alex-gpt-L / trainer_state.json
danurahul's picture
Initial commit
c276d13
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 131.21924548933845,
"global_step": 480000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.14,
"learning_rate": 5e-05,
"loss": 3.4081,
"step": 500
},
{
"epoch": 0.27,
"learning_rate": 4.999316473000684e-05,
"loss": 3.3326,
"step": 1000
},
{
"epoch": 0.41,
"learning_rate": 4.998632946001368e-05,
"loss": 3.3069,
"step": 1500
},
{
"epoch": 0.55,
"learning_rate": 4.997949419002051e-05,
"loss": 3.2839,
"step": 2000
},
{
"epoch": 0.68,
"learning_rate": 4.997265892002734e-05,
"loss": 3.2691,
"step": 2500
},
{
"epoch": 0.82,
"learning_rate": 4.9965823650034176e-05,
"loss": 3.2595,
"step": 3000
},
{
"epoch": 0.96,
"learning_rate": 4.995898838004102e-05,
"loss": 3.2534,
"step": 3500
},
{
"epoch": 1.09,
"learning_rate": 4.995215311004785e-05,
"loss": 3.2124,
"step": 4000
},
{
"epoch": 1.23,
"learning_rate": 4.994531784005468e-05,
"loss": 3.1981,
"step": 4500
},
{
"epoch": 1.37,
"learning_rate": 4.9938482570061516e-05,
"loss": 3.193,
"step": 5000
},
{
"epoch": 1.5,
"learning_rate": 4.993164730006836e-05,
"loss": 3.1885,
"step": 5500
},
{
"epoch": 1.64,
"learning_rate": 4.992481203007519e-05,
"loss": 3.1881,
"step": 6000
},
{
"epoch": 1.78,
"learning_rate": 4.991797676008203e-05,
"loss": 3.192,
"step": 6500
},
{
"epoch": 1.91,
"learning_rate": 4.991114149008886e-05,
"loss": 3.181,
"step": 7000
},
{
"epoch": 2.05,
"learning_rate": 4.9904306220095696e-05,
"loss": 3.1629,
"step": 7500
},
{
"epoch": 2.19,
"learning_rate": 4.989747095010253e-05,
"loss": 3.139,
"step": 8000
},
{
"epoch": 2.32,
"learning_rate": 4.9890635680109366e-05,
"loss": 3.1355,
"step": 8500
},
{
"epoch": 2.46,
"learning_rate": 4.98838004101162e-05,
"loss": 3.1403,
"step": 9000
},
{
"epoch": 2.6,
"learning_rate": 4.9876965140123035e-05,
"loss": 3.1403,
"step": 9500
},
{
"epoch": 2.73,
"learning_rate": 4.987012987012987e-05,
"loss": 3.1366,
"step": 10000
},
{
"epoch": 2.87,
"learning_rate": 4.9863294600136705e-05,
"loss": 3.1378,
"step": 10500
},
{
"epoch": 3.01,
"learning_rate": 4.985645933014355e-05,
"loss": 3.132,
"step": 11000
},
{
"epoch": 3.14,
"learning_rate": 4.984962406015038e-05,
"loss": 3.0939,
"step": 11500
},
{
"epoch": 3.28,
"learning_rate": 4.9842788790157216e-05,
"loss": 3.0984,
"step": 12000
},
{
"epoch": 3.42,
"learning_rate": 4.9835953520164044e-05,
"loss": 3.0947,
"step": 12500
},
{
"epoch": 3.55,
"learning_rate": 4.9829118250170886e-05,
"loss": 3.099,
"step": 13000
},
{
"epoch": 3.69,
"learning_rate": 4.982228298017772e-05,
"loss": 3.1002,
"step": 13500
},
{
"epoch": 3.83,
"learning_rate": 4.9815447710184555e-05,
"loss": 3.0929,
"step": 14000
},
{
"epoch": 3.96,
"learning_rate": 4.980861244019139e-05,
"loss": 3.1047,
"step": 14500
},
{
"epoch": 4.1,
"learning_rate": 4.9801777170198225e-05,
"loss": 3.0691,
"step": 15000
},
{
"epoch": 4.24,
"learning_rate": 4.979494190020506e-05,
"loss": 3.0629,
"step": 15500
},
{
"epoch": 4.37,
"learning_rate": 4.9788106630211895e-05,
"loss": 3.0655,
"step": 16000
},
{
"epoch": 4.51,
"learning_rate": 4.978127136021873e-05,
"loss": 3.0679,
"step": 16500
},
{
"epoch": 4.65,
"learning_rate": 4.977443609022557e-05,
"loss": 3.063,
"step": 17000
},
{
"epoch": 4.78,
"learning_rate": 4.97676008202324e-05,
"loss": 3.065,
"step": 17500
},
{
"epoch": 4.92,
"learning_rate": 4.9760765550239234e-05,
"loss": 3.0706,
"step": 18000
},
{
"epoch": 5.06,
"learning_rate": 4.975393028024607e-05,
"loss": 3.0469,
"step": 18500
},
{
"epoch": 5.19,
"learning_rate": 4.974709501025291e-05,
"loss": 3.0315,
"step": 19000
},
{
"epoch": 5.33,
"learning_rate": 4.9740259740259745e-05,
"loss": 3.0287,
"step": 19500
},
{
"epoch": 5.47,
"learning_rate": 4.973342447026658e-05,
"loss": 3.0319,
"step": 20000
},
{
"epoch": 5.6,
"learning_rate": 4.9726589200273414e-05,
"loss": 3.0376,
"step": 20500
},
{
"epoch": 5.74,
"learning_rate": 4.971975393028025e-05,
"loss": 3.0405,
"step": 21000
},
{
"epoch": 5.88,
"learning_rate": 4.9712918660287084e-05,
"loss": 3.0393,
"step": 21500
},
{
"epoch": 6.01,
"learning_rate": 4.970608339029392e-05,
"loss": 3.0358,
"step": 22000
},
{
"epoch": 6.15,
"learning_rate": 4.9699248120300754e-05,
"loss": 3.0,
"step": 22500
},
{
"epoch": 6.29,
"learning_rate": 4.969241285030759e-05,
"loss": 3.0069,
"step": 23000
},
{
"epoch": 6.42,
"learning_rate": 4.968557758031442e-05,
"loss": 3.0053,
"step": 23500
},
{
"epoch": 6.56,
"learning_rate": 4.967874231032126e-05,
"loss": 3.0082,
"step": 24000
},
{
"epoch": 6.7,
"learning_rate": 4.96719070403281e-05,
"loss": 3.0102,
"step": 24500
},
{
"epoch": 6.83,
"learning_rate": 4.9665071770334934e-05,
"loss": 3.017,
"step": 25000
},
{
"epoch": 6.97,
"learning_rate": 4.965823650034176e-05,
"loss": 3.0128,
"step": 25500
},
{
"epoch": 7.11,
"learning_rate": 4.96514012303486e-05,
"loss": 2.9722,
"step": 26000
},
{
"epoch": 7.24,
"learning_rate": 4.964456596035544e-05,
"loss": 2.9764,
"step": 26500
},
{
"epoch": 7.38,
"learning_rate": 4.9637730690362274e-05,
"loss": 2.9836,
"step": 27000
},
{
"epoch": 7.52,
"learning_rate": 4.963089542036911e-05,
"loss": 2.9837,
"step": 27500
},
{
"epoch": 7.65,
"learning_rate": 4.9624060150375936e-05,
"loss": 2.9803,
"step": 28000
},
{
"epoch": 7.79,
"learning_rate": 4.961722488038278e-05,
"loss": 2.9923,
"step": 28500
},
{
"epoch": 7.93,
"learning_rate": 4.961038961038961e-05,
"loss": 2.9973,
"step": 29000
},
{
"epoch": 8.06,
"learning_rate": 4.960355434039645e-05,
"loss": 2.9631,
"step": 29500
},
{
"epoch": 8.2,
"learning_rate": 4.959671907040329e-05,
"loss": 2.9481,
"step": 30000
},
{
"epoch": 8.34,
"learning_rate": 4.958988380041012e-05,
"loss": 2.9594,
"step": 30500
},
{
"epoch": 8.47,
"learning_rate": 4.958304853041695e-05,
"loss": 2.9552,
"step": 31000
},
{
"epoch": 8.61,
"learning_rate": 4.957621326042379e-05,
"loss": 2.9616,
"step": 31500
},
{
"epoch": 8.75,
"learning_rate": 4.956937799043063e-05,
"loss": 2.9692,
"step": 32000
},
{
"epoch": 8.88,
"learning_rate": 4.956254272043746e-05,
"loss": 2.9657,
"step": 32500
},
{
"epoch": 9.02,
"learning_rate": 4.955570745044429e-05,
"loss": 2.9617,
"step": 33000
},
{
"epoch": 9.16,
"learning_rate": 4.9548872180451126e-05,
"loss": 2.9246,
"step": 33500
},
{
"epoch": 9.29,
"learning_rate": 4.954203691045797e-05,
"loss": 2.9305,
"step": 34000
},
{
"epoch": 9.43,
"learning_rate": 4.95352016404648e-05,
"loss": 2.9364,
"step": 34500
},
{
"epoch": 9.57,
"learning_rate": 4.952836637047164e-05,
"loss": 2.9419,
"step": 35000
},
{
"epoch": 9.7,
"learning_rate": 4.952153110047847e-05,
"loss": 2.9498,
"step": 35500
},
{
"epoch": 9.84,
"learning_rate": 4.951469583048531e-05,
"loss": 2.9423,
"step": 36000
},
{
"epoch": 9.98,
"learning_rate": 4.950786056049214e-05,
"loss": 2.9388,
"step": 36500
},
{
"epoch": 10.11,
"learning_rate": 4.9501025290498976e-05,
"loss": 2.908,
"step": 37000
},
{
"epoch": 10.25,
"learning_rate": 4.949419002050582e-05,
"loss": 2.9081,
"step": 37500
},
{
"epoch": 10.39,
"learning_rate": 4.9487354750512646e-05,
"loss": 2.9072,
"step": 38000
},
{
"epoch": 10.52,
"learning_rate": 4.948051948051948e-05,
"loss": 2.9194,
"step": 38500
},
{
"epoch": 10.66,
"learning_rate": 4.9473684210526315e-05,
"loss": 2.9226,
"step": 39000
},
{
"epoch": 10.8,
"learning_rate": 4.946684894053316e-05,
"loss": 2.9242,
"step": 39500
},
{
"epoch": 10.93,
"learning_rate": 4.946001367053999e-05,
"loss": 2.9218,
"step": 40000
},
{
"epoch": 11.07,
"learning_rate": 4.9453178400546827e-05,
"loss": 2.9096,
"step": 40500
},
{
"epoch": 11.21,
"learning_rate": 4.9446343130553655e-05,
"loss": 2.8805,
"step": 41000
},
{
"epoch": 11.34,
"learning_rate": 4.9439507860560496e-05,
"loss": 2.8983,
"step": 41500
},
{
"epoch": 11.48,
"learning_rate": 4.943267259056733e-05,
"loss": 2.8895,
"step": 42000
},
{
"epoch": 11.62,
"learning_rate": 4.9425837320574166e-05,
"loss": 2.902,
"step": 42500
},
{
"epoch": 11.76,
"learning_rate": 4.9419002050581e-05,
"loss": 2.9048,
"step": 43000
},
{
"epoch": 11.89,
"learning_rate": 4.9412166780587835e-05,
"loss": 2.901,
"step": 43500
},
{
"epoch": 12.03,
"learning_rate": 4.940533151059467e-05,
"loss": 2.8931,
"step": 44000
},
{
"epoch": 12.17,
"learning_rate": 4.9398496240601505e-05,
"loss": 2.8609,
"step": 44500
},
{
"epoch": 12.3,
"learning_rate": 4.939166097060834e-05,
"loss": 2.8731,
"step": 45000
},
{
"epoch": 12.44,
"learning_rate": 4.938482570061518e-05,
"loss": 2.8695,
"step": 45500
},
{
"epoch": 12.58,
"learning_rate": 4.937799043062201e-05,
"loss": 2.8803,
"step": 46000
},
{
"epoch": 12.71,
"learning_rate": 4.9371155160628844e-05,
"loss": 2.8834,
"step": 46500
},
{
"epoch": 12.85,
"learning_rate": 4.9364319890635686e-05,
"loss": 2.8884,
"step": 47000
},
{
"epoch": 12.99,
"learning_rate": 4.935748462064252e-05,
"loss": 2.8881,
"step": 47500
},
{
"epoch": 13.12,
"learning_rate": 4.9350649350649355e-05,
"loss": 2.8503,
"step": 48000
},
{
"epoch": 13.26,
"learning_rate": 4.934381408065618e-05,
"loss": 2.85,
"step": 48500
},
{
"epoch": 13.4,
"learning_rate": 4.9336978810663025e-05,
"loss": 2.8592,
"step": 49000
},
{
"epoch": 13.53,
"learning_rate": 4.933014354066986e-05,
"loss": 2.8528,
"step": 49500
},
{
"epoch": 13.67,
"learning_rate": 4.9323308270676694e-05,
"loss": 2.864,
"step": 50000
},
{
"epoch": 13.81,
"learning_rate": 4.931647300068353e-05,
"loss": 2.8593,
"step": 50500
},
{
"epoch": 13.94,
"learning_rate": 4.9309637730690364e-05,
"loss": 2.8678,
"step": 51000
},
{
"epoch": 14.08,
"learning_rate": 4.93028024606972e-05,
"loss": 2.846,
"step": 51500
},
{
"epoch": 14.22,
"learning_rate": 4.9295967190704034e-05,
"loss": 2.827,
"step": 52000
},
{
"epoch": 14.35,
"learning_rate": 4.928913192071087e-05,
"loss": 2.8338,
"step": 52500
},
{
"epoch": 14.49,
"learning_rate": 4.928229665071771e-05,
"loss": 2.835,
"step": 53000
},
{
"epoch": 14.63,
"learning_rate": 4.927546138072454e-05,
"loss": 2.8436,
"step": 53500
},
{
"epoch": 14.76,
"learning_rate": 4.926862611073137e-05,
"loss": 2.8503,
"step": 54000
},
{
"epoch": 14.9,
"learning_rate": 4.926179084073821e-05,
"loss": 2.8494,
"step": 54500
},
{
"epoch": 15.04,
"learning_rate": 4.925495557074505e-05,
"loss": 2.8412,
"step": 55000
},
{
"epoch": 15.17,
"learning_rate": 4.9248120300751884e-05,
"loss": 2.8029,
"step": 55500
},
{
"epoch": 15.31,
"learning_rate": 4.924128503075872e-05,
"loss": 2.8143,
"step": 56000
},
{
"epoch": 15.45,
"learning_rate": 4.9234449760765553e-05,
"loss": 2.8192,
"step": 56500
},
{
"epoch": 15.58,
"learning_rate": 4.922761449077239e-05,
"loss": 2.827,
"step": 57000
},
{
"epoch": 15.72,
"learning_rate": 4.922077922077922e-05,
"loss": 2.8304,
"step": 57500
},
{
"epoch": 15.86,
"learning_rate": 4.921394395078606e-05,
"loss": 2.836,
"step": 58000
},
{
"epoch": 15.99,
"learning_rate": 4.920710868079289e-05,
"loss": 2.8319,
"step": 58500
},
{
"epoch": 16.13,
"learning_rate": 4.920027341079973e-05,
"loss": 2.7878,
"step": 59000
},
{
"epoch": 16.27,
"learning_rate": 4.919343814080656e-05,
"loss": 2.7968,
"step": 59500
},
{
"epoch": 16.4,
"learning_rate": 4.91866028708134e-05,
"loss": 2.8051,
"step": 60000
},
{
"epoch": 16.54,
"learning_rate": 4.917976760082024e-05,
"loss": 2.806,
"step": 60500
},
{
"epoch": 16.68,
"learning_rate": 4.9172932330827073e-05,
"loss": 2.8105,
"step": 61000
},
{
"epoch": 16.81,
"learning_rate": 4.91660970608339e-05,
"loss": 2.8127,
"step": 61500
},
{
"epoch": 16.95,
"learning_rate": 4.9159261790840736e-05,
"loss": 2.8156,
"step": 62000
},
{
"epoch": 17.09,
"learning_rate": 4.915242652084758e-05,
"loss": 2.7902,
"step": 62500
},
{
"epoch": 17.22,
"learning_rate": 4.914559125085441e-05,
"loss": 2.7727,
"step": 63000
},
{
"epoch": 17.36,
"learning_rate": 4.913875598086125e-05,
"loss": 2.7824,
"step": 63500
},
{
"epoch": 17.5,
"learning_rate": 4.913192071086808e-05,
"loss": 2.7957,
"step": 64000
},
{
"epoch": 17.63,
"learning_rate": 4.912508544087492e-05,
"loss": 2.7884,
"step": 64500
},
{
"epoch": 17.77,
"learning_rate": 4.911825017088175e-05,
"loss": 2.7978,
"step": 65000
},
{
"epoch": 17.91,
"learning_rate": 4.9111414900888587e-05,
"loss": 2.7943,
"step": 65500
},
{
"epoch": 18.04,
"learning_rate": 4.910457963089543e-05,
"loss": 2.7887,
"step": 66000
},
{
"epoch": 18.18,
"learning_rate": 4.9097744360902256e-05,
"loss": 2.7575,
"step": 66500
},
{
"epoch": 18.32,
"learning_rate": 4.909090909090909e-05,
"loss": 2.7736,
"step": 67000
},
{
"epoch": 18.45,
"learning_rate": 4.9084073820915926e-05,
"loss": 2.7681,
"step": 67500
},
{
"epoch": 18.59,
"learning_rate": 4.907723855092277e-05,
"loss": 2.7729,
"step": 68000
},
{
"epoch": 18.73,
"learning_rate": 4.90704032809296e-05,
"loss": 2.7782,
"step": 68500
},
{
"epoch": 18.86,
"learning_rate": 4.906356801093644e-05,
"loss": 2.7764,
"step": 69000
},
{
"epoch": 19.0,
"learning_rate": 4.9056732740943265e-05,
"loss": 2.7843,
"step": 69500
},
{
"epoch": 19.14,
"learning_rate": 4.9049897470950106e-05,
"loss": 2.7397,
"step": 70000
},
{
"epoch": 19.27,
"learning_rate": 4.904306220095694e-05,
"loss": 2.7439,
"step": 70500
},
{
"epoch": 19.41,
"learning_rate": 4.9036226930963776e-05,
"loss": 2.7504,
"step": 71000
},
{
"epoch": 19.55,
"learning_rate": 4.902939166097061e-05,
"loss": 2.7516,
"step": 71500
},
{
"epoch": 19.68,
"learning_rate": 4.9022556390977446e-05,
"loss": 2.7612,
"step": 72000
},
{
"epoch": 19.82,
"learning_rate": 4.901572112098428e-05,
"loss": 2.7767,
"step": 72500
},
{
"epoch": 19.96,
"learning_rate": 4.9008885850991115e-05,
"loss": 2.7686,
"step": 73000
},
{
"epoch": 20.09,
"learning_rate": 4.900205058099795e-05,
"loss": 2.7407,
"step": 73500
},
{
"epoch": 20.23,
"learning_rate": 4.899521531100479e-05,
"loss": 2.7337,
"step": 74000
},
{
"epoch": 20.37,
"learning_rate": 4.898838004101162e-05,
"loss": 2.7353,
"step": 74500
},
{
"epoch": 20.5,
"learning_rate": 4.8981544771018454e-05,
"loss": 2.7383,
"step": 75000
},
{
"epoch": 20.64,
"learning_rate": 4.8974709501025296e-05,
"loss": 2.7409,
"step": 75500
},
{
"epoch": 20.78,
"learning_rate": 4.896787423103213e-05,
"loss": 2.7497,
"step": 76000
},
{
"epoch": 20.91,
"learning_rate": 4.8961038961038966e-05,
"loss": 2.7512,
"step": 76500
},
{
"epoch": 21.05,
"learning_rate": 4.8954203691045794e-05,
"loss": 2.7381,
"step": 77000
},
{
"epoch": 21.19,
"learning_rate": 4.8947368421052635e-05,
"loss": 2.7097,
"step": 77500
},
{
"epoch": 21.32,
"learning_rate": 4.894053315105947e-05,
"loss": 2.7176,
"step": 78000
},
{
"epoch": 21.46,
"learning_rate": 4.8933697881066305e-05,
"loss": 2.7187,
"step": 78500
},
{
"epoch": 21.6,
"learning_rate": 4.892686261107314e-05,
"loss": 2.7352,
"step": 79000
},
{
"epoch": 21.73,
"learning_rate": 4.8920027341079974e-05,
"loss": 2.7303,
"step": 79500
},
{
"epoch": 21.87,
"learning_rate": 4.891319207108681e-05,
"loss": 2.7415,
"step": 80000
},
{
"epoch": 22.01,
"learning_rate": 4.8906356801093644e-05,
"loss": 2.7364,
"step": 80500
},
{
"epoch": 22.14,
"learning_rate": 4.889952153110048e-05,
"loss": 2.6864,
"step": 81000
},
{
"epoch": 22.28,
"learning_rate": 4.889268626110732e-05,
"loss": 2.7004,
"step": 81500
},
{
"epoch": 22.42,
"learning_rate": 4.888585099111415e-05,
"loss": 2.711,
"step": 82000
},
{
"epoch": 22.55,
"learning_rate": 4.887901572112098e-05,
"loss": 2.715,
"step": 82500
},
{
"epoch": 22.69,
"learning_rate": 4.887218045112782e-05,
"loss": 2.7135,
"step": 83000
},
{
"epoch": 22.83,
"learning_rate": 4.886534518113466e-05,
"loss": 2.725,
"step": 83500
},
{
"epoch": 22.96,
"learning_rate": 4.8858509911141494e-05,
"loss": 2.7299,
"step": 84000
},
{
"epoch": 23.1,
"learning_rate": 4.885167464114833e-05,
"loss": 2.693,
"step": 84500
},
{
"epoch": 23.24,
"learning_rate": 4.8844839371155164e-05,
"loss": 2.6783,
"step": 85000
},
{
"epoch": 23.37,
"learning_rate": 4.8838004101162e-05,
"loss": 2.6938,
"step": 85500
},
{
"epoch": 23.51,
"learning_rate": 4.8831168831168833e-05,
"loss": 2.6966,
"step": 86000
},
{
"epoch": 23.65,
"learning_rate": 4.882433356117567e-05,
"loss": 2.693,
"step": 86500
},
{
"epoch": 23.78,
"learning_rate": 4.88174982911825e-05,
"loss": 2.7088,
"step": 87000
},
{
"epoch": 23.92,
"learning_rate": 4.881066302118934e-05,
"loss": 2.7103,
"step": 87500
},
{
"epoch": 24.06,
"learning_rate": 4.880382775119617e-05,
"loss": 2.6963,
"step": 88000
},
{
"epoch": 24.19,
"learning_rate": 4.879699248120301e-05,
"loss": 2.6712,
"step": 88500
},
{
"epoch": 24.33,
"learning_rate": 4.879015721120985e-05,
"loss": 2.6773,
"step": 89000
},
{
"epoch": 24.47,
"learning_rate": 4.8783321941216684e-05,
"loss": 2.6801,
"step": 89500
},
{
"epoch": 24.6,
"learning_rate": 4.877648667122351e-05,
"loss": 2.6889,
"step": 90000
},
{
"epoch": 24.74,
"learning_rate": 4.8769651401230347e-05,
"loss": 2.6861,
"step": 90500
},
{
"epoch": 24.88,
"learning_rate": 4.876281613123719e-05,
"loss": 2.693,
"step": 91000
},
{
"epoch": 25.01,
"learning_rate": 4.875598086124402e-05,
"loss": 2.6889,
"step": 91500
},
{
"epoch": 25.15,
"learning_rate": 4.874914559125086e-05,
"loss": 2.6434,
"step": 92000
},
{
"epoch": 25.29,
"learning_rate": 4.874231032125769e-05,
"loss": 2.6558,
"step": 92500
},
{
"epoch": 25.42,
"learning_rate": 4.873547505126453e-05,
"loss": 2.6626,
"step": 93000
},
{
"epoch": 25.56,
"learning_rate": 4.872863978127136e-05,
"loss": 2.6769,
"step": 93500
},
{
"epoch": 25.7,
"learning_rate": 4.87218045112782e-05,
"loss": 2.6742,
"step": 94000
},
{
"epoch": 25.83,
"learning_rate": 4.871496924128504e-05,
"loss": 2.6876,
"step": 94500
},
{
"epoch": 25.97,
"learning_rate": 4.8708133971291866e-05,
"loss": 2.6842,
"step": 95000
},
{
"epoch": 26.11,
"learning_rate": 4.87012987012987e-05,
"loss": 2.6463,
"step": 95500
},
{
"epoch": 26.24,
"learning_rate": 4.8694463431305536e-05,
"loss": 2.6453,
"step": 96000
},
{
"epoch": 26.38,
"learning_rate": 4.868762816131238e-05,
"loss": 2.6473,
"step": 96500
},
{
"epoch": 26.52,
"learning_rate": 4.868079289131921e-05,
"loss": 2.657,
"step": 97000
},
{
"epoch": 26.65,
"learning_rate": 4.867395762132605e-05,
"loss": 2.6645,
"step": 97500
},
{
"epoch": 26.79,
"learning_rate": 4.8667122351332875e-05,
"loss": 2.6612,
"step": 98000
},
{
"epoch": 26.93,
"learning_rate": 4.866028708133972e-05,
"loss": 2.6681,
"step": 98500
},
{
"epoch": 27.06,
"learning_rate": 4.865345181134655e-05,
"loss": 2.6451,
"step": 99000
},
{
"epoch": 27.2,
"learning_rate": 4.8646616541353386e-05,
"loss": 2.6271,
"step": 99500
},
{
"epoch": 27.34,
"learning_rate": 4.863978127136022e-05,
"loss": 2.6303,
"step": 100000
},
{
"epoch": 27.47,
"learning_rate": 4.8632946001367056e-05,
"loss": 2.6439,
"step": 100500
},
{
"epoch": 27.61,
"learning_rate": 4.862611073137389e-05,
"loss": 2.6458,
"step": 101000
},
{
"epoch": 27.75,
"learning_rate": 4.8619275461380726e-05,
"loss": 2.6524,
"step": 101500
},
{
"epoch": 27.88,
"learning_rate": 4.861244019138757e-05,
"loss": 2.6561,
"step": 102000
},
{
"epoch": 28.02,
"learning_rate": 4.86056049213944e-05,
"loss": 2.6481,
"step": 102500
},
{
"epoch": 28.16,
"learning_rate": 4.859876965140123e-05,
"loss": 2.61,
"step": 103000
},
{
"epoch": 28.29,
"learning_rate": 4.8591934381408065e-05,
"loss": 2.6118,
"step": 103500
},
{
"epoch": 28.43,
"learning_rate": 4.8585099111414906e-05,
"loss": 2.6284,
"step": 104000
},
{
"epoch": 28.57,
"learning_rate": 4.857826384142174e-05,
"loss": 2.6274,
"step": 104500
},
{
"epoch": 28.7,
"learning_rate": 4.8571428571428576e-05,
"loss": 2.6392,
"step": 105000
},
{
"epoch": 28.84,
"learning_rate": 4.8564593301435404e-05,
"loss": 2.644,
"step": 105500
},
{
"epoch": 28.98,
"learning_rate": 4.8557758031442245e-05,
"loss": 2.6482,
"step": 106000
},
{
"epoch": 29.11,
"learning_rate": 4.855092276144908e-05,
"loss": 2.6076,
"step": 106500
},
{
"epoch": 29.25,
"learning_rate": 4.8544087491455915e-05,
"loss": 2.5969,
"step": 107000
},
{
"epoch": 29.39,
"learning_rate": 4.853725222146275e-05,
"loss": 2.6128,
"step": 107500
},
{
"epoch": 29.52,
"learning_rate": 4.8530416951469585e-05,
"loss": 2.62,
"step": 108000
},
{
"epoch": 29.66,
"learning_rate": 4.852358168147642e-05,
"loss": 2.6232,
"step": 108500
},
{
"epoch": 29.8,
"learning_rate": 4.8516746411483254e-05,
"loss": 2.6232,
"step": 109000
},
{
"epoch": 29.93,
"learning_rate": 4.850991114149009e-05,
"loss": 2.633,
"step": 109500
},
{
"epoch": 30.07,
"learning_rate": 4.850307587149693e-05,
"loss": 2.6035,
"step": 110000
},
{
"epoch": 30.21,
"learning_rate": 4.849624060150376e-05,
"loss": 2.5874,
"step": 110500
},
{
"epoch": 30.34,
"learning_rate": 4.8489405331510593e-05,
"loss": 2.5952,
"step": 111000
},
{
"epoch": 30.48,
"learning_rate": 4.8482570061517435e-05,
"loss": 2.6043,
"step": 111500
},
{
"epoch": 30.62,
"learning_rate": 4.847573479152427e-05,
"loss": 2.6067,
"step": 112000
},
{
"epoch": 30.75,
"learning_rate": 4.8468899521531105e-05,
"loss": 2.6119,
"step": 112500
},
{
"epoch": 30.89,
"learning_rate": 4.846206425153794e-05,
"loss": 2.6214,
"step": 113000
},
{
"epoch": 31.03,
"learning_rate": 4.8455228981544774e-05,
"loss": 2.6113,
"step": 113500
},
{
"epoch": 31.16,
"learning_rate": 4.844839371155161e-05,
"loss": 2.5724,
"step": 114000
},
{
"epoch": 31.3,
"learning_rate": 4.8441558441558444e-05,
"loss": 2.5825,
"step": 114500
},
{
"epoch": 31.44,
"learning_rate": 4.843472317156528e-05,
"loss": 2.5849,
"step": 115000
},
{
"epoch": 31.57,
"learning_rate": 4.842788790157211e-05,
"loss": 2.5958,
"step": 115500
},
{
"epoch": 31.71,
"learning_rate": 4.842105263157895e-05,
"loss": 2.5992,
"step": 116000
},
{
"epoch": 31.85,
"learning_rate": 4.841421736158578e-05,
"loss": 2.6051,
"step": 116500
},
{
"epoch": 31.98,
"learning_rate": 4.840738209159262e-05,
"loss": 2.6078,
"step": 117000
},
{
"epoch": 32.12,
"learning_rate": 4.840054682159946e-05,
"loss": 2.56,
"step": 117500
},
{
"epoch": 32.26,
"learning_rate": 4.8393711551606294e-05,
"loss": 2.5672,
"step": 118000
},
{
"epoch": 32.39,
"learning_rate": 4.838687628161312e-05,
"loss": 2.5767,
"step": 118500
},
{
"epoch": 32.53,
"learning_rate": 4.838004101161996e-05,
"loss": 2.5798,
"step": 119000
},
{
"epoch": 32.67,
"learning_rate": 4.83732057416268e-05,
"loss": 2.5858,
"step": 119500
},
{
"epoch": 32.8,
"learning_rate": 4.836637047163363e-05,
"loss": 2.5966,
"step": 120000
},
{
"epoch": 32.94,
"learning_rate": 4.835953520164047e-05,
"loss": 2.5949,
"step": 120500
},
{
"epoch": 33.08,
"learning_rate": 4.83526999316473e-05,
"loss": 2.5606,
"step": 121000
},
{
"epoch": 33.21,
"learning_rate": 4.834586466165414e-05,
"loss": 2.5511,
"step": 121500
},
{
"epoch": 33.35,
"learning_rate": 4.833902939166097e-05,
"loss": 2.5657,
"step": 122000
},
{
"epoch": 33.49,
"learning_rate": 4.833219412166781e-05,
"loss": 2.5705,
"step": 122500
},
{
"epoch": 33.62,
"learning_rate": 4.832535885167465e-05,
"loss": 2.5715,
"step": 123000
},
{
"epoch": 33.76,
"learning_rate": 4.831852358168148e-05,
"loss": 2.5787,
"step": 123500
},
{
"epoch": 33.9,
"learning_rate": 4.831168831168831e-05,
"loss": 2.5778,
"step": 124000
},
{
"epoch": 34.03,
"learning_rate": 4.8304853041695146e-05,
"loss": 2.573,
"step": 124500
},
{
"epoch": 34.17,
"learning_rate": 4.829801777170199e-05,
"loss": 2.5399,
"step": 125000
},
{
"epoch": 34.31,
"learning_rate": 4.829118250170882e-05,
"loss": 2.5387,
"step": 125500
},
{
"epoch": 34.45,
"learning_rate": 4.828434723171566e-05,
"loss": 2.5553,
"step": 126000
},
{
"epoch": 34.58,
"learning_rate": 4.8277511961722486e-05,
"loss": 2.5587,
"step": 126500
},
{
"epoch": 34.72,
"learning_rate": 4.827067669172933e-05,
"loss": 2.5641,
"step": 127000
},
{
"epoch": 34.86,
"learning_rate": 4.826384142173616e-05,
"loss": 2.5707,
"step": 127500
},
{
"epoch": 34.99,
"learning_rate": 4.8257006151743e-05,
"loss": 2.5761,
"step": 128000
},
{
"epoch": 35.13,
"learning_rate": 4.825017088174983e-05,
"loss": 2.5247,
"step": 128500
},
{
"epoch": 35.27,
"learning_rate": 4.8243335611756666e-05,
"loss": 2.5297,
"step": 129000
},
{
"epoch": 35.4,
"learning_rate": 4.82365003417635e-05,
"loss": 2.5373,
"step": 129500
},
{
"epoch": 35.54,
"learning_rate": 4.8229665071770336e-05,
"loss": 2.5436,
"step": 130000
},
{
"epoch": 35.68,
"learning_rate": 4.822282980177718e-05,
"loss": 2.5495,
"step": 130500
},
{
"epoch": 35.81,
"learning_rate": 4.821599453178401e-05,
"loss": 2.566,
"step": 131000
},
{
"epoch": 35.95,
"learning_rate": 4.820915926179084e-05,
"loss": 2.5613,
"step": 131500
},
{
"epoch": 36.09,
"learning_rate": 4.8202323991797675e-05,
"loss": 2.5275,
"step": 132000
},
{
"epoch": 36.22,
"learning_rate": 4.819548872180452e-05,
"loss": 2.5186,
"step": 132500
},
{
"epoch": 36.36,
"learning_rate": 4.818865345181135e-05,
"loss": 2.5293,
"step": 133000
},
{
"epoch": 36.5,
"learning_rate": 4.8181818181818186e-05,
"loss": 2.5351,
"step": 133500
},
{
"epoch": 36.63,
"learning_rate": 4.8174982911825014e-05,
"loss": 2.5375,
"step": 134000
},
{
"epoch": 36.77,
"learning_rate": 4.8168147641831856e-05,
"loss": 2.5438,
"step": 134500
},
{
"epoch": 36.91,
"learning_rate": 4.816131237183869e-05,
"loss": 2.5456,
"step": 135000
},
{
"epoch": 37.04,
"learning_rate": 4.8154477101845525e-05,
"loss": 2.5379,
"step": 135500
},
{
"epoch": 37.18,
"learning_rate": 4.814764183185236e-05,
"loss": 2.5043,
"step": 136000
},
{
"epoch": 37.32,
"learning_rate": 4.8140806561859195e-05,
"loss": 2.5121,
"step": 136500
},
{
"epoch": 37.45,
"learning_rate": 4.813397129186603e-05,
"loss": 2.5139,
"step": 137000
},
{
"epoch": 37.59,
"learning_rate": 4.8127136021872865e-05,
"loss": 2.5278,
"step": 137500
},
{
"epoch": 37.73,
"learning_rate": 4.81203007518797e-05,
"loss": 2.5329,
"step": 138000
},
{
"epoch": 37.86,
"learning_rate": 4.811346548188654e-05,
"loss": 2.5364,
"step": 138500
},
{
"epoch": 38.0,
"learning_rate": 4.810663021189337e-05,
"loss": 2.5463,
"step": 139000
},
{
"epoch": 38.14,
"learning_rate": 4.8099794941900204e-05,
"loss": 2.4857,
"step": 139500
},
{
"epoch": 38.27,
"learning_rate": 4.8092959671907045e-05,
"loss": 2.4959,
"step": 140000
},
{
"epoch": 38.41,
"learning_rate": 4.808612440191388e-05,
"loss": 2.507,
"step": 140500
},
{
"epoch": 38.55,
"learning_rate": 4.8079289131920715e-05,
"loss": 2.5137,
"step": 141000
},
{
"epoch": 38.68,
"learning_rate": 4.807245386192755e-05,
"loss": 2.5184,
"step": 141500
},
{
"epoch": 38.82,
"learning_rate": 4.8065618591934384e-05,
"loss": 2.5339,
"step": 142000
},
{
"epoch": 38.96,
"learning_rate": 4.805878332194122e-05,
"loss": 2.5319,
"step": 142500
},
{
"epoch": 39.09,
"learning_rate": 4.8051948051948054e-05,
"loss": 2.4922,
"step": 143000
},
{
"epoch": 39.23,
"learning_rate": 4.804511278195489e-05,
"loss": 2.4844,
"step": 143500
},
{
"epoch": 39.37,
"learning_rate": 4.8038277511961724e-05,
"loss": 2.4939,
"step": 144000
},
{
"epoch": 39.5,
"learning_rate": 4.803144224196856e-05,
"loss": 2.5038,
"step": 144500
},
{
"epoch": 39.64,
"learning_rate": 4.802460697197539e-05,
"loss": 2.5074,
"step": 145000
},
{
"epoch": 39.78,
"learning_rate": 4.801777170198223e-05,
"loss": 2.5117,
"step": 145500
},
{
"epoch": 39.91,
"learning_rate": 4.801093643198907e-05,
"loss": 2.5152,
"step": 146000
},
{
"epoch": 40.05,
"learning_rate": 4.8004101161995904e-05,
"loss": 2.4997,
"step": 146500
},
{
"epoch": 40.19,
"learning_rate": 4.799726589200273e-05,
"loss": 2.4738,
"step": 147000
},
{
"epoch": 40.32,
"learning_rate": 4.799043062200957e-05,
"loss": 2.4777,
"step": 147500
},
{
"epoch": 40.46,
"learning_rate": 4.798359535201641e-05,
"loss": 2.4953,
"step": 148000
},
{
"epoch": 40.6,
"learning_rate": 4.7976760082023244e-05,
"loss": 2.4929,
"step": 148500
},
{
"epoch": 40.73,
"learning_rate": 4.796992481203008e-05,
"loss": 2.5007,
"step": 149000
},
{
"epoch": 40.87,
"learning_rate": 4.796308954203691e-05,
"loss": 2.5026,
"step": 149500
},
{
"epoch": 41.01,
"learning_rate": 4.795625427204375e-05,
"loss": 2.5095,
"step": 150000
},
{
"epoch": 41.14,
"learning_rate": 4.794941900205058e-05,
"loss": 2.4572,
"step": 150500
},
{
"epoch": 41.28,
"learning_rate": 4.794258373205742e-05,
"loss": 2.4632,
"step": 151000
},
{
"epoch": 41.42,
"learning_rate": 4.793574846206426e-05,
"loss": 2.478,
"step": 151500
},
{
"epoch": 41.55,
"learning_rate": 4.792891319207109e-05,
"loss": 2.4912,
"step": 152000
},
{
"epoch": 41.69,
"learning_rate": 4.792207792207792e-05,
"loss": 2.4844,
"step": 152500
},
{
"epoch": 41.83,
"learning_rate": 4.791524265208476e-05,
"loss": 2.4967,
"step": 153000
},
{
"epoch": 41.96,
"learning_rate": 4.79084073820916e-05,
"loss": 2.4939,
"step": 153500
},
{
"epoch": 42.1,
"learning_rate": 4.790157211209843e-05,
"loss": 2.4654,
"step": 154000
},
{
"epoch": 42.24,
"learning_rate": 4.789473684210526e-05,
"loss": 2.4502,
"step": 154500
},
{
"epoch": 42.37,
"learning_rate": 4.7887901572112096e-05,
"loss": 2.4673,
"step": 155000
},
{
"epoch": 42.51,
"learning_rate": 4.788106630211894e-05,
"loss": 2.4697,
"step": 155500
},
{
"epoch": 42.65,
"learning_rate": 4.787423103212577e-05,
"loss": 2.4791,
"step": 156000
},
{
"epoch": 42.78,
"learning_rate": 4.786739576213261e-05,
"loss": 2.4783,
"step": 156500
},
{
"epoch": 42.92,
"learning_rate": 4.786056049213944e-05,
"loss": 2.4872,
"step": 157000
},
{
"epoch": 43.06,
"learning_rate": 4.785372522214628e-05,
"loss": 2.4711,
"step": 157500
},
{
"epoch": 43.19,
"learning_rate": 4.784688995215311e-05,
"loss": 2.443,
"step": 158000
},
{
"epoch": 43.33,
"learning_rate": 4.7840054682159946e-05,
"loss": 2.4447,
"step": 158500
},
{
"epoch": 43.47,
"learning_rate": 4.783321941216679e-05,
"loss": 2.4653,
"step": 159000
},
{
"epoch": 43.6,
"learning_rate": 4.7826384142173616e-05,
"loss": 2.4677,
"step": 159500
},
{
"epoch": 43.74,
"learning_rate": 4.781954887218045e-05,
"loss": 2.4703,
"step": 160000
},
{
"epoch": 43.88,
"learning_rate": 4.7812713602187285e-05,
"loss": 2.4723,
"step": 160500
},
{
"epoch": 44.01,
"learning_rate": 4.780587833219413e-05,
"loss": 2.4755,
"step": 161000
},
{
"epoch": 44.15,
"learning_rate": 4.779904306220096e-05,
"loss": 2.4305,
"step": 161500
},
{
"epoch": 44.29,
"learning_rate": 4.7792207792207797e-05,
"loss": 2.4368,
"step": 162000
},
{
"epoch": 44.42,
"learning_rate": 4.7785372522214625e-05,
"loss": 2.444,
"step": 162500
},
{
"epoch": 44.56,
"learning_rate": 4.7778537252221466e-05,
"loss": 2.4587,
"step": 163000
},
{
"epoch": 44.7,
"learning_rate": 4.77717019822283e-05,
"loss": 2.4599,
"step": 163500
},
{
"epoch": 44.83,
"learning_rate": 4.7764866712235136e-05,
"loss": 2.4643,
"step": 164000
},
{
"epoch": 44.97,
"learning_rate": 4.775803144224197e-05,
"loss": 2.4688,
"step": 164500
},
{
"epoch": 45.11,
"learning_rate": 4.7751196172248805e-05,
"loss": 2.4327,
"step": 165000
},
{
"epoch": 45.24,
"learning_rate": 4.774436090225564e-05,
"loss": 2.4213,
"step": 165500
},
{
"epoch": 45.38,
"learning_rate": 4.7737525632262475e-05,
"loss": 2.4372,
"step": 166000
},
{
"epoch": 45.52,
"learning_rate": 4.7730690362269316e-05,
"loss": 2.4385,
"step": 166500
},
{
"epoch": 45.65,
"learning_rate": 4.772385509227615e-05,
"loss": 2.4512,
"step": 167000
},
{
"epoch": 45.79,
"learning_rate": 4.771701982228298e-05,
"loss": 2.4543,
"step": 167500
},
{
"epoch": 45.93,
"learning_rate": 4.7710184552289814e-05,
"loss": 2.4567,
"step": 168000
},
{
"epoch": 46.06,
"learning_rate": 4.7703349282296656e-05,
"loss": 2.4389,
"step": 168500
},
{
"epoch": 46.2,
"learning_rate": 4.769651401230349e-05,
"loss": 2.4125,
"step": 169000
},
{
"epoch": 46.34,
"learning_rate": 4.7689678742310325e-05,
"loss": 2.4239,
"step": 169500
},
{
"epoch": 46.47,
"learning_rate": 4.768284347231716e-05,
"loss": 2.4283,
"step": 170000
},
{
"epoch": 46.61,
"learning_rate": 4.7676008202323995e-05,
"loss": 2.4372,
"step": 170500
},
{
"epoch": 46.75,
"learning_rate": 4.766917293233083e-05,
"loss": 2.4478,
"step": 171000
},
{
"epoch": 46.88,
"learning_rate": 4.7662337662337664e-05,
"loss": 2.445,
"step": 171500
},
{
"epoch": 47.02,
"learning_rate": 4.76555023923445e-05,
"loss": 2.4429,
"step": 172000
},
{
"epoch": 47.16,
"learning_rate": 4.7648667122351334e-05,
"loss": 2.397,
"step": 172500
},
{
"epoch": 47.29,
"learning_rate": 4.764183185235817e-05,
"loss": 2.4144,
"step": 173000
},
{
"epoch": 47.43,
"learning_rate": 4.7634996582365004e-05,
"loss": 2.4176,
"step": 173500
},
{
"epoch": 47.57,
"learning_rate": 4.762816131237184e-05,
"loss": 2.4262,
"step": 174000
},
{
"epoch": 47.7,
"learning_rate": 4.762132604237868e-05,
"loss": 2.4353,
"step": 174500
},
{
"epoch": 47.84,
"learning_rate": 4.7614490772385515e-05,
"loss": 2.4362,
"step": 175000
},
{
"epoch": 47.98,
"learning_rate": 4.760765550239234e-05,
"loss": 2.4417,
"step": 175500
},
{
"epoch": 48.11,
"learning_rate": 4.7600820232399184e-05,
"loss": 2.3966,
"step": 176000
},
{
"epoch": 48.25,
"learning_rate": 4.759398496240602e-05,
"loss": 2.3993,
"step": 176500
},
{
"epoch": 48.39,
"learning_rate": 4.7587149692412854e-05,
"loss": 2.4065,
"step": 177000
},
{
"epoch": 48.52,
"learning_rate": 4.758031442241969e-05,
"loss": 2.414,
"step": 177500
},
{
"epoch": 48.66,
"learning_rate": 4.7573479152426524e-05,
"loss": 2.4234,
"step": 178000
},
{
"epoch": 48.8,
"learning_rate": 4.756664388243336e-05,
"loss": 2.4262,
"step": 178500
},
{
"epoch": 48.93,
"learning_rate": 4.755980861244019e-05,
"loss": 2.4329,
"step": 179000
},
{
"epoch": 49.07,
"learning_rate": 4.755297334244703e-05,
"loss": 2.4114,
"step": 179500
},
{
"epoch": 49.21,
"learning_rate": 4.754613807245387e-05,
"loss": 2.3889,
"step": 180000
},
{
"epoch": 49.34,
"learning_rate": 4.75393028024607e-05,
"loss": 0.0066,
"step": 180500
},
{
"epoch": 49.48,
"learning_rate": 4.753246753246753e-05,
"loss": 2.4065,
"step": 181000
},
{
"epoch": 49.62,
"learning_rate": 4.752563226247437e-05,
"loss": 2.4052,
"step": 181500
},
{
"epoch": 49.75,
"learning_rate": 4.751879699248121e-05,
"loss": 2.4143,
"step": 182000
},
{
"epoch": 49.89,
"learning_rate": 4.7511961722488043e-05,
"loss": 2.4229,
"step": 182500
},
{
"epoch": 50.03,
"learning_rate": 4.750512645249487e-05,
"loss": 2.4113,
"step": 183000
},
{
"epoch": 50.16,
"learning_rate": 4.7498291182501706e-05,
"loss": 2.3709,
"step": 183500
},
{
"epoch": 50.3,
"learning_rate": 4.749145591250855e-05,
"loss": 2.3825,
"step": 184000
},
{
"epoch": 50.44,
"learning_rate": 4.748462064251538e-05,
"loss": 2.3969,
"step": 184500
},
{
"epoch": 50.57,
"learning_rate": 4.747778537252222e-05,
"loss": 2.4013,
"step": 185000
},
{
"epoch": 50.71,
"learning_rate": 4.747095010252905e-05,
"loss": 2.4049,
"step": 185500
},
{
"epoch": 50.85,
"learning_rate": 4.746411483253589e-05,
"loss": 2.4081,
"step": 186000
},
{
"epoch": 50.98,
"learning_rate": 4.745727956254272e-05,
"loss": 2.416,
"step": 186500
},
{
"epoch": 51.12,
"learning_rate": 4.7450444292549557e-05,
"loss": 2.3682,
"step": 187000
},
{
"epoch": 51.26,
"learning_rate": 4.74436090225564e-05,
"loss": 2.3701,
"step": 187500
},
{
"epoch": 51.39,
"learning_rate": 4.7436773752563226e-05,
"loss": 2.3815,
"step": 188000
},
{
"epoch": 51.53,
"learning_rate": 4.742993848257006e-05,
"loss": 2.3927,
"step": 188500
},
{
"epoch": 51.67,
"learning_rate": 4.7423103212576896e-05,
"loss": 2.391,
"step": 189000
},
{
"epoch": 51.8,
"learning_rate": 4.741626794258374e-05,
"loss": 2.4008,
"step": 189500
},
{
"epoch": 51.94,
"learning_rate": 4.740943267259057e-05,
"loss": 2.4082,
"step": 190000
},
{
"epoch": 52.08,
"learning_rate": 4.740259740259741e-05,
"loss": 2.3833,
"step": 190500
},
{
"epoch": 52.21,
"learning_rate": 4.7395762132604235e-05,
"loss": 2.3605,
"step": 191000
},
{
"epoch": 52.35,
"learning_rate": 4.7388926862611076e-05,
"loss": 2.3671,
"step": 191500
},
{
"epoch": 52.49,
"learning_rate": 4.738209159261791e-05,
"loss": 2.3795,
"step": 192000
},
{
"epoch": 52.62,
"learning_rate": 4.7375256322624746e-05,
"loss": 2.3847,
"step": 192500
},
{
"epoch": 52.76,
"learning_rate": 4.736842105263158e-05,
"loss": 2.3837,
"step": 193000
},
{
"epoch": 52.9,
"learning_rate": 4.7361585782638416e-05,
"loss": 2.402,
"step": 193500
},
{
"epoch": 53.03,
"learning_rate": 4.735475051264525e-05,
"loss": 2.3843,
"step": 194000
},
{
"epoch": 53.17,
"learning_rate": 4.7347915242652085e-05,
"loss": 2.3485,
"step": 194500
},
{
"epoch": 53.31,
"learning_rate": 4.734107997265893e-05,
"loss": 2.359,
"step": 195000
},
{
"epoch": 53.44,
"learning_rate": 4.733424470266576e-05,
"loss": 2.3675,
"step": 195500
},
{
"epoch": 53.58,
"learning_rate": 4.732740943267259e-05,
"loss": 2.3771,
"step": 196000
},
{
"epoch": 53.72,
"learning_rate": 4.7320574162679424e-05,
"loss": 2.3825,
"step": 196500
},
{
"epoch": 53.85,
"learning_rate": 4.7313738892686266e-05,
"loss": 2.3819,
"step": 197000
},
{
"epoch": 53.99,
"learning_rate": 4.73069036226931e-05,
"loss": 2.3902,
"step": 197500
},
{
"epoch": 54.13,
"learning_rate": 4.7300068352699936e-05,
"loss": 2.3445,
"step": 198000
},
{
"epoch": 54.26,
"learning_rate": 4.729323308270677e-05,
"loss": 2.3435,
"step": 198500
},
{
"epoch": 54.4,
"learning_rate": 4.7286397812713605e-05,
"loss": 2.3632,
"step": 199000
},
{
"epoch": 54.54,
"learning_rate": 4.727956254272044e-05,
"loss": 2.3605,
"step": 199500
},
{
"epoch": 54.67,
"learning_rate": 4.7272727272727275e-05,
"loss": 2.3713,
"step": 200000
},
{
"epoch": 54.81,
"learning_rate": 4.726589200273411e-05,
"loss": 2.3734,
"step": 200500
},
{
"epoch": 54.95,
"learning_rate": 4.7259056732740944e-05,
"loss": 2.3805,
"step": 201000
},
{
"epoch": 55.08,
"learning_rate": 4.725222146274778e-05,
"loss": 2.3473,
"step": 201500
},
{
"epoch": 55.22,
"learning_rate": 4.7245386192754614e-05,
"loss": 2.3306,
"step": 202000
},
{
"epoch": 55.36,
"learning_rate": 4.723855092276145e-05,
"loss": 2.348,
"step": 202500
},
{
"epoch": 55.49,
"learning_rate": 4.723171565276829e-05,
"loss": 2.3537,
"step": 203000
},
{
"epoch": 55.63,
"learning_rate": 4.7224880382775125e-05,
"loss": 2.3617,
"step": 203500
},
{
"epoch": 55.77,
"learning_rate": 4.721804511278195e-05,
"loss": 2.3665,
"step": 204000
},
{
"epoch": 55.9,
"learning_rate": 4.7211209842788795e-05,
"loss": 2.3715,
"step": 204500
},
{
"epoch": 56.04,
"learning_rate": 4.720437457279563e-05,
"loss": 2.3597,
"step": 205000
},
{
"epoch": 56.18,
"learning_rate": 4.7197539302802464e-05,
"loss": 2.3231,
"step": 205500
},
{
"epoch": 56.31,
"learning_rate": 4.71907040328093e-05,
"loss": 2.335,
"step": 206000
},
{
"epoch": 56.45,
"learning_rate": 4.7183868762816134e-05,
"loss": 2.3418,
"step": 206500
},
{
"epoch": 56.59,
"learning_rate": 4.717703349282297e-05,
"loss": 2.3458,
"step": 207000
},
{
"epoch": 56.72,
"learning_rate": 4.7170198222829803e-05,
"loss": 2.3612,
"step": 207500
},
{
"epoch": 56.86,
"learning_rate": 4.716336295283664e-05,
"loss": 2.3632,
"step": 208000
},
{
"epoch": 57.0,
"learning_rate": 4.715652768284348e-05,
"loss": 2.3657,
"step": 208500
},
{
"epoch": 57.14,
"learning_rate": 4.714969241285031e-05,
"loss": 2.3137,
"step": 209000
},
{
"epoch": 57.27,
"learning_rate": 4.714285714285714e-05,
"loss": 2.3256,
"step": 209500
},
{
"epoch": 57.41,
"learning_rate": 4.713602187286398e-05,
"loss": 2.33,
"step": 210000
},
{
"epoch": 57.55,
"learning_rate": 4.712918660287082e-05,
"loss": 2.3427,
"step": 210500
},
{
"epoch": 57.68,
"learning_rate": 4.7122351332877654e-05,
"loss": 2.346,
"step": 211000
},
{
"epoch": 57.82,
"learning_rate": 4.711551606288448e-05,
"loss": 2.3537,
"step": 211500
},
{
"epoch": 57.96,
"learning_rate": 4.7108680792891317e-05,
"loss": 2.3487,
"step": 212000
},
{
"epoch": 58.09,
"learning_rate": 4.710184552289816e-05,
"loss": 2.3228,
"step": 212500
},
{
"epoch": 58.23,
"learning_rate": 4.709501025290499e-05,
"loss": 2.3111,
"step": 213000
},
{
"epoch": 58.37,
"learning_rate": 4.708817498291183e-05,
"loss": 2.3207,
"step": 213500
},
{
"epoch": 58.5,
"learning_rate": 4.708133971291866e-05,
"loss": 2.3281,
"step": 214000
},
{
"epoch": 58.64,
"learning_rate": 4.70745044429255e-05,
"loss": 2.3396,
"step": 214500
},
{
"epoch": 58.78,
"learning_rate": 4.706766917293233e-05,
"loss": 2.3445,
"step": 215000
},
{
"epoch": 58.91,
"learning_rate": 4.706083390293917e-05,
"loss": 2.3502,
"step": 215500
},
{
"epoch": 59.05,
"learning_rate": 4.705399863294601e-05,
"loss": 2.3343,
"step": 216000
},
{
"epoch": 59.19,
"learning_rate": 4.7047163362952836e-05,
"loss": 2.3013,
"step": 216500
},
{
"epoch": 59.32,
"learning_rate": 4.704032809295967e-05,
"loss": 2.3135,
"step": 217000
},
{
"epoch": 59.46,
"learning_rate": 4.7033492822966506e-05,
"loss": 2.3157,
"step": 217500
},
{
"epoch": 59.6,
"learning_rate": 4.702665755297335e-05,
"loss": 2.329,
"step": 218000
},
{
"epoch": 59.73,
"learning_rate": 4.701982228298018e-05,
"loss": 2.3323,
"step": 218500
},
{
"epoch": 59.87,
"learning_rate": 4.701298701298702e-05,
"loss": 2.3365,
"step": 219000
},
{
"epoch": 60.01,
"learning_rate": 4.7006151742993845e-05,
"loss": 2.3396,
"step": 219500
},
{
"epoch": 60.14,
"learning_rate": 4.699931647300069e-05,
"loss": 2.2899,
"step": 220000
},
{
"epoch": 60.28,
"learning_rate": 4.699248120300752e-05,
"loss": 2.2987,
"step": 220500
},
{
"epoch": 60.42,
"learning_rate": 4.6985645933014356e-05,
"loss": 2.3154,
"step": 221000
},
{
"epoch": 60.55,
"learning_rate": 4.697881066302119e-05,
"loss": 2.3181,
"step": 221500
},
{
"epoch": 60.69,
"learning_rate": 4.6971975393028026e-05,
"loss": 2.3242,
"step": 222000
},
{
"epoch": 60.83,
"learning_rate": 4.696514012303486e-05,
"loss": 2.3311,
"step": 222500
},
{
"epoch": 60.96,
"learning_rate": 4.6958304853041696e-05,
"loss": 2.3326,
"step": 223000
},
{
"epoch": 61.1,
"learning_rate": 4.695146958304854e-05,
"loss": 2.2986,
"step": 223500
},
{
"epoch": 61.24,
"learning_rate": 4.694463431305537e-05,
"loss": 2.2872,
"step": 224000
},
{
"epoch": 61.37,
"learning_rate": 4.69377990430622e-05,
"loss": 2.3003,
"step": 224500
},
{
"epoch": 61.51,
"learning_rate": 4.6930963773069035e-05,
"loss": 2.3074,
"step": 225000
},
{
"epoch": 61.65,
"learning_rate": 4.6924128503075876e-05,
"loss": 2.3136,
"step": 225500
},
{
"epoch": 61.78,
"learning_rate": 4.691729323308271e-05,
"loss": 2.3163,
"step": 226000
},
{
"epoch": 61.92,
"learning_rate": 4.6910457963089546e-05,
"loss": 2.3282,
"step": 226500
},
{
"epoch": 62.06,
"learning_rate": 4.690362269309638e-05,
"loss": 2.309,
"step": 227000
},
{
"epoch": 62.19,
"learning_rate": 4.6896787423103215e-05,
"loss": 2.2813,
"step": 227500
},
{
"epoch": 62.33,
"learning_rate": 4.688995215311005e-05,
"loss": 2.2888,
"step": 228000
},
{
"epoch": 62.47,
"learning_rate": 4.6883116883116885e-05,
"loss": 2.2994,
"step": 228500
},
{
"epoch": 62.6,
"learning_rate": 4.687628161312372e-05,
"loss": 2.3015,
"step": 229000
},
{
"epoch": 62.74,
"learning_rate": 4.6869446343130555e-05,
"loss": 2.3094,
"step": 229500
},
{
"epoch": 62.88,
"learning_rate": 4.686261107313739e-05,
"loss": 2.3217,
"step": 230000
},
{
"epoch": 63.01,
"learning_rate": 4.6855775803144224e-05,
"loss": 2.3126,
"step": 230500
},
{
"epoch": 63.15,
"learning_rate": 4.6848940533151066e-05,
"loss": 2.2696,
"step": 231000
},
{
"epoch": 63.29,
"learning_rate": 4.68421052631579e-05,
"loss": 2.2826,
"step": 231500
},
{
"epoch": 63.42,
"learning_rate": 4.6835269993164735e-05,
"loss": 2.2899,
"step": 232000
},
{
"epoch": 63.56,
"learning_rate": 4.6828434723171563e-05,
"loss": 2.2887,
"step": 232500
},
{
"epoch": 63.7,
"learning_rate": 4.6821599453178405e-05,
"loss": 2.3065,
"step": 233000
},
{
"epoch": 63.83,
"learning_rate": 4.681476418318524e-05,
"loss": 2.3073,
"step": 233500
},
{
"epoch": 63.97,
"learning_rate": 4.6807928913192075e-05,
"loss": 2.3111,
"step": 234000
},
{
"epoch": 64.11,
"learning_rate": 4.680109364319891e-05,
"loss": 2.2723,
"step": 234500
},
{
"epoch": 64.24,
"learning_rate": 4.6794258373205744e-05,
"loss": 2.2645,
"step": 235000
},
{
"epoch": 64.38,
"learning_rate": 4.678742310321258e-05,
"loss": 2.2742,
"step": 235500
},
{
"epoch": 64.52,
"learning_rate": 4.6780587833219414e-05,
"loss": 2.2892,
"step": 236000
},
{
"epoch": 64.65,
"learning_rate": 4.677375256322625e-05,
"loss": 2.2938,
"step": 236500
},
{
"epoch": 64.79,
"learning_rate": 4.676691729323309e-05,
"loss": 2.2964,
"step": 237000
},
{
"epoch": 64.93,
"learning_rate": 4.676008202323992e-05,
"loss": 2.3037,
"step": 237500
},
{
"epoch": 65.06,
"learning_rate": 4.675324675324675e-05,
"loss": 2.2862,
"step": 238000
},
{
"epoch": 65.2,
"learning_rate": 4.674641148325359e-05,
"loss": 2.2633,
"step": 238500
},
{
"epoch": 65.34,
"learning_rate": 4.673957621326043e-05,
"loss": 2.2678,
"step": 239000
},
{
"epoch": 65.47,
"learning_rate": 4.6732740943267264e-05,
"loss": 2.2798,
"step": 239500
},
{
"epoch": 65.61,
"learning_rate": 4.672590567327409e-05,
"loss": 2.2782,
"step": 240000
},
{
"epoch": 65.75,
"learning_rate": 4.6719070403280934e-05,
"loss": 2.288,
"step": 240500
},
{
"epoch": 65.88,
"learning_rate": 4.671223513328777e-05,
"loss": 2.2962,
"step": 241000
},
{
"epoch": 66.02,
"learning_rate": 4.67053998632946e-05,
"loss": 2.2894,
"step": 241500
},
{
"epoch": 66.16,
"learning_rate": 4.669856459330144e-05,
"loss": 2.251,
"step": 242000
},
{
"epoch": 66.29,
"learning_rate": 4.669172932330827e-05,
"loss": 2.2583,
"step": 242500
},
{
"epoch": 66.43,
"learning_rate": 4.668489405331511e-05,
"loss": 2.2658,
"step": 243000
},
{
"epoch": 66.57,
"learning_rate": 4.667805878332194e-05,
"loss": 2.2738,
"step": 243500
},
{
"epoch": 66.7,
"learning_rate": 4.667122351332878e-05,
"loss": 2.2824,
"step": 244000
},
{
"epoch": 66.84,
"learning_rate": 4.666438824333562e-05,
"loss": 2.2872,
"step": 244500
},
{
"epoch": 66.98,
"learning_rate": 4.665755297334245e-05,
"loss": 2.2883,
"step": 245000
},
{
"epoch": 67.11,
"learning_rate": 4.665071770334928e-05,
"loss": 2.2555,
"step": 245500
},
{
"epoch": 67.25,
"learning_rate": 4.6643882433356116e-05,
"loss": 2.2512,
"step": 246000
},
{
"epoch": 67.39,
"learning_rate": 4.663704716336296e-05,
"loss": 2.2566,
"step": 246500
},
{
"epoch": 67.52,
"learning_rate": 4.663021189336979e-05,
"loss": 2.268,
"step": 247000
},
{
"epoch": 67.66,
"learning_rate": 4.662337662337663e-05,
"loss": 2.2692,
"step": 247500
},
{
"epoch": 67.8,
"learning_rate": 4.6616541353383456e-05,
"loss": 2.2753,
"step": 248000
},
{
"epoch": 67.93,
"learning_rate": 4.66097060833903e-05,
"loss": 2.2813,
"step": 248500
},
{
"epoch": 68.07,
"learning_rate": 4.660287081339713e-05,
"loss": 2.2562,
"step": 249000
},
{
"epoch": 68.21,
"learning_rate": 4.659603554340397e-05,
"loss": 2.2335,
"step": 249500
},
{
"epoch": 68.34,
"learning_rate": 4.65892002734108e-05,
"loss": 2.2489,
"step": 250000
},
{
"epoch": 68.48,
"learning_rate": 4.6582365003417636e-05,
"loss": 2.2543,
"step": 250500
},
{
"epoch": 68.62,
"learning_rate": 4.657552973342447e-05,
"loss": 2.2639,
"step": 251000
},
{
"epoch": 68.75,
"learning_rate": 4.6568694463431306e-05,
"loss": 2.2737,
"step": 251500
},
{
"epoch": 68.89,
"learning_rate": 4.656185919343815e-05,
"loss": 2.2805,
"step": 252000
},
{
"epoch": 69.03,
"learning_rate": 4.655502392344498e-05,
"loss": 2.2629,
"step": 252500
},
{
"epoch": 69.16,
"learning_rate": 4.654818865345181e-05,
"loss": 2.2303,
"step": 253000
},
{
"epoch": 69.3,
"learning_rate": 4.6541353383458645e-05,
"loss": 2.2406,
"step": 253500
},
{
"epoch": 69.44,
"learning_rate": 4.653451811346549e-05,
"loss": 2.2444,
"step": 254000
},
{
"epoch": 69.57,
"learning_rate": 4.652768284347232e-05,
"loss": 2.2566,
"step": 254500
},
{
"epoch": 69.71,
"learning_rate": 4.6520847573479156e-05,
"loss": 2.2571,
"step": 255000
},
{
"epoch": 69.85,
"learning_rate": 4.6514012303485984e-05,
"loss": 2.2681,
"step": 255500
},
{
"epoch": 69.98,
"learning_rate": 4.6507177033492826e-05,
"loss": 2.272,
"step": 256000
},
{
"epoch": 70.12,
"learning_rate": 4.650034176349966e-05,
"loss": 2.2186,
"step": 256500
},
{
"epoch": 70.26,
"learning_rate": 4.6493506493506495e-05,
"loss": 2.2257,
"step": 257000
},
{
"epoch": 70.39,
"learning_rate": 4.648667122351333e-05,
"loss": 2.2402,
"step": 257500
},
{
"epoch": 70.53,
"learning_rate": 4.6479835953520165e-05,
"loss": 2.2501,
"step": 258000
},
{
"epoch": 70.67,
"learning_rate": 4.6473000683527e-05,
"loss": 2.2504,
"step": 258500
},
{
"epoch": 70.8,
"learning_rate": 4.6466165413533835e-05,
"loss": 2.2584,
"step": 259000
},
{
"epoch": 70.94,
"learning_rate": 4.6459330143540676e-05,
"loss": 2.2668,
"step": 259500
},
{
"epoch": 71.08,
"learning_rate": 4.645249487354751e-05,
"loss": 2.2337,
"step": 260000
},
{
"epoch": 71.21,
"learning_rate": 4.644565960355434e-05,
"loss": 2.2181,
"step": 260500
},
{
"epoch": 71.35,
"learning_rate": 4.6438824333561174e-05,
"loss": 2.2308,
"step": 261000
},
{
"epoch": 71.49,
"learning_rate": 4.6431989063568015e-05,
"loss": 2.2326,
"step": 261500
},
{
"epoch": 71.62,
"learning_rate": 4.642515379357485e-05,
"loss": 2.245,
"step": 262000
},
{
"epoch": 71.76,
"learning_rate": 4.6418318523581685e-05,
"loss": 2.2485,
"step": 262500
},
{
"epoch": 71.9,
"learning_rate": 4.641148325358852e-05,
"loss": 2.2613,
"step": 263000
},
{
"epoch": 72.03,
"learning_rate": 4.6404647983595355e-05,
"loss": 2.2447,
"step": 263500
},
{
"epoch": 72.17,
"learning_rate": 4.639781271360219e-05,
"loss": 2.2129,
"step": 264000
},
{
"epoch": 72.31,
"learning_rate": 4.6390977443609024e-05,
"loss": 2.221,
"step": 264500
},
{
"epoch": 72.44,
"learning_rate": 4.638414217361586e-05,
"loss": 2.2273,
"step": 265000
},
{
"epoch": 72.58,
"learning_rate": 4.6377306903622694e-05,
"loss": 2.2365,
"step": 265500
},
{
"epoch": 72.72,
"learning_rate": 4.637047163362953e-05,
"loss": 2.2332,
"step": 266000
},
{
"epoch": 72.85,
"learning_rate": 4.636363636363636e-05,
"loss": 2.2526,
"step": 266500
},
{
"epoch": 72.99,
"learning_rate": 4.63568010936432e-05,
"loss": 2.2523,
"step": 267000
},
{
"epoch": 73.13,
"learning_rate": 4.634996582365004e-05,
"loss": 2.2042,
"step": 267500
},
{
"epoch": 73.26,
"learning_rate": 4.6343130553656874e-05,
"loss": 2.2098,
"step": 268000
},
{
"epoch": 73.4,
"learning_rate": 4.63362952836637e-05,
"loss": 2.2214,
"step": 268500
},
{
"epoch": 73.54,
"learning_rate": 4.6329460013670544e-05,
"loss": 2.2239,
"step": 269000
},
{
"epoch": 73.67,
"learning_rate": 4.632262474367738e-05,
"loss": 2.2377,
"step": 269500
},
{
"epoch": 73.81,
"learning_rate": 4.6315789473684214e-05,
"loss": 2.2381,
"step": 270000
},
{
"epoch": 73.95,
"learning_rate": 4.630895420369105e-05,
"loss": 2.2397,
"step": 270500
},
{
"epoch": 74.08,
"learning_rate": 4.630211893369788e-05,
"loss": 2.2159,
"step": 271000
},
{
"epoch": 74.22,
"learning_rate": 4.629528366370472e-05,
"loss": 2.1986,
"step": 271500
},
{
"epoch": 74.36,
"learning_rate": 4.628844839371155e-05,
"loss": 2.2109,
"step": 272000
},
{
"epoch": 74.49,
"learning_rate": 4.628161312371839e-05,
"loss": 2.2197,
"step": 272500
},
{
"epoch": 74.63,
"learning_rate": 4.627477785372523e-05,
"loss": 2.2228,
"step": 273000
},
{
"epoch": 74.77,
"learning_rate": 4.626794258373206e-05,
"loss": 2.2331,
"step": 273500
},
{
"epoch": 74.9,
"learning_rate": 4.626110731373889e-05,
"loss": 2.2348,
"step": 274000
},
{
"epoch": 75.04,
"learning_rate": 4.625427204374573e-05,
"loss": 2.2251,
"step": 274500
},
{
"epoch": 75.18,
"learning_rate": 4.624743677375257e-05,
"loss": 2.1874,
"step": 275000
},
{
"epoch": 75.31,
"learning_rate": 4.62406015037594e-05,
"loss": 2.2042,
"step": 275500
},
{
"epoch": 75.45,
"learning_rate": 4.623376623376624e-05,
"loss": 2.2069,
"step": 276000
},
{
"epoch": 75.59,
"learning_rate": 4.6226930963773066e-05,
"loss": 2.2117,
"step": 276500
},
{
"epoch": 75.72,
"learning_rate": 4.622009569377991e-05,
"loss": 2.2256,
"step": 277000
},
{
"epoch": 75.86,
"learning_rate": 4.621326042378674e-05,
"loss": 2.2325,
"step": 277500
},
{
"epoch": 76.0,
"learning_rate": 4.620642515379358e-05,
"loss": 2.2365,
"step": 278000
},
{
"epoch": 76.13,
"learning_rate": 4.619958988380041e-05,
"loss": 2.182,
"step": 278500
},
{
"epoch": 76.27,
"learning_rate": 4.619275461380725e-05,
"loss": 2.1906,
"step": 279000
},
{
"epoch": 76.41,
"learning_rate": 4.618591934381408e-05,
"loss": 2.2033,
"step": 279500
},
{
"epoch": 76.54,
"learning_rate": 4.6179084073820916e-05,
"loss": 2.2111,
"step": 280000
},
{
"epoch": 76.68,
"learning_rate": 4.617224880382776e-05,
"loss": 2.2147,
"step": 280500
},
{
"epoch": 76.82,
"learning_rate": 4.616541353383459e-05,
"loss": 2.2171,
"step": 281000
},
{
"epoch": 76.95,
"learning_rate": 4.615857826384142e-05,
"loss": 2.2259,
"step": 281500
},
{
"epoch": 77.09,
"learning_rate": 4.6151742993848255e-05,
"loss": 2.1938,
"step": 282000
},
{
"epoch": 77.23,
"learning_rate": 4.61449077238551e-05,
"loss": 2.1838,
"step": 282500
},
{
"epoch": 77.36,
"learning_rate": 4.613807245386193e-05,
"loss": 2.1927,
"step": 283000
},
{
"epoch": 77.5,
"learning_rate": 4.6131237183868767e-05,
"loss": 2.198,
"step": 283500
},
{
"epoch": 77.64,
"learning_rate": 4.6124401913875595e-05,
"loss": 2.2002,
"step": 284000
},
{
"epoch": 77.77,
"learning_rate": 4.6117566643882436e-05,
"loss": 2.2115,
"step": 284500
},
{
"epoch": 77.91,
"learning_rate": 4.611073137388927e-05,
"loss": 2.2224,
"step": 285000
},
{
"epoch": 78.05,
"learning_rate": 4.6103896103896106e-05,
"loss": 2.2074,
"step": 285500
},
{
"epoch": 78.18,
"learning_rate": 4.609706083390294e-05,
"loss": 2.1668,
"step": 286000
},
{
"epoch": 78.32,
"learning_rate": 4.6090225563909775e-05,
"loss": 2.1842,
"step": 286500
},
{
"epoch": 78.46,
"learning_rate": 4.608339029391661e-05,
"loss": 2.1886,
"step": 287000
},
{
"epoch": 78.59,
"learning_rate": 4.6076555023923445e-05,
"loss": 2.1941,
"step": 287500
},
{
"epoch": 78.73,
"learning_rate": 4.6069719753930286e-05,
"loss": 2.2041,
"step": 288000
},
{
"epoch": 78.87,
"learning_rate": 4.606288448393712e-05,
"loss": 2.2174,
"step": 288500
},
{
"epoch": 79.0,
"learning_rate": 4.605604921394395e-05,
"loss": 2.2196,
"step": 289000
},
{
"epoch": 79.14,
"learning_rate": 4.6049213943950784e-05,
"loss": 2.162,
"step": 289500
},
{
"epoch": 79.28,
"learning_rate": 4.6042378673957626e-05,
"loss": 2.1761,
"step": 290000
},
{
"epoch": 79.41,
"learning_rate": 4.603554340396446e-05,
"loss": 2.1889,
"step": 290500
},
{
"epoch": 79.55,
"learning_rate": 4.6028708133971295e-05,
"loss": 2.1878,
"step": 291000
},
{
"epoch": 79.69,
"learning_rate": 4.602187286397813e-05,
"loss": 2.1939,
"step": 291500
},
{
"epoch": 79.83,
"learning_rate": 4.6015037593984965e-05,
"loss": 2.2074,
"step": 292000
},
{
"epoch": 79.96,
"learning_rate": 4.60082023239918e-05,
"loss": 2.2052,
"step": 292500
},
{
"epoch": 80.1,
"learning_rate": 4.6001367053998634e-05,
"loss": 2.1769,
"step": 293000
},
{
"epoch": 80.24,
"learning_rate": 4.599453178400547e-05,
"loss": 2.1675,
"step": 293500
},
{
"epoch": 80.37,
"learning_rate": 4.5987696514012304e-05,
"loss": 2.1722,
"step": 294000
},
{
"epoch": 80.51,
"learning_rate": 4.598086124401914e-05,
"loss": 2.1814,
"step": 294500
},
{
"epoch": 80.65,
"learning_rate": 4.5974025974025974e-05,
"loss": 2.183,
"step": 295000
},
{
"epoch": 80.78,
"learning_rate": 4.5967190704032815e-05,
"loss": 2.1974,
"step": 295500
},
{
"epoch": 80.92,
"learning_rate": 4.596035543403965e-05,
"loss": 2.1974,
"step": 296000
},
{
"epoch": 81.06,
"learning_rate": 4.5953520164046485e-05,
"loss": 2.1853,
"step": 296500
},
{
"epoch": 81.19,
"learning_rate": 4.594668489405331e-05,
"loss": 2.1593,
"step": 297000
},
{
"epoch": 81.33,
"learning_rate": 4.5939849624060154e-05,
"loss": 2.1672,
"step": 297500
},
{
"epoch": 81.47,
"learning_rate": 4.593301435406699e-05,
"loss": 2.1748,
"step": 298000
},
{
"epoch": 81.6,
"learning_rate": 4.5926179084073824e-05,
"loss": 2.1794,
"step": 298500
},
{
"epoch": 81.74,
"learning_rate": 4.591934381408066e-05,
"loss": 2.1888,
"step": 299000
},
{
"epoch": 81.88,
"learning_rate": 4.5912508544087494e-05,
"loss": 2.1932,
"step": 299500
},
{
"epoch": 82.01,
"learning_rate": 4.590567327409433e-05,
"loss": 2.1958,
"step": 300000
},
{
"epoch": 82.15,
"learning_rate": 4.589883800410116e-05,
"loss": 2.1528,
"step": 300500
},
{
"epoch": 82.29,
"learning_rate": 4.5892002734108e-05,
"loss": 2.1538,
"step": 301000
},
{
"epoch": 82.42,
"learning_rate": 4.588516746411484e-05,
"loss": 2.1697,
"step": 301500
},
{
"epoch": 82.56,
"learning_rate": 4.587833219412167e-05,
"loss": 2.1753,
"step": 302000
},
{
"epoch": 82.7,
"learning_rate": 4.58714969241285e-05,
"loss": 2.1771,
"step": 302500
},
{
"epoch": 82.83,
"learning_rate": 4.586466165413534e-05,
"loss": 2.1842,
"step": 303000
},
{
"epoch": 82.97,
"learning_rate": 4.585782638414218e-05,
"loss": 2.1916,
"step": 303500
},
{
"epoch": 83.11,
"learning_rate": 4.5850991114149013e-05,
"loss": 2.1436,
"step": 304000
},
{
"epoch": 83.24,
"learning_rate": 4.584415584415585e-05,
"loss": 2.148,
"step": 304500
},
{
"epoch": 83.38,
"learning_rate": 4.583732057416268e-05,
"loss": 2.1559,
"step": 305000
},
{
"epoch": 83.52,
"learning_rate": 4.583048530416952e-05,
"loss": 2.1686,
"step": 305500
},
{
"epoch": 83.65,
"learning_rate": 4.582365003417635e-05,
"loss": 2.1744,
"step": 306000
},
{
"epoch": 83.79,
"learning_rate": 4.581681476418319e-05,
"loss": 2.1742,
"step": 306500
},
{
"epoch": 83.93,
"learning_rate": 4.580997949419002e-05,
"loss": 2.1881,
"step": 307000
},
{
"epoch": 84.06,
"learning_rate": 4.580314422419686e-05,
"loss": 2.1643,
"step": 307500
},
{
"epoch": 84.2,
"learning_rate": 4.579630895420369e-05,
"loss": 2.1451,
"step": 308000
},
{
"epoch": 84.34,
"learning_rate": 4.5789473684210527e-05,
"loss": 2.1479,
"step": 308500
},
{
"epoch": 84.47,
"learning_rate": 4.578263841421737e-05,
"loss": 2.1579,
"step": 309000
},
{
"epoch": 84.61,
"learning_rate": 4.57758031442242e-05,
"loss": 2.1608,
"step": 309500
},
{
"epoch": 84.75,
"learning_rate": 4.576896787423103e-05,
"loss": 2.1697,
"step": 310000
},
{
"epoch": 84.88,
"learning_rate": 4.5762132604237866e-05,
"loss": 2.1809,
"step": 310500
},
{
"epoch": 85.02,
"learning_rate": 4.575529733424471e-05,
"loss": 2.1723,
"step": 311000
},
{
"epoch": 85.16,
"learning_rate": 4.574846206425154e-05,
"loss": 2.1286,
"step": 311500
},
{
"epoch": 85.29,
"learning_rate": 4.574162679425838e-05,
"loss": 2.1458,
"step": 312000
},
{
"epoch": 85.43,
"learning_rate": 4.5734791524265205e-05,
"loss": 2.1496,
"step": 312500
},
{
"epoch": 85.57,
"learning_rate": 4.5727956254272047e-05,
"loss": 2.1572,
"step": 313000
},
{
"epoch": 85.7,
"learning_rate": 4.572112098427888e-05,
"loss": 2.1648,
"step": 313500
},
{
"epoch": 85.84,
"learning_rate": 4.5714285714285716e-05,
"loss": 2.1736,
"step": 314000
},
{
"epoch": 85.98,
"learning_rate": 4.570745044429256e-05,
"loss": 2.1776,
"step": 314500
},
{
"epoch": 86.11,
"learning_rate": 4.5700615174299386e-05,
"loss": 2.1304,
"step": 315000
},
{
"epoch": 86.25,
"learning_rate": 4.569377990430622e-05,
"loss": 2.1302,
"step": 315500
},
{
"epoch": 86.39,
"learning_rate": 4.5686944634313055e-05,
"loss": 2.1441,
"step": 316000
},
{
"epoch": 86.52,
"learning_rate": 4.56801093643199e-05,
"loss": 2.1551,
"step": 316500
},
{
"epoch": 86.66,
"learning_rate": 4.567327409432673e-05,
"loss": 2.1582,
"step": 317000
},
{
"epoch": 86.8,
"learning_rate": 4.566643882433356e-05,
"loss": 2.1666,
"step": 317500
},
{
"epoch": 86.93,
"learning_rate": 4.5659603554340394e-05,
"loss": 2.1599,
"step": 318000
},
{
"epoch": 87.07,
"learning_rate": 4.5652768284347236e-05,
"loss": 2.1394,
"step": 318500
},
{
"epoch": 87.21,
"learning_rate": 4.564593301435407e-05,
"loss": 2.1233,
"step": 319000
},
{
"epoch": 87.34,
"learning_rate": 4.5639097744360906e-05,
"loss": 2.1365,
"step": 319500
},
{
"epoch": 87.48,
"learning_rate": 4.563226247436774e-05,
"loss": 2.1441,
"step": 320000
},
{
"epoch": 87.62,
"learning_rate": 4.5625427204374575e-05,
"loss": 2.1482,
"step": 320500
},
{
"epoch": 87.75,
"learning_rate": 4.561859193438141e-05,
"loss": 2.1599,
"step": 321000
},
{
"epoch": 87.89,
"learning_rate": 4.5611756664388245e-05,
"loss": 2.1559,
"step": 321500
},
{
"epoch": 88.03,
"learning_rate": 4.560492139439508e-05,
"loss": 2.1513,
"step": 322000
},
{
"epoch": 88.16,
"learning_rate": 4.5598086124401914e-05,
"loss": 2.115,
"step": 322500
},
{
"epoch": 88.3,
"learning_rate": 4.559125085440875e-05,
"loss": 2.1336,
"step": 323000
},
{
"epoch": 88.44,
"learning_rate": 4.5584415584415584e-05,
"loss": 2.1394,
"step": 323500
},
{
"epoch": 88.57,
"learning_rate": 4.5577580314422426e-05,
"loss": 2.1366,
"step": 324000
},
{
"epoch": 88.71,
"learning_rate": 4.557074504442926e-05,
"loss": 2.1424,
"step": 324500
},
{
"epoch": 88.85,
"learning_rate": 4.5563909774436095e-05,
"loss": 2.151,
"step": 325000
},
{
"epoch": 88.98,
"learning_rate": 4.555707450444292e-05,
"loss": 2.1611,
"step": 325500
},
{
"epoch": 89.12,
"learning_rate": 4.5550239234449765e-05,
"loss": 2.1216,
"step": 326000
},
{
"epoch": 89.26,
"learning_rate": 4.55434039644566e-05,
"loss": 2.1112,
"step": 326500
},
{
"epoch": 89.39,
"learning_rate": 4.5536568694463434e-05,
"loss": 2.1246,
"step": 327000
},
{
"epoch": 89.53,
"learning_rate": 4.552973342447027e-05,
"loss": 2.1361,
"step": 327500
},
{
"epoch": 89.67,
"learning_rate": 4.5522898154477104e-05,
"loss": 2.1375,
"step": 328000
},
{
"epoch": 89.8,
"learning_rate": 4.551606288448394e-05,
"loss": 2.1438,
"step": 328500
},
{
"epoch": 89.94,
"learning_rate": 4.5509227614490773e-05,
"loss": 2.1525,
"step": 329000
},
{
"epoch": 90.08,
"learning_rate": 4.550239234449761e-05,
"loss": 2.127,
"step": 329500
},
{
"epoch": 90.21,
"learning_rate": 4.549555707450445e-05,
"loss": 2.1043,
"step": 330000
},
{
"epoch": 90.35,
"learning_rate": 4.548872180451128e-05,
"loss": 2.1148,
"step": 330500
},
{
"epoch": 90.49,
"learning_rate": 4.548188653451811e-05,
"loss": 2.1282,
"step": 331000
},
{
"epoch": 90.62,
"learning_rate": 4.547505126452495e-05,
"loss": 2.1347,
"step": 331500
},
{
"epoch": 90.76,
"learning_rate": 4.546821599453179e-05,
"loss": 2.1465,
"step": 332000
},
{
"epoch": 90.9,
"learning_rate": 4.5461380724538624e-05,
"loss": 2.1457,
"step": 332500
},
{
"epoch": 91.03,
"learning_rate": 4.545454545454546e-05,
"loss": 2.1369,
"step": 333000
},
{
"epoch": 91.17,
"learning_rate": 4.544771018455229e-05,
"loss": 2.0965,
"step": 333500
},
{
"epoch": 91.31,
"learning_rate": 4.544087491455913e-05,
"loss": 2.1165,
"step": 334000
},
{
"epoch": 91.44,
"learning_rate": 4.543403964456596e-05,
"loss": 2.1213,
"step": 334500
},
{
"epoch": 91.58,
"learning_rate": 4.54272043745728e-05,
"loss": 2.1286,
"step": 335000
},
{
"epoch": 91.72,
"learning_rate": 4.542036910457963e-05,
"loss": 2.1284,
"step": 335500
},
{
"epoch": 91.85,
"learning_rate": 4.541353383458647e-05,
"loss": 2.1407,
"step": 336000
},
{
"epoch": 91.99,
"learning_rate": 4.54066985645933e-05,
"loss": 2.1417,
"step": 336500
},
{
"epoch": 92.13,
"learning_rate": 4.539986329460014e-05,
"loss": 2.0955,
"step": 337000
},
{
"epoch": 92.26,
"learning_rate": 4.539302802460698e-05,
"loss": 2.0994,
"step": 337500
},
{
"epoch": 92.4,
"learning_rate": 4.538619275461381e-05,
"loss": 2.1162,
"step": 338000
},
{
"epoch": 92.54,
"learning_rate": 4.537935748462064e-05,
"loss": 2.1158,
"step": 338500
},
{
"epoch": 92.67,
"learning_rate": 4.5372522214627476e-05,
"loss": 2.1289,
"step": 339000
},
{
"epoch": 92.81,
"learning_rate": 4.536568694463432e-05,
"loss": 2.1288,
"step": 339500
},
{
"epoch": 92.95,
"learning_rate": 4.535885167464115e-05,
"loss": 2.1417,
"step": 340000
},
{
"epoch": 93.08,
"learning_rate": 4.535201640464799e-05,
"loss": 2.1089,
"step": 340500
},
{
"epoch": 93.22,
"learning_rate": 4.5345181134654815e-05,
"loss": 2.0924,
"step": 341000
},
{
"epoch": 93.36,
"learning_rate": 4.533834586466166e-05,
"loss": 2.1037,
"step": 341500
},
{
"epoch": 93.49,
"learning_rate": 4.533151059466849e-05,
"loss": 2.1097,
"step": 342000
},
{
"epoch": 93.63,
"learning_rate": 4.5324675324675326e-05,
"loss": 2.1164,
"step": 342500
},
{
"epoch": 93.77,
"learning_rate": 4.531784005468217e-05,
"loss": 2.1277,
"step": 343000
},
{
"epoch": 93.9,
"learning_rate": 4.5311004784688996e-05,
"loss": 2.1281,
"step": 343500
},
{
"epoch": 94.04,
"learning_rate": 4.530416951469583e-05,
"loss": 2.1238,
"step": 344000
},
{
"epoch": 94.18,
"learning_rate": 4.5297334244702666e-05,
"loss": 2.0879,
"step": 344500
},
{
"epoch": 94.31,
"learning_rate": 4.529049897470951e-05,
"loss": 2.0903,
"step": 345000
},
{
"epoch": 94.45,
"learning_rate": 4.528366370471634e-05,
"loss": 2.1058,
"step": 345500
},
{
"epoch": 94.59,
"learning_rate": 4.527682843472317e-05,
"loss": 2.1162,
"step": 346000
},
{
"epoch": 94.72,
"learning_rate": 4.5269993164730005e-05,
"loss": 2.1162,
"step": 346500
},
{
"epoch": 94.86,
"learning_rate": 4.5263157894736846e-05,
"loss": 2.1276,
"step": 347000
},
{
"epoch": 95.0,
"learning_rate": 4.525632262474368e-05,
"loss": 2.1259,
"step": 347500
},
{
"epoch": 95.13,
"learning_rate": 4.5249487354750516e-05,
"loss": 2.0818,
"step": 348000
},
{
"epoch": 95.27,
"learning_rate": 4.524265208475735e-05,
"loss": 2.0907,
"step": 348500
},
{
"epoch": 95.41,
"learning_rate": 4.5235816814764186e-05,
"loss": 2.0926,
"step": 349000
},
{
"epoch": 95.54,
"learning_rate": 4.522898154477102e-05,
"loss": 2.1014,
"step": 349500
},
{
"epoch": 95.68,
"learning_rate": 4.5222146274777855e-05,
"loss": 2.1133,
"step": 350000
},
{
"epoch": 95.82,
"learning_rate": 4.521531100478469e-05,
"loss": 2.1189,
"step": 350500
},
{
"epoch": 95.95,
"learning_rate": 4.5208475734791525e-05,
"loss": 2.1202,
"step": 351000
},
{
"epoch": 96.09,
"learning_rate": 4.520164046479836e-05,
"loss": 2.0911,
"step": 351500
},
{
"epoch": 96.23,
"learning_rate": 4.5194805194805194e-05,
"loss": 2.0824,
"step": 352000
},
{
"epoch": 96.36,
"learning_rate": 4.5187969924812036e-05,
"loss": 2.0898,
"step": 352500
},
{
"epoch": 96.5,
"learning_rate": 4.518113465481887e-05,
"loss": 2.0946,
"step": 353000
},
{
"epoch": 96.64,
"learning_rate": 4.5174299384825705e-05,
"loss": 2.1039,
"step": 353500
},
{
"epoch": 96.77,
"learning_rate": 4.5167464114832533e-05,
"loss": 2.1076,
"step": 354000
},
{
"epoch": 96.91,
"learning_rate": 4.5160628844839375e-05,
"loss": 2.1183,
"step": 354500
},
{
"epoch": 97.05,
"learning_rate": 4.515379357484621e-05,
"loss": 2.1028,
"step": 355000
},
{
"epoch": 97.18,
"learning_rate": 4.5146958304853045e-05,
"loss": 2.0748,
"step": 355500
},
{
"epoch": 97.32,
"learning_rate": 4.514012303485988e-05,
"loss": 2.082,
"step": 356000
},
{
"epoch": 97.46,
"learning_rate": 4.5133287764866714e-05,
"loss": 2.0929,
"step": 356500
},
{
"epoch": 97.59,
"learning_rate": 4.512645249487355e-05,
"loss": 2.0978,
"step": 357000
},
{
"epoch": 97.73,
"learning_rate": 4.5119617224880384e-05,
"loss": 2.1015,
"step": 357500
},
{
"epoch": 97.87,
"learning_rate": 4.511278195488722e-05,
"loss": 2.1031,
"step": 358000
},
{
"epoch": 98.0,
"learning_rate": 4.510594668489406e-05,
"loss": 2.1172,
"step": 358500
},
{
"epoch": 98.14,
"learning_rate": 4.509911141490089e-05,
"loss": 2.0695,
"step": 359000
},
{
"epoch": 98.28,
"learning_rate": 4.509227614490772e-05,
"loss": 2.0733,
"step": 359500
},
{
"epoch": 98.41,
"learning_rate": 4.5085440874914565e-05,
"loss": 2.0832,
"step": 360000
},
{
"epoch": 98.55,
"learning_rate": 4.50786056049214e-05,
"loss": 0.0029,
"step": 360500
},
{
"epoch": 98.69,
"learning_rate": 4.5071770334928234e-05,
"loss": 2.0982,
"step": 361000
},
{
"epoch": 98.82,
"learning_rate": 4.506493506493506e-05,
"loss": 2.0996,
"step": 361500
},
{
"epoch": 98.96,
"learning_rate": 4.5058099794941904e-05,
"loss": 2.1084,
"step": 362000
},
{
"epoch": 99.1,
"learning_rate": 4.505126452494874e-05,
"loss": 2.0753,
"step": 362500
},
{
"epoch": 99.23,
"learning_rate": 4.504442925495557e-05,
"loss": 2.0645,
"step": 363000
},
{
"epoch": 99.37,
"learning_rate": 4.503759398496241e-05,
"loss": 2.0722,
"step": 363500
},
{
"epoch": 99.51,
"learning_rate": 4.503075871496924e-05,
"loss": 2.0849,
"step": 364000
},
{
"epoch": 99.64,
"learning_rate": 4.502392344497608e-05,
"loss": 2.0903,
"step": 364500
},
{
"epoch": 99.78,
"learning_rate": 4.501708817498291e-05,
"loss": 2.0973,
"step": 365000
},
{
"epoch": 99.92,
"learning_rate": 4.501025290498975e-05,
"loss": 2.1043,
"step": 365500
},
{
"epoch": 100.05,
"learning_rate": 4.500341763499659e-05,
"loss": 2.0809,
"step": 366000
},
{
"epoch": 100.19,
"learning_rate": 4.499658236500342e-05,
"loss": 2.0633,
"step": 366500
},
{
"epoch": 100.33,
"learning_rate": 4.498974709501025e-05,
"loss": 2.0694,
"step": 367000
},
{
"epoch": 100.46,
"learning_rate": 4.4982911825017086e-05,
"loss": 2.0763,
"step": 367500
},
{
"epoch": 100.6,
"learning_rate": 4.497607655502393e-05,
"loss": 2.0849,
"step": 368000
},
{
"epoch": 100.74,
"learning_rate": 4.496924128503076e-05,
"loss": 2.0855,
"step": 368500
},
{
"epoch": 100.87,
"learning_rate": 4.49624060150376e-05,
"loss": 2.0935,
"step": 369000
},
{
"epoch": 101.01,
"learning_rate": 4.495557074504443e-05,
"loss": 2.1002,
"step": 369500
},
{
"epoch": 101.15,
"learning_rate": 4.494873547505127e-05,
"loss": 2.0488,
"step": 370000
},
{
"epoch": 101.28,
"learning_rate": 4.49419002050581e-05,
"loss": 2.0613,
"step": 370500
},
{
"epoch": 101.42,
"learning_rate": 4.493506493506494e-05,
"loss": 2.0637,
"step": 371000
},
{
"epoch": 101.56,
"learning_rate": 4.492822966507177e-05,
"loss": 2.0769,
"step": 371500
},
{
"epoch": 101.69,
"learning_rate": 4.4921394395078606e-05,
"loss": 2.086,
"step": 372000
},
{
"epoch": 101.83,
"learning_rate": 4.491455912508544e-05,
"loss": 2.0914,
"step": 372500
},
{
"epoch": 101.97,
"learning_rate": 4.4907723855092276e-05,
"loss": 2.0974,
"step": 373000
},
{
"epoch": 102.1,
"learning_rate": 4.490088858509912e-05,
"loss": 2.0534,
"step": 373500
},
{
"epoch": 102.24,
"learning_rate": 4.489405331510595e-05,
"loss": 2.0527,
"step": 374000
},
{
"epoch": 102.38,
"learning_rate": 4.488721804511278e-05,
"loss": 2.0637,
"step": 374500
},
{
"epoch": 102.52,
"learning_rate": 4.4880382775119615e-05,
"loss": 2.0692,
"step": 375000
},
{
"epoch": 102.65,
"learning_rate": 4.487354750512646e-05,
"loss": 2.078,
"step": 375500
},
{
"epoch": 102.79,
"learning_rate": 4.486671223513329e-05,
"loss": 2.0788,
"step": 376000
},
{
"epoch": 102.93,
"learning_rate": 4.4859876965140126e-05,
"loss": 2.089,
"step": 376500
},
{
"epoch": 103.06,
"learning_rate": 4.485304169514696e-05,
"loss": 2.0704,
"step": 377000
},
{
"epoch": 103.2,
"learning_rate": 4.4846206425153796e-05,
"loss": 2.0524,
"step": 377500
},
{
"epoch": 103.34,
"learning_rate": 4.483937115516063e-05,
"loss": 2.0481,
"step": 378000
},
{
"epoch": 103.47,
"learning_rate": 4.4832535885167465e-05,
"loss": 2.0607,
"step": 378500
},
{
"epoch": 103.61,
"learning_rate": 4.482570061517431e-05,
"loss": 2.0742,
"step": 379000
},
{
"epoch": 103.75,
"learning_rate": 4.4818865345181135e-05,
"loss": 2.0698,
"step": 379500
},
{
"epoch": 103.88,
"learning_rate": 4.481203007518797e-05,
"loss": 2.0826,
"step": 380000
},
{
"epoch": 104.02,
"learning_rate": 4.4805194805194805e-05,
"loss": 2.0789,
"step": 380500
},
{
"epoch": 104.16,
"learning_rate": 4.4798359535201646e-05,
"loss": 2.0342,
"step": 381000
},
{
"epoch": 104.29,
"learning_rate": 4.479152426520848e-05,
"loss": 2.0422,
"step": 381500
},
{
"epoch": 104.43,
"learning_rate": 4.4784688995215316e-05,
"loss": 2.0582,
"step": 382000
},
{
"epoch": 104.57,
"learning_rate": 4.4777853725222144e-05,
"loss": 2.0651,
"step": 382500
},
{
"epoch": 104.7,
"learning_rate": 4.4771018455228985e-05,
"loss": 2.0687,
"step": 383000
},
{
"epoch": 104.84,
"learning_rate": 4.476418318523582e-05,
"loss": 2.0763,
"step": 383500
},
{
"epoch": 104.98,
"learning_rate": 4.4757347915242655e-05,
"loss": 2.0866,
"step": 384000
},
{
"epoch": 105.11,
"learning_rate": 4.475051264524949e-05,
"loss": 2.0387,
"step": 384500
},
{
"epoch": 105.25,
"learning_rate": 4.4743677375256325e-05,
"loss": 2.0398,
"step": 385000
},
{
"epoch": 105.39,
"learning_rate": 4.473684210526316e-05,
"loss": 2.0542,
"step": 385500
},
{
"epoch": 105.52,
"learning_rate": 4.4730006835269994e-05,
"loss": 2.0551,
"step": 386000
},
{
"epoch": 105.66,
"learning_rate": 4.472317156527683e-05,
"loss": 2.0639,
"step": 386500
},
{
"epoch": 105.8,
"learning_rate": 4.471633629528367e-05,
"loss": 2.0706,
"step": 387000
},
{
"epoch": 105.93,
"learning_rate": 4.47095010252905e-05,
"loss": 2.0742,
"step": 387500
},
{
"epoch": 106.07,
"learning_rate": 4.470266575529733e-05,
"loss": 2.0517,
"step": 388000
},
{
"epoch": 106.21,
"learning_rate": 4.4695830485304175e-05,
"loss": 2.0298,
"step": 388500
},
{
"epoch": 106.34,
"learning_rate": 4.468899521531101e-05,
"loss": 2.0385,
"step": 389000
},
{
"epoch": 106.48,
"learning_rate": 4.4682159945317844e-05,
"loss": 2.051,
"step": 389500
},
{
"epoch": 106.62,
"learning_rate": 4.467532467532467e-05,
"loss": 2.0592,
"step": 390000
},
{
"epoch": 106.75,
"learning_rate": 4.4668489405331514e-05,
"loss": 2.0676,
"step": 390500
},
{
"epoch": 106.89,
"learning_rate": 4.466165413533835e-05,
"loss": 2.0695,
"step": 391000
},
{
"epoch": 107.03,
"learning_rate": 4.4654818865345184e-05,
"loss": 2.0598,
"step": 391500
},
{
"epoch": 107.16,
"learning_rate": 4.464798359535202e-05,
"loss": 2.024,
"step": 392000
},
{
"epoch": 107.3,
"learning_rate": 4.464114832535885e-05,
"loss": 2.0372,
"step": 392500
},
{
"epoch": 107.44,
"learning_rate": 4.463431305536569e-05,
"loss": 2.0433,
"step": 393000
},
{
"epoch": 107.57,
"learning_rate": 4.462747778537252e-05,
"loss": 2.0472,
"step": 393500
},
{
"epoch": 107.71,
"learning_rate": 4.462064251537936e-05,
"loss": 2.0579,
"step": 394000
},
{
"epoch": 107.85,
"learning_rate": 4.46138072453862e-05,
"loss": 2.0605,
"step": 394500
},
{
"epoch": 107.98,
"learning_rate": 4.460697197539303e-05,
"loss": 2.0745,
"step": 395000
},
{
"epoch": 108.12,
"learning_rate": 4.460013670539986e-05,
"loss": 2.026,
"step": 395500
},
{
"epoch": 108.26,
"learning_rate": 4.45933014354067e-05,
"loss": 2.0251,
"step": 396000
},
{
"epoch": 108.39,
"learning_rate": 4.458646616541354e-05,
"loss": 2.0438,
"step": 396500
},
{
"epoch": 108.53,
"learning_rate": 4.457963089542037e-05,
"loss": 2.0407,
"step": 397000
},
{
"epoch": 108.67,
"learning_rate": 4.457279562542721e-05,
"loss": 2.0477,
"step": 397500
},
{
"epoch": 108.8,
"learning_rate": 4.456596035543404e-05,
"loss": 2.0536,
"step": 398000
},
{
"epoch": 108.94,
"learning_rate": 4.455912508544088e-05,
"loss": 2.065,
"step": 398500
},
{
"epoch": 109.08,
"learning_rate": 4.455228981544771e-05,
"loss": 2.0385,
"step": 399000
},
{
"epoch": 109.21,
"learning_rate": 4.454545454545455e-05,
"loss": 2.0245,
"step": 399500
},
{
"epoch": 109.35,
"learning_rate": 4.453861927546138e-05,
"loss": 2.0304,
"step": 400000
},
{
"epoch": 109.49,
"learning_rate": 4.453178400546822e-05,
"loss": 2.0395,
"step": 400500
},
{
"epoch": 109.62,
"learning_rate": 4.452494873547505e-05,
"loss": 2.0405,
"step": 401000
},
{
"epoch": 109.76,
"learning_rate": 4.4518113465481886e-05,
"loss": 2.0475,
"step": 401500
},
{
"epoch": 109.9,
"learning_rate": 4.451127819548873e-05,
"loss": 2.0538,
"step": 402000
},
{
"epoch": 110.03,
"learning_rate": 4.450444292549556e-05,
"loss": 2.0518,
"step": 402500
},
{
"epoch": 110.17,
"learning_rate": 4.449760765550239e-05,
"loss": 2.0132,
"step": 403000
},
{
"epoch": 110.31,
"learning_rate": 4.4490772385509225e-05,
"loss": 2.0259,
"step": 403500
},
{
"epoch": 110.44,
"learning_rate": 4.448393711551607e-05,
"loss": 2.0302,
"step": 404000
},
{
"epoch": 110.58,
"learning_rate": 4.44771018455229e-05,
"loss": 2.0392,
"step": 404500
},
{
"epoch": 110.72,
"learning_rate": 4.4470266575529737e-05,
"loss": 2.0429,
"step": 405000
},
{
"epoch": 110.85,
"learning_rate": 4.446343130553657e-05,
"loss": 2.0444,
"step": 405500
},
{
"epoch": 110.99,
"learning_rate": 4.4456596035543406e-05,
"loss": 2.0542,
"step": 406000
},
{
"epoch": 111.13,
"learning_rate": 4.444976076555024e-05,
"loss": 2.0086,
"step": 406500
},
{
"epoch": 111.26,
"learning_rate": 4.4442925495557076e-05,
"loss": 2.0216,
"step": 407000
},
{
"epoch": 111.4,
"learning_rate": 4.443609022556392e-05,
"loss": 2.0197,
"step": 407500
},
{
"epoch": 111.54,
"learning_rate": 4.4429254955570745e-05,
"loss": 2.032,
"step": 408000
},
{
"epoch": 111.67,
"learning_rate": 4.442241968557758e-05,
"loss": 2.0413,
"step": 408500
},
{
"epoch": 111.81,
"learning_rate": 4.4415584415584415e-05,
"loss": 2.0456,
"step": 409000
},
{
"epoch": 111.95,
"learning_rate": 4.4408749145591257e-05,
"loss": 2.047,
"step": 409500
},
{
"epoch": 112.08,
"learning_rate": 4.440191387559809e-05,
"loss": 2.0248,
"step": 410000
},
{
"epoch": 112.22,
"learning_rate": 4.4395078605604926e-05,
"loss": 2.0108,
"step": 410500
},
{
"epoch": 112.36,
"learning_rate": 4.4388243335611754e-05,
"loss": 2.0189,
"step": 411000
},
{
"epoch": 112.49,
"learning_rate": 4.4381408065618596e-05,
"loss": 2.0227,
"step": 411500
},
{
"epoch": 112.63,
"learning_rate": 4.437457279562543e-05,
"loss": 2.0325,
"step": 412000
},
{
"epoch": 112.77,
"learning_rate": 4.4367737525632265e-05,
"loss": 2.041,
"step": 412500
},
{
"epoch": 112.9,
"learning_rate": 4.43609022556391e-05,
"loss": 2.0367,
"step": 413000
},
{
"epoch": 113.04,
"learning_rate": 4.4354066985645935e-05,
"loss": 2.0309,
"step": 413500
},
{
"epoch": 113.18,
"learning_rate": 4.434723171565277e-05,
"loss": 1.9949,
"step": 414000
},
{
"epoch": 113.31,
"learning_rate": 4.4340396445659604e-05,
"loss": 2.0091,
"step": 414500
},
{
"epoch": 113.45,
"learning_rate": 4.433356117566644e-05,
"loss": 2.0185,
"step": 415000
},
{
"epoch": 113.59,
"learning_rate": 4.432672590567328e-05,
"loss": 2.0322,
"step": 415500
},
{
"epoch": 113.72,
"learning_rate": 4.431989063568011e-05,
"loss": 2.0378,
"step": 416000
},
{
"epoch": 113.86,
"learning_rate": 4.4313055365686944e-05,
"loss": 2.0344,
"step": 416500
},
{
"epoch": 114.0,
"learning_rate": 4.4306220095693785e-05,
"loss": 2.0438,
"step": 417000
},
{
"epoch": 114.13,
"learning_rate": 4.429938482570062e-05,
"loss": 1.9927,
"step": 417500
},
{
"epoch": 114.27,
"learning_rate": 4.4292549555707455e-05,
"loss": 1.9996,
"step": 418000
},
{
"epoch": 114.41,
"learning_rate": 4.428571428571428e-05,
"loss": 2.0126,
"step": 418500
},
{
"epoch": 114.54,
"learning_rate": 4.4278879015721124e-05,
"loss": 2.0162,
"step": 419000
},
{
"epoch": 114.68,
"learning_rate": 4.427204374572796e-05,
"loss": 2.0288,
"step": 419500
},
{
"epoch": 114.82,
"learning_rate": 4.4265208475734794e-05,
"loss": 2.035,
"step": 420000
},
{
"epoch": 114.95,
"learning_rate": 4.425837320574163e-05,
"loss": 2.0395,
"step": 420500
},
{
"epoch": 115.09,
"learning_rate": 4.4251537935748464e-05,
"loss": 2.0078,
"step": 421000
},
{
"epoch": 115.23,
"learning_rate": 4.42447026657553e-05,
"loss": 2.0002,
"step": 421500
},
{
"epoch": 115.36,
"learning_rate": 4.423786739576213e-05,
"loss": 2.0034,
"step": 422000
},
{
"epoch": 115.5,
"learning_rate": 4.423103212576897e-05,
"loss": 2.0088,
"step": 422500
},
{
"epoch": 115.64,
"learning_rate": 4.422419685577581e-05,
"loss": 2.0203,
"step": 423000
},
{
"epoch": 115.77,
"learning_rate": 4.421736158578264e-05,
"loss": 2.0238,
"step": 423500
},
{
"epoch": 115.91,
"learning_rate": 4.421052631578947e-05,
"loss": 2.0346,
"step": 424000
},
{
"epoch": 116.05,
"learning_rate": 4.4203691045796314e-05,
"loss": 2.0185,
"step": 424500
},
{
"epoch": 116.18,
"learning_rate": 4.419685577580315e-05,
"loss": 1.9889,
"step": 425000
},
{
"epoch": 116.32,
"learning_rate": 4.4190020505809983e-05,
"loss": 1.9968,
"step": 425500
},
{
"epoch": 116.46,
"learning_rate": 4.418318523581682e-05,
"loss": 2.0024,
"step": 426000
},
{
"epoch": 116.59,
"learning_rate": 4.417634996582365e-05,
"loss": 2.0146,
"step": 426500
},
{
"epoch": 116.73,
"learning_rate": 4.416951469583049e-05,
"loss": 2.0248,
"step": 427000
},
{
"epoch": 116.87,
"learning_rate": 4.416267942583732e-05,
"loss": 2.0304,
"step": 427500
},
{
"epoch": 117.0,
"learning_rate": 4.415584415584416e-05,
"loss": 2.027,
"step": 428000
},
{
"epoch": 117.14,
"learning_rate": 4.414900888585099e-05,
"loss": 1.9796,
"step": 428500
},
{
"epoch": 117.28,
"learning_rate": 4.414217361585783e-05,
"loss": 1.9886,
"step": 429000
},
{
"epoch": 117.41,
"learning_rate": 4.413533834586466e-05,
"loss": 2.0039,
"step": 429500
},
{
"epoch": 117.55,
"learning_rate": 4.4128503075871497e-05,
"loss": 2.0054,
"step": 430000
},
{
"epoch": 117.69,
"learning_rate": 4.412166780587834e-05,
"loss": 2.0173,
"step": 430500
},
{
"epoch": 117.82,
"learning_rate": 4.411483253588517e-05,
"loss": 2.0238,
"step": 431000
},
{
"epoch": 117.96,
"learning_rate": 4.4107997265892e-05,
"loss": 2.0268,
"step": 431500
},
{
"epoch": 118.1,
"learning_rate": 4.4101161995898836e-05,
"loss": 1.9865,
"step": 432000
},
{
"epoch": 118.23,
"learning_rate": 4.409432672590568e-05,
"loss": 1.9889,
"step": 432500
},
{
"epoch": 118.37,
"learning_rate": 4.408749145591251e-05,
"loss": 1.9964,
"step": 433000
},
{
"epoch": 118.51,
"learning_rate": 4.408065618591935e-05,
"loss": 2.0049,
"step": 433500
},
{
"epoch": 118.64,
"learning_rate": 4.407382091592618e-05,
"loss": 2.0078,
"step": 434000
},
{
"epoch": 118.78,
"learning_rate": 4.4066985645933017e-05,
"loss": 2.0146,
"step": 434500
},
{
"epoch": 118.92,
"learning_rate": 4.406015037593985e-05,
"loss": 2.016,
"step": 435000
},
{
"epoch": 119.05,
"learning_rate": 4.4053315105946686e-05,
"loss": 2.0019,
"step": 435500
},
{
"epoch": 119.19,
"learning_rate": 4.404647983595353e-05,
"loss": 1.9757,
"step": 436000
},
{
"epoch": 119.33,
"learning_rate": 4.4039644565960356e-05,
"loss": 1.9861,
"step": 436500
},
{
"epoch": 119.46,
"learning_rate": 4.403280929596719e-05,
"loss": 1.9953,
"step": 437000
},
{
"epoch": 119.6,
"learning_rate": 4.4025974025974025e-05,
"loss": 2.005,
"step": 437500
},
{
"epoch": 119.74,
"learning_rate": 4.401913875598087e-05,
"loss": 2.0055,
"step": 438000
},
{
"epoch": 119.87,
"learning_rate": 4.40123034859877e-05,
"loss": 2.0174,
"step": 438500
},
{
"epoch": 120.01,
"learning_rate": 4.4005468215994536e-05,
"loss": 2.0204,
"step": 439000
},
{
"epoch": 120.15,
"learning_rate": 4.3998632946001364e-05,
"loss": 1.9663,
"step": 439500
},
{
"epoch": 120.28,
"learning_rate": 4.3991797676008206e-05,
"loss": 1.9818,
"step": 440000
},
{
"epoch": 120.42,
"learning_rate": 4.398496240601504e-05,
"loss": 1.9914,
"step": 440500
},
{
"epoch": 120.56,
"learning_rate": 4.3978127136021876e-05,
"loss": 1.9949,
"step": 441000
},
{
"epoch": 120.69,
"learning_rate": 4.397129186602871e-05,
"loss": 2.0031,
"step": 441500
},
{
"epoch": 120.83,
"learning_rate": 4.3964456596035545e-05,
"loss": 2.0048,
"step": 442000
},
{
"epoch": 120.97,
"learning_rate": 4.395762132604238e-05,
"loss": 2.018,
"step": 442500
},
{
"epoch": 121.1,
"learning_rate": 4.3950786056049215e-05,
"loss": 1.9803,
"step": 443000
},
{
"epoch": 121.24,
"learning_rate": 4.3943950786056056e-05,
"loss": 1.9769,
"step": 443500
},
{
"epoch": 121.38,
"learning_rate": 4.393711551606289e-05,
"loss": 1.9786,
"step": 444000
},
{
"epoch": 121.51,
"learning_rate": 4.393028024606972e-05,
"loss": 1.99,
"step": 444500
},
{
"epoch": 121.65,
"learning_rate": 4.3923444976076554e-05,
"loss": 1.9929,
"step": 445000
},
{
"epoch": 121.79,
"learning_rate": 4.3916609706083396e-05,
"loss": 2.0034,
"step": 445500
},
{
"epoch": 121.92,
"learning_rate": 4.390977443609023e-05,
"loss": 2.0121,
"step": 446000
},
{
"epoch": 122.06,
"learning_rate": 4.3902939166097065e-05,
"loss": 1.9899,
"step": 446500
},
{
"epoch": 122.2,
"learning_rate": 4.389610389610389e-05,
"loss": 1.9649,
"step": 447000
},
{
"epoch": 122.33,
"learning_rate": 4.3889268626110735e-05,
"loss": 1.9764,
"step": 447500
},
{
"epoch": 122.47,
"learning_rate": 4.388243335611757e-05,
"loss": 1.9795,
"step": 448000
},
{
"epoch": 122.61,
"learning_rate": 4.3875598086124404e-05,
"loss": 1.9988,
"step": 448500
},
{
"epoch": 122.74,
"learning_rate": 4.386876281613124e-05,
"loss": 1.9975,
"step": 449000
},
{
"epoch": 122.88,
"learning_rate": 4.3861927546138074e-05,
"loss": 2.007,
"step": 449500
},
{
"epoch": 123.02,
"learning_rate": 4.385509227614491e-05,
"loss": 2.0015,
"step": 450000
},
{
"epoch": 123.15,
"learning_rate": 4.3848257006151743e-05,
"loss": 1.9606,
"step": 450500
},
{
"epoch": 123.29,
"learning_rate": 4.384142173615858e-05,
"loss": 1.9646,
"step": 451000
},
{
"epoch": 123.43,
"learning_rate": 4.383458646616542e-05,
"loss": 1.9758,
"step": 451500
},
{
"epoch": 123.56,
"learning_rate": 4.382775119617225e-05,
"loss": 1.9893,
"step": 452000
},
{
"epoch": 123.7,
"learning_rate": 4.382091592617908e-05,
"loss": 1.9943,
"step": 452500
},
{
"epoch": 123.84,
"learning_rate": 4.3814080656185924e-05,
"loss": 1.9997,
"step": 453000
},
{
"epoch": 123.97,
"learning_rate": 4.380724538619276e-05,
"loss": 2.0071,
"step": 453500
},
{
"epoch": 124.11,
"learning_rate": 4.3800410116199594e-05,
"loss": 1.9643,
"step": 454000
},
{
"epoch": 124.25,
"learning_rate": 4.379357484620643e-05,
"loss": 1.9644,
"step": 454500
},
{
"epoch": 124.38,
"learning_rate": 4.378673957621326e-05,
"loss": 1.9718,
"step": 455000
},
{
"epoch": 124.52,
"learning_rate": 4.37799043062201e-05,
"loss": 1.9801,
"step": 455500
},
{
"epoch": 124.66,
"learning_rate": 4.377306903622693e-05,
"loss": 1.9836,
"step": 456000
},
{
"epoch": 124.79,
"learning_rate": 4.376623376623377e-05,
"loss": 1.9961,
"step": 456500
},
{
"epoch": 124.93,
"learning_rate": 4.37593984962406e-05,
"loss": 1.9996,
"step": 457000
},
{
"epoch": 125.07,
"learning_rate": 4.375256322624744e-05,
"loss": 1.9744,
"step": 457500
},
{
"epoch": 125.21,
"learning_rate": 4.374572795625427e-05,
"loss": 1.9558,
"step": 458000
},
{
"epoch": 125.34,
"learning_rate": 4.373889268626111e-05,
"loss": 1.9701,
"step": 458500
},
{
"epoch": 125.48,
"learning_rate": 4.373205741626795e-05,
"loss": 1.971,
"step": 459000
},
{
"epoch": 125.62,
"learning_rate": 4.372522214627478e-05,
"loss": 1.9868,
"step": 459500
},
{
"epoch": 125.75,
"learning_rate": 4.371838687628161e-05,
"loss": 1.9827,
"step": 460000
},
{
"epoch": 125.89,
"learning_rate": 4.3711551606288446e-05,
"loss": 1.9944,
"step": 460500
},
{
"epoch": 126.03,
"learning_rate": 4.370471633629529e-05,
"loss": 1.9864,
"step": 461000
},
{
"epoch": 126.16,
"learning_rate": 4.369788106630212e-05,
"loss": 1.9455,
"step": 461500
},
{
"epoch": 126.3,
"learning_rate": 4.369104579630896e-05,
"loss": 1.9598,
"step": 462000
},
{
"epoch": 126.44,
"learning_rate": 4.368421052631579e-05,
"loss": 1.9695,
"step": 462500
},
{
"epoch": 126.57,
"learning_rate": 4.367737525632263e-05,
"loss": 1.9791,
"step": 463000
},
{
"epoch": 126.71,
"learning_rate": 4.367053998632946e-05,
"loss": 1.9733,
"step": 463500
},
{
"epoch": 126.85,
"learning_rate": 4.3663704716336296e-05,
"loss": 1.9899,
"step": 464000
},
{
"epoch": 126.98,
"learning_rate": 4.365686944634314e-05,
"loss": 1.9975,
"step": 464500
},
{
"epoch": 127.12,
"learning_rate": 4.3650034176349966e-05,
"loss": 1.9522,
"step": 465000
},
{
"epoch": 127.26,
"learning_rate": 4.36431989063568e-05,
"loss": 1.9489,
"step": 465500
},
{
"epoch": 127.39,
"learning_rate": 4.3636363636363636e-05,
"loss": 1.961,
"step": 466000
},
{
"epoch": 127.53,
"learning_rate": 4.362952836637048e-05,
"loss": 1.9685,
"step": 466500
},
{
"epoch": 127.67,
"learning_rate": 4.362269309637731e-05,
"loss": 1.9775,
"step": 467000
},
{
"epoch": 127.8,
"learning_rate": 4.361585782638414e-05,
"loss": 1.983,
"step": 467500
},
{
"epoch": 127.94,
"learning_rate": 4.3609022556390975e-05,
"loss": 1.9919,
"step": 468000
},
{
"epoch": 128.08,
"learning_rate": 4.3602187286397816e-05,
"loss": 1.9609,
"step": 468500
},
{
"epoch": 128.21,
"learning_rate": 4.359535201640465e-05,
"loss": 1.9508,
"step": 469000
},
{
"epoch": 128.35,
"learning_rate": 4.3588516746411486e-05,
"loss": 1.9594,
"step": 469500
},
{
"epoch": 128.49,
"learning_rate": 4.358168147641832e-05,
"loss": 1.9627,
"step": 470000
},
{
"epoch": 128.62,
"learning_rate": 4.3574846206425156e-05,
"loss": 1.9675,
"step": 470500
},
{
"epoch": 128.76,
"learning_rate": 4.356801093643199e-05,
"loss": 1.9777,
"step": 471000
},
{
"epoch": 128.9,
"learning_rate": 4.3561175666438825e-05,
"loss": 1.9811,
"step": 471500
},
{
"epoch": 129.03,
"learning_rate": 4.355434039644567e-05,
"loss": 1.975,
"step": 472000
},
{
"epoch": 129.17,
"learning_rate": 4.3547505126452495e-05,
"loss": 1.9393,
"step": 472500
},
{
"epoch": 129.31,
"learning_rate": 4.354066985645933e-05,
"loss": 1.9465,
"step": 473000
},
{
"epoch": 129.44,
"learning_rate": 4.3533834586466164e-05,
"loss": 1.9567,
"step": 473500
},
{
"epoch": 129.58,
"learning_rate": 4.3526999316473006e-05,
"loss": 1.963,
"step": 474000
},
{
"epoch": 129.72,
"learning_rate": 4.352016404647984e-05,
"loss": 1.9731,
"step": 474500
},
{
"epoch": 129.85,
"learning_rate": 4.3513328776486675e-05,
"loss": 1.9787,
"step": 475000
},
{
"epoch": 129.99,
"learning_rate": 4.3506493506493503e-05,
"loss": 1.9779,
"step": 475500
},
{
"epoch": 130.13,
"learning_rate": 4.3499658236500345e-05,
"loss": 1.9351,
"step": 476000
},
{
"epoch": 130.26,
"learning_rate": 4.349282296650718e-05,
"loss": 1.9439,
"step": 476500
},
{
"epoch": 130.4,
"learning_rate": 4.3485987696514015e-05,
"loss": 1.953,
"step": 477000
},
{
"epoch": 130.54,
"learning_rate": 4.347915242652085e-05,
"loss": 1.9584,
"step": 477500
},
{
"epoch": 130.67,
"learning_rate": 4.3472317156527684e-05,
"loss": 1.9635,
"step": 478000
},
{
"epoch": 130.81,
"learning_rate": 4.346548188653452e-05,
"loss": 1.9722,
"step": 478500
},
{
"epoch": 130.95,
"learning_rate": 4.3458646616541354e-05,
"loss": 1.9806,
"step": 479000
},
{
"epoch": 131.08,
"learning_rate": 4.345181134654819e-05,
"loss": 1.9505,
"step": 479500
},
{
"epoch": 131.22,
"learning_rate": 4.344497607655503e-05,
"loss": 1.9355,
"step": 480000
}
],
"max_steps": 3658000,
"num_train_epochs": 1000,
"total_flos": 966230618169802752,
"trial_name": null,
"trial_params": null
}