{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 297351, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.991592427804178e-05, "loss": 2.9537, "step": 500 }, { "epoch": 0.01, "learning_rate": 4.983184855608356e-05, "loss": 2.5833, "step": 1000 }, { "epoch": 0.02, "learning_rate": 4.9747772834125326e-05, "loss": 2.3953, "step": 1500 }, { "epoch": 0.02, "learning_rate": 4.966369711216711e-05, "loss": 2.2926, "step": 2000 }, { "epoch": 0.03, "learning_rate": 4.957962139020888e-05, "loss": 2.1928, "step": 2500 }, { "epoch": 0.03, "learning_rate": 4.9495545668250656e-05, "loss": 2.1732, "step": 3000 }, { "epoch": 0.04, "learning_rate": 4.941146994629243e-05, "loss": 2.1076, "step": 3500 }, { "epoch": 0.04, "learning_rate": 4.9327394224334204e-05, "loss": 2.0544, "step": 4000 }, { "epoch": 0.05, "learning_rate": 4.9243318502375986e-05, "loss": 2.0386, "step": 4500 }, { "epoch": 0.05, "learning_rate": 4.915924278041776e-05, "loss": 1.9983, "step": 5000 }, { "epoch": 0.06, "learning_rate": 4.9075167058459534e-05, "loss": 1.9863, "step": 5500 }, { "epoch": 0.06, "learning_rate": 4.899109133650131e-05, "loss": 1.938, "step": 6000 }, { "epoch": 0.07, "learning_rate": 4.890701561454308e-05, "loss": 1.9275, "step": 6500 }, { "epoch": 0.07, "learning_rate": 4.8822939892584864e-05, "loss": 1.9134, "step": 7000 }, { "epoch": 0.08, "learning_rate": 4.873886417062664e-05, "loss": 1.8751, "step": 7500 }, { "epoch": 0.08, "learning_rate": 4.8654788448668406e-05, "loss": 1.8581, "step": 8000 }, { "epoch": 0.09, "learning_rate": 4.857071272671019e-05, "loss": 1.8479, "step": 8500 }, { "epoch": 0.09, "learning_rate": 4.848663700475196e-05, "loss": 1.8427, "step": 9000 }, { "epoch": 0.1, "learning_rate": 4.840256128279374e-05, "loss": 1.8359, "step": 9500 }, { "epoch": 0.1, "learning_rate": 4.831848556083551e-05, "loss": 1.8171, "step": 10000 }, { "epoch": 0.11, "learning_rate": 4.8234409838877285e-05, "loss": 1.7915, "step": 10500 }, { "epoch": 0.11, "learning_rate": 4.8150334116919066e-05, "loss": 1.7992, "step": 11000 }, { "epoch": 0.12, "learning_rate": 4.806625839496084e-05, "loss": 1.7672, "step": 11500 }, { "epoch": 0.12, "learning_rate": 4.7982182673002615e-05, "loss": 1.7525, "step": 12000 }, { "epoch": 0.13, "learning_rate": 4.789810695104439e-05, "loss": 1.7735, "step": 12500 }, { "epoch": 0.13, "learning_rate": 4.7814031229086164e-05, "loss": 1.7564, "step": 13000 }, { "epoch": 0.14, "learning_rate": 4.7729955507127945e-05, "loss": 1.7295, "step": 13500 }, { "epoch": 0.14, "learning_rate": 4.764587978516972e-05, "loss": 1.7263, "step": 14000 }, { "epoch": 0.15, "learning_rate": 4.7561804063211494e-05, "loss": 1.7199, "step": 14500 }, { "epoch": 0.15, "learning_rate": 4.747772834125327e-05, "loss": 1.6939, "step": 15000 }, { "epoch": 0.16, "learning_rate": 4.739365261929504e-05, "loss": 1.688, "step": 15500 }, { "epoch": 0.16, "learning_rate": 4.7309576897336824e-05, "loss": 1.702, "step": 16000 }, { "epoch": 0.17, "learning_rate": 4.722550117537859e-05, "loss": 1.7018, "step": 16500 }, { "epoch": 0.17, "learning_rate": 4.7141425453420366e-05, "loss": 1.6672, "step": 17000 }, { "epoch": 0.18, "learning_rate": 4.705734973146215e-05, "loss": 1.6682, "step": 17500 }, { "epoch": 0.18, "learning_rate": 4.697327400950392e-05, "loss": 1.6793, "step": 18000 }, { "epoch": 0.19, "learning_rate": 4.6889198287545696e-05, "loss": 1.6461, "step": 18500 }, { "epoch": 0.19, "learning_rate": 4.680512256558747e-05, "loss": 1.6546, "step": 19000 }, { "epoch": 0.2, "learning_rate": 4.6721046843629245e-05, "loss": 1.676, "step": 19500 }, { "epoch": 0.2, "learning_rate": 4.6636971121671026e-05, "loss": 1.6334, "step": 20000 }, { "epoch": 0.21, "learning_rate": 4.65528953997128e-05, "loss": 1.602, "step": 20500 }, { "epoch": 0.21, "learning_rate": 4.6468819677754575e-05, "loss": 1.6335, "step": 21000 }, { "epoch": 0.22, "learning_rate": 4.638474395579635e-05, "loss": 1.614, "step": 21500 }, { "epoch": 0.22, "learning_rate": 4.6300668233838124e-05, "loss": 1.6255, "step": 22000 }, { "epoch": 0.23, "learning_rate": 4.6216592511879905e-05, "loss": 1.6066, "step": 22500 }, { "epoch": 0.23, "learning_rate": 4.613251678992168e-05, "loss": 1.588, "step": 23000 }, { "epoch": 0.24, "learning_rate": 4.6048441067963454e-05, "loss": 1.5889, "step": 23500 }, { "epoch": 0.24, "learning_rate": 4.596436534600523e-05, "loss": 1.5991, "step": 24000 }, { "epoch": 0.25, "learning_rate": 4.5880289624047e-05, "loss": 1.6027, "step": 24500 }, { "epoch": 0.25, "learning_rate": 4.5796213902088784e-05, "loss": 1.6109, "step": 25000 }, { "epoch": 0.26, "learning_rate": 4.571213818013055e-05, "loss": 1.5568, "step": 25500 }, { "epoch": 0.26, "learning_rate": 4.562806245817233e-05, "loss": 1.5824, "step": 26000 }, { "epoch": 0.27, "learning_rate": 4.554398673621411e-05, "loss": 1.5448, "step": 26500 }, { "epoch": 0.27, "learning_rate": 4.545991101425588e-05, "loss": 1.5959, "step": 27000 }, { "epoch": 0.28, "learning_rate": 4.5375835292297656e-05, "loss": 1.5562, "step": 27500 }, { "epoch": 0.28, "learning_rate": 4.529175957033943e-05, "loss": 1.5873, "step": 28000 }, { "epoch": 0.29, "learning_rate": 4.520768384838121e-05, "loss": 1.5608, "step": 28500 }, { "epoch": 0.29, "learning_rate": 4.5123608126422986e-05, "loss": 1.549, "step": 29000 }, { "epoch": 0.3, "learning_rate": 4.503953240446476e-05, "loss": 1.5603, "step": 29500 }, { "epoch": 0.3, "learning_rate": 4.4955456682506534e-05, "loss": 1.5663, "step": 30000 }, { "epoch": 0.31, "learning_rate": 4.487138096054831e-05, "loss": 1.5537, "step": 30500 }, { "epoch": 0.31, "learning_rate": 4.478730523859009e-05, "loss": 1.5122, "step": 31000 }, { "epoch": 0.32, "learning_rate": 4.4703229516631864e-05, "loss": 1.5294, "step": 31500 }, { "epoch": 0.32, "learning_rate": 4.461915379467363e-05, "loss": 1.5304, "step": 32000 }, { "epoch": 0.33, "learning_rate": 4.453507807271541e-05, "loss": 1.518, "step": 32500 }, { "epoch": 0.33, "learning_rate": 4.445100235075719e-05, "loss": 1.5246, "step": 33000 }, { "epoch": 0.34, "learning_rate": 4.436692662879897e-05, "loss": 1.5308, "step": 33500 }, { "epoch": 0.34, "learning_rate": 4.4282850906840737e-05, "loss": 1.5281, "step": 34000 }, { "epoch": 0.35, "learning_rate": 4.419877518488251e-05, "loss": 1.5071, "step": 34500 }, { "epoch": 0.35, "learning_rate": 4.411469946292429e-05, "loss": 1.5088, "step": 35000 }, { "epoch": 0.36, "learning_rate": 4.4030623740966067e-05, "loss": 1.5094, "step": 35500 }, { "epoch": 0.36, "learning_rate": 4.394654801900784e-05, "loss": 1.4856, "step": 36000 }, { "epoch": 0.37, "learning_rate": 4.3862472297049615e-05, "loss": 1.5002, "step": 36500 }, { "epoch": 0.37, "learning_rate": 4.377839657509139e-05, "loss": 1.4891, "step": 37000 }, { "epoch": 0.38, "learning_rate": 4.369432085313317e-05, "loss": 1.5234, "step": 37500 }, { "epoch": 0.38, "learning_rate": 4.3610245131174945e-05, "loss": 1.5026, "step": 38000 }, { "epoch": 0.39, "learning_rate": 4.352616940921672e-05, "loss": 1.4776, "step": 38500 }, { "epoch": 0.39, "learning_rate": 4.3442093687258494e-05, "loss": 1.4842, "step": 39000 }, { "epoch": 0.4, "learning_rate": 4.335801796530027e-05, "loss": 1.4819, "step": 39500 }, { "epoch": 0.4, "learning_rate": 4.327394224334205e-05, "loss": 1.4776, "step": 40000 }, { "epoch": 0.41, "learning_rate": 4.318986652138382e-05, "loss": 1.4867, "step": 40500 }, { "epoch": 0.41, "learning_rate": 4.31057907994256e-05, "loss": 1.4757, "step": 41000 }, { "epoch": 0.42, "learning_rate": 4.302171507746737e-05, "loss": 1.4904, "step": 41500 }, { "epoch": 0.42, "learning_rate": 4.293763935550915e-05, "loss": 1.4781, "step": 42000 }, { "epoch": 0.43, "learning_rate": 4.285356363355092e-05, "loss": 1.4567, "step": 42500 }, { "epoch": 0.43, "learning_rate": 4.2769487911592696e-05, "loss": 1.4649, "step": 43000 }, { "epoch": 0.44, "learning_rate": 4.268541218963448e-05, "loss": 1.4473, "step": 43500 }, { "epoch": 0.44, "learning_rate": 4.260133646767625e-05, "loss": 1.4691, "step": 44000 }, { "epoch": 0.45, "learning_rate": 4.2517260745718026e-05, "loss": 1.4638, "step": 44500 }, { "epoch": 0.45, "learning_rate": 4.24331850237598e-05, "loss": 1.4566, "step": 45000 }, { "epoch": 0.46, "learning_rate": 4.2349109301801575e-05, "loss": 1.4675, "step": 45500 }, { "epoch": 0.46, "learning_rate": 4.226503357984335e-05, "loss": 1.4408, "step": 46000 }, { "epoch": 0.47, "learning_rate": 4.218095785788513e-05, "loss": 1.4504, "step": 46500 }, { "epoch": 0.47, "learning_rate": 4.2096882135926905e-05, "loss": 1.4451, "step": 47000 }, { "epoch": 0.48, "learning_rate": 4.201280641396868e-05, "loss": 1.4457, "step": 47500 }, { "epoch": 0.48, "learning_rate": 4.1928730692010454e-05, "loss": 1.4355, "step": 48000 }, { "epoch": 0.49, "learning_rate": 4.184465497005223e-05, "loss": 1.4426, "step": 48500 }, { "epoch": 0.49, "learning_rate": 4.176057924809401e-05, "loss": 1.465, "step": 49000 }, { "epoch": 0.5, "learning_rate": 4.167650352613578e-05, "loss": 1.4335, "step": 49500 }, { "epoch": 0.5, "learning_rate": 4.159242780417756e-05, "loss": 1.446, "step": 50000 }, { "epoch": 0.51, "learning_rate": 4.150835208221933e-05, "loss": 1.4489, "step": 50500 }, { "epoch": 0.51, "learning_rate": 4.142427636026111e-05, "loss": 1.4378, "step": 51000 }, { "epoch": 0.52, "learning_rate": 4.134020063830288e-05, "loss": 1.4324, "step": 51500 }, { "epoch": 0.52, "learning_rate": 4.1256124916344656e-05, "loss": 1.4204, "step": 52000 }, { "epoch": 0.53, "learning_rate": 4.117204919438644e-05, "loss": 1.4302, "step": 52500 }, { "epoch": 0.53, "learning_rate": 4.108797347242821e-05, "loss": 1.4028, "step": 53000 }, { "epoch": 0.54, "learning_rate": 4.1003897750469986e-05, "loss": 1.438, "step": 53500 }, { "epoch": 0.54, "learning_rate": 4.091982202851176e-05, "loss": 1.4317, "step": 54000 }, { "epoch": 0.55, "learning_rate": 4.0835746306553535e-05, "loss": 1.421, "step": 54500 }, { "epoch": 0.55, "learning_rate": 4.0751670584595316e-05, "loss": 1.4133, "step": 55000 }, { "epoch": 0.56, "learning_rate": 4.066759486263709e-05, "loss": 1.4122, "step": 55500 }, { "epoch": 0.56, "learning_rate": 4.058351914067886e-05, "loss": 1.4078, "step": 56000 }, { "epoch": 0.57, "learning_rate": 4.049944341872064e-05, "loss": 1.3853, "step": 56500 }, { "epoch": 0.58, "learning_rate": 4.0415367696762413e-05, "loss": 1.4164, "step": 57000 }, { "epoch": 0.58, "learning_rate": 4.0331291974804195e-05, "loss": 1.4123, "step": 57500 }, { "epoch": 0.59, "learning_rate": 4.024721625284596e-05, "loss": 1.4198, "step": 58000 }, { "epoch": 0.59, "learning_rate": 4.0163140530887737e-05, "loss": 1.433, "step": 58500 }, { "epoch": 0.6, "learning_rate": 4.007906480892952e-05, "loss": 1.3901, "step": 59000 }, { "epoch": 0.6, "learning_rate": 3.999498908697129e-05, "loss": 1.416, "step": 59500 }, { "epoch": 0.61, "learning_rate": 3.9910913365013067e-05, "loss": 1.4078, "step": 60000 }, { "epoch": 0.61, "learning_rate": 3.982683764305484e-05, "loss": 1.3986, "step": 60500 }, { "epoch": 0.62, "learning_rate": 3.9742761921096615e-05, "loss": 1.3947, "step": 61000 }, { "epoch": 0.62, "learning_rate": 3.9658686199138397e-05, "loss": 1.4176, "step": 61500 }, { "epoch": 0.63, "learning_rate": 3.957461047718017e-05, "loss": 1.3858, "step": 62000 }, { "epoch": 0.63, "learning_rate": 3.9490534755221945e-05, "loss": 1.3857, "step": 62500 }, { "epoch": 0.64, "learning_rate": 3.940645903326372e-05, "loss": 1.3525, "step": 63000 }, { "epoch": 0.64, "learning_rate": 3.9322383311305494e-05, "loss": 1.3782, "step": 63500 }, { "epoch": 0.65, "learning_rate": 3.9238307589347275e-05, "loss": 1.4042, "step": 64000 }, { "epoch": 0.65, "learning_rate": 3.915423186738904e-05, "loss": 1.3989, "step": 64500 }, { "epoch": 0.66, "learning_rate": 3.9070156145430824e-05, "loss": 1.3922, "step": 65000 }, { "epoch": 0.66, "learning_rate": 3.89860804234726e-05, "loss": 1.3817, "step": 65500 }, { "epoch": 0.67, "learning_rate": 3.890200470151437e-05, "loss": 1.3703, "step": 66000 }, { "epoch": 0.67, "learning_rate": 3.881792897955615e-05, "loss": 1.3806, "step": 66500 }, { "epoch": 0.68, "learning_rate": 3.873385325759792e-05, "loss": 1.3659, "step": 67000 }, { "epoch": 0.68, "learning_rate": 3.86497775356397e-05, "loss": 1.3732, "step": 67500 }, { "epoch": 0.69, "learning_rate": 3.856570181368148e-05, "loss": 1.3851, "step": 68000 }, { "epoch": 0.69, "learning_rate": 3.848162609172325e-05, "loss": 1.364, "step": 68500 }, { "epoch": 0.7, "learning_rate": 3.8397550369765026e-05, "loss": 1.3566, "step": 69000 }, { "epoch": 0.7, "learning_rate": 3.83134746478068e-05, "loss": 1.3617, "step": 69500 }, { "epoch": 0.71, "learning_rate": 3.822939892584858e-05, "loss": 1.3772, "step": 70000 }, { "epoch": 0.71, "learning_rate": 3.8145323203890356e-05, "loss": 1.3571, "step": 70500 }, { "epoch": 0.72, "learning_rate": 3.806124748193213e-05, "loss": 1.3501, "step": 71000 }, { "epoch": 0.72, "learning_rate": 3.7977171759973905e-05, "loss": 1.3776, "step": 71500 }, { "epoch": 0.73, "learning_rate": 3.789309603801568e-05, "loss": 1.3486, "step": 72000 }, { "epoch": 0.73, "learning_rate": 3.780902031605746e-05, "loss": 1.3677, "step": 72500 }, { "epoch": 0.74, "learning_rate": 3.7724944594099235e-05, "loss": 1.3278, "step": 73000 }, { "epoch": 0.74, "learning_rate": 3.7640868872141e-05, "loss": 1.3678, "step": 73500 }, { "epoch": 0.75, "learning_rate": 3.7556793150182784e-05, "loss": 1.3428, "step": 74000 }, { "epoch": 0.75, "learning_rate": 3.747271742822456e-05, "loss": 1.3444, "step": 74500 }, { "epoch": 0.76, "learning_rate": 3.738864170626633e-05, "loss": 1.3454, "step": 75000 }, { "epoch": 0.76, "learning_rate": 3.730456598430811e-05, "loss": 1.3514, "step": 75500 }, { "epoch": 0.77, "learning_rate": 3.722049026234988e-05, "loss": 1.3558, "step": 76000 }, { "epoch": 0.77, "learning_rate": 3.713641454039166e-05, "loss": 1.3619, "step": 76500 }, { "epoch": 0.78, "learning_rate": 3.705233881843344e-05, "loss": 1.3488, "step": 77000 }, { "epoch": 0.78, "learning_rate": 3.696826309647521e-05, "loss": 1.3327, "step": 77500 }, { "epoch": 0.79, "learning_rate": 3.6884187374516986e-05, "loss": 1.3437, "step": 78000 }, { "epoch": 0.79, "learning_rate": 3.680011165255876e-05, "loss": 1.3421, "step": 78500 }, { "epoch": 0.8, "learning_rate": 3.671603593060054e-05, "loss": 1.3406, "step": 79000 }, { "epoch": 0.8, "learning_rate": 3.6631960208642316e-05, "loss": 1.3521, "step": 79500 }, { "epoch": 0.81, "learning_rate": 3.6547884486684083e-05, "loss": 1.338, "step": 80000 }, { "epoch": 0.81, "learning_rate": 3.6463808764725865e-05, "loss": 1.3487, "step": 80500 }, { "epoch": 0.82, "learning_rate": 3.637973304276764e-05, "loss": 1.3225, "step": 81000 }, { "epoch": 0.82, "learning_rate": 3.629565732080942e-05, "loss": 1.337, "step": 81500 }, { "epoch": 0.83, "learning_rate": 3.621158159885119e-05, "loss": 1.3566, "step": 82000 }, { "epoch": 0.83, "learning_rate": 3.612750587689296e-05, "loss": 1.3293, "step": 82500 }, { "epoch": 0.84, "learning_rate": 3.6043430154934743e-05, "loss": 1.327, "step": 83000 }, { "epoch": 0.84, "learning_rate": 3.595935443297652e-05, "loss": 1.3121, "step": 83500 }, { "epoch": 0.85, "learning_rate": 3.587527871101829e-05, "loss": 1.3295, "step": 84000 }, { "epoch": 0.85, "learning_rate": 3.579120298906007e-05, "loss": 1.3331, "step": 84500 }, { "epoch": 0.86, "learning_rate": 3.570712726710184e-05, "loss": 1.3298, "step": 85000 }, { "epoch": 0.86, "learning_rate": 3.562305154514362e-05, "loss": 1.327, "step": 85500 }, { "epoch": 0.87, "learning_rate": 3.55389758231854e-05, "loss": 1.3299, "step": 86000 }, { "epoch": 0.87, "learning_rate": 3.545490010122717e-05, "loss": 1.3291, "step": 86500 }, { "epoch": 0.88, "learning_rate": 3.5370824379268945e-05, "loss": 1.3143, "step": 87000 }, { "epoch": 0.88, "learning_rate": 3.528674865731072e-05, "loss": 1.3177, "step": 87500 }, { "epoch": 0.89, "learning_rate": 3.52026729353525e-05, "loss": 1.3099, "step": 88000 }, { "epoch": 0.89, "learning_rate": 3.511859721339427e-05, "loss": 1.3298, "step": 88500 }, { "epoch": 0.9, "learning_rate": 3.503452149143605e-05, "loss": 1.3226, "step": 89000 }, { "epoch": 0.9, "learning_rate": 3.4950445769477824e-05, "loss": 1.3354, "step": 89500 }, { "epoch": 0.91, "learning_rate": 3.48663700475196e-05, "loss": 1.2978, "step": 90000 }, { "epoch": 0.91, "learning_rate": 3.478229432556137e-05, "loss": 1.3165, "step": 90500 }, { "epoch": 0.92, "learning_rate": 3.469821860360315e-05, "loss": 1.3169, "step": 91000 }, { "epoch": 0.92, "learning_rate": 3.461414288164493e-05, "loss": 1.3082, "step": 91500 }, { "epoch": 0.93, "learning_rate": 3.45300671596867e-05, "loss": 1.3075, "step": 92000 }, { "epoch": 0.93, "learning_rate": 3.444599143772848e-05, "loss": 1.3125, "step": 92500 }, { "epoch": 0.94, "learning_rate": 3.436191571577025e-05, "loss": 1.2894, "step": 93000 }, { "epoch": 0.94, "learning_rate": 3.4277839993812026e-05, "loss": 1.3204, "step": 93500 }, { "epoch": 0.95, "learning_rate": 3.419376427185381e-05, "loss": 1.306, "step": 94000 }, { "epoch": 0.95, "learning_rate": 3.410968854989558e-05, "loss": 1.285, "step": 94500 }, { "epoch": 0.96, "learning_rate": 3.4025612827937356e-05, "loss": 1.3063, "step": 95000 }, { "epoch": 0.96, "learning_rate": 3.394153710597913e-05, "loss": 1.2882, "step": 95500 }, { "epoch": 0.97, "learning_rate": 3.3857461384020905e-05, "loss": 1.3026, "step": 96000 }, { "epoch": 0.97, "learning_rate": 3.3773385662062686e-05, "loss": 1.2723, "step": 96500 }, { "epoch": 0.98, "learning_rate": 3.368930994010446e-05, "loss": 1.259, "step": 97000 }, { "epoch": 0.98, "learning_rate": 3.360523421814623e-05, "loss": 1.2865, "step": 97500 }, { "epoch": 0.99, "learning_rate": 3.352115849618801e-05, "loss": 1.2842, "step": 98000 }, { "epoch": 0.99, "learning_rate": 3.3437082774229784e-05, "loss": 1.2946, "step": 98500 }, { "epoch": 1.0, "learning_rate": 3.3353007052271565e-05, "loss": 1.2887, "step": 99000 }, { "epoch": 1.0, "learning_rate": 3.326893133031333e-05, "loss": 1.2033, "step": 99500 }, { "epoch": 1.01, "learning_rate": 3.318485560835511e-05, "loss": 1.1685, "step": 100000 }, { "epoch": 1.01, "learning_rate": 3.310077988639689e-05, "loss": 1.1648, "step": 100500 }, { "epoch": 1.02, "learning_rate": 3.301670416443866e-05, "loss": 1.1755, "step": 101000 }, { "epoch": 1.02, "learning_rate": 3.293262844248044e-05, "loss": 1.1751, "step": 101500 }, { "epoch": 1.03, "learning_rate": 3.284855272052221e-05, "loss": 1.1657, "step": 102000 }, { "epoch": 1.03, "learning_rate": 3.2764476998563986e-05, "loss": 1.1724, "step": 102500 }, { "epoch": 1.04, "learning_rate": 3.268040127660577e-05, "loss": 1.168, "step": 103000 }, { "epoch": 1.04, "learning_rate": 3.259632555464754e-05, "loss": 1.1523, "step": 103500 }, { "epoch": 1.05, "learning_rate": 3.251224983268931e-05, "loss": 1.1616, "step": 104000 }, { "epoch": 1.05, "learning_rate": 3.242817411073109e-05, "loss": 1.1644, "step": 104500 }, { "epoch": 1.06, "learning_rate": 3.2344098388772865e-05, "loss": 1.1874, "step": 105000 }, { "epoch": 1.06, "learning_rate": 3.2260022666814646e-05, "loss": 1.1756, "step": 105500 }, { "epoch": 1.07, "learning_rate": 3.2175946944856414e-05, "loss": 1.1718, "step": 106000 }, { "epoch": 1.07, "learning_rate": 3.209187122289819e-05, "loss": 1.1944, "step": 106500 }, { "epoch": 1.08, "learning_rate": 3.200779550093997e-05, "loss": 1.1774, "step": 107000 }, { "epoch": 1.08, "learning_rate": 3.1923719778981744e-05, "loss": 1.1564, "step": 107500 }, { "epoch": 1.09, "learning_rate": 3.183964405702352e-05, "loss": 1.1594, "step": 108000 }, { "epoch": 1.09, "learning_rate": 3.175556833506529e-05, "loss": 1.178, "step": 108500 }, { "epoch": 1.1, "learning_rate": 3.167149261310707e-05, "loss": 1.1662, "step": 109000 }, { "epoch": 1.1, "learning_rate": 3.158741689114885e-05, "loss": 1.1704, "step": 109500 }, { "epoch": 1.11, "learning_rate": 3.150334116919062e-05, "loss": 1.1665, "step": 110000 }, { "epoch": 1.11, "learning_rate": 3.14192654472324e-05, "loss": 1.2011, "step": 110500 }, { "epoch": 1.12, "learning_rate": 3.133518972527417e-05, "loss": 1.1922, "step": 111000 }, { "epoch": 1.12, "learning_rate": 3.1251114003315946e-05, "loss": 1.1649, "step": 111500 }, { "epoch": 1.13, "learning_rate": 3.116703828135773e-05, "loss": 1.157, "step": 112000 }, { "epoch": 1.14, "learning_rate": 3.1082962559399494e-05, "loss": 1.1699, "step": 112500 }, { "epoch": 1.14, "learning_rate": 3.0998886837441276e-05, "loss": 1.1811, "step": 113000 }, { "epoch": 1.15, "learning_rate": 3.091481111548305e-05, "loss": 1.162, "step": 113500 }, { "epoch": 1.15, "learning_rate": 3.0830735393524824e-05, "loss": 1.1647, "step": 114000 }, { "epoch": 1.16, "learning_rate": 3.0746659671566606e-05, "loss": 1.1704, "step": 114500 }, { "epoch": 1.16, "learning_rate": 3.066258394960837e-05, "loss": 1.1522, "step": 115000 }, { "epoch": 1.17, "learning_rate": 3.0578508227650154e-05, "loss": 1.1487, "step": 115500 }, { "epoch": 1.17, "learning_rate": 3.049443250569193e-05, "loss": 1.1553, "step": 116000 }, { "epoch": 1.18, "learning_rate": 3.04103567837337e-05, "loss": 1.1516, "step": 116500 }, { "epoch": 1.18, "learning_rate": 3.032628106177548e-05, "loss": 1.181, "step": 117000 }, { "epoch": 1.19, "learning_rate": 3.0242205339817252e-05, "loss": 1.1689, "step": 117500 }, { "epoch": 1.19, "learning_rate": 3.0158129617859033e-05, "loss": 1.1638, "step": 118000 }, { "epoch": 1.2, "learning_rate": 3.0074053895900804e-05, "loss": 1.155, "step": 118500 }, { "epoch": 1.2, "learning_rate": 2.998997817394258e-05, "loss": 1.1563, "step": 119000 }, { "epoch": 1.21, "learning_rate": 2.9905902451984356e-05, "loss": 1.1359, "step": 119500 }, { "epoch": 1.21, "learning_rate": 2.982182673002613e-05, "loss": 1.15, "step": 120000 }, { "epoch": 1.22, "learning_rate": 2.973775100806791e-05, "loss": 1.1551, "step": 120500 }, { "epoch": 1.22, "learning_rate": 2.9653675286109683e-05, "loss": 1.1608, "step": 121000 }, { "epoch": 1.23, "learning_rate": 2.9569599564151457e-05, "loss": 1.1809, "step": 121500 }, { "epoch": 1.23, "learning_rate": 2.9485523842193235e-05, "loss": 1.1638, "step": 122000 }, { "epoch": 1.24, "learning_rate": 2.940144812023501e-05, "loss": 1.1688, "step": 122500 }, { "epoch": 1.24, "learning_rate": 2.9317372398276787e-05, "loss": 1.1622, "step": 123000 }, { "epoch": 1.25, "learning_rate": 2.9233296676318562e-05, "loss": 1.156, "step": 123500 }, { "epoch": 1.25, "learning_rate": 2.9149220954360333e-05, "loss": 1.1492, "step": 124000 }, { "epoch": 1.26, "learning_rate": 2.9065145232402114e-05, "loss": 1.1706, "step": 124500 }, { "epoch": 1.26, "learning_rate": 2.898106951044389e-05, "loss": 1.1338, "step": 125000 }, { "epoch": 1.27, "learning_rate": 2.8896993788485666e-05, "loss": 1.1735, "step": 125500 }, { "epoch": 1.27, "learning_rate": 2.881291806652744e-05, "loss": 1.1571, "step": 126000 }, { "epoch": 1.28, "learning_rate": 2.872884234456921e-05, "loss": 1.1629, "step": 126500 }, { "epoch": 1.28, "learning_rate": 2.8644766622610993e-05, "loss": 1.1499, "step": 127000 }, { "epoch": 1.29, "learning_rate": 2.8560690900652764e-05, "loss": 1.158, "step": 127500 }, { "epoch": 1.29, "learning_rate": 2.8476615178694545e-05, "loss": 1.1551, "step": 128000 }, { "epoch": 1.3, "learning_rate": 2.8392539456736316e-05, "loss": 1.1519, "step": 128500 }, { "epoch": 1.3, "learning_rate": 2.830846373477809e-05, "loss": 1.1576, "step": 129000 }, { "epoch": 1.31, "learning_rate": 2.8224388012819868e-05, "loss": 1.1664, "step": 129500 }, { "epoch": 1.31, "learning_rate": 2.8140312290861643e-05, "loss": 1.1642, "step": 130000 }, { "epoch": 1.32, "learning_rate": 2.805623656890342e-05, "loss": 1.1528, "step": 130500 }, { "epoch": 1.32, "learning_rate": 2.7972160846945195e-05, "loss": 1.1467, "step": 131000 }, { "epoch": 1.33, "learning_rate": 2.788808512498697e-05, "loss": 1.1463, "step": 131500 }, { "epoch": 1.33, "learning_rate": 2.7804009403028747e-05, "loss": 1.1686, "step": 132000 }, { "epoch": 1.34, "learning_rate": 2.771993368107052e-05, "loss": 1.1497, "step": 132500 }, { "epoch": 1.34, "learning_rate": 2.7635857959112292e-05, "loss": 1.1389, "step": 133000 }, { "epoch": 1.35, "learning_rate": 2.7551782237154074e-05, "loss": 1.1462, "step": 133500 }, { "epoch": 1.35, "learning_rate": 2.7467706515195845e-05, "loss": 1.135, "step": 134000 }, { "epoch": 1.36, "learning_rate": 2.7383630793237626e-05, "loss": 1.1644, "step": 134500 }, { "epoch": 1.36, "learning_rate": 2.7299555071279397e-05, "loss": 1.1452, "step": 135000 }, { "epoch": 1.37, "learning_rate": 2.721547934932117e-05, "loss": 1.1552, "step": 135500 }, { "epoch": 1.37, "learning_rate": 2.713140362736295e-05, "loss": 1.1544, "step": 136000 }, { "epoch": 1.38, "learning_rate": 2.7047327905404723e-05, "loss": 1.1462, "step": 136500 }, { "epoch": 1.38, "learning_rate": 2.69632521834465e-05, "loss": 1.1312, "step": 137000 }, { "epoch": 1.39, "learning_rate": 2.6879176461488276e-05, "loss": 1.1489, "step": 137500 }, { "epoch": 1.39, "learning_rate": 2.679510073953005e-05, "loss": 1.1482, "step": 138000 }, { "epoch": 1.4, "learning_rate": 2.6711025017571828e-05, "loss": 1.1523, "step": 138500 }, { "epoch": 1.4, "learning_rate": 2.6626949295613602e-05, "loss": 1.1203, "step": 139000 }, { "epoch": 1.41, "learning_rate": 2.654287357365538e-05, "loss": 1.1589, "step": 139500 }, { "epoch": 1.41, "learning_rate": 2.6458797851697154e-05, "loss": 1.1321, "step": 140000 }, { "epoch": 1.42, "learning_rate": 2.6374722129738925e-05, "loss": 1.135, "step": 140500 }, { "epoch": 1.42, "learning_rate": 2.6290646407780707e-05, "loss": 1.1438, "step": 141000 }, { "epoch": 1.43, "learning_rate": 2.6206570685822478e-05, "loss": 1.1355, "step": 141500 }, { "epoch": 1.43, "learning_rate": 2.612249496386426e-05, "loss": 1.1182, "step": 142000 }, { "epoch": 1.44, "learning_rate": 2.603841924190603e-05, "loss": 1.1288, "step": 142500 }, { "epoch": 1.44, "learning_rate": 2.5954343519947804e-05, "loss": 1.1385, "step": 143000 }, { "epoch": 1.45, "learning_rate": 2.5870267797989582e-05, "loss": 1.1368, "step": 143500 }, { "epoch": 1.45, "learning_rate": 2.5786192076031356e-05, "loss": 1.1353, "step": 144000 }, { "epoch": 1.46, "learning_rate": 2.5702116354073134e-05, "loss": 1.126, "step": 144500 }, { "epoch": 1.46, "learning_rate": 2.561804063211491e-05, "loss": 1.1207, "step": 145000 }, { "epoch": 1.47, "learning_rate": 2.5533964910156683e-05, "loss": 1.124, "step": 145500 }, { "epoch": 1.47, "learning_rate": 2.544988918819846e-05, "loss": 1.1325, "step": 146000 }, { "epoch": 1.48, "learning_rate": 2.5365813466240235e-05, "loss": 1.131, "step": 146500 }, { "epoch": 1.48, "learning_rate": 2.5281737744282013e-05, "loss": 1.1128, "step": 147000 }, { "epoch": 1.49, "learning_rate": 2.5197662022323787e-05, "loss": 1.14, "step": 147500 }, { "epoch": 1.49, "learning_rate": 2.5113586300365562e-05, "loss": 1.1309, "step": 148000 }, { "epoch": 1.5, "learning_rate": 2.502951057840734e-05, "loss": 1.1316, "step": 148500 }, { "epoch": 1.5, "learning_rate": 2.4945434856449114e-05, "loss": 1.1294, "step": 149000 }, { "epoch": 1.51, "learning_rate": 2.486135913449089e-05, "loss": 1.1236, "step": 149500 }, { "epoch": 1.51, "learning_rate": 2.4777283412532666e-05, "loss": 1.1151, "step": 150000 }, { "epoch": 1.52, "learning_rate": 2.469320769057444e-05, "loss": 1.1247, "step": 150500 }, { "epoch": 1.52, "learning_rate": 2.460913196861622e-05, "loss": 1.1322, "step": 151000 }, { "epoch": 1.53, "learning_rate": 2.452505624665799e-05, "loss": 1.1577, "step": 151500 }, { "epoch": 1.53, "learning_rate": 2.4440980524699767e-05, "loss": 1.1264, "step": 152000 }, { "epoch": 1.54, "learning_rate": 2.4356904802741542e-05, "loss": 1.1185, "step": 152500 }, { "epoch": 1.54, "learning_rate": 2.427282908078332e-05, "loss": 1.1269, "step": 153000 }, { "epoch": 1.55, "learning_rate": 2.4188753358825094e-05, "loss": 1.1258, "step": 153500 }, { "epoch": 1.55, "learning_rate": 2.410467763686687e-05, "loss": 1.1054, "step": 154000 }, { "epoch": 1.56, "learning_rate": 2.4020601914908643e-05, "loss": 1.1167, "step": 154500 }, { "epoch": 1.56, "learning_rate": 2.393652619295042e-05, "loss": 1.1151, "step": 155000 }, { "epoch": 1.57, "learning_rate": 2.3852450470992195e-05, "loss": 1.1166, "step": 155500 }, { "epoch": 1.57, "learning_rate": 2.376837474903397e-05, "loss": 1.113, "step": 156000 }, { "epoch": 1.58, "learning_rate": 2.3684299027075747e-05, "loss": 1.1263, "step": 156500 }, { "epoch": 1.58, "learning_rate": 2.360022330511752e-05, "loss": 1.1359, "step": 157000 }, { "epoch": 1.59, "learning_rate": 2.35161475831593e-05, "loss": 1.1124, "step": 157500 }, { "epoch": 1.59, "learning_rate": 2.3432071861201074e-05, "loss": 1.1287, "step": 158000 }, { "epoch": 1.6, "learning_rate": 2.3347996139242848e-05, "loss": 1.1315, "step": 158500 }, { "epoch": 1.6, "learning_rate": 2.3263920417284623e-05, "loss": 1.1242, "step": 159000 }, { "epoch": 1.61, "learning_rate": 2.31798446953264e-05, "loss": 1.1009, "step": 159500 }, { "epoch": 1.61, "learning_rate": 2.3095768973368175e-05, "loss": 1.1123, "step": 160000 }, { "epoch": 1.62, "learning_rate": 2.3011693251409953e-05, "loss": 1.118, "step": 160500 }, { "epoch": 1.62, "learning_rate": 2.2927617529451727e-05, "loss": 1.0966, "step": 161000 }, { "epoch": 1.63, "learning_rate": 2.28435418074935e-05, "loss": 1.121, "step": 161500 }, { "epoch": 1.63, "learning_rate": 2.275946608553528e-05, "loss": 1.1106, "step": 162000 }, { "epoch": 1.64, "learning_rate": 2.2675390363577054e-05, "loss": 1.099, "step": 162500 }, { "epoch": 1.64, "learning_rate": 2.259131464161883e-05, "loss": 1.1404, "step": 163000 }, { "epoch": 1.65, "learning_rate": 2.2507238919660602e-05, "loss": 1.1103, "step": 163500 }, { "epoch": 1.65, "learning_rate": 2.242316319770238e-05, "loss": 1.1044, "step": 164000 }, { "epoch": 1.66, "learning_rate": 2.2339087475744155e-05, "loss": 1.1047, "step": 164500 }, { "epoch": 1.66, "learning_rate": 2.2255011753785932e-05, "loss": 1.1019, "step": 165000 }, { "epoch": 1.67, "learning_rate": 2.2170936031827707e-05, "loss": 1.1318, "step": 165500 }, { "epoch": 1.67, "learning_rate": 2.208686030986948e-05, "loss": 1.124, "step": 166000 }, { "epoch": 1.68, "learning_rate": 2.2002784587911256e-05, "loss": 1.1081, "step": 166500 }, { "epoch": 1.68, "learning_rate": 2.1918708865953033e-05, "loss": 1.1222, "step": 167000 }, { "epoch": 1.69, "learning_rate": 2.1834633143994808e-05, "loss": 1.1272, "step": 167500 }, { "epoch": 1.69, "learning_rate": 2.1750557422036586e-05, "loss": 1.1131, "step": 168000 }, { "epoch": 1.7, "learning_rate": 2.166648170007836e-05, "loss": 1.101, "step": 168500 }, { "epoch": 1.71, "learning_rate": 2.1582405978120134e-05, "loss": 1.101, "step": 169000 }, { "epoch": 1.71, "learning_rate": 2.1498330256161912e-05, "loss": 1.1077, "step": 169500 }, { "epoch": 1.72, "learning_rate": 2.1414254534203687e-05, "loss": 1.0943, "step": 170000 }, { "epoch": 1.72, "learning_rate": 2.133017881224546e-05, "loss": 1.0921, "step": 170500 }, { "epoch": 1.73, "learning_rate": 2.1246103090287235e-05, "loss": 1.1058, "step": 171000 }, { "epoch": 1.73, "learning_rate": 2.1162027368329013e-05, "loss": 1.1082, "step": 171500 }, { "epoch": 1.74, "learning_rate": 2.1077951646370788e-05, "loss": 1.0914, "step": 172000 }, { "epoch": 1.74, "learning_rate": 2.0993875924412565e-05, "loss": 1.0545, "step": 172500 }, { "epoch": 1.75, "learning_rate": 2.090980020245434e-05, "loss": 1.1082, "step": 173000 }, { "epoch": 1.75, "learning_rate": 2.0825724480496114e-05, "loss": 1.0983, "step": 173500 }, { "epoch": 1.76, "learning_rate": 2.0741648758537892e-05, "loss": 1.1147, "step": 174000 }, { "epoch": 1.76, "learning_rate": 2.0657573036579666e-05, "loss": 1.1028, "step": 174500 }, { "epoch": 1.77, "learning_rate": 2.0573497314621444e-05, "loss": 1.0928, "step": 175000 }, { "epoch": 1.77, "learning_rate": 2.0489421592663215e-05, "loss": 1.1004, "step": 175500 }, { "epoch": 1.78, "learning_rate": 2.0405345870704993e-05, "loss": 1.0838, "step": 176000 }, { "epoch": 1.78, "learning_rate": 2.0321270148746767e-05, "loss": 1.1067, "step": 176500 }, { "epoch": 1.79, "learning_rate": 2.0237194426788545e-05, "loss": 1.099, "step": 177000 }, { "epoch": 1.79, "learning_rate": 2.015311870483032e-05, "loss": 1.0813, "step": 177500 }, { "epoch": 1.8, "learning_rate": 2.0069042982872094e-05, "loss": 1.111, "step": 178000 }, { "epoch": 1.8, "learning_rate": 1.998496726091387e-05, "loss": 1.1222, "step": 178500 }, { "epoch": 1.81, "learning_rate": 1.9900891538955646e-05, "loss": 1.1217, "step": 179000 }, { "epoch": 1.81, "learning_rate": 1.981681581699742e-05, "loss": 1.0904, "step": 179500 }, { "epoch": 1.82, "learning_rate": 1.97327400950392e-05, "loss": 1.1182, "step": 180000 }, { "epoch": 1.82, "learning_rate": 1.9648664373080973e-05, "loss": 1.0837, "step": 180500 }, { "epoch": 1.83, "learning_rate": 1.9564588651122747e-05, "loss": 1.1082, "step": 181000 }, { "epoch": 1.83, "learning_rate": 1.9480512929164525e-05, "loss": 1.088, "step": 181500 }, { "epoch": 1.84, "learning_rate": 1.93964372072063e-05, "loss": 1.0953, "step": 182000 }, { "epoch": 1.84, "learning_rate": 1.9312361485248077e-05, "loss": 1.1023, "step": 182500 }, { "epoch": 1.85, "learning_rate": 1.9228285763289848e-05, "loss": 1.1088, "step": 183000 }, { "epoch": 1.85, "learning_rate": 1.9144210041331626e-05, "loss": 1.101, "step": 183500 }, { "epoch": 1.86, "learning_rate": 1.90601343193734e-05, "loss": 1.0971, "step": 184000 }, { "epoch": 1.86, "learning_rate": 1.8976058597415178e-05, "loss": 1.1093, "step": 184500 }, { "epoch": 1.87, "learning_rate": 1.8891982875456953e-05, "loss": 1.0865, "step": 185000 }, { "epoch": 1.87, "learning_rate": 1.8807907153498727e-05, "loss": 1.0863, "step": 185500 }, { "epoch": 1.88, "learning_rate": 1.8723831431540505e-05, "loss": 1.0886, "step": 186000 }, { "epoch": 1.88, "learning_rate": 1.863975570958228e-05, "loss": 1.0906, "step": 186500 }, { "epoch": 1.89, "learning_rate": 1.8555679987624057e-05, "loss": 1.0967, "step": 187000 }, { "epoch": 1.89, "learning_rate": 1.8471604265665828e-05, "loss": 1.1083, "step": 187500 }, { "epoch": 1.9, "learning_rate": 1.8387528543707606e-05, "loss": 1.0849, "step": 188000 }, { "epoch": 1.9, "learning_rate": 1.830345282174938e-05, "loss": 1.0916, "step": 188500 }, { "epoch": 1.91, "learning_rate": 1.8219377099791158e-05, "loss": 1.086, "step": 189000 }, { "epoch": 1.91, "learning_rate": 1.8135301377832932e-05, "loss": 1.084, "step": 189500 }, { "epoch": 1.92, "learning_rate": 1.8051225655874707e-05, "loss": 1.0934, "step": 190000 }, { "epoch": 1.92, "learning_rate": 1.796714993391648e-05, "loss": 1.0875, "step": 190500 }, { "epoch": 1.93, "learning_rate": 1.788307421195826e-05, "loss": 1.0852, "step": 191000 }, { "epoch": 1.93, "learning_rate": 1.7798998490000033e-05, "loss": 1.0899, "step": 191500 }, { "epoch": 1.94, "learning_rate": 1.771492276804181e-05, "loss": 1.0927, "step": 192000 }, { "epoch": 1.94, "learning_rate": 1.7630847046083586e-05, "loss": 1.0831, "step": 192500 }, { "epoch": 1.95, "learning_rate": 1.754677132412536e-05, "loss": 1.0674, "step": 193000 }, { "epoch": 1.95, "learning_rate": 1.7462695602167138e-05, "loss": 1.0927, "step": 193500 }, { "epoch": 1.96, "learning_rate": 1.7378619880208912e-05, "loss": 1.0907, "step": 194000 }, { "epoch": 1.96, "learning_rate": 1.729454415825069e-05, "loss": 1.0699, "step": 194500 }, { "epoch": 1.97, "learning_rate": 1.721046843629246e-05, "loss": 1.0774, "step": 195000 }, { "epoch": 1.97, "learning_rate": 1.712639271433424e-05, "loss": 1.0636, "step": 195500 }, { "epoch": 1.98, "learning_rate": 1.7042316992376013e-05, "loss": 1.0867, "step": 196000 }, { "epoch": 1.98, "learning_rate": 1.695824127041779e-05, "loss": 1.0852, "step": 196500 }, { "epoch": 1.99, "learning_rate": 1.6874165548459565e-05, "loss": 1.0765, "step": 197000 }, { "epoch": 1.99, "learning_rate": 1.679008982650134e-05, "loss": 1.0837, "step": 197500 }, { "epoch": 2.0, "learning_rate": 1.6706014104543118e-05, "loss": 1.0867, "step": 198000 }, { "epoch": 2.0, "learning_rate": 1.6621938382584892e-05, "loss": 1.0085, "step": 198500 }, { "epoch": 2.01, "learning_rate": 1.653786266062667e-05, "loss": 0.9456, "step": 199000 }, { "epoch": 2.01, "learning_rate": 1.645378693866844e-05, "loss": 0.9705, "step": 199500 }, { "epoch": 2.02, "learning_rate": 1.636971121671022e-05, "loss": 0.9495, "step": 200000 }, { "epoch": 2.02, "learning_rate": 1.6285635494751993e-05, "loss": 0.9418, "step": 200500 }, { "epoch": 2.03, "learning_rate": 1.620155977279377e-05, "loss": 0.9662, "step": 201000 }, { "epoch": 2.03, "learning_rate": 1.6117484050835545e-05, "loss": 0.9555, "step": 201500 }, { "epoch": 2.04, "learning_rate": 1.603340832887732e-05, "loss": 0.971, "step": 202000 }, { "epoch": 2.04, "learning_rate": 1.5949332606919094e-05, "loss": 0.9524, "step": 202500 }, { "epoch": 2.05, "learning_rate": 1.5865256884960872e-05, "loss": 0.9548, "step": 203000 }, { "epoch": 2.05, "learning_rate": 1.5781181163002646e-05, "loss": 0.9459, "step": 203500 }, { "epoch": 2.06, "learning_rate": 1.5697105441044424e-05, "loss": 0.9789, "step": 204000 }, { "epoch": 2.06, "learning_rate": 1.56130297190862e-05, "loss": 0.9597, "step": 204500 }, { "epoch": 2.07, "learning_rate": 1.5528953997127973e-05, "loss": 0.9598, "step": 205000 }, { "epoch": 2.07, "learning_rate": 1.544487827516975e-05, "loss": 0.9553, "step": 205500 }, { "epoch": 2.08, "learning_rate": 1.5360802553211525e-05, "loss": 0.9534, "step": 206000 }, { "epoch": 2.08, "learning_rate": 1.5276726831253303e-05, "loss": 0.9633, "step": 206500 }, { "epoch": 2.09, "learning_rate": 1.5192651109295076e-05, "loss": 0.9581, "step": 207000 }, { "epoch": 2.09, "learning_rate": 1.5108575387336852e-05, "loss": 0.9878, "step": 207500 }, { "epoch": 2.1, "learning_rate": 1.5024499665378628e-05, "loss": 0.9497, "step": 208000 }, { "epoch": 2.1, "learning_rate": 1.4940423943420404e-05, "loss": 0.9281, "step": 208500 }, { "epoch": 2.11, "learning_rate": 1.485634822146218e-05, "loss": 0.9317, "step": 209000 }, { "epoch": 2.11, "learning_rate": 1.4772272499503953e-05, "loss": 0.9706, "step": 209500 }, { "epoch": 2.12, "learning_rate": 1.4688196777545729e-05, "loss": 0.9442, "step": 210000 }, { "epoch": 2.12, "learning_rate": 1.4604121055587505e-05, "loss": 0.9396, "step": 210500 }, { "epoch": 2.13, "learning_rate": 1.4520045333629281e-05, "loss": 0.949, "step": 211000 }, { "epoch": 2.13, "learning_rate": 1.4435969611671057e-05, "loss": 0.9398, "step": 211500 }, { "epoch": 2.14, "learning_rate": 1.4351893889712832e-05, "loss": 0.9528, "step": 212000 }, { "epoch": 2.14, "learning_rate": 1.4267818167754608e-05, "loss": 0.957, "step": 212500 }, { "epoch": 2.15, "learning_rate": 1.4183742445796384e-05, "loss": 0.9329, "step": 213000 }, { "epoch": 2.15, "learning_rate": 1.409966672383816e-05, "loss": 0.9674, "step": 213500 }, { "epoch": 2.16, "learning_rate": 1.4015591001879933e-05, "loss": 0.9738, "step": 214000 }, { "epoch": 2.16, "learning_rate": 1.3931515279921709e-05, "loss": 0.9381, "step": 214500 }, { "epoch": 2.17, "learning_rate": 1.3847439557963485e-05, "loss": 0.9415, "step": 215000 }, { "epoch": 2.17, "learning_rate": 1.376336383600526e-05, "loss": 0.9667, "step": 215500 }, { "epoch": 2.18, "learning_rate": 1.3679288114047037e-05, "loss": 0.94, "step": 216000 }, { "epoch": 2.18, "learning_rate": 1.359521239208881e-05, "loss": 0.9416, "step": 216500 }, { "epoch": 2.19, "learning_rate": 1.3511136670130586e-05, "loss": 0.9598, "step": 217000 }, { "epoch": 2.19, "learning_rate": 1.3427060948172362e-05, "loss": 0.9426, "step": 217500 }, { "epoch": 2.2, "learning_rate": 1.3342985226214138e-05, "loss": 0.9502, "step": 218000 }, { "epoch": 2.2, "learning_rate": 1.3258909504255914e-05, "loss": 0.9688, "step": 218500 }, { "epoch": 2.21, "learning_rate": 1.3174833782297688e-05, "loss": 0.9631, "step": 219000 }, { "epoch": 2.21, "learning_rate": 1.3090758060339465e-05, "loss": 0.9733, "step": 219500 }, { "epoch": 2.22, "learning_rate": 1.300668233838124e-05, "loss": 0.9459, "step": 220000 }, { "epoch": 2.22, "learning_rate": 1.2922606616423017e-05, "loss": 0.9466, "step": 220500 }, { "epoch": 2.23, "learning_rate": 1.2838530894464793e-05, "loss": 0.9597, "step": 221000 }, { "epoch": 2.23, "learning_rate": 1.2754455172506566e-05, "loss": 0.962, "step": 221500 }, { "epoch": 2.24, "learning_rate": 1.2670379450548342e-05, "loss": 0.941, "step": 222000 }, { "epoch": 2.24, "learning_rate": 1.2586303728590118e-05, "loss": 0.9641, "step": 222500 }, { "epoch": 2.25, "learning_rate": 1.2502228006631894e-05, "loss": 0.9468, "step": 223000 }, { "epoch": 2.25, "learning_rate": 1.2418152284673668e-05, "loss": 0.9348, "step": 223500 }, { "epoch": 2.26, "learning_rate": 1.2334076562715444e-05, "loss": 0.9465, "step": 224000 }, { "epoch": 2.26, "learning_rate": 1.225000084075722e-05, "loss": 0.9397, "step": 224500 }, { "epoch": 2.27, "learning_rate": 1.2165925118798997e-05, "loss": 0.9511, "step": 225000 }, { "epoch": 2.28, "learning_rate": 1.2081849396840771e-05, "loss": 0.9584, "step": 225500 }, { "epoch": 2.28, "learning_rate": 1.1997773674882547e-05, "loss": 0.9475, "step": 226000 }, { "epoch": 2.29, "learning_rate": 1.1913697952924323e-05, "loss": 0.9479, "step": 226500 }, { "epoch": 2.29, "learning_rate": 1.1829622230966098e-05, "loss": 0.9389, "step": 227000 }, { "epoch": 2.3, "learning_rate": 1.1745546509007874e-05, "loss": 0.9296, "step": 227500 }, { "epoch": 2.3, "learning_rate": 1.1661470787049648e-05, "loss": 0.9583, "step": 228000 }, { "epoch": 2.31, "learning_rate": 1.1577395065091424e-05, "loss": 0.9421, "step": 228500 }, { "epoch": 2.31, "learning_rate": 1.14933193431332e-05, "loss": 0.956, "step": 229000 }, { "epoch": 2.32, "learning_rate": 1.1409243621174975e-05, "loss": 0.9465, "step": 229500 }, { "epoch": 2.32, "learning_rate": 1.132516789921675e-05, "loss": 0.949, "step": 230000 }, { "epoch": 2.33, "learning_rate": 1.1241092177258527e-05, "loss": 0.9395, "step": 230500 }, { "epoch": 2.33, "learning_rate": 1.1157016455300303e-05, "loss": 0.9434, "step": 231000 }, { "epoch": 2.34, "learning_rate": 1.1072940733342079e-05, "loss": 0.9427, "step": 231500 }, { "epoch": 2.34, "learning_rate": 1.0988865011383853e-05, "loss": 0.9328, "step": 232000 }, { "epoch": 2.35, "learning_rate": 1.090478928942563e-05, "loss": 0.9507, "step": 232500 }, { "epoch": 2.35, "learning_rate": 1.0820713567467404e-05, "loss": 0.9259, "step": 233000 }, { "epoch": 2.36, "learning_rate": 1.073663784550918e-05, "loss": 0.9239, "step": 233500 }, { "epoch": 2.36, "learning_rate": 1.0652562123550954e-05, "loss": 0.9436, "step": 234000 }, { "epoch": 2.37, "learning_rate": 1.056848640159273e-05, "loss": 0.9416, "step": 234500 }, { "epoch": 2.37, "learning_rate": 1.0484410679634507e-05, "loss": 0.9183, "step": 235000 }, { "epoch": 2.38, "learning_rate": 1.0400334957676281e-05, "loss": 0.9397, "step": 235500 }, { "epoch": 2.38, "learning_rate": 1.0316259235718057e-05, "loss": 0.9445, "step": 236000 }, { "epoch": 2.39, "learning_rate": 1.0232183513759833e-05, "loss": 0.9304, "step": 236500 }, { "epoch": 2.39, "learning_rate": 1.014810779180161e-05, "loss": 0.957, "step": 237000 }, { "epoch": 2.4, "learning_rate": 1.0064032069843386e-05, "loss": 0.9597, "step": 237500 }, { "epoch": 2.4, "learning_rate": 9.97995634788516e-06, "loss": 0.9304, "step": 238000 }, { "epoch": 2.41, "learning_rate": 9.895880625926936e-06, "loss": 0.9216, "step": 238500 }, { "epoch": 2.41, "learning_rate": 9.81180490396871e-06, "loss": 0.9426, "step": 239000 }, { "epoch": 2.42, "learning_rate": 9.727729182010487e-06, "loss": 0.9429, "step": 239500 }, { "epoch": 2.42, "learning_rate": 9.643653460052261e-06, "loss": 0.9411, "step": 240000 }, { "epoch": 2.43, "learning_rate": 9.559577738094037e-06, "loss": 0.9379, "step": 240500 }, { "epoch": 2.43, "learning_rate": 9.475502016135813e-06, "loss": 0.9348, "step": 241000 }, { "epoch": 2.44, "learning_rate": 9.391426294177588e-06, "loss": 0.9384, "step": 241500 }, { "epoch": 2.44, "learning_rate": 9.307350572219364e-06, "loss": 0.9487, "step": 242000 }, { "epoch": 2.45, "learning_rate": 9.22327485026114e-06, "loss": 0.9541, "step": 242500 }, { "epoch": 2.45, "learning_rate": 9.139199128302916e-06, "loss": 0.9151, "step": 243000 }, { "epoch": 2.46, "learning_rate": 9.055123406344692e-06, "loss": 0.9459, "step": 243500 }, { "epoch": 2.46, "learning_rate": 8.971047684386466e-06, "loss": 0.9576, "step": 244000 }, { "epoch": 2.47, "learning_rate": 8.886971962428242e-06, "loss": 0.9614, "step": 244500 }, { "epoch": 2.47, "learning_rate": 8.802896240470017e-06, "loss": 0.9534, "step": 245000 }, { "epoch": 2.48, "learning_rate": 8.718820518511793e-06, "loss": 0.9374, "step": 245500 }, { "epoch": 2.48, "learning_rate": 8.634744796553569e-06, "loss": 0.9473, "step": 246000 }, { "epoch": 2.49, "learning_rate": 8.550669074595343e-06, "loss": 0.9226, "step": 246500 }, { "epoch": 2.49, "learning_rate": 8.46659335263712e-06, "loss": 0.9325, "step": 247000 }, { "epoch": 2.5, "learning_rate": 8.382517630678894e-06, "loss": 0.9334, "step": 247500 }, { "epoch": 2.5, "learning_rate": 8.29844190872067e-06, "loss": 0.9296, "step": 248000 }, { "epoch": 2.51, "learning_rate": 8.214366186762446e-06, "loss": 0.9479, "step": 248500 }, { "epoch": 2.51, "learning_rate": 8.130290464804222e-06, "loss": 0.9382, "step": 249000 }, { "epoch": 2.52, "learning_rate": 8.046214742845998e-06, "loss": 0.9315, "step": 249500 }, { "epoch": 2.52, "learning_rate": 7.962139020887773e-06, "loss": 0.928, "step": 250000 }, { "epoch": 2.53, "learning_rate": 7.878063298929549e-06, "loss": 0.9177, "step": 250500 }, { "epoch": 2.53, "learning_rate": 7.793987576971323e-06, "loss": 0.9426, "step": 251000 }, { "epoch": 2.54, "learning_rate": 7.7099118550131e-06, "loss": 0.9203, "step": 251500 }, { "epoch": 2.54, "learning_rate": 7.6258361330548755e-06, "loss": 0.9336, "step": 252000 }, { "epoch": 2.55, "learning_rate": 7.54176041109665e-06, "loss": 0.9226, "step": 252500 }, { "epoch": 2.55, "learning_rate": 7.457684689138427e-06, "loss": 0.9408, "step": 253000 }, { "epoch": 2.56, "learning_rate": 7.373608967180201e-06, "loss": 0.905, "step": 253500 }, { "epoch": 2.56, "learning_rate": 7.289533245221977e-06, "loss": 0.9285, "step": 254000 }, { "epoch": 2.57, "learning_rate": 7.205457523263752e-06, "loss": 0.9453, "step": 254500 }, { "epoch": 2.57, "learning_rate": 7.121381801305528e-06, "loss": 0.9162, "step": 255000 }, { "epoch": 2.58, "learning_rate": 7.037306079347304e-06, "loss": 0.9277, "step": 255500 }, { "epoch": 2.58, "learning_rate": 6.953230357389079e-06, "loss": 0.9423, "step": 256000 }, { "epoch": 2.59, "learning_rate": 6.869154635430855e-06, "loss": 0.9405, "step": 256500 }, { "epoch": 2.59, "learning_rate": 6.78507891347263e-06, "loss": 0.9366, "step": 257000 }, { "epoch": 2.6, "learning_rate": 6.701003191514406e-06, "loss": 0.9361, "step": 257500 }, { "epoch": 2.6, "learning_rate": 6.616927469556182e-06, "loss": 0.9294, "step": 258000 }, { "epoch": 2.61, "learning_rate": 6.532851747597957e-06, "loss": 0.9222, "step": 258500 }, { "epoch": 2.61, "learning_rate": 6.448776025639733e-06, "loss": 0.9371, "step": 259000 }, { "epoch": 2.62, "learning_rate": 6.364700303681508e-06, "loss": 0.9173, "step": 259500 }, { "epoch": 2.62, "learning_rate": 6.280624581723284e-06, "loss": 0.9427, "step": 260000 }, { "epoch": 2.63, "learning_rate": 6.196548859765059e-06, "loss": 0.9122, "step": 260500 }, { "epoch": 2.63, "learning_rate": 6.112473137806834e-06, "loss": 0.9303, "step": 261000 }, { "epoch": 2.64, "learning_rate": 6.02839741584861e-06, "loss": 0.9178, "step": 261500 }, { "epoch": 2.64, "learning_rate": 5.9443216938903864e-06, "loss": 0.9386, "step": 262000 }, { "epoch": 2.65, "learning_rate": 5.860245971932162e-06, "loss": 0.9144, "step": 262500 }, { "epoch": 2.65, "learning_rate": 5.776170249973937e-06, "loss": 0.9091, "step": 263000 }, { "epoch": 2.66, "learning_rate": 5.692094528015712e-06, "loss": 0.9107, "step": 263500 }, { "epoch": 2.66, "learning_rate": 5.6080188060574874e-06, "loss": 0.9165, "step": 264000 }, { "epoch": 2.67, "learning_rate": 5.5239430840992635e-06, "loss": 0.9414, "step": 264500 }, { "epoch": 2.67, "learning_rate": 5.43986736214104e-06, "loss": 0.9175, "step": 265000 }, { "epoch": 2.68, "learning_rate": 5.355791640182815e-06, "loss": 0.9249, "step": 265500 }, { "epoch": 2.68, "learning_rate": 5.27171591822459e-06, "loss": 0.9176, "step": 266000 }, { "epoch": 2.69, "learning_rate": 5.187640196266365e-06, "loss": 0.9209, "step": 266500 }, { "epoch": 2.69, "learning_rate": 5.103564474308141e-06, "loss": 0.9173, "step": 267000 }, { "epoch": 2.7, "learning_rate": 5.019488752349917e-06, "loss": 0.9115, "step": 267500 }, { "epoch": 2.7, "learning_rate": 4.935413030391693e-06, "loss": 0.917, "step": 268000 }, { "epoch": 2.71, "learning_rate": 4.851337308433468e-06, "loss": 0.9227, "step": 268500 }, { "epoch": 2.71, "learning_rate": 4.767261586475243e-06, "loss": 0.9323, "step": 269000 }, { "epoch": 2.72, "learning_rate": 4.683185864517019e-06, "loss": 0.9217, "step": 269500 }, { "epoch": 2.72, "learning_rate": 4.599110142558794e-06, "loss": 0.9, "step": 270000 }, { "epoch": 2.73, "learning_rate": 4.51503442060057e-06, "loss": 0.919, "step": 270500 }, { "epoch": 2.73, "learning_rate": 4.430958698642346e-06, "loss": 0.9121, "step": 271000 }, { "epoch": 2.74, "learning_rate": 4.346882976684121e-06, "loss": 0.9202, "step": 271500 }, { "epoch": 2.74, "learning_rate": 4.2628072547258966e-06, "loss": 0.9246, "step": 272000 }, { "epoch": 2.75, "learning_rate": 4.178731532767672e-06, "loss": 0.9233, "step": 272500 }, { "epoch": 2.75, "learning_rate": 4.094655810809447e-06, "loss": 0.9228, "step": 273000 }, { "epoch": 2.76, "learning_rate": 4.010580088851223e-06, "loss": 0.9312, "step": 273500 }, { "epoch": 2.76, "learning_rate": 3.926504366892999e-06, "loss": 0.9052, "step": 274000 }, { "epoch": 2.77, "learning_rate": 3.8424286449347745e-06, "loss": 0.9131, "step": 274500 }, { "epoch": 2.77, "learning_rate": 3.7583529229765498e-06, "loss": 0.9215, "step": 275000 }, { "epoch": 2.78, "learning_rate": 3.674277201018325e-06, "loss": 0.9364, "step": 275500 }, { "epoch": 2.78, "learning_rate": 3.5902014790601007e-06, "loss": 0.9186, "step": 276000 }, { "epoch": 2.79, "learning_rate": 3.506125757101877e-06, "loss": 0.9324, "step": 276500 }, { "epoch": 2.79, "learning_rate": 3.422050035143652e-06, "loss": 0.9058, "step": 277000 }, { "epoch": 2.8, "learning_rate": 3.3379743131854277e-06, "loss": 0.9328, "step": 277500 }, { "epoch": 2.8, "learning_rate": 3.253898591227203e-06, "loss": 0.9124, "step": 278000 }, { "epoch": 2.81, "learning_rate": 3.1698228692689782e-06, "loss": 0.9265, "step": 278500 }, { "epoch": 2.81, "learning_rate": 3.0857471473107543e-06, "loss": 0.9062, "step": 279000 }, { "epoch": 2.82, "learning_rate": 3.0016714253525296e-06, "loss": 0.9084, "step": 279500 }, { "epoch": 2.82, "learning_rate": 2.9175957033943053e-06, "loss": 0.9035, "step": 280000 }, { "epoch": 2.83, "learning_rate": 2.833519981436081e-06, "loss": 0.9215, "step": 280500 }, { "epoch": 2.84, "learning_rate": 2.749444259477856e-06, "loss": 0.9205, "step": 281000 }, { "epoch": 2.84, "learning_rate": 2.665368537519632e-06, "loss": 0.914, "step": 281500 }, { "epoch": 2.85, "learning_rate": 2.5812928155614076e-06, "loss": 0.9286, "step": 282000 }, { "epoch": 2.85, "learning_rate": 2.497217093603183e-06, "loss": 0.9142, "step": 282500 }, { "epoch": 2.86, "learning_rate": 2.4131413716449585e-06, "loss": 0.9019, "step": 283000 }, { "epoch": 2.86, "learning_rate": 2.329065649686734e-06, "loss": 0.9042, "step": 283500 }, { "epoch": 2.87, "learning_rate": 2.2449899277285094e-06, "loss": 0.8945, "step": 284000 }, { "epoch": 2.87, "learning_rate": 2.160914205770285e-06, "loss": 0.9091, "step": 284500 }, { "epoch": 2.88, "learning_rate": 2.0768384838120608e-06, "loss": 0.9094, "step": 285000 }, { "epoch": 2.88, "learning_rate": 1.992762761853836e-06, "loss": 0.9003, "step": 285500 }, { "epoch": 2.89, "learning_rate": 1.9086870398956117e-06, "loss": 0.9181, "step": 286000 }, { "epoch": 2.89, "learning_rate": 1.8246113179373872e-06, "loss": 0.8937, "step": 286500 }, { "epoch": 2.9, "learning_rate": 1.7405355959791626e-06, "loss": 0.9399, "step": 287000 }, { "epoch": 2.9, "learning_rate": 1.6564598740209383e-06, "loss": 0.9281, "step": 287500 }, { "epoch": 2.91, "learning_rate": 1.5723841520627138e-06, "loss": 0.902, "step": 288000 }, { "epoch": 2.91, "learning_rate": 1.4883084301044894e-06, "loss": 0.9053, "step": 288500 }, { "epoch": 2.92, "learning_rate": 1.404232708146265e-06, "loss": 0.9179, "step": 289000 }, { "epoch": 2.92, "learning_rate": 1.3201569861880404e-06, "loss": 0.9268, "step": 289500 }, { "epoch": 2.93, "learning_rate": 1.236081264229816e-06, "loss": 0.915, "step": 290000 }, { "epoch": 2.93, "learning_rate": 1.1520055422715917e-06, "loss": 0.9112, "step": 290500 }, { "epoch": 2.94, "learning_rate": 1.067929820313367e-06, "loss": 0.8993, "step": 291000 }, { "epoch": 2.94, "learning_rate": 9.838540983551427e-07, "loss": 0.9164, "step": 291500 }, { "epoch": 2.95, "learning_rate": 8.997783763969182e-07, "loss": 0.9093, "step": 292000 }, { "epoch": 2.95, "learning_rate": 8.157026544386937e-07, "loss": 0.9248, "step": 292500 }, { "epoch": 2.96, "learning_rate": 7.316269324804693e-07, "loss": 0.9113, "step": 293000 }, { "epoch": 2.96, "learning_rate": 6.475512105222447e-07, "loss": 0.8972, "step": 293500 }, { "epoch": 2.97, "learning_rate": 5.634754885640203e-07, "loss": 0.9063, "step": 294000 }, { "epoch": 2.97, "learning_rate": 4.793997666057959e-07, "loss": 0.8965, "step": 294500 }, { "epoch": 2.98, "learning_rate": 3.9532404464757143e-07, "loss": 0.8942, "step": 295000 }, { "epoch": 2.98, "learning_rate": 3.1124832268934695e-07, "loss": 0.915, "step": 295500 }, { "epoch": 2.99, "learning_rate": 2.271726007311225e-07, "loss": 0.9004, "step": 296000 }, { "epoch": 2.99, "learning_rate": 1.4309687877289804e-07, "loss": 0.911, "step": 296500 }, { "epoch": 3.0, "learning_rate": 5.9021156814673575e-08, "loss": 0.9109, "step": 297000 }, { "epoch": 3.0, "step": 297351, "total_flos": 4.068929596395356e+17, "train_loss": 1.1922712472395904, "train_runtime": 76376.5863, "train_samples_per_second": 38.932, "train_steps_per_second": 3.893 } ], "max_steps": 297351, "num_train_epochs": 3, "total_flos": 4.068929596395356e+17, "trial_name": null, "trial_params": null }