loss": 3.2783, + "learning_rate": 4.4333207404608994e-05, + "loss": 3.2569, "step": 34200 }, { "epoch": 0.11, - "learning_rate": 4.4325814071981104e-05, - "loss": 3.2817, + "learning_rate": 4.431663783561662e-05, + "loss": 3.2527, "step": 34300 }, { "epoch": 0.11, - "learning_rate": 4.4309271255864435e-05, - "loss": 3.2823, + "learning_rate": 4.430006826662425e-05, + "loss": 3.2508, "step": 34400 }, { "epoch": 0.11, - "learning_rate": 4.429272843974775e-05, - "loss": 3.2793, + "learning_rate": 4.428349869763188e-05, + "loss": 3.2663, "step": 34500 }, { "epoch": 0.11, - "learning_rate": 4.4276185623631084e-05, - "loss": 3.2741, + "learning_rate": 4.4266929128639504e-05, + "loss": 3.2484, "step": 34600 }, { "epoch": 0.11, - "learning_rate": 4.425964280751441e-05, - "loss": 3.2744, + "learning_rate": 4.425035955964714e-05, + "loss": 3.2569, "step": 34700 }, { "epoch": 0.12, - "learning_rate": 4.424309999139773e-05, - "loss": 3.2765, + "learning_rate": 4.423378999065477e-05, + "loss": 3.252, "step": 34800 }, { "epoch": 0.12, - "learning_rate": 4.4226557175281065e-05, - "loss": 3.285, + "learning_rate": 4.4217220421662395e-05, + "loss": 3.2398, "step": 34900 }, { "epoch": 0.12, - "learning_rate": 4.421001435916439e-05, - "loss": 3.2782, + "learning_rate": 4.420065085267002e-05, + "loss": 3.2416, "step": 35000 }, { "epoch": 0.12, - "learning_rate": 4.419347154304772e-05, - "loss": 3.2879, + "learning_rate": 4.4184081283677654e-05, + "loss": 3.2498, "step": 35100 }, { "epoch": 0.12, - "learning_rate": 4.4176928726931045e-05, - "loss": 3.2843, + "learning_rate": 4.416751171468528e-05, + "loss": 3.2529, "step": 35200 }, { "epoch": 0.12, - "learning_rate": 4.416038591081437e-05, - "loss": 3.2782, + "learning_rate": 4.4150942145692905e-05, + "loss": 3.2522, "step": 35300 }, { "epoch": 0.12, - "learning_rate": 4.41438430946977e-05, - "loss": 3.2875, + "learning_rate": 4.413437257670054e-05, + "loss": 3.2417, "step": 35400 }, { "epoch": 0.12, - "learning_rate": 4.4127300278581025e-05, - "loss": 3.2691, + "learning_rate": 4.4117803007708164e-05, + "loss": 3.2596, "step": 35500 }, { "epoch": 0.12, - "learning_rate": 4.411075746246435e-05, - "loss": 3.2843, + "learning_rate": 4.4101233438715796e-05, + "loss": 3.2585, "step": 35600 }, { "epoch": 0.12, - "learning_rate": 4.409421464634768e-05, - "loss": 3.2993, + "learning_rate": 4.408466386972342e-05, + "loss": 3.2546, "step": 35700 }, { "epoch": 0.12, - "learning_rate": 4.4077671830231006e-05, - "loss": 3.2918, + "learning_rate": 4.406809430073105e-05, + "loss": 3.2534, "step": 35800 }, { "epoch": 0.12, - "learning_rate": 4.406112901411433e-05, - "loss": 3.2835, + "learning_rate": 4.405152473173868e-05, + "loss": 3.2497, "step": 35900 }, { "epoch": 0.12, - "learning_rate": 4.404458619799766e-05, - "loss": 3.2957, + "learning_rate": 4.403495516274631e-05, + "loss": 3.2471, "step": 36000 }, { "epoch": 0.12, - "learning_rate": 4.4028043381880986e-05, - "loss": 3.2742, + "learning_rate": 4.401838559375394e-05, + "loss": 3.2556, "step": 36100 }, { "epoch": 0.12, - "learning_rate": 4.401150056576431e-05, - "loss": 3.2875, + "learning_rate": 4.4001816024761565e-05, + "loss": 3.253, "step": 36200 }, { "epoch": 0.12, - "learning_rate": 4.399495774964764e-05, - "loss": 3.2882, + "learning_rate": 4.39852464557692e-05, + "loss": 3.2383, "step": 36300 }, { "epoch": 0.12, - "learning_rate": 4.3978414933530966e-05, - "loss": 3.271, + "learning_rate": 4.396867688677682e-05, + "loss": 3.2575, "step": 36400 }, { "epoch": 0.12, - "learning_rate": 4.396187211741429e-05, - "loss": 3.2728, + "learning_rate": 4.395210731778445e-05, + "loss": 3.2376, "step": 36500 }, { "epoch": 0.12, - "learning_rate": 4.394532930129762e-05, - "loss": 3.2816, + "learning_rate": 4.393553774879208e-05, + "loss": 3.2524, "step": 36600 }, { "epoch": 0.12, - "learning_rate": 4.392878648518095e-05, - "loss": 3.2792, + "learning_rate": 4.391896817979971e-05, + "loss": 3.2607, "step": 36700 }, { "epoch": 0.12, - "learning_rate": 4.391224366906427e-05, - "loss": 3.2718, + "learning_rate": 4.390239861080734e-05, + "loss": 3.2391, "step": 36800 }, { "epoch": 0.12, - "learning_rate": 4.38957008529476e-05, - "loss": 3.2781, + "learning_rate": 4.3885829041814966e-05, + "loss": 3.2546, "step": 36900 }, { "epoch": 0.12, - "learning_rate": 4.387915803683093e-05, - "loss": 3.2898, + "learning_rate": 4.386925947282259e-05, + "loss": 3.2445, "step": 37000 }, { "epoch": 0.12, - "learning_rate": 4.386261522071425e-05, - "loss": 3.2766, + "learning_rate": 4.3852689903830224e-05, + "loss": 3.2477, "step": 37100 }, { "epoch": 0.12, - "learning_rate": 4.384607240459758e-05, - "loss": 3.272, + "learning_rate": 4.383612033483786e-05, + "loss": 3.2484, "step": 37200 }, { "epoch": 0.12, - "learning_rate": 4.382952958848091e-05, - "loss": 3.2715, + "learning_rate": 4.381955076584548e-05, + "loss": 3.2554, "step": 37300 }, { "epoch": 0.12, - "learning_rate": 4.381298677236423e-05, - "loss": 3.2977, + "learning_rate": 4.380298119685311e-05, + "loss": 3.2561, "step": 37400 }, { "epoch": 0.12, - "learning_rate": 4.3796443956247563e-05, - "loss": 3.2827, + "learning_rate": 4.378641162786074e-05, + "loss": 3.2386, "step": 37500 }, { "epoch": 0.12, - "learning_rate": 4.377990114013089e-05, - "loss": 3.2694, + "learning_rate": 4.376984205886837e-05, + "loss": 3.2467, "step": 37600 }, { "epoch": 0.12, - "learning_rate": 4.376335832401421e-05, - "loss": 3.2857, + "learning_rate": 4.375327248987599e-05, + "loss": 3.2595, "step": 37700 }, { "epoch": 0.13, - "learning_rate": 4.3746815507897544e-05, - "loss": 3.3005, + "learning_rate": 4.3736702920883625e-05, + "loss": 3.2485, "step": 37800 }, { "epoch": 0.13, - "learning_rate": 4.373027269178087e-05, - "loss": 3.2855, + "learning_rate": 4.372013335189125e-05, + "loss": 3.2467, "step": 37900 }, { "epoch": 0.13, - "learning_rate": 4.371372987566419e-05, - "loss": 3.2917, + "learning_rate": 4.3703563782898884e-05, + "loss": 3.2477, "step": 38000 }, { "epoch": 0.13, - "learning_rate": 4.3697187059547524e-05, - "loss": 3.2836, + "learning_rate": 4.368699421390651e-05, + "loss": 3.2461, "step": 38100 }, { "epoch": 0.13, - "learning_rate": 4.368064424343085e-05, - "loss": 3.2942, + "learning_rate": 4.3670424644914135e-05, + "loss": 3.2596, "step": 38200 }, { "epoch": 0.13, - "learning_rate": 4.366410142731417e-05, - "loss": 3.2996, + "learning_rate": 4.365385507592177e-05, + "loss": 3.2514, "step": 38300 }, { "epoch": 0.13, - "learning_rate": 4.3647558611197505e-05, - "loss": 3.284, + "learning_rate": 4.36372855069294e-05, + "loss": 3.2442, "step": 38400 }, { "epoch": 0.13, - "learning_rate": 4.363101579508083e-05, - "loss": 3.2787, + "learning_rate": 4.3620715937937026e-05, + "loss": 3.2626, "step": 38500 }, { "epoch": 0.13, - "learning_rate": 4.3614472978964154e-05, - "loss": 3.2885, + "learning_rate": 4.360414636894465e-05, + "loss": 3.2347, "step": 38600 }, { "epoch": 0.13, - "learning_rate": 4.3597930162847485e-05, - "loss": 3.2825, + "learning_rate": 4.3587576799952285e-05, + "loss": 3.2471, "step": 38700 }, { "epoch": 0.13, - "learning_rate": 4.358138734673081e-05, - "loss": 3.2837, + "learning_rate": 4.357100723095991e-05, + "loss": 3.2518, "step": 38800 }, { "epoch": 0.13, - "learning_rate": 4.3564844530614134e-05, - "loss": 3.2908, + "learning_rate": 4.355443766196754e-05, + "loss": 3.246, "step": 38900 }, { "epoch": 0.13, - "learning_rate": 4.3548301714497465e-05, - "loss": 3.2762, + "learning_rate": 4.353786809297517e-05, + "loss": 3.2378, "step": 39000 }, { "epoch": 0.13, - "learning_rate": 4.353175889838079e-05, - "loss": 3.2765, + "learning_rate": 4.3521298523982795e-05, + "loss": 3.255, "step": 39100 }, { "epoch": 0.13, - "learning_rate": 4.351521608226412e-05, - "loss": 3.2976, + "learning_rate": 4.350472895499043e-05, + "loss": 3.2643, "step": 39200 }, { "epoch": 0.13, - "learning_rate": 4.3498673266147446e-05, - "loss": 3.2692, + "learning_rate": 4.348815938599805e-05, + "loss": 3.2521, "step": 39300 }, { "epoch": 0.13, - "learning_rate": 4.348213045003077e-05, - "loss": 3.2811, + "learning_rate": 4.347158981700568e-05, + "loss": 3.2459, "step": 39400 }, { "epoch": 0.13, - "learning_rate": 4.34655876339141e-05, - "loss": 3.2734, + "learning_rate": 4.345502024801331e-05, + "loss": 3.2469, "step": 39500 }, { "epoch": 0.13, - "learning_rate": 4.3449044817797426e-05, - "loss": 3.2943, + "learning_rate": 4.343845067902094e-05, + "loss": 3.2438, "step": 39600 }, { "epoch": 0.13, - "learning_rate": 4.343250200168075e-05, - "loss": 3.2713, + "learning_rate": 4.342188111002857e-05, + "loss": 3.2418, "step": 39700 }, { "epoch": 0.13, - "learning_rate": 4.341595918556408e-05, - "loss": 3.2813, + "learning_rate": 4.3405311541036196e-05, + "loss": 3.2665, "step": 39800 }, { "epoch": 0.13, - "learning_rate": 4.3399416369447406e-05, - "loss": 3.2692, + "learning_rate": 4.338874197204382e-05, + "loss": 3.2425, "step": 39900 }, { "epoch": 0.13, - "learning_rate": 4.338287355333073e-05, - "loss": 3.2853, + "learning_rate": 4.3372172403051454e-05, + "loss": 3.253, "step": 40000 }, { "epoch": 0.13, - "learning_rate": 4.336633073721406e-05, - "loss": 3.2784, + "learning_rate": 4.335560283405909e-05, + "loss": 3.2465, "step": 40100 }, { "epoch": 0.13, - "learning_rate": 4.334978792109739e-05, - "loss": 3.2939, + "learning_rate": 4.3339033265066706e-05, + "loss": 3.2541, "step": 40200 }, { "epoch": 0.13, - "learning_rate": 4.333324510498071e-05, - "loss": 3.2723, + "learning_rate": 4.332246369607434e-05, + "loss": 3.2447, "step": 40300 }, { "epoch": 0.13, - "learning_rate": 4.331670228886404e-05, - "loss": 3.277, + "learning_rate": 4.330589412708197e-05, + "loss": 3.2481, "step": 40400 }, { "epoch": 0.13, - "learning_rate": 4.330015947274737e-05, - "loss": 3.2739, + "learning_rate": 4.32893245580896e-05, + "loss": 3.2491, "step": 40500 }, { "epoch": 0.13, - "learning_rate": 4.328361665663069e-05, - "loss": 3.2745, + "learning_rate": 4.327275498909722e-05, + "loss": 3.2468, "step": 40600 }, { "epoch": 0.13, - "learning_rate": 4.326707384051402e-05, - "loss": 3.2738, + "learning_rate": 4.3256185420104855e-05, + "loss": 3.2446, "step": 40700 }, { - "epoch": 0.13, - "learning_rate": 4.325053102439735e-05, - "loss": 3.2705, + "epoch": 0.14, + "learning_rate": 4.323961585111248e-05, + "loss": 3.2552, "step": 40800 }, { "epoch": 0.14, - "learning_rate": 4.323398820828067e-05, - "loss": 3.2818, + "learning_rate": 4.3223046282120114e-05, + "loss": 3.2511, "step": 40900 }, { "epoch": 0.14, - "learning_rate": 4.3217445392164003e-05, - "loss": 3.2993, + "learning_rate": 4.320647671312774e-05, + "loss": 3.2463, "step": 41000 }, { "epoch": 0.14, - "learning_rate": 4.320090257604733e-05, - "loss": 3.2867, + "learning_rate": 4.3189907144135365e-05, + "loss": 3.253, "step": 41100 }, { "epoch": 0.14, - "learning_rate": 4.318435975993065e-05, - "loss": 3.2908, + "learning_rate": 4.3173337575143e-05, + "loss": 3.2488, "step": 41200 }, { "epoch": 0.14, - "learning_rate": 4.3167816943813984e-05, - "loss": 3.2906, + "learning_rate": 4.315676800615063e-05, + "loss": 3.2353, "step": 41300 }, { "epoch": 0.14, - "learning_rate": 4.315127412769731e-05, - "loss": 3.2861, + "learning_rate": 4.314019843715825e-05, + "loss": 3.2478, "step": 41400 }, { "epoch": 0.14, - "learning_rate": 4.313473131158063e-05, - "loss": 3.2768, + "learning_rate": 4.312362886816588e-05, + "loss": 3.2462, "step": 41500 }, { "epoch": 0.14, - "learning_rate": 4.3118188495463964e-05, - "loss": 3.2923, + "learning_rate": 4.3107059299173515e-05, + "loss": 3.2454, "step": 41600 }, { "epoch": 0.14, - "learning_rate": 4.310164567934729e-05, - "loss": 3.2733, + "learning_rate": 4.309048973018114e-05, + "loss": 3.257, "step": 41700 }, { "epoch": 0.14, - "learning_rate": 4.308510286323061e-05, - "loss": 3.2874, + "learning_rate": 4.3073920161188766e-05, + "loss": 3.2524, "step": 41800 }, { "epoch": 0.14, - "learning_rate": 4.3068560047113945e-05, - "loss": 3.2837, + "learning_rate": 4.30573505921964e-05, + "loss": 3.2396, "step": 41900 }, { "epoch": 0.14, - "learning_rate": 4.305201723099727e-05, - "loss": 3.2827, + "learning_rate": 4.3040781023204025e-05, + "loss": 3.2557, "step": 42000 }, { "epoch": 0.14, - "learning_rate": 4.3035474414880594e-05, - "loss": 3.2816, + "learning_rate": 4.302421145421166e-05, + "loss": 3.252, "step": 42100 }, { "epoch": 0.14, - "learning_rate": 4.3018931598763925e-05, - "loss": 3.2883, + "learning_rate": 4.300764188521928e-05, + "loss": 3.2549, "step": 42200 }, { "epoch": 0.14, - "learning_rate": 4.300238878264725e-05, - "loss": 3.2763, + "learning_rate": 4.299107231622691e-05, + "loss": 3.2609, "step": 42300 }, { "epoch": 0.14, - "learning_rate": 4.2985845966530574e-05, - "loss": 3.2642, + "learning_rate": 4.297450274723454e-05, + "loss": 3.2527, "step": 42400 }, { "epoch": 0.14, - "learning_rate": 4.2969303150413905e-05, - "loss": 3.2771, + "learning_rate": 4.2957933178242174e-05, + "loss": 3.235, "step": 42500 }, { "epoch": 0.14, - "learning_rate": 4.295276033429723e-05, - "loss": 3.2745, + "learning_rate": 4.294136360924979e-05, + "loss": 3.2272, "step": 42600 }, { "epoch": 0.14, - "learning_rate": 4.2936217518180554e-05, - "loss": 3.2742, + "learning_rate": 4.2924794040257426e-05, + "loss": 3.2437, "step": 42700 }, { "epoch": 0.14, - "learning_rate": 4.2919674702063886e-05, - "loss": 3.2976, + "learning_rate": 4.290822447126506e-05, + "loss": 3.2629, "step": 42800 }, { "epoch": 0.14, - "learning_rate": 4.290313188594721e-05, - "loss": 3.2856, + "learning_rate": 4.2891654902272684e-05, + "loss": 3.2478, "step": 42900 }, { "epoch": 0.14, - "learning_rate": 4.2886589069830535e-05, - "loss": 3.2877, + "learning_rate": 4.287508533328031e-05, + "loss": 3.2512, "step": 43000 }, { "epoch": 0.14, - "learning_rate": 4.2870046253713866e-05, - "loss": 3.268, + "learning_rate": 4.285851576428794e-05, + "loss": 3.2496, "step": 43100 }, { "epoch": 0.14, - "learning_rate": 4.285350343759719e-05, - "loss": 3.2837, + "learning_rate": 4.284194619529557e-05, + "loss": 3.2403, "step": 43200 }, { "epoch": 0.14, - "learning_rate": 4.2836960621480515e-05, - "loss": 3.2773, + "learning_rate": 4.28253766263032e-05, + "loss": 3.242, "step": 43300 }, { "epoch": 0.14, - "learning_rate": 4.2820417805363847e-05, - "loss": 3.2718, + "learning_rate": 4.280880705731083e-05, + "loss": 3.243, "step": 43400 }, { "epoch": 0.14, - "learning_rate": 4.280387498924717e-05, - "loss": 3.2883, + "learning_rate": 4.279223748831845e-05, + "loss": 3.2471, "step": 43500 }, { "epoch": 0.14, - "learning_rate": 4.27873321731305e-05, - "loss": 3.2788, + "learning_rate": 4.2775667919326085e-05, + "loss": 3.2592, "step": 43600 }, { "epoch": 0.14, - "learning_rate": 4.277078935701383e-05, - "loss": 3.2846, + "learning_rate": 4.275909835033372e-05, + "loss": 3.2476, "step": 43700 }, { - "epoch": 0.14, - "learning_rate": 4.275424654089715e-05, - "loss": 3.2723, + "epoch": 0.15, + "learning_rate": 4.274252878134134e-05, + "loss": 3.248, "step": 43800 }, { "epoch": 0.15, - "learning_rate": 4.273770372478048e-05, - "loss": 3.2704, + "learning_rate": 4.272595921234897e-05, + "loss": 3.2378, "step": 43900 }, { "epoch": 0.15, - "learning_rate": 4.272116090866381e-05, - "loss": 3.2752, + "learning_rate": 4.27093896433566e-05, + "loss": 3.2499, "step": 44000 }, { "epoch": 0.15, - "learning_rate": 4.270461809254713e-05, - "loss": 3.2712, + "learning_rate": 4.269282007436423e-05, + "loss": 3.2527, "step": 44100 }, { "epoch": 0.15, - "learning_rate": 4.268807527643046e-05, - "loss": 3.2812, + "learning_rate": 4.2676250505371854e-05, + "loss": 3.2443, "step": 44200 }, { "epoch": 0.15, - "learning_rate": 4.267153246031379e-05, - "loss": 3.2719, + "learning_rate": 4.2659680936379486e-05, + "loss": 3.2477, "step": 44300 }, { "epoch": 0.15, - "learning_rate": 4.265498964419711e-05, - "loss": 3.2726, + "learning_rate": 4.264311136738711e-05, + "loss": 3.2495, "step": 44400 }, { "epoch": 0.15, - "learning_rate": 4.2638446828080444e-05, - "loss": 3.2883, + "learning_rate": 4.2626541798394745e-05, + "loss": 3.245, "step": 44500 }, { "epoch": 0.15, - "learning_rate": 4.262190401196377e-05, - "loss": 3.2805, + "learning_rate": 4.260997222940237e-05, + "loss": 3.2449, "step": 44600 }, { "epoch": 0.15, - "learning_rate": 4.260536119584709e-05, - "loss": 3.3015, + "learning_rate": 4.2593402660409996e-05, + "loss": 3.2511, "step": 44700 }, { "epoch": 0.15, - "learning_rate": 4.2588818379730424e-05, - "loss": 3.2709, + "learning_rate": 4.257683309141763e-05, + "loss": 3.2413, "step": 44800 }, { "epoch": 0.15, - "learning_rate": 4.257227556361374e-05, - "loss": 3.2864, + "learning_rate": 4.256026352242526e-05, + "loss": 3.2423, "step": 44900 }, { "epoch": 0.15, - "learning_rate": 4.255573274749707e-05, - "loss": 3.2695, + "learning_rate": 4.254369395343288e-05, + "loss": 3.2483, "step": 45000 }, { "epoch": 0.15, - "learning_rate": 4.2539189931380404e-05, - "loss": 3.276, + "learning_rate": 4.252712438444051e-05, + "loss": 3.2414, "step": 45100 }, { "epoch": 0.15, - "learning_rate": 4.252264711526372e-05, - "loss": 3.2666, + "learning_rate": 4.2510554815448146e-05, + "loss": 3.2552, "step": 45200 }, { "epoch": 0.15, - "learning_rate": 4.250610429914705e-05, - "loss": 3.2815, + "learning_rate": 4.249398524645577e-05, + "loss": 3.2474, "step": 45300 }, { "epoch": 0.15, - "learning_rate": 4.2489561483030385e-05, - "loss": 3.2822, + "learning_rate": 4.24774156774634e-05, + "loss": 3.2374, "step": 45400 }, { "epoch": 0.15, - "learning_rate": 4.24730186669137e-05, - "loss": 3.2792, + "learning_rate": 4.246084610847103e-05, + "loss": 3.2392, "step": 45500 }, { "epoch": 0.15, - "learning_rate": 4.2456475850797034e-05, - "loss": 3.2849, + "learning_rate": 4.2444276539478656e-05, + "loss": 3.257, "step": 45600 }, { "epoch": 0.15, - "learning_rate": 4.2439933034680365e-05, - "loss": 3.2803, + "learning_rate": 4.242770697048629e-05, + "loss": 3.2656, "step": 45700 }, { "epoch": 0.15, - "learning_rate": 4.242339021856369e-05, - "loss": 3.2746, + "learning_rate": 4.2411137401493914e-05, + "loss": 3.2569, "step": 45800 }, { "epoch": 0.15, - "learning_rate": 4.2406847402447014e-05, - "loss": 3.2647, + "learning_rate": 4.239456783250154e-05, + "loss": 3.2466, "step": 45900 }, { "epoch": 0.15, - "learning_rate": 4.2390304586330345e-05, - "loss": 3.2782, + "learning_rate": 4.237799826350917e-05, + "loss": 3.2382, "step": 46000 }, { "epoch": 0.15, - "learning_rate": 4.237376177021367e-05, - "loss": 3.275, + "learning_rate": 4.2361428694516805e-05, + "loss": 3.2467, "step": 46100 }, { "epoch": 0.15, - "learning_rate": 4.2357218954096994e-05, - "loss": 3.2574, + "learning_rate": 4.2344859125524424e-05, + "loss": 3.2501, "step": 46200 }, { "epoch": 0.15, - "learning_rate": 4.2340676137980326e-05, - "loss": 3.2702, + "learning_rate": 4.232828955653206e-05, + "loss": 3.2362, "step": 46300 }, { "epoch": 0.15, - "learning_rate": 4.232413332186365e-05, - "loss": 3.2754, + "learning_rate": 4.231171998753969e-05, + "loss": 3.2499, "step": 46400 }, { "epoch": 0.15, - "learning_rate": 4.2307590505746975e-05, - "loss": 3.2867, + "learning_rate": 4.2295150418547315e-05, + "loss": 3.2487, "step": 46500 }, { "epoch": 0.15, - "learning_rate": 4.2291047689630306e-05, - "loss": 3.2667, + "learning_rate": 4.227858084955494e-05, + "loss": 3.252, "step": 46600 }, { "epoch": 0.15, - "learning_rate": 4.227450487351363e-05, - "loss": 3.2795, + "learning_rate": 4.2262011280562574e-05, + "loss": 3.2483, "step": 46700 }, { - "epoch": 0.15, - "learning_rate": 4.2257962057396955e-05, - "loss": 3.2763, + "epoch": 0.16, + "learning_rate": 4.22454417115702e-05, + "loss": 3.2438, "step": 46800 }, { "epoch": 0.16, - "learning_rate": 4.2241419241280287e-05, - "loss": 3.2788, + "learning_rate": 4.222887214257783e-05, + "loss": 3.243, "step": 46900 }, { "epoch": 0.16, - "learning_rate": 4.222487642516361e-05, - "loss": 3.2677, + "learning_rate": 4.221230257358546e-05, + "loss": 3.2388, "step": 47000 }, { "epoch": 0.16, - "learning_rate": 4.2208333609046936e-05, - "loss": 3.2683, + "learning_rate": 4.2195733004593084e-05, + "loss": 3.2444, "step": 47100 }, { "epoch": 0.16, - "learning_rate": 4.219179079293027e-05, - "loss": 3.2804, + "learning_rate": 4.2179163435600716e-05, + "loss": 3.2319, "step": 47200 }, { "epoch": 0.16, - "learning_rate": 4.217524797681359e-05, - "loss": 3.2729, + "learning_rate": 4.216259386660835e-05, + "loss": 3.2342, "step": 47300 }, { "epoch": 0.16, - "learning_rate": 4.2158705160696916e-05, - "loss": 3.2818, + "learning_rate": 4.2146024297615975e-05, + "loss": 3.2442, "step": 47400 }, { "epoch": 0.16, - "learning_rate": 4.214216234458024e-05, - "loss": 3.2829, + "learning_rate": 4.21294547286236e-05, + "loss": 3.2393, "step": 47500 }, { "epoch": 0.16, - "learning_rate": 4.212561952846357e-05, - "loss": 3.272, + "learning_rate": 4.211288515963123e-05, + "loss": 3.2367, "step": 47600 }, { "epoch": 0.16, - "learning_rate": 4.21090767123469e-05, - "loss": 3.2847, + "learning_rate": 4.209631559063886e-05, + "loss": 3.2501, "step": 47700 }, { "epoch": 0.16, - "learning_rate": 4.209253389623022e-05, - "loss": 3.2814, + "learning_rate": 4.2079746021646485e-05, + "loss": 3.2452, "step": 47800 }, { "epoch": 0.16, - "learning_rate": 4.207599108011355e-05, - "loss": 3.2718, + "learning_rate": 4.206317645265412e-05, + "loss": 3.2442, "step": 47900 }, { "epoch": 0.16, - "learning_rate": 4.2059448263996884e-05, - "loss": 3.2912, + "learning_rate": 4.204660688366174e-05, + "loss": 3.2376, "step": 48000 }, { "epoch": 0.16, - "learning_rate": 4.20429054478802e-05, - "loss": 3.2841, + "learning_rate": 4.2030037314669376e-05, + "loss": 3.2367, "step": 48100 }, { "epoch": 0.16, - "learning_rate": 4.202636263176353e-05, - "loss": 3.2781, + "learning_rate": 4.2013467745677e-05, + "loss": 3.2489, "step": 48200 }, { "epoch": 0.16, - "learning_rate": 4.2009819815646864e-05, - "loss": 3.2631, + "learning_rate": 4.199689817668463e-05, + "loss": 3.2521, "step": 48300 }, { "epoch": 0.16, - "learning_rate": 4.199327699953018e-05, - "loss": 3.2655, + "learning_rate": 4.198032860769226e-05, + "loss": 3.2567, "step": 48400 }, { "epoch": 0.16, - "learning_rate": 4.197673418341351e-05, - "loss": 3.2698, + "learning_rate": 4.1963759038699886e-05, + "loss": 3.2288, "step": 48500 }, { "epoch": 0.16, - "learning_rate": 4.1960191367296844e-05, - "loss": 3.2651, + "learning_rate": 4.194718946970752e-05, + "loss": 3.243, "step": 48600 }, { "epoch": 0.16, - "learning_rate": 4.194364855118016e-05, - "loss": 3.2819, + "learning_rate": 4.1930619900715144e-05, + "loss": 3.2426, "step": 48700 }, { "epoch": 0.16, - "learning_rate": 4.192710573506349e-05, - "loss": 3.2709, + "learning_rate": 4.191405033172277e-05, + "loss": 3.256, "step": 48800 }, { "epoch": 0.16, - "learning_rate": 4.1910562918946825e-05, - "loss": 3.2778, + "learning_rate": 4.18974807627304e-05, + "loss": 3.2583, "step": 48900 }, { "epoch": 0.16, - "learning_rate": 4.189402010283014e-05, - "loss": 3.2856, + "learning_rate": 4.188091119373803e-05, + "loss": 3.2518, "step": 49000 }, { "epoch": 0.16, - "learning_rate": 4.1877477286713474e-05, - "loss": 3.2965, + "learning_rate": 4.1864341624745654e-05, + "loss": 3.2468, "step": 49100 }, { "epoch": 0.16, - "learning_rate": 4.1860934470596805e-05, - "loss": 3.2803, + "learning_rate": 4.184777205575329e-05, + "loss": 3.2454, "step": 49200 }, { "epoch": 0.16, - "learning_rate": 4.184439165448012e-05, - "loss": 3.263, + "learning_rate": 4.183120248676092e-05, + "loss": 3.2491, "step": 49300 }, { "epoch": 0.16, - "learning_rate": 4.1827848838363454e-05, - "loss": 3.2755, + "learning_rate": 4.1814632917768545e-05, + "loss": 3.2646, "step": 49400 }, { "epoch": 0.16, - "learning_rate": 4.1811306022246785e-05, - "loss": 3.2782, + "learning_rate": 4.179806334877617e-05, + "loss": 3.2585, "step": 49500 }, { "epoch": 0.16, - "learning_rate": 4.17947632061301e-05, - "loss": 3.2788, + "learning_rate": 4.1781493779783804e-05, + "loss": 3.2457, "step": 49600 }, { "epoch": 0.16, - "learning_rate": 4.1778220390013434e-05, - "loss": 3.2698, + "learning_rate": 4.176492421079143e-05, + "loss": 3.2431, "step": 49700 }, { - "epoch": 0.16, - "learning_rate": 4.1761677573896766e-05, - "loss": 3.2774, + "epoch": 0.17, + "learning_rate": 4.174835464179906e-05, + "loss": 3.2433, "step": 49800 }, { "epoch": 0.17, - "learning_rate": 4.174513475778009e-05, - "loss": 3.2741, + "learning_rate": 4.173178507280669e-05, + "loss": 3.2441, "step": 49900 }, { "epoch": 0.17, - "learning_rate": 4.1728591941663415e-05, - "loss": 3.287, + "learning_rate": 4.1715215503814314e-05, + "loss": 3.254, "step": 50000 }, { "epoch": 0.17, - "learning_rate": 4.171204912554674e-05, - "loss": 3.2744, + "learning_rate": 4.1698645934821946e-05, + "loss": 3.2404, "step": 50100 }, { "epoch": 0.17, - "learning_rate": 4.169550630943007e-05, - "loss": 3.2841, + "learning_rate": 4.168207636582957e-05, + "loss": 3.254, "step": 50200 }, { "epoch": 0.17, - "learning_rate": 4.1678963493313395e-05, - "loss": 3.2667, + "learning_rate": 4.16655067968372e-05, + "loss": 3.2355, "step": 50300 }, { "epoch": 0.17, - "learning_rate": 4.166242067719672e-05, - "loss": 3.2733, + "learning_rate": 4.164893722784483e-05, + "loss": 3.2509, "step": 50400 }, { "epoch": 0.17, - "learning_rate": 4.164587786108005e-05, - "loss": 3.2774, + "learning_rate": 4.163236765885246e-05, + "loss": 3.2458, "step": 50500 }, { "epoch": 0.17, - "learning_rate": 4.1629335044963376e-05, - "loss": 3.2722, + "learning_rate": 4.161579808986009e-05, + "loss": 3.2469, "step": 50600 }, { "epoch": 0.17, - "learning_rate": 4.16127922288467e-05, - "loss": 3.2764, + "learning_rate": 4.1599228520867715e-05, + "loss": 3.2565, "step": 50700 }, { "epoch": 0.17, - "learning_rate": 4.159624941273003e-05, - "loss": 3.2835, + "learning_rate": 4.158265895187535e-05, + "loss": 3.2405, "step": 50800 }, { "epoch": 0.17, - "learning_rate": 4.1579706596613356e-05, - "loss": 3.2851, + "learning_rate": 4.156608938288297e-05, + "loss": 3.2361, "step": 50900 }, { "epoch": 0.17, - "learning_rate": 4.156316378049668e-05, - "loss": 3.2814, + "learning_rate": 4.1549519813890606e-05, + "loss": 3.2459, "step": 51000 }, { "epoch": 0.17, - "learning_rate": 4.154662096438001e-05, - "loss": 3.2749, + "learning_rate": 4.153295024489823e-05, + "loss": 3.2475, "step": 51100 }, { "epoch": 0.17, - "learning_rate": 4.1530078148263336e-05, - "loss": 3.2696, + "learning_rate": 4.151638067590586e-05, + "loss": 3.2551, "step": 51200 }, { "epoch": 0.17, - "learning_rate": 4.151353533214666e-05, - "loss": 3.2935, + "learning_rate": 4.149981110691349e-05, + "loss": 3.2275, "step": 51300 }, { "epoch": 0.17, - "learning_rate": 4.149699251602999e-05, - "loss": 3.2737, + "learning_rate": 4.1483241537921116e-05, + "loss": 3.2438, "step": 51400 }, { "epoch": 0.17, - "learning_rate": 4.148044969991332e-05, - "loss": 3.2831, + "learning_rate": 4.146667196892874e-05, + "loss": 3.2507, "step": 51500 }, { "epoch": 0.17, - "learning_rate": 4.146390688379664e-05, - "loss": 3.2638, + "learning_rate": 4.1450102399936374e-05, + "loss": 3.2429, "step": 51600 }, { "epoch": 0.17, - "learning_rate": 4.144736406767997e-05, - "loss": 3.273, + "learning_rate": 4.143353283094401e-05, + "loss": 3.2454, "step": 51700 }, { "epoch": 0.17, - "learning_rate": 4.14308212515633e-05, - "loss": 3.2786, + "learning_rate": 4.141696326195163e-05, + "loss": 3.2471, "step": 51800 }, { "epoch": 0.17, - "learning_rate": 4.141427843544662e-05, - "loss": 3.28, + "learning_rate": 4.140039369295926e-05, + "loss": 3.2453, "step": 51900 }, { "epoch": 0.17, - "learning_rate": 4.139773561932995e-05, - "loss": 3.2827, + "learning_rate": 4.138382412396689e-05, + "loss": 3.2384, "step": 52000 }, { "epoch": 0.17, - "learning_rate": 4.1381192803213284e-05, - "loss": 3.2688, + "learning_rate": 4.136725455497452e-05, + "loss": 3.2522, "step": 52100 }, { "epoch": 0.17, - "learning_rate": 4.13646499870966e-05, - "loss": 3.2596, + "learning_rate": 4.135068498598215e-05, + "loss": 3.243, "step": 52200 }, { "epoch": 0.17, - "learning_rate": 4.134810717097993e-05, - "loss": 3.2704, + "learning_rate": 4.1334115416989775e-05, + "loss": 3.2496, "step": 52300 }, { "epoch": 0.17, - "learning_rate": 4.1331564354863265e-05, - "loss": 3.2792, + "learning_rate": 4.13175458479974e-05, + "loss": 3.2456, "step": 52400 }, { "epoch": 0.17, - "learning_rate": 4.131502153874658e-05, - "loss": 3.2734, + "learning_rate": 4.1300976279005034e-05, + "loss": 3.2445, "step": 52500 }, { "epoch": 0.17, - "learning_rate": 4.1298478722629914e-05, - "loss": 3.2838, + "learning_rate": 4.1284406710012666e-05, + "loss": 3.2577, "step": 52600 }, { "epoch": 0.17, - "learning_rate": 4.128193590651324e-05, - "loss": 3.2762, + "learning_rate": 4.1267837141020285e-05, + "loss": 3.2466, "step": 52700 }, { "epoch": 0.17, - "learning_rate": 4.126539309039656e-05, - "loss": 3.2819, + "learning_rate": 4.125126757202792e-05, + "loss": 3.2486, "step": 52800 }, { "epoch": 0.18, - "learning_rate": 4.1248850274279894e-05, - "loss": 3.2741, + "learning_rate": 4.123469800303555e-05, + "loss": 3.2348, "step": 52900 }, { "epoch": 0.18, - "learning_rate": 4.123230745816322e-05, - "loss": 3.2653, + "learning_rate": 4.1218128434043176e-05, + "loss": 3.2439, "step": 53000 }, { "epoch": 0.18, - "learning_rate": 4.121576464204654e-05, - "loss": 3.2647, + "learning_rate": 4.12015588650508e-05, + "loss": 3.2449, "step": 53100 }, { "epoch": 0.18, - "learning_rate": 4.1199221825929875e-05, - "loss": 3.2723, + "learning_rate": 4.1184989296058435e-05, + "loss": 3.2434, "step": 53200 }, { "epoch": 0.18, - "learning_rate": 4.11826790098132e-05, - "loss": 3.2606, + "learning_rate": 4.116841972706606e-05, + "loss": 3.242, "step": 53300 }, { "epoch": 0.18, - "learning_rate": 4.1166136193696524e-05, - "loss": 3.2717, + "learning_rate": 4.115185015807369e-05, + "loss": 3.2493, "step": 53400 }, { "epoch": 0.18, - "learning_rate": 4.1149593377579855e-05, - "loss": 3.2796, + "learning_rate": 4.113528058908132e-05, + "loss": 3.2387, "step": 53500 }, { "epoch": 0.18, - "learning_rate": 4.113305056146318e-05, - "loss": 3.2854, + "learning_rate": 4.1118711020088945e-05, + "loss": 3.2418, "step": 53600 }, { "epoch": 0.18, - "learning_rate": 4.1116507745346504e-05, - "loss": 3.2598, + "learning_rate": 4.110214145109658e-05, + "loss": 3.2295, "step": 53700 }, { "epoch": 0.18, - "learning_rate": 4.1099964929229835e-05, - "loss": 3.2887, + "learning_rate": 4.108557188210421e-05, + "loss": 3.2463, "step": 53800 }, { "epoch": 0.18, - "learning_rate": 4.108342211311316e-05, - "loss": 3.2692, + "learning_rate": 4.106900231311183e-05, + "loss": 3.2414, "step": 53900 }, { "epoch": 0.18, - "learning_rate": 4.1066879296996484e-05, - "loss": 3.2895, + "learning_rate": 4.105243274411946e-05, + "loss": 3.2426, "step": 54000 }, { "epoch": 0.18, - "learning_rate": 4.1050336480879816e-05, - "loss": 3.2643, + "learning_rate": 4.1035863175127094e-05, + "loss": 3.258, "step": 54100 }, { "epoch": 0.18, - "learning_rate": 4.103379366476314e-05, - "loss": 3.2739, + "learning_rate": 4.101929360613472e-05, + "loss": 3.2583, "step": 54200 }, { "epoch": 0.18, - "learning_rate": 4.101725084864647e-05, - "loss": 3.2844, + "learning_rate": 4.1002724037142346e-05, + "loss": 3.2462, "step": 54300 }, { "epoch": 0.18, - "learning_rate": 4.1000708032529796e-05, - "loss": 3.2898, + "learning_rate": 4.098615446814998e-05, + "loss": 3.2532, "step": 54400 }, { "epoch": 0.18, - "learning_rate": 4.098416521641312e-05, - "loss": 3.2769, + "learning_rate": 4.0969584899157604e-05, + "loss": 3.242, "step": 54500 }, { "epoch": 0.18, - "learning_rate": 4.096762240029645e-05, - "loss": 3.276, + "learning_rate": 4.095301533016524e-05, + "loss": 3.2382, "step": 54600 }, { "epoch": 0.18, - "learning_rate": 4.0951079584179776e-05, - "loss": 3.2716, + "learning_rate": 4.093644576117286e-05, + "loss": 3.2551, "step": 54700 }, { "epoch": 0.18, - "learning_rate": 4.09345367680631e-05, - "loss": 3.275, + "learning_rate": 4.091987619218049e-05, + "loss": 3.242, "step": 54800 }, { "epoch": 0.18, - "learning_rate": 4.091799395194643e-05, - "loss": 3.2815, + "learning_rate": 4.090330662318812e-05, + "loss": 3.2387, "step": 54900 }, { "epoch": 0.18, - "learning_rate": 4.090145113582976e-05, - "loss": 3.2617, + "learning_rate": 4.0886737054195754e-05, + "loss": 3.2386, "step": 55000 }, { "epoch": 0.18, - "learning_rate": 4.088490831971308e-05, - "loss": 3.2822, + "learning_rate": 4.087016748520337e-05, + "loss": 3.247, "step": 55100 }, { "epoch": 0.18, - "learning_rate": 4.086836550359641e-05, - "loss": 3.275, + "learning_rate": 4.0853597916211005e-05, + "loss": 3.2492, "step": 55200 }, { "epoch": 0.18, - "learning_rate": 4.085182268747974e-05, - "loss": 3.2682, + "learning_rate": 4.083702834721864e-05, + "loss": 3.2388, "step": 55300 }, { "epoch": 0.18, - "learning_rate": 4.083527987136306e-05, - "loss": 3.276, + "learning_rate": 4.0820458778226264e-05, + "loss": 3.247, "step": 55400 }, { "epoch": 0.18, - "learning_rate": 4.081873705524639e-05, - "loss": 3.2635, + "learning_rate": 4.080388920923389e-05, + "loss": 3.2247, "step": 55500 }, { "epoch": 0.18, - "learning_rate": 4.080219423912972e-05, - "loss": 3.2695, + "learning_rate": 4.078731964024152e-05, + "loss": 3.2509, "step": 55600 }, { "epoch": 0.18, - "learning_rate": 4.078565142301304e-05, - "loss": 3.2798, + "learning_rate": 4.077075007124915e-05, + "loss": 3.2441, "step": 55700 }, { "epoch": 0.18, - "learning_rate": 4.0769108606896373e-05, - "loss": 3.2667, + "learning_rate": 4.075418050225678e-05, + "loss": 3.2363, "step": 55800 }, { - "epoch": 0.18, - "learning_rate": 4.07525657907797e-05, - "loss": 3.2704, + "epoch": 0.19, + "learning_rate": 4.0737610933264406e-05, + "loss": 3.2309, "step": 55900 }, { "epoch": 0.19, - "learning_rate": 4.073602297466302e-05, - "loss": 3.2718, + "learning_rate": 4.072104136427203e-05, + "loss": 3.2455, "step": 56000 }, { "epoch": 0.19, - "learning_rate": 4.0719480158546354e-05, - "loss": 3.2788, + "learning_rate": 4.0704471795279665e-05, + "loss": 3.2337, "step": 56100 }, { "epoch": 0.19, - "learning_rate": 4.070293734242968e-05, - "loss": 3.2715, + "learning_rate": 4.06879022262873e-05, + "loss": 3.2319, "step": 56200 }, { "epoch": 0.19, - "learning_rate": 4.0686394526313e-05, - "loss": 3.2813, + "learning_rate": 4.0671332657294916e-05, + "loss": 3.2311, "step": 56300 }, { "epoch": 0.19, - "learning_rate": 4.0669851710196334e-05, - "loss": 3.2578, + "learning_rate": 4.065476308830255e-05, + "loss": 3.2484, "step": 56400 }, { "epoch": 0.19, - "learning_rate": 4.065330889407966e-05, - "loss": 3.2768, + "learning_rate": 4.063819351931018e-05, + "loss": 3.2382, "step": 56500 }, { "epoch": 0.19, - "learning_rate": 4.063676607796298e-05, - "loss": 3.2587, + "learning_rate": 4.062162395031781e-05, + "loss": 3.2409, "step": 56600 }, { "epoch": 0.19, - "learning_rate": 4.0620223261846315e-05, - "loss": 3.2674, + "learning_rate": 4.060505438132543e-05, + "loss": 3.2248, "step": 56700 }, { "epoch": 0.19, - "learning_rate": 4.060368044572964e-05, - "loss": 3.281, + "learning_rate": 4.058848481233306e-05, + "loss": 3.2414, "step": 56800 }, { "epoch": 0.19, - "learning_rate": 4.0587137629612964e-05, - "loss": 3.2645, + "learning_rate": 4.057191524334069e-05, + "loss": 3.233, "step": 56900 }, { "epoch": 0.19, - "learning_rate": 4.0570594813496295e-05, - "loss": 3.2587, + "learning_rate": 4.0555345674348324e-05, + "loss": 3.2484, "step": 57000 }, { "epoch": 0.19, - "learning_rate": 4.055405199737962e-05, - "loss": 3.2672, + "learning_rate": 4.053877610535595e-05, + "loss": 3.2532, "step": 57100 }, { "epoch": 0.19, - "learning_rate": 4.0537509181262944e-05, - "loss": 3.2611, + "learning_rate": 4.0522206536363576e-05, + "loss": 3.2527, "step": 57200 }, { "epoch": 0.19, - "learning_rate": 4.0520966365146275e-05, - "loss": 3.2823, + "learning_rate": 4.050563696737121e-05, + "loss": 3.2447, "step": 57300 }, { "epoch": 0.19, - "learning_rate": 4.05044235490296e-05, - "loss": 3.2853, + "learning_rate": 4.0489067398378834e-05, + "loss": 3.2393, "step": 57400 }, { "epoch": 0.19, - "learning_rate": 4.0487880732912924e-05, - "loss": 3.2697, + "learning_rate": 4.047249782938646e-05, + "loss": 3.2333, "step": 57500 }, { "epoch": 0.19, - "learning_rate": 4.0471337916796256e-05, - "loss": 3.2624, + "learning_rate": 4.045592826039409e-05, + "loss": 3.2494, "step": 57600 }, { "epoch": 0.19, - "learning_rate": 4.045479510067958e-05, - "loss": 3.2631, + "learning_rate": 4.043935869140172e-05, + "loss": 3.2256, "step": 57700 }, { "epoch": 0.19, - "learning_rate": 4.0438252284562905e-05, - "loss": 3.2622, + "learning_rate": 4.042278912240935e-05, + "loss": 3.2434, "step": 57800 }, { "epoch": 0.19, - "learning_rate": 4.0421709468446236e-05, - "loss": 3.2699, + "learning_rate": 4.040621955341698e-05, + "loss": 3.2256, "step": 57900 }, { "epoch": 0.19, - "learning_rate": 4.040516665232956e-05, - "loss": 3.2851, + "learning_rate": 4.03896499844246e-05, + "loss": 3.2336, "step": 58000 }, { "epoch": 0.19, - "learning_rate": 4.0388623836212885e-05, - "loss": 3.2694, + "learning_rate": 4.0373080415432235e-05, + "loss": 3.2468, "step": 58100 }, { "epoch": 0.19, - "learning_rate": 4.0372081020096216e-05, - "loss": 3.2844, + "learning_rate": 4.035651084643987e-05, + "loss": 3.2433, "step": 58200 }, { "epoch": 0.19, - "learning_rate": 4.035553820397954e-05, - "loss": 3.2686, + "learning_rate": 4.0339941277447494e-05, + "loss": 3.2476, "step": 58300 }, { "epoch": 0.19, - "learning_rate": 4.033899538786287e-05, - "loss": 3.2773, + "learning_rate": 4.032337170845512e-05, + "loss": 3.2488, "step": 58400 }, { "epoch": 0.19, - "learning_rate": 4.03224525717462e-05, - "loss": 3.2559, + "learning_rate": 4.030680213946275e-05, + "loss": 3.2495, "step": 58500 }, { "epoch": 0.19, - "learning_rate": 4.030590975562952e-05, - "loss": 3.2661, + "learning_rate": 4.029023257047038e-05, + "loss": 3.234, "step": 58600 }, { "epoch": 0.19, - "learning_rate": 4.028936693951285e-05, - "loss": 3.2859, + "learning_rate": 4.0273663001478004e-05, + "loss": 3.2345, "step": 58700 }, { "epoch": 0.19, - "learning_rate": 4.027282412339618e-05, - "loss": 3.2842, + "learning_rate": 4.0257093432485636e-05, + "loss": 3.2438, "step": 58800 }, { - "epoch": 0.19, - "learning_rate": 4.02562813072795e-05, - "loss": 3.2864, + "epoch": 0.2, + "learning_rate": 4.024052386349326e-05, + "loss": 3.2477, "step": 58900 }, { "epoch": 0.2, - "learning_rate": 4.023973849116283e-05, - "loss": 3.2716, + "learning_rate": 4.0223954294500895e-05, + "loss": 3.2387, "step": 59000 }, { "epoch": 0.2, - "learning_rate": 4.022319567504616e-05, - "loss": 3.2941, + "learning_rate": 4.020738472550852e-05, + "loss": 3.2499, "step": 59100 }, { "epoch": 0.2, - "learning_rate": 4.020665285892948e-05, - "loss": 3.2728, + "learning_rate": 4.0190815156516146e-05, + "loss": 3.2412, "step": 59200 }, { "epoch": 0.2, - "learning_rate": 4.0190110042812813e-05, - "loss": 3.2651, + "learning_rate": 4.017424558752378e-05, + "loss": 3.2494, "step": 59300 }, { "epoch": 0.2, - "learning_rate": 4.017356722669614e-05, - "loss": 3.272, + "learning_rate": 4.015767601853141e-05, + "loss": 3.2526, "step": 59400 }, { "epoch": 0.2, - "learning_rate": 4.015702441057946e-05, - "loss": 3.2682, + "learning_rate": 4.014110644953904e-05, + "loss": 3.2332, "step": 59500 }, { "epoch": 0.2, - "learning_rate": 4.0140481594462794e-05, - "loss": 3.2834, + "learning_rate": 4.012453688054666e-05, + "loss": 3.2525, "step": 59600 }, { "epoch": 0.2, - "learning_rate": 4.012393877834612e-05, - "loss": 3.2768, + "learning_rate": 4.0107967311554296e-05, + "loss": 3.2355, "step": 59700 }, { "epoch": 0.2, - "learning_rate": 4.010739596222944e-05, - "loss": 3.2825, + "learning_rate": 4.009139774256192e-05, + "loss": 3.2361, "step": 59800 }, { "epoch": 0.2, - "learning_rate": 4.0090853146112774e-05, - "loss": 3.2888, + "learning_rate": 4.007482817356955e-05, + "loss": 3.2443, "step": 59900 }, { "epoch": 0.2, - "learning_rate": 4.00743103299961e-05, - "loss": 3.2852, + "learning_rate": 4.005825860457718e-05, + "loss": 3.2448, "step": 60000 }, { "epoch": 0.2, - "learning_rate": 4.005776751387942e-05, - "loss": 3.2733, + "learning_rate": 4.0041689035584806e-05, + "loss": 3.2373, "step": 60100 }, { "epoch": 0.2, - "learning_rate": 4.0041224697762755e-05, - "loss": 3.2694, + "learning_rate": 4.002511946659244e-05, + "loss": 3.2407, "step": 60200 }, { "epoch": 0.2, - "learning_rate": 4.002468188164607e-05, - "loss": 3.2803, + "learning_rate": 4.0008549897600064e-05, + "loss": 3.249, "step": 60300 }, { "epoch": 0.2, - "learning_rate": 4.0008139065529404e-05, - "loss": 3.2738, + "learning_rate": 3.999198032860769e-05, + "loss": 3.2453, "step": 60400 }, { "epoch": 0.2, - "learning_rate": 3.9991596249412735e-05, - "loss": 3.2809, + "learning_rate": 3.997541075961532e-05, + "loss": 3.2505, "step": 60500 }, { "epoch": 0.2, - "learning_rate": 3.997505343329606e-05, - "loss": 3.2728, + "learning_rate": 3.9958841190622955e-05, + "loss": 3.2409, "step": 60600 }, { "epoch": 0.2, - "learning_rate": 3.9958510617179384e-05, - "loss": 3.283, + "learning_rate": 3.994227162163058e-05, + "loss": 3.2438, "step": 60700 }, { "epoch": 0.2, - "learning_rate": 3.9941967801062715e-05, - "loss": 3.2633, + "learning_rate": 3.992570205263821e-05, + "loss": 3.2413, "step": 60800 }, { "epoch": 0.2, - "learning_rate": 3.992542498494604e-05, - "loss": 3.2739, + "learning_rate": 3.990913248364584e-05, + "loss": 3.2422, "step": 60900 }, { "epoch": 0.2, - "learning_rate": 3.9908882168829364e-05, - "loss": 3.2639, + "learning_rate": 3.9892562914653465e-05, + "loss": 3.2408, "step": 61000 }, { "epoch": 0.2, - "learning_rate": 3.9892339352712696e-05, - "loss": 3.2659, + "learning_rate": 3.987599334566109e-05, + "loss": 3.2549, "step": 61100 }, { "epoch": 0.2, - "learning_rate": 3.987579653659602e-05, - "loss": 3.2785, + "learning_rate": 3.9859423776668724e-05, + "loss": 3.2536, "step": 61200 }, { "epoch": 0.2, - "learning_rate": 3.9859253720479345e-05, - "loss": 3.2706, + "learning_rate": 3.984285420767635e-05, + "loss": 3.2476, "step": 61300 }, { "epoch": 0.2, - "learning_rate": 3.9842710904362676e-05, - "loss": 3.2732, + "learning_rate": 3.982628463868398e-05, + "loss": 3.2499, "step": 61400 }, { "epoch": 0.2, - "learning_rate": 3.9826168088246e-05, - "loss": 3.2764, + "learning_rate": 3.980971506969161e-05, + "loss": 3.2339, "step": 61500 }, { "epoch": 0.2, - "learning_rate": 3.9809625272129325e-05, - "loss": 3.2644, + "learning_rate": 3.9793145500699234e-05, + "loss": 3.2456, "step": 61600 }, { "epoch": 0.2, - "learning_rate": 3.9793082456012656e-05, - "loss": 3.2631, + "learning_rate": 3.9776575931706866e-05, + "loss": 3.2148, "step": 61700 }, { "epoch": 0.2, - "learning_rate": 3.977653963989598e-05, - "loss": 3.2846, + "learning_rate": 3.97600063627145e-05, + "loss": 3.2546, "step": 61800 }, { - "epoch": 0.2, - "learning_rate": 3.9759996823779306e-05, - "loss": 3.2645, + "epoch": 0.21, + "learning_rate": 3.9743436793722125e-05, + "loss": 3.2489, "step": 61900 }, { "epoch": 0.21, - "learning_rate": 3.974345400766264e-05, - "loss": 3.2657, + "learning_rate": 3.972686722472975e-05, + "loss": 3.2425, "step": 62000 }, { "epoch": 0.21, - "learning_rate": 3.972691119154596e-05, - "loss": 3.2847, + "learning_rate": 3.971029765573738e-05, + "loss": 3.243, "step": 62100 }, { "epoch": 0.21, - "learning_rate": 3.9710368375429286e-05, - "loss": 3.2714, + "learning_rate": 3.969372808674501e-05, + "loss": 3.2491, "step": 62200 }, { "epoch": 0.21, - "learning_rate": 3.969382555931262e-05, - "loss": 3.2759, + "learning_rate": 3.967715851775264e-05, + "loss": 3.2368, "step": 62300 }, { "epoch": 0.21, - "learning_rate": 3.967728274319594e-05, - "loss": 3.2859, + "learning_rate": 3.966058894876027e-05, + "loss": 3.2563, "step": 62400 }, { "epoch": 0.21, - "learning_rate": 3.966073992707927e-05, - "loss": 3.2691, + "learning_rate": 3.964401937976789e-05, + "loss": 3.2389, "step": 62500 }, { "epoch": 0.21, - "learning_rate": 3.96441971109626e-05, - "loss": 3.2632, + "learning_rate": 3.9627449810775526e-05, + "loss": 3.243, "step": 62600 }, { "epoch": 0.21, - "learning_rate": 3.962765429484592e-05, - "loss": 3.281, + "learning_rate": 3.961088024178315e-05, + "loss": 3.2594, "step": 62700 }, { "epoch": 0.21, - "learning_rate": 3.9611111478729253e-05, - "loss": 3.2685, + "learning_rate": 3.959431067279078e-05, + "loss": 3.2334, "step": 62800 }, { "epoch": 0.21, - "learning_rate": 3.959456866261257e-05, - "loss": 3.2606, + "learning_rate": 3.957774110379841e-05, + "loss": 3.2215, "step": 62900 }, { "epoch": 0.21, - "learning_rate": 3.95780258464959e-05, - "loss": 3.2632, + "learning_rate": 3.956117153480604e-05, + "loss": 3.2579, "step": 63000 }, { "epoch": 0.21, - "learning_rate": 3.9561483030379234e-05, - "loss": 3.2696, + "learning_rate": 3.954460196581367e-05, + "loss": 3.2352, "step": 63100 }, { "epoch": 0.21, - "learning_rate": 3.954494021426255e-05, - "loss": 3.2681, + "learning_rate": 3.9528032396821294e-05, + "loss": 3.2356, "step": 63200 }, { "epoch": 0.21, - "learning_rate": 3.952839739814588e-05, - "loss": 3.2706, + "learning_rate": 3.951146282782893e-05, + "loss": 3.2423, "step": 63300 }, { "epoch": 0.21, - "learning_rate": 3.9511854582029214e-05, - "loss": 3.2794, + "learning_rate": 3.949489325883655e-05, + "loss": 3.2382, "step": 63400 }, { "epoch": 0.21, - "learning_rate": 3.949531176591253e-05, - "loss": 3.246, + "learning_rate": 3.9478323689844185e-05, + "loss": 3.2387, "step": 63500 }, { "epoch": 0.21, - "learning_rate": 3.947876894979586e-05, - "loss": 3.2586, + "learning_rate": 3.946175412085181e-05, + "loss": 3.2456, "step": 63600 }, { "epoch": 0.21, - "learning_rate": 3.9462226133679195e-05, - "loss": 3.2695, + "learning_rate": 3.944518455185944e-05, + "loss": 3.2462, "step": 63700 }, { "epoch": 0.21, - "learning_rate": 3.944568331756251e-05, - "loss": 3.2706, + "learning_rate": 3.942861498286707e-05, + "loss": 3.236, "step": 63800 }, { "epoch": 0.21, - "learning_rate": 3.9429140501445844e-05, - "loss": 3.2697, + "learning_rate": 3.9412045413874695e-05, + "loss": 3.2431, "step": 63900 }, { "epoch": 0.21, - "learning_rate": 3.9412597685329175e-05, - "loss": 3.2794, + "learning_rate": 3.939547584488232e-05, + "loss": 3.2574, "step": 64000 }, { "epoch": 0.21, - "learning_rate": 3.939605486921249e-05, - "loss": 3.2611, + "learning_rate": 3.9378906275889954e-05, + "loss": 3.2494, "step": 64100 }, { "epoch": 0.21, - "learning_rate": 3.9379512053095824e-05, - "loss": 3.2624, + "learning_rate": 3.9362336706897586e-05, + "loss": 3.228, "step": 64200 }, { "epoch": 0.21, - "learning_rate": 3.9362969236979155e-05, - "loss": 3.2737, + "learning_rate": 3.934576713790521e-05, + "loss": 3.2459, "step": 64300 }, { "epoch": 0.21, - "learning_rate": 3.934642642086247e-05, - "loss": 3.2777, + "learning_rate": 3.932919756891284e-05, + "loss": 3.246, "step": 64400 }, { "epoch": 0.21, - "learning_rate": 3.9329883604745804e-05, - "loss": 3.2828, + "learning_rate": 3.931262799992047e-05, + "loss": 3.2319, "step": 64500 }, { "epoch": 0.21, - "learning_rate": 3.9313340788629136e-05, - "loss": 3.2732, + "learning_rate": 3.9296058430928096e-05, + "loss": 3.2416, "step": 64600 }, { "epoch": 0.21, - "learning_rate": 3.929679797251246e-05, - "loss": 3.2743, + "learning_rate": 3.927948886193573e-05, + "loss": 3.2388, "step": 64700 }, { "epoch": 0.21, - "learning_rate": 3.9280255156395785e-05, - "loss": 3.2719, + "learning_rate": 3.9262919292943355e-05, + "loss": 3.2518, "step": 64800 }, { - "epoch": 0.21, - "learning_rate": 3.9263712340279116e-05, - "loss": 3.271, + "epoch": 0.22, + "learning_rate": 3.924634972395098e-05, + "loss": 3.2544, "step": 64900 }, { "epoch": 0.22, - "learning_rate": 3.924716952416244e-05, - "loss": 3.2755, + "learning_rate": 3.922978015495861e-05, + "loss": 3.2276, "step": 65000 }, { "epoch": 0.22, - "learning_rate": 3.9230626708045765e-05, - "loss": 3.2623, + "learning_rate": 3.921321058596624e-05, + "loss": 3.2407, "step": 65100 }, { "epoch": 0.22, - "learning_rate": 3.9214083891929097e-05, - "loss": 3.2473, + "learning_rate": 3.9196641016973865e-05, + "loss": 3.2388, "step": 65200 }, { "epoch": 0.22, - "learning_rate": 3.919754107581242e-05, - "loss": 3.265, + "learning_rate": 3.91800714479815e-05, + "loss": 3.2347, "step": 65300 }, { "epoch": 0.22, - "learning_rate": 3.9180998259695746e-05, - "loss": 3.2639, + "learning_rate": 3.916350187898913e-05, + "loss": 3.23, "step": 65400 }, { "epoch": 0.22, - "learning_rate": 3.916445544357907e-05, - "loss": 3.2691, + "learning_rate": 3.9146932309996756e-05, + "loss": 3.256, "step": 65500 }, { "epoch": 0.22, - "learning_rate": 3.91479126274624e-05, - "loss": 3.2797, + "learning_rate": 3.913036274100438e-05, + "loss": 3.2215, "step": 65600 }, { "epoch": 0.22, - "learning_rate": 3.9131369811345726e-05, - "loss": 3.2732, + "learning_rate": 3.911379317201201e-05, + "loss": 3.2425, "step": 65700 }, { "epoch": 0.22, - "learning_rate": 3.911482699522905e-05, - "loss": 3.2771, + "learning_rate": 3.909722360301964e-05, + "loss": 3.238, "step": 65800 }, { "epoch": 0.22, - "learning_rate": 3.909828417911238e-05, - "loss": 3.2604, + "learning_rate": 3.908065403402727e-05, + "loss": 3.2399, "step": 65900 }, { "epoch": 0.22, - "learning_rate": 3.9081741362995706e-05, - "loss": 3.2633, + "learning_rate": 3.906408446503489e-05, + "loss": 3.2504, "step": 66000 }, { "epoch": 0.22, - "learning_rate": 3.906519854687903e-05, - "loss": 3.2683, + "learning_rate": 3.9047514896042524e-05, + "loss": 3.242, "step": 66100 }, { "epoch": 0.22, - "learning_rate": 3.904865573076236e-05, - "loss": 3.2574, + "learning_rate": 3.903094532705016e-05, + "loss": 3.227, "step": 66200 }, { "epoch": 0.22, - "learning_rate": 3.903211291464569e-05, - "loss": 3.2739, + "learning_rate": 3.901437575805778e-05, + "loss": 3.2359, "step": 66300 }, { "epoch": 0.22, - "learning_rate": 3.901557009852901e-05, - "loss": 3.2623, + "learning_rate": 3.899780618906541e-05, + "loss": 3.2384, "step": 66400 }, { "epoch": 0.22, - "learning_rate": 3.899902728241234e-05, - "loss": 3.2689, + "learning_rate": 3.898123662007304e-05, + "loss": 3.2398, "step": 66500 }, { "epoch": 0.22, - "learning_rate": 3.898248446629567e-05, - "loss": 3.2705, + "learning_rate": 3.896466705108067e-05, + "loss": 3.227, "step": 66600 }, { "epoch": 0.22, - "learning_rate": 3.896594165017899e-05, - "loss": 3.2755, + "learning_rate": 3.89480974820883e-05, + "loss": 3.2451, "step": 66700 }, { "epoch": 0.22, - "learning_rate": 3.894939883406232e-05, - "loss": 3.2826, + "learning_rate": 3.8931527913095925e-05, + "loss": 3.2433, "step": 66800 }, { "epoch": 0.22, - "learning_rate": 3.8932856017945654e-05, - "loss": 3.2878, + "learning_rate": 3.891495834410355e-05, + "loss": 3.2375, "step": 66900 }, { "epoch": 0.22, - "learning_rate": 3.891631320182897e-05, - "loss": 3.2755, + "learning_rate": 3.8898388775111184e-05, + "loss": 3.2454, "step": 67000 }, { "epoch": 0.22, - "learning_rate": 3.88997703857123e-05, - "loss": 3.2695, + "learning_rate": 3.8881819206118816e-05, + "loss": 3.2461, "step": 67100 }, { "epoch": 0.22, - "learning_rate": 3.8883227569595635e-05, - "loss": 3.2697, + "learning_rate": 3.8865249637126435e-05, + "loss": 3.2302, "step": 67200 }, { "epoch": 0.22, - "learning_rate": 3.886668475347895e-05, - "loss": 3.253, + "learning_rate": 3.884868006813407e-05, + "loss": 3.2354, "step": 67300 }, { "epoch": 0.22, - "learning_rate": 3.8850141937362284e-05, - "loss": 3.2783, + "learning_rate": 3.88321104991417e-05, + "loss": 3.2427, "step": 67400 }, { "epoch": 0.22, - "learning_rate": 3.8833599121245615e-05, - "loss": 3.2743, + "learning_rate": 3.8815540930149326e-05, + "loss": 3.2403, "step": 67500 }, { "epoch": 0.22, - "learning_rate": 3.881705630512893e-05, - "loss": 3.2665, + "learning_rate": 3.879897136115695e-05, + "loss": 3.2245, "step": 67600 }, { "epoch": 0.22, - "learning_rate": 3.8800513489012264e-05, - "loss": 3.2634, + "learning_rate": 3.8782401792164585e-05, + "loss": 3.2394, "step": 67700 }, { "epoch": 0.22, - "learning_rate": 3.8783970672895595e-05, - "loss": 3.2797, + "learning_rate": 3.876583222317221e-05, + "loss": 3.2532, "step": 67800 }, { - "epoch": 0.22, - "learning_rate": 3.876742785677891e-05, - "loss": 3.2621, + "epoch": 0.23, + "learning_rate": 3.874926265417984e-05, + "loss": 3.2535, "step": 67900 }, { - "epoch": 0.22, - "learning_rate": 3.8750885040662244e-05, - "loss": 3.2649, + "epoch": 0.23, + "learning_rate": 3.873269308518747e-05, + "loss": 3.2401, "step": 68000 }, { "epoch": 0.23, - "learning_rate": 3.873434222454557e-05, - "loss": 3.2647, + "learning_rate": 3.8716123516195095e-05, + "loss": 3.2349, "step": 68100 }, { "epoch": 0.23, - "learning_rate": 3.8717799408428894e-05, - "loss": 3.276, + "learning_rate": 3.869955394720273e-05, + "loss": 3.253, "step": 68200 }, { "epoch": 0.23, - "learning_rate": 3.8701256592312225e-05, - "loss": 3.2668, + "learning_rate": 3.868298437821036e-05, + "loss": 3.2332, "step": 68300 }, { "epoch": 0.23, - "learning_rate": 3.868471377619555e-05, - "loss": 3.2666, + "learning_rate": 3.866641480921798e-05, + "loss": 3.2401, "step": 68400 }, { "epoch": 0.23, - "learning_rate": 3.8668170960078874e-05, - "loss": 3.2688, + "learning_rate": 3.864984524022561e-05, + "loss": 3.2359, "step": 68500 }, { "epoch": 0.23, - "learning_rate": 3.8651628143962205e-05, - "loss": 3.2889, + "learning_rate": 3.8633275671233244e-05, + "loss": 3.2458, "step": 68600 }, { "epoch": 0.23, - "learning_rate": 3.863508532784553e-05, - "loss": 3.2787, + "learning_rate": 3.861670610224087e-05, + "loss": 3.2493, "step": 68700 }, { "epoch": 0.23, - "learning_rate": 3.8618542511728854e-05, - "loss": 3.2738, + "learning_rate": 3.8600136533248496e-05, + "loss": 3.2251, "step": 68800 }, { "epoch": 0.23, - "learning_rate": 3.8601999695612186e-05, - "loss": 3.256, + "learning_rate": 3.858356696425613e-05, + "loss": 3.2484, "step": 68900 }, { "epoch": 0.23, - "learning_rate": 3.858545687949551e-05, - "loss": 3.2739, + "learning_rate": 3.8566997395263754e-05, + "loss": 3.2424, "step": 69000 }, { "epoch": 0.23, - "learning_rate": 3.856891406337884e-05, - "loss": 3.2672, + "learning_rate": 3.855042782627139e-05, + "loss": 3.2317, "step": 69100 }, { "epoch": 0.23, - "learning_rate": 3.8552371247262166e-05, - "loss": 3.2561, + "learning_rate": 3.853385825727901e-05, + "loss": 3.2362, "step": 69200 }, { "epoch": 0.23, - "learning_rate": 3.853582843114549e-05, - "loss": 3.2633, + "learning_rate": 3.851728868828664e-05, + "loss": 3.2435, "step": 69300 }, { "epoch": 0.23, - "learning_rate": 3.851928561502882e-05, - "loss": 3.2617, + "learning_rate": 3.850071911929427e-05, + "loss": 3.2397, "step": 69400 }, { "epoch": 0.23, - "learning_rate": 3.8502742798912146e-05, - "loss": 3.2652, + "learning_rate": 3.8484149550301904e-05, + "loss": 3.2372, "step": 69500 }, { "epoch": 0.23, - "learning_rate": 3.848619998279547e-05, - "loss": 3.2603, + "learning_rate": 3.846757998130952e-05, + "loss": 3.2365, "step": 69600 }, { "epoch": 0.23, - "learning_rate": 3.84696571666788e-05, - "loss": 3.2748, + "learning_rate": 3.8451010412317155e-05, + "loss": 3.2557, "step": 69700 }, { "epoch": 0.23, - "learning_rate": 3.845311435056213e-05, - "loss": 3.2633, + "learning_rate": 3.843444084332479e-05, + "loss": 3.2363, "step": 69800 }, { "epoch": 0.23, - "learning_rate": 3.843657153444545e-05, - "loss": 3.2608, + "learning_rate": 3.8417871274332414e-05, + "loss": 3.2406, "step": 69900 }, { "epoch": 0.23, - "learning_rate": 3.842002871832878e-05, - "loss": 3.2812, + "learning_rate": 3.840130170534004e-05, + "loss": 3.2325, "step": 70000 }, { "epoch": 0.23, - "learning_rate": 3.840348590221211e-05, - "loss": 3.2775, + "learning_rate": 3.838473213634767e-05, + "loss": 3.2417, "step": 70100 }, { "epoch": 0.23, - "learning_rate": 3.838694308609543e-05, - "loss": 3.2708, + "learning_rate": 3.83681625673553e-05, + "loss": 3.2478, "step": 70200 }, { "epoch": 0.23, - "learning_rate": 3.837040026997876e-05, - "loss": 3.2529, + "learning_rate": 3.835159299836293e-05, + "loss": 3.2409, "step": 70300 }, { "epoch": 0.23, - "learning_rate": 3.835385745386209e-05, - "loss": 3.2715, + "learning_rate": 3.8335023429370556e-05, + "loss": 3.2449, "step": 70400 }, { "epoch": 0.23, - "learning_rate": 3.833731463774541e-05, - "loss": 3.2628, + "learning_rate": 3.831845386037818e-05, + "loss": 3.2395, "step": 70500 }, { "epoch": 0.23, - "learning_rate": 3.832077182162874e-05, - "loss": 3.2716, + "learning_rate": 3.8301884291385815e-05, + "loss": 3.2519, "step": 70600 }, { "epoch": 0.23, - "learning_rate": 3.830422900551207e-05, - "loss": 3.2707, + "learning_rate": 3.828531472239345e-05, + "loss": 3.235, "step": 70700 }, { "epoch": 0.23, - "learning_rate": 3.828768618939539e-05, - "loss": 3.2662, + "learning_rate": 3.8268745153401067e-05, + "loss": 3.2414, "step": 70800 }, { "epoch": 0.23, - "learning_rate": 3.8271143373278724e-05, - "loss": 3.2659, + "learning_rate": 3.82521755844087e-05, + "loss": 3.2598, "step": 70900 }, { - "epoch": 0.23, - "learning_rate": 3.825460055716205e-05, - "loss": 3.253, + "epoch": 0.24, + "learning_rate": 3.823560601541633e-05, + "loss": 3.2426, "step": 71000 }, { "epoch": 0.24, - "learning_rate": 3.823805774104537e-05, - "loss": 3.2676, + "learning_rate": 3.821903644642396e-05, + "loss": 3.2473, "step": 71100 }, { "epoch": 0.24, - "learning_rate": 3.8221514924928704e-05, - "loss": 3.2615, + "learning_rate": 3.820246687743158e-05, + "loss": 3.2395, "step": 71200 }, { "epoch": 0.24, - "learning_rate": 3.820497210881203e-05, - "loss": 3.2812, + "learning_rate": 3.8185897308439216e-05, + "loss": 3.2264, "step": 71300 }, { "epoch": 0.24, - "learning_rate": 3.818842929269535e-05, - "loss": 3.2681, + "learning_rate": 3.816932773944684e-05, + "loss": 3.2459, "step": 71400 }, { "epoch": 0.24, - "learning_rate": 3.8171886476578684e-05, - "loss": 3.2791, + "learning_rate": 3.8152758170454474e-05, + "loss": 3.2449, "step": 71500 }, { "epoch": 0.24, - "learning_rate": 3.815534366046201e-05, - "loss": 3.2443, + "learning_rate": 3.81361886014621e-05, + "loss": 3.2336, "step": 71600 }, { "epoch": 0.24, - "learning_rate": 3.8138800844345334e-05, - "loss": 3.2713, + "learning_rate": 3.8119619032469726e-05, + "loss": 3.2412, "step": 71700 }, { "epoch": 0.24, - "learning_rate": 3.8122258028228665e-05, - "loss": 3.2527, + "learning_rate": 3.810304946347736e-05, + "loss": 3.253, "step": 71800 }, { "epoch": 0.24, - "learning_rate": 3.810571521211199e-05, - "loss": 3.2694, + "learning_rate": 3.808647989448499e-05, + "loss": 3.2446, "step": 71900 }, { "epoch": 0.24, - "learning_rate": 3.8089172395995314e-05, - "loss": 3.2703, + "learning_rate": 3.806991032549262e-05, + "loss": 3.2455, "step": 72000 }, { "epoch": 0.24, - "learning_rate": 3.8072629579878645e-05, - "loss": 3.2746, + "learning_rate": 3.805334075650024e-05, + "loss": 3.2407, "step": 72100 }, { "epoch": 0.24, - "learning_rate": 3.805608676376197e-05, - "loss": 3.2656, + "learning_rate": 3.8036771187507875e-05, + "loss": 3.2333, "step": 72200 }, { "epoch": 0.24, - "learning_rate": 3.8039543947645294e-05, - "loss": 3.2604, + "learning_rate": 3.80202016185155e-05, + "loss": 3.2358, "step": 72300 }, { "epoch": 0.24, - "learning_rate": 3.8023001131528626e-05, - "loss": 3.2676, + "learning_rate": 3.800363204952313e-05, + "loss": 3.24, "step": 72400 }, { "epoch": 0.24, - "learning_rate": 3.800645831541195e-05, - "loss": 3.2658, + "learning_rate": 3.798706248053076e-05, + "loss": 3.2246, "step": 72500 }, { "epoch": 0.24, - "learning_rate": 3.7989915499295275e-05, - "loss": 3.2714, + "learning_rate": 3.7970492911538385e-05, + "loss": 3.2363, "step": 72600 }, { "epoch": 0.24, - "learning_rate": 3.7973372683178606e-05, - "loss": 3.2689, + "learning_rate": 3.795392334254602e-05, + "loss": 3.2273, "step": 72700 }, { "epoch": 0.24, - "learning_rate": 3.795682986706193e-05, - "loss": 3.275, + "learning_rate": 3.7937353773553644e-05, + "loss": 3.2304, "step": 72800 }, { "epoch": 0.24, - "learning_rate": 3.7940287050945255e-05, - "loss": 3.2748, + "learning_rate": 3.792078420456127e-05, + "loss": 3.2442, "step": 72900 }, { "epoch": 0.24, - "learning_rate": 3.7923744234828586e-05, - "loss": 3.2614, + "learning_rate": 3.79042146355689e-05, + "loss": 3.2451, "step": 73000 }, { "epoch": 0.24, - "learning_rate": 3.790720141871191e-05, - "loss": 3.2676, + "learning_rate": 3.7887645066576535e-05, + "loss": 3.2503, "step": 73100 }, { "epoch": 0.24, - "learning_rate": 3.789065860259524e-05, - "loss": 3.2591, + "learning_rate": 3.787107549758416e-05, + "loss": 3.2374, "step": 73200 }, { "epoch": 0.24, - "learning_rate": 3.787411578647857e-05, - "loss": 3.2653, + "learning_rate": 3.7854505928591787e-05, + "loss": 3.228, "step": 73300 }, { "epoch": 0.24, - "learning_rate": 3.785757297036189e-05, - "loss": 3.2654, + "learning_rate": 3.783793635959942e-05, + "loss": 3.2312, "step": 73400 }, { "epoch": 0.24, - "learning_rate": 3.784103015424522e-05, - "loss": 3.2677, + "learning_rate": 3.7821366790607045e-05, + "loss": 3.2332, "step": 73500 }, { "epoch": 0.24, - "learning_rate": 3.782448733812855e-05, - "loss": 3.2579, + "learning_rate": 3.780479722161467e-05, + "loss": 3.2484, "step": 73600 }, { "epoch": 0.24, - "learning_rate": 3.780794452201187e-05, - "loss": 3.2727, + "learning_rate": 3.77882276526223e-05, + "loss": 3.2383, "step": 73700 }, { "epoch": 0.24, - "learning_rate": 3.77914017058952e-05, - "loss": 3.2725, + "learning_rate": 3.777165808362993e-05, + "loss": 3.2439, "step": 73800 }, { "epoch": 0.24, - "learning_rate": 3.777485888977853e-05, - "loss": 3.2587, + "learning_rate": 3.775508851463756e-05, + "loss": 3.2455, "step": 73900 }, { - "epoch": 0.24, - "learning_rate": 3.775831607366185e-05, - "loss": 3.2678, + "epoch": 0.25, + "learning_rate": 3.773851894564519e-05, + "loss": 3.2369, "step": 74000 }, { "epoch": 0.25, - "learning_rate": 3.774177325754518e-05, - "loss": 3.2609, + "learning_rate": 3.772194937665281e-05, + "loss": 3.2377, "step": 74100 }, { "epoch": 0.25, - "learning_rate": 3.772523044142851e-05, - "loss": 3.2693, + "learning_rate": 3.7705379807660446e-05, + "loss": 3.2421, "step": 74200 }, { "epoch": 0.25, - "learning_rate": 3.770868762531183e-05, - "loss": 3.2631, + "learning_rate": 3.768881023866807e-05, + "loss": 3.244, "step": 74300 }, { "epoch": 0.25, - "learning_rate": 3.7692144809195164e-05, - "loss": 3.271, + "learning_rate": 3.7672240669675704e-05, + "loss": 3.2479, "step": 74400 }, { "epoch": 0.25, - "learning_rate": 3.767560199307849e-05, - "loss": 3.2663, + "learning_rate": 3.765567110068333e-05, + "loss": 3.2367, "step": 74500 }, { "epoch": 0.25, - "learning_rate": 3.765905917696181e-05, - "loss": 3.2671, + "learning_rate": 3.7639101531690956e-05, + "loss": 3.2384, "step": 74600 }, { "epoch": 0.25, - "learning_rate": 3.7642516360845144e-05, - "loss": 3.2716, + "learning_rate": 3.762253196269859e-05, + "loss": 3.2461, "step": 74700 }, { "epoch": 0.25, - "learning_rate": 3.762597354472847e-05, - "loss": 3.2721, + "learning_rate": 3.7605962393706214e-05, + "loss": 3.2371, "step": 74800 }, { "epoch": 0.25, - "learning_rate": 3.760943072861179e-05, - "loss": 3.2634, + "learning_rate": 3.758939282471384e-05, + "loss": 3.2354, "step": 74900 }, { "epoch": 0.25, - "learning_rate": 3.7592887912495125e-05, - "loss": 3.2766, + "learning_rate": 3.757282325572147e-05, + "loss": 3.2274, "step": 75000 }, { "epoch": 0.25, - "learning_rate": 3.757634509637845e-05, - "loss": 3.2582, + "learning_rate": 3.7556253686729105e-05, + "loss": 3.2474, "step": 75100 }, { "epoch": 0.25, - "learning_rate": 3.7559802280261774e-05, - "loss": 3.265, + "learning_rate": 3.753968411773673e-05, + "loss": 3.2328, "step": 75200 }, { "epoch": 0.25, - "learning_rate": 3.7543259464145105e-05, - "loss": 3.2603, + "learning_rate": 3.752311454874436e-05, + "loss": 3.248, "step": 75300 }, { "epoch": 0.25, - "learning_rate": 3.752671664802843e-05, - "loss": 3.2786, + "learning_rate": 3.750654497975199e-05, + "loss": 3.2355, "step": 75400 }, { "epoch": 0.25, - "learning_rate": 3.7510173831911754e-05, - "loss": 3.2608, + "learning_rate": 3.7489975410759615e-05, + "loss": 3.2228, "step": 75500 }, { "epoch": 0.25, - "learning_rate": 3.7493631015795085e-05, - "loss": 3.2588, + "learning_rate": 3.747340584176725e-05, + "loss": 3.2439, "step": 75600 }, { "epoch": 0.25, - "learning_rate": 3.747708819967841e-05, - "loss": 3.2619, + "learning_rate": 3.7456836272774874e-05, + "loss": 3.236, "step": 75700 }, { "epoch": 0.25, - "learning_rate": 3.7460545383561734e-05, - "loss": 3.2648, + "learning_rate": 3.74402667037825e-05, + "loss": 3.2324, "step": 75800 }, { "epoch": 0.25, - "learning_rate": 3.7444002567445066e-05, - "loss": 3.2686, + "learning_rate": 3.742369713479013e-05, + "loss": 3.2345, "step": 75900 }, { "epoch": 0.25, - "learning_rate": 3.742745975132839e-05, - "loss": 3.2578, + "learning_rate": 3.7407127565797765e-05, + "loss": 3.2541, "step": 76000 }, { "epoch": 0.25, - "learning_rate": 3.7410916935211715e-05, - "loss": 3.2858, + "learning_rate": 3.7390557996805384e-05, + "loss": 3.2353, "step": 76100 }, { "epoch": 0.25, - "learning_rate": 3.7394374119095046e-05, - "loss": 3.2529, + "learning_rate": 3.7373988427813017e-05, + "loss": 3.2357, "step": 76200 }, { "epoch": 0.25, - "learning_rate": 3.737783130297837e-05, - "loss": 3.2609, + "learning_rate": 3.735741885882065e-05, + "loss": 3.2395, "step": 76300 }, { "epoch": 0.25, - "learning_rate": 3.7361288486861695e-05, - "loss": 3.2576, + "learning_rate": 3.7340849289828275e-05, + "loss": 3.2267, "step": 76400 }, { "epoch": 0.25, - "learning_rate": 3.7344745670745026e-05, - "loss": 3.2568, + "learning_rate": 3.73242797208359e-05, + "loss": 3.2452, "step": 76500 }, { "epoch": 0.25, - "learning_rate": 3.732820285462835e-05, - "loss": 3.2537, + "learning_rate": 3.730771015184353e-05, + "loss": 3.2364, "step": 76600 }, { "epoch": 0.25, - "learning_rate": 3.7311660038511675e-05, - "loss": 3.2653, + "learning_rate": 3.729114058285116e-05, + "loss": 3.236, "step": 76700 }, { "epoch": 0.25, - "learning_rate": 3.729511722239501e-05, - "loss": 3.2641, + "learning_rate": 3.727457101385879e-05, + "loss": 3.2322, "step": 76800 }, { "epoch": 0.25, - "learning_rate": 3.727857440627833e-05, - "loss": 3.2592, + "learning_rate": 3.725800144486642e-05, + "loss": 3.2505, "step": 76900 }, { - "epoch": 0.25, - "learning_rate": 3.7262031590161656e-05, - "loss": 3.2692, + "epoch": 0.26, + "learning_rate": 3.7241431875874043e-05, + "loss": 3.2449, "step": 77000 }, { "epoch": 0.26, - "learning_rate": 3.724548877404499e-05, - "loss": 3.2643, + "learning_rate": 3.7224862306881676e-05, + "loss": 3.241, "step": 77100 }, { "epoch": 0.26, - "learning_rate": 3.722894595792831e-05, - "loss": 3.2477, + "learning_rate": 3.720829273788931e-05, + "loss": 3.2367, "step": 77200 }, { "epoch": 0.26, - "learning_rate": 3.7212403141811636e-05, - "loss": 3.2741, + "learning_rate": 3.719172316889693e-05, + "loss": 3.2389, "step": 77300 }, { "epoch": 0.26, - "learning_rate": 3.719586032569497e-05, - "loss": 3.2808, + "learning_rate": 3.717515359990456e-05, + "loss": 3.2345, "step": 77400 }, { "epoch": 0.26, - "learning_rate": 3.717931750957829e-05, - "loss": 3.2613, + "learning_rate": 3.715858403091219e-05, + "loss": 3.2427, "step": 77500 }, { "epoch": 0.26, - "learning_rate": 3.7162774693461623e-05, - "loss": 3.2563, + "learning_rate": 3.714201446191982e-05, + "loss": 3.2475, "step": 77600 }, { "epoch": 0.26, - "learning_rate": 3.714623187734495e-05, - "loss": 3.2537, + "learning_rate": 3.7125444892927444e-05, + "loss": 3.2406, "step": 77700 }, { "epoch": 0.26, - "learning_rate": 3.712968906122827e-05, - "loss": 3.2654, + "learning_rate": 3.710887532393508e-05, + "loss": 3.222, "step": 77800 }, { "epoch": 0.26, - "learning_rate": 3.7113146245111604e-05, - "loss": 3.2727, + "learning_rate": 3.70923057549427e-05, + "loss": 3.2439, "step": 77900 }, { "epoch": 0.26, - "learning_rate": 3.709660342899492e-05, - "loss": 3.2664, + "learning_rate": 3.7075736185950335e-05, + "loss": 3.2342, "step": 78000 }, { "epoch": 0.26, - "learning_rate": 3.708006061287825e-05, - "loss": 3.2765, + "learning_rate": 3.705916661695796e-05, + "loss": 3.2255, "step": 78100 }, { "epoch": 0.26, - "learning_rate": 3.7063517796761584e-05, - "loss": 3.2702, + "learning_rate": 3.704259704796559e-05, + "loss": 3.2257, "step": 78200 }, { "epoch": 0.26, - "learning_rate": 3.70469749806449e-05, - "loss": 3.2621, + "learning_rate": 3.702602747897322e-05, + "loss": 3.2324, "step": 78300 }, { "epoch": 0.26, - "learning_rate": 3.703043216452823e-05, - "loss": 3.2577, + "learning_rate": 3.700945790998085e-05, + "loss": 3.2483, "step": 78400 }, { "epoch": 0.26, - "learning_rate": 3.7013889348411565e-05, - "loss": 3.2605, + "learning_rate": 3.699288834098847e-05, + "loss": 3.2338, "step": 78500 }, { "epoch": 0.26, - "learning_rate": 3.699734653229488e-05, - "loss": 3.27, + "learning_rate": 3.6976318771996104e-05, + "loss": 3.23, "step": 78600 }, { "epoch": 0.26, - "learning_rate": 3.6980803716178214e-05, - "loss": 3.2683, + "learning_rate": 3.6959749203003737e-05, + "loss": 3.2255, "step": 78700 }, { "epoch": 0.26, - "learning_rate": 3.6964260900061545e-05, - "loss": 3.2716, + "learning_rate": 3.694317963401136e-05, + "loss": 3.2307, "step": 78800 }, { "epoch": 0.26, - "learning_rate": 3.694771808394486e-05, - "loss": 3.2534, + "learning_rate": 3.692661006501899e-05, + "loss": 3.2296, "step": 78900 }, { "epoch": 0.26, - "learning_rate": 3.6931175267828194e-05, - "loss": 3.2561, + "learning_rate": 3.691004049602662e-05, + "loss": 3.2394, "step": 79000 }, { "epoch": 0.26, - "learning_rate": 3.6914632451711525e-05, - "loss": 3.2701, + "learning_rate": 3.6893470927034247e-05, + "loss": 3.2359, "step": 79100 }, { "epoch": 0.26, - "learning_rate": 3.689808963559484e-05, - "loss": 3.2741, + "learning_rate": 3.687690135804188e-05, + "loss": 3.226, "step": 79200 }, { "epoch": 0.26, - "learning_rate": 3.6881546819478174e-05, - "loss": 3.2624, + "learning_rate": 3.6860331789049505e-05, + "loss": 3.226, "step": 79300 }, { "epoch": 0.26, - "learning_rate": 3.6865004003361506e-05, - "loss": 3.2695, + "learning_rate": 3.684376222005713e-05, + "loss": 3.2304, "step": 79400 }, { "epoch": 0.26, - "learning_rate": 3.684846118724483e-05, - "loss": 3.2583, + "learning_rate": 3.682719265106476e-05, + "loss": 3.2466, "step": 79500 }, { "epoch": 0.26, - "learning_rate": 3.6831918371128155e-05, - "loss": 3.2651, + "learning_rate": 3.6810623082072396e-05, + "loss": 3.2235, "step": 79600 }, { "epoch": 0.26, - "learning_rate": 3.6815375555011486e-05, - "loss": 3.2663, + "learning_rate": 3.6794053513080015e-05, + "loss": 3.2425, "step": 79700 }, { "epoch": 0.26, - "learning_rate": 3.679883273889481e-05, - "loss": 3.2697, + "learning_rate": 3.677748394408765e-05, + "loss": 3.2322, "step": 79800 }, { "epoch": 0.26, - "learning_rate": 3.6782289922778135e-05, - "loss": 3.2784, + "learning_rate": 3.676091437509528e-05, + "loss": 3.2492, "step": 79900 }, { - "epoch": 0.26, - "learning_rate": 3.6765747106661466e-05, - "loss": 3.2727, + "epoch": 0.27, + "learning_rate": 3.6744344806102906e-05, + "loss": 3.2154, "step": 80000 }, { "epoch": 0.27, - "learning_rate": 3.674920429054479e-05, - "loss": 3.2633, + "learning_rate": 3.672777523711053e-05, + "loss": 3.2329, "step": 80100 }, { "epoch": 0.27, - "learning_rate": 3.6732661474428116e-05, - "loss": 3.2647, + "learning_rate": 3.6711205668118164e-05, + "loss": 3.2245, "step": 80200 }, { "epoch": 0.27, - "learning_rate": 3.671611865831145e-05, - "loss": 3.2597, + "learning_rate": 3.669463609912579e-05, + "loss": 3.2259, "step": 80300 }, { "epoch": 0.27, - "learning_rate": 3.669957584219477e-05, - "loss": 3.2713, + "learning_rate": 3.667806653013342e-05, + "loss": 3.2383, "step": 80400 }, { "epoch": 0.27, - "learning_rate": 3.6683033026078096e-05, - "loss": 3.2642, + "learning_rate": 3.666149696114105e-05, + "loss": 3.2398, "step": 80500 }, { "epoch": 0.27, - "learning_rate": 3.666649020996143e-05, - "loss": 3.2745, + "learning_rate": 3.6644927392148674e-05, + "loss": 3.238, "step": 80600 }, { "epoch": 0.27, - "learning_rate": 3.664994739384475e-05, - "loss": 3.2671, + "learning_rate": 3.662835782315631e-05, + "loss": 3.2296, "step": 80700 }, { "epoch": 0.27, - "learning_rate": 3.6633404577728076e-05, - "loss": 3.2692, + "learning_rate": 3.661178825416394e-05, + "loss": 3.2399, "step": 80800 }, { "epoch": 0.27, - "learning_rate": 3.66168617616114e-05, - "loss": 3.2746, + "learning_rate": 3.659521868517156e-05, + "loss": 3.2414, "step": 80900 }, { "epoch": 0.27, - "learning_rate": 3.660031894549473e-05, - "loss": 3.273, + "learning_rate": 3.657864911617919e-05, + "loss": 3.227, "step": 81000 }, { "epoch": 0.27, - "learning_rate": 3.658377612937806e-05, - "loss": 3.2685, + "learning_rate": 3.6562079547186824e-05, + "loss": 3.2409, "step": 81100 }, { "epoch": 0.27, - "learning_rate": 3.656723331326138e-05, - "loss": 3.2648, + "learning_rate": 3.654550997819445e-05, + "loss": 3.2261, "step": 81200 }, { "epoch": 0.27, - "learning_rate": 3.655069049714471e-05, - "loss": 3.2646, + "learning_rate": 3.6528940409202076e-05, + "loss": 3.2448, "step": 81300 }, { "epoch": 0.27, - "learning_rate": 3.653414768102804e-05, - "loss": 3.267, + "learning_rate": 3.651237084020971e-05, + "loss": 3.2423, "step": 81400 }, { "epoch": 0.27, - "learning_rate": 3.651760486491136e-05, - "loss": 3.2648, + "learning_rate": 3.6495801271217334e-05, + "loss": 3.2332, "step": 81500 }, { "epoch": 0.27, - "learning_rate": 3.650106204879469e-05, - "loss": 3.2617, + "learning_rate": 3.6479231702224967e-05, + "loss": 3.2424, "step": 81600 }, { "epoch": 0.27, - "learning_rate": 3.6484519232678024e-05, - "loss": 3.2792, + "learning_rate": 3.646266213323259e-05, + "loss": 3.2406, "step": 81700 }, { "epoch": 0.27, - "learning_rate": 3.646797641656134e-05, - "loss": 3.2633, + "learning_rate": 3.644609256424022e-05, + "loss": 3.2445, "step": 81800 }, { "epoch": 0.27, - "learning_rate": 3.645143360044467e-05, - "loss": 3.2639, + "learning_rate": 3.642952299524785e-05, + "loss": 3.2361, "step": 81900 }, { "epoch": 0.27, - "learning_rate": 3.6434890784328005e-05, - "loss": 3.2649, + "learning_rate": 3.641295342625548e-05, + "loss": 3.2543, "step": 82000 }, { "epoch": 0.27, - "learning_rate": 3.641834796821132e-05, - "loss": 3.2688, + "learning_rate": 3.63963838572631e-05, + "loss": 3.2461, "step": 82100 }, { "epoch": 0.27, - "learning_rate": 3.6401805152094654e-05, - "loss": 3.2652, + "learning_rate": 3.6379814288270735e-05, + "loss": 3.2281, "step": 82200 }, { "epoch": 0.27, - "learning_rate": 3.6385262335977985e-05, - "loss": 3.2708, + "learning_rate": 3.636324471927837e-05, + "loss": 3.2322, "step": 82300 }, { "epoch": 0.27, - "learning_rate": 3.63687195198613e-05, - "loss": 3.2851, + "learning_rate": 3.6346675150285993e-05, + "loss": 3.2337, "step": 82400 }, { "epoch": 0.27, - "learning_rate": 3.6352176703744634e-05, - "loss": 3.2653, + "learning_rate": 3.633010558129362e-05, + "loss": 3.2371, "step": 82500 }, { "epoch": 0.27, - "learning_rate": 3.6335633887627965e-05, - "loss": 3.2717, + "learning_rate": 3.631353601230125e-05, + "loss": 3.2533, "step": 82600 }, { "epoch": 0.27, - "learning_rate": 3.631909107151128e-05, - "loss": 3.2662, + "learning_rate": 3.629696644330888e-05, + "loss": 3.226, "step": 82700 }, { "epoch": 0.27, - "learning_rate": 3.6302548255394614e-05, - "loss": 3.2613, + "learning_rate": 3.628039687431651e-05, + "loss": 3.2352, "step": 82800 }, { "epoch": 0.27, - "learning_rate": 3.6286005439277946e-05, - "loss": 3.2617, + "learning_rate": 3.6263827305324136e-05, + "loss": 3.2253, "step": 82900 }, { - "epoch": 0.27, - "learning_rate": 3.6269462623161263e-05, - "loss": 3.2712, + "epoch": 0.28, + "learning_rate": 3.624725773633176e-05, + "loss": 3.2402, "step": 83000 }, { - "epoch": 0.27, - "learning_rate": 3.6252919807044595e-05, - "loss": 3.2493, + "epoch": 0.28, + "learning_rate": 3.6230688167339394e-05, + "loss": 3.2427, "step": 83100 }, { "epoch": 0.28, - "learning_rate": 3.6236376990927926e-05, - "loss": 3.2509, + "learning_rate": 3.621411859834702e-05, + "loss": 3.235, "step": 83200 }, { "epoch": 0.28, - "learning_rate": 3.6219834174811244e-05, - "loss": 3.2757, + "learning_rate": 3.6197549029354646e-05, + "loss": 3.2475, "step": 83300 }, { "epoch": 0.28, - "learning_rate": 3.6203291358694575e-05, - "loss": 3.2585, + "learning_rate": 3.618097946036228e-05, + "loss": 3.2205, "step": 83400 }, { "epoch": 0.28, - "learning_rate": 3.61867485425779e-05, - "loss": 3.2671, + "learning_rate": 3.6164409891369904e-05, + "loss": 3.2287, "step": 83500 }, { "epoch": 0.28, - "learning_rate": 3.6170205726461224e-05, - "loss": 3.2674, + "learning_rate": 3.614784032237754e-05, + "loss": 3.2393, "step": 83600 }, { "epoch": 0.28, - "learning_rate": 3.6153662910344556e-05, - "loss": 3.2688, + "learning_rate": 3.613127075338516e-05, + "loss": 3.2321, "step": 83700 }, { "epoch": 0.28, - "learning_rate": 3.613712009422788e-05, - "loss": 3.2623, + "learning_rate": 3.611470118439279e-05, + "loss": 3.235, "step": 83800 }, { "epoch": 0.28, - "learning_rate": 3.612057727811121e-05, - "loss": 3.2566, + "learning_rate": 3.609813161540042e-05, + "loss": 3.2487, "step": 83900 }, { "epoch": 0.28, - "learning_rate": 3.6104034461994536e-05, - "loss": 3.2667, + "learning_rate": 3.6081562046408054e-05, + "loss": 3.2423, "step": 84000 }, { "epoch": 0.28, - "learning_rate": 3.608749164587786e-05, - "loss": 3.2525, + "learning_rate": 3.606499247741568e-05, + "loss": 3.2177, "step": 84100 }, { "epoch": 0.28, - "learning_rate": 3.607094882976119e-05, - "loss": 3.2731, + "learning_rate": 3.6048422908423306e-05, + "loss": 3.2359, "step": 84200 }, { "epoch": 0.28, - "learning_rate": 3.6054406013644516e-05, - "loss": 3.2526, + "learning_rate": 3.603185333943094e-05, + "loss": 3.235, "step": 84300 }, { "epoch": 0.28, - "learning_rate": 3.603786319752784e-05, - "loss": 3.2642, + "learning_rate": 3.6015283770438564e-05, + "loss": 3.236, "step": 84400 }, { "epoch": 0.28, - "learning_rate": 3.602132038141117e-05, - "loss": 3.2553, + "learning_rate": 3.599871420144619e-05, + "loss": 3.2437, "step": 84500 }, { "epoch": 0.28, - "learning_rate": 3.60047775652945e-05, - "loss": 3.2642, + "learning_rate": 3.598214463245382e-05, + "loss": 3.2359, "step": 84600 }, { "epoch": 0.28, - "learning_rate": 3.598823474917782e-05, - "loss": 3.2649, + "learning_rate": 3.596557506346145e-05, + "loss": 3.235, "step": 84700 }, { "epoch": 0.28, - "learning_rate": 3.597169193306115e-05, - "loss": 3.2608, + "learning_rate": 3.594900549446908e-05, + "loss": 3.2456, "step": 84800 }, { "epoch": 0.28, - "learning_rate": 3.595514911694448e-05, - "loss": 3.2602, + "learning_rate": 3.5932435925476707e-05, + "loss": 3.2526, "step": 84900 }, { "epoch": 0.28, - "learning_rate": 3.59386063008278e-05, - "loss": 3.2572, + "learning_rate": 3.591586635648433e-05, + "loss": 3.2429, "step": 85000 }, { "epoch": 0.28, - "learning_rate": 3.592206348471113e-05, - "loss": 3.2625, + "learning_rate": 3.5899296787491965e-05, + "loss": 3.2268, "step": 85100 }, { "epoch": 0.28, - "learning_rate": 3.590552066859446e-05, - "loss": 3.2632, + "learning_rate": 3.58827272184996e-05, + "loss": 3.2352, "step": 85200 }, { "epoch": 0.28, - "learning_rate": 3.588897785247778e-05, - "loss": 3.2539, + "learning_rate": 3.5866157649507223e-05, + "loss": 3.2318, "step": 85300 }, { "epoch": 0.28, - "learning_rate": 3.587243503636111e-05, - "loss": 3.2657, + "learning_rate": 3.584958808051485e-05, + "loss": 3.2366, "step": 85400 }, { "epoch": 0.28, - "learning_rate": 3.585589222024444e-05, - "loss": 3.2631, + "learning_rate": 3.583301851152248e-05, + "loss": 3.2355, "step": 85500 }, { "epoch": 0.28, - "learning_rate": 3.583934940412776e-05, - "loss": 3.2696, + "learning_rate": 3.581644894253011e-05, + "loss": 3.236, "step": 85600 }, { "epoch": 0.28, - "learning_rate": 3.5822806588011094e-05, - "loss": 3.2661, + "learning_rate": 3.579987937353774e-05, + "loss": 3.2272, "step": 85700 }, { "epoch": 0.28, - "learning_rate": 3.5806263771894425e-05, - "loss": 3.2719, + "learning_rate": 3.5783309804545366e-05, + "loss": 3.2345, "step": 85800 }, { "epoch": 0.28, - "learning_rate": 3.578972095577774e-05, - "loss": 3.2622, + "learning_rate": 3.576674023555299e-05, + "loss": 3.2274, "step": 85900 }, { "epoch": 0.28, - "learning_rate": 3.5773178139661074e-05, - "loss": 3.2554, + "learning_rate": 3.5750170666560624e-05, + "loss": 3.2409, "step": 86000 }, { - "epoch": 0.28, - "learning_rate": 3.57566353235444e-05, - "loss": 3.2551, + "epoch": 0.29, + "learning_rate": 3.573360109756825e-05, + "loss": 3.2405, "step": 86100 }, { "epoch": 0.29, - "learning_rate": 3.574009250742772e-05, - "loss": 3.2581, + "learning_rate": 3.5717031528575876e-05, + "loss": 3.2357, "step": 86200 }, { "epoch": 0.29, - "learning_rate": 3.5723549691311054e-05, - "loss": 3.2558, + "learning_rate": 3.570046195958351e-05, + "loss": 3.2326, "step": 86300 }, { "epoch": 0.29, - "learning_rate": 3.570700687519438e-05, - "loss": 3.266, + "learning_rate": 3.568389239059114e-05, + "loss": 3.2339, "step": 86400 }, { "epoch": 0.29, - "learning_rate": 3.5690464059077703e-05, - "loss": 3.2681, + "learning_rate": 3.566732282159877e-05, + "loss": 3.229, "step": 86500 }, { "epoch": 0.29, - "learning_rate": 3.5673921242961035e-05, - "loss": 3.2486, + "learning_rate": 3.565075325260639e-05, + "loss": 3.2422, "step": 86600 }, { "epoch": 0.29, - "learning_rate": 3.565737842684436e-05, - "loss": 3.2682, + "learning_rate": 3.5634183683614026e-05, + "loss": 3.2494, "step": 86700 }, { "epoch": 0.29, - "learning_rate": 3.5640835610727684e-05, - "loss": 3.2613, + "learning_rate": 3.561761411462165e-05, + "loss": 3.2374, "step": 86800 }, { "epoch": 0.29, - "learning_rate": 3.5624292794611015e-05, - "loss": 3.2576, + "learning_rate": 3.5601044545629284e-05, + "loss": 3.237, "step": 86900 }, { "epoch": 0.29, - "learning_rate": 3.560774997849434e-05, - "loss": 3.2673, + "learning_rate": 3.558447497663691e-05, + "loss": 3.2399, "step": 87000 }, { "epoch": 0.29, - "learning_rate": 3.5591207162377664e-05, - "loss": 3.2628, + "learning_rate": 3.5567905407644536e-05, + "loss": 3.2357, "step": 87100 }, { "epoch": 0.29, - "learning_rate": 3.5574664346260996e-05, - "loss": 3.2512, + "learning_rate": 3.555133583865217e-05, + "loss": 3.255, "step": 87200 }, { "epoch": 0.29, - "learning_rate": 3.555812153014432e-05, - "loss": 3.2615, + "learning_rate": 3.5534766269659794e-05, + "loss": 3.2318, "step": 87300 }, { "epoch": 0.29, - "learning_rate": 3.5541578714027645e-05, - "loss": 3.26, + "learning_rate": 3.551819670066742e-05, + "loss": 3.2317, "step": 87400 }, { "epoch": 0.29, - "learning_rate": 3.5525035897910976e-05, - "loss": 3.2657, + "learning_rate": 3.550162713167505e-05, + "loss": 3.2398, "step": 87500 }, { "epoch": 0.29, - "learning_rate": 3.55084930817943e-05, - "loss": 3.2586, + "learning_rate": 3.5485057562682685e-05, + "loss": 3.2272, "step": 87600 }, { "epoch": 0.29, - "learning_rate": 3.5491950265677625e-05, - "loss": 3.2655, + "learning_rate": 3.546848799369031e-05, + "loss": 3.2349, "step": 87700 }, { "epoch": 0.29, - "learning_rate": 3.5475407449560956e-05, - "loss": 3.2617, + "learning_rate": 3.5451918424697937e-05, + "loss": 3.2279, "step": 87800 }, { "epoch": 0.29, - "learning_rate": 3.545886463344428e-05, - "loss": 3.2542, + "learning_rate": 3.543534885570557e-05, + "loss": 3.2343, "step": 87900 }, { "epoch": 0.29, - "learning_rate": 3.544232181732761e-05, - "loss": 3.2411, + "learning_rate": 3.5418779286713195e-05, + "loss": 3.2399, "step": 88000 }, { "epoch": 0.29, - "learning_rate": 3.542577900121094e-05, - "loss": 3.2702, + "learning_rate": 3.540220971772083e-05, + "loss": 3.2443, "step": 88100 }, { "epoch": 0.29, - "learning_rate": 3.540923618509426e-05, - "loss": 3.2572, + "learning_rate": 3.5385640148728453e-05, + "loss": 3.228, "step": 88200 }, { "epoch": 0.29, - "learning_rate": 3.539269336897759e-05, - "loss": 3.2618, + "learning_rate": 3.536907057973608e-05, + "loss": 3.2365, "step": 88300 }, { "epoch": 0.29, - "learning_rate": 3.537615055286092e-05, - "loss": 3.2691, + "learning_rate": 3.535250101074371e-05, + "loss": 3.239, "step": 88400 }, { "epoch": 0.29, - "learning_rate": 3.535960773674424e-05, - "loss": 3.2635, + "learning_rate": 3.533593144175134e-05, + "loss": 3.2189, "step": 88500 }, { "epoch": 0.29, - "learning_rate": 3.534306492062757e-05, - "loss": 3.2694, + "learning_rate": 3.5319361872758963e-05, + "loss": 3.2397, "step": 88600 }, { "epoch": 0.29, - "learning_rate": 3.53265221045109e-05, - "loss": 3.2622, + "learning_rate": 3.5302792303766596e-05, + "loss": 3.232, "step": 88700 }, { "epoch": 0.29, - "learning_rate": 3.530997928839422e-05, - "loss": 3.2523, + "learning_rate": 3.528622273477423e-05, + "loss": 3.2339, "step": 88800 }, { "epoch": 0.29, - "learning_rate": 3.529343647227755e-05, - "loss": 3.275, + "learning_rate": 3.5269653165781854e-05, + "loss": 3.2358, "step": 88900 }, { "epoch": 0.29, - "learning_rate": 3.527689365616088e-05, - "loss": 3.2564, + "learning_rate": 3.525308359678948e-05, + "loss": 3.2359, "step": 89000 }, { - "epoch": 0.29, - "learning_rate": 3.52603508400442e-05, - "loss": 3.263, + "epoch": 0.3, + "learning_rate": 3.523651402779711e-05, + "loss": 3.2325, "step": 89100 }, { "epoch": 0.3, - "learning_rate": 3.5243808023927534e-05, - "loss": 3.2685, + "learning_rate": 3.521994445880474e-05, + "loss": 3.2296, "step": 89200 }, { "epoch": 0.3, - "learning_rate": 3.522726520781086e-05, - "loss": 3.2586, + "learning_rate": 3.520337488981237e-05, + "loss": 3.2339, "step": 89300 }, { "epoch": 0.3, - "learning_rate": 3.521072239169418e-05, - "loss": 3.25, + "learning_rate": 3.518680532082e-05, + "loss": 3.2216, "step": 89400 }, { "epoch": 0.3, - "learning_rate": 3.5194179575577514e-05, - "loss": 3.2568, + "learning_rate": 3.517023575182762e-05, + "loss": 3.2419, "step": 89500 }, { "epoch": 0.3, - "learning_rate": 3.517763675946084e-05, - "loss": 3.2598, + "learning_rate": 3.5153666182835256e-05, + "loss": 3.2348, "step": 89600 }, { "epoch": 0.3, - "learning_rate": 3.516109394334416e-05, - "loss": 3.2488, + "learning_rate": 3.513709661384289e-05, + "loss": 3.2378, "step": 89700 }, { "epoch": 0.3, - "learning_rate": 3.5144551127227494e-05, - "loss": 3.2653, + "learning_rate": 3.512052704485051e-05, + "loss": 3.2371, "step": 89800 }, { "epoch": 0.3, - "learning_rate": 3.512800831111082e-05, - "loss": 3.2596, + "learning_rate": 3.510395747585814e-05, + "loss": 3.2262, "step": 89900 }, { "epoch": 0.3, - "learning_rate": 3.5111465494994144e-05, - "loss": 3.2585, + "learning_rate": 3.508738790686577e-05, + "loss": 3.2282, "step": 90000 }, { "epoch": 0.3, - "learning_rate": 3.5094922678877475e-05, - "loss": 3.2571, + "learning_rate": 3.50708183378734e-05, + "loss": 3.2506, "step": 90100 }, { "epoch": 0.3, - "learning_rate": 3.50783798627608e-05, - "loss": 3.2586, + "learning_rate": 3.5054248768881024e-05, + "loss": 3.2378, "step": 90200 }, { "epoch": 0.3, - "learning_rate": 3.5061837046644124e-05, - "loss": 3.262, + "learning_rate": 3.5037679199888657e-05, + "loss": 3.2378, "step": 90300 }, { "epoch": 0.3, - "learning_rate": 3.5045294230527455e-05, - "loss": 3.2643, + "learning_rate": 3.502110963089628e-05, + "loss": 3.2346, "step": 90400 }, { "epoch": 0.3, - "learning_rate": 3.502875141441078e-05, - "loss": 3.257, + "learning_rate": 3.5004540061903915e-05, + "loss": 3.2204, "step": 90500 }, { "epoch": 0.3, - "learning_rate": 3.5012208598294104e-05, - "loss": 3.2634, + "learning_rate": 3.498797049291154e-05, + "loss": 3.222, "step": 90600 }, { "epoch": 0.3, - "learning_rate": 3.4995665782177436e-05, - "loss": 3.2642, + "learning_rate": 3.497140092391917e-05, + "loss": 3.2352, "step": 90700 }, { "epoch": 0.3, - "learning_rate": 3.497912296606076e-05, - "loss": 3.2506, + "learning_rate": 3.49548313549268e-05, + "loss": 3.2203, "step": 90800 }, { "epoch": 0.3, - "learning_rate": 3.4962580149944085e-05, - "loss": 3.2665, + "learning_rate": 3.493826178593443e-05, + "loss": 3.2452, "step": 90900 }, { "epoch": 0.3, - "learning_rate": 3.4946037333827416e-05, - "loss": 3.2704, + "learning_rate": 3.492169221694205e-05, + "loss": 3.2305, "step": 91000 }, { "epoch": 0.3, - "learning_rate": 3.492949451771074e-05, - "loss": 3.2664, + "learning_rate": 3.4905122647949683e-05, + "loss": 3.2408, "step": 91100 }, { "epoch": 0.3, - "learning_rate": 3.4912951701594065e-05, - "loss": 3.2599, + "learning_rate": 3.4888553078957316e-05, + "loss": 3.2241, "step": 91200 }, { "epoch": 0.3, - "learning_rate": 3.4896408885477396e-05, - "loss": 3.2736, + "learning_rate": 3.487198350996494e-05, + "loss": 3.2287, "step": 91300 }, { "epoch": 0.3, - "learning_rate": 3.487986606936072e-05, - "loss": 3.2523, + "learning_rate": 3.485541394097257e-05, + "loss": 3.2359, "step": 91400 }, { "epoch": 0.3, - "learning_rate": 3.4863323253244045e-05, - "loss": 3.2675, + "learning_rate": 3.48388443719802e-05, + "loss": 3.2272, "step": 91500 }, { "epoch": 0.3, - "learning_rate": 3.484678043712738e-05, - "loss": 3.2675, + "learning_rate": 3.4822274802987826e-05, + "loss": 3.2369, "step": 91600 }, { "epoch": 0.3, - "learning_rate": 3.48302376210107e-05, - "loss": 3.2569, + "learning_rate": 3.480570523399546e-05, + "loss": 3.219, "step": 91700 }, { "epoch": 0.3, - "learning_rate": 3.4813694804894026e-05, - "loss": 3.2536, + "learning_rate": 3.478913566500308e-05, + "loss": 3.232, "step": 91800 }, { "epoch": 0.3, - "learning_rate": 3.479715198877736e-05, - "loss": 3.2658, + "learning_rate": 3.477256609601071e-05, + "loss": 3.2252, "step": 91900 }, { "epoch": 0.3, - "learning_rate": 3.478060917266068e-05, - "loss": 3.2642, + "learning_rate": 3.475599652701834e-05, + "loss": 3.239, "step": 92000 }, { - "epoch": 0.3, - "learning_rate": 3.4764066356544006e-05, - "loss": 3.2714, + "epoch": 0.31, + "learning_rate": 3.473942695802597e-05, + "loss": 3.2355, "step": 92100 }, { "epoch": 0.31, - "learning_rate": 3.474752354042734e-05, - "loss": 3.2686, + "learning_rate": 3.4722857389033595e-05, + "loss": 3.2359, "step": 92200 }, { "epoch": 0.31, - "learning_rate": 3.473098072431066e-05, - "loss": 3.2464, + "learning_rate": 3.470628782004123e-05, + "loss": 3.2358, "step": 92300 }, { "epoch": 0.31, - "learning_rate": 3.471443790819399e-05, - "loss": 3.2589, + "learning_rate": 3.468971825104885e-05, + "loss": 3.2402, "step": 92400 }, { "epoch": 0.31, - "learning_rate": 3.469789509207732e-05, - "loss": 3.2658, + "learning_rate": 3.4673148682056486e-05, + "loss": 3.2411, "step": 92500 }, { "epoch": 0.31, - "learning_rate": 3.468135227596064e-05, - "loss": 3.2554, + "learning_rate": 3.465657911306411e-05, + "loss": 3.2427, "step": 92600 }, { "epoch": 0.31, - "learning_rate": 3.4664809459843974e-05, - "loss": 3.2661, + "learning_rate": 3.464000954407174e-05, + "loss": 3.2437, "step": 92700 }, { "epoch": 0.31, - "learning_rate": 3.46482666437273e-05, - "loss": 3.2749, + "learning_rate": 3.462343997507937e-05, + "loss": 3.2219, "step": 92800 }, { "epoch": 0.31, - "learning_rate": 3.463172382761062e-05, - "loss": 3.275, + "learning_rate": 3.4606870406087e-05, + "loss": 3.2291, "step": 92900 }, { "epoch": 0.31, - "learning_rate": 3.4615181011493954e-05, - "loss": 3.2656, + "learning_rate": 3.459030083709462e-05, + "loss": 3.2326, "step": 93000 }, { "epoch": 0.31, - "learning_rate": 3.459863819537728e-05, - "loss": 3.254, + "learning_rate": 3.4573731268102254e-05, + "loss": 3.2328, "step": 93100 }, { "epoch": 0.31, - "learning_rate": 3.45820953792606e-05, - "loss": 3.2676, + "learning_rate": 3.4557161699109887e-05, + "loss": 3.2412, "step": 93200 }, { "epoch": 0.31, - "learning_rate": 3.4565552563143934e-05, - "loss": 3.2606, + "learning_rate": 3.454059213011751e-05, + "loss": 3.2331, "step": 93300 }, { "epoch": 0.31, - "learning_rate": 3.454900974702725e-05, - "loss": 3.2555, + "learning_rate": 3.452402256112514e-05, + "loss": 3.2408, "step": 93400 }, { "epoch": 0.31, - "learning_rate": 3.4532466930910584e-05, - "loss": 3.2576, + "learning_rate": 3.450745299213277e-05, + "loss": 3.2463, "step": 93500 }, { "epoch": 0.31, - "learning_rate": 3.4515924114793915e-05, - "loss": 3.2762, + "learning_rate": 3.44908834231404e-05, + "loss": 3.2193, "step": 93600 }, { "epoch": 0.31, - "learning_rate": 3.449938129867723e-05, - "loss": 3.258, + "learning_rate": 3.447431385414803e-05, + "loss": 3.2362, "step": 93700 }, { "epoch": 0.31, - "learning_rate": 3.4482838482560564e-05, - "loss": 3.2633, + "learning_rate": 3.4457744285155655e-05, + "loss": 3.2277, "step": 93800 }, { "epoch": 0.31, - "learning_rate": 3.4466295666443895e-05, - "loss": 3.2653, + "learning_rate": 3.444117471616328e-05, + "loss": 3.2267, "step": 93900 }, { "epoch": 0.31, - "learning_rate": 3.444975285032721e-05, - "loss": 3.2522, + "learning_rate": 3.4424605147170913e-05, + "loss": 3.2432, "step": 94000 }, { "epoch": 0.31, - "learning_rate": 3.4433210034210544e-05, - "loss": 3.2494, + "learning_rate": 3.4408035578178546e-05, + "loss": 3.2313, "step": 94100 }, { "epoch": 0.31, - "learning_rate": 3.4416667218093876e-05, - "loss": 3.2713, + "learning_rate": 3.4391466009186165e-05, + "loss": 3.2453, "step": 94200 }, { "epoch": 0.31, - "learning_rate": 3.44001244019772e-05, - "loss": 3.2463, + "learning_rate": 3.43748964401938e-05, + "loss": 3.2433, "step": 94300 }, { "epoch": 0.31, - "learning_rate": 3.4383581585860525e-05, - "loss": 3.2635, + "learning_rate": 3.435832687120143e-05, + "loss": 3.2271, "step": 94400 }, { "epoch": 0.31, - "learning_rate": 3.4367038769743856e-05, - "loss": 3.2574, + "learning_rate": 3.4341757302209056e-05, + "loss": 3.2321, "step": 94500 }, { "epoch": 0.31, - "learning_rate": 3.435049595362718e-05, - "loss": 3.2502, + "learning_rate": 3.432518773321668e-05, + "loss": 3.2307, "step": 94600 }, { "epoch": 0.31, - "learning_rate": 3.4333953137510505e-05, - "loss": 3.2582, + "learning_rate": 3.4308618164224315e-05, + "loss": 3.2298, "step": 94700 }, { "epoch": 0.31, - "learning_rate": 3.4317410321393836e-05, - "loss": 3.2654, + "learning_rate": 3.429204859523194e-05, + "loss": 3.2341, "step": 94800 }, { "epoch": 0.31, - "learning_rate": 3.430086750527716e-05, - "loss": 3.2643, + "learning_rate": 3.427547902623957e-05, + "loss": 3.2277, "step": 94900 }, { "epoch": 0.31, - "learning_rate": 3.4284324689160485e-05, - "loss": 3.2591, + "learning_rate": 3.42589094572472e-05, + "loss": 3.2243, "step": 95000 }, { - "epoch": 0.31, - "learning_rate": 3.426778187304382e-05, - "loss": 3.2538, + "epoch": 0.32, + "learning_rate": 3.4242339888254825e-05, + "loss": 3.2252, "step": 95100 }, { - "epoch": 0.31, - "learning_rate": 3.425123905692714e-05, - "loss": 3.2546, + "epoch": 0.32, + "learning_rate": 3.422577031926246e-05, + "loss": 3.2373, "step": 95200 }, { "epoch": 0.32, - "learning_rate": 3.4234696240810466e-05, - "loss": 3.2509, + "learning_rate": 3.420920075027009e-05, + "loss": 3.2315, "step": 95300 }, { "epoch": 0.32, - "learning_rate": 3.42181534246938e-05, - "loss": 3.2641, + "learning_rate": 3.4192631181277716e-05, + "loss": 3.2376, "step": 95400 }, { "epoch": 0.32, - "learning_rate": 3.420161060857712e-05, - "loss": 3.262, + "learning_rate": 3.417606161228534e-05, + "loss": 3.2266, "step": 95500 }, { "epoch": 0.32, - "learning_rate": 3.4185067792460446e-05, - "loss": 3.2672, + "learning_rate": 3.4159492043292974e-05, + "loss": 3.2262, "step": 95600 }, { "epoch": 0.32, - "learning_rate": 3.416852497634378e-05, - "loss": 3.2492, + "learning_rate": 3.41429224743006e-05, + "loss": 3.2466, "step": 95700 }, { "epoch": 0.32, - "learning_rate": 3.41519821602271e-05, - "loss": 3.2553, + "learning_rate": 3.4126352905308226e-05, + "loss": 3.2479, "step": 95800 }, { "epoch": 0.32, - "learning_rate": 3.4135439344110427e-05, - "loss": 3.2685, + "learning_rate": 3.410978333631586e-05, + "loss": 3.2223, "step": 95900 }, { "epoch": 0.32, - "learning_rate": 3.411889652799375e-05, - "loss": 3.2603, + "learning_rate": 3.4093213767323484e-05, + "loss": 3.2395, "step": 96000 }, { "epoch": 0.32, - "learning_rate": 3.410235371187708e-05, - "loss": 3.2502, + "learning_rate": 3.407664419833112e-05, + "loss": 3.2302, "step": 96100 }, { "epoch": 0.32, - "learning_rate": 3.408581089576041e-05, - "loss": 3.258, + "learning_rate": 3.406007462933874e-05, + "loss": 3.2257, "step": 96200 }, { "epoch": 0.32, - "learning_rate": 3.406926807964373e-05, - "loss": 3.2508, + "learning_rate": 3.404350506034637e-05, + "loss": 3.2366, "step": 96300 }, { "epoch": 0.32, - "learning_rate": 3.405272526352706e-05, - "loss": 3.2375, + "learning_rate": 3.4026935491354e-05, + "loss": 3.2412, "step": 96400 }, { "epoch": 0.32, - "learning_rate": 3.4036182447410394e-05, - "loss": 3.2548, + "learning_rate": 3.4010365922361633e-05, + "loss": 3.2422, "step": 96500 }, { "epoch": 0.32, - "learning_rate": 3.401963963129371e-05, - "loss": 3.2599, + "learning_rate": 3.399379635336926e-05, + "loss": 3.2234, "step": 96600 }, { "epoch": 0.32, - "learning_rate": 3.400309681517704e-05, - "loss": 3.2427, + "learning_rate": 3.3977226784376885e-05, + "loss": 3.2288, "step": 96700 }, { "epoch": 0.32, - "learning_rate": 3.3986553999060374e-05, - "loss": 3.2546, + "learning_rate": 3.396065721538452e-05, + "loss": 3.2311, "step": 96800 }, { "epoch": 0.32, - "learning_rate": 3.397001118294369e-05, - "loss": 3.2457, + "learning_rate": 3.3944087646392143e-05, + "loss": 3.2405, "step": 96900 }, { "epoch": 0.32, - "learning_rate": 3.3953468366827024e-05, - "loss": 3.259, + "learning_rate": 3.392751807739977e-05, + "loss": 3.22, "step": 97000 }, { "epoch": 0.32, - "learning_rate": 3.3936925550710355e-05, - "loss": 3.2589, + "learning_rate": 3.39109485084074e-05, + "loss": 3.2193, "step": 97100 }, { "epoch": 0.32, - "learning_rate": 3.392038273459367e-05, - "loss": 3.2557, + "learning_rate": 3.389437893941503e-05, + "loss": 3.2208, "step": 97200 }, { "epoch": 0.32, - "learning_rate": 3.3903839918477004e-05, - "loss": 3.2607, + "learning_rate": 3.387780937042266e-05, + "loss": 3.2173, "step": 97300 }, { "epoch": 0.32, - "learning_rate": 3.3887297102360335e-05, - "loss": 3.2706, + "learning_rate": 3.3861239801430286e-05, + "loss": 3.2119, "step": 97400 }, { "epoch": 0.32, - "learning_rate": 3.387075428624365e-05, - "loss": 3.2462, + "learning_rate": 3.384467023243791e-05, + "loss": 3.2322, "step": 97500 }, { "epoch": 0.32, - "learning_rate": 3.3854211470126984e-05, - "loss": 3.2611, + "learning_rate": 3.3828100663445545e-05, + "loss": 3.2253, "step": 97600 }, { "epoch": 0.32, - "learning_rate": 3.3837668654010316e-05, - "loss": 3.2471, + "learning_rate": 3.381153109445318e-05, + "loss": 3.2345, "step": 97700 }, { "epoch": 0.32, - "learning_rate": 3.382112583789363e-05, - "loss": 3.2624, + "learning_rate": 3.37949615254608e-05, + "loss": 3.2351, "step": 97800 }, { "epoch": 0.32, - "learning_rate": 3.3804583021776965e-05, - "loss": 3.2702, + "learning_rate": 3.377839195646843e-05, + "loss": 3.2274, "step": 97900 }, { "epoch": 0.32, - "learning_rate": 3.3788040205660296e-05, - "loss": 3.256, + "learning_rate": 3.376182238747606e-05, + "loss": 3.2336, "step": 98000 }, { - "epoch": 0.32, - "learning_rate": 3.3771497389543614e-05, - "loss": 3.2601, + "epoch": 0.33, + "learning_rate": 3.374525281848369e-05, + "loss": 3.2287, "step": 98100 }, { - "epoch": 0.32, - "learning_rate": 3.3754954573426945e-05, - "loss": 3.2534, + "epoch": 0.33, + "learning_rate": 3.372868324949131e-05, + "loss": 3.2335, "step": 98200 }, { "epoch": 0.33, - "learning_rate": 3.3738411757310276e-05, - "loss": 3.2644, + "learning_rate": 3.3712113680498946e-05, + "loss": 3.2347, "step": 98300 }, { "epoch": 0.33, - "learning_rate": 3.3721868941193594e-05, - "loss": 3.2516, + "learning_rate": 3.369554411150657e-05, + "loss": 3.2256, "step": 98400 }, { "epoch": 0.33, - "learning_rate": 3.3705326125076925e-05, - "loss": 3.243, + "learning_rate": 3.3678974542514204e-05, + "loss": 3.2141, "step": 98500 }, { "epoch": 0.33, - "learning_rate": 3.368878330896025e-05, - "loss": 3.2404, + "learning_rate": 3.366240497352183e-05, + "loss": 3.2306, "step": 98600 }, { "epoch": 0.33, - "learning_rate": 3.367224049284358e-05, - "loss": 3.2613, + "learning_rate": 3.3645835404529456e-05, + "loss": 3.2361, "step": 98700 }, { "epoch": 0.33, - "learning_rate": 3.3655697676726906e-05, - "loss": 3.2706, + "learning_rate": 3.362926583553709e-05, + "loss": 3.2326, "step": 98800 }, { "epoch": 0.33, - "learning_rate": 3.363915486061023e-05, - "loss": 3.2475, + "learning_rate": 3.361269626654472e-05, + "loss": 3.2227, "step": 98900 }, { "epoch": 0.33, - "learning_rate": 3.362261204449356e-05, - "loss": 3.2509, + "learning_rate": 3.359612669755235e-05, + "loss": 3.237, "step": 99000 }, { "epoch": 0.33, - "learning_rate": 3.3606069228376886e-05, - "loss": 3.2564, + "learning_rate": 3.357955712855997e-05, + "loss": 3.2404, "step": 99100 }, { "epoch": 0.33, - "learning_rate": 3.358952641226021e-05, - "loss": 3.2648, + "learning_rate": 3.3562987559567605e-05, + "loss": 3.2297, "step": 99200 }, { "epoch": 0.33, - "learning_rate": 3.357298359614354e-05, - "loss": 3.2498, + "learning_rate": 3.354641799057523e-05, + "loss": 3.2177, "step": 99300 }, { "epoch": 0.33, - "learning_rate": 3.3556440780026867e-05, - "loss": 3.2664, + "learning_rate": 3.3529848421582863e-05, + "loss": 3.2255, "step": 99400 }, { "epoch": 0.33, - "learning_rate": 3.353989796391019e-05, - "loss": 3.2729, + "learning_rate": 3.351327885259049e-05, + "loss": 3.229, "step": 99500 }, { "epoch": 0.33, - "learning_rate": 3.352335514779352e-05, - "loss": 3.2632, + "learning_rate": 3.3496709283598115e-05, + "loss": 3.2253, "step": 99600 }, { "epoch": 0.33, - "learning_rate": 3.350681233167685e-05, - "loss": 3.2534, + "learning_rate": 3.348013971460575e-05, + "loss": 3.219, "step": 99700 }, { "epoch": 0.33, - "learning_rate": 3.349026951556017e-05, - "loss": 3.2488, + "learning_rate": 3.3463570145613374e-05, + "loss": 3.243, "step": 99800 }, { "epoch": 0.33, - "learning_rate": 3.34737266994435e-05, - "loss": 3.2572, + "learning_rate": 3.3447000576621e-05, + "loss": 3.2349, "step": 99900 }, { "epoch": 0.33, - "learning_rate": 3.345718388332683e-05, - "loss": 3.2657, + "learning_rate": 3.343043100762863e-05, + "loss": 3.2488, "step": 100000 }, { "epoch": 0.33, - "learning_rate": 3.344064106721015e-05, - "loss": 3.2615, + "learning_rate": 3.3413861438636265e-05, + "loss": 3.2385, "step": 100100 }, { "epoch": 0.33, - "learning_rate": 3.342409825109348e-05, - "loss": 3.2519, + "learning_rate": 3.339729186964389e-05, + "loss": 3.2293, "step": 100200 }, { "epoch": 0.33, - "learning_rate": 3.340755543497681e-05, - "loss": 3.2487, + "learning_rate": 3.3380722300651516e-05, + "loss": 3.2342, "step": 100300 }, { "epoch": 0.33, - "learning_rate": 3.339101261886013e-05, - "loss": 3.2669, + "learning_rate": 3.336415273165915e-05, + "loss": 3.2411, "step": 100400 }, { "epoch": 0.33, - "learning_rate": 3.3374469802743464e-05, - "loss": 3.2567, + "learning_rate": 3.3347583162666775e-05, + "loss": 3.2371, "step": 100500 }, { "epoch": 0.33, - "learning_rate": 3.335792698662679e-05, - "loss": 3.266, + "learning_rate": 3.333101359367441e-05, + "loss": 3.2258, "step": 100600 }, { "epoch": 0.33, - "learning_rate": 3.334138417051011e-05, - "loss": 3.2476, + "learning_rate": 3.3314444024682026e-05, + "loss": 3.2356, "step": 100700 }, { "epoch": 0.33, - "learning_rate": 3.3324841354393444e-05, - "loss": 3.2634, + "learning_rate": 3.329787445568966e-05, + "loss": 3.229, "step": 100800 }, { "epoch": 0.33, - "learning_rate": 3.3308298538276775e-05, - "loss": 3.2518, + "learning_rate": 3.328130488669729e-05, + "loss": 3.2363, "step": 100900 }, { "epoch": 0.33, - "learning_rate": 3.329175572216009e-05, - "loss": 3.2505, + "learning_rate": 3.326473531770492e-05, + "loss": 3.226, "step": 101000 }, { - "epoch": 0.33, - "learning_rate": 3.3275212906043424e-05, - "loss": 3.2456, + "epoch": 0.34, + "learning_rate": 3.324816574871254e-05, + "loss": 3.2386, "step": 101100 }, { - "epoch": 0.33, - "learning_rate": 3.325867008992675e-05, - "loss": 3.2318, + "epoch": 0.34, + "learning_rate": 3.3231596179720176e-05, + "loss": 3.2363, "step": 101200 }, { "epoch": 0.34, - "learning_rate": 3.3242127273810073e-05, - "loss": 3.2553, + "learning_rate": 3.32150266107278e-05, + "loss": 3.2304, "step": 101300 }, { "epoch": 0.34, - "learning_rate": 3.3225584457693405e-05, - "loss": 3.2426, + "learning_rate": 3.3198457041735434e-05, + "loss": 3.2295, "step": 101400 }, { "epoch": 0.34, - "learning_rate": 3.320904164157673e-05, - "loss": 3.2574, + "learning_rate": 3.318188747274306e-05, + "loss": 3.2289, "step": 101500 }, { "epoch": 0.34, - "learning_rate": 3.3192498825460054e-05, - "loss": 3.271, + "learning_rate": 3.3165317903750686e-05, + "loss": 3.2365, "step": 101600 }, { "epoch": 0.34, - "learning_rate": 3.3175956009343385e-05, - "loss": 3.2631, + "learning_rate": 3.314874833475832e-05, + "loss": 3.2313, "step": 101700 }, { "epoch": 0.34, - "learning_rate": 3.315941319322671e-05, - "loss": 3.2554, + "learning_rate": 3.313217876576595e-05, + "loss": 3.2274, "step": 101800 }, { "epoch": 0.34, - "learning_rate": 3.3142870377110034e-05, - "loss": 3.2509, + "learning_rate": 3.311560919677357e-05, + "loss": 3.2199, "step": 101900 }, { "epoch": 0.34, - "learning_rate": 3.3126327560993365e-05, - "loss": 3.2547, + "learning_rate": 3.30990396277812e-05, + "loss": 3.2383, "step": 102000 }, { "epoch": 0.34, - "learning_rate": 3.310978474487669e-05, - "loss": 3.2674, + "learning_rate": 3.3082470058788835e-05, + "loss": 3.2247, "step": 102100 }, { "epoch": 0.34, - "learning_rate": 3.3093241928760015e-05, - "loss": 3.2682, + "learning_rate": 3.306590048979646e-05, + "loss": 3.2384, "step": 102200 }, { "epoch": 0.34, - "learning_rate": 3.3076699112643346e-05, - "loss": 3.247, + "learning_rate": 3.304933092080409e-05, + "loss": 3.2346, "step": 102300 }, { "epoch": 0.34, - "learning_rate": 3.306015629652667e-05, - "loss": 3.2585, + "learning_rate": 3.303276135181172e-05, + "loss": 3.2464, "step": 102400 }, { "epoch": 0.34, - "learning_rate": 3.3043613480409995e-05, - "loss": 3.2473, + "learning_rate": 3.3016191782819345e-05, + "loss": 3.2331, "step": 102500 }, { "epoch": 0.34, - "learning_rate": 3.3027070664293326e-05, - "loss": 3.2527, + "learning_rate": 3.299962221382698e-05, + "loss": 3.2337, "step": 102600 }, { "epoch": 0.34, - "learning_rate": 3.301052784817665e-05, - "loss": 3.2581, + "learning_rate": 3.2983052644834604e-05, + "loss": 3.2389, "step": 102700 }, { "epoch": 0.34, - "learning_rate": 3.299398503205998e-05, - "loss": 3.2472, + "learning_rate": 3.296648307584223e-05, + "loss": 3.2324, "step": 102800 }, { "epoch": 0.34, - "learning_rate": 3.297744221594331e-05, - "loss": 3.2582, + "learning_rate": 3.294991350684986e-05, + "loss": 3.2205, "step": 102900 }, { "epoch": 0.34, - "learning_rate": 3.296089939982663e-05, - "loss": 3.2706, + "learning_rate": 3.2933343937857495e-05, + "loss": 3.2256, "step": 103000 }, { "epoch": 0.34, - "learning_rate": 3.294435658370996e-05, - "loss": 3.2725, + "learning_rate": 3.2916774368865114e-05, + "loss": 3.2269, "step": 103100 }, { "epoch": 0.34, - "learning_rate": 3.292781376759329e-05, - "loss": 3.2477, + "learning_rate": 3.2900204799872746e-05, + "loss": 3.2183, "step": 103200 }, { "epoch": 0.34, - "learning_rate": 3.291127095147661e-05, - "loss": 3.2604, + "learning_rate": 3.288363523088038e-05, + "loss": 3.2285, "step": 103300 }, { "epoch": 0.34, - "learning_rate": 3.289472813535994e-05, - "loss": 3.2636, + "learning_rate": 3.2867065661888005e-05, + "loss": 3.2214, "step": 103400 }, { "epoch": 0.34, - "learning_rate": 3.287818531924327e-05, - "loss": 3.2683, + "learning_rate": 3.285049609289563e-05, + "loss": 3.2273, "step": 103500 }, { "epoch": 0.34, - "learning_rate": 3.286164250312659e-05, - "loss": 3.26, + "learning_rate": 3.283392652390326e-05, + "loss": 3.231, "step": 103600 }, { "epoch": 0.34, - "learning_rate": 3.284509968700992e-05, - "loss": 3.2666, + "learning_rate": 3.281735695491089e-05, + "loss": 3.2162, "step": 103700 }, { "epoch": 0.34, - "learning_rate": 3.282855687089325e-05, - "loss": 3.2449, + "learning_rate": 3.280078738591852e-05, + "loss": 3.2362, "step": 103800 }, { "epoch": 0.34, - "learning_rate": 3.281201405477657e-05, - "loss": 3.2597, + "learning_rate": 3.278421781692615e-05, + "loss": 3.2199, "step": 103900 }, { "epoch": 0.34, - "learning_rate": 3.2795471238659904e-05, - "loss": 3.2521, + "learning_rate": 3.276764824793377e-05, + "loss": 3.2301, "step": 104000 }, { "epoch": 0.34, - "learning_rate": 3.277892842254323e-05, - "loss": 3.2453, + "learning_rate": 3.2751078678941406e-05, + "loss": 3.235, "step": 104100 }, { - "epoch": 0.34, - "learning_rate": 3.276238560642655e-05, - "loss": 3.2639, + "epoch": 0.35, + "learning_rate": 3.273450910994904e-05, + "loss": 3.2261, "step": 104200 }, { "epoch": 0.35, - "learning_rate": 3.2745842790309884e-05, - "loss": 3.2598, + "learning_rate": 3.271793954095666e-05, + "loss": 3.2321, "step": 104300 }, { "epoch": 0.35, - "learning_rate": 3.272929997419321e-05, - "loss": 3.264, + "learning_rate": 3.270136997196429e-05, + "loss": 3.2355, "step": 104400 }, { "epoch": 0.35, - "learning_rate": 3.271275715807653e-05, - "loss": 3.2736, + "learning_rate": 3.268480040297192e-05, + "loss": 3.2353, "step": 104500 }, { "epoch": 0.35, - "learning_rate": 3.2696214341959864e-05, - "loss": 3.2444, + "learning_rate": 3.266823083397955e-05, + "loss": 3.2207, "step": 104600 }, { "epoch": 0.35, - "learning_rate": 3.267967152584319e-05, - "loss": 3.2562, + "learning_rate": 3.2651661264987174e-05, + "loss": 3.2329, "step": 104700 }, { "epoch": 0.35, - "learning_rate": 3.2663128709726513e-05, - "loss": 3.2625, + "learning_rate": 3.263509169599481e-05, + "loss": 3.2261, "step": 104800 }, { "epoch": 0.35, - "learning_rate": 3.2646585893609845e-05, - "loss": 3.2529, + "learning_rate": 3.261852212700243e-05, + "loss": 3.2343, "step": 104900 }, { "epoch": 0.35, - "learning_rate": 3.263004307749317e-05, - "loss": 3.2427, + "learning_rate": 3.2601952558010065e-05, + "loss": 3.225, "step": 105000 }, { "epoch": 0.35, - "learning_rate": 3.2613500261376494e-05, - "loss": 3.2623, + "learning_rate": 3.258538298901769e-05, + "loss": 3.2261, "step": 105100 }, { "epoch": 0.35, - "learning_rate": 3.2596957445259825e-05, - "loss": 3.247, + "learning_rate": 3.256881342002532e-05, + "loss": 3.233, "step": 105200 }, { "epoch": 0.35, - "learning_rate": 3.258041462914315e-05, - "loss": 3.25, + "learning_rate": 3.255224385103295e-05, + "loss": 3.2243, "step": 105300 }, { "epoch": 0.35, - "learning_rate": 3.2563871813026474e-05, - "loss": 3.2543, + "learning_rate": 3.253567428204058e-05, + "loss": 3.238, "step": 105400 }, { "epoch": 0.35, - "learning_rate": 3.2547328996909806e-05, - "loss": 3.2667, + "learning_rate": 3.25191047130482e-05, + "loss": 3.2217, "step": 105500 }, { "epoch": 0.35, - "learning_rate": 3.253078618079313e-05, - "loss": 3.2512, + "learning_rate": 3.2502535144055834e-05, + "loss": 3.2263, "step": 105600 }, { "epoch": 0.35, - "learning_rate": 3.2514243364676455e-05, - "loss": 3.2645, + "learning_rate": 3.2485965575063466e-05, + "loss": 3.24, "step": 105700 }, { "epoch": 0.35, - "learning_rate": 3.2497700548559786e-05, - "loss": 3.2437, + "learning_rate": 3.246939600607109e-05, + "loss": 3.2362, "step": 105800 }, { "epoch": 0.35, - "learning_rate": 3.248115773244311e-05, - "loss": 3.2566, + "learning_rate": 3.245282643707872e-05, + "loss": 3.2442, "step": 105900 }, { "epoch": 0.35, - "learning_rate": 3.2464614916326435e-05, - "loss": 3.2543, + "learning_rate": 3.243625686808635e-05, + "loss": 3.2427, "step": 106000 }, { "epoch": 0.35, - "learning_rate": 3.2448072100209766e-05, - "loss": 3.2631, + "learning_rate": 3.2419687299093976e-05, + "loss": 3.2308, "step": 106100 }, { "epoch": 0.35, - "learning_rate": 3.243152928409309e-05, - "loss": 3.2499, + "learning_rate": 3.240311773010161e-05, + "loss": 3.2239, "step": 106200 }, { "epoch": 0.35, - "learning_rate": 3.2414986467976415e-05, - "loss": 3.2435, + "learning_rate": 3.2386548161109235e-05, + "loss": 3.2405, "step": 106300 }, { "epoch": 0.35, - "learning_rate": 3.239844365185975e-05, - "loss": 3.2612, + "learning_rate": 3.236997859211686e-05, + "loss": 3.2283, "step": 106400 }, { "epoch": 0.35, - "learning_rate": 3.238190083574307e-05, - "loss": 3.2565, + "learning_rate": 3.235340902312449e-05, + "loss": 3.2221, "step": 106500 }, { "epoch": 0.35, - "learning_rate": 3.2365358019626396e-05, - "loss": 3.2454, + "learning_rate": 3.2336839454132126e-05, + "loss": 3.2467, "step": 106600 }, { "epoch": 0.35, - "learning_rate": 3.234881520350973e-05, - "loss": 3.2609, + "learning_rate": 3.2320269885139745e-05, + "loss": 3.2298, "step": 106700 }, { "epoch": 0.35, - "learning_rate": 3.233227238739305e-05, - "loss": 3.2491, + "learning_rate": 3.230370031614738e-05, + "loss": 3.2264, "step": 106800 }, { "epoch": 0.35, - "learning_rate": 3.2315729571276376e-05, - "loss": 3.2552, + "learning_rate": 3.228713074715501e-05, + "loss": 3.2204, "step": 106900 }, { "epoch": 0.35, - "learning_rate": 3.229918675515971e-05, - "loss": 3.2555, + "learning_rate": 3.2270561178162636e-05, + "loss": 3.2318, "step": 107000 }, { "epoch": 0.35, - "learning_rate": 3.228264393904303e-05, - "loss": 3.2598, + "learning_rate": 3.225399160917026e-05, + "loss": 3.2317, "step": 107100 }, { - "epoch": 0.35, - "learning_rate": 3.226610112292636e-05, - "loss": 3.275, + "epoch": 0.36, + "learning_rate": 3.2237422040177894e-05, + "loss": 3.2323, "step": 107200 }, { "epoch": 0.36, - "learning_rate": 3.224955830680969e-05, - "loss": 3.2497, + "learning_rate": 3.222085247118552e-05, + "loss": 3.2188, "step": 107300 }, { "epoch": 0.36, - "learning_rate": 3.223301549069301e-05, - "loss": 3.2512, + "learning_rate": 3.220428290219315e-05, + "loss": 3.2382, "step": 107400 }, { "epoch": 0.36, - "learning_rate": 3.2216472674576344e-05, - "loss": 3.2622, + "learning_rate": 3.218771333320078e-05, + "loss": 3.2385, "step": 107500 }, { "epoch": 0.36, - "learning_rate": 3.219992985845967e-05, - "loss": 3.265, + "learning_rate": 3.2171143764208404e-05, + "loss": 3.2225, "step": 107600 }, { "epoch": 0.36, - "learning_rate": 3.218338704234299e-05, - "loss": 3.2593, + "learning_rate": 3.215457419521604e-05, + "loss": 3.2201, "step": 107700 }, { "epoch": 0.36, - "learning_rate": 3.2166844226226324e-05, - "loss": 3.245, + "learning_rate": 3.213800462622367e-05, + "loss": 3.233, "step": 107800 }, { "epoch": 0.36, - "learning_rate": 3.215030141010965e-05, - "loss": 3.2429, + "learning_rate": 3.212143505723129e-05, + "loss": 3.2328, "step": 107900 }, { "epoch": 0.36, - "learning_rate": 3.213375859399297e-05, - "loss": 3.2386, + "learning_rate": 3.210486548823892e-05, + "loss": 3.2275, "step": 108000 }, { "epoch": 0.36, - "learning_rate": 3.2117215777876304e-05, - "loss": 3.251, + "learning_rate": 3.2088295919246554e-05, + "loss": 3.2484, "step": 108100 }, { "epoch": 0.36, - "learning_rate": 3.210067296175963e-05, - "loss": 3.253, + "learning_rate": 3.207172635025418e-05, + "loss": 3.2282, "step": 108200 }, { "epoch": 0.36, - "learning_rate": 3.2084130145642953e-05, - "loss": 3.2625, + "learning_rate": 3.2055156781261805e-05, + "loss": 3.2229, "step": 108300 }, { "epoch": 0.36, - "learning_rate": 3.2067587329526285e-05, - "loss": 3.2448, + "learning_rate": 3.203858721226944e-05, + "loss": 3.2231, "step": 108400 }, { "epoch": 0.36, - "learning_rate": 3.205104451340961e-05, - "loss": 3.252, + "learning_rate": 3.2022017643277064e-05, + "loss": 3.2365, "step": 108500 }, { "epoch": 0.36, - "learning_rate": 3.2034501697292934e-05, - "loss": 3.244, + "learning_rate": 3.2005448074284696e-05, + "loss": 3.2248, "step": 108600 }, { "epoch": 0.36, - "learning_rate": 3.2017958881176265e-05, - "loss": 3.2716, + "learning_rate": 3.198887850529232e-05, + "loss": 3.2227, "step": 108700 }, { "epoch": 0.36, - "learning_rate": 3.200141606505958e-05, - "loss": 3.2486, + "learning_rate": 3.197230893629995e-05, + "loss": 3.2154, "step": 108800 }, { "epoch": 0.36, - "learning_rate": 3.1984873248942914e-05, - "loss": 3.2509, + "learning_rate": 3.195573936730758e-05, + "loss": 3.2262, "step": 108900 }, { "epoch": 0.36, - "learning_rate": 3.1968330432826246e-05, - "loss": 3.2505, + "learning_rate": 3.193916979831521e-05, + "loss": 3.2372, "step": 109000 }, { "epoch": 0.36, - "learning_rate": 3.195178761670957e-05, - "loss": 3.2614, + "learning_rate": 3.192260022932284e-05, + "loss": 3.2315, "step": 109100 }, { "epoch": 0.36, - "learning_rate": 3.1935244800592895e-05, - "loss": 3.2498, + "learning_rate": 3.1906030660330465e-05, + "loss": 3.2385, "step": 109200 }, { "epoch": 0.36, - "learning_rate": 3.1918701984476226e-05, - "loss": 3.2461, + "learning_rate": 3.188946109133809e-05, + "loss": 3.2223, "step": 109300 }, { "epoch": 0.36, - "learning_rate": 3.190215916835955e-05, - "loss": 3.252, + "learning_rate": 3.187289152234572e-05, + "loss": 3.2236, "step": 109400 }, { "epoch": 0.36, - "learning_rate": 3.1885616352242875e-05, - "loss": 3.2684, + "learning_rate": 3.185632195335335e-05, + "loss": 3.2245, "step": 109500 }, { "epoch": 0.36, - "learning_rate": 3.1869073536126206e-05, - "loss": 3.2564, + "learning_rate": 3.1839752384360975e-05, + "loss": 3.2415, "step": 109600 }, { "epoch": 0.36, - "learning_rate": 3.185253072000953e-05, - "loss": 3.2538, + "learning_rate": 3.182318281536861e-05, + "loss": 3.227, "step": 109700 }, { "epoch": 0.36, - "learning_rate": 3.1835987903892855e-05, - "loss": 3.2667, + "learning_rate": 3.180661324637624e-05, + "loss": 3.222, "step": 109800 }, { "epoch": 0.36, - "learning_rate": 3.181944508777619e-05, - "loss": 3.268, + "learning_rate": 3.1790043677383866e-05, + "loss": 3.2142, "step": 109900 }, { "epoch": 0.36, - "learning_rate": 3.180290227165951e-05, - "loss": 3.2611, + "learning_rate": 3.177347410839149e-05, + "loss": 3.2194, "step": 110000 }, { "epoch": 0.36, - "learning_rate": 3.1786359455542836e-05, - "loss": 3.2614, + "learning_rate": 3.1756904539399124e-05, + "loss": 3.2304, "step": 110100 }, { - "epoch": 0.36, - "learning_rate": 3.176981663942617e-05, - "loss": 3.2639, + "epoch": 0.37, + "learning_rate": 3.174033497040675e-05, + "loss": 3.2377, "step": 110200 }, { - "epoch": 0.36, - "learning_rate": 3.175327382330949e-05, - "loss": 3.2461, + "epoch": 0.37, + "learning_rate": 3.172376540141438e-05, + "loss": 3.2376, "step": 110300 }, { "epoch": 0.37, - "learning_rate": 3.1736731007192816e-05, - "loss": 3.2381, + "learning_rate": 3.170719583242201e-05, + "loss": 3.232, "step": 110400 }, { "epoch": 0.37, - "learning_rate": 3.172018819107615e-05, - "loss": 3.2614, + "learning_rate": 3.1690626263429634e-05, + "loss": 3.2356, "step": 110500 }, { "epoch": 0.37, - "learning_rate": 3.170364537495947e-05, - "loss": 3.2706, + "learning_rate": 3.167405669443727e-05, + "loss": 3.223, "step": 110600 }, { "epoch": 0.37, - "learning_rate": 3.1687102558842797e-05, - "loss": 3.2566, + "learning_rate": 3.165748712544489e-05, + "loss": 3.2433, "step": 110700 }, { "epoch": 0.37, - "learning_rate": 3.167055974272613e-05, - "loss": 3.251, + "learning_rate": 3.164091755645252e-05, + "loss": 3.2333, "step": 110800 }, { "epoch": 0.37, - "learning_rate": 3.165401692660945e-05, - "loss": 3.2492, + "learning_rate": 3.162434798746015e-05, + "loss": 3.2223, "step": 110900 }, { "epoch": 0.37, - "learning_rate": 3.163747411049278e-05, - "loss": 3.2478, + "learning_rate": 3.1607778418467784e-05, + "loss": 3.2395, "step": 111000 }, { "epoch": 0.37, - "learning_rate": 3.162093129437611e-05, - "loss": 3.2479, + "learning_rate": 3.159120884947541e-05, + "loss": 3.2346, "step": 111100 }, { "epoch": 0.37, - "learning_rate": 3.160438847825943e-05, - "loss": 3.2489, + "learning_rate": 3.1574639280483035e-05, + "loss": 3.2348, "step": 111200 }, { "epoch": 0.37, - "learning_rate": 3.1587845662142764e-05, - "loss": 3.2688, + "learning_rate": 3.155806971149067e-05, + "loss": 3.2257, "step": 111300 }, { "epoch": 0.37, - "learning_rate": 3.157130284602608e-05, - "loss": 3.2459, + "learning_rate": 3.1541500142498294e-05, + "loss": 3.2289, "step": 111400 }, { "epoch": 0.37, - "learning_rate": 3.155476002990941e-05, - "loss": 3.2491, + "learning_rate": 3.1524930573505926e-05, + "loss": 3.2265, "step": 111500 }, { "epoch": 0.37, - "learning_rate": 3.1538217213792744e-05, - "loss": 3.2474, + "learning_rate": 3.150836100451355e-05, + "loss": 3.2324, "step": 111600 }, { "epoch": 0.37, - "learning_rate": 3.152167439767606e-05, - "loss": 3.2456, + "learning_rate": 3.149179143552118e-05, + "loss": 3.2251, "step": 111700 }, { "epoch": 0.37, - "learning_rate": 3.1505131581559393e-05, - "loss": 3.2515, + "learning_rate": 3.147522186652881e-05, + "loss": 3.2295, "step": 111800 }, { "epoch": 0.37, - "learning_rate": 3.1488588765442725e-05, - "loss": 3.2537, + "learning_rate": 3.1458652297536436e-05, + "loss": 3.2176, "step": 111900 }, { "epoch": 0.37, - "learning_rate": 3.147204594932604e-05, - "loss": 3.2649, + "learning_rate": 3.144208272854406e-05, + "loss": 3.2224, "step": 112000 }, { "epoch": 0.37, - "learning_rate": 3.1455503133209374e-05, - "loss": 3.2436, + "learning_rate": 3.1425513159551695e-05, + "loss": 3.2243, "step": 112100 }, { "epoch": 0.37, - "learning_rate": 3.1438960317092705e-05, - "loss": 3.2633, + "learning_rate": 3.140894359055933e-05, + "loss": 3.2256, "step": 112200 }, { "epoch": 0.37, - "learning_rate": 3.142241750097602e-05, - "loss": 3.2567, + "learning_rate": 3.139237402156695e-05, + "loss": 3.2403, "step": 112300 }, { "epoch": 0.37, - "learning_rate": 3.1405874684859354e-05, - "loss": 3.2506, + "learning_rate": 3.137580445257458e-05, + "loss": 3.2341, "step": 112400 }, { "epoch": 0.37, - "learning_rate": 3.1389331868742686e-05, - "loss": 3.2619, + "learning_rate": 3.135923488358221e-05, + "loss": 3.2252, "step": 112500 }, { "epoch": 0.37, - "learning_rate": 3.1372789052626e-05, - "loss": 3.2337, + "learning_rate": 3.134266531458984e-05, + "loss": 3.2344, "step": 112600 }, { "epoch": 0.37, - "learning_rate": 3.1356246236509335e-05, - "loss": 3.2546, + "learning_rate": 3.132609574559747e-05, + "loss": 3.2295, "step": 112700 }, { "epoch": 0.37, - "learning_rate": 3.1339703420392666e-05, - "loss": 3.2644, + "learning_rate": 3.1309526176605096e-05, + "loss": 3.2217, "step": 112800 }, { "epoch": 0.37, - "learning_rate": 3.1323160604275984e-05, - "loss": 3.2641, + "learning_rate": 3.129295660761272e-05, + "loss": 3.2301, "step": 112900 }, { "epoch": 0.37, - "learning_rate": 3.1306617788159315e-05, - "loss": 3.2572, + "learning_rate": 3.1276387038620354e-05, + "loss": 3.2276, "step": 113000 }, { "epoch": 0.37, - "learning_rate": 3.1290074972042646e-05, - "loss": 3.2529, + "learning_rate": 3.125981746962798e-05, + "loss": 3.2163, "step": 113100 }, { - "epoch": 0.37, - "learning_rate": 3.1273532155925964e-05, - "loss": 3.2674, + "epoch": 0.38, + "learning_rate": 3.1243247900635606e-05, + "loss": 3.2197, "step": 113200 }, { - "epoch": 0.37, - "learning_rate": 3.1256989339809295e-05, - "loss": 3.2632, + "epoch": 0.38, + "learning_rate": 3.122667833164324e-05, + "loss": 3.2331, "step": 113300 }, { "epoch": 0.38, - "learning_rate": 3.124044652369263e-05, - "loss": 3.2638, + "learning_rate": 3.121010876265087e-05, + "loss": 3.2393, "step": 113400 }, { "epoch": 0.38, - "learning_rate": 3.122390370757595e-05, - "loss": 3.2595, + "learning_rate": 3.11935391936585e-05, + "loss": 3.2349, "step": 113500 }, { "epoch": 0.38, - "learning_rate": 3.1207360891459276e-05, - "loss": 3.2524, + "learning_rate": 3.117696962466612e-05, + "loss": 3.2398, "step": 113600 }, { "epoch": 0.38, - "learning_rate": 3.119081807534261e-05, - "loss": 3.2444, + "learning_rate": 3.1160400055673755e-05, + "loss": 3.2226, "step": 113700 }, { "epoch": 0.38, - "learning_rate": 3.117427525922593e-05, - "loss": 3.2588, + "learning_rate": 3.114383048668138e-05, + "loss": 3.235, "step": 113800 }, { "epoch": 0.38, - "learning_rate": 3.1157732443109256e-05, - "loss": 3.2632, + "learning_rate": 3.1127260917689014e-05, + "loss": 3.2323, "step": 113900 }, { "epoch": 0.38, - "learning_rate": 3.114118962699258e-05, - "loss": 3.2611, + "learning_rate": 3.111069134869664e-05, + "loss": 3.2148, "step": 114000 }, { "epoch": 0.38, - "learning_rate": 3.112464681087591e-05, - "loss": 3.2551, + "learning_rate": 3.1094121779704265e-05, + "loss": 3.2374, "step": 114100 }, { "epoch": 0.38, - "learning_rate": 3.1108103994759237e-05, - "loss": 3.2622, + "learning_rate": 3.10775522107119e-05, + "loss": 3.2386, "step": 114200 }, { "epoch": 0.38, - "learning_rate": 3.109156117864256e-05, - "loss": 3.2489, + "learning_rate": 3.106098264171953e-05, + "loss": 3.2384, "step": 114300 }, { "epoch": 0.38, - "learning_rate": 3.107501836252589e-05, - "loss": 3.2541, + "learning_rate": 3.104441307272715e-05, + "loss": 3.2152, "step": 114400 }, { "epoch": 0.38, - "learning_rate": 3.105847554640922e-05, - "loss": 3.2511, + "learning_rate": 3.102784350373478e-05, + "loss": 3.2395, "step": 114500 }, { "epoch": 0.38, - "learning_rate": 3.104193273029254e-05, - "loss": 3.2567, + "learning_rate": 3.1011273934742415e-05, + "loss": 3.2241, "step": 114600 }, { "epoch": 0.38, - "learning_rate": 3.102538991417587e-05, - "loss": 3.2569, + "learning_rate": 3.099470436575004e-05, + "loss": 3.2374, "step": 114700 }, { "epoch": 0.38, - "learning_rate": 3.10088470980592e-05, - "loss": 3.2586, + "learning_rate": 3.0978134796757666e-05, + "loss": 3.2332, "step": 114800 }, { "epoch": 0.38, - "learning_rate": 3.099230428194252e-05, - "loss": 3.2541, + "learning_rate": 3.09615652277653e-05, + "loss": 3.222, "step": 114900 }, { "epoch": 0.38, - "learning_rate": 3.097576146582585e-05, - "loss": 3.256, + "learning_rate": 3.0944995658772925e-05, + "loss": 3.2152, "step": 115000 }, { "epoch": 0.38, - "learning_rate": 3.095921864970918e-05, - "loss": 3.254, + "learning_rate": 3.092842608978056e-05, + "loss": 3.2408, "step": 115100 }, { "epoch": 0.38, - "learning_rate": 3.09426758335925e-05, - "loss": 3.2426, + "learning_rate": 3.091185652078818e-05, + "loss": 3.2377, "step": 115200 }, { "epoch": 0.38, - "learning_rate": 3.0926133017475834e-05, - "loss": 3.2499, + "learning_rate": 3.089528695179581e-05, + "loss": 3.2156, "step": 115300 }, { "epoch": 0.38, - "learning_rate": 3.090959020135916e-05, - "loss": 3.2554, + "learning_rate": 3.087871738280344e-05, + "loss": 3.213, "step": 115400 }, { "epoch": 0.38, - "learning_rate": 3.089304738524248e-05, - "loss": 3.2437, + "learning_rate": 3.0862147813811074e-05, + "loss": 3.2395, "step": 115500 }, { "epoch": 0.38, - "learning_rate": 3.0876504569125814e-05, - "loss": 3.2515, + "learning_rate": 3.084557824481869e-05, + "loss": 3.2366, "step": 115600 }, { "epoch": 0.38, - "learning_rate": 3.0859961753009145e-05, - "loss": 3.2665, + "learning_rate": 3.0829008675826326e-05, + "loss": 3.2261, "step": 115700 }, { "epoch": 0.38, - "learning_rate": 3.084341893689246e-05, - "loss": 3.2462, + "learning_rate": 3.081243910683396e-05, + "loss": 3.2225, "step": 115800 }, { "epoch": 0.38, - "learning_rate": 3.0826876120775794e-05, - "loss": 3.2389, + "learning_rate": 3.0795869537841584e-05, + "loss": 3.2136, "step": 115900 }, { "epoch": 0.38, - "learning_rate": 3.0810333304659126e-05, - "loss": 3.2469, + "learning_rate": 3.077929996884921e-05, + "loss": 3.2334, "step": 116000 }, { "epoch": 0.38, - "learning_rate": 3.079379048854244e-05, - "loss": 3.2634, + "learning_rate": 3.076273039985684e-05, + "loss": 3.2375, "step": 116100 }, { - "epoch": 0.38, - "learning_rate": 3.0777247672425775e-05, - "loss": 3.2555, + "epoch": 0.39, + "learning_rate": 3.074616083086447e-05, + "loss": 3.2291, "step": 116200 }, { - "epoch": 0.38, - "learning_rate": 3.0760704856309106e-05, - "loss": 3.257, - "step": 116300 + "epoch": 0.39, + "learning_rate": 3.07295912618721e-05, + "loss": 3.2267, + "step": 116300 }, { "epoch": 0.39, - "learning_rate": 3.0744162040192424e-05, - "loss": 3.2578, + "learning_rate": 3.071302169287973e-05, + "loss": 3.2334, "step": 116400 }, { "epoch": 0.39, - "learning_rate": 3.0727619224075755e-05, - "loss": 3.2435, + "learning_rate": 3.069645212388735e-05, + "loss": 3.243, "step": 116500 }, { "epoch": 0.39, - "learning_rate": 3.071107640795908e-05, - "loss": 3.2459, + "learning_rate": 3.0679882554894985e-05, + "loss": 3.2383, "step": 116600 }, { "epoch": 0.39, - "learning_rate": 3.0694533591842404e-05, - "loss": 3.2538, + "learning_rate": 3.066331298590262e-05, + "loss": 3.2226, "step": 116700 }, { "epoch": 0.39, - "learning_rate": 3.0677990775725735e-05, - "loss": 3.24, + "learning_rate": 3.064674341691024e-05, + "loss": 3.2293, "step": 116800 }, { "epoch": 0.39, - "learning_rate": 3.066144795960906e-05, - "loss": 3.2555, + "learning_rate": 3.063017384791787e-05, + "loss": 3.2295, "step": 116900 }, { "epoch": 0.39, - "learning_rate": 3.0644905143492384e-05, - "loss": 3.2574, + "learning_rate": 3.06136042789255e-05, + "loss": 3.2255, "step": 117000 }, { "epoch": 0.39, - "learning_rate": 3.0628362327375716e-05, - "loss": 3.247, + "learning_rate": 3.059703470993313e-05, + "loss": 3.2237, "step": 117100 }, { "epoch": 0.39, - "learning_rate": 3.061181951125904e-05, - "loss": 3.2465, + "learning_rate": 3.0580465140940754e-05, + "loss": 3.2296, "step": 117200 }, { "epoch": 0.39, - "learning_rate": 3.0595276695142365e-05, - "loss": 3.264, + "learning_rate": 3.0563895571948386e-05, + "loss": 3.2146, "step": 117300 }, { "epoch": 0.39, - "learning_rate": 3.0578733879025696e-05, - "loss": 3.2506, + "learning_rate": 3.054732600295601e-05, + "loss": 3.233, "step": 117400 }, { "epoch": 0.39, - "learning_rate": 3.056219106290902e-05, - "loss": 3.2582, + "learning_rate": 3.0530756433963645e-05, + "loss": 3.2368, "step": 117500 }, { "epoch": 0.39, - "learning_rate": 3.054564824679235e-05, - "loss": 3.25, + "learning_rate": 3.0514186864971274e-05, + "loss": 3.2226, "step": 117600 }, { "epoch": 0.39, - "learning_rate": 3.0529105430675677e-05, - "loss": 3.2487, + "learning_rate": 3.0497617295978896e-05, + "loss": 3.2194, "step": 117700 }, { "epoch": 0.39, - "learning_rate": 3.0512562614559004e-05, - "loss": 3.242, + "learning_rate": 3.048104772698653e-05, + "loss": 3.2265, "step": 117800 }, { "epoch": 0.39, - "learning_rate": 3.0496019798442332e-05, - "loss": 3.2457, + "learning_rate": 3.046447815799415e-05, + "loss": 3.2417, "step": 117900 }, { "epoch": 0.39, - "learning_rate": 3.0479476982325657e-05, - "loss": 3.2446, + "learning_rate": 3.0447908589001784e-05, + "loss": 3.2405, "step": 118000 }, { "epoch": 0.39, - "learning_rate": 3.0462934166208985e-05, - "loss": 3.248, + "learning_rate": 3.0431339020009413e-05, + "loss": 3.2319, "step": 118100 }, { "epoch": 0.39, - "learning_rate": 3.0446391350092313e-05, - "loss": 3.2506, + "learning_rate": 3.041476945101704e-05, + "loss": 3.2268, "step": 118200 }, { "epoch": 0.39, - "learning_rate": 3.0429848533975634e-05, - "loss": 3.2581, + "learning_rate": 3.0398199882024668e-05, + "loss": 3.2309, "step": 118300 }, { "epoch": 0.39, - "learning_rate": 3.0413305717858965e-05, - "loss": 3.2469, + "learning_rate": 3.03816303130323e-05, + "loss": 3.2208, "step": 118400 }, { "epoch": 0.39, - "learning_rate": 3.0396762901742293e-05, - "loss": 3.2618, + "learning_rate": 3.0365060744039927e-05, + "loss": 3.2245, "step": 118500 }, { "epoch": 0.39, - "learning_rate": 3.0380220085625614e-05, - "loss": 3.2452, + "learning_rate": 3.0348491175047556e-05, + "loss": 3.2487, "step": 118600 }, { "epoch": 0.39, - "learning_rate": 3.0363677269508946e-05, - "loss": 3.2527, + "learning_rate": 3.0331921606055185e-05, + "loss": 3.2202, "step": 118700 }, { "epoch": 0.39, - "learning_rate": 3.0347134453392274e-05, - "loss": 3.2585, + "learning_rate": 3.031535203706281e-05, + "loss": 3.2295, "step": 118800 }, { "epoch": 0.39, - "learning_rate": 3.0330591637275595e-05, - "loss": 3.2476, + "learning_rate": 3.029878246807044e-05, + "loss": 3.2206, "step": 118900 }, { "epoch": 0.39, - "learning_rate": 3.0314048821158926e-05, - "loss": 3.2521, + "learning_rate": 3.0282212899078073e-05, + "loss": 3.2292, "step": 119000 }, { "epoch": 0.39, - "learning_rate": 3.0297506005042254e-05, - "loss": 3.2575, + "learning_rate": 3.02656433300857e-05, + "loss": 3.2261, "step": 119100 }, { - "epoch": 0.39, - "learning_rate": 3.0280963188925575e-05, - "loss": 3.2661, + "epoch": 0.4, + "learning_rate": 3.0249073761093328e-05, + "loss": 3.2271, "step": 119200 }, { - "epoch": 0.39, - "learning_rate": 3.0264420372808906e-05, - "loss": 3.2576, + "epoch": 0.4, + "learning_rate": 3.0232504192100957e-05, + "loss": 3.2221, "step": 119300 }, { "epoch": 0.4, - "learning_rate": 3.0247877556692234e-05, - "loss": 3.2403, + "learning_rate": 3.0215934623108583e-05, + "loss": 3.2278, "step": 119400 }, { "epoch": 0.4, - "learning_rate": 3.0231334740575555e-05, - "loss": 3.253, + "learning_rate": 3.0199365054116212e-05, + "loss": 3.2219, "step": 119500 }, { "epoch": 0.4, - "learning_rate": 3.0214791924458887e-05, - "loss": 3.2435, + "learning_rate": 3.0182795485123844e-05, + "loss": 3.2203, "step": 119600 }, { "epoch": 0.4, - "learning_rate": 3.0198249108342215e-05, - "loss": 3.2379, + "learning_rate": 3.016622591613147e-05, + "loss": 3.2124, "step": 119700 }, { "epoch": 0.4, - "learning_rate": 3.0181706292225543e-05, - "loss": 3.2457, + "learning_rate": 3.01496563471391e-05, + "loss": 3.2194, "step": 119800 }, { "epoch": 0.4, - "learning_rate": 3.0165163476108864e-05, - "loss": 3.2565, + "learning_rate": 3.013308677814673e-05, + "loss": 3.2409, "step": 119900 }, { "epoch": 0.4, - "learning_rate": 3.0148620659992195e-05, - "loss": 3.2483, + "learning_rate": 3.0116517209154354e-05, + "loss": 3.2318, "step": 120000 }, { "epoch": 0.4, - "learning_rate": 3.0132077843875523e-05, - "loss": 3.2476, + "learning_rate": 3.0099947640161984e-05, + "loss": 3.2093, "step": 120100 }, { "epoch": 0.4, - "learning_rate": 3.0115535027758844e-05, - "loss": 3.2481, + "learning_rate": 3.0083378071169616e-05, + "loss": 3.2183, "step": 120200 }, { "epoch": 0.4, - "learning_rate": 3.0098992211642175e-05, - "loss": 3.2485, + "learning_rate": 3.0066808502177242e-05, + "loss": 3.2256, "step": 120300 }, { "epoch": 0.4, - "learning_rate": 3.0082449395525503e-05, - "loss": 3.2542, + "learning_rate": 3.005023893318487e-05, + "loss": 3.227, "step": 120400 }, { "epoch": 0.4, - "learning_rate": 3.0065906579408825e-05, - "loss": 3.2604, + "learning_rate": 3.00336693641925e-05, + "loss": 3.2367, "step": 120500 }, { "epoch": 0.4, - "learning_rate": 3.0049363763292156e-05, - "loss": 3.2569, + "learning_rate": 3.0017099795200126e-05, + "loss": 3.2392, "step": 120600 }, { "epoch": 0.4, - "learning_rate": 3.0032820947175484e-05, - "loss": 3.2416, + "learning_rate": 3.0000530226207755e-05, + "loss": 3.2285, "step": 120700 }, { "epoch": 0.4, - "learning_rate": 3.0016278131058805e-05, - "loss": 3.2531, + "learning_rate": 2.9983960657215388e-05, + "loss": 3.2154, "step": 120800 }, { "epoch": 0.4, - "learning_rate": 2.9999735314942136e-05, - "loss": 3.2484, + "learning_rate": 2.9967391088223014e-05, + "loss": 3.2316, "step": 120900 }, { "epoch": 0.4, - "learning_rate": 2.9983192498825464e-05, - "loss": 3.2483, + "learning_rate": 2.9950821519230643e-05, + "loss": 3.2332, "step": 121000 }, { "epoch": 0.4, - "learning_rate": 2.9966649682708785e-05, - "loss": 3.2284, + "learning_rate": 2.9934251950238272e-05, + "loss": 3.2192, "step": 121100 }, { "epoch": 0.4, - "learning_rate": 2.9950106866592113e-05, - "loss": 3.2521, + "learning_rate": 2.9917682381245898e-05, + "loss": 3.2238, "step": 121200 }, { "epoch": 0.4, - "learning_rate": 2.9933564050475445e-05, - "loss": 3.2531, + "learning_rate": 2.9901112812253527e-05, + "loss": 3.2334, "step": 121300 }, { "epoch": 0.4, - "learning_rate": 2.9917021234358766e-05, - "loss": 3.2729, + "learning_rate": 2.988454324326116e-05, + "loss": 3.2313, "step": 121400 }, { "epoch": 0.4, - "learning_rate": 2.9900478418242094e-05, - "loss": 3.246, + "learning_rate": 2.9867973674268786e-05, + "loss": 3.231, "step": 121500 }, { "epoch": 0.4, - "learning_rate": 2.9883935602125425e-05, - "loss": 3.2473, + "learning_rate": 2.9851404105276415e-05, + "loss": 3.2317, "step": 121600 }, { "epoch": 0.4, - "learning_rate": 2.9867392786008746e-05, - "loss": 3.2486, + "learning_rate": 2.9834834536284044e-05, + "loss": 3.245, "step": 121700 }, { "epoch": 0.4, - "learning_rate": 2.9850849969892074e-05, - "loss": 3.2536, + "learning_rate": 2.981826496729167e-05, + "loss": 3.2195, "step": 121800 }, { "epoch": 0.4, - "learning_rate": 2.9834307153775405e-05, - "loss": 3.2572, + "learning_rate": 2.98016953982993e-05, + "loss": 3.2271, "step": 121900 }, { "epoch": 0.4, - "learning_rate": 2.9817764337658733e-05, - "loss": 3.2524, + "learning_rate": 2.9785125829306932e-05, + "loss": 3.2187, "step": 122000 }, { "epoch": 0.4, - "learning_rate": 2.9801221521542054e-05, - "loss": 3.2476, + "learning_rate": 2.9768556260314558e-05, + "loss": 3.2208, "step": 122100 }, { "epoch": 0.4, - "learning_rate": 2.9784678705425386e-05, - "loss": 3.2344, + "learning_rate": 2.9751986691322187e-05, + "loss": 3.2191, "step": 122200 }, { - "epoch": 0.4, - "learning_rate": 2.9768135889308714e-05, - "loss": 3.2537, + "epoch": 0.41, + "learning_rate": 2.9735417122329816e-05, + "loss": 3.2307, "step": 122300 }, { - "epoch": 0.4, - "learning_rate": 2.9751593073192035e-05, - "loss": 3.2488, + "epoch": 0.41, + "learning_rate": 2.9718847553337442e-05, + "loss": 3.2211, "step": 122400 }, { "epoch": 0.41, - "learning_rate": 2.9735050257075363e-05, - "loss": 3.2463, + "learning_rate": 2.970227798434507e-05, + "loss": 3.2381, "step": 122500 }, { "epoch": 0.41, - "learning_rate": 2.9718507440958694e-05, - "loss": 3.2449, + "learning_rate": 2.9685708415352704e-05, + "loss": 3.2402, "step": 122600 }, { "epoch": 0.41, - "learning_rate": 2.9701964624842015e-05, - "loss": 3.2469, + "learning_rate": 2.966913884636033e-05, + "loss": 3.2266, "step": 122700 }, { "epoch": 0.41, - "learning_rate": 2.9685421808725343e-05, - "loss": 3.2463, + "learning_rate": 2.965256927736796e-05, + "loss": 3.2324, "step": 122800 }, { "epoch": 0.41, - "learning_rate": 2.9668878992608674e-05, - "loss": 3.2526, + "learning_rate": 2.9635999708375588e-05, + "loss": 3.2224, "step": 122900 }, { "epoch": 0.41, - "learning_rate": 2.9652336176491995e-05, - "loss": 3.2531, + "learning_rate": 2.9619430139383214e-05, + "loss": 3.2309, "step": 123000 }, { "epoch": 0.41, - "learning_rate": 2.9635793360375323e-05, - "loss": 3.2586, + "learning_rate": 2.9602860570390846e-05, + "loss": 3.2154, "step": 123100 }, { "epoch": 0.41, - "learning_rate": 2.9619250544258655e-05, - "loss": 3.2502, + "learning_rate": 2.9586291001398475e-05, + "loss": 3.2346, "step": 123200 }, { "epoch": 0.41, - "learning_rate": 2.9602707728141976e-05, - "loss": 3.2462, + "learning_rate": 2.95697214324061e-05, + "loss": 3.2175, "step": 123300 }, { "epoch": 0.41, - "learning_rate": 2.9586164912025304e-05, - "loss": 3.2505, + "learning_rate": 2.955315186341373e-05, + "loss": 3.2232, "step": 123400 }, { "epoch": 0.41, - "learning_rate": 2.9569622095908635e-05, - "loss": 3.2433, + "learning_rate": 2.953658229442136e-05, + "loss": 3.2271, "step": 123500 }, { "epoch": 0.41, - "learning_rate": 2.9553079279791956e-05, - "loss": 3.255, + "learning_rate": 2.9520012725428986e-05, + "loss": 3.2256, "step": 123600 }, { "epoch": 0.41, - "learning_rate": 2.9536536463675284e-05, - "loss": 3.2574, + "learning_rate": 2.9503443156436618e-05, + "loss": 3.2454, "step": 123700 }, { "epoch": 0.41, - "learning_rate": 2.9519993647558612e-05, - "loss": 3.2417, + "learning_rate": 2.9486873587444247e-05, + "loss": 3.2222, "step": 123800 }, { "epoch": 0.41, - "learning_rate": 2.9503450831441937e-05, - "loss": 3.2446, + "learning_rate": 2.9470304018451873e-05, + "loss": 3.2316, "step": 123900 }, { "epoch": 0.41, - "learning_rate": 2.9486908015325265e-05, - "loss": 3.2475, + "learning_rate": 2.9453734449459502e-05, + "loss": 3.2242, "step": 124000 }, { "epoch": 0.41, - "learning_rate": 2.9470365199208592e-05, - "loss": 3.2457, + "learning_rate": 2.943716488046713e-05, + "loss": 3.229, "step": 124100 }, { "epoch": 0.41, - "learning_rate": 2.9453822383091924e-05, - "loss": 3.2543, + "learning_rate": 2.9420595311474757e-05, + "loss": 3.2243, "step": 124200 }, { "epoch": 0.41, - "learning_rate": 2.9437279566975245e-05, - "loss": 3.2416, + "learning_rate": 2.940402574248239e-05, + "loss": 3.2444, "step": 124300 }, { "epoch": 0.41, - "learning_rate": 2.9420736750858573e-05, - "loss": 3.2442, + "learning_rate": 2.938745617349002e-05, + "loss": 3.2197, "step": 124400 }, { "epoch": 0.41, - "learning_rate": 2.9404193934741904e-05, - "loss": 3.2543, + "learning_rate": 2.9370886604497645e-05, + "loss": 3.2308, "step": 124500 }, { "epoch": 0.41, - "learning_rate": 2.9387651118625225e-05, - "loss": 3.2471, + "learning_rate": 2.9354317035505274e-05, + "loss": 3.2265, "step": 124600 }, { "epoch": 0.41, - "learning_rate": 2.9371108302508553e-05, - "loss": 3.2496, + "learning_rate": 2.9337747466512903e-05, + "loss": 3.2085, "step": 124700 }, { "epoch": 0.41, - "learning_rate": 2.9354565486391885e-05, - "loss": 3.2618, + "learning_rate": 2.932117789752053e-05, + "loss": 3.2301, "step": 124800 }, { "epoch": 0.41, - "learning_rate": 2.9338022670275206e-05, - "loss": 3.2468, + "learning_rate": 2.9304608328528162e-05, + "loss": 3.2408, "step": 124900 }, { "epoch": 0.41, - "learning_rate": 2.9321479854158534e-05, - "loss": 3.2503, + "learning_rate": 2.928803875953579e-05, + "loss": 3.2132, "step": 125000 }, { "epoch": 0.41, - "learning_rate": 2.930493703804186e-05, - "loss": 3.2449, + "learning_rate": 2.9271469190543417e-05, + "loss": 3.2224, "step": 125100 }, { "epoch": 0.41, - "learning_rate": 2.9288394221925186e-05, - "loss": 3.2516, + "learning_rate": 2.9254899621551046e-05, + "loss": 3.2286, "step": 125200 }, { - "epoch": 0.41, - "learning_rate": 2.9271851405808514e-05, - "loss": 3.2648, + "epoch": 0.42, + "learning_rate": 2.9238330052558675e-05, + "loss": 3.2283, "step": 125300 }, { - "epoch": 0.41, - "learning_rate": 2.9255308589691842e-05, - "loss": 3.2436, + "epoch": 0.42, + "learning_rate": 2.92217604835663e-05, + "loss": 3.2219, "step": 125400 }, { "epoch": 0.42, - "learning_rate": 2.9238765773575166e-05, - "loss": 3.2397, + "learning_rate": 2.9205190914573934e-05, + "loss": 3.2264, "step": 125500 }, { "epoch": 0.42, - "learning_rate": 2.9222222957458494e-05, - "loss": 3.2397, + "learning_rate": 2.9188621345581563e-05, + "loss": 3.2186, "step": 125600 }, { "epoch": 0.42, - "learning_rate": 2.9205680141341822e-05, - "loss": 3.2437, + "learning_rate": 2.917205177658919e-05, + "loss": 3.2227, "step": 125700 }, { "epoch": 0.42, - "learning_rate": 2.9189137325225147e-05, - "loss": 3.2428, + "learning_rate": 2.9155482207596818e-05, + "loss": 3.232, "step": 125800 }, { "epoch": 0.42, - "learning_rate": 2.9172594509108475e-05, - "loss": 3.2562, + "learning_rate": 2.9138912638604447e-05, + "loss": 3.2313, "step": 125900 }, { "epoch": 0.42, - "learning_rate": 2.9156051692991803e-05, - "loss": 3.2584, + "learning_rate": 2.9122343069612073e-05, + "loss": 3.2293, "step": 126000 }, { "epoch": 0.42, - "learning_rate": 2.9139508876875134e-05, - "loss": 3.2693, + "learning_rate": 2.9105773500619705e-05, + "loss": 3.2284, "step": 126100 }, { "epoch": 0.42, - "learning_rate": 2.9122966060758455e-05, - "loss": 3.2517, + "learning_rate": 2.9089203931627335e-05, + "loss": 3.2362, "step": 126200 }, { "epoch": 0.42, - "learning_rate": 2.9106423244641783e-05, - "loss": 3.2631, + "learning_rate": 2.907263436263496e-05, + "loss": 3.2199, "step": 126300 }, { "epoch": 0.42, - "learning_rate": 2.908988042852511e-05, - "loss": 3.2408, + "learning_rate": 2.905606479364259e-05, + "loss": 3.2282, "step": 126400 }, { "epoch": 0.42, - "learning_rate": 2.9073337612408435e-05, - "loss": 3.2568, + "learning_rate": 2.903949522465022e-05, + "loss": 3.2222, "step": 126500 }, { "epoch": 0.42, - "learning_rate": 2.9056794796291763e-05, - "loss": 3.2513, + "learning_rate": 2.9022925655657845e-05, + "loss": 3.2246, "step": 126600 }, { "epoch": 0.42, - "learning_rate": 2.904025198017509e-05, - "loss": 3.2604, + "learning_rate": 2.9006356086665477e-05, + "loss": 3.2297, "step": 126700 }, { "epoch": 0.42, - "learning_rate": 2.9023709164058416e-05, - "loss": 3.2353, + "learning_rate": 2.89897865176731e-05, + "loss": 3.2119, "step": 126800 }, { "epoch": 0.42, - "learning_rate": 2.9007166347941744e-05, - "loss": 3.2449, + "learning_rate": 2.8973216948680732e-05, + "loss": 3.2196, "step": 126900 }, { "epoch": 0.42, - "learning_rate": 2.8990623531825072e-05, - "loss": 3.2629, + "learning_rate": 2.895664737968836e-05, + "loss": 3.2241, "step": 127000 }, { "epoch": 0.42, - "learning_rate": 2.8974080715708396e-05, - "loss": 3.2463, + "learning_rate": 2.8940077810695987e-05, + "loss": 3.2189, "step": 127100 }, { "epoch": 0.42, - "learning_rate": 2.8957537899591724e-05, - "loss": 3.2455, + "learning_rate": 2.8923508241703617e-05, + "loss": 3.2313, "step": 127200 }, { "epoch": 0.42, - "learning_rate": 2.8940995083475052e-05, - "loss": 3.2578, + "learning_rate": 2.890693867271125e-05, + "loss": 3.2264, "step": 127300 }, { "epoch": 0.42, - "learning_rate": 2.8924452267358377e-05, - "loss": 3.2416, + "learning_rate": 2.889036910371887e-05, + "loss": 3.2281, "step": 127400 }, { "epoch": 0.42, - "learning_rate": 2.8907909451241705e-05, - "loss": 3.2529, + "learning_rate": 2.8873799534726504e-05, + "loss": 3.2295, "step": 127500 }, { "epoch": 0.42, - "learning_rate": 2.8891366635125032e-05, - "loss": 3.2408, + "learning_rate": 2.8857229965734133e-05, + "loss": 3.2186, "step": 127600 }, { "epoch": 0.42, - "learning_rate": 2.8874823819008357e-05, - "loss": 3.2489, + "learning_rate": 2.884066039674176e-05, + "loss": 3.2196, "step": 127700 }, { "epoch": 0.42, - "learning_rate": 2.8858281002891685e-05, - "loss": 3.2468, + "learning_rate": 2.882409082774939e-05, + "loss": 3.2222, "step": 127800 }, { "epoch": 0.42, - "learning_rate": 2.8841738186775013e-05, - "loss": 3.252, + "learning_rate": 2.880752125875702e-05, + "loss": 3.2249, "step": 127900 }, { "epoch": 0.42, - "learning_rate": 2.8825195370658337e-05, - "loss": 3.237, + "learning_rate": 2.8790951689764643e-05, + "loss": 3.2254, "step": 128000 }, { "epoch": 0.42, - "learning_rate": 2.8808652554541665e-05, - "loss": 3.2453, + "learning_rate": 2.8774382120772276e-05, + "loss": 3.2127, "step": 128100 }, { "epoch": 0.42, - "learning_rate": 2.8792109738424993e-05, - "loss": 3.2345, + "learning_rate": 2.8757812551779905e-05, + "loss": 3.2291, "step": 128200 }, { - "epoch": 0.42, - "learning_rate": 2.877556692230832e-05, - "loss": 3.2482, + "epoch": 0.43, + "learning_rate": 2.874124298278753e-05, + "loss": 3.22, "step": 128300 }, { - "epoch": 0.42, - "learning_rate": 2.8759024106191646e-05, - "loss": 3.2486, + "epoch": 0.43, + "learning_rate": 2.872467341379516e-05, + "loss": 3.2345, "step": 128400 }, { "epoch": 0.43, - "learning_rate": 2.8742481290074974e-05, - "loss": 3.2381, + "learning_rate": 2.8708103844802793e-05, + "loss": 3.2199, "step": 128500 }, { "epoch": 0.43, - "learning_rate": 2.87259384739583e-05, - "loss": 3.235, + "learning_rate": 2.8691534275810415e-05, + "loss": 3.2286, "step": 128600 }, { "epoch": 0.43, - "learning_rate": 2.8709395657841626e-05, - "loss": 3.2541, + "learning_rate": 2.8674964706818048e-05, + "loss": 3.2335, "step": 128700 }, { "epoch": 0.43, - "learning_rate": 2.8692852841724954e-05, - "loss": 3.2401, + "learning_rate": 2.8658395137825677e-05, + "loss": 3.2214, "step": 128800 }, { "epoch": 0.43, - "learning_rate": 2.8676310025608282e-05, - "loss": 3.2602, + "learning_rate": 2.8641825568833303e-05, + "loss": 3.221, "step": 128900 }, { "epoch": 0.43, - "learning_rate": 2.8659767209491606e-05, - "loss": 3.2464, + "learning_rate": 2.8625255999840932e-05, + "loss": 3.2138, "step": 129000 }, { "epoch": 0.43, - "learning_rate": 2.8643224393374934e-05, - "loss": 3.23, + "learning_rate": 2.8608686430848565e-05, + "loss": 3.2296, "step": 129100 }, { "epoch": 0.43, - "learning_rate": 2.8626681577258262e-05, - "loss": 3.2497, + "learning_rate": 2.8592116861856187e-05, + "loss": 3.2253, "step": 129200 }, { "epoch": 0.43, - "learning_rate": 2.8610138761141587e-05, - "loss": 3.2428, + "learning_rate": 2.857554729286382e-05, + "loss": 3.2294, "step": 129300 }, { "epoch": 0.43, - "learning_rate": 2.8593595945024915e-05, - "loss": 3.2494, + "learning_rate": 2.855897772387145e-05, + "loss": 3.2132, "step": 129400 }, { "epoch": 0.43, - "learning_rate": 2.8577053128908243e-05, - "loss": 3.249, + "learning_rate": 2.8542408154879075e-05, + "loss": 3.2269, "step": 129500 }, { "epoch": 0.43, - "learning_rate": 2.8560510312791567e-05, - "loss": 3.2527, + "learning_rate": 2.8525838585886704e-05, + "loss": 3.2239, "step": 129600 }, { "epoch": 0.43, - "learning_rate": 2.8543967496674895e-05, - "loss": 3.2407, + "learning_rate": 2.8509269016894337e-05, + "loss": 3.2232, "step": 129700 }, { "epoch": 0.43, - "learning_rate": 2.8527424680558223e-05, - "loss": 3.259, + "learning_rate": 2.849269944790196e-05, + "loss": 3.2173, "step": 129800 }, { "epoch": 0.43, - "learning_rate": 2.8510881864441548e-05, - "loss": 3.2507, + "learning_rate": 2.847612987890959e-05, + "loss": 3.2268, "step": 129900 }, { "epoch": 0.43, - "learning_rate": 2.8494339048324876e-05, - "loss": 3.2468, + "learning_rate": 2.845956030991722e-05, + "loss": 3.2327, "step": 130000 }, { "epoch": 0.43, - "learning_rate": 2.8477796232208203e-05, - "loss": 3.2577, + "learning_rate": 2.8442990740924847e-05, + "loss": 3.2153, "step": 130100 }, { "epoch": 0.43, - "learning_rate": 2.8461253416091528e-05, - "loss": 3.2545, + "learning_rate": 2.8426421171932476e-05, + "loss": 3.2188, "step": 130200 }, { "epoch": 0.43, - "learning_rate": 2.8444710599974856e-05, - "loss": 3.2605, + "learning_rate": 2.840985160294011e-05, + "loss": 3.2433, "step": 130300 }, { "epoch": 0.43, - "learning_rate": 2.8428167783858184e-05, - "loss": 3.2484, + "learning_rate": 2.839328203394773e-05, + "loss": 3.2227, "step": 130400 }, { "epoch": 0.43, - "learning_rate": 2.8411624967741512e-05, - "loss": 3.2433, + "learning_rate": 2.8376712464955363e-05, + "loss": 3.2353, "step": 130500 }, { "epoch": 0.43, - "learning_rate": 2.8395082151624836e-05, - "loss": 3.2461, + "learning_rate": 2.8360142895962993e-05, + "loss": 3.2305, "step": 130600 }, { "epoch": 0.43, - "learning_rate": 2.8378539335508164e-05, - "loss": 3.2434, + "learning_rate": 2.834357332697062e-05, + "loss": 3.2248, "step": 130700 }, { "epoch": 0.43, - "learning_rate": 2.8361996519391492e-05, - "loss": 3.246, + "learning_rate": 2.8327003757978248e-05, + "loss": 3.235, "step": 130800 }, { "epoch": 0.43, - "learning_rate": 2.8345453703274817e-05, - "loss": 3.2424, + "learning_rate": 2.831043418898588e-05, + "loss": 3.2387, "step": 130900 }, { "epoch": 0.43, - "learning_rate": 2.8328910887158145e-05, - "loss": 3.2442, + "learning_rate": 2.8293864619993503e-05, + "loss": 3.2295, "step": 131000 }, { "epoch": 0.43, - "learning_rate": 2.8312368071041473e-05, - "loss": 3.2511, + "learning_rate": 2.8277295051001135e-05, + "loss": 3.2201, "step": 131100 }, { "epoch": 0.43, - "learning_rate": 2.8295825254924797e-05, - "loss": 3.2481, + "learning_rate": 2.8260725482008764e-05, + "loss": 3.2156, "step": 131200 }, { - "epoch": 0.43, - "learning_rate": 2.8279282438808125e-05, - "loss": 3.2603, + "epoch": 0.44, + "learning_rate": 2.824415591301639e-05, + "loss": 3.2252, "step": 131300 }, { - "epoch": 0.43, - "learning_rate": 2.8262739622691453e-05, - "loss": 3.2761, + "epoch": 0.44, + "learning_rate": 2.822758634402402e-05, + "loss": 3.2277, "step": 131400 }, { "epoch": 0.44, - "learning_rate": 2.8246196806574777e-05, - "loss": 3.2635, + "learning_rate": 2.8211016775031652e-05, + "loss": 3.2286, "step": 131500 }, { "epoch": 0.44, - "learning_rate": 2.8229653990458105e-05, - "loss": 3.245, + "learning_rate": 2.8194447206039275e-05, + "loss": 3.2298, "step": 131600 }, { "epoch": 0.44, - "learning_rate": 2.8213111174341433e-05, - "loss": 3.256, + "learning_rate": 2.8177877637046907e-05, + "loss": 3.2223, "step": 131700 }, { "epoch": 0.44, - "learning_rate": 2.8196568358224758e-05, - "loss": 3.2481, + "learning_rate": 2.8161308068054536e-05, + "loss": 3.2411, "step": 131800 }, { "epoch": 0.44, - "learning_rate": 2.8180025542108086e-05, - "loss": 3.2468, + "learning_rate": 2.8144738499062162e-05, + "loss": 3.2296, "step": 131900 }, { "epoch": 0.44, - "learning_rate": 2.8163482725991414e-05, - "loss": 3.2462, + "learning_rate": 2.812816893006979e-05, + "loss": 3.2354, "step": 132000 }, { "epoch": 0.44, - "learning_rate": 2.8146939909874738e-05, - "loss": 3.2508, + "learning_rate": 2.8111599361077424e-05, + "loss": 3.2113, "step": 132100 }, { "epoch": 0.44, - "learning_rate": 2.8130397093758066e-05, - "loss": 3.2519, + "learning_rate": 2.8095029792085046e-05, + "loss": 3.2163, "step": 132200 }, { "epoch": 0.44, - "learning_rate": 2.8113854277641394e-05, - "loss": 3.2456, + "learning_rate": 2.807846022309268e-05, + "loss": 3.2109, "step": 132300 }, { "epoch": 0.44, - "learning_rate": 2.8097311461524722e-05, - "loss": 3.2385, + "learning_rate": 2.8061890654100308e-05, + "loss": 3.2313, "step": 132400 }, { "epoch": 0.44, - "learning_rate": 2.8080768645408046e-05, - "loss": 3.2466, + "learning_rate": 2.8045321085107934e-05, + "loss": 3.2192, "step": 132500 }, { "epoch": 0.44, - "learning_rate": 2.8064225829291374e-05, - "loss": 3.2453, + "learning_rate": 2.8028751516115563e-05, + "loss": 3.2196, "step": 132600 }, { "epoch": 0.44, - "learning_rate": 2.8047683013174702e-05, - "loss": 3.2365, + "learning_rate": 2.8012181947123196e-05, + "loss": 3.2198, "step": 132700 }, { "epoch": 0.44, - "learning_rate": 2.8031140197058027e-05, - "loss": 3.2478, + "learning_rate": 2.799561237813082e-05, + "loss": 3.2182, "step": 132800 }, { "epoch": 0.44, - "learning_rate": 2.8014597380941355e-05, - "loss": 3.2321, + "learning_rate": 2.797904280913845e-05, + "loss": 3.2294, "step": 132900 }, { "epoch": 0.44, - "learning_rate": 2.7998054564824683e-05, - "loss": 3.2555, + "learning_rate": 2.796247324014608e-05, + "loss": 3.2133, "step": 133000 }, { "epoch": 0.44, - "learning_rate": 2.7981511748708007e-05, - "loss": 3.2502, + "learning_rate": 2.7945903671153706e-05, + "loss": 3.2242, "step": 133100 }, { "epoch": 0.44, - "learning_rate": 2.7964968932591335e-05, - "loss": 3.2376, + "learning_rate": 2.7929334102161335e-05, + "loss": 3.2268, "step": 133200 }, { "epoch": 0.44, - "learning_rate": 2.7948426116474663e-05, - "loss": 3.2628, + "learning_rate": 2.7912764533168968e-05, + "loss": 3.2337, "step": 133300 }, { "epoch": 0.44, - "learning_rate": 2.7931883300357988e-05, - "loss": 3.239, + "learning_rate": 2.7896194964176593e-05, + "loss": 3.215, "step": 133400 }, { "epoch": 0.44, - "learning_rate": 2.7915340484241316e-05, - "loss": 3.2512, + "learning_rate": 2.7879625395184223e-05, + "loss": 3.2271, "step": 133500 }, { "epoch": 0.44, - "learning_rate": 2.7898797668124643e-05, - "loss": 3.2568, + "learning_rate": 2.7863055826191852e-05, + "loss": 3.2246, "step": 133600 }, { "epoch": 0.44, - "learning_rate": 2.7882254852007965e-05, - "loss": 3.2496, + "learning_rate": 2.7846486257199478e-05, + "loss": 3.2251, "step": 133700 }, { "epoch": 0.44, - "learning_rate": 2.7865712035891296e-05, - "loss": 3.2565, + "learning_rate": 2.7829916688207107e-05, + "loss": 3.2179, "step": 133800 }, { "epoch": 0.44, - "learning_rate": 2.7849169219774624e-05, - "loss": 3.2547, + "learning_rate": 2.781334711921474e-05, + "loss": 3.2296, "step": 133900 }, { "epoch": 0.44, - "learning_rate": 2.7832626403657945e-05, - "loss": 3.2583, + "learning_rate": 2.7796777550222365e-05, + "loss": 3.2174, "step": 134000 }, { "epoch": 0.44, - "learning_rate": 2.7816083587541276e-05, - "loss": 3.2532, + "learning_rate": 2.7780207981229994e-05, + "loss": 3.2197, "step": 134100 }, { "epoch": 0.44, - "learning_rate": 2.7799540771424604e-05, - "loss": 3.2361, + "learning_rate": 2.7763638412237624e-05, + "loss": 3.2132, "step": 134200 }, { - "epoch": 0.44, - "learning_rate": 2.7782997955307925e-05, - "loss": 3.2337, + "epoch": 0.45, + "learning_rate": 2.774706884324525e-05, + "loss": 3.2248, "step": 134300 }, { - "epoch": 0.44, - "learning_rate": 2.7766455139191257e-05, - "loss": 3.2601, + "epoch": 0.45, + "learning_rate": 2.773049927425288e-05, + "loss": 3.2264, "step": 134400 }, { "epoch": 0.45, - "learning_rate": 2.7749912323074585e-05, - "loss": 3.2302, + "learning_rate": 2.771392970526051e-05, + "loss": 3.2295, "step": 134500 }, { "epoch": 0.45, - "learning_rate": 2.7733369506957913e-05, - "loss": 3.2384, + "learning_rate": 2.7697360136268137e-05, + "loss": 3.2363, "step": 134600 }, { "epoch": 0.45, - "learning_rate": 2.7716826690841237e-05, - "loss": 3.2524, + "learning_rate": 2.7680790567275766e-05, + "loss": 3.2137, "step": 134700 }, { "epoch": 0.45, - "learning_rate": 2.7700283874724565e-05, - "loss": 3.2321, + "learning_rate": 2.7664220998283396e-05, + "loss": 3.2227, "step": 134800 }, { "epoch": 0.45, - "learning_rate": 2.7683741058607893e-05, - "loss": 3.2429, + "learning_rate": 2.764765142929102e-05, + "loss": 3.2089, "step": 134900 }, { "epoch": 0.45, - "learning_rate": 2.7667198242491214e-05, - "loss": 3.2487, + "learning_rate": 2.763108186029865e-05, + "loss": 3.2158, "step": 135000 }, { "epoch": 0.45, - "learning_rate": 2.7650655426374545e-05, - "loss": 3.2382, + "learning_rate": 2.7614512291306283e-05, + "loss": 3.2242, "step": 135100 }, { "epoch": 0.45, - "learning_rate": 2.7634112610257873e-05, - "loss": 3.2676, + "learning_rate": 2.759794272231391e-05, + "loss": 3.2298, "step": 135200 }, { "epoch": 0.45, - "learning_rate": 2.7617569794141194e-05, - "loss": 3.2454, + "learning_rate": 2.7581373153321538e-05, + "loss": 3.2311, "step": 135300 }, { "epoch": 0.45, - "learning_rate": 2.7601026978024526e-05, - "loss": 3.2544, + "learning_rate": 2.7564803584329164e-05, + "loss": 3.2269, "step": 135400 }, { "epoch": 0.45, - "learning_rate": 2.7584484161907854e-05, - "loss": 3.2345, + "learning_rate": 2.7548234015336793e-05, + "loss": 3.2398, "step": 135500 }, { "epoch": 0.45, - "learning_rate": 2.7567941345791175e-05, - "loss": 3.2416, + "learning_rate": 2.7531664446344422e-05, + "loss": 3.2279, "step": 135600 }, { "epoch": 0.45, - "learning_rate": 2.7551398529674506e-05, - "loss": 3.2517, + "learning_rate": 2.7515094877352048e-05, + "loss": 3.2175, "step": 135700 }, { "epoch": 0.45, - "learning_rate": 2.7534855713557834e-05, - "loss": 3.2491, + "learning_rate": 2.749852530835968e-05, + "loss": 3.2316, "step": 135800 }, { "epoch": 0.45, - "learning_rate": 2.7518312897441155e-05, - "loss": 3.2563, + "learning_rate": 2.748195573936731e-05, + "loss": 3.2238, "step": 135900 }, { "epoch": 0.45, - "learning_rate": 2.7501770081324487e-05, - "loss": 3.2486, + "learning_rate": 2.7465386170374936e-05, + "loss": 3.1977, "step": 136000 }, { "epoch": 0.45, - "learning_rate": 2.7485227265207814e-05, - "loss": 3.2351, + "learning_rate": 2.7448816601382565e-05, + "loss": 3.2147, "step": 136100 }, { "epoch": 0.45, - "learning_rate": 2.7468684449091136e-05, - "loss": 3.2413, + "learning_rate": 2.7432247032390194e-05, + "loss": 3.2307, "step": 136200 }, { "epoch": 0.45, - "learning_rate": 2.7452141632974464e-05, - "loss": 3.2481, + "learning_rate": 2.741567746339782e-05, + "loss": 3.2341, "step": 136300 }, { "epoch": 0.45, - "learning_rate": 2.7435598816857795e-05, - "loss": 3.2446, + "learning_rate": 2.7399107894405453e-05, + "loss": 3.2241, "step": 136400 }, { "epoch": 0.45, - "learning_rate": 2.7419056000741116e-05, - "loss": 3.2651, + "learning_rate": 2.7382538325413082e-05, + "loss": 3.2129, "step": 136500 }, { "epoch": 0.45, - "learning_rate": 2.7402513184624444e-05, - "loss": 3.2315, + "learning_rate": 2.7365968756420708e-05, + "loss": 3.224, "step": 136600 }, { "epoch": 0.45, - "learning_rate": 2.7385970368507775e-05, - "loss": 3.2531, + "learning_rate": 2.7349399187428337e-05, + "loss": 3.2184, "step": 136700 }, { "epoch": 0.45, - "learning_rate": 2.7369427552391103e-05, - "loss": 3.2483, + "learning_rate": 2.733282961843597e-05, + "loss": 3.2284, "step": 136800 }, { "epoch": 0.45, - "learning_rate": 2.7352884736274424e-05, - "loss": 3.2523, + "learning_rate": 2.7316260049443592e-05, + "loss": 3.2366, "step": 136900 }, { "epoch": 0.45, - "learning_rate": 2.7336341920157756e-05, - "loss": 3.2586, + "learning_rate": 2.7299690480451225e-05, + "loss": 3.2337, "step": 137000 }, { "epoch": 0.45, - "learning_rate": 2.7319799104041083e-05, - "loss": 3.2489, + "learning_rate": 2.7283120911458854e-05, + "loss": 3.2357, "step": 137100 }, { "epoch": 0.45, - "learning_rate": 2.7303256287924405e-05, - "loss": 3.2367, + "learning_rate": 2.726655134246648e-05, + "loss": 3.2118, "step": 137200 }, { - "epoch": 0.45, - "learning_rate": 2.7286713471807736e-05, - "loss": 3.2464, + "epoch": 0.46, + "learning_rate": 2.724998177347411e-05, + "loss": 3.2289, "step": 137300 }, { - "epoch": 0.45, - "learning_rate": 2.7270170655691064e-05, - "loss": 3.238, + "epoch": 0.46, + "learning_rate": 2.723341220448174e-05, + "loss": 3.2298, "step": 137400 }, { - "epoch": 0.45, - "learning_rate": 2.7253627839574385e-05, - "loss": 3.2439, + "epoch": 0.46, + "learning_rate": 2.7216842635489364e-05, + "loss": 3.2182, "step": 137500 }, { "epoch": 0.46, - "learning_rate": 2.7237085023457713e-05, - "loss": 3.2541, + "learning_rate": 2.7200273066496996e-05, + "loss": 3.2296, "step": 137600 }, { "epoch": 0.46, - "learning_rate": 2.7220542207341044e-05, - "loss": 3.2535, + "learning_rate": 2.7183703497504626e-05, + "loss": 3.2118, "step": 137700 }, { "epoch": 0.46, - "learning_rate": 2.7203999391224365e-05, - "loss": 3.2317, + "learning_rate": 2.716713392851225e-05, + "loss": 3.2149, "step": 137800 }, { "epoch": 0.46, - "learning_rate": 2.7187456575107693e-05, - "loss": 3.2556, + "learning_rate": 2.715056435951988e-05, + "loss": 3.2249, "step": 137900 }, { "epoch": 0.46, - "learning_rate": 2.7170913758991025e-05, - "loss": 3.2629, + "learning_rate": 2.7133994790527513e-05, + "loss": 3.2382, "step": 138000 }, { "epoch": 0.46, - "learning_rate": 2.7154370942874346e-05, - "loss": 3.2423, + "learning_rate": 2.7117425221535136e-05, + "loss": 3.217, "step": 138100 }, { "epoch": 0.46, - "learning_rate": 2.7137828126757674e-05, - "loss": 3.2539, + "learning_rate": 2.7100855652542768e-05, + "loss": 3.2368, "step": 138200 }, { "epoch": 0.46, - "learning_rate": 2.7121285310641005e-05, - "loss": 3.2593, + "learning_rate": 2.7084286083550397e-05, + "loss": 3.2178, "step": 138300 }, { "epoch": 0.46, - "learning_rate": 2.7104742494524326e-05, - "loss": 3.2425, + "learning_rate": 2.7067716514558023e-05, + "loss": 3.2173, "step": 138400 }, { "epoch": 0.46, - "learning_rate": 2.7088199678407654e-05, - "loss": 3.2566, + "learning_rate": 2.7051146945565652e-05, + "loss": 3.2224, "step": 138500 }, { "epoch": 0.46, - "learning_rate": 2.7071656862290985e-05, - "loss": 3.2485, + "learning_rate": 2.7034577376573285e-05, + "loss": 3.2209, "step": 138600 }, { "epoch": 0.46, - "learning_rate": 2.7055114046174307e-05, - "loss": 3.2414, + "learning_rate": 2.7018007807580907e-05, + "loss": 3.2192, "step": 138700 }, { "epoch": 0.46, - "learning_rate": 2.7038571230057634e-05, - "loss": 3.2584, + "learning_rate": 2.700143823858854e-05, + "loss": 3.2266, "step": 138800 }, { "epoch": 0.46, - "learning_rate": 2.7022028413940962e-05, - "loss": 3.257, + "learning_rate": 2.698486866959617e-05, + "loss": 3.2137, "step": 138900 }, { "epoch": 0.46, - "learning_rate": 2.7005485597824294e-05, - "loss": 3.2496, + "learning_rate": 2.6968299100603795e-05, + "loss": 3.2217, "step": 139000 }, { "epoch": 0.46, - "learning_rate": 2.6988942781707615e-05, - "loss": 3.2441, + "learning_rate": 2.6951729531611424e-05, + "loss": 3.2383, "step": 139100 }, { "epoch": 0.46, - "learning_rate": 2.6972399965590943e-05, - "loss": 3.2497, + "learning_rate": 2.6935159962619057e-05, + "loss": 3.2284, "step": 139200 }, { "epoch": 0.46, - "learning_rate": 2.6955857149474274e-05, - "loss": 3.245, + "learning_rate": 2.691859039362668e-05, + "loss": 3.2103, "step": 139300 }, { "epoch": 0.46, - "learning_rate": 2.6939314333357595e-05, - "loss": 3.2491, + "learning_rate": 2.6902020824634312e-05, + "loss": 3.2048, "step": 139400 }, { "epoch": 0.46, - "learning_rate": 2.6922771517240923e-05, - "loss": 3.2447, + "learning_rate": 2.688545125564194e-05, + "loss": 3.2156, "step": 139500 }, { "epoch": 0.46, - "learning_rate": 2.6906228701124254e-05, - "loss": 3.241, + "learning_rate": 2.6868881686649567e-05, + "loss": 3.2312, "step": 139600 }, { "epoch": 0.46, - "learning_rate": 2.6889685885007576e-05, - "loss": 3.2374, + "learning_rate": 2.6852312117657196e-05, + "loss": 3.2305, "step": 139700 }, { "epoch": 0.46, - "learning_rate": 2.6873143068890904e-05, - "loss": 3.2395, + "learning_rate": 2.683574254866483e-05, + "loss": 3.2263, "step": 139800 }, { "epoch": 0.46, - "learning_rate": 2.6856600252774235e-05, - "loss": 3.2537, + "learning_rate": 2.681917297967245e-05, + "loss": 3.22, "step": 139900 }, { "epoch": 0.46, - "learning_rate": 2.6840057436657556e-05, - "loss": 3.2505, + "learning_rate": 2.6802603410680084e-05, + "loss": 3.2181, "step": 140000 }, { "epoch": 0.46, - "learning_rate": 2.6823514620540884e-05, - "loss": 3.2474, + "learning_rate": 2.6786033841687713e-05, + "loss": 3.2224, "step": 140100 }, { "epoch": 0.46, - "learning_rate": 2.6806971804424212e-05, - "loss": 3.2571, + "learning_rate": 2.676946427269534e-05, + "loss": 3.2351, "step": 140200 }, { "epoch": 0.46, - "learning_rate": 2.6790428988307536e-05, - "loss": 3.2573, + "learning_rate": 2.6752894703702968e-05, + "loss": 3.2244, "step": 140300 }, { - "epoch": 0.46, - "learning_rate": 2.6773886172190864e-05, - "loss": 3.2363, + "epoch": 0.47, + "learning_rate": 2.67363251347106e-05, + "loss": 3.225, "step": 140400 }, { - "epoch": 0.46, - "learning_rate": 2.6757343356074192e-05, - "loss": 3.243, + "epoch": 0.47, + "learning_rate": 2.6719755565718223e-05, + "loss": 3.2308, "step": 140500 }, { "epoch": 0.47, - "learning_rate": 2.6740800539957517e-05, - "loss": 3.2355, + "learning_rate": 2.6703185996725856e-05, + "loss": 3.2282, "step": 140600 }, { "epoch": 0.47, - "learning_rate": 2.6724257723840845e-05, - "loss": 3.2466, + "learning_rate": 2.6686616427733485e-05, + "loss": 3.2132, "step": 140700 }, { "epoch": 0.47, - "learning_rate": 2.6707714907724173e-05, - "loss": 3.2434, + "learning_rate": 2.667004685874111e-05, + "loss": 3.2157, "step": 140800 }, { "epoch": 0.47, - "learning_rate": 2.6691172091607504e-05, - "loss": 3.2513, + "learning_rate": 2.665347728974874e-05, + "loss": 3.2119, "step": 140900 }, { "epoch": 0.47, - "learning_rate": 2.6674629275490825e-05, - "loss": 3.2277, + "learning_rate": 2.6636907720756372e-05, + "loss": 3.2202, "step": 141000 }, { "epoch": 0.47, - "learning_rate": 2.6658086459374153e-05, - "loss": 3.2501, + "learning_rate": 2.6620338151763995e-05, + "loss": 3.2244, "step": 141100 }, { "epoch": 0.47, - "learning_rate": 2.6641543643257484e-05, - "loss": 3.2502, + "learning_rate": 2.6603768582771627e-05, + "loss": 3.2192, "step": 141200 }, { "epoch": 0.47, - "learning_rate": 2.6625000827140805e-05, - "loss": 3.241, + "learning_rate": 2.6587199013779257e-05, + "loss": 3.2168, "step": 141300 }, { "epoch": 0.47, - "learning_rate": 2.6608458011024133e-05, - "loss": 3.2506, + "learning_rate": 2.6570629444786882e-05, + "loss": 3.2163, "step": 141400 }, { "epoch": 0.47, - "learning_rate": 2.659191519490746e-05, - "loss": 3.2479, + "learning_rate": 2.655405987579451e-05, + "loss": 3.2176, "step": 141500 }, { "epoch": 0.47, - "learning_rate": 2.6575372378790786e-05, - "loss": 3.2357, + "learning_rate": 2.6537490306802144e-05, + "loss": 3.2219, "step": 141600 }, { "epoch": 0.47, - "learning_rate": 2.6558829562674114e-05, - "loss": 3.2455, + "learning_rate": 2.6520920737809767e-05, + "loss": 3.2229, "step": 141700 }, { "epoch": 0.47, - "learning_rate": 2.654228674655744e-05, - "loss": 3.2284, + "learning_rate": 2.65043511688174e-05, + "loss": 3.2251, "step": 141800 }, { "epoch": 0.47, - "learning_rate": 2.6525743930440766e-05, - "loss": 3.2365, + "learning_rate": 2.648778159982503e-05, + "loss": 3.2147, "step": 141900 }, { "epoch": 0.47, - "learning_rate": 2.6509201114324094e-05, - "loss": 3.2395, + "learning_rate": 2.6471212030832654e-05, + "loss": 3.2329, "step": 142000 }, { "epoch": 0.47, - "learning_rate": 2.6492658298207422e-05, - "loss": 3.2453, + "learning_rate": 2.6454642461840283e-05, + "loss": 3.2006, "step": 142100 }, { "epoch": 0.47, - "learning_rate": 2.6476115482090747e-05, - "loss": 3.2582, + "learning_rate": 2.6438072892847916e-05, + "loss": 3.2302, "step": 142200 }, { "epoch": 0.47, - "learning_rate": 2.6459572665974074e-05, - "loss": 3.2534, + "learning_rate": 2.642150332385554e-05, + "loss": 3.2187, "step": 142300 }, { "epoch": 0.47, - "learning_rate": 2.6443029849857402e-05, - "loss": 3.2494, + "learning_rate": 2.640493375486317e-05, + "loss": 3.2308, "step": 142400 }, { "epoch": 0.47, - "learning_rate": 2.6426487033740727e-05, - "loss": 3.2501, + "learning_rate": 2.63883641858708e-05, + "loss": 3.2184, "step": 142500 }, { "epoch": 0.47, - "learning_rate": 2.6409944217624055e-05, - "loss": 3.2483, + "learning_rate": 2.6371794616878426e-05, + "loss": 3.2199, "step": 142600 }, { "epoch": 0.47, - "learning_rate": 2.6393401401507383e-05, - "loss": 3.2448, + "learning_rate": 2.6355225047886055e-05, + "loss": 3.2249, "step": 142700 }, { "epoch": 0.47, - "learning_rate": 2.6376858585390707e-05, - "loss": 3.2458, + "learning_rate": 2.6338655478893688e-05, + "loss": 3.221, "step": 142800 }, { "epoch": 0.47, - "learning_rate": 2.6360315769274035e-05, - "loss": 3.2339, + "learning_rate": 2.632208590990131e-05, + "loss": 3.2254, "step": 142900 }, { "epoch": 0.47, - "learning_rate": 2.6343772953157363e-05, - "loss": 3.2389, + "learning_rate": 2.6305516340908943e-05, + "loss": 3.2197, "step": 143000 }, { "epoch": 0.47, - "learning_rate": 2.632723013704069e-05, - "loss": 3.248, + "learning_rate": 2.6288946771916572e-05, + "loss": 3.2145, "step": 143100 }, { "epoch": 0.47, - "learning_rate": 2.6310687320924016e-05, - "loss": 3.248, + "learning_rate": 2.6272377202924198e-05, + "loss": 3.2317, "step": 143200 }, { "epoch": 0.47, - "learning_rate": 2.6294144504807344e-05, - "loss": 3.2443, + "learning_rate": 2.6255807633931827e-05, + "loss": 3.2097, "step": 143300 }, { - "epoch": 0.47, - "learning_rate": 2.627760168869067e-05, - "loss": 3.2322, + "epoch": 0.48, + "learning_rate": 2.623923806493946e-05, + "loss": 3.2249, "step": 143400 }, { - "epoch": 0.47, - "learning_rate": 2.6261058872573996e-05, - "loss": 3.2485, + "epoch": 0.48, + "learning_rate": 2.6222668495947082e-05, + "loss": 3.2229, "step": 143500 }, { "epoch": 0.48, - "learning_rate": 2.6244516056457324e-05, - "loss": 3.2461, + "learning_rate": 2.6206098926954715e-05, + "loss": 3.2314, "step": 143600 }, { "epoch": 0.48, - "learning_rate": 2.6227973240340652e-05, - "loss": 3.2513, + "learning_rate": 2.6189529357962344e-05, + "loss": 3.2178, "step": 143700 }, { "epoch": 0.48, - "learning_rate": 2.6211430424223976e-05, - "loss": 3.2507, + "learning_rate": 2.617295978896997e-05, + "loss": 3.219, "step": 143800 }, { "epoch": 0.48, - "learning_rate": 2.6194887608107304e-05, - "loss": 3.2368, + "learning_rate": 2.61563902199776e-05, + "loss": 3.2161, "step": 143900 }, { "epoch": 0.48, - "learning_rate": 2.6178344791990632e-05, - "loss": 3.2569, + "learning_rate": 2.613982065098523e-05, + "loss": 3.2139, "step": 144000 }, { "epoch": 0.48, - "learning_rate": 2.6161801975873957e-05, - "loss": 3.2391, + "learning_rate": 2.6123251081992854e-05, + "loss": 3.2303, "step": 144100 }, { "epoch": 0.48, - "learning_rate": 2.6145259159757285e-05, - "loss": 3.2445, + "learning_rate": 2.6106681513000487e-05, + "loss": 3.2213, "step": 144200 }, { "epoch": 0.48, - "learning_rate": 2.6128716343640613e-05, - "loss": 3.2527, + "learning_rate": 2.6090111944008112e-05, + "loss": 3.2237, "step": 144300 }, { "epoch": 0.48, - "learning_rate": 2.6112173527523937e-05, - "loss": 3.2566, + "learning_rate": 2.607354237501574e-05, + "loss": 3.2234, "step": 144400 }, { "epoch": 0.48, - "learning_rate": 2.6095630711407265e-05, - "loss": 3.2522, + "learning_rate": 2.605697280602337e-05, + "loss": 3.2243, "step": 144500 }, { "epoch": 0.48, - "learning_rate": 2.6079087895290593e-05, - "loss": 3.2488, + "learning_rate": 2.6040403237030997e-05, + "loss": 3.2164, "step": 144600 }, { "epoch": 0.48, - "learning_rate": 2.6062545079173918e-05, - "loss": 3.2339, + "learning_rate": 2.6023833668038626e-05, + "loss": 3.2225, "step": 144700 }, { "epoch": 0.48, - "learning_rate": 2.6046002263057245e-05, - "loss": 3.2459, + "learning_rate": 2.600726409904626e-05, + "loss": 3.2298, "step": 144800 }, { "epoch": 0.48, - "learning_rate": 2.6029459446940573e-05, - "loss": 3.2285, + "learning_rate": 2.5990694530053884e-05, + "loss": 3.2206, "step": 144900 }, { "epoch": 0.48, - "learning_rate": 2.6012916630823898e-05, - "loss": 3.2396, + "learning_rate": 2.5974124961061514e-05, + "loss": 3.2198, "step": 145000 }, { "epoch": 0.48, - "learning_rate": 2.5996373814707226e-05, - "loss": 3.2382, + "learning_rate": 2.5957555392069143e-05, + "loss": 3.2283, "step": 145100 }, { "epoch": 0.48, - "learning_rate": 2.5979830998590554e-05, - "loss": 3.2432, + "learning_rate": 2.594098582307677e-05, + "loss": 3.2158, "step": 145200 }, { "epoch": 0.48, - "learning_rate": 2.596328818247388e-05, - "loss": 3.2278, + "learning_rate": 2.5924416254084398e-05, + "loss": 3.2232, "step": 145300 }, { "epoch": 0.48, - "learning_rate": 2.5946745366357206e-05, - "loss": 3.2369, + "learning_rate": 2.590784668509203e-05, + "loss": 3.2186, "step": 145400 }, { "epoch": 0.48, - "learning_rate": 2.5930202550240534e-05, - "loss": 3.2431, + "learning_rate": 2.5891277116099656e-05, + "loss": 3.2297, "step": 145500 }, { "epoch": 0.48, - "learning_rate": 2.5913659734123862e-05, - "loss": 3.2232, + "learning_rate": 2.5874707547107285e-05, + "loss": 3.23, "step": 145600 }, { "epoch": 0.48, - "learning_rate": 2.5897116918007187e-05, - "loss": 3.2485, + "learning_rate": 2.5858137978114915e-05, + "loss": 3.2242, "step": 145700 }, { "epoch": 0.48, - "learning_rate": 2.5880574101890515e-05, - "loss": 3.2377, + "learning_rate": 2.584156840912254e-05, + "loss": 3.2239, "step": 145800 }, { "epoch": 0.48, - "learning_rate": 2.5864031285773842e-05, - "loss": 3.2466, + "learning_rate": 2.582499884013017e-05, + "loss": 3.2156, "step": 145900 }, { "epoch": 0.48, - "learning_rate": 2.5847488469657167e-05, - "loss": 3.2489, + "learning_rate": 2.5808429271137802e-05, + "loss": 3.2097, "step": 146000 }, { "epoch": 0.48, - "learning_rate": 2.5830945653540495e-05, - "loss": 3.2454, + "learning_rate": 2.5791859702145428e-05, + "loss": 3.2027, "step": 146100 }, { "epoch": 0.48, - "learning_rate": 2.5814402837423823e-05, - "loss": 3.2343, + "learning_rate": 2.5775290133153057e-05, + "loss": 3.2147, "step": 146200 }, { "epoch": 0.48, - "learning_rate": 2.5797860021307147e-05, - "loss": 3.2482, + "learning_rate": 2.5758720564160686e-05, + "loss": 3.2159, "step": 146300 }, { - "epoch": 0.48, - "learning_rate": 2.5781317205190475e-05, - "loss": 3.2507, + "epoch": 0.49, + "learning_rate": 2.5742150995168312e-05, + "loss": 3.213, "step": 146400 }, { - "epoch": 0.48, - "learning_rate": 2.5764774389073803e-05, - "loss": 3.249, + "epoch": 0.49, + "learning_rate": 2.5725581426175945e-05, + "loss": 3.2189, "step": 146500 }, { "epoch": 0.49, - "learning_rate": 2.5748231572957128e-05, - "loss": 3.242, + "learning_rate": 2.5709011857183574e-05, + "loss": 3.2198, "step": 146600 }, { "epoch": 0.49, - "learning_rate": 2.5731688756840456e-05, - "loss": 3.2409, + "learning_rate": 2.56924422881912e-05, + "loss": 3.2303, "step": 146700 }, { "epoch": 0.49, - "learning_rate": 2.5715145940723784e-05, - "loss": 3.2478, + "learning_rate": 2.567587271919883e-05, + "loss": 3.2105, "step": 146800 }, { "epoch": 0.49, - "learning_rate": 2.5698603124607108e-05, - "loss": 3.2529, + "learning_rate": 2.5659303150206458e-05, + "loss": 3.2282, "step": 146900 }, { "epoch": 0.49, - "learning_rate": 2.5682060308490436e-05, - "loss": 3.2355, + "learning_rate": 2.5642733581214084e-05, + "loss": 3.2173, "step": 147000 }, { "epoch": 0.49, - "learning_rate": 2.5665517492373764e-05, - "loss": 3.2612, + "learning_rate": 2.5626164012221717e-05, + "loss": 3.2143, "step": 147100 }, { "epoch": 0.49, - "learning_rate": 2.564897467625709e-05, - "loss": 3.2357, + "learning_rate": 2.5609594443229346e-05, + "loss": 3.2082, "step": 147200 }, { "epoch": 0.49, - "learning_rate": 2.5632431860140416e-05, - "loss": 3.2423, + "learning_rate": 2.559302487423697e-05, + "loss": 3.2274, "step": 147300 }, { "epoch": 0.49, - "learning_rate": 2.5615889044023744e-05, - "loss": 3.2307, + "learning_rate": 2.55764553052446e-05, + "loss": 3.2419, "step": 147400 }, { "epoch": 0.49, - "learning_rate": 2.5599346227907072e-05, - "loss": 3.2371, + "learning_rate": 2.555988573625223e-05, + "loss": 3.2227, "step": 147500 }, { "epoch": 0.49, - "learning_rate": 2.5582803411790397e-05, - "loss": 3.2437, + "learning_rate": 2.5543316167259856e-05, + "loss": 3.2344, "step": 147600 }, { "epoch": 0.49, - "learning_rate": 2.5566260595673725e-05, - "loss": 3.2424, + "learning_rate": 2.552674659826749e-05, + "loss": 3.2287, "step": 147700 }, { "epoch": 0.49, - "learning_rate": 2.5549717779557053e-05, - "loss": 3.2416, + "learning_rate": 2.5510177029275118e-05, + "loss": 3.2179, "step": 147800 }, { "epoch": 0.49, - "learning_rate": 2.5533174963440377e-05, - "loss": 3.2388, + "learning_rate": 2.5493607460282744e-05, + "loss": 3.2217, "step": 147900 }, { "epoch": 0.49, - "learning_rate": 2.5516632147323705e-05, - "loss": 3.2432, + "learning_rate": 2.5477037891290373e-05, + "loss": 3.2359, "step": 148000 }, { "epoch": 0.49, - "learning_rate": 2.5500089331207033e-05, - "loss": 3.235, + "learning_rate": 2.5460468322298002e-05, + "loss": 3.2277, "step": 148100 }, { "epoch": 0.49, - "learning_rate": 2.5483546515090358e-05, - "loss": 3.2333, + "learning_rate": 2.5443898753305628e-05, + "loss": 3.2103, "step": 148200 }, { "epoch": 0.49, - "learning_rate": 2.5467003698973685e-05, - "loss": 3.2502, + "learning_rate": 2.542732918431326e-05, + "loss": 3.213, "step": 148300 }, { "epoch": 0.49, - "learning_rate": 2.5450460882857013e-05, - "loss": 3.2537, + "learning_rate": 2.541075961532089e-05, + "loss": 3.2063, "step": 148400 }, { "epoch": 0.49, - "learning_rate": 2.5433918066740338e-05, - "loss": 3.2347, + "learning_rate": 2.5394190046328515e-05, + "loss": 3.2153, "step": 148500 }, { "epoch": 0.49, - "learning_rate": 2.5417375250623666e-05, - "loss": 3.2508, + "learning_rate": 2.5377620477336145e-05, + "loss": 3.2187, "step": 148600 }, { "epoch": 0.49, - "learning_rate": 2.5400832434506994e-05, - "loss": 3.2562, + "learning_rate": 2.5361050908343774e-05, + "loss": 3.2132, "step": 148700 }, { "epoch": 0.49, - "learning_rate": 2.538428961839032e-05, - "loss": 3.2432, + "learning_rate": 2.53444813393514e-05, + "loss": 3.2091, "step": 148800 }, { "epoch": 0.49, - "learning_rate": 2.5367746802273646e-05, - "loss": 3.2292, + "learning_rate": 2.5327911770359032e-05, + "loss": 3.2153, "step": 148900 }, { "epoch": 0.49, - "learning_rate": 2.5351203986156974e-05, - "loss": 3.2329, + "learning_rate": 2.531134220136666e-05, + "loss": 3.2265, "step": 149000 }, { "epoch": 0.49, - "learning_rate": 2.5334661170040295e-05, - "loss": 3.2463, + "learning_rate": 2.5294772632374287e-05, + "loss": 3.2141, "step": 149100 }, { "epoch": 0.49, - "learning_rate": 2.5318118353923627e-05, - "loss": 3.2461, + "learning_rate": 2.5278203063381916e-05, + "loss": 3.2269, "step": 149200 }, { "epoch": 0.49, - "learning_rate": 2.5301575537806955e-05, - "loss": 3.2421, + "learning_rate": 2.5261633494389546e-05, + "loss": 3.2248, "step": 149300 }, { - "epoch": 0.49, - "learning_rate": 2.5285032721690282e-05, - "loss": 3.2611, + "epoch": 0.5, + "learning_rate": 2.524506392539717e-05, + "loss": 3.2274, "step": 149400 }, { - "epoch": 0.49, - "learning_rate": 2.5268489905573607e-05, - "loss": 3.2355, + "epoch": 0.5, + "learning_rate": 2.5228494356404804e-05, + "loss": 3.2308, "step": 149500 }, { - "epoch": 0.49, - "learning_rate": 2.5251947089456935e-05, - "loss": 3.2306, + "epoch": 0.5, + "learning_rate": 2.5211924787412433e-05, + "loss": 3.2069, "step": 149600 }, { "epoch": 0.5, - "learning_rate": 2.5235404273340263e-05, - "loss": 3.2521, + "learning_rate": 2.519535521842006e-05, + "loss": 3.2335, "step": 149700 }, { "epoch": 0.5, - "learning_rate": 2.5218861457223587e-05, - "loss": 3.2594, + "learning_rate": 2.5178785649427688e-05, + "loss": 3.223, "step": 149800 }, { "epoch": 0.5, - "learning_rate": 2.5202318641106915e-05, - "loss": 3.2526, + "learning_rate": 2.5162216080435317e-05, + "loss": 3.23, "step": 149900 }, { "epoch": 0.5, - "learning_rate": 2.5185775824990243e-05, - "loss": 3.2341, + "learning_rate": 2.5145646511442943e-05, + "loss": 3.2203, "step": 150000 }, { "epoch": 0.5, - "learning_rate": 2.5169233008873568e-05, - "loss": 3.2307, + "learning_rate": 2.5129076942450576e-05, + "loss": 3.2192, "step": 150100 }, { "epoch": 0.5, - "learning_rate": 2.5152690192756896e-05, - "loss": 3.2473, + "learning_rate": 2.5112507373458205e-05, + "loss": 3.2091, "step": 150200 }, { "epoch": 0.5, - "learning_rate": 2.5136147376640224e-05, - "loss": 3.2472, + "learning_rate": 2.509593780446583e-05, + "loss": 3.2199, "step": 150300 }, { "epoch": 0.5, - "learning_rate": 2.5119604560523545e-05, - "loss": 3.249, + "learning_rate": 2.507936823547346e-05, + "loss": 3.2189, "step": 150400 }, { "epoch": 0.5, - "learning_rate": 2.5103061744406876e-05, - "loss": 3.2448, + "learning_rate": 2.506279866648109e-05, + "loss": 3.2123, "step": 150500 }, { "epoch": 0.5, - "learning_rate": 2.5086518928290204e-05, - "loss": 3.2359, + "learning_rate": 2.5046229097488715e-05, + "loss": 3.2053, "step": 150600 }, { "epoch": 0.5, - "learning_rate": 2.5069976112173525e-05, - "loss": 3.2416, + "learning_rate": 2.5029659528496348e-05, + "loss": 3.2243, "step": 150700 }, { "epoch": 0.5, - "learning_rate": 2.5053433296056856e-05, - "loss": 3.2408, + "learning_rate": 2.5013089959503977e-05, + "loss": 3.2081, "step": 150800 }, { "epoch": 0.5, - "learning_rate": 2.5036890479940184e-05, - "loss": 3.2398, + "learning_rate": 2.4996520390511603e-05, + "loss": 3.2182, "step": 150900 }, { "epoch": 0.5, - "learning_rate": 2.5020347663823506e-05, - "loss": 3.2477, + "learning_rate": 2.4979950821519232e-05, + "loss": 3.2189, "step": 151000 }, { "epoch": 0.5, - "learning_rate": 2.5003804847706837e-05, - "loss": 3.2486, + "learning_rate": 2.496338125252686e-05, + "loss": 3.2217, "step": 151100 }, { "epoch": 0.5, - "learning_rate": 2.4987262031590165e-05, - "loss": 3.2229, + "learning_rate": 2.4946811683534487e-05, + "loss": 3.2156, "step": 151200 }, { "epoch": 0.5, - "learning_rate": 2.497071921547349e-05, - "loss": 3.2583, + "learning_rate": 2.493024211454212e-05, + "loss": 3.2229, "step": 151300 }, { "epoch": 0.5, - "learning_rate": 2.4954176399356817e-05, - "loss": 3.2412, + "learning_rate": 2.4913672545549745e-05, + "loss": 3.2108, "step": 151400 }, { "epoch": 0.5, - "learning_rate": 2.4937633583240145e-05, - "loss": 3.2396, + "learning_rate": 2.4897102976557375e-05, + "loss": 3.2318, "step": 151500 }, { "epoch": 0.5, - "learning_rate": 2.492109076712347e-05, - "loss": 3.24, + "learning_rate": 2.4880533407565004e-05, + "loss": 3.2274, "step": 151600 }, { "epoch": 0.5, - "learning_rate": 2.4904547951006794e-05, - "loss": 3.2408, + "learning_rate": 2.4863963838572633e-05, + "loss": 3.212, "step": 151700 }, { "epoch": 0.5, - "learning_rate": 2.4888005134890126e-05, - "loss": 3.2473, + "learning_rate": 2.484739426958026e-05, + "loss": 3.2243, "step": 151800 }, { "epoch": 0.5, - "learning_rate": 2.487146231877345e-05, - "loss": 3.2522, + "learning_rate": 2.483082470058789e-05, + "loss": 3.2059, "step": 151900 }, { "epoch": 0.5, - "learning_rate": 2.4854919502656778e-05, - "loss": 3.2365, + "learning_rate": 2.4814255131595517e-05, + "loss": 3.2264, "step": 152000 }, { "epoch": 0.5, - "learning_rate": 2.4838376686540106e-05, - "loss": 3.2455, + "learning_rate": 2.4797685562603146e-05, + "loss": 3.2324, "step": 152100 }, { "epoch": 0.5, - "learning_rate": 2.482183387042343e-05, - "loss": 3.2273, + "learning_rate": 2.4781115993610776e-05, + "loss": 3.2233, "step": 152200 }, { "epoch": 0.5, - "learning_rate": 2.480529105430676e-05, - "loss": 3.249, + "learning_rate": 2.4764546424618405e-05, + "loss": 3.2342, "step": 152300 }, { - "epoch": 0.5, - "learning_rate": 2.4788748238190086e-05, - "loss": 3.2422, + "epoch": 0.51, + "learning_rate": 2.474797685562603e-05, + "loss": 3.2193, "step": 152400 }, { - "epoch": 0.5, - "learning_rate": 2.477220542207341e-05, - "loss": 3.2458, + "epoch": 0.51, + "learning_rate": 2.4731407286633663e-05, + "loss": 3.2501, "step": 152500 }, { - "epoch": 0.5, - "learning_rate": 2.475566260595674e-05, - "loss": 3.2415, + "epoch": 0.51, + "learning_rate": 2.471483771764129e-05, + "loss": 3.2225, "step": 152600 }, { "epoch": 0.51, - "learning_rate": 2.4739119789840067e-05, - "loss": 3.236, + "learning_rate": 2.4698268148648918e-05, + "loss": 3.2076, "step": 152700 }, { "epoch": 0.51, - "learning_rate": 2.472257697372339e-05, - "loss": 3.2522, + "learning_rate": 2.4681698579656547e-05, + "loss": 3.2151, "step": 152800 }, { "epoch": 0.51, - "learning_rate": 2.470603415760672e-05, - "loss": 3.2642, + "learning_rate": 2.4665129010664177e-05, + "loss": 3.2064, "step": 152900 }, { "epoch": 0.51, - "learning_rate": 2.4689491341490044e-05, - "loss": 3.2393, + "learning_rate": 2.4648559441671803e-05, + "loss": 3.2132, "step": 153000 }, { "epoch": 0.51, - "learning_rate": 2.4672948525373375e-05, - "loss": 3.2341, + "learning_rate": 2.4631989872679435e-05, + "loss": 3.2306, "step": 153100 }, { "epoch": 0.51, - "learning_rate": 2.46564057092567e-05, - "loss": 3.2309, + "learning_rate": 2.461542030368706e-05, + "loss": 3.2373, "step": 153200 }, { "epoch": 0.51, - "learning_rate": 2.4639862893140024e-05, - "loss": 3.2424, + "learning_rate": 2.459885073469469e-05, + "loss": 3.2166, "step": 153300 }, { "epoch": 0.51, - "learning_rate": 2.4623320077023355e-05, - "loss": 3.2388, + "learning_rate": 2.458228116570232e-05, + "loss": 3.2198, "step": 153400 }, { "epoch": 0.51, - "learning_rate": 2.460677726090668e-05, - "loss": 3.232, + "learning_rate": 2.456571159670995e-05, + "loss": 3.2135, "step": 153500 }, { "epoch": 0.51, - "learning_rate": 2.4590234444790004e-05, - "loss": 3.2512, + "learning_rate": 2.4549142027717574e-05, + "loss": 3.2008, "step": 153600 }, { "epoch": 0.51, - "learning_rate": 2.4573691628673336e-05, - "loss": 3.2486, + "learning_rate": 2.4532572458725207e-05, + "loss": 3.215, "step": 153700 }, { "epoch": 0.51, - "learning_rate": 2.455714881255666e-05, - "loss": 3.2348, + "learning_rate": 2.4516002889732833e-05, + "loss": 3.2426, "step": 153800 }, { "epoch": 0.51, - "learning_rate": 2.4540605996439985e-05, - "loss": 3.2378, + "learning_rate": 2.4499433320740462e-05, + "loss": 3.2137, "step": 153900 }, { "epoch": 0.51, - "learning_rate": 2.4524063180323316e-05, - "loss": 3.2338, + "learning_rate": 2.448286375174809e-05, + "loss": 3.2177, "step": 154000 }, { "epoch": 0.51, - "learning_rate": 2.450752036420664e-05, - "loss": 3.2389, + "learning_rate": 2.446629418275572e-05, + "loss": 3.2256, "step": 154100 }, { "epoch": 0.51, - "learning_rate": 2.449097754808997e-05, - "loss": 3.2448, + "learning_rate": 2.4449724613763346e-05, + "loss": 3.2111, "step": 154200 }, { "epoch": 0.51, - "learning_rate": 2.4474434731973293e-05, - "loss": 3.2481, + "learning_rate": 2.443315504477098e-05, + "loss": 3.2284, "step": 154300 }, { "epoch": 0.51, - "learning_rate": 2.445789191585662e-05, - "loss": 3.2331, + "learning_rate": 2.4416585475778605e-05, + "loss": 3.2174, "step": 154400 }, { "epoch": 0.51, - "learning_rate": 2.444134909973995e-05, - "loss": 3.244, + "learning_rate": 2.4400015906786234e-05, + "loss": 3.2156, "step": 154500 }, { "epoch": 0.51, - "learning_rate": 2.4424806283623273e-05, - "loss": 3.2427, + "learning_rate": 2.4383446337793863e-05, + "loss": 3.2307, "step": 154600 }, { "epoch": 0.51, - "learning_rate": 2.44082634675066e-05, - "loss": 3.2379, + "learning_rate": 2.4366876768801492e-05, + "loss": 3.2055, "step": 154700 }, { "epoch": 0.51, - "learning_rate": 2.439172065138993e-05, - "loss": 3.2518, + "learning_rate": 2.4350307199809118e-05, + "loss": 3.2108, "step": 154800 }, { "epoch": 0.51, - "learning_rate": 2.4375177835273254e-05, - "loss": 3.2453, + "learning_rate": 2.433373763081675e-05, + "loss": 3.2131, "step": 154900 }, { "epoch": 0.51, - "learning_rate": 2.4358635019156582e-05, - "loss": 3.257, + "learning_rate": 2.4317168061824376e-05, + "loss": 3.212, "step": 155000 }, { "epoch": 0.51, - "learning_rate": 2.434209220303991e-05, - "loss": 3.2442, + "learning_rate": 2.4300598492832006e-05, + "loss": 3.2146, "step": 155100 }, { "epoch": 0.51, - "learning_rate": 2.4325549386923234e-05, - "loss": 3.2417, + "learning_rate": 2.428402892383963e-05, + "loss": 3.2176, "step": 155200 }, { "epoch": 0.51, - "learning_rate": 2.4309006570806566e-05, - "loss": 3.2312, + "learning_rate": 2.4267459354847264e-05, + "loss": 3.2155, "step": 155300 }, { "epoch": 0.51, - "learning_rate": 2.429246375468989e-05, - "loss": 3.2477, + "learning_rate": 2.425088978585489e-05, + "loss": 3.2257, "step": 155400 }, { - "epoch": 0.51, - "learning_rate": 2.4275920938573215e-05, - "loss": 3.2444, + "epoch": 0.52, + "learning_rate": 2.423432021686252e-05, + "loss": 3.2212, "step": 155500 }, { - "epoch": 0.51, - "learning_rate": 2.4259378122456543e-05, - "loss": 3.2474, + "epoch": 0.52, + "learning_rate": 2.421775064787015e-05, + "loss": 3.2313, "step": 155600 }, { "epoch": 0.52, - "learning_rate": 2.424283530633987e-05, - "loss": 3.2493, + "learning_rate": 2.4201181078877778e-05, + "loss": 3.2174, "step": 155700 }, { "epoch": 0.52, - "learning_rate": 2.4226292490223195e-05, - "loss": 3.2478, + "learning_rate": 2.4184611509885403e-05, + "loss": 3.2207, "step": 155800 }, { "epoch": 0.52, - "learning_rate": 2.4209749674106523e-05, - "loss": 3.2394, + "learning_rate": 2.4168041940893036e-05, + "loss": 3.2239, "step": 155900 }, { "epoch": 0.52, - "learning_rate": 2.419320685798985e-05, - "loss": 3.2324, + "learning_rate": 2.4151472371900662e-05, + "loss": 3.2188, "step": 156000 }, { "epoch": 0.52, - "learning_rate": 2.4176664041873175e-05, - "loss": 3.246, + "learning_rate": 2.413490280290829e-05, + "loss": 3.2222, "step": 156100 }, { "epoch": 0.52, - "learning_rate": 2.4160121225756503e-05, - "loss": 3.2348, + "learning_rate": 2.411833323391592e-05, + "loss": 3.2209, "step": 156200 }, { "epoch": 0.52, - "learning_rate": 2.414357840963983e-05, - "loss": 3.2305, + "learning_rate": 2.410176366492355e-05, + "loss": 3.2226, "step": 156300 }, { "epoch": 0.52, - "learning_rate": 2.412703559352316e-05, - "loss": 3.2474, + "learning_rate": 2.4085194095931175e-05, + "loss": 3.2146, "step": 156400 }, { "epoch": 0.52, - "learning_rate": 2.4110492777406484e-05, - "loss": 3.2417, + "learning_rate": 2.4068624526938808e-05, + "loss": 3.2019, "step": 156500 }, { "epoch": 0.52, - "learning_rate": 2.409394996128981e-05, - "loss": 3.2415, + "learning_rate": 2.4052054957946434e-05, + "loss": 3.213, "step": 156600 }, { "epoch": 0.52, - "learning_rate": 2.407740714517314e-05, - "loss": 3.2402, + "learning_rate": 2.4035485388954063e-05, + "loss": 3.2051, "step": 156700 }, { "epoch": 0.52, - "learning_rate": 2.4060864329056464e-05, - "loss": 3.2335, + "learning_rate": 2.4018915819961692e-05, + "loss": 3.2262, "step": 156800 }, { "epoch": 0.52, - "learning_rate": 2.4044321512939792e-05, - "loss": 3.237, + "learning_rate": 2.400234625096932e-05, + "loss": 3.2098, "step": 156900 }, { "epoch": 0.52, - "learning_rate": 2.402777869682312e-05, - "loss": 3.2325, + "learning_rate": 2.3985776681976947e-05, + "loss": 3.2209, "step": 157000 }, { "epoch": 0.52, - "learning_rate": 2.4011235880706444e-05, - "loss": 3.2442, + "learning_rate": 2.396920711298458e-05, + "loss": 3.2172, "step": 157100 }, { "epoch": 0.52, - "learning_rate": 2.3994693064589772e-05, - "loss": 3.2521, + "learning_rate": 2.3952637543992205e-05, + "loss": 3.2234, "step": 157200 }, { "epoch": 0.52, - "learning_rate": 2.39781502484731e-05, - "loss": 3.2446, + "learning_rate": 2.3936067974999835e-05, + "loss": 3.2136, "step": 157300 }, { "epoch": 0.52, - "learning_rate": 2.3961607432356425e-05, - "loss": 3.2415, + "learning_rate": 2.3919498406007464e-05, + "loss": 3.2271, "step": 157400 }, { "epoch": 0.52, - "learning_rate": 2.3945064616239753e-05, - "loss": 3.2497, + "learning_rate": 2.3902928837015093e-05, + "loss": 3.2114, "step": 157500 }, { "epoch": 0.52, - "learning_rate": 2.392852180012308e-05, - "loss": 3.2431, + "learning_rate": 2.388635926802272e-05, + "loss": 3.2014, "step": 157600 }, { "epoch": 0.52, - "learning_rate": 2.3911978984006405e-05, - "loss": 3.2538, + "learning_rate": 2.386978969903035e-05, + "loss": 3.2182, "step": 157700 }, { "epoch": 0.52, - "learning_rate": 2.3895436167889733e-05, - "loss": 3.2418, + "learning_rate": 2.3853220130037977e-05, + "loss": 3.2097, "step": 157800 }, { "epoch": 0.52, - "learning_rate": 2.387889335177306e-05, - "loss": 3.2394, + "learning_rate": 2.3836650561045606e-05, + "loss": 3.222, "step": 157900 }, { "epoch": 0.52, - "learning_rate": 2.3862350535656386e-05, - "loss": 3.2354, + "learning_rate": 2.3820080992053236e-05, + "loss": 3.2259, "step": 158000 }, { "epoch": 0.52, - "learning_rate": 2.3845807719539713e-05, - "loss": 3.2503, + "learning_rate": 2.3803511423060865e-05, + "loss": 3.2167, "step": 158100 }, { "epoch": 0.52, - "learning_rate": 2.382926490342304e-05, - "loss": 3.2458, + "learning_rate": 2.378694185406849e-05, + "loss": 3.2333, "step": 158200 }, { "epoch": 0.52, - "learning_rate": 2.3812722087306366e-05, - "loss": 3.2393, + "learning_rate": 2.3770372285076123e-05, + "loss": 3.2201, "step": 158300 }, { "epoch": 0.52, - "learning_rate": 2.3796179271189694e-05, - "loss": 3.2412, + "learning_rate": 2.375380271608375e-05, + "loss": 3.2387, "step": 158400 }, { - "epoch": 0.52, - "learning_rate": 2.3779636455073022e-05, - "loss": 3.2515, + "epoch": 0.53, + "learning_rate": 2.373723314709138e-05, + "loss": 3.2158, "step": 158500 }, { - "epoch": 0.52, - "learning_rate": 2.376309363895635e-05, - "loss": 3.2411, + "epoch": 0.53, + "learning_rate": 2.3720663578099008e-05, + "loss": 3.2183, "step": 158600 }, { "epoch": 0.53, - "learning_rate": 2.3746550822839674e-05, - "loss": 3.2439, + "learning_rate": 2.3704094009106637e-05, + "loss": 3.2102, "step": 158700 }, { "epoch": 0.53, - "learning_rate": 2.3730008006723002e-05, - "loss": 3.2328, + "learning_rate": 2.3687524440114266e-05, + "loss": 3.2226, "step": 158800 }, { "epoch": 0.53, - "learning_rate": 2.371346519060633e-05, - "loss": 3.2493, + "learning_rate": 2.3670954871121895e-05, + "loss": 3.21, "step": 158900 }, { "epoch": 0.53, - "learning_rate": 2.3696922374489655e-05, - "loss": 3.2349, + "learning_rate": 2.365438530212952e-05, + "loss": 3.1934, "step": 159000 }, { "epoch": 0.53, - "learning_rate": 2.3680379558372983e-05, - "loss": 3.2485, + "learning_rate": 2.363781573313715e-05, + "loss": 3.2183, "step": 159100 }, { "epoch": 0.53, - "learning_rate": 2.366383674225631e-05, - "loss": 3.2378, + "learning_rate": 2.362124616414478e-05, + "loss": 3.2046, "step": 159200 }, { "epoch": 0.53, - "learning_rate": 2.3647293926139635e-05, - "loss": 3.2567, + "learning_rate": 2.360467659515241e-05, + "loss": 3.2182, "step": 159300 }, { "epoch": 0.53, - "learning_rate": 2.3630751110022963e-05, - "loss": 3.2457, + "learning_rate": 2.3588107026160038e-05, + "loss": 3.2251, "step": 159400 }, { "epoch": 0.53, - "learning_rate": 2.361420829390629e-05, - "loss": 3.2408, + "learning_rate": 2.3571537457167664e-05, + "loss": 3.2097, "step": 159500 }, { "epoch": 0.53, - "learning_rate": 2.3597665477789615e-05, - "loss": 3.2504, + "learning_rate": 2.3554967888175293e-05, + "loss": 3.2196, "step": 159600 }, { "epoch": 0.53, - "learning_rate": 2.3581122661672943e-05, - "loss": 3.2181, + "learning_rate": 2.3538398319182922e-05, + "loss": 3.2091, "step": 159700 }, { "epoch": 0.53, - "learning_rate": 2.356457984555627e-05, - "loss": 3.2452, + "learning_rate": 2.352182875019055e-05, + "loss": 3.2071, "step": 159800 }, { "epoch": 0.53, - "learning_rate": 2.3548037029439596e-05, - "loss": 3.2495, + "learning_rate": 2.350525918119818e-05, + "loss": 3.2071, "step": 159900 }, { "epoch": 0.53, - "learning_rate": 2.3531494213322924e-05, - "loss": 3.2336, + "learning_rate": 2.348868961220581e-05, + "loss": 3.2082, "step": 160000 }, { "epoch": 0.53, - "learning_rate": 2.351495139720625e-05, - "loss": 3.2378, + "learning_rate": 2.3472120043213435e-05, + "loss": 3.2178, "step": 160100 }, { "epoch": 0.53, - "learning_rate": 2.3498408581089576e-05, - "loss": 3.2335, + "learning_rate": 2.3455550474221065e-05, + "loss": 3.2252, "step": 160200 }, { "epoch": 0.53, - "learning_rate": 2.3481865764972904e-05, - "loss": 3.2521, + "learning_rate": 2.3438980905228694e-05, + "loss": 3.2326, "step": 160300 }, { "epoch": 0.53, - "learning_rate": 2.3465322948856232e-05, - "loss": 3.2371, + "learning_rate": 2.3422411336236323e-05, + "loss": 3.2149, "step": 160400 }, { "epoch": 0.53, - "learning_rate": 2.344878013273956e-05, - "loss": 3.243, + "learning_rate": 2.3405841767243952e-05, + "loss": 3.2187, "step": 160500 }, { "epoch": 0.53, - "learning_rate": 2.3432237316622884e-05, - "loss": 3.2391, + "learning_rate": 2.338927219825158e-05, + "loss": 3.2216, "step": 160600 }, { "epoch": 0.53, - "learning_rate": 2.341569450050621e-05, - "loss": 3.2362, + "learning_rate": 2.3372702629259207e-05, + "loss": 3.2157, "step": 160700 }, { "epoch": 0.53, - "learning_rate": 2.339915168438954e-05, - "loss": 3.2409, + "learning_rate": 2.335613306026684e-05, + "loss": 3.2188, "step": 160800 }, { "epoch": 0.53, - "learning_rate": 2.3382608868272865e-05, - "loss": 3.2338, + "learning_rate": 2.3339563491274466e-05, + "loss": 3.2099, "step": 160900 }, { "epoch": 0.53, - "learning_rate": 2.336606605215619e-05, - "loss": 3.2346, + "learning_rate": 2.3322993922282095e-05, + "loss": 3.2184, "step": 161000 }, { "epoch": 0.53, - "learning_rate": 2.334952323603952e-05, - "loss": 3.2359, + "learning_rate": 2.3306424353289724e-05, + "loss": 3.2162, "step": 161100 }, { "epoch": 0.53, - "learning_rate": 2.3332980419922845e-05, - "loss": 3.2422, + "learning_rate": 2.3289854784297353e-05, + "loss": 3.2167, "step": 161200 }, { "epoch": 0.53, - "learning_rate": 2.331643760380617e-05, - "loss": 3.2396, + "learning_rate": 2.327328521530498e-05, + "loss": 3.2164, "step": 161300 }, { "epoch": 0.53, - "learning_rate": 2.32998947876895e-05, - "loss": 3.2392, + "learning_rate": 2.3256715646312612e-05, + "loss": 3.2222, "step": 161400 }, { - "epoch": 0.53, - "learning_rate": 2.3283351971572826e-05, - "loss": 3.2409, + "epoch": 0.54, + "learning_rate": 2.3240146077320238e-05, + "loss": 3.2174, "step": 161500 }, { - "epoch": 0.53, - "learning_rate": 2.3266809155456154e-05, - "loss": 3.2508, + "epoch": 0.54, + "learning_rate": 2.3223576508327867e-05, + "loss": 3.2111, "step": 161600 }, { - "epoch": 0.53, - "learning_rate": 2.325026633933948e-05, - "loss": 3.2347, + "epoch": 0.54, + "learning_rate": 2.3207006939335496e-05, + "loss": 3.2132, "step": 161700 }, { "epoch": 0.54, - "learning_rate": 2.3233723523222806e-05, - "loss": 3.2474, + "learning_rate": 2.3190437370343125e-05, + "loss": 3.2218, "step": 161800 }, { "epoch": 0.54, - "learning_rate": 2.3217180707106134e-05, - "loss": 3.2473, + "learning_rate": 2.317386780135075e-05, + "loss": 3.2056, "step": 161900 }, { "epoch": 0.54, - "learning_rate": 2.320063789098946e-05, - "loss": 3.24, + "learning_rate": 2.3157298232358384e-05, + "loss": 3.2133, "step": 162000 }, { "epoch": 0.54, - "learning_rate": 2.3184095074872786e-05, - "loss": 3.2291, + "learning_rate": 2.314072866336601e-05, + "loss": 3.2275, "step": 162100 }, { "epoch": 0.54, - "learning_rate": 2.3167552258756114e-05, - "loss": 3.2368, + "learning_rate": 2.312415909437364e-05, + "loss": 3.2189, "step": 162200 }, { "epoch": 0.54, - "learning_rate": 2.315100944263944e-05, - "loss": 3.246, + "learning_rate": 2.3107589525381268e-05, + "loss": 3.2206, "step": 162300 }, { "epoch": 0.54, - "learning_rate": 2.3134466626522767e-05, - "loss": 3.2411, + "learning_rate": 2.3091019956388897e-05, + "loss": 3.2203, "step": 162400 }, { "epoch": 0.54, - "learning_rate": 2.3117923810406095e-05, - "loss": 3.2544, + "learning_rate": 2.3074450387396523e-05, + "loss": 3.2114, "step": 162500 }, { "epoch": 0.54, - "learning_rate": 2.310138099428942e-05, - "loss": 3.2261, + "learning_rate": 2.3057880818404155e-05, + "loss": 3.2298, "step": 162600 }, { "epoch": 0.54, - "learning_rate": 2.308483817817275e-05, - "loss": 3.2463, + "learning_rate": 2.304131124941178e-05, + "loss": 3.2187, "step": 162700 }, { "epoch": 0.54, - "learning_rate": 2.3068295362056075e-05, - "loss": 3.2444, + "learning_rate": 2.302474168041941e-05, + "loss": 3.2125, "step": 162800 }, { "epoch": 0.54, - "learning_rate": 2.30517525459394e-05, - "loss": 3.2472, + "learning_rate": 2.300817211142704e-05, + "loss": 3.2196, "step": 162900 }, { "epoch": 0.54, - "learning_rate": 2.303520972982273e-05, - "loss": 3.2331, + "learning_rate": 2.299160254243467e-05, + "loss": 3.2183, "step": 163000 }, { "epoch": 0.54, - "learning_rate": 2.3018666913706055e-05, - "loss": 3.2528, + "learning_rate": 2.2975032973442295e-05, + "loss": 3.2161, "step": 163100 }, { "epoch": 0.54, - "learning_rate": 2.300212409758938e-05, - "loss": 3.2472, + "learning_rate": 2.2958463404449927e-05, + "loss": 3.2134, "step": 163200 }, { "epoch": 0.54, - "learning_rate": 2.2985581281472708e-05, - "loss": 3.2289, + "learning_rate": 2.2941893835457553e-05, + "loss": 3.2221, "step": 163300 }, { "epoch": 0.54, - "learning_rate": 2.2969038465356036e-05, - "loss": 3.2396, + "learning_rate": 2.2925324266465182e-05, + "loss": 3.2096, "step": 163400 }, { "epoch": 0.54, - "learning_rate": 2.295249564923936e-05, - "loss": 3.236, + "learning_rate": 2.290875469747281e-05, + "loss": 3.2248, "step": 163500 }, { "epoch": 0.54, - "learning_rate": 2.2935952833122688e-05, - "loss": 3.2404, + "learning_rate": 2.289218512848044e-05, + "loss": 3.2274, "step": 163600 }, { "epoch": 0.54, - "learning_rate": 2.2919410017006016e-05, - "loss": 3.2232, + "learning_rate": 2.2875615559488067e-05, + "loss": 3.226, "step": 163700 }, { "epoch": 0.54, - "learning_rate": 2.2902867200889344e-05, - "loss": 3.2322, + "learning_rate": 2.2859045990495696e-05, + "loss": 3.2257, "step": 163800 }, { "epoch": 0.54, - "learning_rate": 2.288632438477267e-05, - "loss": 3.2399, + "learning_rate": 2.2842476421503325e-05, + "loss": 3.2302, "step": 163900 }, { "epoch": 0.54, - "learning_rate": 2.2869781568655997e-05, - "loss": 3.2422, + "learning_rate": 2.2825906852510954e-05, + "loss": 3.2168, "step": 164000 }, { "epoch": 0.54, - "learning_rate": 2.2853238752539324e-05, - "loss": 3.2393, + "learning_rate": 2.280933728351858e-05, + "loss": 3.2274, "step": 164100 }, { "epoch": 0.54, - "learning_rate": 2.283669593642265e-05, - "loss": 3.2434, + "learning_rate": 2.2792767714526213e-05, + "loss": 3.2094, "step": 164200 }, { "epoch": 0.54, - "learning_rate": 2.2820153120305977e-05, - "loss": 3.2474, + "learning_rate": 2.277619814553384e-05, + "loss": 3.222, "step": 164300 }, { "epoch": 0.54, - "learning_rate": 2.2803610304189305e-05, - "loss": 3.2384, + "learning_rate": 2.2759628576541468e-05, + "loss": 3.225, "step": 164400 }, { - "epoch": 0.54, - "learning_rate": 2.278706748807263e-05, - "loss": 3.2381, + "epoch": 0.55, + "learning_rate": 2.2743059007549097e-05, + "loss": 3.2139, "step": 164500 }, { - "epoch": 0.54, - "learning_rate": 2.2770524671955957e-05, - "loss": 3.2439, + "epoch": 0.55, + "learning_rate": 2.2726489438556726e-05, + "loss": 3.2275, "step": 164600 }, { - "epoch": 0.54, - "learning_rate": 2.2753981855839285e-05, - "loss": 3.2491, + "epoch": 0.55, + "learning_rate": 2.2709919869564352e-05, + "loss": 3.217, "step": 164700 }, { "epoch": 0.55, - "learning_rate": 2.273743903972261e-05, - "loss": 3.24, + "learning_rate": 2.2693350300571984e-05, + "loss": 3.2205, "step": 164800 }, { "epoch": 0.55, - "learning_rate": 2.2720896223605938e-05, - "loss": 3.2394, + "learning_rate": 2.267678073157961e-05, + "loss": 3.2178, "step": 164900 }, { "epoch": 0.55, - "learning_rate": 2.2704353407489266e-05, - "loss": 3.2299, + "learning_rate": 2.266021116258724e-05, + "loss": 3.2022, "step": 165000 }, { "epoch": 0.55, - "learning_rate": 2.268781059137259e-05, - "loss": 3.2377, + "learning_rate": 2.264364159359487e-05, + "loss": 3.2236, "step": 165100 }, { "epoch": 0.55, - "learning_rate": 2.2671267775255918e-05, - "loss": 3.2351, + "learning_rate": 2.2627072024602498e-05, + "loss": 3.2191, "step": 165200 }, { "epoch": 0.55, - "learning_rate": 2.2654724959139246e-05, - "loss": 3.2439, + "learning_rate": 2.2610502455610124e-05, + "loss": 3.2038, "step": 165300 }, { "epoch": 0.55, - "learning_rate": 2.263818214302257e-05, - "loss": 3.2256, + "learning_rate": 2.2593932886617756e-05, + "loss": 3.2108, "step": 165400 }, { "epoch": 0.55, - "learning_rate": 2.26216393269059e-05, - "loss": 3.2266, + "learning_rate": 2.2577363317625382e-05, + "loss": 3.2065, "step": 165500 }, { "epoch": 0.55, - "learning_rate": 2.2605096510789226e-05, - "loss": 3.2459, + "learning_rate": 2.256079374863301e-05, + "loss": 3.2168, "step": 165600 }, { "epoch": 0.55, - "learning_rate": 2.258855369467255e-05, - "loss": 3.2388, + "learning_rate": 2.254422417964064e-05, + "loss": 3.222, "step": 165700 }, { "epoch": 0.55, - "learning_rate": 2.257201087855588e-05, - "loss": 3.2449, + "learning_rate": 2.252765461064827e-05, + "loss": 3.2179, "step": 165800 }, { "epoch": 0.55, - "learning_rate": 2.2555468062439207e-05, - "loss": 3.2476, + "learning_rate": 2.2511085041655895e-05, + "loss": 3.2166, "step": 165900 }, { "epoch": 0.55, - "learning_rate": 2.2538925246322535e-05, - "loss": 3.2432, + "learning_rate": 2.2494515472663528e-05, + "loss": 3.2093, "step": 166000 }, { "epoch": 0.55, - "learning_rate": 2.252238243020586e-05, - "loss": 3.235, + "learning_rate": 2.2477945903671154e-05, + "loss": 3.238, "step": 166100 }, { "epoch": 0.55, - "learning_rate": 2.2505839614089187e-05, - "loss": 3.2409, + "learning_rate": 2.2461376334678783e-05, + "loss": 3.2243, "step": 166200 }, { "epoch": 0.55, - "learning_rate": 2.2489296797972515e-05, - "loss": 3.2407, + "learning_rate": 2.2444806765686412e-05, + "loss": 3.2205, "step": 166300 }, { "epoch": 0.55, - "learning_rate": 2.247275398185584e-05, - "loss": 3.2224, + "learning_rate": 2.242823719669404e-05, + "loss": 3.2243, "step": 166400 }, { "epoch": 0.55, - "learning_rate": 2.2456211165739168e-05, - "loss": 3.2423, + "learning_rate": 2.2411667627701667e-05, + "loss": 3.2148, "step": 166500 }, { "epoch": 0.55, - "learning_rate": 2.2439668349622495e-05, - "loss": 3.2434, + "learning_rate": 2.23950980587093e-05, + "loss": 3.214, "step": 166600 }, { "epoch": 0.55, - "learning_rate": 2.242312553350582e-05, - "loss": 3.2469, + "learning_rate": 2.2378528489716926e-05, + "loss": 3.2244, "step": 166700 }, { "epoch": 0.55, - "learning_rate": 2.2406582717389148e-05, - "loss": 3.2291, + "learning_rate": 2.2361958920724555e-05, + "loss": 3.2258, "step": 166800 }, { "epoch": 0.55, - "learning_rate": 2.2390039901272476e-05, - "loss": 3.2298, + "learning_rate": 2.2345389351732184e-05, + "loss": 3.2191, "step": 166900 }, { "epoch": 0.55, - "learning_rate": 2.23734970851558e-05, - "loss": 3.241, + "learning_rate": 2.2328819782739813e-05, + "loss": 3.2106, "step": 167000 }, { "epoch": 0.55, - "learning_rate": 2.2356954269039128e-05, - "loss": 3.2396, + "learning_rate": 2.231225021374744e-05, + "loss": 3.2171, "step": 167100 }, { "epoch": 0.55, - "learning_rate": 2.2340411452922456e-05, - "loss": 3.2544, + "learning_rate": 2.2295680644755072e-05, + "loss": 3.2075, "step": 167200 }, { "epoch": 0.55, - "learning_rate": 2.232386863680578e-05, - "loss": 3.2422, + "learning_rate": 2.2279111075762698e-05, + "loss": 3.211, "step": 167300 }, { "epoch": 0.55, - "learning_rate": 2.230732582068911e-05, - "loss": 3.2417, + "learning_rate": 2.2262541506770327e-05, + "loss": 3.2132, "step": 167400 }, { - "epoch": 0.55, - "learning_rate": 2.2290783004572437e-05, - "loss": 3.2348, + "epoch": 0.56, + "learning_rate": 2.2245971937777956e-05, + "loss": 3.23, "step": 167500 }, { - "epoch": 0.55, - "learning_rate": 2.227424018845576e-05, - "loss": 3.2486, + "epoch": 0.56, + "learning_rate": 2.2229402368785585e-05, + "loss": 3.2116, "step": 167600 }, { - "epoch": 0.55, - "learning_rate": 2.225769737233909e-05, - "loss": 3.2375, + "epoch": 0.56, + "learning_rate": 2.221283279979321e-05, + "loss": 3.224, "step": 167700 }, { "epoch": 0.56, - "learning_rate": 2.2241154556222417e-05, - "loss": 3.2442, + "learning_rate": 2.2196263230800844e-05, + "loss": 3.2222, "step": 167800 }, { "epoch": 0.56, - "learning_rate": 2.2224611740105745e-05, - "loss": 3.2392, + "learning_rate": 2.217969366180847e-05, + "loss": 3.2164, "step": 167900 }, { "epoch": 0.56, - "learning_rate": 2.220806892398907e-05, - "loss": 3.2413, + "learning_rate": 2.21631240928161e-05, + "loss": 3.2285, "step": 168000 }, { "epoch": 0.56, - "learning_rate": 2.2191526107872397e-05, - "loss": 3.2351, + "learning_rate": 2.2146554523823724e-05, + "loss": 3.2157, "step": 168100 }, { "epoch": 0.56, - "learning_rate": 2.2174983291755725e-05, - "loss": 3.2392, + "learning_rate": 2.2129984954831357e-05, + "loss": 3.2168, "step": 168200 }, { "epoch": 0.56, - "learning_rate": 2.215844047563905e-05, - "loss": 3.251, + "learning_rate": 2.2113415385838983e-05, + "loss": 3.2078, "step": 168300 }, { "epoch": 0.56, - "learning_rate": 2.2141897659522374e-05, - "loss": 3.2369, + "learning_rate": 2.2096845816846612e-05, + "loss": 3.1972, "step": 168400 }, { "epoch": 0.56, - "learning_rate": 2.2125354843405706e-05, - "loss": 3.2283, + "learning_rate": 2.208027624785424e-05, + "loss": 3.2122, "step": 168500 }, { "epoch": 0.56, - "learning_rate": 2.210881202728903e-05, - "loss": 3.2428, + "learning_rate": 2.206370667886187e-05, + "loss": 3.208, "step": 168600 }, { "epoch": 0.56, - "learning_rate": 2.2092269211172355e-05, - "loss": 3.2285, + "learning_rate": 2.2047137109869496e-05, + "loss": 3.2052, "step": 168700 }, { "epoch": 0.56, - "learning_rate": 2.2075726395055686e-05, - "loss": 3.2345, + "learning_rate": 2.203056754087713e-05, + "loss": 3.2134, "step": 168800 }, { "epoch": 0.56, - "learning_rate": 2.205918357893901e-05, - "loss": 3.2399, + "learning_rate": 2.2013997971884755e-05, + "loss": 3.2198, "step": 168900 }, { "epoch": 0.56, - "learning_rate": 2.204264076282234e-05, - "loss": 3.2292, + "learning_rate": 2.1997428402892384e-05, + "loss": 3.2389, "step": 169000 }, { "epoch": 0.56, - "learning_rate": 2.2026097946705666e-05, - "loss": 3.2366, + "learning_rate": 2.1980858833900013e-05, + "loss": 3.2038, "step": 169100 }, { "epoch": 0.56, - "learning_rate": 2.200955513058899e-05, - "loss": 3.2502, + "learning_rate": 2.1964289264907642e-05, + "loss": 3.2153, "step": 169200 }, { "epoch": 0.56, - "learning_rate": 2.199301231447232e-05, - "loss": 3.2386, + "learning_rate": 2.1947719695915268e-05, + "loss": 3.218, "step": 169300 }, { "epoch": 0.56, - "learning_rate": 2.1976469498355647e-05, - "loss": 3.2445, + "learning_rate": 2.19311501269229e-05, + "loss": 3.2073, "step": 169400 }, { "epoch": 0.56, - "learning_rate": 2.195992668223897e-05, - "loss": 3.2265, + "learning_rate": 2.1914580557930527e-05, + "loss": 3.2081, "step": 169500 }, { "epoch": 0.56, - "learning_rate": 2.19433838661223e-05, - "loss": 3.2321, + "learning_rate": 2.1898010988938156e-05, + "loss": 3.2194, "step": 169600 }, { "epoch": 0.56, - "learning_rate": 2.1926841050005624e-05, - "loss": 3.2246, + "learning_rate": 2.1881441419945785e-05, + "loss": 3.2059, "step": 169700 }, { "epoch": 0.56, - "learning_rate": 2.1910298233888952e-05, - "loss": 3.2327, + "learning_rate": 2.1864871850953414e-05, + "loss": 3.2232, "step": 169800 }, { "epoch": 0.56, - "learning_rate": 2.189375541777228e-05, - "loss": 3.2388, + "learning_rate": 2.184830228196104e-05, + "loss": 3.2131, "step": 169900 }, { "epoch": 0.56, - "learning_rate": 2.1877212601655604e-05, - "loss": 3.2386, + "learning_rate": 2.1831732712968673e-05, + "loss": 3.2144, "step": 170000 }, { "epoch": 0.56, - "learning_rate": 2.1860669785538935e-05, - "loss": 3.242, + "learning_rate": 2.18151631439763e-05, + "loss": 3.2059, "step": 170100 }, { "epoch": 0.56, - "learning_rate": 2.184412696942226e-05, - "loss": 3.2284, + "learning_rate": 2.1798593574983928e-05, + "loss": 3.2204, "step": 170200 }, { "epoch": 0.56, - "learning_rate": 2.1827584153305585e-05, - "loss": 3.2349, + "learning_rate": 2.1782024005991557e-05, + "loss": 3.2271, "step": 170300 }, { "epoch": 0.56, - "learning_rate": 2.1811041337188916e-05, - "loss": 3.2226, + "learning_rate": 2.1765454436999186e-05, + "loss": 3.2162, "step": 170400 }, { - "epoch": 0.56, - "learning_rate": 2.179449852107224e-05, - "loss": 3.2311, + "epoch": 0.57, + "learning_rate": 2.1748884868006815e-05, + "loss": 3.2095, "step": 170500 }, { - "epoch": 0.56, - "learning_rate": 2.1777955704955565e-05, - "loss": 3.2425, + "epoch": 0.57, + "learning_rate": 2.1732315299014444e-05, + "loss": 3.2096, "step": 170600 }, { - "epoch": 0.56, - "learning_rate": 2.1761412888838896e-05, - "loss": 3.2293, + "epoch": 0.57, + "learning_rate": 2.171574573002207e-05, + "loss": 3.2119, "step": 170700 }, { "epoch": 0.57, - "learning_rate": 2.174487007272222e-05, - "loss": 3.2412, + "learning_rate": 2.16991761610297e-05, + "loss": 3.2224, "step": 170800 }, { "epoch": 0.57, - "learning_rate": 2.1728327256605545e-05, - "loss": 3.2343, + "learning_rate": 2.168260659203733e-05, + "loss": 3.2099, "step": 170900 }, { "epoch": 0.57, - "learning_rate": 2.1711784440488873e-05, - "loss": 3.2274, + "learning_rate": 2.1666037023044958e-05, + "loss": 3.2122, "step": 171000 }, { "epoch": 0.57, - "learning_rate": 2.16952416243722e-05, - "loss": 3.2412, + "learning_rate": 2.1649467454052587e-05, + "loss": 3.2208, "step": 171100 }, { "epoch": 0.57, - "learning_rate": 2.167869880825553e-05, - "loss": 3.2346, + "learning_rate": 2.1632897885060216e-05, + "loss": 3.207, "step": 171200 }, { "epoch": 0.57, - "learning_rate": 2.1662155992138854e-05, - "loss": 3.232, + "learning_rate": 2.1616328316067842e-05, + "loss": 3.2111, "step": 171300 }, { "epoch": 0.57, - "learning_rate": 2.164561317602218e-05, - "loss": 3.2322, + "learning_rate": 2.159975874707547e-05, + "loss": 3.2171, "step": 171400 }, { "epoch": 0.57, - "learning_rate": 2.162907035990551e-05, - "loss": 3.2558, + "learning_rate": 2.15831891780831e-05, + "loss": 3.2098, "step": 171500 }, { "epoch": 0.57, - "learning_rate": 2.1612527543788834e-05, - "loss": 3.2349, + "learning_rate": 2.156661960909073e-05, + "loss": 3.2209, "step": 171600 }, { "epoch": 0.57, - "learning_rate": 2.1595984727672162e-05, - "loss": 3.2243, + "learning_rate": 2.155005004009836e-05, + "loss": 3.2129, "step": 171700 }, { "epoch": 0.57, - "learning_rate": 2.157944191155549e-05, - "loss": 3.2361, + "learning_rate": 2.1533480471105988e-05, + "loss": 3.2184, "step": 171800 }, { "epoch": 0.57, - "learning_rate": 2.1562899095438814e-05, - "loss": 3.2343, + "learning_rate": 2.1516910902113614e-05, + "loss": 3.2078, "step": 171900 }, { "epoch": 0.57, - "learning_rate": 2.1546356279322142e-05, - "loss": 3.2517, + "learning_rate": 2.1500341333121243e-05, + "loss": 3.1978, "step": 172000 }, { "epoch": 0.57, - "learning_rate": 2.152981346320547e-05, - "loss": 3.2364, + "learning_rate": 2.1483771764128872e-05, + "loss": 3.2174, "step": 172100 }, { "epoch": 0.57, - "learning_rate": 2.1513270647088795e-05, - "loss": 3.2368, + "learning_rate": 2.14672021951365e-05, + "loss": 3.2091, "step": 172200 }, { "epoch": 0.57, - "learning_rate": 2.1496727830972123e-05, - "loss": 3.234, + "learning_rate": 2.145063262614413e-05, + "loss": 3.2273, "step": 172300 }, { "epoch": 0.57, - "learning_rate": 2.148018501485545e-05, - "loss": 3.2417, + "learning_rate": 2.143406305715176e-05, + "loss": 3.2248, "step": 172400 }, { "epoch": 0.57, - "learning_rate": 2.1463642198738775e-05, - "loss": 3.2377, + "learning_rate": 2.141749348815939e-05, + "loss": 3.2139, "step": 172500 }, { "epoch": 0.57, - "learning_rate": 2.1447099382622103e-05, - "loss": 3.2333, + "learning_rate": 2.1400923919167015e-05, + "loss": 3.2183, "step": 172600 }, { "epoch": 0.57, - "learning_rate": 2.143055656650543e-05, - "loss": 3.2384, + "learning_rate": 2.1384354350174644e-05, + "loss": 3.2161, "step": 172700 }, { "epoch": 0.57, - "learning_rate": 2.1414013750388755e-05, - "loss": 3.2461, + "learning_rate": 2.1367784781182273e-05, + "loss": 3.2103, "step": 172800 }, { "epoch": 0.57, - "learning_rate": 2.1397470934272083e-05, - "loss": 3.238, + "learning_rate": 2.1351215212189903e-05, + "loss": 3.2244, "step": 172900 }, { "epoch": 0.57, - "learning_rate": 2.138092811815541e-05, - "loss": 3.2408, + "learning_rate": 2.133464564319753e-05, + "loss": 3.2045, "step": 173000 }, { "epoch": 0.57, - "learning_rate": 2.1364385302038736e-05, - "loss": 3.2326, + "learning_rate": 2.131807607420516e-05, + "loss": 3.2181, "step": 173100 }, { "epoch": 0.57, - "learning_rate": 2.1347842485922064e-05, - "loss": 3.2286, + "learning_rate": 2.1301506505212787e-05, + "loss": 3.2184, "step": 173200 }, { "epoch": 0.57, - "learning_rate": 2.1331299669805392e-05, - "loss": 3.2332, + "learning_rate": 2.1284936936220416e-05, + "loss": 3.2278, "step": 173300 }, { "epoch": 0.57, - "learning_rate": 2.131475685368872e-05, - "loss": 3.2429, + "learning_rate": 2.1268367367228045e-05, + "loss": 3.2055, "step": 173400 }, { "epoch": 0.57, - "learning_rate": 2.1298214037572044e-05, - "loss": 3.2444, + "learning_rate": 2.1251797798235674e-05, + "loss": 3.2179, "step": 173500 }, { - "epoch": 0.57, - "learning_rate": 2.1281671221455372e-05, - "loss": 3.2354, + "epoch": 0.58, + "learning_rate": 2.12352282292433e-05, + "loss": 3.2125, "step": 173600 }, { - "epoch": 0.57, - "learning_rate": 2.12651284053387e-05, - "loss": 3.2424, + "epoch": 0.58, + "learning_rate": 2.1218658660250933e-05, + "loss": 3.2107, "step": 173700 }, { "epoch": 0.58, - "learning_rate": 2.1248585589222025e-05, - "loss": 3.2391, + "learning_rate": 2.120208909125856e-05, + "loss": 3.2069, "step": 173800 }, { "epoch": 0.58, - "learning_rate": 2.1232042773105352e-05, - "loss": 3.247, + "learning_rate": 2.1185519522266188e-05, + "loss": 3.2293, "step": 173900 }, { "epoch": 0.58, - "learning_rate": 2.121549995698868e-05, - "loss": 3.233, + "learning_rate": 2.1168949953273817e-05, + "loss": 3.2222, "step": 174000 }, { "epoch": 0.58, - "learning_rate": 2.1198957140872005e-05, - "loss": 3.2309, + "learning_rate": 2.1152380384281446e-05, + "loss": 3.2199, "step": 174100 }, { "epoch": 0.58, - "learning_rate": 2.1182414324755333e-05, - "loss": 3.2377, + "learning_rate": 2.1135810815289072e-05, + "loss": 3.2056, "step": 174200 }, { "epoch": 0.58, - "learning_rate": 2.116587150863866e-05, - "loss": 3.2439, + "learning_rate": 2.1119241246296705e-05, + "loss": 3.2268, "step": 174300 }, { "epoch": 0.58, - "learning_rate": 2.1149328692521985e-05, - "loss": 3.2305, + "learning_rate": 2.110267167730433e-05, + "loss": 3.2109, "step": 174400 }, { "epoch": 0.58, - "learning_rate": 2.1132785876405313e-05, - "loss": 3.237, + "learning_rate": 2.108610210831196e-05, + "loss": 3.2206, "step": 174500 }, { "epoch": 0.58, - "learning_rate": 2.111624306028864e-05, - "loss": 3.2385, + "learning_rate": 2.106953253931959e-05, + "loss": 3.2069, "step": 174600 }, { "epoch": 0.58, - "learning_rate": 2.1099700244171966e-05, - "loss": 3.2425, + "learning_rate": 2.1052962970327218e-05, + "loss": 3.2137, "step": 174700 }, { "epoch": 0.58, - "learning_rate": 2.1083157428055294e-05, - "loss": 3.2439, + "learning_rate": 2.1036393401334844e-05, + "loss": 3.2231, "step": 174800 }, { "epoch": 0.58, - "learning_rate": 2.106661461193862e-05, - "loss": 3.2435, + "learning_rate": 2.1019823832342477e-05, + "loss": 3.2157, "step": 174900 }, { "epoch": 0.58, - "learning_rate": 2.1050071795821946e-05, - "loss": 3.2269, + "learning_rate": 2.1003254263350102e-05, + "loss": 3.2173, "step": 175000 }, { "epoch": 0.58, - "learning_rate": 2.1033528979705274e-05, - "loss": 3.2308, + "learning_rate": 2.098668469435773e-05, + "loss": 3.2336, "step": 175100 }, { "epoch": 0.58, - "learning_rate": 2.1016986163588602e-05, - "loss": 3.236, + "learning_rate": 2.097011512536536e-05, + "loss": 3.219, "step": 175200 }, { "epoch": 0.58, - "learning_rate": 2.100044334747193e-05, - "loss": 3.2448, + "learning_rate": 2.095354555637299e-05, + "loss": 3.2058, "step": 175300 }, { "epoch": 0.58, - "learning_rate": 2.0983900531355254e-05, - "loss": 3.2304, + "learning_rate": 2.0936975987380616e-05, + "loss": 3.2108, "step": 175400 }, { "epoch": 0.58, - "learning_rate": 2.0967357715238582e-05, - "loss": 3.2432, + "learning_rate": 2.092040641838825e-05, + "loss": 3.2162, "step": 175500 }, { "epoch": 0.58, - "learning_rate": 2.095081489912191e-05, - "loss": 3.2307, + "learning_rate": 2.0903836849395874e-05, + "loss": 3.2056, "step": 175600 }, { "epoch": 0.58, - "learning_rate": 2.0934272083005235e-05, - "loss": 3.2353, + "learning_rate": 2.0887267280403503e-05, + "loss": 3.2143, "step": 175700 }, { "epoch": 0.58, - "learning_rate": 2.0917729266888563e-05, - "loss": 3.2319, + "learning_rate": 2.0870697711411133e-05, + "loss": 3.2066, "step": 175800 }, { "epoch": 0.58, - "learning_rate": 2.090118645077189e-05, - "loss": 3.241, + "learning_rate": 2.0854128142418762e-05, + "loss": 3.2056, "step": 175900 }, { "epoch": 0.58, - "learning_rate": 2.0884643634655215e-05, - "loss": 3.2408, + "learning_rate": 2.0837558573426388e-05, + "loss": 3.2122, "step": 176000 }, { "epoch": 0.58, - "learning_rate": 2.086810081853854e-05, - "loss": 3.2493, + "learning_rate": 2.082098900443402e-05, + "loss": 3.2139, "step": 176100 }, { "epoch": 0.58, - "learning_rate": 2.085155800242187e-05, - "loss": 3.2384, + "learning_rate": 2.0804419435441646e-05, + "loss": 3.2123, "step": 176200 }, { "epoch": 0.58, - "learning_rate": 2.0835015186305196e-05, - "loss": 3.2481, + "learning_rate": 2.0787849866449275e-05, + "loss": 3.2147, "step": 176300 }, { "epoch": 0.58, - "learning_rate": 2.0818472370188523e-05, - "loss": 3.2388, + "learning_rate": 2.0771280297456904e-05, + "loss": 3.2279, "step": 176400 }, { "epoch": 0.58, - "learning_rate": 2.080192955407185e-05, - "loss": 3.242, + "learning_rate": 2.0754710728464534e-05, + "loss": 3.2111, "step": 176500 }, { - "epoch": 0.58, - "learning_rate": 2.0785386737955176e-05, - "loss": 3.2267, + "epoch": 0.59, + "learning_rate": 2.073814115947216e-05, + "loss": 3.2211, "step": 176600 }, { - "epoch": 0.58, - "learning_rate": 2.0768843921838504e-05, - "loss": 3.2264, + "epoch": 0.59, + "learning_rate": 2.0721571590479792e-05, + "loss": 3.2094, "step": 176700 }, { - "epoch": 0.58, - "learning_rate": 2.0752301105721832e-05, - "loss": 3.2495, + "epoch": 0.59, + "learning_rate": 2.0705002021487418e-05, + "loss": 3.2107, "step": 176800 }, { "epoch": 0.59, - "learning_rate": 2.0735758289605156e-05, - "loss": 3.2315, + "learning_rate": 2.0688432452495047e-05, + "loss": 3.2158, "step": 176900 }, { "epoch": 0.59, - "learning_rate": 2.0719215473488484e-05, - "loss": 3.2329, + "learning_rate": 2.0671862883502673e-05, + "loss": 3.2056, "step": 177000 }, { "epoch": 0.59, - "learning_rate": 2.0702672657371812e-05, - "loss": 3.2295, + "learning_rate": 2.0655293314510306e-05, + "loss": 3.2228, "step": 177100 }, { "epoch": 0.59, - "learning_rate": 2.0686129841255137e-05, - "loss": 3.2336, + "learning_rate": 2.063872374551793e-05, + "loss": 3.2119, "step": 177200 }, { "epoch": 0.59, - "learning_rate": 2.0669587025138465e-05, - "loss": 3.2401, + "learning_rate": 2.062215417652556e-05, + "loss": 3.2208, "step": 177300 }, { "epoch": 0.59, - "learning_rate": 2.065304420902179e-05, - "loss": 3.2386, + "learning_rate": 2.060558460753319e-05, + "loss": 3.2222, "step": 177400 }, { "epoch": 0.59, - "learning_rate": 2.063650139290512e-05, - "loss": 3.2328, + "learning_rate": 2.058901503854082e-05, + "loss": 3.2195, "step": 177500 }, { "epoch": 0.59, - "learning_rate": 2.0619958576788445e-05, - "loss": 3.2413, + "learning_rate": 2.0572445469548445e-05, + "loss": 3.221, "step": 177600 }, { "epoch": 0.59, - "learning_rate": 2.060341576067177e-05, - "loss": 3.2395, + "learning_rate": 2.0555875900556077e-05, + "loss": 3.2316, "step": 177700 }, { "epoch": 0.59, - "learning_rate": 2.05868729445551e-05, - "loss": 3.2279, + "learning_rate": 2.0539306331563703e-05, + "loss": 3.2149, "step": 177800 }, { "epoch": 0.59, - "learning_rate": 2.0570330128438425e-05, - "loss": 3.2368, + "learning_rate": 2.0522736762571332e-05, + "loss": 3.2003, "step": 177900 }, { "epoch": 0.59, - "learning_rate": 2.055378731232175e-05, - "loss": 3.2239, + "learning_rate": 2.050616719357896e-05, + "loss": 3.2055, "step": 178000 }, { "epoch": 0.59, - "learning_rate": 2.053724449620508e-05, - "loss": 3.2394, + "learning_rate": 2.048959762458659e-05, + "loss": 3.2178, "step": 178100 }, { "epoch": 0.59, - "learning_rate": 2.0520701680088406e-05, - "loss": 3.2384, + "learning_rate": 2.0473028055594217e-05, + "loss": 3.2139, "step": 178200 }, { "epoch": 0.59, - "learning_rate": 2.050415886397173e-05, - "loss": 3.2459, + "learning_rate": 2.045645848660185e-05, + "loss": 3.2057, "step": 178300 }, { "epoch": 0.59, - "learning_rate": 2.048761604785506e-05, - "loss": 3.2515, + "learning_rate": 2.0439888917609475e-05, + "loss": 3.2186, "step": 178400 }, { "epoch": 0.59, - "learning_rate": 2.0471073231738386e-05, - "loss": 3.2241, + "learning_rate": 2.0423319348617104e-05, + "loss": 3.2105, "step": 178500 }, { "epoch": 0.59, - "learning_rate": 2.0454530415621714e-05, - "loss": 3.2369, + "learning_rate": 2.0406749779624733e-05, + "loss": 3.2051, "step": 178600 }, { "epoch": 0.59, - "learning_rate": 2.043798759950504e-05, - "loss": 3.2441, + "learning_rate": 2.0390180210632363e-05, + "loss": 3.2133, "step": 178700 }, { "epoch": 0.59, - "learning_rate": 2.0421444783388366e-05, - "loss": 3.2333, + "learning_rate": 2.037361064163999e-05, + "loss": 3.2348, "step": 178800 }, { "epoch": 0.59, - "learning_rate": 2.0404901967271694e-05, - "loss": 3.2325, + "learning_rate": 2.035704107264762e-05, + "loss": 3.2199, "step": 178900 }, { "epoch": 0.59, - "learning_rate": 2.038835915115502e-05, - "loss": 3.2315, + "learning_rate": 2.0340471503655247e-05, + "loss": 3.2118, "step": 179000 }, { "epoch": 0.59, - "learning_rate": 2.0371816335038347e-05, - "loss": 3.2207, + "learning_rate": 2.0323901934662876e-05, + "loss": 3.206, "step": 179100 }, { "epoch": 0.59, - "learning_rate": 2.0355273518921675e-05, - "loss": 3.2392, + "learning_rate": 2.0307332365670505e-05, + "loss": 3.2025, "step": 179200 }, { "epoch": 0.59, - "learning_rate": 2.0338730702805e-05, - "loss": 3.243, + "learning_rate": 2.0290762796678134e-05, + "loss": 3.2123, "step": 179300 }, { "epoch": 0.59, - "learning_rate": 2.0322187886688327e-05, - "loss": 3.2299, + "learning_rate": 2.027419322768576e-05, + "loss": 3.2126, "step": 179400 }, { "epoch": 0.59, - "learning_rate": 2.0305645070571655e-05, - "loss": 3.229, + "learning_rate": 2.0257623658693393e-05, + "loss": 3.2246, "step": 179500 }, { - "epoch": 0.59, - "learning_rate": 2.028910225445498e-05, - "loss": 3.25, + "epoch": 0.6, + "learning_rate": 2.024105408970102e-05, + "loss": 3.2044, "step": 179600 }, { - "epoch": 0.59, - "learning_rate": 2.027255943833831e-05, - "loss": 3.2382, + "epoch": 0.6, + "learning_rate": 2.0224484520708648e-05, + "loss": 3.2238, "step": 179700 }, { - "epoch": 0.59, - "learning_rate": 2.0256016622221636e-05, - "loss": 3.2351, + "epoch": 0.6, + "learning_rate": 2.0207914951716277e-05, + "loss": 3.2209, "step": 179800 }, { "epoch": 0.6, - "learning_rate": 2.023947380610496e-05, - "loss": 3.2375, + "learning_rate": 2.0191345382723906e-05, + "loss": 3.2077, "step": 179900 }, { "epoch": 0.6, - "learning_rate": 2.0222930989988288e-05, - "loss": 3.2347, + "learning_rate": 2.0174775813731532e-05, + "loss": 3.2099, "step": 180000 }, { "epoch": 0.6, - "learning_rate": 2.0206388173871616e-05, - "loss": 3.2456, + "learning_rate": 2.0158206244739165e-05, + "loss": 3.2346, "step": 180100 }, { "epoch": 0.6, - "learning_rate": 2.018984535775494e-05, - "loss": 3.2344, + "learning_rate": 2.014163667574679e-05, + "loss": 3.2103, "step": 180200 }, { "epoch": 0.6, - "learning_rate": 2.017330254163827e-05, - "loss": 3.2231, + "learning_rate": 2.012506710675442e-05, + "loss": 3.2181, "step": 180300 }, { "epoch": 0.6, - "learning_rate": 2.0156759725521596e-05, - "loss": 3.2298, + "learning_rate": 2.010849753776205e-05, + "loss": 3.2152, "step": 180400 }, { "epoch": 0.6, - "learning_rate": 2.014021690940492e-05, - "loss": 3.2341, + "learning_rate": 2.0091927968769678e-05, + "loss": 3.2175, "step": 180500 }, { "epoch": 0.6, - "learning_rate": 2.012367409328825e-05, - "loss": 3.2487, + "learning_rate": 2.0075358399777304e-05, + "loss": 3.2149, "step": 180600 }, { "epoch": 0.6, - "learning_rate": 2.0107131277171577e-05, - "loss": 3.2404, + "learning_rate": 2.0058788830784937e-05, + "loss": 3.2166, "step": 180700 }, { "epoch": 0.6, - "learning_rate": 2.0090588461054905e-05, - "loss": 3.2449, + "learning_rate": 2.0042219261792562e-05, + "loss": 3.2107, "step": 180800 }, { "epoch": 0.6, - "learning_rate": 2.007404564493823e-05, - "loss": 3.2524, + "learning_rate": 2.002564969280019e-05, + "loss": 3.2124, "step": 180900 }, { "epoch": 0.6, - "learning_rate": 2.0057502828821557e-05, - "loss": 3.2329, + "learning_rate": 2.000908012380782e-05, + "loss": 3.2106, "step": 181000 }, { "epoch": 0.6, - "learning_rate": 2.0040960012704885e-05, - "loss": 3.2242, + "learning_rate": 1.999251055481545e-05, + "loss": 3.2197, "step": 181100 }, { "epoch": 0.6, - "learning_rate": 2.002441719658821e-05, - "loss": 3.2354, + "learning_rate": 1.9975940985823076e-05, + "loss": 3.2246, "step": 181200 }, { "epoch": 0.6, - "learning_rate": 2.0007874380471537e-05, - "loss": 3.2452, + "learning_rate": 1.9959371416830705e-05, + "loss": 3.2074, "step": 181300 }, { "epoch": 0.6, - "learning_rate": 1.9991331564354865e-05, - "loss": 3.2281, + "learning_rate": 1.9942801847838334e-05, + "loss": 3.2075, "step": 181400 }, { "epoch": 0.6, - "learning_rate": 1.997478874823819e-05, - "loss": 3.243, + "learning_rate": 1.9926232278845963e-05, + "loss": 3.211, "step": 181500 }, { "epoch": 0.6, - "learning_rate": 1.9958245932121518e-05, - "loss": 3.2374, + "learning_rate": 1.990966270985359e-05, + "loss": 3.2053, "step": 181600 }, { "epoch": 0.6, - "learning_rate": 1.9941703116004846e-05, - "loss": 3.2342, + "learning_rate": 1.9893093140861222e-05, + "loss": 3.2205, "step": 181700 }, { "epoch": 0.6, - "learning_rate": 1.992516029988817e-05, - "loss": 3.2345, + "learning_rate": 1.9876523571868848e-05, + "loss": 3.199, "step": 181800 }, { "epoch": 0.6, - "learning_rate": 1.9908617483771498e-05, - "loss": 3.2341, + "learning_rate": 1.9859954002876477e-05, + "loss": 3.2271, "step": 181900 }, { "epoch": 0.6, - "learning_rate": 1.9892074667654826e-05, - "loss": 3.2379, + "learning_rate": 1.9843384433884106e-05, + "loss": 3.2162, "step": 182000 }, { "epoch": 0.6, - "learning_rate": 1.987553185153815e-05, - "loss": 3.2395, + "learning_rate": 1.9826814864891735e-05, + "loss": 3.2215, "step": 182100 }, { "epoch": 0.6, - "learning_rate": 1.985898903542148e-05, - "loss": 3.2301, + "learning_rate": 1.9810245295899365e-05, + "loss": 3.1948, "step": 182200 }, { "epoch": 0.6, - "learning_rate": 1.9842446219304807e-05, - "loss": 3.2414, + "learning_rate": 1.9793675726906994e-05, + "loss": 3.23, "step": 182300 }, { "epoch": 0.6, - "learning_rate": 1.982590340318813e-05, - "loss": 3.2423, + "learning_rate": 1.977710615791462e-05, + "loss": 3.2102, "step": 182400 }, { "epoch": 0.6, - "learning_rate": 1.980936058707146e-05, - "loss": 3.2311, + "learning_rate": 1.976053658892225e-05, + "loss": 3.1882, "step": 182500 }, { - "epoch": 0.6, - "learning_rate": 1.9792817770954787e-05, - "loss": 3.2344, + "epoch": 0.61, + "learning_rate": 1.9743967019929878e-05, + "loss": 3.2112, "step": 182600 }, { - "epoch": 0.6, - "learning_rate": 1.9776274954838115e-05, - "loss": 3.2277, + "epoch": 0.61, + "learning_rate": 1.9727397450937507e-05, + "loss": 3.2204, "step": 182700 }, { - "epoch": 0.6, - "learning_rate": 1.975973213872144e-05, - "loss": 3.2379, + "epoch": 0.61, + "learning_rate": 1.9710827881945136e-05, + "loss": 3.2033, "step": 182800 }, { "epoch": 0.61, - "learning_rate": 1.9743189322604767e-05, - "loss": 3.2414, + "learning_rate": 1.9694258312952766e-05, + "loss": 3.2034, "step": 182900 }, { "epoch": 0.61, - "learning_rate": 1.9726646506488095e-05, - "loss": 3.2279, + "learning_rate": 1.967768874396039e-05, + "loss": 3.2138, "step": 183000 }, { "epoch": 0.61, - "learning_rate": 1.971010369037142e-05, - "loss": 3.247, + "learning_rate": 1.966111917496802e-05, + "loss": 3.2213, "step": 183100 }, { "epoch": 0.61, - "learning_rate": 1.9693560874254748e-05, - "loss": 3.2421, + "learning_rate": 1.964454960597565e-05, + "loss": 3.2022, "step": 183200 }, { "epoch": 0.61, - "learning_rate": 1.9677018058138076e-05, - "loss": 3.2455, + "learning_rate": 1.962798003698328e-05, + "loss": 3.2096, "step": 183300 }, { "epoch": 0.61, - "learning_rate": 1.96604752420214e-05, - "loss": 3.2471, + "learning_rate": 1.9611410467990908e-05, + "loss": 3.2053, "step": 183400 }, { "epoch": 0.61, - "learning_rate": 1.9643932425904728e-05, - "loss": 3.2436, + "learning_rate": 1.9594840898998537e-05, + "loss": 3.2069, "step": 183500 }, { "epoch": 0.61, - "learning_rate": 1.9627389609788056e-05, - "loss": 3.2282, + "learning_rate": 1.9578271330006163e-05, + "loss": 3.2051, "step": 183600 }, { "epoch": 0.61, - "learning_rate": 1.961084679367138e-05, - "loss": 3.2397, + "learning_rate": 1.9561701761013792e-05, + "loss": 3.2068, "step": 183700 }, { "epoch": 0.61, - "learning_rate": 1.959430397755471e-05, - "loss": 3.2301, + "learning_rate": 1.954513219202142e-05, + "loss": 3.2107, "step": 183800 }, { "epoch": 0.61, - "learning_rate": 1.9577761161438036e-05, - "loss": 3.2323, + "learning_rate": 1.952856262302905e-05, + "loss": 3.2082, "step": 183900 }, { "epoch": 0.61, - "learning_rate": 1.956121834532136e-05, - "loss": 3.2347, + "learning_rate": 1.951199305403668e-05, + "loss": 3.2135, "step": 184000 }, { "epoch": 0.61, - "learning_rate": 1.954467552920469e-05, - "loss": 3.2405, + "learning_rate": 1.949542348504431e-05, + "loss": 3.2131, "step": 184100 }, { "epoch": 0.61, - "learning_rate": 1.9528132713088017e-05, - "loss": 3.2259, + "learning_rate": 1.947885391605194e-05, + "loss": 3.217, "step": 184200 }, { "epoch": 0.61, - "learning_rate": 1.951158989697134e-05, - "loss": 3.2456, + "learning_rate": 1.9462284347059564e-05, + "loss": 3.2085, "step": 184300 }, { "epoch": 0.61, - "learning_rate": 1.949504708085467e-05, - "loss": 3.2307, + "learning_rate": 1.9445714778067193e-05, + "loss": 3.2023, "step": 184400 }, { "epoch": 0.61, - "learning_rate": 1.9478504264737997e-05, - "loss": 3.2445, + "learning_rate": 1.9429145209074823e-05, + "loss": 3.2041, "step": 184500 }, { "epoch": 0.61, - "learning_rate": 1.946196144862132e-05, - "loss": 3.2443, + "learning_rate": 1.9412575640082452e-05, + "loss": 3.1917, "step": 184600 }, { "epoch": 0.61, - "learning_rate": 1.944541863250465e-05, - "loss": 3.2369, + "learning_rate": 1.939600607109008e-05, + "loss": 3.2282, "step": 184700 }, { "epoch": 0.61, - "learning_rate": 1.9428875816387977e-05, - "loss": 3.2373, + "learning_rate": 1.937943650209771e-05, + "loss": 3.2208, "step": 184800 }, { "epoch": 0.61, - "learning_rate": 1.9412333000271305e-05, - "loss": 3.2426, + "learning_rate": 1.9362866933105336e-05, + "loss": 3.1997, "step": 184900 }, { "epoch": 0.61, - "learning_rate": 1.939579018415463e-05, - "loss": 3.2375, + "learning_rate": 1.9346297364112965e-05, + "loss": 3.2031, "step": 185000 }, { "epoch": 0.61, - "learning_rate": 1.9379247368037954e-05, - "loss": 3.236, + "learning_rate": 1.9329727795120595e-05, + "loss": 3.209, "step": 185100 }, { "epoch": 0.61, - "learning_rate": 1.9362704551921286e-05, - "loss": 3.2431, + "learning_rate": 1.9313158226128224e-05, + "loss": 3.2041, "step": 185200 }, { "epoch": 0.61, - "learning_rate": 1.934616173580461e-05, - "loss": 3.2381, + "learning_rate": 1.9296588657135853e-05, + "loss": 3.2266, "step": 185300 }, { "epoch": 0.61, - "learning_rate": 1.9329618919687935e-05, - "loss": 3.2361, + "learning_rate": 1.9280019088143482e-05, + "loss": 3.2112, "step": 185400 }, { "epoch": 0.61, - "learning_rate": 1.9313076103571266e-05, - "loss": 3.2282, + "learning_rate": 1.9263449519151108e-05, + "loss": 3.203, "step": 185500 }, { - "epoch": 0.61, - "learning_rate": 1.929653328745459e-05, - "loss": 3.2299, + "epoch": 0.62, + "learning_rate": 1.9246879950158737e-05, + "loss": 3.1993, "step": 185600 }, { - "epoch": 0.61, - "learning_rate": 1.9279990471337915e-05, - "loss": 3.2396, + "epoch": 0.62, + "learning_rate": 1.9230310381166366e-05, + "loss": 3.2096, "step": 185700 }, { - "epoch": 0.61, - "learning_rate": 1.9263447655221247e-05, - "loss": 3.2286, + "epoch": 0.62, + "learning_rate": 1.9213740812173996e-05, + "loss": 3.2016, "step": 185800 }, { "epoch": 0.62, - "learning_rate": 1.924690483910457e-05, - "loss": 3.2218, + "learning_rate": 1.919717124318162e-05, + "loss": 3.2328, "step": 185900 }, { "epoch": 0.62, - "learning_rate": 1.92303620229879e-05, - "loss": 3.226, + "learning_rate": 1.9180601674189254e-05, + "loss": 3.2087, "step": 186000 }, { "epoch": 0.62, - "learning_rate": 1.9213819206871227e-05, - "loss": 3.2288, + "learning_rate": 1.916403210519688e-05, + "loss": 3.2094, "step": 186100 }, { "epoch": 0.62, - "learning_rate": 1.919727639075455e-05, - "loss": 3.2416, + "learning_rate": 1.914746253620451e-05, + "loss": 3.2157, "step": 186200 }, { "epoch": 0.62, - "learning_rate": 1.918073357463788e-05, - "loss": 3.2373, + "learning_rate": 1.9130892967212138e-05, + "loss": 3.2215, "step": 186300 }, { "epoch": 0.62, - "learning_rate": 1.9164190758521204e-05, - "loss": 3.2304, + "learning_rate": 1.9114323398219767e-05, + "loss": 3.2244, "step": 186400 }, { "epoch": 0.62, - "learning_rate": 1.9147647942404532e-05, - "loss": 3.2258, + "learning_rate": 1.9097753829227393e-05, + "loss": 3.2091, "step": 186500 }, { "epoch": 0.62, - "learning_rate": 1.913110512628786e-05, - "loss": 3.2384, + "learning_rate": 1.9081184260235026e-05, + "loss": 3.218, "step": 186600 }, { "epoch": 0.62, - "learning_rate": 1.9114562310171184e-05, - "loss": 3.2358, + "learning_rate": 1.906461469124265e-05, + "loss": 3.2123, "step": 186700 }, { "epoch": 0.62, - "learning_rate": 1.9098019494054512e-05, - "loss": 3.2259, + "learning_rate": 1.904804512225028e-05, + "loss": 3.1967, "step": 186800 }, { "epoch": 0.62, - "learning_rate": 1.908147667793784e-05, - "loss": 3.2362, + "learning_rate": 1.903147555325791e-05, + "loss": 3.1944, "step": 186900 }, { "epoch": 0.62, - "learning_rate": 1.9064933861821165e-05, - "loss": 3.2283, + "learning_rate": 1.901490598426554e-05, + "loss": 3.2196, "step": 187000 }, { "epoch": 0.62, - "learning_rate": 1.9048391045704496e-05, - "loss": 3.2307, + "learning_rate": 1.8998336415273165e-05, + "loss": 3.2202, "step": 187100 }, { "epoch": 0.62, - "learning_rate": 1.903184822958782e-05, - "loss": 3.2333, + "learning_rate": 1.8981766846280798e-05, + "loss": 3.2133, "step": 187200 }, { "epoch": 0.62, - "learning_rate": 1.9015305413471145e-05, - "loss": 3.2289, + "learning_rate": 1.8965197277288423e-05, + "loss": 3.2015, "step": 187300 }, { "epoch": 0.62, - "learning_rate": 1.8998762597354476e-05, - "loss": 3.2501, + "learning_rate": 1.8948627708296053e-05, + "loss": 3.2106, "step": 187400 }, { "epoch": 0.62, - "learning_rate": 1.89822197812378e-05, - "loss": 3.2408, + "learning_rate": 1.8932058139303682e-05, + "loss": 3.213, "step": 187500 }, { "epoch": 0.62, - "learning_rate": 1.8965676965121125e-05, - "loss": 3.2438, + "learning_rate": 1.891548857031131e-05, + "loss": 3.2015, "step": 187600 }, { "epoch": 0.62, - "learning_rate": 1.8949134149004453e-05, - "loss": 3.2267, + "learning_rate": 1.8898919001318937e-05, + "loss": 3.195, "step": 187700 }, { "epoch": 0.62, - "learning_rate": 1.893259133288778e-05, - "loss": 3.2329, + "learning_rate": 1.888234943232657e-05, + "loss": 3.202, "step": 187800 }, { "epoch": 0.62, - "learning_rate": 1.8916048516771106e-05, - "loss": 3.22, + "learning_rate": 1.8865779863334195e-05, + "loss": 3.2147, "step": 187900 }, { "epoch": 0.62, - "learning_rate": 1.8899505700654434e-05, - "loss": 3.2369, + "learning_rate": 1.8849210294341825e-05, + "loss": 3.2094, "step": 188000 }, { "epoch": 0.62, - "learning_rate": 1.888296288453776e-05, - "loss": 3.2316, + "learning_rate": 1.8832640725349454e-05, + "loss": 3.2107, "step": 188100 }, { "epoch": 0.62, - "learning_rate": 1.886642006842109e-05, - "loss": 3.2531, + "learning_rate": 1.8816071156357083e-05, + "loss": 3.2142, "step": 188200 }, { "epoch": 0.62, - "learning_rate": 1.8849877252304414e-05, - "loss": 3.2321, + "learning_rate": 1.879950158736471e-05, + "loss": 3.1991, "step": 188300 }, { "epoch": 0.62, - "learning_rate": 1.8833334436187742e-05, - "loss": 3.2312, + "learning_rate": 1.878293201837234e-05, + "loss": 3.2112, "step": 188400 }, { "epoch": 0.62, - "learning_rate": 1.881679162007107e-05, - "loss": 3.2272, + "learning_rate": 1.8766362449379967e-05, + "loss": 3.217, "step": 188500 }, { - "epoch": 0.62, - "learning_rate": 1.8800248803954394e-05, - "loss": 3.2453, + "epoch": 0.63, + "learning_rate": 1.8749792880387596e-05, + "loss": 3.2094, "step": 188600 }, { - "epoch": 0.62, - "learning_rate": 1.8783705987837722e-05, - "loss": 3.2434, + "epoch": 0.63, + "learning_rate": 1.8733223311395226e-05, + "loss": 3.2199, "step": 188700 }, { - "epoch": 0.62, - "learning_rate": 1.876716317172105e-05, - "loss": 3.2363, + "epoch": 0.63, + "learning_rate": 1.8716653742402855e-05, + "loss": 3.2165, "step": 188800 }, { - "epoch": 0.62, - "learning_rate": 1.8750620355604375e-05, - "loss": 3.2344, + "epoch": 0.63, + "learning_rate": 1.870008417341048e-05, + "loss": 3.2216, "step": 188900 }, { "epoch": 0.63, - "learning_rate": 1.8734077539487703e-05, - "loss": 3.2372, + "learning_rate": 1.8683514604418113e-05, + "loss": 3.2022, "step": 189000 }, { "epoch": 0.63, - "learning_rate": 1.871753472337103e-05, - "loss": 3.2379, + "learning_rate": 1.866694503542574e-05, + "loss": 3.2169, "step": 189100 }, { "epoch": 0.63, - "learning_rate": 1.8700991907254355e-05, - "loss": 3.2254, + "learning_rate": 1.8650375466433368e-05, + "loss": 3.2172, "step": 189200 }, { "epoch": 0.63, - "learning_rate": 1.8684449091137683e-05, - "loss": 3.238, + "learning_rate": 1.8633805897440997e-05, + "loss": 3.1992, "step": 189300 }, { "epoch": 0.63, - "learning_rate": 1.866790627502101e-05, - "loss": 3.2365, + "learning_rate": 1.8617236328448627e-05, + "loss": 3.2133, "step": 189400 }, { "epoch": 0.63, - "learning_rate": 1.8651363458904336e-05, - "loss": 3.2299, + "learning_rate": 1.8600666759456252e-05, + "loss": 3.2031, "step": 189500 }, { "epoch": 0.63, - "learning_rate": 1.8634820642787664e-05, - "loss": 3.2445, + "learning_rate": 1.8584097190463885e-05, + "loss": 3.2065, "step": 189600 }, { "epoch": 0.63, - "learning_rate": 1.861827782667099e-05, - "loss": 3.2299, + "learning_rate": 1.856752762147151e-05, + "loss": 3.2336, "step": 189700 }, { "epoch": 0.63, - "learning_rate": 1.8601735010554316e-05, - "loss": 3.2337, + "learning_rate": 1.855095805247914e-05, + "loss": 3.2006, "step": 189800 }, { "epoch": 0.63, - "learning_rate": 1.8585192194437644e-05, - "loss": 3.241, + "learning_rate": 1.853438848348677e-05, + "loss": 3.218, "step": 189900 }, { "epoch": 0.63, - "learning_rate": 1.8568649378320972e-05, - "loss": 3.2336, + "learning_rate": 1.85178189144944e-05, + "loss": 3.2102, "step": 190000 }, { "epoch": 0.63, - "learning_rate": 1.85521065622043e-05, - "loss": 3.2475, + "learning_rate": 1.8501249345502024e-05, + "loss": 3.2073, "step": 190100 }, { "epoch": 0.63, - "learning_rate": 1.8535563746087624e-05, - "loss": 3.2282, + "learning_rate": 1.8484679776509654e-05, + "loss": 3.2091, "step": 190200 }, { "epoch": 0.63, - "learning_rate": 1.8519020929970952e-05, - "loss": 3.2336, + "learning_rate": 1.8468110207517283e-05, + "loss": 3.2118, "step": 190300 }, { "epoch": 0.63, - "learning_rate": 1.850247811385428e-05, - "loss": 3.2223, + "learning_rate": 1.8451540638524912e-05, + "loss": 3.2146, "step": 190400 }, { "epoch": 0.63, - "learning_rate": 1.8485935297737605e-05, - "loss": 3.237, + "learning_rate": 1.8434971069532538e-05, + "loss": 3.2176, "step": 190500 }, { "epoch": 0.63, - "learning_rate": 1.8469392481620933e-05, - "loss": 3.2268, + "learning_rate": 1.841840150054017e-05, + "loss": 3.2038, "step": 190600 }, { "epoch": 0.63, - "learning_rate": 1.845284966550426e-05, - "loss": 3.2294, + "learning_rate": 1.8401831931547796e-05, + "loss": 3.2063, "step": 190700 }, { "epoch": 0.63, - "learning_rate": 1.8436306849387585e-05, - "loss": 3.2349, + "learning_rate": 1.8385262362555425e-05, + "loss": 3.2042, "step": 190800 }, { "epoch": 0.63, - "learning_rate": 1.8419764033270913e-05, - "loss": 3.239, + "learning_rate": 1.8368692793563055e-05, + "loss": 3.2107, "step": 190900 }, { "epoch": 0.63, - "learning_rate": 1.840322121715424e-05, - "loss": 3.2249, + "learning_rate": 1.8352123224570684e-05, + "loss": 3.2044, "step": 191000 }, { "epoch": 0.63, - "learning_rate": 1.8386678401037565e-05, - "loss": 3.2335, + "learning_rate": 1.833555365557831e-05, + "loss": 3.2205, "step": 191100 }, { "epoch": 0.63, - "learning_rate": 1.8370135584920893e-05, - "loss": 3.2271, + "learning_rate": 1.8318984086585942e-05, + "loss": 3.2036, "step": 191200 }, { "epoch": 0.63, - "learning_rate": 1.835359276880422e-05, - "loss": 3.232, + "learning_rate": 1.8302414517593568e-05, + "loss": 3.2105, "step": 191300 }, { "epoch": 0.63, - "learning_rate": 1.8337049952687546e-05, - "loss": 3.2273, + "learning_rate": 1.8285844948601197e-05, + "loss": 3.2051, "step": 191400 }, { "epoch": 0.63, - "learning_rate": 1.8320507136570874e-05, - "loss": 3.2404, + "learning_rate": 1.8269275379608826e-05, + "loss": 3.2023, "step": 191500 }, { "epoch": 0.63, - "learning_rate": 1.83039643204542e-05, - "loss": 3.2454, + "learning_rate": 1.8252705810616456e-05, + "loss": 3.2084, "step": 191600 }, { - "epoch": 0.63, - "learning_rate": 1.8287421504337526e-05, - "loss": 3.2313, + "epoch": 0.64, + "learning_rate": 1.823613624162408e-05, + "loss": 3.2098, "step": 191700 }, { - "epoch": 0.63, - "learning_rate": 1.8270878688220854e-05, - "loss": 3.2249, + "epoch": 0.64, + "learning_rate": 1.8219566672631714e-05, + "loss": 3.216, "step": 191800 }, { - "epoch": 0.63, - "learning_rate": 1.8254335872104182e-05, - "loss": 3.2219, + "epoch": 0.64, + "learning_rate": 1.820299710363934e-05, + "loss": 3.2113, "step": 191900 }, { "epoch": 0.64, - "learning_rate": 1.8237793055987507e-05, - "loss": 3.2312, + "learning_rate": 1.818642753464697e-05, + "loss": 3.2106, "step": 192000 }, { "epoch": 0.64, - "learning_rate": 1.8221250239870835e-05, - "loss": 3.2344, + "learning_rate": 1.8169857965654598e-05, + "loss": 3.2105, "step": 192100 }, { "epoch": 0.64, - "learning_rate": 1.8204707423754162e-05, - "loss": 3.2349, + "learning_rate": 1.8153288396662227e-05, + "loss": 3.2169, "step": 192200 }, { "epoch": 0.64, - "learning_rate": 1.818816460763749e-05, - "loss": 3.2447, + "learning_rate": 1.8136718827669853e-05, + "loss": 3.2081, "step": 192300 }, { "epoch": 0.64, - "learning_rate": 1.8171621791520815e-05, - "loss": 3.2212, + "learning_rate": 1.8120149258677486e-05, + "loss": 3.2154, "step": 192400 }, { "epoch": 0.64, - "learning_rate": 1.8155078975404143e-05, - "loss": 3.2284, + "learning_rate": 1.810357968968511e-05, + "loss": 3.2097, "step": 192500 }, { "epoch": 0.64, - "learning_rate": 1.813853615928747e-05, - "loss": 3.2247, + "learning_rate": 1.808701012069274e-05, + "loss": 3.2035, "step": 192600 }, { "epoch": 0.64, - "learning_rate": 1.8121993343170795e-05, - "loss": 3.2227, + "learning_rate": 1.807044055170037e-05, + "loss": 3.2127, "step": 192700 }, { "epoch": 0.64, - "learning_rate": 1.810545052705412e-05, - "loss": 3.2372, + "learning_rate": 1.8053870982708e-05, + "loss": 3.2086, "step": 192800 }, { "epoch": 0.64, - "learning_rate": 1.808890771093745e-05, - "loss": 3.2332, + "learning_rate": 1.8037301413715625e-05, + "loss": 3.2048, "step": 192900 }, { "epoch": 0.64, - "learning_rate": 1.8072364894820776e-05, - "loss": 3.2189, + "learning_rate": 1.8020731844723258e-05, + "loss": 3.2162, "step": 193000 }, { "epoch": 0.64, - "learning_rate": 1.80558220787041e-05, - "loss": 3.2395, + "learning_rate": 1.8004162275730884e-05, + "loss": 3.2113, "step": 193100 }, { "epoch": 0.64, - "learning_rate": 1.803927926258743e-05, - "loss": 3.2343, + "learning_rate": 1.7987592706738513e-05, + "loss": 3.2067, "step": 193200 }, { "epoch": 0.64, - "learning_rate": 1.8022736446470756e-05, - "loss": 3.2339, + "learning_rate": 1.7971023137746142e-05, + "loss": 3.2054, "step": 193300 }, { "epoch": 0.64, - "learning_rate": 1.8006193630354084e-05, - "loss": 3.2441, + "learning_rate": 1.795445356875377e-05, + "loss": 3.2263, "step": 193400 }, { "epoch": 0.64, - "learning_rate": 1.7989650814237412e-05, - "loss": 3.2307, + "learning_rate": 1.7937883999761397e-05, + "loss": 3.2259, "step": 193500 }, { "epoch": 0.64, - "learning_rate": 1.7973107998120736e-05, - "loss": 3.224, + "learning_rate": 1.792131443076903e-05, + "loss": 3.209, "step": 193600 }, { "epoch": 0.64, - "learning_rate": 1.7956565182004064e-05, - "loss": 3.2356, + "learning_rate": 1.7904744861776655e-05, + "loss": 3.2209, "step": 193700 }, { "epoch": 0.64, - "learning_rate": 1.7940022365887392e-05, - "loss": 3.2271, + "learning_rate": 1.7888175292784285e-05, + "loss": 3.196, "step": 193800 }, { "epoch": 0.64, - "learning_rate": 1.7923479549770717e-05, - "loss": 3.2234, + "learning_rate": 1.7871605723791914e-05, + "loss": 3.2132, "step": 193900 }, { "epoch": 0.64, - "learning_rate": 1.7906936733654045e-05, - "loss": 3.223, + "learning_rate": 1.7855036154799543e-05, + "loss": 3.2047, "step": 194000 }, { "epoch": 0.64, - "learning_rate": 1.789039391753737e-05, - "loss": 3.2417, + "learning_rate": 1.783846658580717e-05, + "loss": 3.1997, "step": 194100 }, { "epoch": 0.64, - "learning_rate": 1.7873851101420697e-05, - "loss": 3.225, + "learning_rate": 1.78218970168148e-05, + "loss": 3.2146, "step": 194200 }, { "epoch": 0.64, - "learning_rate": 1.7857308285304025e-05, - "loss": 3.2354, + "learning_rate": 1.7805327447822427e-05, + "loss": 3.2159, "step": 194300 }, { "epoch": 0.64, - "learning_rate": 1.784076546918735e-05, - "loss": 3.2295, + "learning_rate": 1.7788757878830056e-05, + "loss": 3.218, "step": 194400 }, { "epoch": 0.64, - "learning_rate": 1.782422265307068e-05, - "loss": 3.2377, + "learning_rate": 1.7772188309837686e-05, + "loss": 3.2143, "step": 194500 }, { "epoch": 0.64, - "learning_rate": 1.7807679836954005e-05, - "loss": 3.232, + "learning_rate": 1.7755618740845315e-05, + "loss": 3.2165, "step": 194600 }, { - "epoch": 0.64, - "learning_rate": 1.779113702083733e-05, - "loss": 3.2402, + "epoch": 0.65, + "learning_rate": 1.773904917185294e-05, + "loss": 3.2065, "step": 194700 }, { - "epoch": 0.64, - "learning_rate": 1.777459420472066e-05, - "loss": 3.2288, + "epoch": 0.65, + "learning_rate": 1.772247960286057e-05, + "loss": 3.209, "step": 194800 }, { - "epoch": 0.64, - "learning_rate": 1.7758051388603986e-05, - "loss": 3.2274, + "epoch": 0.65, + "learning_rate": 1.77059100338682e-05, + "loss": 3.1997, "step": 194900 }, { "epoch": 0.65, - "learning_rate": 1.774150857248731e-05, - "loss": 3.2249, + "learning_rate": 1.7689340464875828e-05, + "loss": 3.2126, "step": 195000 }, { "epoch": 0.65, - "learning_rate": 1.7724965756370642e-05, - "loss": 3.2447, + "learning_rate": 1.7672770895883457e-05, + "loss": 3.2111, "step": 195100 }, { "epoch": 0.65, - "learning_rate": 1.7708422940253966e-05, - "loss": 3.2294, + "learning_rate": 1.7656201326891087e-05, + "loss": 3.213, "step": 195200 }, { "epoch": 0.65, - "learning_rate": 1.769188012413729e-05, - "loss": 3.2179, + "learning_rate": 1.7639631757898713e-05, + "loss": 3.1941, "step": 195300 }, { "epoch": 0.65, - "learning_rate": 1.767533730802062e-05, - "loss": 3.2449, + "learning_rate": 1.7623062188906342e-05, + "loss": 3.2127, "step": 195400 }, { "epoch": 0.65, - "learning_rate": 1.7658794491903947e-05, - "loss": 3.2291, + "learning_rate": 1.760649261991397e-05, + "loss": 3.2127, "step": 195500 }, { "epoch": 0.65, - "learning_rate": 1.7642251675787275e-05, - "loss": 3.2413, + "learning_rate": 1.75899230509216e-05, + "loss": 3.1989, "step": 195600 }, { "epoch": 0.65, - "learning_rate": 1.76257088596706e-05, - "loss": 3.2333, + "learning_rate": 1.757335348192923e-05, + "loss": 3.2102, "step": 195700 }, { "epoch": 0.65, - "learning_rate": 1.7609166043553927e-05, - "loss": 3.2383, + "learning_rate": 1.755678391293686e-05, + "loss": 3.2103, "step": 195800 }, { "epoch": 0.65, - "learning_rate": 1.7592623227437255e-05, - "loss": 3.2328, + "learning_rate": 1.7540214343944484e-05, + "loss": 3.2125, "step": 195900 }, { "epoch": 0.65, - "learning_rate": 1.757608041132058e-05, - "loss": 3.223, + "learning_rate": 1.7523644774952114e-05, + "loss": 3.2185, "step": 196000 }, { "epoch": 0.65, - "learning_rate": 1.7559537595203907e-05, - "loss": 3.2298, + "learning_rate": 1.7507075205959743e-05, + "loss": 3.2028, "step": 196100 }, { "epoch": 0.65, - "learning_rate": 1.7542994779087235e-05, - "loss": 3.2373, + "learning_rate": 1.7490505636967372e-05, + "loss": 3.1988, "step": 196200 }, { "epoch": 0.65, - "learning_rate": 1.752645196297056e-05, - "loss": 3.2341, + "learning_rate": 1.7473936067975e-05, + "loss": 3.2054, "step": 196300 }, { "epoch": 0.65, - "learning_rate": 1.7509909146853888e-05, - "loss": 3.2228, + "learning_rate": 1.745736649898263e-05, + "loss": 3.2123, "step": 196400 }, { "epoch": 0.65, - "learning_rate": 1.7493366330737216e-05, - "loss": 3.2404, + "learning_rate": 1.744079692999026e-05, + "loss": 3.2197, "step": 196500 }, { "epoch": 0.65, - "learning_rate": 1.747682351462054e-05, - "loss": 3.2297, + "learning_rate": 1.7424227360997885e-05, + "loss": 3.2052, "step": 196600 }, { "epoch": 0.65, - "learning_rate": 1.7460280698503868e-05, - "loss": 3.2413, + "learning_rate": 1.7407657792005515e-05, + "loss": 3.213, "step": 196700 }, { "epoch": 0.65, - "learning_rate": 1.7443737882387196e-05, - "loss": 3.2234, + "learning_rate": 1.7391088223013144e-05, + "loss": 3.2339, "step": 196800 }, { "epoch": 0.65, - "learning_rate": 1.742719506627052e-05, - "loss": 3.2257, + "learning_rate": 1.7374518654020773e-05, + "loss": 3.2103, "step": 196900 }, { "epoch": 0.65, - "learning_rate": 1.741065225015385e-05, - "loss": 3.2256, + "learning_rate": 1.7357949085028402e-05, + "loss": 3.2076, "step": 197000 }, { "epoch": 0.65, - "learning_rate": 1.7394109434037176e-05, - "loss": 3.2354, + "learning_rate": 1.734137951603603e-05, + "loss": 3.2111, "step": 197100 }, { "epoch": 0.65, - "learning_rate": 1.73775666179205e-05, - "loss": 3.2416, + "learning_rate": 1.7324809947043657e-05, + "loss": 3.2042, "step": 197200 }, { "epoch": 0.65, - "learning_rate": 1.736102380180383e-05, - "loss": 3.2235, + "learning_rate": 1.7308240378051286e-05, + "loss": 3.2044, "step": 197300 }, { "epoch": 0.65, - "learning_rate": 1.7344480985687157e-05, - "loss": 3.2341, + "learning_rate": 1.7291670809058916e-05, + "loss": 3.2034, "step": 197400 }, { "epoch": 0.65, - "learning_rate": 1.732793816957048e-05, - "loss": 3.2408, + "learning_rate": 1.7275101240066545e-05, + "loss": 3.2202, "step": 197500 }, { "epoch": 0.65, - "learning_rate": 1.731139535345381e-05, - "loss": 3.233, + "learning_rate": 1.7258531671074174e-05, + "loss": 3.2144, "step": 197600 }, { - "epoch": 0.65, - "learning_rate": 1.7294852537337137e-05, + "epoch": 0.66, + "learning_rate": 1.7241962102081803e-05, "loss": 3.2129, "step": 197700 }, { - "epoch": 0.65, - "learning_rate": 1.7278309721220465e-05, - "loss": 3.2282, + "epoch": 0.66, + "learning_rate": 1.722539253308943e-05, + "loss": 3.2161, "step": 197800 }, { - "epoch": 0.65, - "learning_rate": 1.726176690510379e-05, - "loss": 3.2286, + "epoch": 0.66, + "learning_rate": 1.7208822964097058e-05, + "loss": 3.1943, "step": 197900 }, { "epoch": 0.66, - "learning_rate": 1.7245224088987118e-05, - "loss": 3.2334, + "learning_rate": 1.7192253395104687e-05, + "loss": 3.2116, "step": 198000 }, { "epoch": 0.66, - "learning_rate": 1.7228681272870446e-05, - "loss": 3.2379, + "learning_rate": 1.7175683826112317e-05, + "loss": 3.2197, "step": 198100 }, { "epoch": 0.66, - "learning_rate": 1.721213845675377e-05, - "loss": 3.2225, + "learning_rate": 1.7159114257119946e-05, + "loss": 3.2022, "step": 198200 }, { "epoch": 0.66, - "learning_rate": 1.7195595640637098e-05, - "loss": 3.2176, + "learning_rate": 1.7142544688127575e-05, + "loss": 3.2089, "step": 198300 }, { "epoch": 0.66, - "learning_rate": 1.7179052824520426e-05, - "loss": 3.2342, + "learning_rate": 1.71259751191352e-05, + "loss": 3.2023, "step": 198400 }, { "epoch": 0.66, - "learning_rate": 1.716251000840375e-05, - "loss": 3.21, + "learning_rate": 1.7109405550142834e-05, + "loss": 3.2181, "step": 198500 }, { "epoch": 0.66, - "learning_rate": 1.714596719228708e-05, - "loss": 3.2301, + "learning_rate": 1.709283598115046e-05, + "loss": 3.205, "step": 198600 }, { "epoch": 0.66, - "learning_rate": 1.7129424376170406e-05, - "loss": 3.247, + "learning_rate": 1.707626641215809e-05, + "loss": 3.2179, "step": 198700 }, { "epoch": 0.66, - "learning_rate": 1.711288156005373e-05, - "loss": 3.2358, + "learning_rate": 1.7059696843165714e-05, + "loss": 3.201, "step": 198800 }, { "epoch": 0.66, - "learning_rate": 1.709633874393706e-05, - "loss": 3.2371, + "learning_rate": 1.7043127274173347e-05, + "loss": 3.2126, "step": 198900 }, { "epoch": 0.66, - "learning_rate": 1.7079795927820387e-05, - "loss": 3.2258, + "learning_rate": 1.7026557705180973e-05, + "loss": 3.1959, "step": 199000 }, { "epoch": 0.66, - "learning_rate": 1.706325311170371e-05, - "loss": 3.2237, + "learning_rate": 1.7009988136188602e-05, + "loss": 3.1999, "step": 199100 }, { "epoch": 0.66, - "learning_rate": 1.704671029558704e-05, - "loss": 3.2227, + "learning_rate": 1.699341856719623e-05, + "loss": 3.2214, "step": 199200 }, { "epoch": 0.66, - "learning_rate": 1.7030167479470367e-05, - "loss": 3.2289, + "learning_rate": 1.697684899820386e-05, + "loss": 3.2283, "step": 199300 }, { "epoch": 0.66, - "learning_rate": 1.701362466335369e-05, - "loss": 3.2273, + "learning_rate": 1.6960279429211486e-05, + "loss": 3.2203, "step": 199400 }, { "epoch": 0.66, - "learning_rate": 1.699708184723702e-05, - "loss": 3.2309, + "learning_rate": 1.694370986021912e-05, + "loss": 3.1907, "step": 199500 }, { "epoch": 0.66, - "learning_rate": 1.6980539031120347e-05, - "loss": 3.2358, + "learning_rate": 1.6927140291226745e-05, + "loss": 3.1986, "step": 199600 }, { "epoch": 0.66, - "learning_rate": 1.6963996215003675e-05, - "loss": 3.2187, + "learning_rate": 1.6910570722234374e-05, + "loss": 3.1994, "step": 199700 }, { "epoch": 0.66, - "learning_rate": 1.6947453398887e-05, - "loss": 3.2218, + "learning_rate": 1.6894001153242003e-05, + "loss": 3.1981, "step": 199800 }, { "epoch": 0.66, - "learning_rate": 1.6930910582770328e-05, - "loss": 3.2304, + "learning_rate": 1.6877431584249632e-05, + "loss": 3.2137, "step": 199900 }, { "epoch": 0.66, - "learning_rate": 1.6914367766653656e-05, - "loss": 3.2219, + "learning_rate": 1.6860862015257258e-05, + "loss": 3.204, "step": 200000 }, { "epoch": 0.66, - "learning_rate": 1.689782495053698e-05, - "loss": 3.2404, + "learning_rate": 1.684429244626489e-05, + "loss": 3.2166, "step": 200100 }, { "epoch": 0.66, - "learning_rate": 1.6881282134420308e-05, - "loss": 3.2395, + "learning_rate": 1.6827722877272516e-05, + "loss": 3.2157, "step": 200200 }, { "epoch": 0.66, - "learning_rate": 1.6864739318303636e-05, - "loss": 3.2354, + "learning_rate": 1.6811153308280146e-05, + "loss": 3.2037, "step": 200300 }, { "epoch": 0.66, - "learning_rate": 1.684819650218696e-05, - "loss": 3.2193, + "learning_rate": 1.6794583739287775e-05, + "loss": 3.2089, "step": 200400 }, { "epoch": 0.66, - "learning_rate": 1.6831653686070285e-05, - "loss": 3.2225, + "learning_rate": 1.6778014170295404e-05, + "loss": 3.2135, "step": 200500 }, { "epoch": 0.66, - "learning_rate": 1.6815110869953616e-05, - "loss": 3.2327, + "learning_rate": 1.676144460130303e-05, + "loss": 3.2092, "step": 200600 }, { - "epoch": 0.66, - "learning_rate": 1.679856805383694e-05, - "loss": 3.2374, + "epoch": 0.67, + "learning_rate": 1.6744875032310662e-05, + "loss": 3.2038, "step": 200700 }, { - "epoch": 0.66, - "learning_rate": 1.678202523772027e-05, - "loss": 3.2281, + "epoch": 0.67, + "learning_rate": 1.672830546331829e-05, + "loss": 3.2133, "step": 200800 }, { - "epoch": 0.66, - "learning_rate": 1.6765482421603597e-05, - "loss": 3.2368, + "epoch": 0.67, + "learning_rate": 1.6711735894325918e-05, + "loss": 3.2193, "step": 200900 }, { "epoch": 0.67, - "learning_rate": 1.674893960548692e-05, - "loss": 3.2386, + "learning_rate": 1.6695166325333547e-05, + "loss": 3.2117, "step": 201000 }, { "epoch": 0.67, - "learning_rate": 1.673239678937025e-05, - "loss": 3.2207, + "learning_rate": 1.6678596756341176e-05, + "loss": 3.2155, "step": 201100 }, { "epoch": 0.67, - "learning_rate": 1.6715853973253577e-05, - "loss": 3.2254, + "learning_rate": 1.6662027187348802e-05, + "loss": 3.1926, "step": 201200 }, { "epoch": 0.67, - "learning_rate": 1.6699311157136902e-05, - "loss": 3.2274, + "learning_rate": 1.6645457618356434e-05, + "loss": 3.2177, "step": 201300 }, { "epoch": 0.67, - "learning_rate": 1.668276834102023e-05, - "loss": 3.2266, + "learning_rate": 1.662888804936406e-05, + "loss": 3.2024, "step": 201400 }, { "epoch": 0.67, - "learning_rate": 1.6666225524903558e-05, - "loss": 3.2328, + "learning_rate": 1.661231848037169e-05, + "loss": 3.2102, "step": 201500 }, { "epoch": 0.67, - "learning_rate": 1.6649682708786882e-05, - "loss": 3.2137, + "learning_rate": 1.659574891137932e-05, + "loss": 3.2033, "step": 201600 }, { "epoch": 0.67, - "learning_rate": 1.663313989267021e-05, - "loss": 3.237, + "learning_rate": 1.6579179342386948e-05, + "loss": 3.2061, "step": 201700 }, { "epoch": 0.67, - "learning_rate": 1.6616597076553535e-05, - "loss": 3.2324, + "learning_rate": 1.6562609773394574e-05, + "loss": 3.2203, "step": 201800 }, { "epoch": 0.67, - "learning_rate": 1.6600054260436866e-05, - "loss": 3.2334, + "learning_rate": 1.6546040204402206e-05, + "loss": 3.2093, "step": 201900 }, { "epoch": 0.67, - "learning_rate": 1.658351144432019e-05, - "loss": 3.2387, + "learning_rate": 1.6529470635409832e-05, + "loss": 3.2131, "step": 202000 }, { "epoch": 0.67, - "learning_rate": 1.6566968628203515e-05, - "loss": 3.2386, + "learning_rate": 1.651290106641746e-05, + "loss": 3.1958, "step": 202100 }, { "epoch": 0.67, - "learning_rate": 1.6550425812086846e-05, - "loss": 3.2219, + "learning_rate": 1.649633149742509e-05, + "loss": 3.1999, "step": 202200 }, { "epoch": 0.67, - "learning_rate": 1.653388299597017e-05, - "loss": 3.2428, + "learning_rate": 1.647976192843272e-05, + "loss": 3.2168, "step": 202300 }, { "epoch": 0.67, - "learning_rate": 1.6517340179853495e-05, - "loss": 3.2337, + "learning_rate": 1.6463192359440345e-05, + "loss": 3.2204, "step": 202400 }, { "epoch": 0.67, - "learning_rate": 1.6500797363736827e-05, - "loss": 3.2371, + "learning_rate": 1.6446622790447978e-05, + "loss": 3.1891, "step": 202500 }, { "epoch": 0.67, - "learning_rate": 1.648425454762015e-05, - "loss": 3.2357, + "learning_rate": 1.6430053221455604e-05, + "loss": 3.2116, "step": 202600 }, { "epoch": 0.67, - "learning_rate": 1.6467711731503476e-05, - "loss": 3.2267, + "learning_rate": 1.6413483652463233e-05, + "loss": 3.2116, "step": 202700 }, { "epoch": 0.67, - "learning_rate": 1.6451168915386807e-05, - "loss": 3.2392, + "learning_rate": 1.6396914083470862e-05, + "loss": 3.2156, "step": 202800 }, { "epoch": 0.67, - "learning_rate": 1.643462609927013e-05, - "loss": 3.2313, + "learning_rate": 1.638034451447849e-05, + "loss": 3.2012, "step": 202900 }, { "epoch": 0.67, - "learning_rate": 1.641808328315346e-05, - "loss": 3.237, + "learning_rate": 1.6363774945486117e-05, + "loss": 3.2175, "step": 203000 }, { "epoch": 0.67, - "learning_rate": 1.6401540467036784e-05, - "loss": 3.2302, + "learning_rate": 1.6347205376493746e-05, + "loss": 3.2165, "step": 203100 }, { "epoch": 0.67, - "learning_rate": 1.6384997650920112e-05, - "loss": 3.2379, + "learning_rate": 1.6330635807501376e-05, + "loss": 3.2112, "step": 203200 }, { "epoch": 0.67, - "learning_rate": 1.636845483480344e-05, - "loss": 3.2171, + "learning_rate": 1.6314066238509005e-05, + "loss": 3.2194, "step": 203300 }, { "epoch": 0.67, - "learning_rate": 1.6351912018686764e-05, - "loss": 3.2237, + "learning_rate": 1.629749666951663e-05, + "loss": 3.217, "step": 203400 }, { "epoch": 0.67, - "learning_rate": 1.6335369202570092e-05, - "loss": 3.2424, + "learning_rate": 1.6280927100524263e-05, + "loss": 3.2142, "step": 203500 }, { "epoch": 0.67, - "learning_rate": 1.631882638645342e-05, - "loss": 3.2292, + "learning_rate": 1.626435753153189e-05, + "loss": 3.2103, "step": 203600 }, { - "epoch": 0.67, - "learning_rate": 1.6302283570336745e-05, - "loss": 3.2262, + "epoch": 0.68, + "learning_rate": 1.624778796253952e-05, + "loss": 3.2168, "step": 203700 }, { - "epoch": 0.67, - "learning_rate": 1.6285740754220073e-05, - "loss": 3.2236, + "epoch": 0.68, + "learning_rate": 1.6231218393547148e-05, + "loss": 3.2153, "step": 203800 }, { - "epoch": 0.67, - "learning_rate": 1.62691979381034e-05, - "loss": 3.2241, + "epoch": 0.68, + "learning_rate": 1.6214648824554777e-05, + "loss": 3.2123, "step": 203900 }, { - "epoch": 0.67, - "learning_rate": 1.6252655121986725e-05, - "loss": 3.2275, + "epoch": 0.68, + "learning_rate": 1.6198079255562403e-05, + "loss": 3.2171, "step": 204000 }, { "epoch": 0.68, - "learning_rate": 1.6236112305870056e-05, - "loss": 3.2283, + "learning_rate": 1.6181509686570035e-05, + "loss": 3.2188, "step": 204100 }, { "epoch": 0.68, - "learning_rate": 1.621956948975338e-05, - "loss": 3.2188, + "learning_rate": 1.616494011757766e-05, + "loss": 3.2026, "step": 204200 }, { "epoch": 0.68, - "learning_rate": 1.6203026673636706e-05, - "loss": 3.2077, + "learning_rate": 1.614837054858529e-05, + "loss": 3.1926, "step": 204300 }, { "epoch": 0.68, - "learning_rate": 1.6186483857520033e-05, - "loss": 3.2344, + "learning_rate": 1.613180097959292e-05, + "loss": 3.2184, "step": 204400 }, { "epoch": 0.68, - "learning_rate": 1.616994104140336e-05, - "loss": 3.2209, + "learning_rate": 1.611523141060055e-05, + "loss": 3.2056, "step": 204500 }, { "epoch": 0.68, - "learning_rate": 1.6153398225286686e-05, - "loss": 3.2377, + "learning_rate": 1.6098661841608174e-05, + "loss": 3.2104, "step": 204600 }, { "epoch": 0.68, - "learning_rate": 1.6136855409170014e-05, - "loss": 3.2275, + "learning_rate": 1.6082092272615807e-05, + "loss": 3.2201, "step": 204700 }, { "epoch": 0.68, - "learning_rate": 1.6120312593053342e-05, - "loss": 3.2346, + "learning_rate": 1.6065522703623433e-05, + "loss": 3.2007, "step": 204800 }, { "epoch": 0.68, - "learning_rate": 1.6103769776936666e-05, - "loss": 3.2306, + "learning_rate": 1.6048953134631062e-05, + "loss": 3.2181, "step": 204900 }, { "epoch": 0.68, - "learning_rate": 1.6087226960819994e-05, - "loss": 3.2046, + "learning_rate": 1.603238356563869e-05, + "loss": 3.1903, "step": 205000 }, { "epoch": 0.68, - "learning_rate": 1.6070684144703322e-05, - "loss": 3.2228, + "learning_rate": 1.601581399664632e-05, + "loss": 3.2141, "step": 205100 }, { "epoch": 0.68, - "learning_rate": 1.605414132858665e-05, - "loss": 3.2538, + "learning_rate": 1.5999244427653946e-05, + "loss": 3.2096, "step": 205200 }, { "epoch": 0.68, - "learning_rate": 1.6037598512469975e-05, - "loss": 3.2279, + "learning_rate": 1.598267485866158e-05, + "loss": 3.205, "step": 205300 }, { "epoch": 0.68, - "learning_rate": 1.6021055696353303e-05, - "loss": 3.233, + "learning_rate": 1.5966105289669205e-05, + "loss": 3.2026, "step": 205400 }, { "epoch": 0.68, - "learning_rate": 1.600451288023663e-05, - "loss": 3.2272, + "learning_rate": 1.5949535720676834e-05, + "loss": 3.2046, "step": 205500 }, { "epoch": 0.68, - "learning_rate": 1.5987970064119955e-05, - "loss": 3.224, + "learning_rate": 1.5932966151684463e-05, + "loss": 3.2164, "step": 205600 }, { "epoch": 0.68, - "learning_rate": 1.5971427248003283e-05, - "loss": 3.2302, + "learning_rate": 1.5916396582692092e-05, + "loss": 3.2124, "step": 205700 }, { "epoch": 0.68, - "learning_rate": 1.595488443188661e-05, - "loss": 3.2254, + "learning_rate": 1.5899827013699718e-05, + "loss": 3.2063, "step": 205800 }, { "epoch": 0.68, - "learning_rate": 1.5938341615769935e-05, - "loss": 3.2294, + "learning_rate": 1.588325744470735e-05, + "loss": 3.22, "step": 205900 }, { "epoch": 0.68, - "learning_rate": 1.5921798799653263e-05, - "loss": 3.2239, + "learning_rate": 1.5866687875714977e-05, + "loss": 3.2044, "step": 206000 }, { "epoch": 0.68, - "learning_rate": 1.590525598353659e-05, - "loss": 3.2282, + "learning_rate": 1.5850118306722606e-05, + "loss": 3.2041, "step": 206100 }, { "epoch": 0.68, - "learning_rate": 1.5888713167419916e-05, - "loss": 3.225, + "learning_rate": 1.5833548737730235e-05, + "loss": 3.2142, "step": 206200 }, { "epoch": 0.68, - "learning_rate": 1.5872170351303244e-05, - "loss": 3.2174, + "learning_rate": 1.5816979168737864e-05, + "loss": 3.2063, "step": 206300 }, { "epoch": 0.68, - "learning_rate": 1.585562753518657e-05, - "loss": 3.218, + "learning_rate": 1.580040959974549e-05, + "loss": 3.2229, "step": 206400 }, { "epoch": 0.68, - "learning_rate": 1.5839084719069896e-05, - "loss": 3.2394, + "learning_rate": 1.5783840030753123e-05, + "loss": 3.2208, "step": 206500 }, { "epoch": 0.68, - "learning_rate": 1.5822541902953224e-05, - "loss": 3.2201, + "learning_rate": 1.576727046176075e-05, + "loss": 3.2127, "step": 206600 }, { "epoch": 0.68, - "learning_rate": 1.5805999086836552e-05, - "loss": 3.2181, + "learning_rate": 1.5750700892768378e-05, + "loss": 3.2129, "step": 206700 }, { - "epoch": 0.68, - "learning_rate": 1.5789456270719877e-05, - "loss": 3.2116, + "epoch": 0.69, + "learning_rate": 1.5734131323776007e-05, + "loss": 3.2164, "step": 206800 }, { - "epoch": 0.68, - "learning_rate": 1.5772913454603204e-05, - "loss": 3.214, + "epoch": 0.69, + "learning_rate": 1.5717561754783636e-05, + "loss": 3.2164, "step": 206900 }, { - "epoch": 0.68, - "learning_rate": 1.5756370638486532e-05, - "loss": 3.2215, + "epoch": 0.69, + "learning_rate": 1.5700992185791262e-05, + "loss": 3.2027, "step": 207000 }, { "epoch": 0.69, - "learning_rate": 1.573982782236986e-05, - "loss": 3.2275, + "learning_rate": 1.5684422616798894e-05, + "loss": 3.206, "step": 207100 }, { "epoch": 0.69, - "learning_rate": 1.5723285006253185e-05, - "loss": 3.2301, + "learning_rate": 1.566785304780652e-05, + "loss": 3.2023, "step": 207200 }, { "epoch": 0.69, - "learning_rate": 1.5706742190136513e-05, - "loss": 3.2208, + "learning_rate": 1.565128347881415e-05, + "loss": 3.2103, "step": 207300 }, { "epoch": 0.69, - "learning_rate": 1.569019937401984e-05, - "loss": 3.2345, + "learning_rate": 1.563471390982178e-05, + "loss": 3.217, "step": 207400 }, { "epoch": 0.69, - "learning_rate": 1.5673656557903165e-05, - "loss": 3.2377, + "learning_rate": 1.5618144340829408e-05, + "loss": 3.2069, "step": 207500 }, { "epoch": 0.69, - "learning_rate": 1.5657113741786493e-05, - "loss": 3.226, + "learning_rate": 1.5601574771837034e-05, + "loss": 3.2172, "step": 207600 }, { "epoch": 0.69, - "learning_rate": 1.564057092566982e-05, - "loss": 3.2392, + "learning_rate": 1.5585005202844663e-05, + "loss": 3.213, "step": 207700 }, { "epoch": 0.69, - "learning_rate": 1.5624028109553146e-05, - "loss": 3.2296, + "learning_rate": 1.5568435633852292e-05, + "loss": 3.1998, "step": 207800 }, { "epoch": 0.69, - "learning_rate": 1.560748529343647e-05, - "loss": 3.2288, + "learning_rate": 1.555186606485992e-05, + "loss": 3.2063, "step": 207900 }, { "epoch": 0.69, - "learning_rate": 1.55909424773198e-05, - "loss": 3.228, + "learning_rate": 1.553529649586755e-05, + "loss": 3.2105, "step": 208000 }, { "epoch": 0.69, - "learning_rate": 1.5574399661203126e-05, - "loss": 3.2338, + "learning_rate": 1.551872692687518e-05, + "loss": 3.2186, "step": 208100 }, { "epoch": 0.69, - "learning_rate": 1.5557856845086454e-05, - "loss": 3.2245, + "learning_rate": 1.550215735788281e-05, + "loss": 3.2136, "step": 208200 }, { "epoch": 0.69, - "learning_rate": 1.5541314028969782e-05, - "loss": 3.2278, + "learning_rate": 1.5485587788890435e-05, + "loss": 3.1979, "step": 208300 }, { "epoch": 0.69, - "learning_rate": 1.5524771212853106e-05, - "loss": 3.228, + "learning_rate": 1.5469018219898064e-05, + "loss": 3.2201, "step": 208400 }, { "epoch": 0.69, - "learning_rate": 1.5508228396736434e-05, - "loss": 3.2347, + "learning_rate": 1.5452448650905693e-05, + "loss": 3.2041, "step": 208500 }, { "epoch": 0.69, - "learning_rate": 1.5491685580619762e-05, - "loss": 3.2341, + "learning_rate": 1.5435879081913322e-05, + "loss": 3.2177, "step": 208600 }, { "epoch": 0.69, - "learning_rate": 1.5475142764503087e-05, - "loss": 3.2229, + "learning_rate": 1.541930951292095e-05, + "loss": 3.2171, "step": 208700 }, { "epoch": 0.69, - "learning_rate": 1.5458599948386415e-05, - "loss": 3.2169, + "learning_rate": 1.540273994392858e-05, + "loss": 3.2134, "step": 208800 }, { "epoch": 0.69, - "learning_rate": 1.5442057132269743e-05, - "loss": 3.2493, + "learning_rate": 1.5386170374936207e-05, + "loss": 3.2089, "step": 208900 }, { "epoch": 0.69, - "learning_rate": 1.5425514316153067e-05, - "loss": 3.2421, + "learning_rate": 1.5369600805943836e-05, + "loss": 3.2007, "step": 209000 }, { "epoch": 0.69, - "learning_rate": 1.5408971500036395e-05, - "loss": 3.2345, + "learning_rate": 1.5353031236951465e-05, + "loss": 3.2131, "step": 209100 }, { "epoch": 0.69, - "learning_rate": 1.539242868391972e-05, - "loss": 3.2206, + "learning_rate": 1.5336461667959094e-05, + "loss": 3.2048, "step": 209200 }, { "epoch": 0.69, - "learning_rate": 1.537588586780305e-05, - "loss": 3.2227, + "learning_rate": 1.5319892098966723e-05, + "loss": 3.2046, "step": 209300 }, { "epoch": 0.69, - "learning_rate": 1.5359343051686375e-05, - "loss": 3.2274, + "learning_rate": 1.5303322529974353e-05, + "loss": 3.2242, "step": 209400 }, { "epoch": 0.69, - "learning_rate": 1.53428002355697e-05, - "loss": 3.2289, + "learning_rate": 1.528675296098198e-05, + "loss": 3.2035, "step": 209500 }, { "epoch": 0.69, - "learning_rate": 1.532625741945303e-05, - "loss": 3.223, + "learning_rate": 1.5270183391989608e-05, + "loss": 3.2067, "step": 209600 }, { "epoch": 0.69, - "learning_rate": 1.5309714603336356e-05, - "loss": 3.211, + "learning_rate": 1.5253613822997237e-05, + "loss": 3.2158, "step": 209700 }, { - "epoch": 0.69, - "learning_rate": 1.529317178721968e-05, - "loss": 3.2255, + "epoch": 0.7, + "learning_rate": 1.5237044254004864e-05, + "loss": 3.2135, "step": 209800 }, { - "epoch": 0.69, - "learning_rate": 1.527662897110301e-05, - "loss": 3.2144, + "epoch": 0.7, + "learning_rate": 1.5220474685012495e-05, + "loss": 3.21, "step": 209900 }, { - "epoch": 0.69, - "learning_rate": 1.5260086154986336e-05, - "loss": 3.2107, + "epoch": 0.7, + "learning_rate": 1.5203905116020123e-05, + "loss": 3.2142, "step": 210000 }, { "epoch": 0.7, - "learning_rate": 1.5243543338869662e-05, - "loss": 3.2262, + "learning_rate": 1.518733554702775e-05, + "loss": 3.2031, "step": 210100 }, { "epoch": 0.7, - "learning_rate": 1.522700052275299e-05, - "loss": 3.2254, + "learning_rate": 1.5170765978035381e-05, + "loss": 3.2151, "step": 210200 }, { "epoch": 0.7, - "learning_rate": 1.5210457706636317e-05, - "loss": 3.2262, + "learning_rate": 1.5154196409043009e-05, + "loss": 3.2074, "step": 210300 }, { "epoch": 0.7, - "learning_rate": 1.5193914890519644e-05, - "loss": 3.213, + "learning_rate": 1.5137626840050636e-05, + "loss": 3.2047, "step": 210400 }, { "epoch": 0.7, - "learning_rate": 1.517737207440297e-05, - "loss": 3.2287, + "learning_rate": 1.5121057271058267e-05, + "loss": 3.2033, "step": 210500 }, { "epoch": 0.7, - "learning_rate": 1.5160829258286297e-05, - "loss": 3.2259, + "learning_rate": 1.5104487702065895e-05, + "loss": 3.2055, "step": 210600 }, { "epoch": 0.7, - "learning_rate": 1.5144286442169625e-05, - "loss": 3.2214, + "learning_rate": 1.5087918133073522e-05, + "loss": 3.222, "step": 210700 }, { "epoch": 0.7, - "learning_rate": 1.5127743626052951e-05, - "loss": 3.2184, + "learning_rate": 1.5071348564081153e-05, + "loss": 3.2139, "step": 210800 }, { "epoch": 0.7, - "learning_rate": 1.5111200809936277e-05, - "loss": 3.2174, + "learning_rate": 1.505477899508878e-05, + "loss": 3.2039, "step": 210900 }, { "epoch": 0.7, - "learning_rate": 1.5094657993819605e-05, - "loss": 3.2122, + "learning_rate": 1.5038209426096408e-05, + "loss": 3.2032, "step": 211000 }, { "epoch": 0.7, - "learning_rate": 1.5078115177702931e-05, - "loss": 3.2344, + "learning_rate": 1.5021639857104039e-05, + "loss": 3.2188, "step": 211100 }, { "epoch": 0.7, - "learning_rate": 1.5061572361586258e-05, - "loss": 3.2194, + "learning_rate": 1.5005070288111666e-05, + "loss": 3.2164, "step": 211200 }, { "epoch": 0.7, - "learning_rate": 1.5045029545469586e-05, - "loss": 3.2268, + "learning_rate": 1.4988500719119294e-05, + "loss": 3.1936, "step": 211300 }, { "epoch": 0.7, - "learning_rate": 1.5028486729352912e-05, - "loss": 3.2215, + "learning_rate": 1.4971931150126925e-05, + "loss": 3.2153, "step": 211400 }, { "epoch": 0.7, - "learning_rate": 1.501194391323624e-05, - "loss": 3.2137, + "learning_rate": 1.4955361581134552e-05, + "loss": 3.2276, "step": 211500 }, { "epoch": 0.7, - "learning_rate": 1.4995401097119566e-05, - "loss": 3.2224, + "learning_rate": 1.493879201214218e-05, + "loss": 3.2091, "step": 211600 }, { "epoch": 0.7, - "learning_rate": 1.4978858281002892e-05, - "loss": 3.2359, + "learning_rate": 1.492222244314981e-05, + "loss": 3.2166, "step": 211700 }, { "epoch": 0.7, - "learning_rate": 1.496231546488622e-05, - "loss": 3.2345, + "learning_rate": 1.4905652874157438e-05, + "loss": 3.2097, "step": 211800 }, { "epoch": 0.7, - "learning_rate": 1.4945772648769546e-05, - "loss": 3.2309, + "learning_rate": 1.4889083305165066e-05, + "loss": 3.2009, "step": 211900 }, { "epoch": 0.7, - "learning_rate": 1.4929229832652873e-05, - "loss": 3.2221, + "learning_rate": 1.4872513736172693e-05, + "loss": 3.2078, "step": 212000 }, { "epoch": 0.7, - "learning_rate": 1.49126870165362e-05, - "loss": 3.2354, + "learning_rate": 1.4855944167180324e-05, + "loss": 3.1974, "step": 212100 }, { "epoch": 0.7, - "learning_rate": 1.4896144200419527e-05, - "loss": 3.239, + "learning_rate": 1.4839374598187952e-05, + "loss": 3.2081, "step": 212200 }, { "epoch": 0.7, - "learning_rate": 1.4879601384302851e-05, - "loss": 3.2341, + "learning_rate": 1.482280502919558e-05, + "loss": 3.2127, "step": 212300 }, { "epoch": 0.7, - "learning_rate": 1.4863058568186181e-05, - "loss": 3.2317, + "learning_rate": 1.480623546020321e-05, + "loss": 3.2013, "step": 212400 }, { "epoch": 0.7, - "learning_rate": 1.4846515752069507e-05, - "loss": 3.2175, + "learning_rate": 1.4789665891210838e-05, + "loss": 3.198, "step": 212500 }, { "epoch": 0.7, - "learning_rate": 1.4829972935952835e-05, - "loss": 3.2318, + "learning_rate": 1.4773096322218467e-05, + "loss": 3.213, "step": 212600 }, { "epoch": 0.7, - "learning_rate": 1.4813430119836161e-05, - "loss": 3.2361, + "learning_rate": 1.4756526753226096e-05, + "loss": 3.217, "step": 212700 }, { - "epoch": 0.7, - "learning_rate": 1.4796887303719486e-05, - "loss": 3.2198, + "epoch": 0.71, + "learning_rate": 1.4739957184233724e-05, + "loss": 3.2223, "step": 212800 }, { - "epoch": 0.7, - "learning_rate": 1.4780344487602815e-05, - "loss": 3.2249, + "epoch": 0.71, + "learning_rate": 1.4723387615241353e-05, + "loss": 3.2084, "step": 212900 }, { - "epoch": 0.7, - "learning_rate": 1.4763801671486142e-05, - "loss": 3.2325, + "epoch": 0.71, + "learning_rate": 1.4706818046248982e-05, + "loss": 3.2058, "step": 213000 }, { "epoch": 0.71, - "learning_rate": 1.4747258855369466e-05, - "loss": 3.2207, + "learning_rate": 1.469024847725661e-05, + "loss": 3.2136, "step": 213100 }, { "epoch": 0.71, - "learning_rate": 1.4730716039252796e-05, - "loss": 3.216, + "learning_rate": 1.4673678908264239e-05, + "loss": 3.2128, "step": 213200 }, { "epoch": 0.71, - "learning_rate": 1.4714173223136122e-05, - "loss": 3.2278, + "learning_rate": 1.4657109339271868e-05, + "loss": 3.2026, "step": 213300 }, { "epoch": 0.71, - "learning_rate": 1.469763040701945e-05, - "loss": 3.2046, + "learning_rate": 1.4640539770279495e-05, + "loss": 3.2095, "step": 213400 }, { "epoch": 0.71, - "learning_rate": 1.4681087590902776e-05, - "loss": 3.2214, + "learning_rate": 1.4623970201287125e-05, + "loss": 3.2105, "step": 213500 }, { "epoch": 0.71, - "learning_rate": 1.46645447747861e-05, - "loss": 3.2349, + "learning_rate": 1.4607400632294754e-05, + "loss": 3.2065, "step": 213600 }, { "epoch": 0.71, - "learning_rate": 1.464800195866943e-05, - "loss": 3.2295, + "learning_rate": 1.4590831063302381e-05, + "loss": 3.2127, "step": 213700 }, { "epoch": 0.71, - "learning_rate": 1.4631459142552757e-05, - "loss": 3.2238, + "learning_rate": 1.457426149431001e-05, + "loss": 3.2109, "step": 213800 }, { "epoch": 0.71, - "learning_rate": 1.4614916326436081e-05, - "loss": 3.2328, + "learning_rate": 1.455769192531764e-05, + "loss": 3.2129, "step": 213900 }, { "epoch": 0.71, - "learning_rate": 1.459837351031941e-05, - "loss": 3.2284, + "learning_rate": 1.4541122356325267e-05, + "loss": 3.2073, "step": 214000 }, { "epoch": 0.71, - "learning_rate": 1.4581830694202735e-05, - "loss": 3.2291, + "learning_rate": 1.4524552787332896e-05, + "loss": 3.204, "step": 214100 }, { "epoch": 0.71, - "learning_rate": 1.4565287878086061e-05, - "loss": 3.2241, + "learning_rate": 1.4507983218340526e-05, + "loss": 3.1946, "step": 214200 }, { "epoch": 0.71, - "learning_rate": 1.4548745061969391e-05, - "loss": 3.2261, + "learning_rate": 1.4491413649348153e-05, + "loss": 3.1985, "step": 214300 }, { "epoch": 0.71, - "learning_rate": 1.4532202245852716e-05, - "loss": 3.2266, + "learning_rate": 1.4474844080355782e-05, + "loss": 3.2131, "step": 214400 }, { "epoch": 0.71, - "learning_rate": 1.4515659429736045e-05, - "loss": 3.2286, + "learning_rate": 1.4458274511363412e-05, + "loss": 3.205, "step": 214500 }, { "epoch": 0.71, - "learning_rate": 1.4499116613619371e-05, - "loss": 3.2204, + "learning_rate": 1.4441704942371039e-05, + "loss": 3.21, "step": 214600 }, { "epoch": 0.71, - "learning_rate": 1.4482573797502696e-05, - "loss": 3.2378, + "learning_rate": 1.4425135373378668e-05, + "loss": 3.1882, "step": 214700 }, { "epoch": 0.71, - "learning_rate": 1.4466030981386026e-05, - "loss": 3.2296, + "learning_rate": 1.4408565804386297e-05, + "loss": 3.2093, "step": 214800 }, { "epoch": 0.71, - "learning_rate": 1.444948816526935e-05, - "loss": 3.2164, + "learning_rate": 1.4391996235393927e-05, + "loss": 3.1959, "step": 214900 }, { "epoch": 0.71, - "learning_rate": 1.4432945349152676e-05, - "loss": 3.2139, + "learning_rate": 1.4375426666401554e-05, + "loss": 3.2058, "step": 215000 }, { "epoch": 0.71, - "learning_rate": 1.4416402533036006e-05, - "loss": 3.2196, + "learning_rate": 1.4358857097409183e-05, + "loss": 3.2058, "step": 215100 }, { "epoch": 0.71, - "learning_rate": 1.439985971691933e-05, - "loss": 3.2271, + "learning_rate": 1.4342287528416813e-05, + "loss": 3.1981, "step": 215200 }, { "epoch": 0.71, - "learning_rate": 1.4383316900802657e-05, - "loss": 3.2253, + "learning_rate": 1.432571795942444e-05, + "loss": 3.2173, "step": 215300 }, { "epoch": 0.71, - "learning_rate": 1.4366774084685985e-05, - "loss": 3.22, + "learning_rate": 1.430914839043207e-05, + "loss": 3.1971, "step": 215400 }, { "epoch": 0.71, - "learning_rate": 1.4350231268569311e-05, - "loss": 3.2166, + "learning_rate": 1.4292578821439699e-05, + "loss": 3.2072, "step": 215500 }, { "epoch": 0.71, - "learning_rate": 1.433368845245264e-05, - "loss": 3.2289, + "learning_rate": 1.4276009252447326e-05, + "loss": 3.2008, "step": 215600 }, { "epoch": 0.71, - "learning_rate": 1.4317145636335965e-05, - "loss": 3.2332, + "learning_rate": 1.4259439683454955e-05, + "loss": 3.1914, "step": 215700 }, { - "epoch": 0.71, - "learning_rate": 1.4300602820219291e-05, - "loss": 3.2239, + "epoch": 0.72, + "learning_rate": 1.4242870114462584e-05, + "loss": 3.1974, "step": 215800 }, { - "epoch": 0.71, - "learning_rate": 1.4284060004102621e-05, - "loss": 3.2292, + "epoch": 0.72, + "learning_rate": 1.4226300545470212e-05, + "loss": 3.1991, "step": 215900 }, { - "epoch": 0.71, - "learning_rate": 1.4267517187985945e-05, - "loss": 3.2264, + "epoch": 0.72, + "learning_rate": 1.4209730976477841e-05, + "loss": 3.1959, "step": 216000 }, { - "epoch": 0.71, - "learning_rate": 1.4250974371869272e-05, - "loss": 3.2311, + "epoch": 0.72, + "learning_rate": 1.419316140748547e-05, + "loss": 3.2113, "step": 216100 }, { "epoch": 0.72, - "learning_rate": 1.42344315557526e-05, - "loss": 3.2259, + "learning_rate": 1.4176591838493098e-05, + "loss": 3.1974, "step": 216200 }, { "epoch": 0.72, - "learning_rate": 1.4217888739635926e-05, - "loss": 3.2308, + "learning_rate": 1.4160022269500725e-05, + "loss": 3.2075, "step": 216300 }, { "epoch": 0.72, - "learning_rate": 1.4201345923519252e-05, - "loss": 3.2292, + "learning_rate": 1.4143452700508356e-05, + "loss": 3.2106, "step": 216400 }, { "epoch": 0.72, - "learning_rate": 1.418480310740258e-05, - "loss": 3.2345, + "learning_rate": 1.4126883131515984e-05, + "loss": 3.2003, "step": 216500 }, { "epoch": 0.72, - "learning_rate": 1.4168260291285906e-05, - "loss": 3.2297, + "learning_rate": 1.4110313562523611e-05, + "loss": 3.1879, "step": 216600 }, { "epoch": 0.72, - "learning_rate": 1.4151717475169234e-05, - "loss": 3.2273, + "learning_rate": 1.4093743993531242e-05, + "loss": 3.2126, "step": 216700 }, { "epoch": 0.72, - "learning_rate": 1.413517465905256e-05, - "loss": 3.2256, + "learning_rate": 1.407717442453887e-05, + "loss": 3.2016, "step": 216800 }, { "epoch": 0.72, - "learning_rate": 1.4118631842935887e-05, - "loss": 3.2297, + "learning_rate": 1.4060604855546497e-05, + "loss": 3.211, "step": 216900 }, { "epoch": 0.72, - "learning_rate": 1.4102089026819215e-05, - "loss": 3.214, + "learning_rate": 1.4044035286554128e-05, + "loss": 3.1997, "step": 217000 }, { "epoch": 0.72, - "learning_rate": 1.408554621070254e-05, - "loss": 3.2228, + "learning_rate": 1.4027465717561756e-05, + "loss": 3.2103, "step": 217100 }, { "epoch": 0.72, - "learning_rate": 1.4069003394585867e-05, - "loss": 3.2289, + "learning_rate": 1.4010896148569383e-05, + "loss": 3.196, "step": 217200 }, { "epoch": 0.72, - "learning_rate": 1.4052460578469195e-05, - "loss": 3.2406, + "learning_rate": 1.3994326579577014e-05, + "loss": 3.2021, "step": 217300 }, { "epoch": 0.72, - "learning_rate": 1.4035917762352521e-05, - "loss": 3.2446, + "learning_rate": 1.3977757010584642e-05, + "loss": 3.2191, "step": 217400 }, { "epoch": 0.72, - "learning_rate": 1.4019374946235847e-05, - "loss": 3.2331, + "learning_rate": 1.3961187441592269e-05, + "loss": 3.2132, "step": 217500 }, { "epoch": 0.72, - "learning_rate": 1.4002832130119175e-05, - "loss": 3.2407, + "learning_rate": 1.39446178725999e-05, + "loss": 3.2086, "step": 217600 }, { "epoch": 0.72, - "learning_rate": 1.3986289314002502e-05, - "loss": 3.2233, + "learning_rate": 1.3928048303607527e-05, + "loss": 3.2059, "step": 217700 }, { "epoch": 0.72, - "learning_rate": 1.396974649788583e-05, - "loss": 3.2134, + "learning_rate": 1.3911478734615155e-05, + "loss": 3.1954, "step": 217800 }, { "epoch": 0.72, - "learning_rate": 1.3953203681769156e-05, - "loss": 3.2192, + "learning_rate": 1.3894909165622786e-05, + "loss": 3.2142, "step": 217900 }, { "epoch": 0.72, - "learning_rate": 1.3936660865652482e-05, - "loss": 3.2357, + "learning_rate": 1.3878339596630413e-05, + "loss": 3.2026, "step": 218000 }, { "epoch": 0.72, - "learning_rate": 1.392011804953581e-05, - "loss": 3.2293, + "learning_rate": 1.3861770027638041e-05, + "loss": 3.2073, "step": 218100 }, { "epoch": 0.72, - "learning_rate": 1.3903575233419136e-05, - "loss": 3.2336, + "learning_rate": 1.3845200458645672e-05, + "loss": 3.212, "step": 218200 }, { "epoch": 0.72, - "learning_rate": 1.3887032417302462e-05, - "loss": 3.2268, + "learning_rate": 1.38286308896533e-05, + "loss": 3.1912, "step": 218300 }, { "epoch": 0.72, - "learning_rate": 1.387048960118579e-05, - "loss": 3.2261, + "learning_rate": 1.3812061320660927e-05, + "loss": 3.211, "step": 218400 }, { "epoch": 0.72, - "learning_rate": 1.3853946785069116e-05, - "loss": 3.2152, + "learning_rate": 1.3795491751668558e-05, + "loss": 3.1964, "step": 218500 }, { "epoch": 0.72, - "learning_rate": 1.3837403968952443e-05, - "loss": 3.2371, + "learning_rate": 1.3778922182676185e-05, + "loss": 3.2132, "step": 218600 }, { "epoch": 0.72, - "learning_rate": 1.382086115283577e-05, - "loss": 3.2242, + "learning_rate": 1.3762352613683813e-05, + "loss": 3.1995, "step": 218700 }, { - "epoch": 0.72, - "learning_rate": 1.3804318336719097e-05, - "loss": 3.2144, + "epoch": 0.73, + "learning_rate": 1.3745783044691444e-05, + "loss": 3.2109, "step": 218800 }, { - "epoch": 0.72, - "learning_rate": 1.3787775520602425e-05, - "loss": 3.2265, + "epoch": 0.73, + "learning_rate": 1.3729213475699071e-05, + "loss": 3.2125, "step": 218900 }, { - "epoch": 0.72, - "learning_rate": 1.3771232704485751e-05, - "loss": 3.2288, + "epoch": 0.73, + "learning_rate": 1.3712643906706699e-05, + "loss": 3.2031, "step": 219000 }, { - "epoch": 0.72, - "learning_rate": 1.3754689888369077e-05, - "loss": 3.2301, + "epoch": 0.73, + "learning_rate": 1.369607433771433e-05, + "loss": 3.1986, "step": 219100 }, { "epoch": 0.73, - "learning_rate": 1.3738147072252405e-05, - "loss": 3.2292, + "learning_rate": 1.3679504768721957e-05, + "loss": 3.1981, "step": 219200 }, { "epoch": 0.73, - "learning_rate": 1.3721604256135731e-05, - "loss": 3.2243, + "learning_rate": 1.3662935199729585e-05, + "loss": 3.2263, "step": 219300 }, { "epoch": 0.73, - "learning_rate": 1.3705061440019058e-05, - "loss": 3.2145, + "learning_rate": 1.3646365630737216e-05, + "loss": 3.2184, "step": 219400 }, { "epoch": 0.73, - "learning_rate": 1.3688518623902385e-05, - "loss": 3.2151, + "learning_rate": 1.3629796061744843e-05, + "loss": 3.2163, "step": 219500 }, { "epoch": 0.73, - "learning_rate": 1.3671975807785712e-05, - "loss": 3.2129, + "learning_rate": 1.361322649275247e-05, + "loss": 3.1977, "step": 219600 }, { "epoch": 0.73, - "learning_rate": 1.3655432991669038e-05, - "loss": 3.2263, + "learning_rate": 1.3596656923760101e-05, + "loss": 3.2052, "step": 219700 }, { "epoch": 0.73, - "learning_rate": 1.3638890175552366e-05, - "loss": 3.2195, + "learning_rate": 1.3580087354767729e-05, + "loss": 3.197, "step": 219800 }, { "epoch": 0.73, - "learning_rate": 1.3622347359435692e-05, - "loss": 3.2189, + "learning_rate": 1.3563517785775356e-05, + "loss": 3.2158, "step": 219900 }, { "epoch": 0.73, - "learning_rate": 1.360580454331902e-05, - "loss": 3.2307, + "learning_rate": 1.3546948216782987e-05, + "loss": 3.2057, "step": 220000 }, { "epoch": 0.73, - "learning_rate": 1.3589261727202346e-05, - "loss": 3.2292, + "learning_rate": 1.3530378647790615e-05, + "loss": 3.2018, "step": 220100 }, { "epoch": 0.73, - "learning_rate": 1.3572718911085672e-05, - "loss": 3.2097, + "learning_rate": 1.3513809078798242e-05, + "loss": 3.2021, "step": 220200 }, { "epoch": 0.73, - "learning_rate": 1.3556176094969e-05, - "loss": 3.2338, + "learning_rate": 1.3497239509805873e-05, + "loss": 3.2095, "step": 220300 }, { "epoch": 0.73, - "learning_rate": 1.3539633278852327e-05, - "loss": 3.2049, + "learning_rate": 1.34806699408135e-05, + "loss": 3.2058, "step": 220400 }, { "epoch": 0.73, - "learning_rate": 1.3523090462735651e-05, - "loss": 3.2335, + "learning_rate": 1.3464100371821128e-05, + "loss": 3.2061, "step": 220500 }, { "epoch": 0.73, - "learning_rate": 1.350654764661898e-05, - "loss": 3.2323, + "learning_rate": 1.3447530802828756e-05, + "loss": 3.2059, "step": 220600 }, { "epoch": 0.73, - "learning_rate": 1.3490004830502307e-05, - "loss": 3.2232, + "learning_rate": 1.3430961233836387e-05, + "loss": 3.2033, "step": 220700 }, { "epoch": 0.73, - "learning_rate": 1.3473462014385632e-05, - "loss": 3.2379, + "learning_rate": 1.3414391664844014e-05, + "loss": 3.2032, "step": 220800 }, { "epoch": 0.73, - "learning_rate": 1.3456919198268961e-05, - "loss": 3.224, + "learning_rate": 1.3397822095851642e-05, + "loss": 3.1968, "step": 220900 }, { "epoch": 0.73, - "learning_rate": 1.3440376382152287e-05, - "loss": 3.2179, + "learning_rate": 1.3381252526859273e-05, + "loss": 3.1994, "step": 221000 }, { "epoch": 0.73, - "learning_rate": 1.3423833566035615e-05, - "loss": 3.2167, + "learning_rate": 1.33646829578669e-05, + "loss": 3.2166, "step": 221100 }, { "epoch": 0.73, - "learning_rate": 1.3407290749918942e-05, - "loss": 3.2261, + "learning_rate": 1.3348113388874528e-05, + "loss": 3.2152, "step": 221200 }, { "epoch": 0.73, - "learning_rate": 1.3390747933802266e-05, - "loss": 3.2298, + "learning_rate": 1.3331543819882159e-05, + "loss": 3.1944, "step": 221300 }, { "epoch": 0.73, - "learning_rate": 1.3374205117685596e-05, - "loss": 3.2209, + "learning_rate": 1.3314974250889786e-05, + "loss": 3.1912, "step": 221400 }, { "epoch": 0.73, - "learning_rate": 1.3357662301568922e-05, - "loss": 3.23, + "learning_rate": 1.3298404681897414e-05, + "loss": 3.2152, "step": 221500 }, { "epoch": 0.73, - "learning_rate": 1.3341119485452246e-05, - "loss": 3.2163, + "learning_rate": 1.3281835112905044e-05, + "loss": 3.2086, "step": 221600 }, { "epoch": 0.73, - "learning_rate": 1.3324576669335576e-05, - "loss": 3.2371, + "learning_rate": 1.3265265543912672e-05, + "loss": 3.2133, "step": 221700 }, { - "epoch": 0.73, - "learning_rate": 1.33080338532189e-05, - "loss": 3.2248, + "epoch": 0.74, + "learning_rate": 1.32486959749203e-05, + "loss": 3.2056, "step": 221800 }, { - "epoch": 0.73, - "learning_rate": 1.329149103710223e-05, - "loss": 3.2067, + "epoch": 0.74, + "learning_rate": 1.323212640592793e-05, + "loss": 3.2106, "step": 221900 }, { - "epoch": 0.73, - "learning_rate": 1.3274948220985556e-05, - "loss": 3.2273, + "epoch": 0.74, + "learning_rate": 1.3215556836935558e-05, + "loss": 3.2022, "step": 222000 }, { - "epoch": 0.73, - "learning_rate": 1.3258405404868881e-05, - "loss": 3.2296, + "epoch": 0.74, + "learning_rate": 1.3198987267943185e-05, + "loss": 3.2117, "step": 222100 }, { "epoch": 0.74, - "learning_rate": 1.324186258875221e-05, - "loss": 3.2314, + "learning_rate": 1.3182417698950816e-05, + "loss": 3.1989, "step": 222200 }, { "epoch": 0.74, - "learning_rate": 1.3225319772635537e-05, - "loss": 3.2147, + "learning_rate": 1.3165848129958444e-05, + "loss": 3.208, "step": 222300 }, { "epoch": 0.74, - "learning_rate": 1.3208776956518861e-05, - "loss": 3.2219, + "learning_rate": 1.3149278560966071e-05, + "loss": 3.1975, "step": 222400 }, { "epoch": 0.74, - "learning_rate": 1.3192234140402191e-05, - "loss": 3.2168, + "learning_rate": 1.3132708991973702e-05, + "loss": 3.1923, "step": 222500 }, { "epoch": 0.74, - "learning_rate": 1.3175691324285516e-05, - "loss": 3.2188, + "learning_rate": 1.311613942298133e-05, + "loss": 3.2061, "step": 222600 }, { "epoch": 0.74, - "learning_rate": 1.3159148508168842e-05, - "loss": 3.213, + "learning_rate": 1.3099569853988957e-05, + "loss": 3.2101, "step": 222700 }, { "epoch": 0.74, - "learning_rate": 1.3142605692052171e-05, - "loss": 3.2197, + "learning_rate": 1.3083000284996588e-05, + "loss": 3.2026, "step": 222800 }, { "epoch": 0.74, - "learning_rate": 1.3126062875935496e-05, - "loss": 3.2143, + "learning_rate": 1.3066430716004216e-05, + "loss": 3.2158, "step": 222900 }, { "epoch": 0.74, - "learning_rate": 1.3109520059818826e-05, - "loss": 3.215, + "learning_rate": 1.3049861147011843e-05, + "loss": 3.1983, "step": 223000 }, { "epoch": 0.74, - "learning_rate": 1.309297724370215e-05, - "loss": 3.2176, + "learning_rate": 1.3033291578019474e-05, + "loss": 3.2061, "step": 223100 }, { "epoch": 0.74, - "learning_rate": 1.3076434427585476e-05, - "loss": 3.2314, + "learning_rate": 1.3016722009027102e-05, + "loss": 3.2016, "step": 223200 }, { "epoch": 0.74, - "learning_rate": 1.3059891611468806e-05, - "loss": 3.233, + "learning_rate": 1.3000152440034729e-05, + "loss": 3.21, "step": 223300 }, { "epoch": 0.74, - "learning_rate": 1.304334879535213e-05, - "loss": 3.2213, + "learning_rate": 1.298358287104236e-05, + "loss": 3.2083, "step": 223400 }, { "epoch": 0.74, - "learning_rate": 1.3026805979235457e-05, - "loss": 3.2222, + "learning_rate": 1.2967013302049988e-05, + "loss": 3.2064, "step": 223500 }, { "epoch": 0.74, - "learning_rate": 1.3010263163118786e-05, - "loss": 3.2205, + "learning_rate": 1.2950443733057615e-05, + "loss": 3.2008, "step": 223600 }, { "epoch": 0.74, - "learning_rate": 1.299372034700211e-05, - "loss": 3.22, + "learning_rate": 1.2933874164065246e-05, + "loss": 3.1965, "step": 223700 }, { "epoch": 0.74, - "learning_rate": 1.2977177530885437e-05, - "loss": 3.2314, + "learning_rate": 1.2917304595072873e-05, + "loss": 3.206, "step": 223800 }, { "epoch": 0.74, - "learning_rate": 1.2960634714768765e-05, - "loss": 3.2242, + "learning_rate": 1.2900735026080501e-05, + "loss": 3.2057, "step": 223900 }, { "epoch": 0.74, - "learning_rate": 1.2944091898652091e-05, - "loss": 3.2299, + "learning_rate": 1.2884165457088132e-05, + "loss": 3.2018, "step": 224000 }, { "epoch": 0.74, - "learning_rate": 1.292754908253542e-05, - "loss": 3.2339, + "learning_rate": 1.286759588809576e-05, + "loss": 3.1939, "step": 224100 }, { "epoch": 0.74, - "learning_rate": 1.2911006266418745e-05, - "loss": 3.23, + "learning_rate": 1.2851026319103387e-05, + "loss": 3.2039, "step": 224200 }, { "epoch": 0.74, - "learning_rate": 1.2894463450302072e-05, - "loss": 3.2215, + "learning_rate": 1.2834456750111018e-05, + "loss": 3.2135, "step": 224300 }, { "epoch": 0.74, - "learning_rate": 1.28779206341854e-05, - "loss": 3.2294, + "learning_rate": 1.2817887181118645e-05, + "loss": 3.2111, "step": 224400 }, { "epoch": 0.74, - "learning_rate": 1.2861377818068726e-05, - "loss": 3.2321, + "learning_rate": 1.2801317612126273e-05, + "loss": 3.204, "step": 224500 }, { "epoch": 0.74, - "learning_rate": 1.2844835001952052e-05, - "loss": 3.2227, + "learning_rate": 1.2784748043133904e-05, + "loss": 3.2038, "step": 224600 }, { "epoch": 0.74, - "learning_rate": 1.282829218583538e-05, - "loss": 3.2287, + "learning_rate": 1.2768178474141531e-05, + "loss": 3.2013, "step": 224700 }, { "epoch": 0.74, - "learning_rate": 1.2811749369718706e-05, - "loss": 3.231, + "learning_rate": 1.2751608905149159e-05, + "loss": 3.2112, "step": 224800 }, { - "epoch": 0.74, - "learning_rate": 1.2795206553602032e-05, - "loss": 3.2334, + "epoch": 0.75, + "learning_rate": 1.2735039336156788e-05, + "loss": 3.195, "step": 224900 }, { - "epoch": 0.74, - "learning_rate": 1.277866373748536e-05, - "loss": 3.2392, + "epoch": 0.75, + "learning_rate": 1.2718469767164417e-05, + "loss": 3.2133, "step": 225000 }, { - "epoch": 0.74, - "learning_rate": 1.2762120921368686e-05, - "loss": 3.2337, + "epoch": 0.75, + "learning_rate": 1.2701900198172045e-05, + "loss": 3.1925, "step": 225100 }, { "epoch": 0.75, - "learning_rate": 1.2745578105252014e-05, - "loss": 3.2214, + "learning_rate": 1.2685330629179674e-05, + "loss": 3.206, "step": 225200 }, { "epoch": 0.75, - "learning_rate": 1.272903528913534e-05, - "loss": 3.2287, + "learning_rate": 1.2668761060187303e-05, + "loss": 3.2129, "step": 225300 }, { "epoch": 0.75, - "learning_rate": 1.2712492473018667e-05, - "loss": 3.2202, + "learning_rate": 1.265219149119493e-05, + "loss": 3.2173, "step": 225400 }, { "epoch": 0.75, - "learning_rate": 1.2695949656901995e-05, - "loss": 3.2234, + "learning_rate": 1.263562192220256e-05, + "loss": 3.2037, "step": 225500 }, { "epoch": 0.75, - "learning_rate": 1.2679406840785321e-05, - "loss": 3.236, + "learning_rate": 1.2619052353210189e-05, + "loss": 3.2033, "step": 225600 }, { "epoch": 0.75, - "learning_rate": 1.2662864024668647e-05, - "loss": 3.2189, + "learning_rate": 1.2602482784217816e-05, + "loss": 3.2127, "step": 225700 }, { "epoch": 0.75, - "learning_rate": 1.2646321208551975e-05, - "loss": 3.2014, + "learning_rate": 1.2585913215225446e-05, + "loss": 3.2027, "step": 225800 }, { "epoch": 0.75, - "learning_rate": 1.2629778392435301e-05, - "loss": 3.2467, + "learning_rate": 1.2569343646233075e-05, + "loss": 3.2037, "step": 225900 }, { "epoch": 0.75, - "learning_rate": 1.2613235576318628e-05, - "loss": 3.231, + "learning_rate": 1.2552774077240702e-05, + "loss": 3.2007, "step": 226000 }, { "epoch": 0.75, - "learning_rate": 1.2596692760201956e-05, - "loss": 3.2339, + "learning_rate": 1.2536204508248332e-05, + "loss": 3.2014, "step": 226100 }, { "epoch": 0.75, - "learning_rate": 1.2580149944085282e-05, - "loss": 3.2132, + "learning_rate": 1.251963493925596e-05, + "loss": 3.1889, "step": 226200 }, { "epoch": 0.75, - "learning_rate": 1.256360712796861e-05, - "loss": 3.2232, + "learning_rate": 1.2503065370263588e-05, + "loss": 3.2099, "step": 226300 }, { "epoch": 0.75, - "learning_rate": 1.2547064311851936e-05, - "loss": 3.2083, + "learning_rate": 1.2486495801271218e-05, + "loss": 3.2096, "step": 226400 }, { "epoch": 0.75, - "learning_rate": 1.2530521495735262e-05, - "loss": 3.2257, + "learning_rate": 1.2469926232278847e-05, + "loss": 3.2107, "step": 226500 }, { "epoch": 0.75, - "learning_rate": 1.251397867961859e-05, - "loss": 3.2228, + "learning_rate": 1.2453356663286474e-05, + "loss": 3.2204, "step": 226600 }, { "epoch": 0.75, - "learning_rate": 1.2497435863501916e-05, - "loss": 3.216, + "learning_rate": 1.2436787094294103e-05, + "loss": 3.2084, "step": 226700 }, { "epoch": 0.75, - "learning_rate": 1.2480893047385244e-05, - "loss": 3.229, + "learning_rate": 1.2420217525301733e-05, + "loss": 3.2124, "step": 226800 }, { "epoch": 0.75, - "learning_rate": 1.246435023126857e-05, - "loss": 3.2197, + "learning_rate": 1.2403647956309362e-05, + "loss": 3.194, "step": 226900 }, { "epoch": 0.75, - "learning_rate": 1.2447807415151897e-05, - "loss": 3.2022, + "learning_rate": 1.238707838731699e-05, + "loss": 3.2007, "step": 227000 }, { "epoch": 0.75, - "learning_rate": 1.2431264599035223e-05, - "loss": 3.2261, + "learning_rate": 1.2370508818324619e-05, + "loss": 3.2026, "step": 227100 }, { "epoch": 0.75, - "learning_rate": 1.241472178291855e-05, - "loss": 3.2306, + "learning_rate": 1.2353939249332248e-05, + "loss": 3.2027, "step": 227200 }, { "epoch": 0.75, - "learning_rate": 1.2398178966801877e-05, - "loss": 3.2291, + "learning_rate": 1.2337369680339875e-05, + "loss": 3.2051, "step": 227300 }, { "epoch": 0.75, - "learning_rate": 1.2381636150685203e-05, - "loss": 3.2243, + "learning_rate": 1.2320800111347505e-05, + "loss": 3.2089, "step": 227400 }, { "epoch": 0.75, - "learning_rate": 1.2365093334568531e-05, - "loss": 3.2242, + "learning_rate": 1.2304230542355134e-05, + "loss": 3.2059, "step": 227500 }, { "epoch": 0.75, - "learning_rate": 1.2348550518451857e-05, - "loss": 3.2226, + "learning_rate": 1.2287660973362761e-05, + "loss": 3.2139, "step": 227600 }, { "epoch": 0.75, - "learning_rate": 1.2332007702335184e-05, - "loss": 3.2229, + "learning_rate": 1.227109140437039e-05, + "loss": 3.2041, "step": 227700 }, { "epoch": 0.75, - "learning_rate": 1.2315464886218512e-05, - "loss": 3.2123, + "learning_rate": 1.225452183537802e-05, + "loss": 3.1896, "step": 227800 }, { - "epoch": 0.75, - "learning_rate": 1.2298922070101838e-05, - "loss": 3.2171, + "epoch": 0.76, + "learning_rate": 1.2237952266385649e-05, + "loss": 3.1921, "step": 227900 }, { - "epoch": 0.75, - "learning_rate": 1.2282379253985166e-05, - "loss": 3.2277, + "epoch": 0.76, + "learning_rate": 1.2221382697393276e-05, + "loss": 3.1886, "step": 228000 }, { - "epoch": 0.75, - "learning_rate": 1.2265836437868492e-05, - "loss": 3.2214, + "epoch": 0.76, + "learning_rate": 1.2204813128400906e-05, + "loss": 3.2056, "step": 228100 }, { "epoch": 0.76, - "learning_rate": 1.2249293621751818e-05, - "loss": 3.2311, + "learning_rate": 1.2188243559408533e-05, + "loss": 3.2103, "step": 228200 }, { "epoch": 0.76, - "learning_rate": 1.2232750805635146e-05, - "loss": 3.2288, + "learning_rate": 1.2171673990416162e-05, + "loss": 3.2052, "step": 228300 }, { "epoch": 0.76, - "learning_rate": 1.2216207989518472e-05, - "loss": 3.2256, + "learning_rate": 1.2155104421423791e-05, + "loss": 3.1899, "step": 228400 }, { "epoch": 0.76, - "learning_rate": 1.2199665173401799e-05, - "loss": 3.2279, + "learning_rate": 1.2138534852431419e-05, + "loss": 3.19, "step": 228500 }, { "epoch": 0.76, - "learning_rate": 1.2183122357285127e-05, - "loss": 3.2084, + "learning_rate": 1.2121965283439048e-05, + "loss": 3.2068, "step": 228600 }, { "epoch": 0.76, - "learning_rate": 1.2166579541168453e-05, - "loss": 3.2236, + "learning_rate": 1.2105395714446677e-05, + "loss": 3.2082, "step": 228700 }, { "epoch": 0.76, - "learning_rate": 1.2150036725051779e-05, - "loss": 3.2173, + "learning_rate": 1.2088826145454305e-05, + "loss": 3.1911, "step": 228800 }, { "epoch": 0.76, - "learning_rate": 1.2133493908935107e-05, - "loss": 3.2402, + "learning_rate": 1.2072256576461934e-05, + "loss": 3.1928, "step": 228900 }, { "epoch": 0.76, - "learning_rate": 1.2116951092818433e-05, - "loss": 3.2264, + "learning_rate": 1.2055687007469563e-05, + "loss": 3.1964, "step": 229000 }, { "epoch": 0.76, - "learning_rate": 1.2100408276701761e-05, - "loss": 3.2104, + "learning_rate": 1.203911743847719e-05, + "loss": 3.1941, "step": 229100 }, { "epoch": 0.76, - "learning_rate": 1.2083865460585087e-05, - "loss": 3.2274, + "learning_rate": 1.202254786948482e-05, + "loss": 3.2056, "step": 229200 }, { "epoch": 0.76, - "learning_rate": 1.2067322644468413e-05, - "loss": 3.224, + "learning_rate": 1.200597830049245e-05, + "loss": 3.1963, "step": 229300 }, { "epoch": 0.76, - "learning_rate": 1.2050779828351741e-05, - "loss": 3.2091, + "learning_rate": 1.1989408731500077e-05, + "loss": 3.1977, "step": 229400 }, { "epoch": 0.76, - "learning_rate": 1.2034237012235066e-05, - "loss": 3.2274, + "learning_rate": 1.1972839162507706e-05, + "loss": 3.2055, "step": 229500 }, { "epoch": 0.76, - "learning_rate": 1.2017694196118394e-05, - "loss": 3.227, + "learning_rate": 1.1956269593515335e-05, + "loss": 3.208, "step": 229600 }, { "epoch": 0.76, - "learning_rate": 1.2001151380001722e-05, - "loss": 3.2294, + "learning_rate": 1.1939700024522963e-05, + "loss": 3.1937, "step": 229700 }, { "epoch": 0.76, - "learning_rate": 1.1984608563885048e-05, - "loss": 3.228, + "learning_rate": 1.1923130455530592e-05, + "loss": 3.2012, "step": 229800 }, { "epoch": 0.76, - "learning_rate": 1.1968065747768374e-05, - "loss": 3.2269, + "learning_rate": 1.1906560886538221e-05, + "loss": 3.2016, "step": 229900 }, { "epoch": 0.76, - "learning_rate": 1.1951522931651702e-05, - "loss": 3.2256, + "learning_rate": 1.1889991317545849e-05, + "loss": 3.1975, "step": 230000 }, { "epoch": 0.76, - "learning_rate": 1.1934980115535028e-05, - "loss": 3.213, + "learning_rate": 1.1873421748553478e-05, + "loss": 3.2078, "step": 230100 }, { "epoch": 0.76, - "learning_rate": 1.1918437299418356e-05, - "loss": 3.2329, + "learning_rate": 1.1856852179561107e-05, + "loss": 3.1885, "step": 230200 }, { "epoch": 0.76, - "learning_rate": 1.1901894483301681e-05, - "loss": 3.231, + "learning_rate": 1.1840282610568735e-05, + "loss": 3.2109, "step": 230300 }, { "epoch": 0.76, - "learning_rate": 1.1885351667185009e-05, - "loss": 3.2333, + "learning_rate": 1.1823713041576364e-05, + "loss": 3.2004, "step": 230400 }, { "epoch": 0.76, - "learning_rate": 1.1868808851068337e-05, - "loss": 3.217, + "learning_rate": 1.1807143472583991e-05, + "loss": 3.1954, "step": 230500 }, { "epoch": 0.76, - "learning_rate": 1.1852266034951661e-05, - "loss": 3.22, + "learning_rate": 1.179057390359162e-05, + "loss": 3.2114, "step": 230600 }, { "epoch": 0.76, - "learning_rate": 1.183572321883499e-05, - "loss": 3.2179, + "learning_rate": 1.177400433459925e-05, + "loss": 3.2114, "step": 230700 }, { "epoch": 0.76, - "learning_rate": 1.1819180402718315e-05, - "loss": 3.221, + "learning_rate": 1.1757434765606877e-05, + "loss": 3.2104, "step": 230800 }, { - "epoch": 0.76, - "learning_rate": 1.1802637586601643e-05, - "loss": 3.2246, + "epoch": 0.77, + "learning_rate": 1.1740865196614506e-05, + "loss": 3.2037, "step": 230900 }, { - "epoch": 0.76, - "learning_rate": 1.178609477048497e-05, - "loss": 3.2326, + "epoch": 0.77, + "learning_rate": 1.1724295627622136e-05, + "loss": 3.1939, "step": 231000 }, { - "epoch": 0.76, - "learning_rate": 1.1769551954368296e-05, - "loss": 3.2094, + "epoch": 0.77, + "learning_rate": 1.1707726058629763e-05, + "loss": 3.1934, "step": 231100 }, { - "epoch": 0.76, - "learning_rate": 1.1753009138251624e-05, - "loss": 3.2129, + "epoch": 0.77, + "learning_rate": 1.1691156489637392e-05, + "loss": 3.2031, "step": 231200 }, { "epoch": 0.77, - "learning_rate": 1.1736466322134952e-05, - "loss": 3.229, + "learning_rate": 1.1674586920645022e-05, + "loss": 3.1987, "step": 231300 }, { "epoch": 0.77, - "learning_rate": 1.1719923506018276e-05, - "loss": 3.2283, + "learning_rate": 1.1658017351652649e-05, + "loss": 3.2036, "step": 231400 }, { "epoch": 0.77, - "learning_rate": 1.1703380689901604e-05, - "loss": 3.2207, + "learning_rate": 1.1641447782660278e-05, + "loss": 3.2034, "step": 231500 }, { "epoch": 0.77, - "learning_rate": 1.168683787378493e-05, - "loss": 3.2489, + "learning_rate": 1.1624878213667907e-05, + "loss": 3.1989, "step": 231600 }, { "epoch": 0.77, - "learning_rate": 1.1670295057668258e-05, - "loss": 3.2253, + "learning_rate": 1.1608308644675535e-05, + "loss": 3.2002, "step": 231700 }, { "epoch": 0.77, - "learning_rate": 1.1653752241551584e-05, - "loss": 3.2299, + "learning_rate": 1.1591739075683164e-05, + "loss": 3.2198, "step": 231800 }, { "epoch": 0.77, - "learning_rate": 1.163720942543491e-05, - "loss": 3.2038, + "learning_rate": 1.1575169506690793e-05, + "loss": 3.1994, "step": 231900 }, { "epoch": 0.77, - "learning_rate": 1.1620666609318239e-05, - "loss": 3.2242, + "learning_rate": 1.1558599937698421e-05, + "loss": 3.1982, "step": 232000 }, { "epoch": 0.77, - "learning_rate": 1.1604123793201565e-05, - "loss": 3.2254, + "learning_rate": 1.154203036870605e-05, + "loss": 3.1939, "step": 232100 }, { "epoch": 0.77, - "learning_rate": 1.1587580977084891e-05, - "loss": 3.2248, + "learning_rate": 1.152546079971368e-05, + "loss": 3.2011, "step": 232200 }, { "epoch": 0.77, - "learning_rate": 1.1571038160968219e-05, - "loss": 3.2163, + "learning_rate": 1.1508891230721307e-05, + "loss": 3.2023, "step": 232300 }, { "epoch": 0.77, - "learning_rate": 1.1554495344851545e-05, - "loss": 3.2423, + "learning_rate": 1.1492321661728936e-05, + "loss": 3.1956, "step": 232400 }, { "epoch": 0.77, - "learning_rate": 1.1537952528734871e-05, - "loss": 3.2317, + "learning_rate": 1.1475752092736563e-05, + "loss": 3.1954, "step": 232500 }, { "epoch": 0.77, - "learning_rate": 1.15214097126182e-05, - "loss": 3.2249, + "learning_rate": 1.1459182523744193e-05, + "loss": 3.2009, "step": 232600 }, { "epoch": 0.77, - "learning_rate": 1.1504866896501526e-05, - "loss": 3.2198, + "learning_rate": 1.1442612954751822e-05, + "loss": 3.2081, "step": 232700 }, { "epoch": 0.77, - "learning_rate": 1.1488324080384854e-05, - "loss": 3.2232, + "learning_rate": 1.142604338575945e-05, + "loss": 3.202, "step": 232800 }, { "epoch": 0.77, - "learning_rate": 1.147178126426818e-05, - "loss": 3.2176, + "learning_rate": 1.1409473816767079e-05, + "loss": 3.1957, "step": 232900 }, { "epoch": 0.77, - "learning_rate": 1.1455238448151506e-05, - "loss": 3.2313, + "learning_rate": 1.1392904247774708e-05, + "loss": 3.1923, "step": 233000 }, { "epoch": 0.77, - "learning_rate": 1.1438695632034834e-05, - "loss": 3.2256, + "learning_rate": 1.1376334678782335e-05, + "loss": 3.1985, "step": 233100 }, { "epoch": 0.77, - "learning_rate": 1.1422152815918158e-05, - "loss": 3.2252, + "learning_rate": 1.1359765109789965e-05, + "loss": 3.1888, "step": 233200 }, { "epoch": 0.77, - "learning_rate": 1.1405609999801486e-05, - "loss": 3.2195, + "learning_rate": 1.1343195540797594e-05, + "loss": 3.2072, "step": 233300 }, { "epoch": 0.77, - "learning_rate": 1.1389067183684814e-05, - "loss": 3.2287, + "learning_rate": 1.1326625971805221e-05, + "loss": 3.198, "step": 233400 }, { "epoch": 0.77, - "learning_rate": 1.137252436756814e-05, - "loss": 3.2274, + "learning_rate": 1.131005640281285e-05, + "loss": 3.2095, "step": 233500 }, { "epoch": 0.77, - "learning_rate": 1.1355981551451467e-05, - "loss": 3.2185, + "learning_rate": 1.129348683382048e-05, + "loss": 3.211, "step": 233600 }, { "epoch": 0.77, - "learning_rate": 1.1339438735334795e-05, - "loss": 3.2278, + "learning_rate": 1.1276917264828107e-05, + "loss": 3.1971, "step": 233700 }, { "epoch": 0.77, - "learning_rate": 1.1322895919218121e-05, - "loss": 3.2185, + "learning_rate": 1.1260347695835736e-05, + "loss": 3.2054, "step": 233800 }, { - "epoch": 0.77, - "learning_rate": 1.1306353103101449e-05, - "loss": 3.2237, + "epoch": 0.78, + "learning_rate": 1.1243778126843366e-05, + "loss": 3.2044, "step": 233900 }, { - "epoch": 0.77, - "learning_rate": 1.1289810286984773e-05, - "loss": 3.221, + "epoch": 0.78, + "learning_rate": 1.1227208557850993e-05, + "loss": 3.1993, "step": 234000 }, { - "epoch": 0.77, - "learning_rate": 1.1273267470868101e-05, - "loss": 3.2152, + "epoch": 0.78, + "learning_rate": 1.1210638988858622e-05, + "loss": 3.2091, "step": 234100 }, { - "epoch": 0.77, - "learning_rate": 1.125672465475143e-05, - "loss": 3.23, + "epoch": 0.78, + "learning_rate": 1.1194069419866252e-05, + "loss": 3.2097, "step": 234200 }, { "epoch": 0.78, - "learning_rate": 1.1240181838634754e-05, - "loss": 3.2167, + "learning_rate": 1.1177499850873879e-05, + "loss": 3.2031, "step": 234300 }, { "epoch": 0.78, - "learning_rate": 1.1223639022518082e-05, - "loss": 3.219, + "learning_rate": 1.1160930281881508e-05, + "loss": 3.1867, "step": 234400 }, { "epoch": 0.78, - "learning_rate": 1.1207096206401408e-05, - "loss": 3.2259, + "learning_rate": 1.1144360712889137e-05, + "loss": 3.203, "step": 234500 }, { "epoch": 0.78, - "learning_rate": 1.1190553390284736e-05, - "loss": 3.2177, + "learning_rate": 1.1127791143896765e-05, + "loss": 3.2104, "step": 234600 }, { "epoch": 0.78, - "learning_rate": 1.1174010574168062e-05, - "loss": 3.2199, + "learning_rate": 1.1111221574904394e-05, + "loss": 3.1894, "step": 234700 }, { "epoch": 0.78, - "learning_rate": 1.1157467758051388e-05, - "loss": 3.2249, + "learning_rate": 1.1094652005912022e-05, + "loss": 3.2143, "step": 234800 }, { "epoch": 0.78, - "learning_rate": 1.1140924941934716e-05, - "loss": 3.2231, + "learning_rate": 1.1078082436919651e-05, + "loss": 3.2056, "step": 234900 }, { "epoch": 0.78, - "learning_rate": 1.1124382125818044e-05, - "loss": 3.2161, + "learning_rate": 1.106151286792728e-05, + "loss": 3.2047, "step": 235000 }, { "epoch": 0.78, - "learning_rate": 1.1107839309701369e-05, - "loss": 3.223, + "learning_rate": 1.1044943298934908e-05, + "loss": 3.1941, "step": 235100 }, { "epoch": 0.78, - "learning_rate": 1.1091296493584697e-05, - "loss": 3.2142, + "learning_rate": 1.1028373729942537e-05, + "loss": 3.202, "step": 235200 }, { "epoch": 0.78, - "learning_rate": 1.1074753677468023e-05, - "loss": 3.2126, + "learning_rate": 1.1011804160950166e-05, + "loss": 3.2181, "step": 235300 }, { "epoch": 0.78, - "learning_rate": 1.105821086135135e-05, - "loss": 3.2136, + "learning_rate": 1.0995234591957794e-05, + "loss": 3.2038, "step": 235400 }, { "epoch": 0.78, - "learning_rate": 1.1041668045234677e-05, - "loss": 3.2069, + "learning_rate": 1.0978665022965423e-05, + "loss": 3.1839, "step": 235500 }, { "epoch": 0.78, - "learning_rate": 1.1025125229118003e-05, - "loss": 3.2034, + "learning_rate": 1.0962095453973052e-05, + "loss": 3.1914, "step": 235600 }, { "epoch": 0.78, - "learning_rate": 1.1008582413001331e-05, - "loss": 3.2187, + "learning_rate": 1.094552588498068e-05, + "loss": 3.202, "step": 235700 }, { "epoch": 0.78, - "learning_rate": 1.0992039596884657e-05, - "loss": 3.2117, + "learning_rate": 1.0928956315988309e-05, + "loss": 3.2015, "step": 235800 }, { "epoch": 0.78, - "learning_rate": 1.0975496780767984e-05, - "loss": 3.2301, + "learning_rate": 1.0912386746995938e-05, + "loss": 3.2038, "step": 235900 }, { "epoch": 0.78, - "learning_rate": 1.0958953964651311e-05, - "loss": 3.2285, + "learning_rate": 1.0895817178003565e-05, + "loss": 3.2038, "step": 236000 }, { "epoch": 0.78, - "learning_rate": 1.0942411148534638e-05, - "loss": 3.2254, + "learning_rate": 1.0879247609011195e-05, + "loss": 3.1973, "step": 236100 }, { "epoch": 0.78, - "learning_rate": 1.0925868332417964e-05, - "loss": 3.2316, + "learning_rate": 1.0862678040018824e-05, + "loss": 3.2014, "step": 236200 }, { "epoch": 0.78, - "learning_rate": 1.0909325516301292e-05, - "loss": 3.2238, + "learning_rate": 1.0846108471026451e-05, + "loss": 3.1948, "step": 236300 }, { "epoch": 0.78, - "learning_rate": 1.0892782700184618e-05, - "loss": 3.2149, + "learning_rate": 1.082953890203408e-05, + "loss": 3.2121, "step": 236400 }, { "epoch": 0.78, - "learning_rate": 1.0876239884067946e-05, - "loss": 3.216, + "learning_rate": 1.081296933304171e-05, + "loss": 3.1987, "step": 236500 }, { "epoch": 0.78, - "learning_rate": 1.0859697067951272e-05, - "loss": 3.2164, + "learning_rate": 1.0796399764049337e-05, + "loss": 3.2045, "step": 236600 }, { "epoch": 0.78, - "learning_rate": 1.0843154251834598e-05, - "loss": 3.2226, + "learning_rate": 1.0779830195056966e-05, + "loss": 3.1962, "step": 236700 }, { "epoch": 0.78, - "learning_rate": 1.0826611435717926e-05, - "loss": 3.2252, + "learning_rate": 1.0763260626064596e-05, + "loss": 3.2013, "step": 236800 }, { - "epoch": 0.78, - "learning_rate": 1.0810068619601253e-05, - "loss": 3.2375, + "epoch": 0.79, + "learning_rate": 1.0746691057072223e-05, + "loss": 3.2051, "step": 236900 }, { - "epoch": 0.78, - "learning_rate": 1.0793525803484579e-05, - "loss": 3.2314, + "epoch": 0.79, + "learning_rate": 1.0730121488079852e-05, + "loss": 3.2003, "step": 237000 }, { - "epoch": 0.78, - "learning_rate": 1.0776982987367907e-05, - "loss": 3.2316, + "epoch": 0.79, + "learning_rate": 1.071355191908748e-05, + "loss": 3.2019, "step": 237100 }, { - "epoch": 0.78, - "learning_rate": 1.0760440171251233e-05, - "loss": 3.2203, + "epoch": 0.79, + "learning_rate": 1.0696982350095109e-05, + "loss": 3.2067, "step": 237200 }, { "epoch": 0.79, - "learning_rate": 1.074389735513456e-05, - "loss": 3.2212, + "learning_rate": 1.0680412781102738e-05, + "loss": 3.2017, "step": 237300 }, { "epoch": 0.79, - "learning_rate": 1.0727354539017887e-05, - "loss": 3.2242, + "learning_rate": 1.0663843212110366e-05, + "loss": 3.2005, "step": 237400 }, { "epoch": 0.79, - "learning_rate": 1.0710811722901213e-05, - "loss": 3.2361, + "learning_rate": 1.0647273643117995e-05, + "loss": 3.2052, "step": 237500 }, { "epoch": 0.79, - "learning_rate": 1.0694268906784541e-05, - "loss": 3.2217, + "learning_rate": 1.0630704074125624e-05, + "loss": 3.2038, "step": 237600 }, { "epoch": 0.79, - "learning_rate": 1.0677726090667866e-05, - "loss": 3.2175, + "learning_rate": 1.0614134505133252e-05, + "loss": 3.2004, "step": 237700 }, { "epoch": 0.79, - "learning_rate": 1.0661183274551194e-05, - "loss": 3.2224, + "learning_rate": 1.0597564936140881e-05, + "loss": 3.1898, "step": 237800 }, { "epoch": 0.79, - "learning_rate": 1.0644640458434522e-05, - "loss": 3.2317, + "learning_rate": 1.058099536714851e-05, + "loss": 3.2144, "step": 237900 }, { "epoch": 0.79, - "learning_rate": 1.0628097642317846e-05, - "loss": 3.2147, + "learning_rate": 1.0564425798156138e-05, + "loss": 3.2156, "step": 238000 }, { "epoch": 0.79, - "learning_rate": 1.0611554826201174e-05, - "loss": 3.2249, + "learning_rate": 1.0547856229163767e-05, + "loss": 3.1812, "step": 238100 }, { "epoch": 0.79, - "learning_rate": 1.0595012010084502e-05, - "loss": 3.2261, + "learning_rate": 1.0531286660171396e-05, + "loss": 3.1975, "step": 238200 }, { "epoch": 0.79, - "learning_rate": 1.0578469193967828e-05, - "loss": 3.2294, + "learning_rate": 1.0514717091179024e-05, + "loss": 3.1936, "step": 238300 }, { "epoch": 0.79, - "learning_rate": 1.0561926377851155e-05, - "loss": 3.2178, + "learning_rate": 1.0498147522186653e-05, + "loss": 3.1991, "step": 238400 }, { "epoch": 0.79, - "learning_rate": 1.054538356173448e-05, - "loss": 3.228, + "learning_rate": 1.0481577953194282e-05, + "loss": 3.2074, "step": 238500 }, { "epoch": 0.79, - "learning_rate": 1.0528840745617809e-05, - "loss": 3.2237, + "learning_rate": 1.0465008384201911e-05, + "loss": 3.1967, "step": 238600 }, { "epoch": 0.79, - "learning_rate": 1.0512297929501137e-05, - "loss": 3.2282, + "learning_rate": 1.0448438815209539e-05, + "loss": 3.1987, "step": 238700 }, { "epoch": 0.79, - "learning_rate": 1.0495755113384461e-05, - "loss": 3.2142, + "learning_rate": 1.0431869246217168e-05, + "loss": 3.2024, "step": 238800 }, { "epoch": 0.79, - "learning_rate": 1.0479212297267789e-05, - "loss": 3.2121, + "learning_rate": 1.0415299677224797e-05, + "loss": 3.2069, "step": 238900 }, { "epoch": 0.79, - "learning_rate": 1.0462669481151115e-05, - "loss": 3.2224, + "learning_rate": 1.0398730108232425e-05, + "loss": 3.2106, "step": 239000 }, { "epoch": 0.79, - "learning_rate": 1.0446126665034443e-05, - "loss": 3.2293, + "learning_rate": 1.0382160539240054e-05, + "loss": 3.2127, "step": 239100 }, { "epoch": 0.79, - "learning_rate": 1.042958384891777e-05, - "loss": 3.223, + "learning_rate": 1.0365590970247683e-05, + "loss": 3.2007, "step": 239200 }, { "epoch": 0.79, - "learning_rate": 1.0413041032801096e-05, - "loss": 3.2256, + "learning_rate": 1.034902140125531e-05, + "loss": 3.1959, "step": 239300 }, { "epoch": 0.79, - "learning_rate": 1.0396498216684424e-05, - "loss": 3.2416, + "learning_rate": 1.033245183226294e-05, + "loss": 3.181, "step": 239400 }, { "epoch": 0.79, - "learning_rate": 1.037995540056775e-05, - "loss": 3.2155, + "learning_rate": 1.0315882263270569e-05, + "loss": 3.2124, "step": 239500 }, { "epoch": 0.79, - "learning_rate": 1.0363412584451076e-05, - "loss": 3.2162, + "learning_rate": 1.0299312694278198e-05, + "loss": 3.2178, "step": 239600 }, { "epoch": 0.79, - "learning_rate": 1.0346869768334404e-05, - "loss": 3.2125, + "learning_rate": 1.0282743125285826e-05, + "loss": 3.202, "step": 239700 }, { "epoch": 0.79, - "learning_rate": 1.033032695221773e-05, - "loss": 3.2126, + "learning_rate": 1.0266173556293455e-05, + "loss": 3.1981, "step": 239800 }, { - "epoch": 0.79, - "learning_rate": 1.0313784136101056e-05, - "loss": 3.2255, + "epoch": 0.8, + "learning_rate": 1.0249603987301084e-05, + "loss": 3.2119, "step": 239900 }, { - "epoch": 0.79, - "learning_rate": 1.0297241319984384e-05, - "loss": 3.2178, + "epoch": 0.8, + "learning_rate": 1.0233034418308712e-05, + "loss": 3.1918, "step": 240000 }, { - "epoch": 0.79, - "learning_rate": 1.028069850386771e-05, - "loss": 3.2192, + "epoch": 0.8, + "learning_rate": 1.021646484931634e-05, + "loss": 3.1887, "step": 240100 }, { - "epoch": 0.79, - "learning_rate": 1.0264155687751038e-05, + "epoch": 0.8, + "learning_rate": 1.019989528032397e-05, "loss": 3.2138, "step": 240200 }, { "epoch": 0.8, - "learning_rate": 1.0247612871634365e-05, - "loss": 3.2154, + "learning_rate": 1.0183325711331597e-05, + "loss": 3.1969, "step": 240300 }, { "epoch": 0.8, - "learning_rate": 1.0231070055517691e-05, - "loss": 3.2144, + "learning_rate": 1.0166756142339227e-05, + "loss": 3.2009, "step": 240400 }, { "epoch": 0.8, - "learning_rate": 1.0214527239401019e-05, - "loss": 3.2252, + "learning_rate": 1.0150186573346856e-05, + "loss": 3.2071, "step": 240500 }, { "epoch": 0.8, - "learning_rate": 1.0197984423284345e-05, - "loss": 3.2331, + "learning_rate": 1.0133617004354483e-05, + "loss": 3.2043, "step": 240600 }, { "epoch": 0.8, - "learning_rate": 1.0181441607167671e-05, - "loss": 3.236, + "learning_rate": 1.0117047435362113e-05, + "loss": 3.1884, "step": 240700 }, { "epoch": 0.8, - "learning_rate": 1.0164898791051e-05, - "loss": 3.2265, + "learning_rate": 1.0100477866369742e-05, + "loss": 3.1934, "step": 240800 }, { "epoch": 0.8, - "learning_rate": 1.0148355974934325e-05, - "loss": 3.2162, + "learning_rate": 1.008390829737737e-05, + "loss": 3.2103, "step": 240900 }, { "epoch": 0.8, - "learning_rate": 1.0131813158817652e-05, - "loss": 3.2271, + "learning_rate": 1.0067338728384999e-05, + "loss": 3.1946, "step": 241000 }, { "epoch": 0.8, - "learning_rate": 1.011527034270098e-05, - "loss": 3.221, + "learning_rate": 1.0050769159392628e-05, + "loss": 3.195, "step": 241100 }, { "epoch": 0.8, - "learning_rate": 1.0098727526584306e-05, - "loss": 3.2314, + "learning_rate": 1.0034199590400255e-05, + "loss": 3.198, "step": 241200 }, { "epoch": 0.8, - "learning_rate": 1.0082184710467634e-05, - "loss": 3.2172, + "learning_rate": 1.0017630021407884e-05, + "loss": 3.2096, "step": 241300 }, { "epoch": 0.8, - "learning_rate": 1.006564189435096e-05, - "loss": 3.2033, + "learning_rate": 1.0001060452415512e-05, + "loss": 3.2068, "step": 241400 }, { "epoch": 0.8, - "learning_rate": 1.0049099078234286e-05, - "loss": 3.2219, + "learning_rate": 9.984490883423141e-06, + "loss": 3.194, "step": 241500 }, { "epoch": 0.8, - "learning_rate": 1.0032556262117614e-05, - "loss": 3.2107, + "learning_rate": 9.96792131443077e-06, + "loss": 3.1972, "step": 241600 }, { "epoch": 0.8, - "learning_rate": 1.0016013446000939e-05, - "loss": 3.2272, + "learning_rate": 9.951351745438398e-06, + "loss": 3.2035, "step": 241700 }, { "epoch": 0.8, - "learning_rate": 9.999470629884267e-06, - "loss": 3.2188, + "learning_rate": 9.934782176446027e-06, + "loss": 3.2039, "step": 241800 }, { "epoch": 0.8, - "learning_rate": 9.982927813767595e-06, - "loss": 3.2327, + "learning_rate": 9.918212607453656e-06, + "loss": 3.2024, "step": 241900 }, { "epoch": 0.8, - "learning_rate": 9.96638499765092e-06, - "loss": 3.2225, + "learning_rate": 9.901643038461284e-06, + "loss": 3.199, "step": 242000 }, { "epoch": 0.8, - "learning_rate": 9.949842181534247e-06, - "loss": 3.2252, + "learning_rate": 9.885073469468913e-06, + "loss": 3.2126, "step": 242100 }, { "epoch": 0.8, - "learning_rate": 9.933299365417573e-06, - "loss": 3.2331, + "learning_rate": 9.868503900476542e-06, + "loss": 3.1901, "step": 242200 }, { "epoch": 0.8, - "learning_rate": 9.916756549300901e-06, - "loss": 3.2099, + "learning_rate": 9.85193433148417e-06, + "loss": 3.1887, "step": 242300 }, { "epoch": 0.8, - "learning_rate": 9.900213733184229e-06, - "loss": 3.2063, + "learning_rate": 9.835364762491799e-06, + "loss": 3.194, "step": 242400 }, { "epoch": 0.8, - "learning_rate": 9.883670917067554e-06, - "loss": 3.2239, + "learning_rate": 9.818795193499428e-06, + "loss": 3.2044, "step": 242500 }, { "epoch": 0.8, - "learning_rate": 9.867128100950882e-06, - "loss": 3.2276, + "learning_rate": 9.802225624507056e-06, + "loss": 3.1921, "step": 242600 }, { "epoch": 0.8, - "learning_rate": 9.85058528483421e-06, - "loss": 3.2067, + "learning_rate": 9.785656055514685e-06, + "loss": 3.1993, "step": 242700 }, { "epoch": 0.8, - "learning_rate": 9.834042468717536e-06, - "loss": 3.2311, + "learning_rate": 9.769086486522314e-06, + "loss": 3.2003, "step": 242800 }, { "epoch": 0.8, - "learning_rate": 9.817499652600862e-06, - "loss": 3.2166, + "learning_rate": 9.752516917529942e-06, + "loss": 3.2048, "step": 242900 }, { - "epoch": 0.8, - "learning_rate": 9.800956836484188e-06, - "loss": 3.2267, + "epoch": 0.81, + "learning_rate": 9.73594734853757e-06, + "loss": 3.1987, "step": 243000 }, { - "epoch": 0.8, - "learning_rate": 9.784414020367516e-06, - "loss": 3.2151, + "epoch": 0.81, + "learning_rate": 9.7193777795452e-06, + "loss": 3.1816, "step": 243100 }, { - "epoch": 0.8, - "learning_rate": 9.767871204250842e-06, - "loss": 3.2389, + "epoch": 0.81, + "learning_rate": 9.702808210552828e-06, + "loss": 3.199, "step": 243200 }, { - "epoch": 0.8, - "learning_rate": 9.751328388134169e-06, - "loss": 3.2212, + "epoch": 0.81, + "learning_rate": 9.686238641560457e-06, + "loss": 3.1944, "step": 243300 }, { "epoch": 0.81, - "learning_rate": 9.734785572017496e-06, - "loss": 3.2187, + "learning_rate": 9.669669072568084e-06, + "loss": 3.2134, "step": 243400 }, { "epoch": 0.81, - "learning_rate": 9.718242755900823e-06, - "loss": 3.2265, + "learning_rate": 9.653099503575713e-06, + "loss": 3.1945, "step": 243500 }, { "epoch": 0.81, - "learning_rate": 9.701699939784149e-06, - "loss": 3.2133, + "learning_rate": 9.636529934583343e-06, + "loss": 3.1955, "step": 243600 }, { "epoch": 0.81, - "learning_rate": 9.685157123667477e-06, - "loss": 3.2243, + "learning_rate": 9.61996036559097e-06, + "loss": 3.2001, "step": 243700 }, { "epoch": 0.81, - "learning_rate": 9.668614307550803e-06, - "loss": 3.2045, + "learning_rate": 9.6033907965986e-06, + "loss": 3.2, "step": 243800 }, { "epoch": 0.81, - "learning_rate": 9.652071491434131e-06, - "loss": 3.2233, + "learning_rate": 9.586821227606229e-06, + "loss": 3.2009, "step": 243900 }, { "epoch": 0.81, - "learning_rate": 9.635528675317457e-06, - "loss": 3.2073, + "learning_rate": 9.570251658613856e-06, + "loss": 3.202, "step": 244000 }, { "epoch": 0.81, - "learning_rate": 9.618985859200783e-06, - "loss": 3.2173, + "learning_rate": 9.553682089621485e-06, + "loss": 3.1903, "step": 244100 }, { "epoch": 0.81, - "learning_rate": 9.602443043084111e-06, - "loss": 3.2233, + "learning_rate": 9.537112520629114e-06, + "loss": 3.205, "step": 244200 }, { "epoch": 0.81, - "learning_rate": 9.585900226967438e-06, - "loss": 3.2304, + "learning_rate": 9.520542951636742e-06, + "loss": 3.193, "step": 244300 }, { "epoch": 0.81, - "learning_rate": 9.569357410850764e-06, - "loss": 3.213, + "learning_rate": 9.503973382644371e-06, + "loss": 3.1997, "step": 244400 }, { "epoch": 0.81, - "learning_rate": 9.552814594734092e-06, - "loss": 3.2104, + "learning_rate": 9.487403813652e-06, + "loss": 3.1954, "step": 244500 }, { "epoch": 0.81, - "learning_rate": 9.536271778617418e-06, - "loss": 3.215, + "learning_rate": 9.470834244659628e-06, + "loss": 3.2054, "step": 244600 }, { "epoch": 0.81, - "learning_rate": 9.519728962500744e-06, - "loss": 3.2168, + "learning_rate": 9.454264675667257e-06, + "loss": 3.2179, "step": 244700 }, { "epoch": 0.81, - "learning_rate": 9.503186146384072e-06, - "loss": 3.2142, + "learning_rate": 9.437695106674886e-06, + "loss": 3.1996, "step": 244800 }, { "epoch": 0.81, - "learning_rate": 9.486643330267398e-06, - "loss": 3.2159, + "learning_rate": 9.421125537682514e-06, + "loss": 3.1986, "step": 244900 }, { "epoch": 0.81, - "learning_rate": 9.470100514150726e-06, - "loss": 3.2112, + "learning_rate": 9.404555968690143e-06, + "loss": 3.2045, "step": 245000 }, { "epoch": 0.81, - "learning_rate": 9.453557698034052e-06, - "loss": 3.2136, + "learning_rate": 9.387986399697772e-06, + "loss": 3.2094, "step": 245100 }, { "epoch": 0.81, - "learning_rate": 9.437014881917379e-06, - "loss": 3.2208, + "learning_rate": 9.3714168307054e-06, + "loss": 3.189, "step": 245200 }, { "epoch": 0.81, - "learning_rate": 9.420472065800707e-06, - "loss": 3.2191, + "learning_rate": 9.354847261713029e-06, + "loss": 3.1997, "step": 245300 }, { "epoch": 0.81, - "learning_rate": 9.403929249684031e-06, - "loss": 3.2225, + "learning_rate": 9.338277692720658e-06, + "loss": 3.208, "step": 245400 }, { "epoch": 0.81, - "learning_rate": 9.387386433567359e-06, - "loss": 3.2305, + "learning_rate": 9.321708123728286e-06, + "loss": 3.2134, "step": 245500 }, { "epoch": 0.81, - "learning_rate": 9.370843617450687e-06, - "loss": 3.2402, + "learning_rate": 9.305138554735915e-06, + "loss": 3.2009, "step": 245600 }, { "epoch": 0.81, - "learning_rate": 9.354300801334013e-06, - "loss": 3.2247, + "learning_rate": 9.288568985743542e-06, + "loss": 3.1935, "step": 245700 }, { "epoch": 0.81, - "learning_rate": 9.33775798521734e-06, - "loss": 3.2249, + "learning_rate": 9.271999416751172e-06, + "loss": 3.198, "step": 245800 }, { "epoch": 0.81, - "learning_rate": 9.321215169100667e-06, - "loss": 3.2293, + "learning_rate": 9.2554298477588e-06, + "loss": 3.2074, "step": 245900 }, { - "epoch": 0.81, - "learning_rate": 9.304672352983994e-06, - "loss": 3.2142, + "epoch": 0.82, + "learning_rate": 9.238860278766428e-06, + "loss": 3.2067, "step": 246000 }, { - "epoch": 0.81, - "learning_rate": 9.288129536867322e-06, - "loss": 3.23, + "epoch": 0.82, + "learning_rate": 9.222290709774058e-06, + "loss": 3.2029, "step": 246100 }, { - "epoch": 0.81, - "learning_rate": 9.271586720750646e-06, - "loss": 3.2142, + "epoch": 0.82, + "learning_rate": 9.205721140781687e-06, + "loss": 3.1951, "step": 246200 }, { - "epoch": 0.81, - "learning_rate": 9.255043904633974e-06, - "loss": 3.2255, + "epoch": 0.82, + "learning_rate": 9.189151571789314e-06, + "loss": 3.1994, "step": 246300 }, { "epoch": 0.82, - "learning_rate": 9.238501088517302e-06, - "loss": 3.2204, + "learning_rate": 9.172582002796943e-06, + "loss": 3.2009, "step": 246400 }, { "epoch": 0.82, - "learning_rate": 9.221958272400628e-06, - "loss": 3.22, + "learning_rate": 9.156012433804573e-06, + "loss": 3.2079, "step": 246500 }, { "epoch": 0.82, - "learning_rate": 9.205415456283954e-06, - "loss": 3.2341, + "learning_rate": 9.1394428648122e-06, + "loss": 3.2066, "step": 246600 }, { "epoch": 0.82, - "learning_rate": 9.18887264016728e-06, - "loss": 3.2416, + "learning_rate": 9.12287329581983e-06, + "loss": 3.2019, "step": 246700 }, { "epoch": 0.82, - "learning_rate": 9.172329824050609e-06, - "loss": 3.2219, + "learning_rate": 9.106303726827459e-06, + "loss": 3.2203, "step": 246800 }, { "epoch": 0.82, - "learning_rate": 9.155787007933935e-06, - "loss": 3.2225, + "learning_rate": 9.089734157835086e-06, + "loss": 3.2037, "step": 246900 }, { "epoch": 0.82, - "learning_rate": 9.139244191817261e-06, - "loss": 3.2175, + "learning_rate": 9.073164588842715e-06, + "loss": 3.209, "step": 247000 }, { "epoch": 0.82, - "learning_rate": 9.122701375700589e-06, - "loss": 3.2151, + "learning_rate": 9.056595019850344e-06, + "loss": 3.2121, "step": 247100 }, { "epoch": 0.82, - "learning_rate": 9.106158559583917e-06, - "loss": 3.2106, + "learning_rate": 9.040025450857972e-06, + "loss": 3.2017, "step": 247200 }, { "epoch": 0.82, - "learning_rate": 9.089615743467241e-06, - "loss": 3.2113, + "learning_rate": 9.023455881865601e-06, + "loss": 3.2235, "step": 247300 }, { "epoch": 0.82, - "learning_rate": 9.07307292735057e-06, - "loss": 3.2067, + "learning_rate": 9.00688631287323e-06, + "loss": 3.2089, "step": 247400 }, { "epoch": 0.82, - "learning_rate": 9.056530111233896e-06, - "loss": 3.2171, + "learning_rate": 8.990316743880858e-06, + "loss": 3.1986, "step": 247500 }, { "epoch": 0.82, - "learning_rate": 9.039987295117223e-06, - "loss": 3.218, + "learning_rate": 8.973747174888487e-06, + "loss": 3.2099, "step": 247600 }, { "epoch": 0.82, - "learning_rate": 9.02344447900055e-06, - "loss": 3.2266, + "learning_rate": 8.957177605896116e-06, + "loss": 3.1863, "step": 247700 }, { "epoch": 0.82, - "learning_rate": 9.006901662883876e-06, - "loss": 3.219, + "learning_rate": 8.940608036903744e-06, + "loss": 3.2018, "step": 247800 }, { "epoch": 0.82, - "learning_rate": 8.990358846767204e-06, - "loss": 3.2154, + "learning_rate": 8.924038467911373e-06, + "loss": 3.201, "step": 247900 }, { "epoch": 0.82, - "learning_rate": 8.97381603065053e-06, - "loss": 3.2089, + "learning_rate": 8.907468898919e-06, + "loss": 3.1937, "step": 248000 }, { "epoch": 0.82, - "learning_rate": 8.957273214533856e-06, - "loss": 3.2259, + "learning_rate": 8.89089932992663e-06, + "loss": 3.1958, "step": 248100 }, { "epoch": 0.82, - "learning_rate": 8.940730398417184e-06, - "loss": 3.2254, + "learning_rate": 8.874329760934259e-06, + "loss": 3.1989, "step": 248200 }, { "epoch": 0.82, - "learning_rate": 8.92418758230051e-06, - "loss": 3.2102, + "learning_rate": 8.857760191941886e-06, + "loss": 3.2101, "step": 248300 }, { "epoch": 0.82, - "learning_rate": 8.907644766183837e-06, - "loss": 3.2187, + "learning_rate": 8.841190622949516e-06, + "loss": 3.1967, "step": 248400 }, { "epoch": 0.82, - "learning_rate": 8.891101950067165e-06, - "loss": 3.2163, + "learning_rate": 8.824621053957145e-06, + "loss": 3.201, "step": 248500 }, { "epoch": 0.82, - "learning_rate": 8.87455913395049e-06, - "loss": 3.218, + "learning_rate": 8.808051484964772e-06, + "loss": 3.2023, "step": 248600 }, { "epoch": 0.82, - "learning_rate": 8.858016317833819e-06, - "loss": 3.2241, + "learning_rate": 8.791481915972402e-06, + "loss": 3.2087, "step": 248700 }, { "epoch": 0.82, - "learning_rate": 8.841473501717145e-06, - "loss": 3.2193, + "learning_rate": 8.77491234698003e-06, + "loss": 3.1992, "step": 248800 }, { "epoch": 0.82, - "learning_rate": 8.824930685600471e-06, - "loss": 3.231, + "learning_rate": 8.758342777987658e-06, + "loss": 3.1887, "step": 248900 }, { - "epoch": 0.82, - "learning_rate": 8.808387869483799e-06, - "loss": 3.2135, + "epoch": 0.83, + "learning_rate": 8.741773208995288e-06, + "loss": 3.1964, "step": 249000 }, { - "epoch": 0.82, - "learning_rate": 8.791845053367125e-06, - "loss": 3.2221, + "epoch": 0.83, + "learning_rate": 8.725203640002917e-06, + "loss": 3.2034, "step": 249100 }, { - "epoch": 0.82, - "learning_rate": 8.775302237250452e-06, - "loss": 3.2015, + "epoch": 0.83, + "learning_rate": 8.708634071010544e-06, + "loss": 3.1985, "step": 249200 }, { - "epoch": 0.82, - "learning_rate": 8.75875942113378e-06, - "loss": 3.2196, + "epoch": 0.83, + "learning_rate": 8.692064502018173e-06, + "loss": 3.2018, "step": 249300 }, { "epoch": 0.83, - "learning_rate": 8.742216605017106e-06, - "loss": 3.2229, + "learning_rate": 8.675494933025803e-06, + "loss": 3.2133, "step": 249400 }, { "epoch": 0.83, - "learning_rate": 8.725673788900432e-06, - "loss": 3.2164, + "learning_rate": 8.65892536403343e-06, + "loss": 3.1963, "step": 249500 }, { "epoch": 0.83, - "learning_rate": 8.70913097278376e-06, - "loss": 3.2257, + "learning_rate": 8.64235579504106e-06, + "loss": 3.1949, "step": 249600 }, { "epoch": 0.83, - "learning_rate": 8.692588156667086e-06, - "loss": 3.2164, + "learning_rate": 8.625786226048689e-06, + "loss": 3.2099, "step": 249700 }, { "epoch": 0.83, - "learning_rate": 8.676045340550414e-06, - "loss": 3.215, + "learning_rate": 8.609216657056316e-06, + "loss": 3.2079, "step": 249800 }, { "epoch": 0.83, - "learning_rate": 8.659502524433739e-06, - "loss": 3.205, + "learning_rate": 8.592647088063945e-06, + "loss": 3.1977, "step": 249900 }, { "epoch": 0.83, - "learning_rate": 8.642959708317066e-06, - "loss": 3.2089, + "learning_rate": 8.576077519071573e-06, + "loss": 3.1937, "step": 250000 }, { "epoch": 0.83, - "learning_rate": 8.626416892200394e-06, - "loss": 3.2043, + "learning_rate": 8.559507950079202e-06, + "loss": 3.2079, "step": 250100 }, { "epoch": 0.83, - "learning_rate": 8.60987407608372e-06, - "loss": 3.2072, + "learning_rate": 8.542938381086831e-06, + "loss": 3.2087, "step": 250200 }, { "epoch": 0.83, - "learning_rate": 8.593331259967047e-06, - "loss": 3.2192, + "learning_rate": 8.52636881209446e-06, + "loss": 3.1957, "step": 250300 }, { "epoch": 0.83, - "learning_rate": 8.576788443850375e-06, - "loss": 3.2194, + "learning_rate": 8.509799243102088e-06, + "loss": 3.2, "step": 250400 }, { "epoch": 0.83, - "learning_rate": 8.560245627733701e-06, - "loss": 3.2241, + "learning_rate": 8.493229674109717e-06, + "loss": 3.1944, "step": 250500 }, { "epoch": 0.83, - "learning_rate": 8.543702811617027e-06, - "loss": 3.2131, + "learning_rate": 8.476660105117346e-06, + "loss": 3.1983, "step": 250600 }, { "epoch": 0.83, - "learning_rate": 8.527159995500353e-06, - "loss": 3.2192, + "learning_rate": 8.460090536124974e-06, + "loss": 3.2095, "step": 250700 }, { "epoch": 0.83, - "learning_rate": 8.510617179383681e-06, - "loss": 3.215, + "learning_rate": 8.443520967132603e-06, + "loss": 3.1867, "step": 250800 }, { "epoch": 0.83, - "learning_rate": 8.49407436326701e-06, - "loss": 3.228, + "learning_rate": 8.426951398140232e-06, + "loss": 3.1876, "step": 250900 }, { "epoch": 0.83, - "learning_rate": 8.477531547150334e-06, - "loss": 3.2162, + "learning_rate": 8.41038182914786e-06, + "loss": 3.1878, "step": 251000 }, { "epoch": 0.83, - "learning_rate": 8.460988731033662e-06, - "loss": 3.2225, + "learning_rate": 8.393812260155489e-06, + "loss": 3.204, "step": 251100 }, { "epoch": 0.83, - "learning_rate": 8.444445914916988e-06, - "loss": 3.2252, + "learning_rate": 8.377242691163118e-06, + "loss": 3.1925, "step": 251200 }, { "epoch": 0.83, - "learning_rate": 8.427903098800316e-06, - "loss": 3.2164, + "learning_rate": 8.360673122170746e-06, + "loss": 3.1958, "step": 251300 }, { "epoch": 0.83, - "learning_rate": 8.411360282683642e-06, - "loss": 3.2267, + "learning_rate": 8.344103553178375e-06, + "loss": 3.1978, "step": 251400 }, { "epoch": 0.83, - "learning_rate": 8.394817466566968e-06, - "loss": 3.2188, + "learning_rate": 8.327533984186004e-06, + "loss": 3.1858, "step": 251500 }, { "epoch": 0.83, - "learning_rate": 8.378274650450296e-06, - "loss": 3.2228, + "learning_rate": 8.310964415193633e-06, + "loss": 3.2066, "step": 251600 }, { "epoch": 0.83, - "learning_rate": 8.361731834333623e-06, - "loss": 3.2283, + "learning_rate": 8.29439484620126e-06, + "loss": 3.2071, "step": 251700 }, { "epoch": 0.83, - "learning_rate": 8.345189018216949e-06, - "loss": 3.2204, + "learning_rate": 8.27782527720889e-06, + "loss": 3.1957, "step": 251800 }, { "epoch": 0.83, - "learning_rate": 8.328646202100277e-06, - "loss": 3.2194, + "learning_rate": 8.26125570821652e-06, + "loss": 3.1972, "step": 251900 }, { - "epoch": 0.83, - "learning_rate": 8.312103385983603e-06, - "loss": 3.2219, + "epoch": 0.84, + "learning_rate": 8.244686139224147e-06, + "loss": 3.1925, "step": 252000 }, { - "epoch": 0.83, - "learning_rate": 8.29556056986693e-06, - "loss": 3.2085, + "epoch": 0.84, + "learning_rate": 8.228116570231776e-06, + "loss": 3.1924, "step": 252100 }, { - "epoch": 0.83, - "learning_rate": 8.279017753750257e-06, - "loss": 3.2133, + "epoch": 0.84, + "learning_rate": 8.211547001239405e-06, + "loss": 3.196, "step": 252200 }, { - "epoch": 0.83, - "learning_rate": 8.262474937633583e-06, - "loss": 3.2244, + "epoch": 0.84, + "learning_rate": 8.194977432247033e-06, + "loss": 3.1984, "step": 252300 }, { "epoch": 0.84, - "learning_rate": 8.245932121516911e-06, - "loss": 3.2245, + "learning_rate": 8.178407863254662e-06, + "loss": 3.1963, "step": 252400 }, { "epoch": 0.84, - "learning_rate": 8.229389305400237e-06, - "loss": 3.2169, + "learning_rate": 8.161838294262291e-06, + "loss": 3.1956, "step": 252500 }, { "epoch": 0.84, - "learning_rate": 8.212846489283564e-06, - "loss": 3.2202, + "learning_rate": 8.145268725269919e-06, + "loss": 3.2056, "step": 252600 }, { "epoch": 0.84, - "learning_rate": 8.196303673166892e-06, - "loss": 3.213, + "learning_rate": 8.128699156277548e-06, + "loss": 3.204, "step": 252700 }, { "epoch": 0.84, - "learning_rate": 8.179760857050218e-06, - "loss": 3.2145, + "learning_rate": 8.112129587285177e-06, + "loss": 3.1987, "step": 252800 }, { "epoch": 0.84, - "learning_rate": 8.163218040933544e-06, - "loss": 3.233, + "learning_rate": 8.095560018292805e-06, + "loss": 3.206, "step": 252900 }, { "epoch": 0.84, - "learning_rate": 8.146675224816872e-06, - "loss": 3.2078, + "learning_rate": 8.078990449300434e-06, + "loss": 3.21, "step": 253000 }, { "epoch": 0.84, - "learning_rate": 8.130132408700198e-06, - "loss": 3.205, + "learning_rate": 8.062420880308063e-06, + "loss": 3.1935, "step": 253100 }, { "epoch": 0.84, - "learning_rate": 8.113589592583524e-06, - "loss": 3.2204, + "learning_rate": 8.04585131131569e-06, + "loss": 3.2134, "step": 253200 }, { "epoch": 0.84, - "learning_rate": 8.097046776466852e-06, - "loss": 3.223, + "learning_rate": 8.02928174232332e-06, + "loss": 3.2063, "step": 253300 }, { "epoch": 0.84, - "learning_rate": 8.080503960350179e-06, - "loss": 3.2109, + "learning_rate": 8.012712173330949e-06, + "loss": 3.2013, "step": 253400 }, { "epoch": 0.84, - "learning_rate": 8.063961144233507e-06, - "loss": 3.2133, + "learning_rate": 7.996142604338576e-06, + "loss": 3.2077, "step": 253500 }, { "epoch": 0.84, - "learning_rate": 8.047418328116833e-06, - "loss": 3.2281, + "learning_rate": 7.979573035346206e-06, + "loss": 3.206, "step": 253600 }, { "epoch": 0.84, - "learning_rate": 8.030875512000159e-06, - "loss": 3.2132, + "learning_rate": 7.963003466353835e-06, + "loss": 3.1939, "step": 253700 }, { "epoch": 0.84, - "learning_rate": 8.014332695883487e-06, - "loss": 3.223, + "learning_rate": 7.946433897361462e-06, + "loss": 3.191, "step": 253800 }, { "epoch": 0.84, - "learning_rate": 7.997789879766811e-06, - "loss": 3.2231, + "learning_rate": 7.929864328369092e-06, + "loss": 3.1991, "step": 253900 }, { "epoch": 0.84, - "learning_rate": 7.98124706365014e-06, - "loss": 3.2159, + "learning_rate": 7.91329475937672e-06, + "loss": 3.2004, "step": 254000 }, { "epoch": 0.84, - "learning_rate": 7.964704247533467e-06, - "loss": 3.2223, + "learning_rate": 7.896725190384348e-06, + "loss": 3.1892, "step": 254100 }, { "epoch": 0.84, - "learning_rate": 7.948161431416794e-06, - "loss": 3.2098, + "learning_rate": 7.880155621391977e-06, + "loss": 3.1907, "step": 254200 }, { "epoch": 0.84, - "learning_rate": 7.93161861530012e-06, - "loss": 3.2113, + "learning_rate": 7.863586052399607e-06, + "loss": 3.2009, "step": 254300 }, { "epoch": 0.84, - "learning_rate": 7.915075799183446e-06, - "loss": 3.2099, + "learning_rate": 7.847016483407234e-06, + "loss": 3.1993, "step": 254400 }, { "epoch": 0.84, - "learning_rate": 7.898532983066774e-06, - "loss": 3.2104, + "learning_rate": 7.830446914414863e-06, + "loss": 3.2089, "step": 254500 }, { "epoch": 0.84, - "learning_rate": 7.881990166950102e-06, - "loss": 3.2137, + "learning_rate": 7.813877345422491e-06, + "loss": 3.1968, "step": 254600 }, { "epoch": 0.84, - "learning_rate": 7.865447350833426e-06, - "loss": 3.217, + "learning_rate": 7.79730777643012e-06, + "loss": 3.2019, "step": 254700 }, { "epoch": 0.84, - "learning_rate": 7.848904534716754e-06, - "loss": 3.2263, + "learning_rate": 7.78073820743775e-06, + "loss": 3.2021, "step": 254800 }, { "epoch": 0.84, - "learning_rate": 7.832361718600082e-06, - "loss": 3.2169, + "learning_rate": 7.764168638445377e-06, + "loss": 3.2017, "step": 254900 }, { - "epoch": 0.84, - "learning_rate": 7.815818902483408e-06, - "loss": 3.2145, + "epoch": 0.85, + "learning_rate": 7.747599069453006e-06, + "loss": 3.2069, "step": 255000 }, { - "epoch": 0.84, - "learning_rate": 7.799276086366735e-06, - "loss": 3.2145, + "epoch": 0.85, + "learning_rate": 7.731029500460635e-06, + "loss": 3.2048, "step": 255100 }, { - "epoch": 0.84, - "learning_rate": 7.782733270250061e-06, - "loss": 3.2234, + "epoch": 0.85, + "learning_rate": 7.714459931468263e-06, + "loss": 3.2125, "step": 255200 }, { - "epoch": 0.84, - "learning_rate": 7.766190454133389e-06, - "loss": 3.2194, + "epoch": 0.85, + "learning_rate": 7.697890362475892e-06, + "loss": 3.2086, "step": 255300 }, { "epoch": 0.85, - "learning_rate": 7.749647638016715e-06, - "loss": 3.2206, + "learning_rate": 7.681320793483521e-06, + "loss": 3.2043, "step": 255400 }, { "epoch": 0.85, - "learning_rate": 7.733104821900041e-06, - "loss": 3.2108, + "learning_rate": 7.664751224491149e-06, + "loss": 3.1995, "step": 255500 }, { "epoch": 0.85, - "learning_rate": 7.71656200578337e-06, - "loss": 3.2199, + "learning_rate": 7.648181655498778e-06, + "loss": 3.2046, "step": 255600 }, { "epoch": 0.85, - "learning_rate": 7.700019189666695e-06, - "loss": 3.2261, + "learning_rate": 7.631612086506407e-06, + "loss": 3.2028, "step": 255700 }, { "epoch": 0.85, - "learning_rate": 7.683476373550022e-06, - "loss": 3.2189, + "learning_rate": 7.6150425175140345e-06, + "loss": 3.2075, "step": 255800 }, { "epoch": 0.85, - "learning_rate": 7.66693355743335e-06, - "loss": 3.2146, + "learning_rate": 7.598472948521664e-06, + "loss": 3.1995, "step": 255900 }, { "epoch": 0.85, - "learning_rate": 7.650390741316676e-06, - "loss": 3.2167, + "learning_rate": 7.581903379529293e-06, + "loss": 3.211, "step": 256000 }, { "epoch": 0.85, - "learning_rate": 7.633847925200004e-06, - "loss": 3.2153, + "learning_rate": 7.5653338105369205e-06, + "loss": 3.1842, "step": 256100 }, { "epoch": 0.85, - "learning_rate": 7.617305109083329e-06, - "loss": 3.2149, + "learning_rate": 7.54876424154455e-06, + "loss": 3.1958, "step": 256200 }, { "epoch": 0.85, - "learning_rate": 7.600762292966657e-06, - "loss": 3.224, + "learning_rate": 7.532194672552179e-06, + "loss": 3.2064, "step": 256300 }, { "epoch": 0.85, - "learning_rate": 7.584219476849984e-06, - "loss": 3.2284, + "learning_rate": 7.515625103559806e-06, + "loss": 3.1934, "step": 256400 }, { "epoch": 0.85, - "learning_rate": 7.5676766607333095e-06, - "loss": 3.2244, + "learning_rate": 7.499055534567436e-06, + "loss": 3.1988, "step": 256500 }, { "epoch": 0.85, - "learning_rate": 7.5511338446166366e-06, - "loss": 3.2194, + "learning_rate": 7.482485965575063e-06, + "loss": 3.2002, "step": 256600 }, { "epoch": 0.85, - "learning_rate": 7.5345910284999645e-06, - "loss": 3.2141, + "learning_rate": 7.465916396582692e-06, + "loss": 3.2069, "step": 256700 }, { "epoch": 0.85, - "learning_rate": 7.5180482123832916e-06, - "loss": 3.2233, + "learning_rate": 7.4493468275903215e-06, + "loss": 3.1969, "step": 256800 }, { "epoch": 0.85, - "learning_rate": 7.501505396266617e-06, - "loss": 3.2097, + "learning_rate": 7.432777258597949e-06, + "loss": 3.2161, "step": 256900 }, { "epoch": 0.85, - "learning_rate": 7.484962580149944e-06, - "loss": 3.2061, + "learning_rate": 7.416207689605578e-06, + "loss": 3.1883, "step": 257000 }, { "epoch": 0.85, - "learning_rate": 7.468419764033271e-06, - "loss": 3.2181, + "learning_rate": 7.3996381206132074e-06, + "loss": 3.1967, "step": 257100 }, { "epoch": 0.85, - "learning_rate": 7.451876947916599e-06, - "loss": 3.2228, + "learning_rate": 7.383068551620835e-06, + "loss": 3.1958, "step": 257200 }, { "epoch": 0.85, - "learning_rate": 7.435334131799924e-06, - "loss": 3.2272, + "learning_rate": 7.366498982628464e-06, + "loss": 3.2047, "step": 257300 }, { "epoch": 0.85, - "learning_rate": 7.4187913156832515e-06, - "loss": 3.235, + "learning_rate": 7.349929413636093e-06, + "loss": 3.2122, "step": 257400 }, { "epoch": 0.85, - "learning_rate": 7.4022484995665785e-06, - "loss": 3.2288, + "learning_rate": 7.333359844643721e-06, + "loss": 3.1884, "step": 257500 }, { "epoch": 0.85, - "learning_rate": 7.385705683449905e-06, - "loss": 3.2106, + "learning_rate": 7.31679027565135e-06, + "loss": 3.198, "step": 257600 }, { "epoch": 0.85, - "learning_rate": 7.369162867333232e-06, - "loss": 3.2053, + "learning_rate": 7.300220706658979e-06, + "loss": 3.1932, "step": 257700 }, { "epoch": 0.85, - "learning_rate": 7.352620051216559e-06, - "loss": 3.215, + "learning_rate": 7.283651137666607e-06, + "loss": 3.1862, "step": 257800 }, { "epoch": 0.85, - "learning_rate": 7.336077235099886e-06, - "loss": 3.2134, + "learning_rate": 7.267081568674236e-06, + "loss": 3.211, "step": 257900 }, { "epoch": 0.85, - "learning_rate": 7.319534418983212e-06, - "loss": 3.2145, + "learning_rate": 7.250511999681865e-06, + "loss": 3.2244, "step": 258000 }, { - "epoch": 0.85, - "learning_rate": 7.302991602866539e-06, - "loss": 3.2059, + "epoch": 0.86, + "learning_rate": 7.233942430689493e-06, + "loss": 3.1907, "step": 258100 }, { - "epoch": 0.85, - "learning_rate": 7.286448786749866e-06, - "loss": 3.2141, + "epoch": 0.86, + "learning_rate": 7.217372861697122e-06, + "loss": 3.2034, "step": 258200 }, { - "epoch": 0.85, - "learning_rate": 7.2699059706331935e-06, - "loss": 3.2285, + "epoch": 0.86, + "learning_rate": 7.200803292704751e-06, + "loss": 3.1948, "step": 258300 }, { - "epoch": 0.85, - "learning_rate": 7.25336315451652e-06, - "loss": 3.2386, + "epoch": 0.86, + "learning_rate": 7.184233723712379e-06, + "loss": 3.2051, "step": 258400 }, { "epoch": 0.86, - "learning_rate": 7.236820338399847e-06, - "loss": 3.2227, + "learning_rate": 7.167664154720008e-06, + "loss": 3.2098, "step": 258500 }, { "epoch": 0.86, - "learning_rate": 7.220277522283174e-06, - "loss": 3.2176, + "learning_rate": 7.151094585727637e-06, + "loss": 3.1924, "step": 258600 }, { "epoch": 0.86, - "learning_rate": 7.203734706166501e-06, - "loss": 3.218, + "learning_rate": 7.1345250167352646e-06, + "loss": 3.2036, "step": 258700 }, { "epoch": 0.86, - "learning_rate": 7.187191890049827e-06, - "loss": 3.2293, + "learning_rate": 7.117955447742894e-06, + "loss": 3.187, "step": 258800 }, { "epoch": 0.86, - "learning_rate": 7.170649073933154e-06, - "loss": 3.2278, + "learning_rate": 7.101385878750521e-06, + "loss": 3.1963, "step": 258900 }, { "epoch": 0.86, - "learning_rate": 7.154106257816481e-06, - "loss": 3.2057, + "learning_rate": 7.0848163097581505e-06, + "loss": 3.198, "step": 259000 }, { "epoch": 0.86, - "learning_rate": 7.1375634416998075e-06, - "loss": 3.2027, + "learning_rate": 7.06824674076578e-06, + "loss": 3.2008, "step": 259100 }, { "epoch": 0.86, - "learning_rate": 7.121020625583135e-06, - "loss": 3.2224, + "learning_rate": 7.051677171773407e-06, + "loss": 3.1906, "step": 259200 }, { "epoch": 0.86, - "learning_rate": 7.104477809466462e-06, - "loss": 3.2053, + "learning_rate": 7.035107602781036e-06, + "loss": 3.1933, "step": 259300 }, { "epoch": 0.86, - "learning_rate": 7.087934993349789e-06, - "loss": 3.2237, + "learning_rate": 7.018538033788666e-06, + "loss": 3.187, "step": 259400 }, { "epoch": 0.86, - "learning_rate": 7.071392177233115e-06, - "loss": 3.2155, + "learning_rate": 7.001968464796293e-06, + "loss": 3.2086, "step": 259500 }, { "epoch": 0.86, - "learning_rate": 7.054849361116442e-06, - "loss": 3.2046, + "learning_rate": 6.985398895803922e-06, + "loss": 3.1764, "step": 259600 }, { "epoch": 0.86, - "learning_rate": 7.038306544999769e-06, - "loss": 3.2, + "learning_rate": 6.9688293268115515e-06, + "loss": 3.2072, "step": 259700 }, { "epoch": 0.86, - "learning_rate": 7.021763728883096e-06, - "loss": 3.2218, + "learning_rate": 6.95225975781918e-06, + "loss": 3.1944, "step": 259800 }, { "epoch": 0.86, - "learning_rate": 7.0052209127664224e-06, - "loss": 3.2195, + "learning_rate": 6.935690188826808e-06, + "loss": 3.2033, "step": 259900 }, { "epoch": 0.86, - "learning_rate": 6.9886780966497495e-06, - "loss": 3.2079, + "learning_rate": 6.9191206198344375e-06, + "loss": 3.1849, "step": 260000 }, { "epoch": 0.86, - "learning_rate": 6.972135280533077e-06, - "loss": 3.206, + "learning_rate": 6.902551050842066e-06, + "loss": 3.2032, "step": 260100 }, { "epoch": 0.86, - "learning_rate": 6.955592464416402e-06, - "loss": 3.2265, + "learning_rate": 6.885981481849694e-06, + "loss": 3.1968, "step": 260200 }, { "epoch": 0.86, - "learning_rate": 6.939049648299729e-06, - "loss": 3.2202, + "learning_rate": 6.869411912857323e-06, + "loss": 3.1946, "step": 260300 }, { "epoch": 0.86, - "learning_rate": 6.922506832183057e-06, - "loss": 3.2185, + "learning_rate": 6.852842343864952e-06, + "loss": 3.2021, "step": 260400 }, { "epoch": 0.86, - "learning_rate": 6.905964016066384e-06, - "loss": 3.2105, + "learning_rate": 6.83627277487258e-06, + "loss": 3.1977, "step": 260500 }, { "epoch": 0.86, - "learning_rate": 6.889421199949709e-06, - "loss": 3.2258, + "learning_rate": 6.819703205880209e-06, + "loss": 3.1991, "step": 260600 }, { "epoch": 0.86, - "learning_rate": 6.8728783838330365e-06, - "loss": 3.2235, + "learning_rate": 6.803133636887838e-06, + "loss": 3.188, "step": 260700 }, { "epoch": 0.86, - "learning_rate": 6.856335567716364e-06, - "loss": 3.2096, + "learning_rate": 6.786564067895466e-06, + "loss": 3.1872, "step": 260800 }, { "epoch": 0.86, - "learning_rate": 6.8397927515996915e-06, - "loss": 3.2049, + "learning_rate": 6.769994498903094e-06, + "loss": 3.2008, "step": 260900 }, { "epoch": 0.86, - "learning_rate": 6.823249935483017e-06, - "loss": 3.2196, + "learning_rate": 6.753424929910724e-06, + "loss": 3.2057, "step": 261000 }, { - "epoch": 0.86, - "learning_rate": 6.806707119366344e-06, - "loss": 3.229, + "epoch": 0.87, + "learning_rate": 6.736855360918353e-06, + "loss": 3.1991, "step": 261100 }, { - "epoch": 0.86, - "learning_rate": 6.790164303249672e-06, - "loss": 3.2036, + "epoch": 0.87, + "learning_rate": 6.72028579192598e-06, + "loss": 3.204, "step": 261200 }, { - "epoch": 0.86, - "learning_rate": 6.773621487132997e-06, - "loss": 3.2263, + "epoch": 0.87, + "learning_rate": 6.7037162229336095e-06, + "loss": 3.2068, "step": 261300 }, { - "epoch": 0.86, - "learning_rate": 6.757078671016324e-06, - "loss": 3.2097, + "epoch": 0.87, + "learning_rate": 6.687146653941239e-06, + "loss": 3.1978, "step": 261400 }, { "epoch": 0.87, - "learning_rate": 6.740535854899651e-06, - "loss": 3.2201, + "learning_rate": 6.670577084948866e-06, + "loss": 3.2118, "step": 261500 }, { "epoch": 0.87, - "learning_rate": 6.7239930387829785e-06, - "loss": 3.2176, + "learning_rate": 6.6540075159564954e-06, + "loss": 3.2004, "step": 261600 }, { "epoch": 0.87, - "learning_rate": 6.707450222666305e-06, - "loss": 3.2269, + "learning_rate": 6.637437946964125e-06, + "loss": 3.2003, "step": 261700 }, { "epoch": 0.87, - "learning_rate": 6.690907406549632e-06, - "loss": 3.2038, + "learning_rate": 6.620868377971752e-06, + "loss": 3.1993, "step": 261800 }, { "epoch": 0.87, - "learning_rate": 6.674364590432959e-06, - "loss": 3.1985, + "learning_rate": 6.604298808979381e-06, + "loss": 3.1891, "step": 261900 }, { "epoch": 0.87, - "learning_rate": 6.657821774316286e-06, - "loss": 3.2328, + "learning_rate": 6.5877292399870106e-06, + "loss": 3.205, "step": 262000 }, { "epoch": 0.87, - "learning_rate": 6.641278958199612e-06, - "loss": 3.2153, + "learning_rate": 6.571159670994638e-06, + "loss": 3.1891, "step": 262100 }, { "epoch": 0.87, - "learning_rate": 6.624736142082939e-06, - "loss": 3.2044, + "learning_rate": 6.554590102002267e-06, + "loss": 3.2069, "step": 262200 }, { "epoch": 0.87, - "learning_rate": 6.608193325966266e-06, - "loss": 3.2121, + "learning_rate": 6.5380205330098965e-06, + "loss": 3.1997, "step": 262300 }, { "epoch": 0.87, - "learning_rate": 6.591650509849593e-06, - "loss": 3.2118, + "learning_rate": 6.521450964017524e-06, + "loss": 3.1968, "step": 262400 }, { "epoch": 0.87, - "learning_rate": 6.57510769373292e-06, - "loss": 3.2136, + "learning_rate": 6.504881395025153e-06, + "loss": 3.2007, "step": 262500 }, { "epoch": 0.87, - "learning_rate": 6.558564877616247e-06, - "loss": 3.2199, + "learning_rate": 6.488311826032782e-06, + "loss": 3.2007, "step": 262600 }, { "epoch": 0.87, - "learning_rate": 6.542022061499574e-06, - "loss": 3.233, + "learning_rate": 6.47174225704041e-06, + "loss": 3.1845, "step": 262700 }, { "epoch": 0.87, - "learning_rate": 6.5254792453829e-06, - "loss": 3.2242, + "learning_rate": 6.455172688048039e-06, + "loss": 3.2023, "step": 262800 }, { "epoch": 0.87, - "learning_rate": 6.508936429266227e-06, - "loss": 3.1949, + "learning_rate": 6.438603119055668e-06, + "loss": 3.2095, "step": 262900 }, { "epoch": 0.87, - "learning_rate": 6.492393613149554e-06, - "loss": 3.2118, + "learning_rate": 6.422033550063296e-06, + "loss": 3.2095, "step": 263000 }, { "epoch": 0.87, - "learning_rate": 6.475850797032881e-06, - "loss": 3.2181, + "learning_rate": 6.405463981070925e-06, + "loss": 3.1914, "step": 263100 }, { "epoch": 0.87, - "learning_rate": 6.4593079809162075e-06, - "loss": 3.2172, + "learning_rate": 6.3888944120785526e-06, + "loss": 3.1991, "step": 263200 }, { "epoch": 0.87, - "learning_rate": 6.4427651647995345e-06, - "loss": 3.2177, + "learning_rate": 6.372324843086182e-06, + "loss": 3.1961, "step": 263300 }, { "epoch": 0.87, - "learning_rate": 6.426222348682862e-06, - "loss": 3.2102, + "learning_rate": 6.355755274093811e-06, + "loss": 3.1998, "step": 263400 }, { "epoch": 0.87, - "learning_rate": 6.409679532566189e-06, - "loss": 3.2177, + "learning_rate": 6.3391857051014385e-06, + "loss": 3.1975, "step": 263500 }, { "epoch": 0.87, - "learning_rate": 6.393136716449515e-06, - "loss": 3.2259, + "learning_rate": 6.322616136109068e-06, + "loss": 3.1991, "step": 263600 }, { "epoch": 0.87, - "learning_rate": 6.376593900332842e-06, - "loss": 3.2305, + "learning_rate": 6.306046567116697e-06, + "loss": 3.2056, "step": 263700 }, { "epoch": 0.87, - "learning_rate": 6.360051084216169e-06, - "loss": 3.2247, + "learning_rate": 6.289476998124324e-06, + "loss": 3.2045, "step": 263800 }, { "epoch": 0.87, - "learning_rate": 6.3435082680994944e-06, - "loss": 3.2086, + "learning_rate": 6.272907429131954e-06, + "loss": 3.1925, "step": 263900 }, { "epoch": 0.87, - "learning_rate": 6.326965451982822e-06, - "loss": 3.2164, + "learning_rate": 6.256337860139583e-06, + "loss": 3.2032, "step": 264000 }, { - "epoch": 0.87, - "learning_rate": 6.3104226358661494e-06, - "loss": 3.2158, + "epoch": 0.88, + "learning_rate": 6.239768291147211e-06, + "loss": 3.193, "step": 264100 }, { - "epoch": 0.87, - "learning_rate": 6.2938798197494765e-06, - "loss": 3.2034, + "epoch": 0.88, + "learning_rate": 6.2231987221548395e-06, + "loss": 3.2059, "step": 264200 }, { - "epoch": 0.87, - "learning_rate": 6.277337003632802e-06, - "loss": 3.2282, + "epoch": 0.88, + "learning_rate": 6.206629153162468e-06, + "loss": 3.1985, "step": 264300 }, { - "epoch": 0.87, - "learning_rate": 6.260794187516129e-06, - "loss": 3.2125, + "epoch": 0.88, + "learning_rate": 6.190059584170097e-06, + "loss": 3.2031, "step": 264400 }, { "epoch": 0.88, - "learning_rate": 6.244251371399457e-06, - "loss": 3.2086, + "learning_rate": 6.1734900151777255e-06, + "loss": 3.2033, "step": 264500 }, { "epoch": 0.88, - "learning_rate": 6.227708555282783e-06, - "loss": 3.2104, + "learning_rate": 6.156920446185354e-06, + "loss": 3.1953, "step": 264600 }, { "epoch": 0.88, - "learning_rate": 6.21116573916611e-06, - "loss": 3.2256, + "learning_rate": 6.140350877192982e-06, + "loss": 3.2069, "step": 264700 }, { "epoch": 0.88, - "learning_rate": 6.1946229230494364e-06, - "loss": 3.2317, + "learning_rate": 6.123781308200611e-06, + "loss": 3.2004, "step": 264800 }, { "epoch": 0.88, - "learning_rate": 6.178080106932764e-06, - "loss": 3.216, + "learning_rate": 6.10721173920824e-06, + "loss": 3.1999, "step": 264900 }, { "epoch": 0.88, - "learning_rate": 6.161537290816091e-06, - "loss": 3.223, + "learning_rate": 6.090642170215868e-06, + "loss": 3.2048, "step": 265000 }, { "epoch": 0.88, - "learning_rate": 6.144994474699417e-06, - "loss": 3.2177, + "learning_rate": 6.074072601223497e-06, + "loss": 3.2061, "step": 265100 }, { "epoch": 0.88, - "learning_rate": 6.128451658582744e-06, - "loss": 3.2064, + "learning_rate": 6.057503032231126e-06, + "loss": 3.1851, "step": 265200 }, { "epoch": 0.88, - "learning_rate": 6.111908842466071e-06, - "loss": 3.2168, + "learning_rate": 6.040933463238754e-06, + "loss": 3.201, "step": 265300 }, { "epoch": 0.88, - "learning_rate": 6.095366026349398e-06, - "loss": 3.2267, + "learning_rate": 6.024363894246383e-06, + "loss": 3.2028, "step": 265400 }, { "epoch": 0.88, - "learning_rate": 6.078823210232724e-06, - "loss": 3.2146, + "learning_rate": 6.007794325254012e-06, + "loss": 3.2002, "step": 265500 }, { "epoch": 0.88, - "learning_rate": 6.062280394116051e-06, - "loss": 3.2213, + "learning_rate": 5.99122475626164e-06, + "loss": 3.1904, "step": 265600 }, { "epoch": 0.88, - "learning_rate": 6.045737577999378e-06, - "loss": 3.2195, + "learning_rate": 5.974655187269269e-06, + "loss": 3.1885, "step": 265700 }, { "epoch": 0.88, - "learning_rate": 6.0291947618827055e-06, - "loss": 3.2131, + "learning_rate": 5.9580856182768975e-06, + "loss": 3.1876, "step": 265800 }, { "epoch": 0.88, - "learning_rate": 6.012651945766032e-06, - "loss": 3.229, + "learning_rate": 5.941516049284526e-06, + "loss": 3.2017, "step": 265900 }, { "epoch": 0.88, - "learning_rate": 5.996109129649359e-06, - "loss": 3.2099, + "learning_rate": 5.924946480292154e-06, + "loss": 3.1939, "step": 266000 }, { "epoch": 0.88, - "learning_rate": 5.979566313532686e-06, - "loss": 3.2208, + "learning_rate": 5.9083769112997834e-06, + "loss": 3.1861, "step": 266100 }, { "epoch": 0.88, - "learning_rate": 5.963023497416012e-06, - "loss": 3.2222, + "learning_rate": 5.891807342307412e-06, + "loss": 3.2075, "step": 266200 }, { "epoch": 0.88, - "learning_rate": 5.946480681299339e-06, - "loss": 3.2234, + "learning_rate": 5.875237773315041e-06, + "loss": 3.2062, "step": 266300 }, { "epoch": 0.88, - "learning_rate": 5.929937865182665e-06, - "loss": 3.21, + "learning_rate": 5.858668204322669e-06, + "loss": 3.2042, "step": 266400 }, { "epoch": 0.88, - "learning_rate": 5.913395049065993e-06, - "loss": 3.2173, + "learning_rate": 5.842098635330298e-06, + "loss": 3.1906, "step": 266500 }, { "epoch": 0.88, - "learning_rate": 5.8968522329493196e-06, - "loss": 3.2111, + "learning_rate": 5.825529066337927e-06, + "loss": 3.1885, "step": 266600 }, { "epoch": 0.88, - "learning_rate": 5.880309416832647e-06, - "loss": 3.2074, + "learning_rate": 5.808959497345555e-06, + "loss": 3.2018, "step": 266700 }, { "epoch": 0.88, - "learning_rate": 5.863766600715973e-06, - "loss": 3.2177, + "learning_rate": 5.7923899283531845e-06, + "loss": 3.1924, "step": 266800 }, { "epoch": 0.88, - "learning_rate": 5.847223784599301e-06, - "loss": 3.2001, + "learning_rate": 5.775820359360813e-06, + "loss": 3.1831, "step": 266900 }, { "epoch": 0.88, - "learning_rate": 5.830680968482627e-06, - "loss": 3.2274, + "learning_rate": 5.759250790368441e-06, + "loss": 3.1926, "step": 267000 }, { - "epoch": 0.88, - "learning_rate": 5.814138152365954e-06, - "loss": 3.2166, + "epoch": 0.89, + "learning_rate": 5.74268122137607e-06, + "loss": 3.1895, "step": 267100 }, { - "epoch": 0.88, - "learning_rate": 5.79759533624928e-06, - "loss": 3.2162, + "epoch": 0.89, + "learning_rate": 5.726111652383699e-06, + "loss": 3.2005, "step": 267200 }, { - "epoch": 0.88, - "learning_rate": 5.781052520132607e-06, - "loss": 3.2159, + "epoch": 0.89, + "learning_rate": 5.709542083391327e-06, + "loss": 3.199, "step": 267300 }, { - "epoch": 0.88, - "learning_rate": 5.7645097040159345e-06, - "loss": 3.2237, + "epoch": 0.89, + "learning_rate": 5.692972514398956e-06, + "loss": 3.1953, "step": 267400 }, { "epoch": 0.89, - "learning_rate": 5.747966887899261e-06, - "loss": 3.2126, + "learning_rate": 5.676402945406585e-06, + "loss": 3.2068, "step": 267500 }, { "epoch": 0.89, - "learning_rate": 5.731424071782588e-06, - "loss": 3.2088, + "learning_rate": 5.659833376414213e-06, + "loss": 3.2019, "step": 267600 }, { "epoch": 0.89, - "learning_rate": 5.714881255665915e-06, - "loss": 3.2136, + "learning_rate": 5.643263807421842e-06, + "loss": 3.1942, "step": 267700 }, { "epoch": 0.89, - "learning_rate": 5.698338439549242e-06, - "loss": 3.2237, + "learning_rate": 5.626694238429471e-06, + "loss": 3.2005, "step": 267800 }, { "epoch": 0.89, - "learning_rate": 5.681795623432568e-06, - "loss": 3.2079, + "learning_rate": 5.610124669437099e-06, + "loss": 3.1976, "step": 267900 }, { "epoch": 0.89, - "learning_rate": 5.665252807315895e-06, - "loss": 3.232, + "learning_rate": 5.593555100444727e-06, + "loss": 3.1944, "step": 268000 }, { "epoch": 0.89, - "learning_rate": 5.648709991199222e-06, - "loss": 3.2233, + "learning_rate": 5.5769855314523565e-06, + "loss": 3.2012, "step": 268100 }, { "epoch": 0.89, - "learning_rate": 5.632167175082549e-06, - "loss": 3.2131, + "learning_rate": 5.560415962459985e-06, + "loss": 3.2054, "step": 268200 }, { "epoch": 0.89, - "learning_rate": 5.615624358965876e-06, - "loss": 3.2187, + "learning_rate": 5.543846393467613e-06, + "loss": 3.1957, "step": 268300 }, { "epoch": 0.89, - "learning_rate": 5.599081542849203e-06, - "loss": 3.2156, + "learning_rate": 5.5272768244752424e-06, + "loss": 3.2021, "step": 268400 }, { "epoch": 0.89, - "learning_rate": 5.58253872673253e-06, - "loss": 3.2185, + "learning_rate": 5.510707255482871e-06, + "loss": 3.1878, "step": 268500 }, { "epoch": 0.89, - "learning_rate": 5.565995910615857e-06, - "loss": 3.236, + "learning_rate": 5.494137686490499e-06, + "loss": 3.2068, "step": 268600 }, { "epoch": 0.89, - "learning_rate": 5.549453094499183e-06, - "loss": 3.2232, + "learning_rate": 5.477568117498128e-06, + "loss": 3.1908, "step": 268700 }, { "epoch": 0.89, - "learning_rate": 5.532910278382509e-06, - "loss": 3.2201, + "learning_rate": 5.460998548505757e-06, + "loss": 3.2027, "step": 268800 }, { "epoch": 0.89, - "learning_rate": 5.516367462265836e-06, - "loss": 3.2054, + "learning_rate": 5.444428979513385e-06, + "loss": 3.1964, "step": 268900 }, { "epoch": 0.89, - "learning_rate": 5.4998246461491634e-06, - "loss": 3.2212, + "learning_rate": 5.427859410521014e-06, + "loss": 3.1848, "step": 269000 }, { "epoch": 0.89, - "learning_rate": 5.4832818300324905e-06, - "loss": 3.2065, + "learning_rate": 5.411289841528643e-06, + "loss": 3.1923, "step": 269100 }, { "epoch": 0.89, - "learning_rate": 5.466739013915817e-06, - "loss": 3.2176, + "learning_rate": 5.394720272536271e-06, + "loss": 3.188, "step": 269200 }, { "epoch": 0.89, - "learning_rate": 5.450196197799144e-06, - "loss": 3.2282, + "learning_rate": 5.378150703543899e-06, + "loss": 3.1933, "step": 269300 }, { "epoch": 0.89, - "learning_rate": 5.433653381682471e-06, - "loss": 3.2042, + "learning_rate": 5.3615811345515286e-06, + "loss": 3.2027, "step": 269400 }, { "epoch": 0.89, - "learning_rate": 5.417110565565798e-06, - "loss": 3.2102, + "learning_rate": 5.345011565559157e-06, + "loss": 3.1905, "step": 269500 }, { "epoch": 0.89, - "learning_rate": 5.400567749449124e-06, - "loss": 3.2231, + "learning_rate": 5.328441996566785e-06, + "loss": 3.1919, "step": 269600 }, { "epoch": 0.89, - "learning_rate": 5.384024933332451e-06, - "loss": 3.2141, + "learning_rate": 5.3118724275744145e-06, + "loss": 3.1936, "step": 269700 }, { "epoch": 0.89, - "learning_rate": 5.367482117215778e-06, - "loss": 3.2144, + "learning_rate": 5.295302858582043e-06, + "loss": 3.1943, "step": 269800 }, { "epoch": 0.89, - "learning_rate": 5.350939301099105e-06, - "loss": 3.2256, + "learning_rate": 5.278733289589671e-06, + "loss": 3.1764, "step": 269900 }, { "epoch": 0.89, - "learning_rate": 5.334396484982432e-06, - "loss": 3.223, + "learning_rate": 5.2621637205973e-06, + "loss": 3.1938, "step": 270000 }, { - "epoch": 0.89, - "learning_rate": 5.317853668865759e-06, - "loss": 3.2048, + "epoch": 0.9, + "learning_rate": 5.245594151604929e-06, + "loss": 3.2053, "step": 270100 }, { - "epoch": 0.89, - "learning_rate": 5.301310852749086e-06, - "loss": 3.2175, + "epoch": 0.9, + "learning_rate": 5.229024582612557e-06, + "loss": 3.1941, "step": 270200 }, { - "epoch": 0.89, - "learning_rate": 5.284768036632412e-06, - "loss": 3.2169, + "epoch": 0.9, + "learning_rate": 5.2124550136201855e-06, + "loss": 3.1898, "step": 270300 }, - { - "epoch": 0.89, - "learning_rate": 5.268225220515739e-06, - "loss": 3.2184, + { + "epoch": 0.9, + "learning_rate": 5.195885444627815e-06, + "loss": 3.1886, "step": 270400 }, { - "epoch": 0.89, - "learning_rate": 5.251682404399065e-06, - "loss": 3.2173, + "epoch": 0.9, + "learning_rate": 5.179315875635443e-06, + "loss": 3.2037, "step": 270500 }, { "epoch": 0.9, - "learning_rate": 5.235139588282393e-06, - "loss": 3.22, + "learning_rate": 5.162746306643071e-06, + "loss": 3.1957, "step": 270600 }, { "epoch": 0.9, - "learning_rate": 5.2185967721657195e-06, - "loss": 3.2237, + "learning_rate": 5.146176737650701e-06, + "loss": 3.1859, "step": 270700 }, { "epoch": 0.9, - "learning_rate": 5.2020539560490466e-06, - "loss": 3.1947, + "learning_rate": 5.129607168658329e-06, + "loss": 3.2039, "step": 270800 }, { "epoch": 0.9, - "learning_rate": 5.185511139932373e-06, - "loss": 3.2158, + "learning_rate": 5.113037599665957e-06, + "loss": 3.1869, "step": 270900 }, { "epoch": 0.9, - "learning_rate": 5.168968323815701e-06, - "loss": 3.2122, + "learning_rate": 5.0964680306735865e-06, + "loss": 3.2138, "step": 271000 }, { "epoch": 0.9, - "learning_rate": 5.152425507699027e-06, - "loss": 3.2191, + "learning_rate": 5.079898461681215e-06, + "loss": 3.1947, "step": 271100 }, { "epoch": 0.9, - "learning_rate": 5.135882691582353e-06, - "loss": 3.2119, + "learning_rate": 5.063328892688843e-06, + "loss": 3.1938, "step": 271200 }, { "epoch": 0.9, - "learning_rate": 5.11933987546568e-06, - "loss": 3.2334, + "learning_rate": 5.046759323696472e-06, + "loss": 3.2019, "step": 271300 }, { "epoch": 0.9, - "learning_rate": 5.102797059349007e-06, - "loss": 3.2109, + "learning_rate": 5.030189754704101e-06, + "loss": 3.1861, "step": 271400 }, { "epoch": 0.9, - "learning_rate": 5.086254243232334e-06, - "loss": 3.2182, + "learning_rate": 5.013620185711729e-06, + "loss": 3.1945, "step": 271500 }, { "epoch": 0.9, - "learning_rate": 5.069711427115661e-06, - "loss": 3.231, + "learning_rate": 4.9970506167193575e-06, + "loss": 3.2061, "step": 271600 }, { "epoch": 0.9, - "learning_rate": 5.053168610998988e-06, - "loss": 3.2235, + "learning_rate": 4.980481047726987e-06, + "loss": 3.1892, "step": 271700 }, { "epoch": 0.9, - "learning_rate": 5.036625794882315e-06, - "loss": 3.215, + "learning_rate": 4.963911478734615e-06, + "loss": 3.2042, "step": 271800 }, { "epoch": 0.9, - "learning_rate": 5.020082978765642e-06, - "loss": 3.2117, + "learning_rate": 4.9473419097422435e-06, + "loss": 3.1973, "step": 271900 }, { "epoch": 0.9, - "learning_rate": 5.003540162648968e-06, - "loss": 3.2244, + "learning_rate": 4.930772340749873e-06, + "loss": 3.1865, "step": 272000 }, { "epoch": 0.9, - "learning_rate": 4.986997346532295e-06, - "loss": 3.2114, + "learning_rate": 4.914202771757501e-06, + "loss": 3.2016, "step": 272100 }, { "epoch": 0.9, - "learning_rate": 4.970454530415622e-06, - "loss": 3.2127, + "learning_rate": 4.897633202765129e-06, + "loss": 3.1844, "step": 272200 }, { "epoch": 0.9, - "learning_rate": 4.9539117142989485e-06, - "loss": 3.2133, + "learning_rate": 4.881063633772759e-06, + "loss": 3.1993, "step": 272300 }, { "epoch": 0.9, - "learning_rate": 4.9373688981822755e-06, - "loss": 3.2087, + "learning_rate": 4.864494064780387e-06, + "loss": 3.1829, "step": 272400 }, { "epoch": 0.9, - "learning_rate": 4.920826082065602e-06, - "loss": 3.2238, + "learning_rate": 4.847924495788015e-06, + "loss": 3.1932, "step": 272500 }, { "epoch": 0.9, - "learning_rate": 4.90428326594893e-06, - "loss": 3.2152, + "learning_rate": 4.8313549267956445e-06, + "loss": 3.1942, "step": 272600 }, { "epoch": 0.9, - "learning_rate": 4.887740449832256e-06, - "loss": 3.2088, + "learning_rate": 4.814785357803273e-06, + "loss": 3.2129, "step": 272700 }, { "epoch": 0.9, - "learning_rate": 4.871197633715583e-06, - "loss": 3.2056, + "learning_rate": 4.798215788810902e-06, + "loss": 3.1984, "step": 272800 }, { "epoch": 0.9, - "learning_rate": 4.854654817598909e-06, - "loss": 3.221, + "learning_rate": 4.7816462198185304e-06, + "loss": 3.1943, "step": 272900 }, { "epoch": 0.9, - "learning_rate": 4.838112001482237e-06, - "loss": 3.2242, + "learning_rate": 4.765076650826159e-06, + "loss": 3.2095, "step": 273000 }, { - "epoch": 0.9, - "learning_rate": 4.821569185365563e-06, - "loss": 3.2055, + "epoch": 0.91, + "learning_rate": 4.748507081833788e-06, + "loss": 3.2085, "step": 273100 }, { - "epoch": 0.9, - "learning_rate": 4.8050263692488905e-06, - "loss": 3.2109, + "epoch": 0.91, + "learning_rate": 4.731937512841416e-06, + "loss": 3.2091, "step": 273200 }, { - "epoch": 0.9, - "learning_rate": 4.788483553132217e-06, - "loss": 3.2133, + "epoch": 0.91, + "learning_rate": 4.7153679438490456e-06, + "loss": 3.2097, "step": 273300 }, { - "epoch": 0.9, - "learning_rate": 4.771940737015544e-06, - "loss": 3.2159, + "epoch": 0.91, + "learning_rate": 4.698798374856674e-06, + "loss": 3.1987, "step": 273400 }, { - "epoch": 0.9, - "learning_rate": 4.755397920898871e-06, - "loss": 3.2194, + "epoch": 0.91, + "learning_rate": 4.682228805864302e-06, + "loss": 3.1736, "step": 273500 }, { "epoch": 0.91, - "learning_rate": 4.738855104782197e-06, - "loss": 3.2264, + "learning_rate": 4.665659236871931e-06, + "loss": 3.1976, "step": 273600 }, { "epoch": 0.91, - "learning_rate": 4.722312288665524e-06, - "loss": 3.2145, + "learning_rate": 4.64908966787956e-06, + "loss": 3.2155, "step": 273700 }, { "epoch": 0.91, - "learning_rate": 4.705769472548851e-06, - "loss": 3.201, + "learning_rate": 4.632520098887188e-06, + "loss": 3.1932, "step": 273800 }, { "epoch": 0.91, - "learning_rate": 4.689226656432178e-06, - "loss": 3.2046, + "learning_rate": 4.6159505298948166e-06, + "loss": 3.2084, "step": 273900 }, { "epoch": 0.91, - "learning_rate": 4.6726838403155045e-06, - "loss": 3.2163, + "learning_rate": 4.599380960902446e-06, + "loss": 3.2019, "step": 274000 }, { "epoch": 0.91, - "learning_rate": 4.656141024198832e-06, - "loss": 3.2124, + "learning_rate": 4.582811391910074e-06, + "loss": 3.1943, "step": 274100 }, { "epoch": 0.91, - "learning_rate": 4.639598208082159e-06, - "loss": 3.2133, + "learning_rate": 4.5662418229177025e-06, + "loss": 3.1962, "step": 274200 }, { "epoch": 0.91, - "learning_rate": 4.623055391965486e-06, - "loss": 3.2204, + "learning_rate": 4.549672253925332e-06, + "loss": 3.1974, "step": 274300 }, { "epoch": 0.91, - "learning_rate": 4.606512575848812e-06, - "loss": 3.2195, + "learning_rate": 4.53310268493296e-06, + "loss": 3.1936, "step": 274400 }, { "epoch": 0.91, - "learning_rate": 4.589969759732139e-06, - "loss": 3.1909, + "learning_rate": 4.516533115940588e-06, + "loss": 3.2041, "step": 274500 }, { "epoch": 0.91, - "learning_rate": 4.573426943615466e-06, - "loss": 3.2171, + "learning_rate": 4.499963546948217e-06, + "loss": 3.2056, "step": 274600 }, { "epoch": 0.91, - "learning_rate": 4.556884127498793e-06, - "loss": 3.2185, + "learning_rate": 4.483393977955846e-06, + "loss": 3.2052, "step": 274700 }, { "epoch": 0.91, - "learning_rate": 4.5403413113821194e-06, - "loss": 3.2152, + "learning_rate": 4.466824408963474e-06, + "loss": 3.1982, "step": 274800 }, { "epoch": 0.91, - "learning_rate": 4.523798495265446e-06, - "loss": 3.2114, + "learning_rate": 4.450254839971103e-06, + "loss": 3.1906, "step": 274900 }, { "epoch": 0.91, - "learning_rate": 4.507255679148773e-06, - "loss": 3.225, + "learning_rate": 4.433685270978732e-06, + "loss": 3.1926, "step": 275000 }, { "epoch": 0.91, - "learning_rate": 4.4907128630321e-06, - "loss": 3.2152, + "learning_rate": 4.41711570198636e-06, + "loss": 3.1982, "step": 275100 }, { "epoch": 0.91, - "learning_rate": 4.474170046915427e-06, - "loss": 3.1953, + "learning_rate": 4.400546132993989e-06, + "loss": 3.1937, "step": 275200 }, { "epoch": 0.91, - "learning_rate": 4.457627230798753e-06, - "loss": 3.2129, + "learning_rate": 4.383976564001618e-06, + "loss": 3.1874, "step": 275300 }, { "epoch": 0.91, - "learning_rate": 4.44108441468208e-06, - "loss": 3.2131, + "learning_rate": 4.367406995009246e-06, + "loss": 3.1878, "step": 275400 }, { "epoch": 0.91, - "learning_rate": 4.424541598565407e-06, - "loss": 3.2156, + "learning_rate": 4.3508374260168745e-06, + "loss": 3.2009, "step": 275500 }, { "epoch": 0.91, - "learning_rate": 4.407998782448734e-06, - "loss": 3.2232, + "learning_rate": 4.334267857024503e-06, + "loss": 3.2132, "step": 275600 }, { "epoch": 0.91, - "learning_rate": 4.3914559663320606e-06, - "loss": 3.2089, + "learning_rate": 4.317698288032132e-06, + "loss": 3.1897, "step": 275700 }, { "epoch": 0.91, - "learning_rate": 4.374913150215388e-06, - "loss": 3.2168, + "learning_rate": 4.3011287190397605e-06, + "loss": 3.1978, "step": 275800 }, { "epoch": 0.91, - "learning_rate": 4.358370334098715e-06, - "loss": 3.2052, + "learning_rate": 4.284559150047389e-06, + "loss": 3.2, "step": 275900 }, { "epoch": 0.91, - "learning_rate": 4.341827517982041e-06, - "loss": 3.2259, + "learning_rate": 4.267989581055018e-06, + "loss": 3.1906, "step": 276000 }, { "epoch": 0.91, - "learning_rate": 4.325284701865368e-06, - "loss": 3.2029, + "learning_rate": 4.251420012062646e-06, + "loss": 3.1906, "step": 276100 }, { - "epoch": 0.91, - "learning_rate": 4.308741885748695e-06, - "loss": 3.2275, + "epoch": 0.92, + "learning_rate": 4.234850443070275e-06, + "loss": 3.1991, "step": 276200 }, { - "epoch": 0.91, - "learning_rate": 4.292199069632022e-06, - "loss": 3.2216, + "epoch": 0.92, + "learning_rate": 4.218280874077904e-06, + "loss": 3.1945, "step": 276300 }, { - "epoch": 0.91, - "learning_rate": 4.275656253515348e-06, - "loss": 3.2145, + "epoch": 0.92, + "learning_rate": 4.201711305085532e-06, + "loss": 3.2049, "step": 276400 }, { - "epoch": 0.91, - "learning_rate": 4.2591134373986755e-06, - "loss": 3.212, + "epoch": 0.92, + "learning_rate": 4.185141736093161e-06, + "loss": 3.194, "step": 276500 }, { "epoch": 0.92, - "learning_rate": 4.242570621282002e-06, - "loss": 3.2195, + "learning_rate": 4.16857216710079e-06, + "loss": 3.194, "step": 276600 }, { "epoch": 0.92, - "learning_rate": 4.22602780516533e-06, - "loss": 3.2062, + "learning_rate": 4.152002598108418e-06, + "loss": 3.1953, "step": 276700 }, { "epoch": 0.92, - "learning_rate": 4.209484989048656e-06, - "loss": 3.2096, + "learning_rate": 4.135433029116047e-06, + "loss": 3.1893, "step": 276800 }, { "epoch": 0.92, - "learning_rate": 4.192942172931983e-06, - "loss": 3.2087, + "learning_rate": 4.118863460123675e-06, + "loss": 3.2006, "step": 276900 }, { "epoch": 0.92, - "learning_rate": 4.176399356815309e-06, - "loss": 3.203, + "learning_rate": 4.102293891131304e-06, + "loss": 3.2029, "step": 277000 }, { "epoch": 0.92, - "learning_rate": 4.159856540698637e-06, + "learning_rate": 4.0857243221389325e-06, "loss": 3.2134, "step": 277100 }, { "epoch": 0.92, - "learning_rate": 4.143313724581963e-06, - "loss": 3.2182, + "learning_rate": 4.069154753146561e-06, + "loss": 3.1961, "step": 277200 }, { "epoch": 0.92, - "learning_rate": 4.1267709084652896e-06, - "loss": 3.208, + "learning_rate": 4.05258518415419e-06, + "loss": 3.1829, "step": 277300 }, { "epoch": 0.92, - "learning_rate": 4.110228092348617e-06, - "loss": 3.2121, + "learning_rate": 4.0360156151618184e-06, + "loss": 3.1846, "step": 277400 }, { "epoch": 0.92, - "learning_rate": 4.093685276231944e-06, - "loss": 3.2105, + "learning_rate": 4.019446046169447e-06, + "loss": 3.2041, "step": 277500 }, { "epoch": 0.92, - "learning_rate": 4.077142460115271e-06, - "loss": 3.2228, + "learning_rate": 4.002876477177076e-06, + "loss": 3.1943, "step": 277600 }, { "epoch": 0.92, - "learning_rate": 4.060599643998597e-06, - "loss": 3.2149, + "learning_rate": 3.986306908184704e-06, + "loss": 3.208, "step": 277700 }, { "epoch": 0.92, - "learning_rate": 4.044056827881924e-06, - "loss": 3.2107, + "learning_rate": 3.969737339192333e-06, + "loss": 3.1927, "step": 277800 }, { "epoch": 0.92, - "learning_rate": 4.027514011765251e-06, - "loss": 3.2071, + "learning_rate": 3.953167770199961e-06, + "loss": 3.2091, "step": 277900 }, { "epoch": 0.92, - "learning_rate": 4.010971195648578e-06, - "loss": 3.2262, + "learning_rate": 3.93659820120759e-06, + "loss": 3.2018, "step": 278000 }, { "epoch": 0.92, - "learning_rate": 3.9944283795319045e-06, - "loss": 3.2158, + "learning_rate": 3.920028632215219e-06, + "loss": 3.1928, "step": 278100 }, { "epoch": 0.92, - "learning_rate": 3.9778855634152315e-06, - "loss": 3.199, + "learning_rate": 3.903459063222847e-06, + "loss": 3.1958, "step": 278200 }, { "epoch": 0.92, - "learning_rate": 3.961342747298559e-06, - "loss": 3.2057, + "learning_rate": 3.886889494230476e-06, + "loss": 3.1915, "step": 278300 }, { "epoch": 0.92, - "learning_rate": 3.944799931181886e-06, - "loss": 3.23, + "learning_rate": 3.8703199252381046e-06, + "loss": 3.184, "step": 278400 }, { "epoch": 0.92, - "learning_rate": 3.928257115065212e-06, - "loss": 3.2048, + "learning_rate": 3.853750356245733e-06, + "loss": 3.1804, "step": 278500 }, { "epoch": 0.92, - "learning_rate": 3.911714298948538e-06, - "loss": 3.2243, + "learning_rate": 3.837180787253362e-06, + "loss": 3.2093, "step": 278600 }, { "epoch": 0.92, - "learning_rate": 3.895171482831866e-06, - "loss": 3.2103, + "learning_rate": 3.8206112182609905e-06, + "loss": 3.1918, "step": 278700 }, { "epoch": 0.92, - "learning_rate": 3.878628666715192e-06, - "loss": 3.222, + "learning_rate": 3.8040416492686193e-06, + "loss": 3.1972, "step": 278800 }, { "epoch": 0.92, - "learning_rate": 3.862085850598519e-06, - "loss": 3.227, + "learning_rate": 3.7874720802762476e-06, + "loss": 3.1872, "step": 278900 }, { "epoch": 0.92, - "learning_rate": 3.845543034481846e-06, - "loss": 3.2258, + "learning_rate": 3.770902511283877e-06, + "loss": 3.1887, "step": 279000 }, { "epoch": 0.92, - "learning_rate": 3.8290002183651735e-06, - "loss": 3.2118, + "learning_rate": 3.754332942291505e-06, + "loss": 3.2183, "step": 279100 }, { - "epoch": 0.92, - "learning_rate": 3.8124574022484998e-06, - "loss": 3.2124, + "epoch": 0.93, + "learning_rate": 3.7377633732991335e-06, + "loss": 3.186, "step": 279200 }, { - "epoch": 0.92, - "learning_rate": 3.795914586131827e-06, - "loss": 3.2096, + "epoch": 0.93, + "learning_rate": 3.7211938043067627e-06, + "loss": 3.2088, "step": 279300 }, { - "epoch": 0.92, - "learning_rate": 3.7793717700151535e-06, - "loss": 3.195, + "epoch": 0.93, + "learning_rate": 3.704624235314391e-06, + "loss": 3.2052, "step": 279400 }, { - "epoch": 0.92, - "learning_rate": 3.7628289538984806e-06, - "loss": 3.2198, + "epoch": 0.93, + "learning_rate": 3.6880546663220195e-06, + "loss": 3.185, "step": 279500 }, { "epoch": 0.93, - "learning_rate": 3.746286137781807e-06, - "loss": 3.2074, + "learning_rate": 3.6714850973296487e-06, + "loss": 3.187, "step": 279600 }, { "epoch": 0.93, - "learning_rate": 3.7297433216651334e-06, - "loss": 3.1993, + "learning_rate": 3.654915528337277e-06, + "loss": 3.196, "step": 279700 }, { "epoch": 0.93, - "learning_rate": 3.713200505548461e-06, - "loss": 3.2058, + "learning_rate": 3.6383459593449054e-06, + "loss": 3.1924, "step": 279800 }, { "epoch": 0.93, - "learning_rate": 3.696657689431787e-06, - "loss": 3.2126, + "learning_rate": 3.6217763903525346e-06, + "loss": 3.1811, "step": 279900 }, { "epoch": 0.93, - "learning_rate": 3.6801148733151147e-06, - "loss": 3.2169, + "learning_rate": 3.605206821360163e-06, + "loss": 3.2053, "step": 280000 }, { "epoch": 0.93, - "learning_rate": 3.663572057198441e-06, - "loss": 3.217, + "learning_rate": 3.5886372523677913e-06, + "loss": 3.2049, "step": 280100 }, { "epoch": 0.93, - "learning_rate": 3.647029241081768e-06, - "loss": 3.223, + "learning_rate": 3.57206768337542e-06, + "loss": 3.2003, "step": 280200 }, { "epoch": 0.93, - "learning_rate": 3.6304864249650946e-06, - "loss": 3.208, + "learning_rate": 3.555498114383049e-06, + "loss": 3.18, "step": 280300 }, { "epoch": 0.93, - "learning_rate": 3.6139436088484217e-06, - "loss": 3.221, + "learning_rate": 3.5389285453906776e-06, + "loss": 3.1911, "step": 280400 }, { "epoch": 0.93, - "learning_rate": 3.5974007927317483e-06, - "loss": 3.2079, + "learning_rate": 3.522358976398306e-06, + "loss": 3.1912, "step": 280500 }, { "epoch": 0.93, - "learning_rate": 3.5808579766150754e-06, - "loss": 3.2119, + "learning_rate": 3.505789407405935e-06, + "loss": 3.1971, "step": 280600 }, { "epoch": 0.93, - "learning_rate": 3.564315160498402e-06, - "loss": 3.2172, + "learning_rate": 3.4892198384135636e-06, + "loss": 3.1857, "step": 280700 }, { "epoch": 0.93, - "learning_rate": 3.547772344381729e-06, - "loss": 3.2074, + "learning_rate": 3.472650269421192e-06, + "loss": 3.2056, "step": 280800 }, { "epoch": 0.93, - "learning_rate": 3.531229528265056e-06, - "loss": 3.207, + "learning_rate": 3.456080700428821e-06, + "loss": 3.198, "step": 280900 }, { "epoch": 0.93, - "learning_rate": 3.5146867121483825e-06, - "loss": 3.206, + "learning_rate": 3.4395111314364495e-06, + "loss": 3.1944, "step": 281000 }, { "epoch": 0.93, - "learning_rate": 3.4981438960317095e-06, - "loss": 3.2186, + "learning_rate": 3.422941562444078e-06, + "loss": 3.1959, "step": 281100 }, { "epoch": 0.93, - "learning_rate": 3.481601079915036e-06, - "loss": 3.2232, + "learning_rate": 3.406371993451706e-06, + "loss": 3.1845, "step": 281200 }, { "epoch": 0.93, - "learning_rate": 3.4650582637983633e-06, - "loss": 3.2219, + "learning_rate": 3.3898024244593354e-06, + "loss": 3.1892, "step": 281300 }, { "epoch": 0.93, - "learning_rate": 3.44851544768169e-06, - "loss": 3.2111, + "learning_rate": 3.3732328554669638e-06, + "loss": 3.177, "step": 281400 }, { "epoch": 0.93, - "learning_rate": 3.431972631565017e-06, - "loss": 3.2241, + "learning_rate": 3.356663286474592e-06, + "loss": 3.212, "step": 281500 }, { "epoch": 0.93, - "learning_rate": 3.4154298154483432e-06, - "loss": 3.2079, + "learning_rate": 3.3400937174822213e-06, + "loss": 3.2007, "step": 281600 }, { "epoch": 0.93, - "learning_rate": 3.3988869993316707e-06, - "loss": 3.2109, + "learning_rate": 3.3235241484898497e-06, + "loss": 3.2081, "step": 281700 }, { "epoch": 0.93, - "learning_rate": 3.382344183214997e-06, - "loss": 3.2175, + "learning_rate": 3.306954579497478e-06, + "loss": 3.1967, "step": 281800 }, { "epoch": 0.93, - "learning_rate": 3.3658013670983244e-06, - "loss": 3.2135, + "learning_rate": 3.2903850105051073e-06, + "loss": 3.2081, "step": 281900 }, { "epoch": 0.93, - "learning_rate": 3.3492585509816507e-06, - "loss": 3.2205, + "learning_rate": 3.2738154415127356e-06, + "loss": 3.2023, "step": 282000 }, { "epoch": 0.93, - "learning_rate": 3.332715734864978e-06, - "loss": 3.2031, + "learning_rate": 3.257245872520364e-06, + "loss": 3.2075, "step": 282100 }, { - "epoch": 0.93, - "learning_rate": 3.3161729187483044e-06, - "loss": 3.2165, + "epoch": 0.94, + "learning_rate": 3.2406763035279923e-06, + "loss": 3.1768, "step": 282200 }, { - "epoch": 0.93, - "learning_rate": 3.299630102631631e-06, - "loss": 3.2207, + "epoch": 0.94, + "learning_rate": 3.2241067345356215e-06, + "loss": 3.197, "step": 282300 }, { - "epoch": 0.93, - "learning_rate": 3.283087286514958e-06, - "loss": 3.2225, + "epoch": 0.94, + "learning_rate": 3.20753716554325e-06, + "loss": 3.1984, "step": 282400 }, { - "epoch": 0.93, - "learning_rate": 3.2665444703982848e-06, - "loss": 3.2181, + "epoch": 0.94, + "learning_rate": 3.1909675965508783e-06, + "loss": 3.2127, "step": 282500 }, { - "epoch": 0.93, - "learning_rate": 3.250001654281612e-06, - "loss": 3.2178, + "epoch": 0.94, + "learning_rate": 3.1743980275585075e-06, + "loss": 3.1937, "step": 282600 }, { "epoch": 0.94, - "learning_rate": 3.2334588381649385e-06, - "loss": 3.2113, + "learning_rate": 3.157828458566136e-06, + "loss": 3.1999, "step": 282700 }, { "epoch": 0.94, - "learning_rate": 3.2169160220482656e-06, - "loss": 3.2177, + "learning_rate": 3.141258889573764e-06, + "loss": 3.1962, "step": 282800 }, { "epoch": 0.94, - "learning_rate": 3.2003732059315922e-06, - "loss": 3.2269, + "learning_rate": 3.124689320581393e-06, + "loss": 3.1872, "step": 282900 }, { "epoch": 0.94, - "learning_rate": 3.1838303898149193e-06, - "loss": 3.2226, + "learning_rate": 3.1081197515890217e-06, + "loss": 3.2094, "step": 283000 }, { "epoch": 0.94, - "learning_rate": 3.167287573698246e-06, - "loss": 3.2158, + "learning_rate": 3.09155018259665e-06, + "loss": 3.2024, "step": 283100 }, { "epoch": 0.94, - "learning_rate": 3.150744757581573e-06, - "loss": 3.2321, + "learning_rate": 3.074980613604279e-06, + "loss": 3.2066, "step": 283200 }, { "epoch": 0.94, - "learning_rate": 3.1342019414648997e-06, - "loss": 3.2041, + "learning_rate": 3.0584110446119077e-06, + "loss": 3.1938, "step": 283300 }, { "epoch": 0.94, - "learning_rate": 3.1176591253482263e-06, - "loss": 3.2085, + "learning_rate": 3.0418414756195365e-06, + "loss": 3.1987, "step": 283400 }, { "epoch": 0.94, - "learning_rate": 3.1011163092315534e-06, - "loss": 3.2112, + "learning_rate": 3.025271906627165e-06, + "loss": 3.1939, "step": 283500 }, { "epoch": 0.94, - "learning_rate": 3.08457349311488e-06, - "loss": 3.2034, + "learning_rate": 3.0087023376347936e-06, + "loss": 3.1908, "step": 283600 }, { "epoch": 0.94, - "learning_rate": 3.068030676998207e-06, - "loss": 3.2191, + "learning_rate": 2.9921327686424224e-06, + "loss": 3.1876, "step": 283700 }, { "epoch": 0.94, - "learning_rate": 3.051487860881534e-06, - "loss": 3.2216, + "learning_rate": 2.975563199650051e-06, + "loss": 3.1957, "step": 283800 }, { "epoch": 0.94, - "learning_rate": 3.034945044764861e-06, - "loss": 3.2283, + "learning_rate": 2.9589936306576795e-06, + "loss": 3.1796, "step": 283900 }, { "epoch": 0.94, - "learning_rate": 3.018402228648187e-06, - "loss": 3.2204, + "learning_rate": 2.9424240616653083e-06, + "loss": 3.188, "step": 284000 }, { "epoch": 0.94, - "learning_rate": 3.001859412531514e-06, - "loss": 3.2243, + "learning_rate": 2.9258544926729367e-06, + "loss": 3.2003, "step": 284100 }, { "epoch": 0.94, - "learning_rate": 2.985316596414841e-06, - "loss": 3.2203, + "learning_rate": 2.9092849236805654e-06, + "loss": 3.1939, "step": 284200 }, { "epoch": 0.94, - "learning_rate": 2.968773780298168e-06, - "loss": 3.2006, + "learning_rate": 2.8927153546881942e-06, + "loss": 3.1908, "step": 284300 }, { "epoch": 0.94, - "learning_rate": 2.9522309641814946e-06, - "loss": 3.2136, + "learning_rate": 2.8761457856958226e-06, + "loss": 3.1916, "step": 284400 }, { "epoch": 0.94, - "learning_rate": 2.9356881480648216e-06, - "loss": 3.218, + "learning_rate": 2.8595762167034514e-06, + "loss": 3.2058, "step": 284500 }, { "epoch": 0.94, - "learning_rate": 2.9191453319481483e-06, - "loss": 3.214, + "learning_rate": 2.8430066477110797e-06, + "loss": 3.1948, "step": 284600 }, { "epoch": 0.94, - "learning_rate": 2.9026025158314754e-06, - "loss": 3.2167, + "learning_rate": 2.8264370787187085e-06, + "loss": 3.2074, "step": 284700 }, { "epoch": 0.94, - "learning_rate": 2.886059699714802e-06, - "loss": 3.2243, + "learning_rate": 2.8098675097263373e-06, + "loss": 3.1944, "step": 284800 }, { "epoch": 0.94, - "learning_rate": 2.869516883598129e-06, - "loss": 3.2146, + "learning_rate": 2.7932979407339656e-06, + "loss": 3.2124, "step": 284900 }, { "epoch": 0.94, - "learning_rate": 2.8529740674814557e-06, - "loss": 3.2202, + "learning_rate": 2.7767283717415944e-06, + "loss": 3.1756, "step": 285000 }, { "epoch": 0.94, - "learning_rate": 2.836431251364783e-06, - "loss": 3.2094, + "learning_rate": 2.760158802749223e-06, + "loss": 3.1963, "step": 285100 }, { - "epoch": 0.94, - "learning_rate": 2.819888435248109e-06, - "loss": 3.2113, + "epoch": 0.95, + "learning_rate": 2.7435892337568516e-06, + "loss": 3.207, "step": 285200 }, { - "epoch": 0.94, - "learning_rate": 2.803345619131436e-06, - "loss": 3.2202, + "epoch": 0.95, + "learning_rate": 2.7270196647644803e-06, + "loss": 3.1815, "step": 285300 }, { - "epoch": 0.94, - "learning_rate": 2.7868028030147628e-06, - "loss": 3.2215, + "epoch": 0.95, + "learning_rate": 2.7104500957721087e-06, + "loss": 3.1843, "step": 285400 }, { - "epoch": 0.94, - "learning_rate": 2.77025998689809e-06, - "loss": 3.2075, + "epoch": 0.95, + "learning_rate": 2.6938805267797375e-06, + "loss": 3.19, "step": 285500 }, { - "epoch": 0.94, - "learning_rate": 2.7537171707814165e-06, - "loss": 3.2211, + "epoch": 0.95, + "learning_rate": 2.6773109577873663e-06, + "loss": 3.1823, "step": 285600 }, { "epoch": 0.95, - "learning_rate": 2.7371743546647436e-06, - "loss": 3.2196, + "learning_rate": 2.6607413887949946e-06, + "loss": 3.1977, "step": 285700 }, { "epoch": 0.95, - "learning_rate": 2.7206315385480702e-06, - "loss": 3.2289, + "learning_rate": 2.6441718198026234e-06, + "loss": 3.2004, "step": 285800 }, { "epoch": 0.95, - "learning_rate": 2.7040887224313973e-06, - "loss": 3.2023, + "learning_rate": 2.6276022508102518e-06, + "loss": 3.2022, "step": 285900 }, { "epoch": 0.95, - "learning_rate": 2.687545906314724e-06, - "loss": 3.2242, + "learning_rate": 2.6110326818178805e-06, + "loss": 3.1907, "step": 286000 }, { "epoch": 0.95, - "learning_rate": 2.6710030901980506e-06, - "loss": 3.2228, + "learning_rate": 2.5944631128255093e-06, + "loss": 3.1913, "step": 286100 }, { "epoch": 0.95, - "learning_rate": 2.6544602740813777e-06, - "loss": 3.2271, + "learning_rate": 2.5778935438331377e-06, + "loss": 3.1965, "step": 286200 }, { "epoch": 0.95, - "learning_rate": 2.6379174579647043e-06, - "loss": 3.211, + "learning_rate": 2.5613239748407665e-06, + "loss": 3.2009, "step": 286300 }, { "epoch": 0.95, - "learning_rate": 2.621374641848031e-06, - "loss": 3.2089, + "learning_rate": 2.5447544058483953e-06, + "loss": 3.1979, "step": 286400 }, { "epoch": 0.95, - "learning_rate": 2.604831825731358e-06, + "learning_rate": 2.528184836856024e-06, "loss": 3.2045, "step": 286500 }, { "epoch": 0.95, - "learning_rate": 2.5882890096146847e-06, - "loss": 3.2121, + "learning_rate": 2.5116152678636524e-06, + "loss": 3.216, "step": 286600 }, { "epoch": 0.95, - "learning_rate": 2.571746193498012e-06, - "loss": 3.2064, + "learning_rate": 2.495045698871281e-06, + "loss": 3.1947, "step": 286700 }, { "epoch": 0.95, - "learning_rate": 2.5552033773813384e-06, - "loss": 3.2231, + "learning_rate": 2.47847612987891e-06, + "loss": 3.2021, "step": 286800 }, { "epoch": 0.95, - "learning_rate": 2.538660561264665e-06, - "loss": 3.2206, + "learning_rate": 2.4619065608865383e-06, + "loss": 3.2067, "step": 286900 }, { "epoch": 0.95, - "learning_rate": 2.522117745147992e-06, - "loss": 3.2181, + "learning_rate": 2.445336991894167e-06, + "loss": 3.2126, "step": 287000 }, { "epoch": 0.95, - "learning_rate": 2.505574929031319e-06, - "loss": 3.2059, + "learning_rate": 2.428767422901796e-06, + "loss": 3.1981, "step": 287100 }, { "epoch": 0.95, - "learning_rate": 2.489032112914646e-06, - "loss": 3.2238, + "learning_rate": 2.4121978539094242e-06, + "loss": 3.2215, "step": 287200 }, { "epoch": 0.95, - "learning_rate": 2.4724892967979726e-06, - "loss": 3.204, + "learning_rate": 2.395628284917053e-06, + "loss": 3.1964, "step": 287300 }, { "epoch": 0.95, - "learning_rate": 2.4559464806812996e-06, - "loss": 3.2031, + "learning_rate": 2.3790587159246814e-06, + "loss": 3.1968, "step": 287400 }, { "epoch": 0.95, - "learning_rate": 2.4394036645646263e-06, - "loss": 3.2129, + "learning_rate": 2.36248914693231e-06, + "loss": 3.1969, "step": 287500 }, { "epoch": 0.95, - "learning_rate": 2.4228608484479534e-06, - "loss": 3.2166, + "learning_rate": 2.345919577939939e-06, + "loss": 3.186, "step": 287600 }, { "epoch": 0.95, - "learning_rate": 2.4063180323312796e-06, - "loss": 3.2136, + "learning_rate": 2.3293500089475673e-06, + "loss": 3.1977, "step": 287700 }, { "epoch": 0.95, - "learning_rate": 2.3897752162146067e-06, - "loss": 3.2167, + "learning_rate": 2.312780439955196e-06, + "loss": 3.1927, "step": 287800 }, { "epoch": 0.95, - "learning_rate": 2.3732324000979333e-06, - "loss": 3.2002, + "learning_rate": 2.2962108709628244e-06, + "loss": 3.1928, "step": 287900 }, { "epoch": 0.95, - "learning_rate": 2.3566895839812604e-06, - "loss": 3.2087, + "learning_rate": 2.2796413019704532e-06, + "loss": 3.1832, "step": 288000 }, { "epoch": 0.95, - "learning_rate": 2.340146767864587e-06, - "loss": 3.2058, + "learning_rate": 2.263071732978082e-06, + "loss": 3.1958, "step": 288100 }, { - "epoch": 0.95, - "learning_rate": 2.323603951747914e-06, - "loss": 3.2142, + "epoch": 0.96, + "learning_rate": 2.2465021639857104e-06, + "loss": 3.1934, "step": 288200 }, { - "epoch": 0.95, - "learning_rate": 2.3070611356312408e-06, - "loss": 3.2121, + "epoch": 0.96, + "learning_rate": 2.229932594993339e-06, + "loss": 3.1973, "step": 288300 }, { - "epoch": 0.95, - "learning_rate": 2.290518319514568e-06, - "loss": 3.2165, + "epoch": 0.96, + "learning_rate": 2.213363026000968e-06, + "loss": 3.2021, "step": 288400 }, { - "epoch": 0.95, - "learning_rate": 2.2739755033978945e-06, - "loss": 3.2133, + "epoch": 0.96, + "learning_rate": 2.1967934570085963e-06, + "loss": 3.2052, "step": 288500 }, { - "epoch": 0.95, - "learning_rate": 2.2574326872812216e-06, - "loss": 3.2224, + "epoch": 0.96, + "learning_rate": 2.180223888016225e-06, + "loss": 3.205, "step": 288600 }, { "epoch": 0.96, - "learning_rate": 2.2408898711645482e-06, - "loss": 3.2014, + "learning_rate": 2.1636543190238534e-06, + "loss": 3.1919, "step": 288700 }, { "epoch": 0.96, - "learning_rate": 2.2243470550478753e-06, - "loss": 3.208, + "learning_rate": 2.147084750031482e-06, + "loss": 3.1802, "step": 288800 }, { "epoch": 0.96, - "learning_rate": 2.2078042389312015e-06, - "loss": 3.2049, + "learning_rate": 2.130515181039111e-06, + "loss": 3.1896, "step": 288900 }, { "epoch": 0.96, - "learning_rate": 2.1912614228145286e-06, - "loss": 3.211, + "learning_rate": 2.1139456120467393e-06, + "loss": 3.1952, "step": 289000 }, { "epoch": 0.96, - "learning_rate": 2.1747186066978553e-06, - "loss": 3.2117, + "learning_rate": 2.097376043054368e-06, + "loss": 3.193, "step": 289100 }, { "epoch": 0.96, - "learning_rate": 2.1581757905811823e-06, - "loss": 3.2105, + "learning_rate": 2.0808064740619965e-06, + "loss": 3.1995, "step": 289200 }, { "epoch": 0.96, - "learning_rate": 2.141632974464509e-06, - "loss": 3.2084, + "learning_rate": 2.0642369050696253e-06, + "loss": 3.1722, "step": 289300 }, { "epoch": 0.96, - "learning_rate": 2.125090158347836e-06, - "loss": 3.2132, + "learning_rate": 2.047667336077254e-06, + "loss": 3.1898, "step": 289400 }, { "epoch": 0.96, - "learning_rate": 2.1085473422311627e-06, - "loss": 3.2126, + "learning_rate": 2.031097767084883e-06, + "loss": 3.1856, "step": 289500 }, { "epoch": 0.96, - "learning_rate": 2.09200452611449e-06, - "loss": 3.2169, + "learning_rate": 2.014528198092511e-06, + "loss": 3.1907, "step": 289600 }, { "epoch": 0.96, - "learning_rate": 2.0754617099978164e-06, - "loss": 3.2065, + "learning_rate": 1.99795862910014e-06, + "loss": 3.2043, "step": 289700 }, { "epoch": 0.96, - "learning_rate": 2.0589188938811435e-06, - "loss": 3.2273, + "learning_rate": 1.9813890601077688e-06, + "loss": 3.1981, "step": 289800 }, { "epoch": 0.96, - "learning_rate": 2.04237607776447e-06, - "loss": 3.2041, + "learning_rate": 1.9648194911153975e-06, + "loss": 3.1953, "step": 289900 }, { "epoch": 0.96, - "learning_rate": 2.0258332616477972e-06, - "loss": 3.2115, + "learning_rate": 1.948249922123026e-06, + "loss": 3.1966, "step": 290000 }, { "epoch": 0.96, - "learning_rate": 2.0092904455311235e-06, - "loss": 3.205, + "learning_rate": 1.9316803531306547e-06, + "loss": 3.195, "step": 290100 }, { "epoch": 0.96, - "learning_rate": 1.9927476294144505e-06, - "loss": 3.2109, + "learning_rate": 1.915110784138283e-06, + "loss": 3.2012, "step": 290200 }, { "epoch": 0.96, - "learning_rate": 1.976204813297777e-06, - "loss": 3.2222, + "learning_rate": 1.8985412151459116e-06, + "loss": 3.187, "step": 290300 }, { "epoch": 0.96, - "learning_rate": 1.9596619971811043e-06, - "loss": 3.2167, + "learning_rate": 1.8819716461535404e-06, + "loss": 3.1955, "step": 290400 }, { "epoch": 0.96, - "learning_rate": 1.943119181064431e-06, - "loss": 3.2184, + "learning_rate": 1.865402077161169e-06, + "loss": 3.2055, "step": 290500 }, { "epoch": 0.96, - "learning_rate": 1.926576364947758e-06, - "loss": 3.2063, + "learning_rate": 1.8488325081687977e-06, + "loss": 3.188, "step": 290600 }, { "epoch": 0.96, - "learning_rate": 1.9100335488310847e-06, - "loss": 3.2064, + "learning_rate": 1.832262939176426e-06, + "loss": 3.1897, "step": 290700 }, { "epoch": 0.96, - "learning_rate": 1.8934907327144115e-06, - "loss": 3.2036, + "learning_rate": 1.8156933701840549e-06, + "loss": 3.1816, "step": 290800 }, { "epoch": 0.96, - "learning_rate": 1.8769479165977384e-06, - "loss": 3.2089, + "learning_rate": 1.7991238011916837e-06, + "loss": 3.1946, "step": 290900 }, { "epoch": 0.96, - "learning_rate": 1.8604051004810652e-06, - "loss": 3.2037, + "learning_rate": 1.782554232199312e-06, + "loss": 3.2138, "step": 291000 }, { "epoch": 0.96, - "learning_rate": 1.8438622843643921e-06, - "loss": 3.2097, + "learning_rate": 1.7659846632069408e-06, + "loss": 3.2028, "step": 291100 }, { - "epoch": 0.96, - "learning_rate": 1.827319468247719e-06, - "loss": 3.2083, + "epoch": 0.97, + "learning_rate": 1.7494150942145692e-06, + "loss": 3.1968, "step": 291200 }, { - "epoch": 0.96, - "learning_rate": 1.8107766521310458e-06, - "loss": 3.2177, + "epoch": 0.97, + "learning_rate": 1.732845525222198e-06, + "loss": 3.1996, "step": 291300 }, { - "epoch": 0.96, - "learning_rate": 1.7942338360143723e-06, - "loss": 3.2059, + "epoch": 0.97, + "learning_rate": 1.7162759562298267e-06, + "loss": 3.1971, "step": 291400 }, { - "epoch": 0.96, - "learning_rate": 1.7776910198976991e-06, - "loss": 3.2141, + "epoch": 0.97, + "learning_rate": 1.699706387237455e-06, + "loss": 3.1903, "step": 291500 }, { - "epoch": 0.96, - "learning_rate": 1.761148203781026e-06, - "loss": 3.2057, + "epoch": 0.97, + "learning_rate": 1.6831368182450839e-06, + "loss": 3.2047, "step": 291600 }, { "epoch": 0.97, - "learning_rate": 1.7446053876643529e-06, - "loss": 3.1882, + "learning_rate": 1.6665672492527124e-06, + "loss": 3.198, "step": 291700 }, { "epoch": 0.97, - "learning_rate": 1.7280625715476797e-06, - "loss": 3.2158, + "learning_rate": 1.649997680260341e-06, + "loss": 3.1874, "step": 291800 }, { "epoch": 0.97, - "learning_rate": 1.7115197554310066e-06, - "loss": 3.2132, + "learning_rate": 1.6334281112679698e-06, + "loss": 3.1945, "step": 291900 }, { "epoch": 0.97, - "learning_rate": 1.6949769393143335e-06, - "loss": 3.2246, + "learning_rate": 1.6168585422755984e-06, + "loss": 3.1789, "step": 292000 }, { "epoch": 0.97, - "learning_rate": 1.6784341231976603e-06, - "loss": 3.2225, + "learning_rate": 1.6002889732832271e-06, + "loss": 3.1932, "step": 292100 }, { "epoch": 0.97, - "learning_rate": 1.6618913070809872e-06, - "loss": 3.216, + "learning_rate": 1.583719404290856e-06, + "loss": 3.1847, "step": 292200 }, { "epoch": 0.97, - "learning_rate": 1.645348490964314e-06, - "loss": 3.2302, + "learning_rate": 1.5671498352984843e-06, + "loss": 3.2007, "step": 292300 }, { "epoch": 0.97, - "learning_rate": 1.628805674847641e-06, - "loss": 3.2145, + "learning_rate": 1.5505802663061129e-06, + "loss": 3.2008, "step": 292400 }, { "epoch": 0.97, - "learning_rate": 1.6122628587309678e-06, - "loss": 3.2149, + "learning_rate": 1.5340106973137416e-06, + "loss": 3.1925, "step": 292500 }, { "epoch": 0.97, - "learning_rate": 1.5957200426142942e-06, - "loss": 3.2058, + "learning_rate": 1.5174411283213702e-06, + "loss": 3.191, "step": 292600 }, { "epoch": 0.97, - "learning_rate": 1.579177226497621e-06, - "loss": 3.2138, + "learning_rate": 1.5008715593289988e-06, + "loss": 3.205, "step": 292700 }, { "epoch": 0.97, - "learning_rate": 1.562634410380948e-06, - "loss": 3.2141, + "learning_rate": 1.4843019903366273e-06, + "loss": 3.1892, "step": 292800 }, { "epoch": 0.97, - "learning_rate": 1.5460915942642748e-06, - "loss": 3.1934, + "learning_rate": 1.4677324213442561e-06, + "loss": 3.1991, "step": 292900 }, { "epoch": 0.97, - "learning_rate": 1.5295487781476017e-06, - "loss": 3.2085, + "learning_rate": 1.4511628523518847e-06, + "loss": 3.1787, "step": 293000 }, { "epoch": 0.97, - "learning_rate": 1.5130059620309285e-06, - "loss": 3.2065, + "learning_rate": 1.4345932833595133e-06, + "loss": 3.189, "step": 293100 }, { "epoch": 0.97, - "learning_rate": 1.4964631459142554e-06, - "loss": 3.2164, + "learning_rate": 1.4180237143671418e-06, + "loss": 3.1957, "step": 293200 }, { "epoch": 0.97, - "learning_rate": 1.4799203297975823e-06, - "loss": 3.2089, + "learning_rate": 1.4014541453747706e-06, + "loss": 3.1977, "step": 293300 }, { "epoch": 0.97, - "learning_rate": 1.4633775136809091e-06, - "loss": 3.2065, + "learning_rate": 1.3848845763823992e-06, + "loss": 3.1947, "step": 293400 }, { "epoch": 0.97, - "learning_rate": 1.4468346975642358e-06, - "loss": 3.2077, + "learning_rate": 1.368315007390028e-06, + "loss": 3.192, "step": 293500 }, { "epoch": 0.97, - "learning_rate": 1.4302918814475627e-06, - "loss": 3.2056, + "learning_rate": 1.3517454383976565e-06, + "loss": 3.1893, "step": 293600 }, { "epoch": 0.97, - "learning_rate": 1.4137490653308895e-06, - "loss": 3.2158, + "learning_rate": 1.3351758694052851e-06, + "loss": 3.195, "step": 293700 }, { "epoch": 0.97, - "learning_rate": 1.3972062492142164e-06, - "loss": 3.208, + "learning_rate": 1.3186063004129137e-06, + "loss": 3.2036, "step": 293800 }, { "epoch": 0.97, - "learning_rate": 1.3806634330975432e-06, - "loss": 3.2034, + "learning_rate": 1.3020367314205425e-06, + "loss": 3.1751, "step": 293900 }, { "epoch": 0.97, - "learning_rate": 1.3641206169808701e-06, - "loss": 3.223, + "learning_rate": 1.285467162428171e-06, + "loss": 3.1862, "step": 294000 }, { "epoch": 0.97, - "learning_rate": 1.3475778008641968e-06, - "loss": 3.1986, + "learning_rate": 1.2688975934357996e-06, + "loss": 3.2041, "step": 294100 }, { "epoch": 0.97, - "learning_rate": 1.3310349847475236e-06, - "loss": 3.213, + "learning_rate": 1.2523280244434282e-06, + "loss": 3.2073, "step": 294200 }, { - "epoch": 0.97, - "learning_rate": 1.3144921686308505e-06, - "loss": 3.2191, + "epoch": 0.98, + "learning_rate": 1.2357584554510567e-06, + "loss": 3.1847, "step": 294300 }, { - "epoch": 0.97, - "learning_rate": 1.2979493525141774e-06, - "loss": 3.2027, + "epoch": 0.98, + "learning_rate": 1.2191888864586855e-06, + "loss": 3.2026, "step": 294400 }, { - "epoch": 0.97, - "learning_rate": 1.2814065363975042e-06, - "loss": 3.2177, + "epoch": 0.98, + "learning_rate": 1.202619317466314e-06, + "loss": 3.1919, "step": 294500 }, { - "epoch": 0.97, - "learning_rate": 1.2648637202808309e-06, - "loss": 3.1982, + "epoch": 0.98, + "learning_rate": 1.1860497484739427e-06, + "loss": 3.1985, "step": 294600 }, { "epoch": 0.98, - "learning_rate": 1.2483209041641577e-06, - "loss": 3.2195, + "learning_rate": 1.1694801794815712e-06, + "loss": 3.2101, "step": 294700 }, { "epoch": 0.98, - "learning_rate": 1.2317780880474846e-06, - "loss": 3.204, + "learning_rate": 1.1529106104892e-06, + "loss": 3.1899, "step": 294800 }, { "epoch": 0.98, - "learning_rate": 1.2152352719308115e-06, - "loss": 3.2043, + "learning_rate": 1.1363410414968286e-06, + "loss": 3.1927, "step": 294900 }, { "epoch": 0.98, - "learning_rate": 1.1986924558141381e-06, - "loss": 3.217, + "learning_rate": 1.1197714725044574e-06, + "loss": 3.1931, "step": 295000 }, { "epoch": 0.98, - "learning_rate": 1.182149639697465e-06, - "loss": 3.2007, + "learning_rate": 1.103201903512086e-06, + "loss": 3.1946, "step": 295100 }, { "epoch": 0.98, - "learning_rate": 1.1656068235807918e-06, - "loss": 3.2129, + "learning_rate": 1.0866323345197145e-06, + "loss": 3.1989, "step": 295200 }, { "epoch": 0.98, - "learning_rate": 1.1490640074641187e-06, - "loss": 3.2117, + "learning_rate": 1.0700627655273433e-06, + "loss": 3.1924, "step": 295300 }, { "epoch": 0.98, - "learning_rate": 1.1325211913474454e-06, - "loss": 3.2091, + "learning_rate": 1.0534931965349719e-06, + "loss": 3.2012, "step": 295400 }, { "epoch": 0.98, - "learning_rate": 1.1159783752307722e-06, - "loss": 3.2112, + "learning_rate": 1.0369236275426004e-06, + "loss": 3.1935, "step": 295500 }, { "epoch": 0.98, - "learning_rate": 1.099435559114099e-06, - "loss": 3.2084, + "learning_rate": 1.020354058550229e-06, + "loss": 3.1971, "step": 295600 }, { "epoch": 0.98, - "learning_rate": 1.082892742997426e-06, - "loss": 3.1951, + "learning_rate": 1.0037844895578576e-06, + "loss": 3.182, "step": 295700 }, { "epoch": 0.98, - "learning_rate": 1.0663499268807528e-06, - "loss": 3.2097, + "learning_rate": 9.872149205654864e-07, + "loss": 3.2003, "step": 295800 }, { "epoch": 0.98, - "learning_rate": 1.0498071107640797e-06, - "loss": 3.22, + "learning_rate": 9.70645351573115e-07, + "loss": 3.1981, "step": 295900 }, { "epoch": 0.98, - "learning_rate": 1.0332642946474063e-06, - "loss": 3.2024, + "learning_rate": 9.540757825807435e-07, + "loss": 3.2116, "step": 296000 }, { "epoch": 0.98, - "learning_rate": 1.0167214785307332e-06, - "loss": 3.214, + "learning_rate": 9.375062135883722e-07, + "loss": 3.1974, "step": 296100 }, { "epoch": 0.98, - "learning_rate": 1.00017866241406e-06, - "loss": 3.2218, + "learning_rate": 9.209366445960007e-07, + "loss": 3.1994, "step": 296200 }, { "epoch": 0.98, - "learning_rate": 9.83635846297387e-07, - "loss": 3.2131, + "learning_rate": 9.043670756036295e-07, + "loss": 3.2025, "step": 296300 }, { "epoch": 0.98, - "learning_rate": 9.670930301807138e-07, - "loss": 3.1993, + "learning_rate": 8.877975066112581e-07, + "loss": 3.1962, "step": 296400 }, { "epoch": 0.98, - "learning_rate": 9.505502140640406e-07, - "loss": 3.2195, + "learning_rate": 8.712279376188867e-07, + "loss": 3.1907, "step": 296500 }, { "epoch": 0.98, - "learning_rate": 9.340073979473674e-07, - "loss": 3.2226, + "learning_rate": 8.546583686265152e-07, + "loss": 3.1928, "step": 296600 }, { "epoch": 0.98, - "learning_rate": 9.174645818306942e-07, - "loss": 3.2104, + "learning_rate": 8.38088799634144e-07, + "loss": 3.1951, "step": 296700 }, { "epoch": 0.98, - "learning_rate": 9.00921765714021e-07, - "loss": 3.2096, + "learning_rate": 8.215192306417726e-07, + "loss": 3.1842, "step": 296800 }, { "epoch": 0.98, - "learning_rate": 8.843789495973479e-07, - "loss": 3.2324, + "learning_rate": 8.049496616494013e-07, + "loss": 3.1921, "step": 296900 }, { "epoch": 0.98, - "learning_rate": 8.678361334806748e-07, - "loss": 3.1977, + "learning_rate": 7.883800926570298e-07, + "loss": 3.1984, "step": 297000 }, { "epoch": 0.98, - "learning_rate": 8.512933173640016e-07, - "loss": 3.2092, + "learning_rate": 7.718105236646585e-07, + "loss": 3.1898, "step": 297100 }, { "epoch": 0.98, - "learning_rate": 8.347505012473283e-07, - "loss": 3.2122, + "learning_rate": 7.552409546722871e-07, + "loss": 3.2005, "step": 297200 }, { - "epoch": 0.98, - "learning_rate": 8.182076851306551e-07, - "loss": 3.222, + "epoch": 0.99, + "learning_rate": 7.386713856799158e-07, + "loss": 3.1964, "step": 297300 }, { - "epoch": 0.98, - "learning_rate": 8.01664869013982e-07, - "loss": 3.2019, + "epoch": 0.99, + "learning_rate": 7.221018166875443e-07, + "loss": 3.1889, "step": 297400 }, { - "epoch": 0.98, - "learning_rate": 7.851220528973089e-07, - "loss": 3.2155, + "epoch": 0.99, + "learning_rate": 7.055322476951729e-07, + "loss": 3.2061, "step": 297500 }, { - "epoch": 0.98, - "learning_rate": 7.685792367806356e-07, - "loss": 3.2188, + "epoch": 0.99, + "learning_rate": 6.889626787028016e-07, + "loss": 3.1963, "step": 297600 }, { - "epoch": 0.98, - "learning_rate": 7.520364206639625e-07, - "loss": 3.2055, + "epoch": 0.99, + "learning_rate": 6.723931097104303e-07, + "loss": 3.1858, "step": 297700 }, { "epoch": 0.99, - "learning_rate": 7.354936045472893e-07, - "loss": 3.227, + "learning_rate": 6.558235407180589e-07, + "loss": 3.1937, "step": 297800 }, { "epoch": 0.99, - "learning_rate": 7.189507884306161e-07, - "loss": 3.2068, + "learning_rate": 6.392539717256875e-07, + "loss": 3.1931, "step": 297900 }, { "epoch": 0.99, - "learning_rate": 7.02407972313943e-07, - "loss": 3.2258, + "learning_rate": 6.226844027333162e-07, + "loss": 3.1911, "step": 298000 }, { "epoch": 0.99, - "learning_rate": 6.858651561972698e-07, - "loss": 3.2147, + "learning_rate": 6.061148337409447e-07, + "loss": 3.1961, "step": 298100 }, { "epoch": 0.99, - "learning_rate": 6.693223400805967e-07, - "loss": 3.2091, + "learning_rate": 5.895452647485733e-07, + "loss": 3.2042, "step": 298200 }, { "epoch": 0.99, - "learning_rate": 6.527795239639235e-07, - "loss": 3.2025, + "learning_rate": 5.72975695756202e-07, + "loss": 3.1891, "step": 298300 }, { "epoch": 0.99, - "learning_rate": 6.362367078472503e-07, - "loss": 3.22, + "learning_rate": 5.564061267638307e-07, + "loss": 3.1903, "step": 298400 }, { "epoch": 0.99, - "learning_rate": 6.196938917305772e-07, - "loss": 3.2106, + "learning_rate": 5.398365577714593e-07, + "loss": 3.202, "step": 298500 }, { "epoch": 0.99, - "learning_rate": 6.031510756139039e-07, - "loss": 3.215, + "learning_rate": 5.232669887790879e-07, + "loss": 3.1893, "step": 298600 }, { "epoch": 0.99, - "learning_rate": 5.866082594972308e-07, - "loss": 3.2134, + "learning_rate": 5.066974197867166e-07, + "loss": 3.1945, "step": 298700 }, { "epoch": 0.99, - "learning_rate": 5.700654433805577e-07, - "loss": 3.2006, + "learning_rate": 4.901278507943452e-07, + "loss": 3.1845, "step": 298800 }, { "epoch": 0.99, - "learning_rate": 5.535226272638844e-07, - "loss": 3.2093, + "learning_rate": 4.735582818019738e-07, + "loss": 3.1887, "step": 298900 }, { "epoch": 0.99, - "learning_rate": 5.369798111472113e-07, - "loss": 3.219, + "learning_rate": 4.5698871280960246e-07, + "loss": 3.1914, "step": 299000 }, { "epoch": 0.99, - "learning_rate": 5.20436995030538e-07, - "loss": 3.2185, + "learning_rate": 4.4041914381723103e-07, + "loss": 3.1897, "step": 299100 }, { "epoch": 0.99, - "learning_rate": 5.038941789138649e-07, - "loss": 3.2186, + "learning_rate": 4.238495748248597e-07, + "loss": 3.1971, "step": 299200 }, { "epoch": 0.99, - "learning_rate": 4.873513627971917e-07, - "loss": 3.2104, + "learning_rate": 4.072800058324883e-07, + "loss": 3.1771, "step": 299300 }, { "epoch": 0.99, - "learning_rate": 4.708085466805186e-07, - "loss": 3.2135, + "learning_rate": 3.907104368401169e-07, + "loss": 3.2013, "step": 299400 }, { "epoch": 0.99, - "learning_rate": 4.5426573056384535e-07, - "loss": 3.2173, + "learning_rate": 3.741408678477456e-07, + "loss": 3.2098, "step": 299500 }, { "epoch": 0.99, - "learning_rate": 4.377229144471722e-07, - "loss": 3.2153, + "learning_rate": 3.575712988553742e-07, + "loss": 3.2141, "step": 299600 }, { "epoch": 0.99, - "learning_rate": 4.211800983304991e-07, - "loss": 3.2024, + "learning_rate": 3.410017298630028e-07, + "loss": 3.1915, "step": 299700 }, { "epoch": 0.99, - "learning_rate": 4.0463728221382583e-07, - "loss": 3.2402, + "learning_rate": 3.2443216087063145e-07, + "loss": 3.1944, "step": 299800 }, { "epoch": 0.99, - "learning_rate": 3.880944660971527e-07, - "loss": 3.1929, + "learning_rate": 3.0786259187826007e-07, + "loss": 3.2052, "step": 299900 }, { "epoch": 0.99, - "learning_rate": 3.715516499804795e-07, - "loss": 3.2123, + "learning_rate": 2.912930228858887e-07, + "loss": 3.1782, "step": 300000 }, { "epoch": 0.99, - "learning_rate": 3.550088338638063e-07, - "loss": 3.2161, + "learning_rate": 2.747234538935173e-07, + "loss": 3.2006, "step": 300100 }, { "epoch": 0.99, - "learning_rate": 3.3846601774713313e-07, - "loss": 3.2216, + "learning_rate": 2.58153884901146e-07, + "loss": 3.2034, "step": 300200 }, { - "epoch": 0.99, - "learning_rate": 3.2192320163045994e-07, - "loss": 3.2204, + "epoch": 1.0, + "learning_rate": 2.415843159087746e-07, + "loss": 3.1802, "step": 300300 }, { - "epoch": 0.99, - "learning_rate": 3.053803855137868e-07, - "loss": 3.2127, + "epoch": 1.0, + "learning_rate": 2.250147469164032e-07, + "loss": 3.1951, "step": 300400 }, { - "epoch": 0.99, - "learning_rate": 2.888375693971136e-07, - "loss": 3.2248, + "epoch": 1.0, + "learning_rate": 2.0844517792403183e-07, + "loss": 3.2002, "step": 300500 }, { - "epoch": 0.99, - "learning_rate": 2.7229475328044043e-07, - "loss": 3.2068, + "epoch": 1.0, + "learning_rate": 1.9187560893166048e-07, + "loss": 3.2057, "step": 300600 }, { - "epoch": 0.99, - "learning_rate": 2.557519371637673e-07, - "loss": 3.2173, + "epoch": 1.0, + "learning_rate": 1.753060399392891e-07, + "loss": 3.1817, "step": 300700 }, { "epoch": 1.0, - "learning_rate": 2.392091210470941e-07, - "loss": 3.223, + "learning_rate": 1.5873647094691776e-07, + "loss": 3.1965, "step": 300800 }, { "epoch": 1.0, - "learning_rate": 2.2266630493042091e-07, - "loss": 3.2024, + "learning_rate": 1.4216690195454635e-07, + "loss": 3.1806, "step": 300900 }, { "epoch": 1.0, - "learning_rate": 2.0612348881374775e-07, - "loss": 3.2027, + "learning_rate": 1.25597332962175e-07, + "loss": 3.2019, "step": 301000 }, { "epoch": 1.0, - "learning_rate": 1.8958067269707456e-07, - "loss": 3.2021, + "learning_rate": 1.0902776396980363e-07, + "loss": 3.1854, "step": 301100 }, { "epoch": 1.0, - "learning_rate": 1.730378565804014e-07, - "loss": 3.208, + "learning_rate": 9.245819497743225e-08, + "loss": 3.1878, "step": 301200 }, { "epoch": 1.0, - "learning_rate": 1.5649504046372824e-07, - "loss": 3.2202, + "learning_rate": 7.588862598506089e-08, + "loss": 3.1899, "step": 301300 }, { "epoch": 1.0, - "learning_rate": 1.3995222434705505e-07, - "loss": 3.216, + "learning_rate": 5.93190569926895e-08, + "loss": 3.1923, "step": 301400 }, { "epoch": 1.0, - "learning_rate": 1.2340940823038189e-07, - "loss": 3.214, + "learning_rate": 4.274948800031814e-08, + "loss": 3.2046, "step": 301500 - }, - { - "epoch": 1.0, - "learning_rate": 1.0686659211370871e-07, - "loss": 3.2043, - "step": 301600 - }, - { - "epoch": 1.0, - "learning_rate": 9.032377599703553e-08, - "loss": 3.2183, - "step": 301700 - }, - { - "epoch": 1.0, - "learning_rate": 7.378095988036236e-08, - "loss": 3.2225, - "step": 301800 - }, - { - "epoch": 1.0, - "learning_rate": 5.723814376368919e-08, - "loss": 3.2166, - "step": 301900 - }, - { - "epoch": 1.0, - "learning_rate": 4.0695327647016006e-08, - "loss": 3.2158, - "step": 302000 } ], - "max_steps": 302246, + "max_steps": 301758, "num_train_epochs": 1, - "total_flos": 2.580120367792128e+18, + "total_flos": 2.575848645328896e+18, "trial_name": null, "trial_params": null }