HotelBERT / trainer_state.json
FabianGroeger's picture
initial upload of HotelBERT
c224a44
raw
history blame
No virus
144 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 27.98460846534406,
"global_step": 560000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.996876717805207e-05,
"loss": 7.0842,
"step": 500
},
{
"epoch": 0.05,
"learning_rate": 4.9937534356104144e-05,
"loss": 6.6438,
"step": 1000
},
{
"epoch": 0.07,
"learning_rate": 4.990630153415622e-05,
"loss": 6.5737,
"step": 1500
},
{
"epoch": 0.1,
"learning_rate": 4.987506871220829e-05,
"loss": 6.5159,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 4.984383589026036e-05,
"loss": 6.4759,
"step": 2500
},
{
"epoch": 0.15,
"learning_rate": 4.981260306831243e-05,
"loss": 6.4494,
"step": 3000
},
{
"epoch": 0.17,
"learning_rate": 4.97813702463645e-05,
"loss": 6.4225,
"step": 3500
},
{
"epoch": 0.2,
"learning_rate": 4.975013742441657e-05,
"loss": 6.3925,
"step": 4000
},
{
"epoch": 0.22,
"learning_rate": 4.9718904602468644e-05,
"loss": 6.3596,
"step": 4500
},
{
"epoch": 0.25,
"learning_rate": 4.968767178052072e-05,
"loss": 6.3223,
"step": 5000
},
{
"epoch": 0.27,
"learning_rate": 4.9656438958572785e-05,
"loss": 6.2606,
"step": 5500
},
{
"epoch": 0.3,
"learning_rate": 4.962520613662486e-05,
"loss": 6.2084,
"step": 6000
},
{
"epoch": 0.32,
"learning_rate": 4.959397331467693e-05,
"loss": 6.1361,
"step": 6500
},
{
"epoch": 0.35,
"learning_rate": 4.9562740492729e-05,
"loss": 6.071,
"step": 7000
},
{
"epoch": 0.37,
"learning_rate": 4.9531507670781075e-05,
"loss": 5.8919,
"step": 7500
},
{
"epoch": 0.4,
"learning_rate": 4.950027484883314e-05,
"loss": 5.5238,
"step": 8000
},
{
"epoch": 0.42,
"learning_rate": 4.946904202688522e-05,
"loss": 5.2675,
"step": 8500
},
{
"epoch": 0.45,
"learning_rate": 4.9437809204937285e-05,
"loss": 5.0533,
"step": 9000
},
{
"epoch": 0.47,
"learning_rate": 4.940657638298936e-05,
"loss": 4.7952,
"step": 9500
},
{
"epoch": 0.5,
"learning_rate": 4.937534356104143e-05,
"loss": 4.5975,
"step": 10000
},
{
"epoch": 0.52,
"learning_rate": 4.93441107390935e-05,
"loss": 4.4187,
"step": 10500
},
{
"epoch": 0.55,
"learning_rate": 4.9312877917145575e-05,
"loss": 4.2773,
"step": 11000
},
{
"epoch": 0.57,
"learning_rate": 4.928164509519764e-05,
"loss": 4.1502,
"step": 11500
},
{
"epoch": 0.6,
"learning_rate": 4.925041227324971e-05,
"loss": 4.0437,
"step": 12000
},
{
"epoch": 0.62,
"learning_rate": 4.921917945130179e-05,
"loss": 3.947,
"step": 12500
},
{
"epoch": 0.65,
"learning_rate": 4.918794662935386e-05,
"loss": 3.848,
"step": 13000
},
{
"epoch": 0.67,
"learning_rate": 4.915671380740593e-05,
"loss": 3.7852,
"step": 13500
},
{
"epoch": 0.7,
"learning_rate": 4.9125480985458e-05,
"loss": 3.7079,
"step": 14000
},
{
"epoch": 0.72,
"learning_rate": 4.909424816351007e-05,
"loss": 3.647,
"step": 14500
},
{
"epoch": 0.75,
"learning_rate": 4.906301534156214e-05,
"loss": 3.5871,
"step": 15000
},
{
"epoch": 0.77,
"learning_rate": 4.9031782519614216e-05,
"loss": 3.5298,
"step": 15500
},
{
"epoch": 0.8,
"learning_rate": 4.900054969766629e-05,
"loss": 3.4878,
"step": 16000
},
{
"epoch": 0.82,
"learning_rate": 4.896931687571836e-05,
"loss": 3.4355,
"step": 16500
},
{
"epoch": 0.85,
"learning_rate": 4.8938084053770425e-05,
"loss": 3.3967,
"step": 17000
},
{
"epoch": 0.87,
"learning_rate": 4.89068512318225e-05,
"loss": 3.3442,
"step": 17500
},
{
"epoch": 0.9,
"learning_rate": 4.8875618409874574e-05,
"loss": 3.3194,
"step": 18000
},
{
"epoch": 0.92,
"learning_rate": 4.884438558792664e-05,
"loss": 3.2803,
"step": 18500
},
{
"epoch": 0.95,
"learning_rate": 4.8813152765978715e-05,
"loss": 3.2553,
"step": 19000
},
{
"epoch": 0.97,
"learning_rate": 4.878191994403078e-05,
"loss": 3.2061,
"step": 19500
},
{
"epoch": 1.0,
"learning_rate": 4.875068712208286e-05,
"loss": 3.187,
"step": 20000
},
{
"epoch": 1.0,
"eval_loss": 3.0986874103546143,
"eval_runtime": 81.7163,
"eval_samples_per_second": 518.134,
"eval_steps_per_second": 64.773,
"step": 20011
},
{
"epoch": 1.02,
"learning_rate": 4.8719454300134925e-05,
"loss": 3.1521,
"step": 20500
},
{
"epoch": 1.05,
"learning_rate": 4.8688221478187e-05,
"loss": 3.125,
"step": 21000
},
{
"epoch": 1.07,
"learning_rate": 4.865698865623907e-05,
"loss": 3.1055,
"step": 21500
},
{
"epoch": 1.1,
"learning_rate": 4.862575583429114e-05,
"loss": 3.0812,
"step": 22000
},
{
"epoch": 1.12,
"learning_rate": 4.8594523012343215e-05,
"loss": 3.0549,
"step": 22500
},
{
"epoch": 1.15,
"learning_rate": 4.856329019039528e-05,
"loss": 3.0322,
"step": 23000
},
{
"epoch": 1.17,
"learning_rate": 4.8532057368447356e-05,
"loss": 3.0124,
"step": 23500
},
{
"epoch": 1.2,
"learning_rate": 4.850082454649943e-05,
"loss": 2.9935,
"step": 24000
},
{
"epoch": 1.22,
"learning_rate": 4.84695917245515e-05,
"loss": 2.9711,
"step": 24500
},
{
"epoch": 1.25,
"learning_rate": 4.843835890260357e-05,
"loss": 2.9543,
"step": 25000
},
{
"epoch": 1.27,
"learning_rate": 4.840712608065564e-05,
"loss": 2.9321,
"step": 25500
},
{
"epoch": 1.3,
"learning_rate": 4.837589325870771e-05,
"loss": 2.9138,
"step": 26000
},
{
"epoch": 1.32,
"learning_rate": 4.834466043675979e-05,
"loss": 2.9024,
"step": 26500
},
{
"epoch": 1.35,
"learning_rate": 4.8313427614811856e-05,
"loss": 2.8827,
"step": 27000
},
{
"epoch": 1.37,
"learning_rate": 4.828219479286393e-05,
"loss": 2.865,
"step": 27500
},
{
"epoch": 1.4,
"learning_rate": 4.8250961970916e-05,
"loss": 2.8484,
"step": 28000
},
{
"epoch": 1.42,
"learning_rate": 4.8219729148968065e-05,
"loss": 2.8291,
"step": 28500
},
{
"epoch": 1.45,
"learning_rate": 4.8188496327020146e-05,
"loss": 2.8192,
"step": 29000
},
{
"epoch": 1.47,
"learning_rate": 4.8157263505072214e-05,
"loss": 2.8048,
"step": 29500
},
{
"epoch": 1.5,
"learning_rate": 4.812603068312429e-05,
"loss": 2.8006,
"step": 30000
},
{
"epoch": 1.52,
"learning_rate": 4.8094797861176355e-05,
"loss": 2.7749,
"step": 30500
},
{
"epoch": 1.55,
"learning_rate": 4.806356503922842e-05,
"loss": 2.7719,
"step": 31000
},
{
"epoch": 1.57,
"learning_rate": 4.80323322172805e-05,
"loss": 2.7517,
"step": 31500
},
{
"epoch": 1.6,
"learning_rate": 4.800109939533257e-05,
"loss": 2.7411,
"step": 32000
},
{
"epoch": 1.62,
"learning_rate": 4.796986657338464e-05,
"loss": 2.7355,
"step": 32500
},
{
"epoch": 1.65,
"learning_rate": 4.793863375143671e-05,
"loss": 2.718,
"step": 33000
},
{
"epoch": 1.67,
"learning_rate": 4.790740092948878e-05,
"loss": 2.7018,
"step": 33500
},
{
"epoch": 1.7,
"learning_rate": 4.7876168107540855e-05,
"loss": 2.7002,
"step": 34000
},
{
"epoch": 1.72,
"learning_rate": 4.784493528559293e-05,
"loss": 2.6822,
"step": 34500
},
{
"epoch": 1.75,
"learning_rate": 4.7813702463644996e-05,
"loss": 2.6779,
"step": 35000
},
{
"epoch": 1.77,
"learning_rate": 4.778246964169707e-05,
"loss": 2.6531,
"step": 35500
},
{
"epoch": 1.8,
"learning_rate": 4.775123681974914e-05,
"loss": 2.6505,
"step": 36000
},
{
"epoch": 1.82,
"learning_rate": 4.772000399780121e-05,
"loss": 2.6469,
"step": 36500
},
{
"epoch": 1.85,
"learning_rate": 4.768877117585328e-05,
"loss": 2.6373,
"step": 37000
},
{
"epoch": 1.87,
"learning_rate": 4.7657538353905354e-05,
"loss": 2.6297,
"step": 37500
},
{
"epoch": 1.9,
"learning_rate": 4.762630553195743e-05,
"loss": 2.6108,
"step": 38000
},
{
"epoch": 1.92,
"learning_rate": 4.7595072710009496e-05,
"loss": 2.6075,
"step": 38500
},
{
"epoch": 1.95,
"learning_rate": 4.756383988806157e-05,
"loss": 2.5989,
"step": 39000
},
{
"epoch": 1.97,
"learning_rate": 4.753260706611364e-05,
"loss": 2.5877,
"step": 39500
},
{
"epoch": 2.0,
"learning_rate": 4.750137424416571e-05,
"loss": 2.5723,
"step": 40000
},
{
"epoch": 2.0,
"eval_loss": 2.5052835941314697,
"eval_runtime": 80.9375,
"eval_samples_per_second": 523.119,
"eval_steps_per_second": 65.396,
"step": 40022
},
{
"epoch": 2.02,
"learning_rate": 4.7470141422217786e-05,
"loss": 2.563,
"step": 40500
},
{
"epoch": 2.05,
"learning_rate": 4.7438908600269853e-05,
"loss": 2.5626,
"step": 41000
},
{
"epoch": 2.07,
"learning_rate": 4.740767577832193e-05,
"loss": 2.5513,
"step": 41500
},
{
"epoch": 2.1,
"learning_rate": 4.7376442956373995e-05,
"loss": 2.5488,
"step": 42000
},
{
"epoch": 2.12,
"learning_rate": 4.734521013442606e-05,
"loss": 2.5346,
"step": 42500
},
{
"epoch": 2.15,
"learning_rate": 4.7313977312478144e-05,
"loss": 2.5278,
"step": 43000
},
{
"epoch": 2.17,
"learning_rate": 4.728274449053021e-05,
"loss": 2.5206,
"step": 43500
},
{
"epoch": 2.2,
"learning_rate": 4.7251511668582285e-05,
"loss": 2.5126,
"step": 44000
},
{
"epoch": 2.22,
"learning_rate": 4.722027884663435e-05,
"loss": 2.5098,
"step": 44500
},
{
"epoch": 2.25,
"learning_rate": 4.718904602468642e-05,
"loss": 2.5023,
"step": 45000
},
{
"epoch": 2.27,
"learning_rate": 4.7157813202738495e-05,
"loss": 2.4923,
"step": 45500
},
{
"epoch": 2.3,
"learning_rate": 4.712658038079057e-05,
"loss": 2.4837,
"step": 46000
},
{
"epoch": 2.32,
"learning_rate": 4.7095347558842636e-05,
"loss": 2.4783,
"step": 46500
},
{
"epoch": 2.35,
"learning_rate": 4.706411473689471e-05,
"loss": 2.473,
"step": 47000
},
{
"epoch": 2.37,
"learning_rate": 4.703288191494678e-05,
"loss": 2.4662,
"step": 47500
},
{
"epoch": 2.4,
"learning_rate": 4.700164909299885e-05,
"loss": 2.4585,
"step": 48000
},
{
"epoch": 2.42,
"learning_rate": 4.6970416271050927e-05,
"loss": 2.4584,
"step": 48500
},
{
"epoch": 2.45,
"learning_rate": 4.6939183449102994e-05,
"loss": 2.452,
"step": 49000
},
{
"epoch": 2.47,
"learning_rate": 4.690795062715507e-05,
"loss": 2.4444,
"step": 49500
},
{
"epoch": 2.5,
"learning_rate": 4.6876717805207136e-05,
"loss": 2.4335,
"step": 50000
},
{
"epoch": 2.52,
"learning_rate": 4.684548498325921e-05,
"loss": 2.4284,
"step": 50500
},
{
"epoch": 2.55,
"learning_rate": 4.681425216131128e-05,
"loss": 2.4284,
"step": 51000
},
{
"epoch": 2.57,
"learning_rate": 4.678301933936335e-05,
"loss": 2.4232,
"step": 51500
},
{
"epoch": 2.6,
"learning_rate": 4.6751786517415426e-05,
"loss": 2.4164,
"step": 52000
},
{
"epoch": 2.62,
"learning_rate": 4.6720553695467493e-05,
"loss": 2.4078,
"step": 52500
},
{
"epoch": 2.65,
"learning_rate": 4.668932087351957e-05,
"loss": 2.4032,
"step": 53000
},
{
"epoch": 2.67,
"learning_rate": 4.6658088051571635e-05,
"loss": 2.4042,
"step": 53500
},
{
"epoch": 2.7,
"learning_rate": 4.662685522962371e-05,
"loss": 2.3996,
"step": 54000
},
{
"epoch": 2.72,
"learning_rate": 4.6595622407675784e-05,
"loss": 2.3903,
"step": 54500
},
{
"epoch": 2.75,
"learning_rate": 4.656438958572785e-05,
"loss": 2.3884,
"step": 55000
},
{
"epoch": 2.77,
"learning_rate": 4.6533156763779925e-05,
"loss": 2.3811,
"step": 55500
},
{
"epoch": 2.8,
"learning_rate": 4.650192394183199e-05,
"loss": 2.3796,
"step": 56000
},
{
"epoch": 2.82,
"learning_rate": 4.647069111988406e-05,
"loss": 2.3694,
"step": 56500
},
{
"epoch": 2.85,
"learning_rate": 4.643945829793614e-05,
"loss": 2.3737,
"step": 57000
},
{
"epoch": 2.87,
"learning_rate": 4.640822547598821e-05,
"loss": 2.3666,
"step": 57500
},
{
"epoch": 2.9,
"learning_rate": 4.637699265404028e-05,
"loss": 2.3562,
"step": 58000
},
{
"epoch": 2.92,
"learning_rate": 4.634575983209235e-05,
"loss": 2.357,
"step": 58500
},
{
"epoch": 2.95,
"learning_rate": 4.631452701014442e-05,
"loss": 2.3465,
"step": 59000
},
{
"epoch": 2.97,
"learning_rate": 4.62832941881965e-05,
"loss": 2.3487,
"step": 59500
},
{
"epoch": 3.0,
"learning_rate": 4.6252061366248566e-05,
"loss": 2.3438,
"step": 60000
},
{
"epoch": 3.0,
"eval_loss": 2.2806928157806396,
"eval_runtime": 81.0976,
"eval_samples_per_second": 522.087,
"eval_steps_per_second": 65.267,
"step": 60033
},
{
"epoch": 3.02,
"learning_rate": 4.6220828544300634e-05,
"loss": 2.3323,
"step": 60500
},
{
"epoch": 3.05,
"learning_rate": 4.618959572235271e-05,
"loss": 2.3298,
"step": 61000
},
{
"epoch": 3.07,
"learning_rate": 4.6158362900404776e-05,
"loss": 2.3231,
"step": 61500
},
{
"epoch": 3.1,
"learning_rate": 4.612713007845685e-05,
"loss": 2.3205,
"step": 62000
},
{
"epoch": 3.12,
"learning_rate": 4.6095897256508924e-05,
"loss": 2.3229,
"step": 62500
},
{
"epoch": 3.15,
"learning_rate": 4.606466443456099e-05,
"loss": 2.3097,
"step": 63000
},
{
"epoch": 3.17,
"learning_rate": 4.6033431612613066e-05,
"loss": 2.3139,
"step": 63500
},
{
"epoch": 3.2,
"learning_rate": 4.600219879066513e-05,
"loss": 2.3046,
"step": 64000
},
{
"epoch": 3.22,
"learning_rate": 4.597096596871721e-05,
"loss": 2.3037,
"step": 64500
},
{
"epoch": 3.25,
"learning_rate": 4.593973314676928e-05,
"loss": 2.2963,
"step": 65000
},
{
"epoch": 3.27,
"learning_rate": 4.590850032482135e-05,
"loss": 2.2929,
"step": 65500
},
{
"epoch": 3.3,
"learning_rate": 4.5877267502873424e-05,
"loss": 2.2935,
"step": 66000
},
{
"epoch": 3.32,
"learning_rate": 4.584603468092549e-05,
"loss": 2.2986,
"step": 66500
},
{
"epoch": 3.35,
"learning_rate": 4.5814801858977565e-05,
"loss": 2.2883,
"step": 67000
},
{
"epoch": 3.37,
"learning_rate": 4.578356903702963e-05,
"loss": 2.2842,
"step": 67500
},
{
"epoch": 3.4,
"learning_rate": 4.575233621508171e-05,
"loss": 2.273,
"step": 68000
},
{
"epoch": 3.42,
"learning_rate": 4.572110339313378e-05,
"loss": 2.2754,
"step": 68500
},
{
"epoch": 3.45,
"learning_rate": 4.568987057118585e-05,
"loss": 2.2792,
"step": 69000
},
{
"epoch": 3.47,
"learning_rate": 4.565863774923792e-05,
"loss": 2.2664,
"step": 69500
},
{
"epoch": 3.5,
"learning_rate": 4.562740492728999e-05,
"loss": 2.2642,
"step": 70000
},
{
"epoch": 3.52,
"learning_rate": 4.5596172105342065e-05,
"loss": 2.2556,
"step": 70500
},
{
"epoch": 3.55,
"learning_rate": 4.556493928339414e-05,
"loss": 2.2614,
"step": 71000
},
{
"epoch": 3.57,
"learning_rate": 4.5533706461446206e-05,
"loss": 2.2549,
"step": 71500
},
{
"epoch": 3.6,
"learning_rate": 4.550247363949828e-05,
"loss": 2.2513,
"step": 72000
},
{
"epoch": 3.62,
"learning_rate": 4.547124081755035e-05,
"loss": 2.2518,
"step": 72500
},
{
"epoch": 3.65,
"learning_rate": 4.5440007995602416e-05,
"loss": 2.2552,
"step": 73000
},
{
"epoch": 3.67,
"learning_rate": 4.5408775173654497e-05,
"loss": 2.2443,
"step": 73500
},
{
"epoch": 3.7,
"learning_rate": 4.5377542351706564e-05,
"loss": 2.2444,
"step": 74000
},
{
"epoch": 3.72,
"learning_rate": 4.534630952975863e-05,
"loss": 2.2418,
"step": 74500
},
{
"epoch": 3.75,
"learning_rate": 4.5315076707810706e-05,
"loss": 2.2369,
"step": 75000
},
{
"epoch": 3.77,
"learning_rate": 4.528384388586277e-05,
"loss": 2.2321,
"step": 75500
},
{
"epoch": 3.8,
"learning_rate": 4.5252611063914854e-05,
"loss": 2.2289,
"step": 76000
},
{
"epoch": 3.82,
"learning_rate": 4.522137824196692e-05,
"loss": 2.2313,
"step": 76500
},
{
"epoch": 3.85,
"learning_rate": 4.519014542001899e-05,
"loss": 2.2309,
"step": 77000
},
{
"epoch": 3.87,
"learning_rate": 4.5158912598071063e-05,
"loss": 2.2331,
"step": 77500
},
{
"epoch": 3.9,
"learning_rate": 4.512767977612313e-05,
"loss": 2.2139,
"step": 78000
},
{
"epoch": 3.92,
"learning_rate": 4.5096446954175205e-05,
"loss": 2.2197,
"step": 78500
},
{
"epoch": 3.95,
"learning_rate": 4.506521413222728e-05,
"loss": 2.214,
"step": 79000
},
{
"epoch": 3.97,
"learning_rate": 4.503398131027935e-05,
"loss": 2.2163,
"step": 79500
},
{
"epoch": 4.0,
"learning_rate": 4.500274848833142e-05,
"loss": 2.2165,
"step": 80000
},
{
"epoch": 4.0,
"eval_loss": 2.1498630046844482,
"eval_runtime": 81.0523,
"eval_samples_per_second": 522.379,
"eval_steps_per_second": 65.304,
"step": 80044
},
{
"epoch": 4.02,
"learning_rate": 4.497151566638349e-05,
"loss": 2.1989,
"step": 80500
},
{
"epoch": 4.05,
"learning_rate": 4.494028284443556e-05,
"loss": 2.2004,
"step": 81000
},
{
"epoch": 4.07,
"learning_rate": 4.490905002248764e-05,
"loss": 2.1983,
"step": 81500
},
{
"epoch": 4.1,
"learning_rate": 4.4877817200539705e-05,
"loss": 2.1891,
"step": 82000
},
{
"epoch": 4.12,
"learning_rate": 4.484658437859178e-05,
"loss": 2.1902,
"step": 82500
},
{
"epoch": 4.15,
"learning_rate": 4.4815351556643846e-05,
"loss": 2.1935,
"step": 83000
},
{
"epoch": 4.17,
"learning_rate": 4.478411873469592e-05,
"loss": 2.1835,
"step": 83500
},
{
"epoch": 4.2,
"learning_rate": 4.475288591274799e-05,
"loss": 2.1863,
"step": 84000
},
{
"epoch": 4.22,
"learning_rate": 4.472165309080006e-05,
"loss": 2.177,
"step": 84500
},
{
"epoch": 4.25,
"learning_rate": 4.4690420268852136e-05,
"loss": 2.1814,
"step": 85000
},
{
"epoch": 4.27,
"learning_rate": 4.4659187446904204e-05,
"loss": 2.1741,
"step": 85500
},
{
"epoch": 4.3,
"learning_rate": 4.462795462495628e-05,
"loss": 2.1782,
"step": 86000
},
{
"epoch": 4.32,
"learning_rate": 4.4596721803008346e-05,
"loss": 2.1733,
"step": 86500
},
{
"epoch": 4.35,
"learning_rate": 4.456548898106042e-05,
"loss": 2.1652,
"step": 87000
},
{
"epoch": 4.37,
"learning_rate": 4.4534256159112494e-05,
"loss": 2.1719,
"step": 87500
},
{
"epoch": 4.4,
"learning_rate": 4.450302333716456e-05,
"loss": 2.1672,
"step": 88000
},
{
"epoch": 4.42,
"learning_rate": 4.4471790515216636e-05,
"loss": 2.1622,
"step": 88500
},
{
"epoch": 4.45,
"learning_rate": 4.44405576932687e-05,
"loss": 2.1614,
"step": 89000
},
{
"epoch": 4.47,
"learning_rate": 4.440932487132077e-05,
"loss": 2.1683,
"step": 89500
},
{
"epoch": 4.5,
"learning_rate": 4.437809204937285e-05,
"loss": 2.1638,
"step": 90000
},
{
"epoch": 4.52,
"learning_rate": 4.434685922742492e-05,
"loss": 2.1583,
"step": 90500
},
{
"epoch": 4.55,
"learning_rate": 4.431562640547699e-05,
"loss": 2.1588,
"step": 91000
},
{
"epoch": 4.57,
"learning_rate": 4.428439358352906e-05,
"loss": 2.1533,
"step": 91500
},
{
"epoch": 4.6,
"learning_rate": 4.425316076158113e-05,
"loss": 2.1483,
"step": 92000
},
{
"epoch": 4.62,
"learning_rate": 4.422192793963321e-05,
"loss": 2.1449,
"step": 92500
},
{
"epoch": 4.65,
"learning_rate": 4.419069511768528e-05,
"loss": 2.1507,
"step": 93000
},
{
"epoch": 4.67,
"learning_rate": 4.4159462295737344e-05,
"loss": 2.145,
"step": 93500
},
{
"epoch": 4.7,
"learning_rate": 4.412822947378942e-05,
"loss": 2.1391,
"step": 94000
},
{
"epoch": 4.72,
"learning_rate": 4.4096996651841486e-05,
"loss": 2.1343,
"step": 94500
},
{
"epoch": 4.75,
"learning_rate": 4.406576382989356e-05,
"loss": 2.1392,
"step": 95000
},
{
"epoch": 4.77,
"learning_rate": 4.4034531007945635e-05,
"loss": 2.147,
"step": 95500
},
{
"epoch": 4.8,
"learning_rate": 4.40032981859977e-05,
"loss": 2.1306,
"step": 96000
},
{
"epoch": 4.82,
"learning_rate": 4.3972065364049776e-05,
"loss": 2.1302,
"step": 96500
},
{
"epoch": 4.85,
"learning_rate": 4.3940832542101844e-05,
"loss": 2.1323,
"step": 97000
},
{
"epoch": 4.87,
"learning_rate": 4.390959972015392e-05,
"loss": 2.1289,
"step": 97500
},
{
"epoch": 4.9,
"learning_rate": 4.387836689820599e-05,
"loss": 2.1307,
"step": 98000
},
{
"epoch": 4.92,
"learning_rate": 4.384713407625806e-05,
"loss": 2.1293,
"step": 98500
},
{
"epoch": 4.95,
"learning_rate": 4.3815901254310134e-05,
"loss": 2.1281,
"step": 99000
},
{
"epoch": 4.97,
"learning_rate": 4.37846684323622e-05,
"loss": 2.1276,
"step": 99500
},
{
"epoch": 5.0,
"learning_rate": 4.3753435610414276e-05,
"loss": 2.1126,
"step": 100000
},
{
"epoch": 5.0,
"eval_loss": 2.054161310195923,
"eval_runtime": 80.7428,
"eval_samples_per_second": 524.381,
"eval_steps_per_second": 65.554,
"step": 100055
},
{
"epoch": 5.02,
"learning_rate": 4.372220278846634e-05,
"loss": 2.1102,
"step": 100500
},
{
"epoch": 5.05,
"learning_rate": 4.369096996651842e-05,
"loss": 2.1058,
"step": 101000
},
{
"epoch": 5.07,
"learning_rate": 4.365973714457049e-05,
"loss": 2.1111,
"step": 101500
},
{
"epoch": 5.1,
"learning_rate": 4.362850432262256e-05,
"loss": 2.1108,
"step": 102000
},
{
"epoch": 5.12,
"learning_rate": 4.3597271500674633e-05,
"loss": 2.1042,
"step": 102500
},
{
"epoch": 5.15,
"learning_rate": 4.35660386787267e-05,
"loss": 2.1036,
"step": 103000
},
{
"epoch": 5.17,
"learning_rate": 4.3534805856778775e-05,
"loss": 2.1062,
"step": 103500
},
{
"epoch": 5.2,
"learning_rate": 4.350357303483085e-05,
"loss": 2.1054,
"step": 104000
},
{
"epoch": 5.22,
"learning_rate": 4.347234021288292e-05,
"loss": 2.0862,
"step": 104500
},
{
"epoch": 5.25,
"learning_rate": 4.3441107390934984e-05,
"loss": 2.1023,
"step": 105000
},
{
"epoch": 5.27,
"learning_rate": 4.340987456898706e-05,
"loss": 2.0947,
"step": 105500
},
{
"epoch": 5.3,
"learning_rate": 4.3378641747039126e-05,
"loss": 2.0999,
"step": 106000
},
{
"epoch": 5.32,
"learning_rate": 4.334740892509121e-05,
"loss": 2.0983,
"step": 106500
},
{
"epoch": 5.35,
"learning_rate": 4.3316176103143275e-05,
"loss": 2.0936,
"step": 107000
},
{
"epoch": 5.37,
"learning_rate": 4.328494328119534e-05,
"loss": 2.0904,
"step": 107500
},
{
"epoch": 5.4,
"learning_rate": 4.3253710459247416e-05,
"loss": 2.0965,
"step": 108000
},
{
"epoch": 5.42,
"learning_rate": 4.3222477637299484e-05,
"loss": 2.0892,
"step": 108500
},
{
"epoch": 5.45,
"learning_rate": 4.3191244815351565e-05,
"loss": 2.0854,
"step": 109000
},
{
"epoch": 5.47,
"learning_rate": 4.316001199340363e-05,
"loss": 2.0853,
"step": 109500
},
{
"epoch": 5.5,
"learning_rate": 4.31287791714557e-05,
"loss": 2.0842,
"step": 110000
},
{
"epoch": 5.52,
"learning_rate": 4.3097546349507774e-05,
"loss": 2.0806,
"step": 110500
},
{
"epoch": 5.55,
"learning_rate": 4.306631352755984e-05,
"loss": 2.08,
"step": 111000
},
{
"epoch": 5.57,
"learning_rate": 4.3035080705611916e-05,
"loss": 2.074,
"step": 111500
},
{
"epoch": 5.6,
"learning_rate": 4.300384788366399e-05,
"loss": 2.0752,
"step": 112000
},
{
"epoch": 5.62,
"learning_rate": 4.297261506171606e-05,
"loss": 2.0758,
"step": 112500
},
{
"epoch": 5.65,
"learning_rate": 4.294138223976813e-05,
"loss": 2.0762,
"step": 113000
},
{
"epoch": 5.67,
"learning_rate": 4.29101494178202e-05,
"loss": 2.0746,
"step": 113500
},
{
"epoch": 5.7,
"learning_rate": 4.2878916595872273e-05,
"loss": 2.0662,
"step": 114000
},
{
"epoch": 5.72,
"learning_rate": 4.284768377392435e-05,
"loss": 2.0711,
"step": 114500
},
{
"epoch": 5.75,
"learning_rate": 4.2816450951976415e-05,
"loss": 2.0651,
"step": 115000
},
{
"epoch": 5.77,
"learning_rate": 4.278521813002849e-05,
"loss": 2.0638,
"step": 115500
},
{
"epoch": 5.8,
"learning_rate": 4.275398530808056e-05,
"loss": 2.0657,
"step": 116000
},
{
"epoch": 5.82,
"learning_rate": 4.272275248613263e-05,
"loss": 2.0639,
"step": 116500
},
{
"epoch": 5.85,
"learning_rate": 4.26915196641847e-05,
"loss": 2.057,
"step": 117000
},
{
"epoch": 5.87,
"learning_rate": 4.266028684223677e-05,
"loss": 2.0578,
"step": 117500
},
{
"epoch": 5.9,
"learning_rate": 4.262905402028885e-05,
"loss": 2.053,
"step": 118000
},
{
"epoch": 5.92,
"learning_rate": 4.2597821198340915e-05,
"loss": 2.0597,
"step": 118500
},
{
"epoch": 5.95,
"learning_rate": 4.256658837639298e-05,
"loss": 2.0525,
"step": 119000
},
{
"epoch": 5.97,
"learning_rate": 4.2535355554445056e-05,
"loss": 2.0499,
"step": 119500
},
{
"epoch": 6.0,
"learning_rate": 4.250412273249713e-05,
"loss": 2.0472,
"step": 120000
},
{
"epoch": 6.0,
"eval_loss": 1.9931981563568115,
"eval_runtime": 81.0207,
"eval_samples_per_second": 522.582,
"eval_steps_per_second": 65.329,
"step": 120066
},
{
"epoch": 6.02,
"learning_rate": 4.2472889910549205e-05,
"loss": 2.0484,
"step": 120500
},
{
"epoch": 6.05,
"learning_rate": 4.244165708860127e-05,
"loss": 2.0476,
"step": 121000
},
{
"epoch": 6.07,
"learning_rate": 4.241042426665334e-05,
"loss": 2.0426,
"step": 121500
},
{
"epoch": 6.1,
"learning_rate": 4.2379191444705414e-05,
"loss": 2.0414,
"step": 122000
},
{
"epoch": 6.12,
"learning_rate": 4.234795862275748e-05,
"loss": 2.0393,
"step": 122500
},
{
"epoch": 6.15,
"learning_rate": 4.231672580080956e-05,
"loss": 2.0369,
"step": 123000
},
{
"epoch": 6.17,
"learning_rate": 4.228549297886163e-05,
"loss": 2.0427,
"step": 123500
},
{
"epoch": 6.2,
"learning_rate": 4.22542601569137e-05,
"loss": 2.0384,
"step": 124000
},
{
"epoch": 6.22,
"learning_rate": 4.222302733496577e-05,
"loss": 2.0362,
"step": 124500
},
{
"epoch": 6.25,
"learning_rate": 4.219179451301784e-05,
"loss": 2.0375,
"step": 125000
},
{
"epoch": 6.27,
"learning_rate": 4.216056169106991e-05,
"loss": 2.0337,
"step": 125500
},
{
"epoch": 6.3,
"learning_rate": 4.212932886912199e-05,
"loss": 2.0287,
"step": 126000
},
{
"epoch": 6.32,
"learning_rate": 4.2098096047174055e-05,
"loss": 2.0292,
"step": 126500
},
{
"epoch": 6.35,
"learning_rate": 4.206686322522613e-05,
"loss": 2.0295,
"step": 127000
},
{
"epoch": 6.37,
"learning_rate": 4.20356304032782e-05,
"loss": 2.0283,
"step": 127500
},
{
"epoch": 6.4,
"learning_rate": 4.200439758133027e-05,
"loss": 2.026,
"step": 128000
},
{
"epoch": 6.42,
"learning_rate": 4.1973164759382345e-05,
"loss": 2.0261,
"step": 128500
},
{
"epoch": 6.45,
"learning_rate": 4.194193193743441e-05,
"loss": 2.029,
"step": 129000
},
{
"epoch": 6.47,
"learning_rate": 4.191069911548649e-05,
"loss": 2.0272,
"step": 129500
},
{
"epoch": 6.5,
"learning_rate": 4.1879466293538554e-05,
"loss": 2.0237,
"step": 130000
},
{
"epoch": 6.52,
"learning_rate": 4.184823347159063e-05,
"loss": 2.0217,
"step": 130500
},
{
"epoch": 6.55,
"learning_rate": 4.1817000649642696e-05,
"loss": 2.0251,
"step": 131000
},
{
"epoch": 6.57,
"learning_rate": 4.178576782769477e-05,
"loss": 2.0214,
"step": 131500
},
{
"epoch": 6.6,
"learning_rate": 4.1754535005746845e-05,
"loss": 2.0149,
"step": 132000
},
{
"epoch": 6.62,
"learning_rate": 4.172330218379891e-05,
"loss": 2.0144,
"step": 132500
},
{
"epoch": 6.65,
"learning_rate": 4.169206936185098e-05,
"loss": 2.0159,
"step": 133000
},
{
"epoch": 6.67,
"learning_rate": 4.1660836539903054e-05,
"loss": 2.0138,
"step": 133500
},
{
"epoch": 6.7,
"learning_rate": 4.162960371795513e-05,
"loss": 2.0109,
"step": 134000
},
{
"epoch": 6.72,
"learning_rate": 4.15983708960072e-05,
"loss": 2.0186,
"step": 134500
},
{
"epoch": 6.75,
"learning_rate": 4.156713807405927e-05,
"loss": 2.0163,
"step": 135000
},
{
"epoch": 6.77,
"learning_rate": 4.153590525211134e-05,
"loss": 2.0064,
"step": 135500
},
{
"epoch": 6.8,
"learning_rate": 4.150467243016341e-05,
"loss": 2.0061,
"step": 136000
},
{
"epoch": 6.82,
"learning_rate": 4.147343960821548e-05,
"loss": 2.0079,
"step": 136500
},
{
"epoch": 6.85,
"learning_rate": 4.144220678626756e-05,
"loss": 2.0035,
"step": 137000
},
{
"epoch": 6.87,
"learning_rate": 4.141097396431963e-05,
"loss": 2.0046,
"step": 137500
},
{
"epoch": 6.9,
"learning_rate": 4.1379741142371695e-05,
"loss": 1.9988,
"step": 138000
},
{
"epoch": 6.92,
"learning_rate": 4.134850832042377e-05,
"loss": 2.0018,
"step": 138500
},
{
"epoch": 6.95,
"learning_rate": 4.131727549847584e-05,
"loss": 1.9995,
"step": 139000
},
{
"epoch": 6.97,
"learning_rate": 4.128604267652791e-05,
"loss": 2.0006,
"step": 139500
},
{
"epoch": 7.0,
"learning_rate": 4.1254809854579985e-05,
"loss": 2.007,
"step": 140000
},
{
"epoch": 7.0,
"eval_loss": 1.9391331672668457,
"eval_runtime": 80.9026,
"eval_samples_per_second": 523.345,
"eval_steps_per_second": 65.424,
"step": 140077
},
{
"epoch": 7.02,
"learning_rate": 4.122357703263205e-05,
"loss": 1.993,
"step": 140500
},
{
"epoch": 7.05,
"learning_rate": 4.119234421068413e-05,
"loss": 1.9912,
"step": 141000
},
{
"epoch": 7.07,
"learning_rate": 4.1161111388736194e-05,
"loss": 1.994,
"step": 141500
},
{
"epoch": 7.1,
"learning_rate": 4.112987856678827e-05,
"loss": 1.9908,
"step": 142000
},
{
"epoch": 7.12,
"learning_rate": 4.109864574484034e-05,
"loss": 1.9887,
"step": 142500
},
{
"epoch": 7.15,
"learning_rate": 4.106741292289241e-05,
"loss": 1.9912,
"step": 143000
},
{
"epoch": 7.17,
"learning_rate": 4.1036180100944485e-05,
"loss": 1.9827,
"step": 143500
},
{
"epoch": 7.2,
"learning_rate": 4.100494727899655e-05,
"loss": 1.9854,
"step": 144000
},
{
"epoch": 7.22,
"learning_rate": 4.0973714457048626e-05,
"loss": 1.9858,
"step": 144500
},
{
"epoch": 7.25,
"learning_rate": 4.09424816351007e-05,
"loss": 1.9852,
"step": 145000
},
{
"epoch": 7.27,
"learning_rate": 4.091124881315277e-05,
"loss": 1.9845,
"step": 145500
},
{
"epoch": 7.3,
"learning_rate": 4.088001599120484e-05,
"loss": 1.9786,
"step": 146000
},
{
"epoch": 7.32,
"learning_rate": 4.084878316925691e-05,
"loss": 1.9811,
"step": 146500
},
{
"epoch": 7.35,
"learning_rate": 4.081755034730898e-05,
"loss": 1.9806,
"step": 147000
},
{
"epoch": 7.37,
"learning_rate": 4.078631752536105e-05,
"loss": 1.9802,
"step": 147500
},
{
"epoch": 7.4,
"learning_rate": 4.0755084703413126e-05,
"loss": 1.9769,
"step": 148000
},
{
"epoch": 7.42,
"learning_rate": 4.07238518814652e-05,
"loss": 1.9736,
"step": 148500
},
{
"epoch": 7.45,
"learning_rate": 4.069261905951727e-05,
"loss": 1.9771,
"step": 149000
},
{
"epoch": 7.47,
"learning_rate": 4.0661386237569335e-05,
"loss": 1.9703,
"step": 149500
},
{
"epoch": 7.5,
"learning_rate": 4.063015341562141e-05,
"loss": 1.9692,
"step": 150000
},
{
"epoch": 7.52,
"learning_rate": 4.059892059367348e-05,
"loss": 1.9723,
"step": 150500
},
{
"epoch": 7.55,
"learning_rate": 4.056768777172556e-05,
"loss": 1.9718,
"step": 151000
},
{
"epoch": 7.57,
"learning_rate": 4.0536454949777625e-05,
"loss": 1.9738,
"step": 151500
},
{
"epoch": 7.6,
"learning_rate": 4.050522212782969e-05,
"loss": 1.9748,
"step": 152000
},
{
"epoch": 7.62,
"learning_rate": 4.047398930588177e-05,
"loss": 1.975,
"step": 152500
},
{
"epoch": 7.65,
"learning_rate": 4.0442756483933834e-05,
"loss": 1.9751,
"step": 153000
},
{
"epoch": 7.67,
"learning_rate": 4.041152366198591e-05,
"loss": 1.9693,
"step": 153500
},
{
"epoch": 7.7,
"learning_rate": 4.038029084003798e-05,
"loss": 1.9749,
"step": 154000
},
{
"epoch": 7.72,
"learning_rate": 4.034905801809005e-05,
"loss": 1.9679,
"step": 154500
},
{
"epoch": 7.75,
"learning_rate": 4.0317825196142124e-05,
"loss": 1.9679,
"step": 155000
},
{
"epoch": 7.77,
"learning_rate": 4.028659237419419e-05,
"loss": 1.9666,
"step": 155500
},
{
"epoch": 7.8,
"learning_rate": 4.0255359552246266e-05,
"loss": 1.9615,
"step": 156000
},
{
"epoch": 7.82,
"learning_rate": 4.022412673029834e-05,
"loss": 1.9598,
"step": 156500
},
{
"epoch": 7.85,
"learning_rate": 4.019289390835041e-05,
"loss": 1.9633,
"step": 157000
},
{
"epoch": 7.87,
"learning_rate": 4.016166108640248e-05,
"loss": 1.9622,
"step": 157500
},
{
"epoch": 7.9,
"learning_rate": 4.013042826445455e-05,
"loss": 1.9594,
"step": 158000
},
{
"epoch": 7.92,
"learning_rate": 4.0099195442506624e-05,
"loss": 1.955,
"step": 158500
},
{
"epoch": 7.95,
"learning_rate": 4.00679626205587e-05,
"loss": 1.9573,
"step": 159000
},
{
"epoch": 7.97,
"learning_rate": 4.0036729798610766e-05,
"loss": 1.966,
"step": 159500
},
{
"epoch": 8.0,
"learning_rate": 4.000549697666284e-05,
"loss": 1.9487,
"step": 160000
},
{
"epoch": 8.0,
"eval_loss": 1.9000049829483032,
"eval_runtime": 80.8787,
"eval_samples_per_second": 523.5,
"eval_steps_per_second": 65.444,
"step": 160088
},
{
"epoch": 8.02,
"learning_rate": 3.997426415471491e-05,
"loss": 1.9467,
"step": 160500
},
{
"epoch": 8.05,
"learning_rate": 3.9943031332766975e-05,
"loss": 1.9428,
"step": 161000
},
{
"epoch": 8.07,
"learning_rate": 3.9911798510819056e-05,
"loss": 1.9556,
"step": 161500
},
{
"epoch": 8.1,
"learning_rate": 3.988056568887112e-05,
"loss": 1.9495,
"step": 162000
},
{
"epoch": 8.12,
"learning_rate": 3.98493328669232e-05,
"loss": 1.9486,
"step": 162500
},
{
"epoch": 8.15,
"learning_rate": 3.9818100044975265e-05,
"loss": 1.9417,
"step": 163000
},
{
"epoch": 8.17,
"learning_rate": 3.978686722302733e-05,
"loss": 1.9427,
"step": 163500
},
{
"epoch": 8.2,
"learning_rate": 3.975563440107941e-05,
"loss": 1.9379,
"step": 164000
},
{
"epoch": 8.22,
"learning_rate": 3.972440157913148e-05,
"loss": 1.944,
"step": 164500
},
{
"epoch": 8.25,
"learning_rate": 3.9693168757183555e-05,
"loss": 1.9406,
"step": 165000
},
{
"epoch": 8.27,
"learning_rate": 3.966193593523562e-05,
"loss": 1.9441,
"step": 165500
},
{
"epoch": 8.3,
"learning_rate": 3.963070311328769e-05,
"loss": 1.9488,
"step": 166000
},
{
"epoch": 8.32,
"learning_rate": 3.9599470291339764e-05,
"loss": 1.9393,
"step": 166500
},
{
"epoch": 8.35,
"learning_rate": 3.956823746939184e-05,
"loss": 1.9394,
"step": 167000
},
{
"epoch": 8.37,
"learning_rate": 3.9537004647443906e-05,
"loss": 1.939,
"step": 167500
},
{
"epoch": 8.4,
"learning_rate": 3.950577182549598e-05,
"loss": 1.936,
"step": 168000
},
{
"epoch": 8.42,
"learning_rate": 3.947453900354805e-05,
"loss": 1.9403,
"step": 168500
},
{
"epoch": 8.45,
"learning_rate": 3.944330618160012e-05,
"loss": 1.9352,
"step": 169000
},
{
"epoch": 8.47,
"learning_rate": 3.941207335965219e-05,
"loss": 1.9368,
"step": 169500
},
{
"epoch": 8.5,
"learning_rate": 3.9380840537704264e-05,
"loss": 1.9376,
"step": 170000
},
{
"epoch": 8.52,
"learning_rate": 3.934960771575634e-05,
"loss": 1.9346,
"step": 170500
},
{
"epoch": 8.55,
"learning_rate": 3.9318374893808406e-05,
"loss": 1.9382,
"step": 171000
},
{
"epoch": 8.57,
"learning_rate": 3.928714207186048e-05,
"loss": 1.938,
"step": 171500
},
{
"epoch": 8.6,
"learning_rate": 3.925590924991255e-05,
"loss": 1.93,
"step": 172000
},
{
"epoch": 8.62,
"learning_rate": 3.922467642796462e-05,
"loss": 1.9283,
"step": 172500
},
{
"epoch": 8.65,
"learning_rate": 3.9193443606016696e-05,
"loss": 1.9218,
"step": 173000
},
{
"epoch": 8.67,
"learning_rate": 3.916221078406876e-05,
"loss": 1.931,
"step": 173500
},
{
"epoch": 8.7,
"learning_rate": 3.913097796212084e-05,
"loss": 1.9309,
"step": 174000
},
{
"epoch": 8.72,
"learning_rate": 3.9099745140172905e-05,
"loss": 1.9296,
"step": 174500
},
{
"epoch": 8.75,
"learning_rate": 3.906851231822497e-05,
"loss": 1.924,
"step": 175000
},
{
"epoch": 8.77,
"learning_rate": 3.9037279496277053e-05,
"loss": 1.9327,
"step": 175500
},
{
"epoch": 8.8,
"learning_rate": 3.900604667432912e-05,
"loss": 1.9197,
"step": 176000
},
{
"epoch": 8.82,
"learning_rate": 3.8974813852381195e-05,
"loss": 1.9193,
"step": 176500
},
{
"epoch": 8.85,
"learning_rate": 3.894358103043326e-05,
"loss": 1.9206,
"step": 177000
},
{
"epoch": 8.87,
"learning_rate": 3.891234820848533e-05,
"loss": 1.9216,
"step": 177500
},
{
"epoch": 8.9,
"learning_rate": 3.888111538653741e-05,
"loss": 1.9188,
"step": 178000
},
{
"epoch": 8.92,
"learning_rate": 3.884988256458948e-05,
"loss": 1.9221,
"step": 178500
},
{
"epoch": 8.95,
"learning_rate": 3.881864974264155e-05,
"loss": 1.9206,
"step": 179000
},
{
"epoch": 8.97,
"learning_rate": 3.878741692069362e-05,
"loss": 1.9242,
"step": 179500
},
{
"epoch": 9.0,
"learning_rate": 3.875618409874569e-05,
"loss": 1.9257,
"step": 180000
},
{
"epoch": 9.0,
"eval_loss": 1.864593505859375,
"eval_runtime": 80.895,
"eval_samples_per_second": 523.395,
"eval_steps_per_second": 65.431,
"step": 180099
},
{
"epoch": 9.02,
"learning_rate": 3.872495127679776e-05,
"loss": 1.9161,
"step": 180500
},
{
"epoch": 9.05,
"learning_rate": 3.8693718454849836e-05,
"loss": 1.9163,
"step": 181000
},
{
"epoch": 9.07,
"learning_rate": 3.8662485632901904e-05,
"loss": 1.914,
"step": 181500
},
{
"epoch": 9.09,
"learning_rate": 3.863125281095398e-05,
"loss": 1.9116,
"step": 182000
},
{
"epoch": 9.12,
"learning_rate": 3.8600019989006045e-05,
"loss": 1.909,
"step": 182500
},
{
"epoch": 9.14,
"learning_rate": 3.856878716705812e-05,
"loss": 1.9148,
"step": 183000
},
{
"epoch": 9.17,
"learning_rate": 3.8537554345110194e-05,
"loss": 1.9078,
"step": 183500
},
{
"epoch": 9.19,
"learning_rate": 3.850632152316226e-05,
"loss": 1.9113,
"step": 184000
},
{
"epoch": 9.22,
"learning_rate": 3.8475088701214336e-05,
"loss": 1.9089,
"step": 184500
},
{
"epoch": 9.24,
"learning_rate": 3.84438558792664e-05,
"loss": 1.908,
"step": 185000
},
{
"epoch": 9.27,
"learning_rate": 3.841262305731848e-05,
"loss": 1.9118,
"step": 185500
},
{
"epoch": 9.29,
"learning_rate": 3.8381390235370545e-05,
"loss": 1.901,
"step": 186000
},
{
"epoch": 9.32,
"learning_rate": 3.835015741342262e-05,
"loss": 1.9031,
"step": 186500
},
{
"epoch": 9.34,
"learning_rate": 3.831892459147469e-05,
"loss": 1.9069,
"step": 187000
},
{
"epoch": 9.37,
"learning_rate": 3.828769176952676e-05,
"loss": 1.9037,
"step": 187500
},
{
"epoch": 9.39,
"learning_rate": 3.8256458947578835e-05,
"loss": 1.8997,
"step": 188000
},
{
"epoch": 9.42,
"learning_rate": 3.82252261256309e-05,
"loss": 1.9024,
"step": 188500
},
{
"epoch": 9.44,
"learning_rate": 3.819399330368298e-05,
"loss": 1.9035,
"step": 189000
},
{
"epoch": 9.47,
"learning_rate": 3.816276048173505e-05,
"loss": 1.9035,
"step": 189500
},
{
"epoch": 9.49,
"learning_rate": 3.813152765978712e-05,
"loss": 1.9011,
"step": 190000
},
{
"epoch": 9.52,
"learning_rate": 3.810029483783919e-05,
"loss": 1.9071,
"step": 190500
},
{
"epoch": 9.54,
"learning_rate": 3.806906201589126e-05,
"loss": 1.9032,
"step": 191000
},
{
"epoch": 9.57,
"learning_rate": 3.803782919394333e-05,
"loss": 1.8986,
"step": 191500
},
{
"epoch": 9.59,
"learning_rate": 3.800659637199541e-05,
"loss": 1.8996,
"step": 192000
},
{
"epoch": 9.62,
"learning_rate": 3.7975363550047476e-05,
"loss": 1.8963,
"step": 192500
},
{
"epoch": 9.64,
"learning_rate": 3.794413072809955e-05,
"loss": 1.8981,
"step": 193000
},
{
"epoch": 9.67,
"learning_rate": 3.791289790615162e-05,
"loss": 1.9042,
"step": 193500
},
{
"epoch": 9.69,
"learning_rate": 3.7881665084203685e-05,
"loss": 1.8958,
"step": 194000
},
{
"epoch": 9.72,
"learning_rate": 3.7850432262255766e-05,
"loss": 1.8975,
"step": 194500
},
{
"epoch": 9.74,
"learning_rate": 3.7819199440307834e-05,
"loss": 1.8925,
"step": 195000
},
{
"epoch": 9.77,
"learning_rate": 3.77879666183599e-05,
"loss": 1.8883,
"step": 195500
},
{
"epoch": 9.79,
"learning_rate": 3.7756733796411976e-05,
"loss": 1.9021,
"step": 196000
},
{
"epoch": 9.82,
"learning_rate": 3.772550097446404e-05,
"loss": 1.9004,
"step": 196500
},
{
"epoch": 9.84,
"learning_rate": 3.769426815251612e-05,
"loss": 1.8899,
"step": 197000
},
{
"epoch": 9.87,
"learning_rate": 3.766303533056819e-05,
"loss": 1.8924,
"step": 197500
},
{
"epoch": 9.89,
"learning_rate": 3.763180250862026e-05,
"loss": 1.8888,
"step": 198000
},
{
"epoch": 9.92,
"learning_rate": 3.760056968667233e-05,
"loss": 1.8918,
"step": 198500
},
{
"epoch": 9.94,
"learning_rate": 3.75693368647244e-05,
"loss": 1.8857,
"step": 199000
},
{
"epoch": 9.97,
"learning_rate": 3.7538104042776475e-05,
"loss": 1.884,
"step": 199500
},
{
"epoch": 9.99,
"learning_rate": 3.750687122082855e-05,
"loss": 1.8952,
"step": 200000
},
{
"epoch": 10.0,
"eval_loss": 1.834604024887085,
"eval_runtime": 80.8164,
"eval_samples_per_second": 523.904,
"eval_steps_per_second": 65.494,
"step": 200110
},
{
"epoch": 10.02,
"learning_rate": 3.747563839888062e-05,
"loss": 1.8863,
"step": 200500
},
{
"epoch": 10.04,
"learning_rate": 3.744440557693269e-05,
"loss": 1.8832,
"step": 201000
},
{
"epoch": 10.07,
"learning_rate": 3.741317275498476e-05,
"loss": 1.8871,
"step": 201500
},
{
"epoch": 10.09,
"learning_rate": 3.738193993303683e-05,
"loss": 1.8874,
"step": 202000
},
{
"epoch": 10.12,
"learning_rate": 3.73507071110889e-05,
"loss": 1.8756,
"step": 202500
},
{
"epoch": 10.14,
"learning_rate": 3.7319474289140974e-05,
"loss": 1.8853,
"step": 203000
},
{
"epoch": 10.17,
"learning_rate": 3.728824146719305e-05,
"loss": 1.8779,
"step": 203500
},
{
"epoch": 10.19,
"learning_rate": 3.7257008645245116e-05,
"loss": 1.8808,
"step": 204000
},
{
"epoch": 10.22,
"learning_rate": 3.722577582329719e-05,
"loss": 1.8776,
"step": 204500
},
{
"epoch": 10.24,
"learning_rate": 3.719454300134926e-05,
"loss": 1.8773,
"step": 205000
},
{
"epoch": 10.27,
"learning_rate": 3.7163310179401325e-05,
"loss": 1.878,
"step": 205500
},
{
"epoch": 10.29,
"learning_rate": 3.7132077357453406e-05,
"loss": 1.8763,
"step": 206000
},
{
"epoch": 10.32,
"learning_rate": 3.7100844535505474e-05,
"loss": 1.8795,
"step": 206500
},
{
"epoch": 10.34,
"learning_rate": 3.706961171355755e-05,
"loss": 1.8709,
"step": 207000
},
{
"epoch": 10.37,
"learning_rate": 3.7038378891609615e-05,
"loss": 1.8771,
"step": 207500
},
{
"epoch": 10.39,
"learning_rate": 3.700714606966168e-05,
"loss": 1.871,
"step": 208000
},
{
"epoch": 10.42,
"learning_rate": 3.6975913247713764e-05,
"loss": 1.8733,
"step": 208500
},
{
"epoch": 10.44,
"learning_rate": 3.694468042576583e-05,
"loss": 1.8719,
"step": 209000
},
{
"epoch": 10.47,
"learning_rate": 3.69134476038179e-05,
"loss": 1.8728,
"step": 209500
},
{
"epoch": 10.49,
"learning_rate": 3.688221478186997e-05,
"loss": 1.8712,
"step": 210000
},
{
"epoch": 10.52,
"learning_rate": 3.685098195992204e-05,
"loss": 1.8698,
"step": 210500
},
{
"epoch": 10.54,
"learning_rate": 3.6819749137974115e-05,
"loss": 1.8762,
"step": 211000
},
{
"epoch": 10.57,
"learning_rate": 3.678851631602619e-05,
"loss": 1.8686,
"step": 211500
},
{
"epoch": 10.59,
"learning_rate": 3.6757283494078257e-05,
"loss": 1.8684,
"step": 212000
},
{
"epoch": 10.62,
"learning_rate": 3.672605067213033e-05,
"loss": 1.8663,
"step": 212500
},
{
"epoch": 10.64,
"learning_rate": 3.66948178501824e-05,
"loss": 1.8685,
"step": 213000
},
{
"epoch": 10.67,
"learning_rate": 3.666358502823447e-05,
"loss": 1.8676,
"step": 213500
},
{
"epoch": 10.69,
"learning_rate": 3.663235220628655e-05,
"loss": 1.8718,
"step": 214000
},
{
"epoch": 10.72,
"learning_rate": 3.6601119384338614e-05,
"loss": 1.8626,
"step": 214500
},
{
"epoch": 10.74,
"learning_rate": 3.656988656239069e-05,
"loss": 1.8601,
"step": 215000
},
{
"epoch": 10.77,
"learning_rate": 3.6538653740442756e-05,
"loss": 1.8629,
"step": 215500
},
{
"epoch": 10.79,
"learning_rate": 3.650742091849483e-05,
"loss": 1.8628,
"step": 216000
},
{
"epoch": 10.82,
"learning_rate": 3.64761880965469e-05,
"loss": 1.8661,
"step": 216500
},
{
"epoch": 10.84,
"learning_rate": 3.644495527459897e-05,
"loss": 1.8627,
"step": 217000
},
{
"epoch": 10.87,
"learning_rate": 3.6413722452651046e-05,
"loss": 1.8651,
"step": 217500
},
{
"epoch": 10.89,
"learning_rate": 3.6382489630703114e-05,
"loss": 1.8676,
"step": 218000
},
{
"epoch": 10.92,
"learning_rate": 3.635125680875519e-05,
"loss": 1.8604,
"step": 218500
},
{
"epoch": 10.94,
"learning_rate": 3.6320023986807255e-05,
"loss": 1.8631,
"step": 219000
},
{
"epoch": 10.97,
"learning_rate": 3.628879116485933e-05,
"loss": 1.8636,
"step": 219500
},
{
"epoch": 10.99,
"learning_rate": 3.6257558342911404e-05,
"loss": 1.8591,
"step": 220000
},
{
"epoch": 11.0,
"eval_loss": 1.805991530418396,
"eval_runtime": 80.9106,
"eval_samples_per_second": 523.293,
"eval_steps_per_second": 65.418,
"step": 220121
},
{
"epoch": 11.02,
"learning_rate": 3.622632552096347e-05,
"loss": 1.8554,
"step": 220500
},
{
"epoch": 11.04,
"learning_rate": 3.6195092699015546e-05,
"loss": 1.8545,
"step": 221000
},
{
"epoch": 11.07,
"learning_rate": 3.616385987706761e-05,
"loss": 1.8444,
"step": 221500
},
{
"epoch": 11.09,
"learning_rate": 3.613262705511968e-05,
"loss": 1.8531,
"step": 222000
},
{
"epoch": 11.12,
"learning_rate": 3.610139423317176e-05,
"loss": 1.852,
"step": 222500
},
{
"epoch": 11.14,
"learning_rate": 3.607016141122383e-05,
"loss": 1.8545,
"step": 223000
},
{
"epoch": 11.17,
"learning_rate": 3.6038928589275896e-05,
"loss": 1.8514,
"step": 223500
},
{
"epoch": 11.19,
"learning_rate": 3.600769576732797e-05,
"loss": 1.8446,
"step": 224000
},
{
"epoch": 11.22,
"learning_rate": 3.597646294538004e-05,
"loss": 1.8502,
"step": 224500
},
{
"epoch": 11.24,
"learning_rate": 3.594523012343212e-05,
"loss": 1.8509,
"step": 225000
},
{
"epoch": 11.27,
"learning_rate": 3.591399730148419e-05,
"loss": 1.8524,
"step": 225500
},
{
"epoch": 11.29,
"learning_rate": 3.5882764479536254e-05,
"loss": 1.853,
"step": 226000
},
{
"epoch": 11.32,
"learning_rate": 3.585153165758833e-05,
"loss": 1.8523,
"step": 226500
},
{
"epoch": 11.34,
"learning_rate": 3.5820298835640396e-05,
"loss": 1.8522,
"step": 227000
},
{
"epoch": 11.37,
"learning_rate": 3.578906601369247e-05,
"loss": 1.8485,
"step": 227500
},
{
"epoch": 11.39,
"learning_rate": 3.5757833191744544e-05,
"loss": 1.8477,
"step": 228000
},
{
"epoch": 11.42,
"learning_rate": 3.572660036979661e-05,
"loss": 1.8465,
"step": 228500
},
{
"epoch": 11.44,
"learning_rate": 3.5695367547848686e-05,
"loss": 1.8521,
"step": 229000
},
{
"epoch": 11.47,
"learning_rate": 3.5664134725900754e-05,
"loss": 1.8491,
"step": 229500
},
{
"epoch": 11.49,
"learning_rate": 3.563290190395283e-05,
"loss": 1.8514,
"step": 230000
},
{
"epoch": 11.52,
"learning_rate": 3.56016690820049e-05,
"loss": 1.8497,
"step": 230500
},
{
"epoch": 11.54,
"learning_rate": 3.557043626005697e-05,
"loss": 1.8525,
"step": 231000
},
{
"epoch": 11.57,
"learning_rate": 3.5539203438109044e-05,
"loss": 1.8456,
"step": 231500
},
{
"epoch": 11.59,
"learning_rate": 3.550797061616111e-05,
"loss": 1.8493,
"step": 232000
},
{
"epoch": 11.62,
"learning_rate": 3.5476737794213186e-05,
"loss": 1.8425,
"step": 232500
},
{
"epoch": 11.64,
"learning_rate": 3.544550497226525e-05,
"loss": 1.8421,
"step": 233000
},
{
"epoch": 11.67,
"learning_rate": 3.541427215031733e-05,
"loss": 1.8499,
"step": 233500
},
{
"epoch": 11.69,
"learning_rate": 3.53830393283694e-05,
"loss": 1.8379,
"step": 234000
},
{
"epoch": 11.72,
"learning_rate": 3.535180650642147e-05,
"loss": 1.8443,
"step": 234500
},
{
"epoch": 11.74,
"learning_rate": 3.532057368447354e-05,
"loss": 1.8443,
"step": 235000
},
{
"epoch": 11.77,
"learning_rate": 3.528934086252561e-05,
"loss": 1.8472,
"step": 235500
},
{
"epoch": 11.79,
"learning_rate": 3.5258108040577685e-05,
"loss": 1.837,
"step": 236000
},
{
"epoch": 11.82,
"learning_rate": 3.522687521862976e-05,
"loss": 1.8415,
"step": 236500
},
{
"epoch": 11.84,
"learning_rate": 3.519564239668183e-05,
"loss": 1.8409,
"step": 237000
},
{
"epoch": 11.87,
"learning_rate": 3.51644095747339e-05,
"loss": 1.8314,
"step": 237500
},
{
"epoch": 11.89,
"learning_rate": 3.513317675278597e-05,
"loss": 1.8407,
"step": 238000
},
{
"epoch": 11.92,
"learning_rate": 3.5101943930838036e-05,
"loss": 1.8414,
"step": 238500
},
{
"epoch": 11.94,
"learning_rate": 3.507071110889012e-05,
"loss": 1.8354,
"step": 239000
},
{
"epoch": 11.97,
"learning_rate": 3.5039478286942184e-05,
"loss": 1.8368,
"step": 239500
},
{
"epoch": 11.99,
"learning_rate": 3.500824546499425e-05,
"loss": 1.839,
"step": 240000
},
{
"epoch": 12.0,
"eval_loss": 1.7868399620056152,
"eval_runtime": 80.9133,
"eval_samples_per_second": 523.276,
"eval_steps_per_second": 65.416,
"step": 240132
},
{
"epoch": 12.02,
"learning_rate": 3.4977012643046326e-05,
"loss": 1.8311,
"step": 240500
},
{
"epoch": 12.04,
"learning_rate": 3.4945779821098393e-05,
"loss": 1.8268,
"step": 241000
},
{
"epoch": 12.07,
"learning_rate": 3.4914546999150475e-05,
"loss": 1.8299,
"step": 241500
},
{
"epoch": 12.09,
"learning_rate": 3.488331417720254e-05,
"loss": 1.8362,
"step": 242000
},
{
"epoch": 12.12,
"learning_rate": 3.485208135525461e-05,
"loss": 1.8285,
"step": 242500
},
{
"epoch": 12.14,
"learning_rate": 3.4820848533306684e-05,
"loss": 1.8226,
"step": 243000
},
{
"epoch": 12.17,
"learning_rate": 3.478961571135875e-05,
"loss": 1.8222,
"step": 243500
},
{
"epoch": 12.19,
"learning_rate": 3.4758382889410825e-05,
"loss": 1.8248,
"step": 244000
},
{
"epoch": 12.22,
"learning_rate": 3.47271500674629e-05,
"loss": 1.8281,
"step": 244500
},
{
"epoch": 12.24,
"learning_rate": 3.469591724551497e-05,
"loss": 1.8299,
"step": 245000
},
{
"epoch": 12.27,
"learning_rate": 3.466468442356704e-05,
"loss": 1.8276,
"step": 245500
},
{
"epoch": 12.29,
"learning_rate": 3.463345160161911e-05,
"loss": 1.8324,
"step": 246000
},
{
"epoch": 12.32,
"learning_rate": 3.460221877967118e-05,
"loss": 1.8266,
"step": 246500
},
{
"epoch": 12.34,
"learning_rate": 3.457098595772326e-05,
"loss": 1.8242,
"step": 247000
},
{
"epoch": 12.37,
"learning_rate": 3.4539753135775325e-05,
"loss": 1.8211,
"step": 247500
},
{
"epoch": 12.39,
"learning_rate": 3.45085203138274e-05,
"loss": 1.8301,
"step": 248000
},
{
"epoch": 12.42,
"learning_rate": 3.4477287491879467e-05,
"loss": 1.8235,
"step": 248500
},
{
"epoch": 12.44,
"learning_rate": 3.444605466993154e-05,
"loss": 1.8281,
"step": 249000
},
{
"epoch": 12.47,
"learning_rate": 3.441482184798361e-05,
"loss": 1.826,
"step": 249500
},
{
"epoch": 12.49,
"learning_rate": 3.438358902603568e-05,
"loss": 1.8222,
"step": 250000
},
{
"epoch": 12.52,
"learning_rate": 3.435235620408776e-05,
"loss": 1.8162,
"step": 250500
},
{
"epoch": 12.54,
"learning_rate": 3.4321123382139824e-05,
"loss": 1.8247,
"step": 251000
},
{
"epoch": 12.57,
"learning_rate": 3.42898905601919e-05,
"loss": 1.8252,
"step": 251500
},
{
"epoch": 12.59,
"learning_rate": 3.4258657738243966e-05,
"loss": 1.8241,
"step": 252000
},
{
"epoch": 12.62,
"learning_rate": 3.422742491629604e-05,
"loss": 1.8261,
"step": 252500
},
{
"epoch": 12.64,
"learning_rate": 3.4196192094348114e-05,
"loss": 1.8208,
"step": 253000
},
{
"epoch": 12.67,
"learning_rate": 3.416495927240018e-05,
"loss": 1.8311,
"step": 253500
},
{
"epoch": 12.69,
"learning_rate": 3.413372645045225e-05,
"loss": 1.8198,
"step": 254000
},
{
"epoch": 12.72,
"learning_rate": 3.4102493628504324e-05,
"loss": 1.8178,
"step": 254500
},
{
"epoch": 12.74,
"learning_rate": 3.407126080655639e-05,
"loss": 1.8204,
"step": 255000
},
{
"epoch": 12.77,
"learning_rate": 3.404002798460847e-05,
"loss": 1.8191,
"step": 255500
},
{
"epoch": 12.79,
"learning_rate": 3.400879516266054e-05,
"loss": 1.8214,
"step": 256000
},
{
"epoch": 12.82,
"learning_rate": 3.397756234071261e-05,
"loss": 1.8196,
"step": 256500
},
{
"epoch": 12.84,
"learning_rate": 3.394632951876468e-05,
"loss": 1.8208,
"step": 257000
},
{
"epoch": 12.87,
"learning_rate": 3.391509669681675e-05,
"loss": 1.8118,
"step": 257500
},
{
"epoch": 12.89,
"learning_rate": 3.388386387486883e-05,
"loss": 1.8194,
"step": 258000
},
{
"epoch": 12.92,
"learning_rate": 3.38526310529209e-05,
"loss": 1.8087,
"step": 258500
},
{
"epoch": 12.94,
"learning_rate": 3.3821398230972965e-05,
"loss": 1.811,
"step": 259000
},
{
"epoch": 12.97,
"learning_rate": 3.379016540902504e-05,
"loss": 1.8126,
"step": 259500
},
{
"epoch": 12.99,
"learning_rate": 3.3758932587077106e-05,
"loss": 1.8125,
"step": 260000
},
{
"epoch": 13.0,
"eval_loss": 1.7630648612976074,
"eval_runtime": 80.8714,
"eval_samples_per_second": 523.547,
"eval_steps_per_second": 65.45,
"step": 260143
},
{
"epoch": 13.02,
"learning_rate": 3.372769976512918e-05,
"loss": 1.811,
"step": 260500
},
{
"epoch": 13.04,
"learning_rate": 3.3696466943181255e-05,
"loss": 1.8085,
"step": 261000
},
{
"epoch": 13.07,
"learning_rate": 3.366523412123332e-05,
"loss": 1.8081,
"step": 261500
},
{
"epoch": 13.09,
"learning_rate": 3.36340012992854e-05,
"loss": 1.8104,
"step": 262000
},
{
"epoch": 13.12,
"learning_rate": 3.3602768477337464e-05,
"loss": 1.808,
"step": 262500
},
{
"epoch": 13.14,
"learning_rate": 3.357153565538954e-05,
"loss": 1.8047,
"step": 263000
},
{
"epoch": 13.17,
"learning_rate": 3.354030283344161e-05,
"loss": 1.8046,
"step": 263500
},
{
"epoch": 13.19,
"learning_rate": 3.350907001149368e-05,
"loss": 1.8061,
"step": 264000
},
{
"epoch": 13.22,
"learning_rate": 3.3477837189545754e-05,
"loss": 1.8071,
"step": 264500
},
{
"epoch": 13.24,
"learning_rate": 3.344660436759782e-05,
"loss": 1.8171,
"step": 265000
},
{
"epoch": 13.27,
"learning_rate": 3.3415371545649896e-05,
"loss": 1.8055,
"step": 265500
},
{
"epoch": 13.29,
"learning_rate": 3.3384138723701964e-05,
"loss": 1.8065,
"step": 266000
},
{
"epoch": 13.32,
"learning_rate": 3.335290590175404e-05,
"loss": 1.8104,
"step": 266500
},
{
"epoch": 13.34,
"learning_rate": 3.332167307980611e-05,
"loss": 1.804,
"step": 267000
},
{
"epoch": 13.37,
"learning_rate": 3.329044025785818e-05,
"loss": 1.8022,
"step": 267500
},
{
"epoch": 13.39,
"learning_rate": 3.325920743591025e-05,
"loss": 1.8046,
"step": 268000
},
{
"epoch": 13.42,
"learning_rate": 3.322797461396232e-05,
"loss": 1.8017,
"step": 268500
},
{
"epoch": 13.44,
"learning_rate": 3.3196741792014395e-05,
"loss": 1.8119,
"step": 269000
},
{
"epoch": 13.47,
"learning_rate": 3.316550897006647e-05,
"loss": 1.8047,
"step": 269500
},
{
"epoch": 13.49,
"learning_rate": 3.313427614811854e-05,
"loss": 1.8013,
"step": 270000
},
{
"epoch": 13.52,
"learning_rate": 3.3103043326170605e-05,
"loss": 1.8063,
"step": 270500
},
{
"epoch": 13.54,
"learning_rate": 3.307181050422268e-05,
"loss": 1.7995,
"step": 271000
},
{
"epoch": 13.57,
"learning_rate": 3.3040577682274746e-05,
"loss": 1.8046,
"step": 271500
},
{
"epoch": 13.59,
"learning_rate": 3.300934486032683e-05,
"loss": 1.8081,
"step": 272000
},
{
"epoch": 13.62,
"learning_rate": 3.2978112038378895e-05,
"loss": 1.8051,
"step": 272500
},
{
"epoch": 13.64,
"learning_rate": 3.294687921643096e-05,
"loss": 1.8055,
"step": 273000
},
{
"epoch": 13.67,
"learning_rate": 3.2915646394483037e-05,
"loss": 1.8044,
"step": 273500
},
{
"epoch": 13.69,
"learning_rate": 3.2884413572535104e-05,
"loss": 1.8024,
"step": 274000
},
{
"epoch": 13.72,
"learning_rate": 3.285318075058718e-05,
"loss": 1.8019,
"step": 274500
},
{
"epoch": 13.74,
"learning_rate": 3.282194792863925e-05,
"loss": 1.8005,
"step": 275000
},
{
"epoch": 13.77,
"learning_rate": 3.279071510669132e-05,
"loss": 1.8033,
"step": 275500
},
{
"epoch": 13.79,
"learning_rate": 3.2759482284743394e-05,
"loss": 1.797,
"step": 276000
},
{
"epoch": 13.82,
"learning_rate": 3.272824946279546e-05,
"loss": 1.7982,
"step": 276500
},
{
"epoch": 13.84,
"learning_rate": 3.2697016640847536e-05,
"loss": 1.8006,
"step": 277000
},
{
"epoch": 13.87,
"learning_rate": 3.266578381889961e-05,
"loss": 1.8047,
"step": 277500
},
{
"epoch": 13.89,
"learning_rate": 3.263455099695168e-05,
"loss": 1.8001,
"step": 278000
},
{
"epoch": 13.92,
"learning_rate": 3.260331817500375e-05,
"loss": 1.8024,
"step": 278500
},
{
"epoch": 13.94,
"learning_rate": 3.257208535305582e-05,
"loss": 1.7996,
"step": 279000
},
{
"epoch": 13.97,
"learning_rate": 3.2540852531107894e-05,
"loss": 1.794,
"step": 279500
},
{
"epoch": 13.99,
"learning_rate": 3.250961970915997e-05,
"loss": 1.7972,
"step": 280000
},
{
"epoch": 14.0,
"eval_loss": 1.7481426000595093,
"eval_runtime": 80.9838,
"eval_samples_per_second": 522.821,
"eval_steps_per_second": 65.359,
"step": 280154
},
{
"epoch": 14.02,
"learning_rate": 3.2478386887212035e-05,
"loss": 1.7931,
"step": 280500
},
{
"epoch": 14.04,
"learning_rate": 3.244715406526411e-05,
"loss": 1.7925,
"step": 281000
},
{
"epoch": 14.07,
"learning_rate": 3.241592124331618e-05,
"loss": 1.7925,
"step": 281500
},
{
"epoch": 14.09,
"learning_rate": 3.2384688421368245e-05,
"loss": 1.7898,
"step": 282000
},
{
"epoch": 14.12,
"learning_rate": 3.235345559942032e-05,
"loss": 1.7953,
"step": 282500
},
{
"epoch": 14.14,
"learning_rate": 3.232222277747239e-05,
"loss": 1.7934,
"step": 283000
},
{
"epoch": 14.17,
"learning_rate": 3.229098995552447e-05,
"loss": 1.7883,
"step": 283500
},
{
"epoch": 14.19,
"learning_rate": 3.2259757133576535e-05,
"loss": 1.7965,
"step": 284000
},
{
"epoch": 14.22,
"learning_rate": 3.22285243116286e-05,
"loss": 1.7871,
"step": 284500
},
{
"epoch": 14.24,
"learning_rate": 3.2197291489680676e-05,
"loss": 1.7871,
"step": 285000
},
{
"epoch": 14.27,
"learning_rate": 3.2166058667732744e-05,
"loss": 1.7853,
"step": 285500
},
{
"epoch": 14.29,
"learning_rate": 3.2134825845784825e-05,
"loss": 1.7897,
"step": 286000
},
{
"epoch": 14.32,
"learning_rate": 3.210359302383689e-05,
"loss": 1.7853,
"step": 286500
},
{
"epoch": 14.34,
"learning_rate": 3.207236020188896e-05,
"loss": 1.7862,
"step": 287000
},
{
"epoch": 14.37,
"learning_rate": 3.2041127379941034e-05,
"loss": 1.7853,
"step": 287500
},
{
"epoch": 14.39,
"learning_rate": 3.20098945579931e-05,
"loss": 1.7906,
"step": 288000
},
{
"epoch": 14.42,
"learning_rate": 3.1978661736045176e-05,
"loss": 1.7891,
"step": 288500
},
{
"epoch": 14.44,
"learning_rate": 3.194742891409725e-05,
"loss": 1.7915,
"step": 289000
},
{
"epoch": 14.47,
"learning_rate": 3.191619609214932e-05,
"loss": 1.7874,
"step": 289500
},
{
"epoch": 14.49,
"learning_rate": 3.188496327020139e-05,
"loss": 1.7879,
"step": 290000
},
{
"epoch": 14.52,
"learning_rate": 3.185373044825346e-05,
"loss": 1.7848,
"step": 290500
},
{
"epoch": 14.54,
"learning_rate": 3.1822497626305534e-05,
"loss": 1.7879,
"step": 291000
},
{
"epoch": 14.57,
"learning_rate": 3.179126480435761e-05,
"loss": 1.7854,
"step": 291500
},
{
"epoch": 14.59,
"learning_rate": 3.1760031982409675e-05,
"loss": 1.7835,
"step": 292000
},
{
"epoch": 14.62,
"learning_rate": 3.172879916046175e-05,
"loss": 1.7859,
"step": 292500
},
{
"epoch": 14.64,
"learning_rate": 3.169756633851382e-05,
"loss": 1.7825,
"step": 293000
},
{
"epoch": 14.67,
"learning_rate": 3.166633351656589e-05,
"loss": 1.7856,
"step": 293500
},
{
"epoch": 14.69,
"learning_rate": 3.1635100694617966e-05,
"loss": 1.788,
"step": 294000
},
{
"epoch": 14.72,
"learning_rate": 3.160386787267003e-05,
"loss": 1.7842,
"step": 294500
},
{
"epoch": 14.74,
"learning_rate": 3.157263505072211e-05,
"loss": 1.7848,
"step": 295000
},
{
"epoch": 14.77,
"learning_rate": 3.1541402228774175e-05,
"loss": 1.779,
"step": 295500
},
{
"epoch": 14.79,
"learning_rate": 3.151016940682624e-05,
"loss": 1.7816,
"step": 296000
},
{
"epoch": 14.82,
"learning_rate": 3.1478936584878316e-05,
"loss": 1.7856,
"step": 296500
},
{
"epoch": 14.84,
"learning_rate": 3.144770376293039e-05,
"loss": 1.7765,
"step": 297000
},
{
"epoch": 14.87,
"learning_rate": 3.1416470940982465e-05,
"loss": 1.786,
"step": 297500
},
{
"epoch": 14.89,
"learning_rate": 3.138523811903453e-05,
"loss": 1.7782,
"step": 298000
},
{
"epoch": 14.92,
"learning_rate": 3.13540052970866e-05,
"loss": 1.7817,
"step": 298500
},
{
"epoch": 14.94,
"learning_rate": 3.1322772475138674e-05,
"loss": 1.7789,
"step": 299000
},
{
"epoch": 14.97,
"learning_rate": 3.129153965319075e-05,
"loss": 1.7786,
"step": 299500
},
{
"epoch": 14.99,
"learning_rate": 3.126030683124282e-05,
"loss": 1.7814,
"step": 300000
},
{
"epoch": 15.0,
"eval_loss": 1.7306526899337769,
"eval_runtime": 80.8426,
"eval_samples_per_second": 523.734,
"eval_steps_per_second": 65.473,
"step": 300165
},
{
"epoch": 15.02,
"learning_rate": 3.122907400929489e-05,
"loss": 1.779,
"step": 300500
},
{
"epoch": 15.04,
"learning_rate": 3.119784118734696e-05,
"loss": 1.7737,
"step": 301000
},
{
"epoch": 15.07,
"learning_rate": 3.116660836539903e-05,
"loss": 1.7743,
"step": 301500
},
{
"epoch": 15.09,
"learning_rate": 3.11353755434511e-05,
"loss": 1.7702,
"step": 302000
},
{
"epoch": 15.12,
"learning_rate": 3.1104142721503173e-05,
"loss": 1.7722,
"step": 302500
},
{
"epoch": 15.14,
"learning_rate": 3.107290989955525e-05,
"loss": 1.7704,
"step": 303000
},
{
"epoch": 15.17,
"learning_rate": 3.1041677077607315e-05,
"loss": 1.7726,
"step": 303500
},
{
"epoch": 15.19,
"learning_rate": 3.101044425565939e-05,
"loss": 1.7684,
"step": 304000
},
{
"epoch": 15.22,
"learning_rate": 3.097921143371146e-05,
"loss": 1.7723,
"step": 304500
},
{
"epoch": 15.24,
"learning_rate": 3.094797861176353e-05,
"loss": 1.7726,
"step": 305000
},
{
"epoch": 15.27,
"learning_rate": 3.0916745789815605e-05,
"loss": 1.7714,
"step": 305500
},
{
"epoch": 15.29,
"learning_rate": 3.088551296786767e-05,
"loss": 1.7683,
"step": 306000
},
{
"epoch": 15.32,
"learning_rate": 3.085428014591975e-05,
"loss": 1.7728,
"step": 306500
},
{
"epoch": 15.34,
"learning_rate": 3.0823047323971815e-05,
"loss": 1.7719,
"step": 307000
},
{
"epoch": 15.37,
"learning_rate": 3.079181450202389e-05,
"loss": 1.7737,
"step": 307500
},
{
"epoch": 15.39,
"learning_rate": 3.076058168007596e-05,
"loss": 1.7685,
"step": 308000
},
{
"epoch": 15.42,
"learning_rate": 3.072934885812803e-05,
"loss": 1.7675,
"step": 308500
},
{
"epoch": 15.44,
"learning_rate": 3.0698116036180105e-05,
"loss": 1.7728,
"step": 309000
},
{
"epoch": 15.47,
"learning_rate": 3.066688321423217e-05,
"loss": 1.7648,
"step": 309500
},
{
"epoch": 15.49,
"learning_rate": 3.063565039228424e-05,
"loss": 1.7631,
"step": 310000
},
{
"epoch": 15.52,
"learning_rate": 3.060441757033632e-05,
"loss": 1.7693,
"step": 310500
},
{
"epoch": 15.54,
"learning_rate": 3.057318474838839e-05,
"loss": 1.7657,
"step": 311000
},
{
"epoch": 15.57,
"learning_rate": 3.054195192644046e-05,
"loss": 1.7632,
"step": 311500
},
{
"epoch": 15.59,
"learning_rate": 3.051071910449253e-05,
"loss": 1.7655,
"step": 312000
},
{
"epoch": 15.62,
"learning_rate": 3.04794862825446e-05,
"loss": 1.773,
"step": 312500
},
{
"epoch": 15.64,
"learning_rate": 3.044825346059667e-05,
"loss": 1.771,
"step": 313000
},
{
"epoch": 15.67,
"learning_rate": 3.0417020638648746e-05,
"loss": 1.7654,
"step": 313500
},
{
"epoch": 15.69,
"learning_rate": 3.0385787816700817e-05,
"loss": 1.7675,
"step": 314000
},
{
"epoch": 15.72,
"learning_rate": 3.0354554994752888e-05,
"loss": 1.763,
"step": 314500
},
{
"epoch": 15.74,
"learning_rate": 3.032332217280496e-05,
"loss": 1.7677,
"step": 315000
},
{
"epoch": 15.77,
"learning_rate": 3.029208935085703e-05,
"loss": 1.768,
"step": 315500
},
{
"epoch": 15.79,
"learning_rate": 3.0260856528909104e-05,
"loss": 1.7676,
"step": 316000
},
{
"epoch": 15.82,
"learning_rate": 3.0229623706961174e-05,
"loss": 1.7603,
"step": 316500
},
{
"epoch": 15.84,
"learning_rate": 3.0198390885013245e-05,
"loss": 1.7584,
"step": 317000
},
{
"epoch": 15.87,
"learning_rate": 3.0167158063065316e-05,
"loss": 1.768,
"step": 317500
},
{
"epoch": 15.89,
"learning_rate": 3.0135925241117384e-05,
"loss": 1.7609,
"step": 318000
},
{
"epoch": 15.92,
"learning_rate": 3.0104692419169455e-05,
"loss": 1.7658,
"step": 318500
},
{
"epoch": 15.94,
"learning_rate": 3.0073459597221532e-05,
"loss": 1.7593,
"step": 319000
},
{
"epoch": 15.97,
"learning_rate": 3.0042226775273603e-05,
"loss": 1.7652,
"step": 319500
},
{
"epoch": 15.99,
"learning_rate": 3.0010993953325674e-05,
"loss": 1.7662,
"step": 320000
},
{
"epoch": 16.0,
"eval_loss": 1.7128653526306152,
"eval_runtime": 80.8512,
"eval_samples_per_second": 523.678,
"eval_steps_per_second": 65.466,
"step": 320176
},
{
"epoch": 16.02,
"learning_rate": 2.997976113137774e-05,
"loss": 1.7638,
"step": 320500
},
{
"epoch": 16.04,
"learning_rate": 2.9948528309429812e-05,
"loss": 1.7568,
"step": 321000
},
{
"epoch": 16.07,
"learning_rate": 2.991729548748189e-05,
"loss": 1.7578,
"step": 321500
},
{
"epoch": 16.09,
"learning_rate": 2.988606266553396e-05,
"loss": 1.7517,
"step": 322000
},
{
"epoch": 16.12,
"learning_rate": 2.9854829843586028e-05,
"loss": 1.76,
"step": 322500
},
{
"epoch": 16.14,
"learning_rate": 2.98235970216381e-05,
"loss": 1.7607,
"step": 323000
},
{
"epoch": 16.17,
"learning_rate": 2.979236419969017e-05,
"loss": 1.7622,
"step": 323500
},
{
"epoch": 16.19,
"learning_rate": 2.976113137774224e-05,
"loss": 1.7604,
"step": 324000
},
{
"epoch": 16.22,
"learning_rate": 2.9729898555794315e-05,
"loss": 1.7598,
"step": 324500
},
{
"epoch": 16.24,
"learning_rate": 2.9698665733846386e-05,
"loss": 1.7572,
"step": 325000
},
{
"epoch": 16.27,
"learning_rate": 2.9667432911898457e-05,
"loss": 1.7541,
"step": 325500
},
{
"epoch": 16.29,
"learning_rate": 2.9636200089950528e-05,
"loss": 1.7549,
"step": 326000
},
{
"epoch": 16.32,
"learning_rate": 2.96049672680026e-05,
"loss": 1.7625,
"step": 326500
},
{
"epoch": 16.34,
"learning_rate": 2.9573734446054673e-05,
"loss": 1.7551,
"step": 327000
},
{
"epoch": 16.37,
"learning_rate": 2.9542501624106744e-05,
"loss": 1.7545,
"step": 327500
},
{
"epoch": 16.39,
"learning_rate": 2.9511268802158814e-05,
"loss": 1.7525,
"step": 328000
},
{
"epoch": 16.42,
"learning_rate": 2.9480035980210885e-05,
"loss": 1.7537,
"step": 328500
},
{
"epoch": 16.44,
"learning_rate": 2.9448803158262956e-05,
"loss": 1.7559,
"step": 329000
},
{
"epoch": 16.47,
"learning_rate": 2.9417570336315027e-05,
"loss": 1.7551,
"step": 329500
},
{
"epoch": 16.49,
"learning_rate": 2.93863375143671e-05,
"loss": 1.7507,
"step": 330000
},
{
"epoch": 16.52,
"learning_rate": 2.9355104692419172e-05,
"loss": 1.7492,
"step": 330500
},
{
"epoch": 16.54,
"learning_rate": 2.9323871870471243e-05,
"loss": 1.7561,
"step": 331000
},
{
"epoch": 16.57,
"learning_rate": 2.9292639048523314e-05,
"loss": 1.7515,
"step": 331500
},
{
"epoch": 16.59,
"learning_rate": 2.9261406226575385e-05,
"loss": 1.7496,
"step": 332000
},
{
"epoch": 16.62,
"learning_rate": 2.923017340462746e-05,
"loss": 1.7565,
"step": 332500
},
{
"epoch": 16.64,
"learning_rate": 2.919894058267953e-05,
"loss": 1.7499,
"step": 333000
},
{
"epoch": 16.67,
"learning_rate": 2.91677077607316e-05,
"loss": 1.7528,
"step": 333500
},
{
"epoch": 16.69,
"learning_rate": 2.913647493878367e-05,
"loss": 1.7548,
"step": 334000
},
{
"epoch": 16.72,
"learning_rate": 2.910524211683574e-05,
"loss": 1.7502,
"step": 334500
},
{
"epoch": 16.74,
"learning_rate": 2.907400929488781e-05,
"loss": 1.7511,
"step": 335000
},
{
"epoch": 16.77,
"learning_rate": 2.9042776472939887e-05,
"loss": 1.7493,
"step": 335500
},
{
"epoch": 16.79,
"learning_rate": 2.9011543650991958e-05,
"loss": 1.7518,
"step": 336000
},
{
"epoch": 16.82,
"learning_rate": 2.8980310829044026e-05,
"loss": 1.7525,
"step": 336500
},
{
"epoch": 16.84,
"learning_rate": 2.8949078007096097e-05,
"loss": 1.7512,
"step": 337000
},
{
"epoch": 16.87,
"learning_rate": 2.8917845185148167e-05,
"loss": 1.7467,
"step": 337500
},
{
"epoch": 16.89,
"learning_rate": 2.8886612363200245e-05,
"loss": 1.7506,
"step": 338000
},
{
"epoch": 16.92,
"learning_rate": 2.8855379541252313e-05,
"loss": 1.7442,
"step": 338500
},
{
"epoch": 16.94,
"learning_rate": 2.8824146719304383e-05,
"loss": 1.7462,
"step": 339000
},
{
"epoch": 16.97,
"learning_rate": 2.8792913897356454e-05,
"loss": 1.75,
"step": 339500
},
{
"epoch": 16.99,
"learning_rate": 2.8761681075408525e-05,
"loss": 1.7446,
"step": 340000
},
{
"epoch": 17.0,
"eval_loss": 1.7006747722625732,
"eval_runtime": 81.9179,
"eval_samples_per_second": 516.859,
"eval_steps_per_second": 64.613,
"step": 340187
},
{
"epoch": 17.02,
"learning_rate": 2.8730448253460596e-05,
"loss": 1.7475,
"step": 340500
},
{
"epoch": 17.04,
"learning_rate": 2.869921543151267e-05,
"loss": 1.7432,
"step": 341000
},
{
"epoch": 17.07,
"learning_rate": 2.866798260956474e-05,
"loss": 1.7499,
"step": 341500
},
{
"epoch": 17.09,
"learning_rate": 2.8636749787616812e-05,
"loss": 1.7432,
"step": 342000
},
{
"epoch": 17.12,
"learning_rate": 2.8605516965668883e-05,
"loss": 1.7365,
"step": 342500
},
{
"epoch": 17.14,
"learning_rate": 2.8574284143720954e-05,
"loss": 1.7398,
"step": 343000
},
{
"epoch": 17.17,
"learning_rate": 2.8543051321773028e-05,
"loss": 1.7395,
"step": 343500
},
{
"epoch": 17.19,
"learning_rate": 2.85118184998251e-05,
"loss": 1.741,
"step": 344000
},
{
"epoch": 17.22,
"learning_rate": 2.848058567787717e-05,
"loss": 1.7447,
"step": 344500
},
{
"epoch": 17.24,
"learning_rate": 2.844935285592924e-05,
"loss": 1.74,
"step": 345000
},
{
"epoch": 17.27,
"learning_rate": 2.841812003398131e-05,
"loss": 1.7436,
"step": 345500
},
{
"epoch": 17.29,
"learning_rate": 2.8386887212033382e-05,
"loss": 1.7429,
"step": 346000
},
{
"epoch": 17.32,
"learning_rate": 2.8355654390085456e-05,
"loss": 1.7386,
"step": 346500
},
{
"epoch": 17.34,
"learning_rate": 2.8324421568137527e-05,
"loss": 1.7445,
"step": 347000
},
{
"epoch": 17.37,
"learning_rate": 2.8293188746189598e-05,
"loss": 1.7333,
"step": 347500
},
{
"epoch": 17.39,
"learning_rate": 2.826195592424167e-05,
"loss": 1.735,
"step": 348000
},
{
"epoch": 17.42,
"learning_rate": 2.8230723102293737e-05,
"loss": 1.7443,
"step": 348500
},
{
"epoch": 17.44,
"learning_rate": 2.8199490280345814e-05,
"loss": 1.7404,
"step": 349000
},
{
"epoch": 17.47,
"learning_rate": 2.8168257458397885e-05,
"loss": 1.739,
"step": 349500
},
{
"epoch": 17.49,
"learning_rate": 2.8137024636449956e-05,
"loss": 1.7397,
"step": 350000
},
{
"epoch": 17.52,
"learning_rate": 2.8105791814502023e-05,
"loss": 1.7426,
"step": 350500
},
{
"epoch": 17.54,
"learning_rate": 2.8074558992554094e-05,
"loss": 1.7324,
"step": 351000
},
{
"epoch": 17.57,
"learning_rate": 2.8043326170606165e-05,
"loss": 1.7429,
"step": 351500
},
{
"epoch": 17.59,
"learning_rate": 2.8012093348658243e-05,
"loss": 1.7374,
"step": 352000
},
{
"epoch": 17.62,
"learning_rate": 2.798086052671031e-05,
"loss": 1.7435,
"step": 352500
},
{
"epoch": 17.64,
"learning_rate": 2.794962770476238e-05,
"loss": 1.7395,
"step": 353000
},
{
"epoch": 17.67,
"learning_rate": 2.7918394882814452e-05,
"loss": 1.7372,
"step": 353500
},
{
"epoch": 17.69,
"learning_rate": 2.7887162060866523e-05,
"loss": 1.7374,
"step": 354000
},
{
"epoch": 17.72,
"learning_rate": 2.78559292389186e-05,
"loss": 1.7332,
"step": 354500
},
{
"epoch": 17.74,
"learning_rate": 2.7824696416970668e-05,
"loss": 1.7451,
"step": 355000
},
{
"epoch": 17.77,
"learning_rate": 2.779346359502274e-05,
"loss": 1.7345,
"step": 355500
},
{
"epoch": 17.79,
"learning_rate": 2.776223077307481e-05,
"loss": 1.7409,
"step": 356000
},
{
"epoch": 17.82,
"learning_rate": 2.773099795112688e-05,
"loss": 1.7304,
"step": 356500
},
{
"epoch": 17.84,
"learning_rate": 2.769976512917895e-05,
"loss": 1.7382,
"step": 357000
},
{
"epoch": 17.87,
"learning_rate": 2.7668532307231026e-05,
"loss": 1.7367,
"step": 357500
},
{
"epoch": 17.89,
"learning_rate": 2.7637299485283096e-05,
"loss": 1.7415,
"step": 358000
},
{
"epoch": 17.92,
"learning_rate": 2.7606066663335167e-05,
"loss": 1.7332,
"step": 358500
},
{
"epoch": 17.94,
"learning_rate": 2.7574833841387238e-05,
"loss": 1.7359,
"step": 359000
},
{
"epoch": 17.97,
"learning_rate": 2.754360101943931e-05,
"loss": 1.7345,
"step": 359500
},
{
"epoch": 17.99,
"learning_rate": 2.7512368197491383e-05,
"loss": 1.7315,
"step": 360000
},
{
"epoch": 18.0,
"eval_loss": 1.6893686056137085,
"eval_runtime": 80.6287,
"eval_samples_per_second": 525.123,
"eval_steps_per_second": 65.647,
"step": 360198
},
{
"epoch": 18.02,
"learning_rate": 2.7481135375543454e-05,
"loss": 1.7336,
"step": 360500
},
{
"epoch": 18.04,
"learning_rate": 2.7449902553595525e-05,
"loss": 1.7206,
"step": 361000
},
{
"epoch": 18.07,
"learning_rate": 2.7418669731647596e-05,
"loss": 1.7247,
"step": 361500
},
{
"epoch": 18.09,
"learning_rate": 2.7387436909699667e-05,
"loss": 1.7327,
"step": 362000
},
{
"epoch": 18.12,
"learning_rate": 2.7356204087751734e-05,
"loss": 1.7305,
"step": 362500
},
{
"epoch": 18.14,
"learning_rate": 2.7324971265803812e-05,
"loss": 1.7286,
"step": 363000
},
{
"epoch": 18.17,
"learning_rate": 2.7293738443855883e-05,
"loss": 1.7269,
"step": 363500
},
{
"epoch": 18.19,
"learning_rate": 2.7262505621907953e-05,
"loss": 1.7269,
"step": 364000
},
{
"epoch": 18.21,
"learning_rate": 2.723127279996002e-05,
"loss": 1.7327,
"step": 364500
},
{
"epoch": 18.24,
"learning_rate": 2.7200039978012092e-05,
"loss": 1.728,
"step": 365000
},
{
"epoch": 18.26,
"learning_rate": 2.7168807156064163e-05,
"loss": 1.7295,
"step": 365500
},
{
"epoch": 18.29,
"learning_rate": 2.713757433411624e-05,
"loss": 1.7294,
"step": 366000
},
{
"epoch": 18.31,
"learning_rate": 2.710634151216831e-05,
"loss": 1.7249,
"step": 366500
},
{
"epoch": 18.34,
"learning_rate": 2.707510869022038e-05,
"loss": 1.724,
"step": 367000
},
{
"epoch": 18.36,
"learning_rate": 2.704387586827245e-05,
"loss": 1.733,
"step": 367500
},
{
"epoch": 18.39,
"learning_rate": 2.701264304632452e-05,
"loss": 1.7272,
"step": 368000
},
{
"epoch": 18.41,
"learning_rate": 2.6981410224376598e-05,
"loss": 1.7247,
"step": 368500
},
{
"epoch": 18.44,
"learning_rate": 2.6950177402428665e-05,
"loss": 1.7301,
"step": 369000
},
{
"epoch": 18.46,
"learning_rate": 2.6918944580480736e-05,
"loss": 1.7251,
"step": 369500
},
{
"epoch": 18.49,
"learning_rate": 2.6887711758532807e-05,
"loss": 1.7208,
"step": 370000
},
{
"epoch": 18.51,
"learning_rate": 2.6856478936584878e-05,
"loss": 1.7285,
"step": 370500
},
{
"epoch": 18.54,
"learning_rate": 2.682524611463695e-05,
"loss": 1.7315,
"step": 371000
},
{
"epoch": 18.56,
"learning_rate": 2.6794013292689023e-05,
"loss": 1.7234,
"step": 371500
},
{
"epoch": 18.59,
"learning_rate": 2.6762780470741094e-05,
"loss": 1.7272,
"step": 372000
},
{
"epoch": 18.61,
"learning_rate": 2.6731547648793165e-05,
"loss": 1.726,
"step": 372500
},
{
"epoch": 18.64,
"learning_rate": 2.6700314826845236e-05,
"loss": 1.7294,
"step": 373000
},
{
"epoch": 18.66,
"learning_rate": 2.6669082004897307e-05,
"loss": 1.7229,
"step": 373500
},
{
"epoch": 18.69,
"learning_rate": 2.663784918294938e-05,
"loss": 1.7274,
"step": 374000
},
{
"epoch": 18.71,
"learning_rate": 2.660661636100145e-05,
"loss": 1.7337,
"step": 374500
},
{
"epoch": 18.74,
"learning_rate": 2.6575383539053523e-05,
"loss": 1.7322,
"step": 375000
},
{
"epoch": 18.76,
"learning_rate": 2.6544150717105593e-05,
"loss": 1.7221,
"step": 375500
},
{
"epoch": 18.79,
"learning_rate": 2.6512917895157664e-05,
"loss": 1.7281,
"step": 376000
},
{
"epoch": 18.81,
"learning_rate": 2.6481685073209732e-05,
"loss": 1.7271,
"step": 376500
},
{
"epoch": 18.84,
"learning_rate": 2.645045225126181e-05,
"loss": 1.7212,
"step": 377000
},
{
"epoch": 18.86,
"learning_rate": 2.641921942931388e-05,
"loss": 1.7246,
"step": 377500
},
{
"epoch": 18.89,
"learning_rate": 2.638798660736595e-05,
"loss": 1.7228,
"step": 378000
},
{
"epoch": 18.91,
"learning_rate": 2.635675378541802e-05,
"loss": 1.7191,
"step": 378500
},
{
"epoch": 18.94,
"learning_rate": 2.632552096347009e-05,
"loss": 1.7246,
"step": 379000
},
{
"epoch": 18.96,
"learning_rate": 2.6294288141522167e-05,
"loss": 1.7214,
"step": 379500
},
{
"epoch": 18.99,
"learning_rate": 2.6263055319574238e-05,
"loss": 1.7227,
"step": 380000
},
{
"epoch": 19.0,
"eval_loss": 1.6773531436920166,
"eval_runtime": 80.9514,
"eval_samples_per_second": 523.03,
"eval_steps_per_second": 65.385,
"step": 380209
},
{
"epoch": 19.01,
"learning_rate": 2.623182249762631e-05,
"loss": 1.7174,
"step": 380500
},
{
"epoch": 19.04,
"learning_rate": 2.6200589675678376e-05,
"loss": 1.7219,
"step": 381000
},
{
"epoch": 19.06,
"learning_rate": 2.6169356853730447e-05,
"loss": 1.7179,
"step": 381500
},
{
"epoch": 19.09,
"learning_rate": 2.6138124031782518e-05,
"loss": 1.714,
"step": 382000
},
{
"epoch": 19.11,
"learning_rate": 2.6106891209834596e-05,
"loss": 1.7232,
"step": 382500
},
{
"epoch": 19.14,
"learning_rate": 2.6075658387886663e-05,
"loss": 1.7187,
"step": 383000
},
{
"epoch": 19.16,
"learning_rate": 2.6044425565938734e-05,
"loss": 1.7164,
"step": 383500
},
{
"epoch": 19.19,
"learning_rate": 2.6013192743990805e-05,
"loss": 1.7108,
"step": 384000
},
{
"epoch": 19.21,
"learning_rate": 2.5981959922042876e-05,
"loss": 1.7166,
"step": 384500
},
{
"epoch": 19.24,
"learning_rate": 2.595072710009495e-05,
"loss": 1.717,
"step": 385000
},
{
"epoch": 19.26,
"learning_rate": 2.591949427814702e-05,
"loss": 1.7186,
"step": 385500
},
{
"epoch": 19.29,
"learning_rate": 2.588826145619909e-05,
"loss": 1.715,
"step": 386000
},
{
"epoch": 19.31,
"learning_rate": 2.5857028634251162e-05,
"loss": 1.7177,
"step": 386500
},
{
"epoch": 19.34,
"learning_rate": 2.5825795812303233e-05,
"loss": 1.7191,
"step": 387000
},
{
"epoch": 19.36,
"learning_rate": 2.5794562990355304e-05,
"loss": 1.7156,
"step": 387500
},
{
"epoch": 19.39,
"learning_rate": 2.576333016840738e-05,
"loss": 1.71,
"step": 388000
},
{
"epoch": 19.41,
"learning_rate": 2.573209734645945e-05,
"loss": 1.7133,
"step": 388500
},
{
"epoch": 19.44,
"learning_rate": 2.570086452451152e-05,
"loss": 1.7168,
"step": 389000
},
{
"epoch": 19.46,
"learning_rate": 2.566963170256359e-05,
"loss": 1.7133,
"step": 389500
},
{
"epoch": 19.49,
"learning_rate": 2.5638398880615662e-05,
"loss": 1.7177,
"step": 390000
},
{
"epoch": 19.51,
"learning_rate": 2.5607166058667736e-05,
"loss": 1.7163,
"step": 390500
},
{
"epoch": 19.54,
"learning_rate": 2.5575933236719807e-05,
"loss": 1.7148,
"step": 391000
},
{
"epoch": 19.56,
"learning_rate": 2.5544700414771878e-05,
"loss": 1.7127,
"step": 391500
},
{
"epoch": 19.59,
"learning_rate": 2.551346759282395e-05,
"loss": 1.7185,
"step": 392000
},
{
"epoch": 19.61,
"learning_rate": 2.5482234770876016e-05,
"loss": 1.7062,
"step": 392500
},
{
"epoch": 19.64,
"learning_rate": 2.5451001948928087e-05,
"loss": 1.7142,
"step": 393000
},
{
"epoch": 19.66,
"learning_rate": 2.5419769126980165e-05,
"loss": 1.7166,
"step": 393500
},
{
"epoch": 19.69,
"learning_rate": 2.5388536305032236e-05,
"loss": 1.7181,
"step": 394000
},
{
"epoch": 19.71,
"learning_rate": 2.5357303483084306e-05,
"loss": 1.713,
"step": 394500
},
{
"epoch": 19.74,
"learning_rate": 2.5326070661136374e-05,
"loss": 1.7058,
"step": 395000
},
{
"epoch": 19.76,
"learning_rate": 2.5294837839188445e-05,
"loss": 1.7122,
"step": 395500
},
{
"epoch": 19.79,
"learning_rate": 2.5263605017240522e-05,
"loss": 1.7139,
"step": 396000
},
{
"epoch": 19.81,
"learning_rate": 2.5232372195292593e-05,
"loss": 1.7107,
"step": 396500
},
{
"epoch": 19.84,
"learning_rate": 2.520113937334466e-05,
"loss": 1.7138,
"step": 397000
},
{
"epoch": 19.86,
"learning_rate": 2.516990655139673e-05,
"loss": 1.715,
"step": 397500
},
{
"epoch": 19.89,
"learning_rate": 2.5138673729448802e-05,
"loss": 1.7054,
"step": 398000
},
{
"epoch": 19.91,
"learning_rate": 2.5107440907500873e-05,
"loss": 1.7099,
"step": 398500
},
{
"epoch": 19.94,
"learning_rate": 2.5076208085552947e-05,
"loss": 1.7159,
"step": 399000
},
{
"epoch": 19.96,
"learning_rate": 2.504497526360502e-05,
"loss": 1.7027,
"step": 399500
},
{
"epoch": 19.99,
"learning_rate": 2.501374244165709e-05,
"loss": 1.7129,
"step": 400000
},
{
"epoch": 20.0,
"eval_loss": 1.666919231414795,
"eval_runtime": 80.8571,
"eval_samples_per_second": 523.64,
"eval_steps_per_second": 65.461,
"step": 400220
},
{
"epoch": 20.01,
"learning_rate": 2.498250961970916e-05,
"loss": 1.7126,
"step": 400500
},
{
"epoch": 20.04,
"learning_rate": 2.4951276797761234e-05,
"loss": 1.6989,
"step": 401000
},
{
"epoch": 20.06,
"learning_rate": 2.4920043975813305e-05,
"loss": 1.7107,
"step": 401500
},
{
"epoch": 20.09,
"learning_rate": 2.4888811153865373e-05,
"loss": 1.7049,
"step": 402000
},
{
"epoch": 20.11,
"learning_rate": 2.4857578331917447e-05,
"loss": 1.71,
"step": 402500
},
{
"epoch": 20.14,
"learning_rate": 2.4826345509969518e-05,
"loss": 1.7096,
"step": 403000
},
{
"epoch": 20.16,
"learning_rate": 2.4795112688021592e-05,
"loss": 1.7059,
"step": 403500
},
{
"epoch": 20.19,
"learning_rate": 2.476387986607366e-05,
"loss": 1.707,
"step": 404000
},
{
"epoch": 20.21,
"learning_rate": 2.473264704412573e-05,
"loss": 1.7061,
"step": 404500
},
{
"epoch": 20.24,
"learning_rate": 2.4701414222177805e-05,
"loss": 1.7076,
"step": 405000
},
{
"epoch": 20.26,
"learning_rate": 2.4670181400229875e-05,
"loss": 1.7006,
"step": 405500
},
{
"epoch": 20.29,
"learning_rate": 2.4638948578281946e-05,
"loss": 1.7043,
"step": 406000
},
{
"epoch": 20.31,
"learning_rate": 2.4607715756334017e-05,
"loss": 1.7011,
"step": 406500
},
{
"epoch": 20.34,
"learning_rate": 2.4576482934386088e-05,
"loss": 1.7029,
"step": 407000
},
{
"epoch": 20.36,
"learning_rate": 2.454525011243816e-05,
"loss": 1.7061,
"step": 407500
},
{
"epoch": 20.39,
"learning_rate": 2.4514017290490233e-05,
"loss": 1.6962,
"step": 408000
},
{
"epoch": 20.41,
"learning_rate": 2.4482784468542304e-05,
"loss": 1.7072,
"step": 408500
},
{
"epoch": 20.44,
"learning_rate": 2.4451551646594375e-05,
"loss": 1.7007,
"step": 409000
},
{
"epoch": 20.46,
"learning_rate": 2.4420318824646446e-05,
"loss": 1.7083,
"step": 409500
},
{
"epoch": 20.49,
"learning_rate": 2.4389086002698517e-05,
"loss": 1.7062,
"step": 410000
},
{
"epoch": 20.51,
"learning_rate": 2.435785318075059e-05,
"loss": 1.7039,
"step": 410500
},
{
"epoch": 20.54,
"learning_rate": 2.4326620358802658e-05,
"loss": 1.7011,
"step": 411000
},
{
"epoch": 20.56,
"learning_rate": 2.429538753685473e-05,
"loss": 1.711,
"step": 411500
},
{
"epoch": 20.59,
"learning_rate": 2.4264154714906803e-05,
"loss": 1.7017,
"step": 412000
},
{
"epoch": 20.61,
"learning_rate": 2.4232921892958874e-05,
"loss": 1.6973,
"step": 412500
},
{
"epoch": 20.64,
"learning_rate": 2.4201689071010945e-05,
"loss": 1.7045,
"step": 413000
},
{
"epoch": 20.66,
"learning_rate": 2.4170456249063016e-05,
"loss": 1.7024,
"step": 413500
},
{
"epoch": 20.69,
"learning_rate": 2.4139223427115087e-05,
"loss": 1.7003,
"step": 414000
},
{
"epoch": 20.71,
"learning_rate": 2.410799060516716e-05,
"loss": 1.7004,
"step": 414500
},
{
"epoch": 20.74,
"learning_rate": 2.4076757783219232e-05,
"loss": 1.6969,
"step": 415000
},
{
"epoch": 20.76,
"learning_rate": 2.4045524961271303e-05,
"loss": 1.7026,
"step": 415500
},
{
"epoch": 20.79,
"learning_rate": 2.4014292139323374e-05,
"loss": 1.7019,
"step": 416000
},
{
"epoch": 20.81,
"learning_rate": 2.3983059317375444e-05,
"loss": 1.7006,
"step": 416500
},
{
"epoch": 20.84,
"learning_rate": 2.3951826495427515e-05,
"loss": 1.6951,
"step": 417000
},
{
"epoch": 20.86,
"learning_rate": 2.392059367347959e-05,
"loss": 1.6976,
"step": 417500
},
{
"epoch": 20.89,
"learning_rate": 2.3889360851531657e-05,
"loss": 1.7059,
"step": 418000
},
{
"epoch": 20.91,
"learning_rate": 2.3858128029583728e-05,
"loss": 1.6923,
"step": 418500
},
{
"epoch": 20.94,
"learning_rate": 2.3826895207635802e-05,
"loss": 1.6991,
"step": 419000
},
{
"epoch": 20.96,
"learning_rate": 2.3795662385687873e-05,
"loss": 1.7017,
"step": 419500
},
{
"epoch": 20.99,
"learning_rate": 2.3764429563739944e-05,
"loss": 1.7028,
"step": 420000
},
{
"epoch": 21.0,
"eval_loss": 1.657880187034607,
"eval_runtime": 80.8889,
"eval_samples_per_second": 523.434,
"eval_steps_per_second": 65.435,
"step": 420231
},
{
"epoch": 21.01,
"learning_rate": 2.3733196741792015e-05,
"loss": 1.6894,
"step": 420500
},
{
"epoch": 21.04,
"learning_rate": 2.3701963919844086e-05,
"loss": 1.6935,
"step": 421000
},
{
"epoch": 21.06,
"learning_rate": 2.367073109789616e-05,
"loss": 1.6964,
"step": 421500
},
{
"epoch": 21.09,
"learning_rate": 2.363949827594823e-05,
"loss": 1.6904,
"step": 422000
},
{
"epoch": 21.11,
"learning_rate": 2.36082654540003e-05,
"loss": 1.694,
"step": 422500
},
{
"epoch": 21.14,
"learning_rate": 2.3577032632052372e-05,
"loss": 1.691,
"step": 423000
},
{
"epoch": 21.16,
"learning_rate": 2.3545799810104443e-05,
"loss": 1.6951,
"step": 423500
},
{
"epoch": 21.19,
"learning_rate": 2.3514566988156514e-05,
"loss": 1.6943,
"step": 424000
},
{
"epoch": 21.21,
"learning_rate": 2.348333416620859e-05,
"loss": 1.6884,
"step": 424500
},
{
"epoch": 21.24,
"learning_rate": 2.3452101344260656e-05,
"loss": 1.6939,
"step": 425000
},
{
"epoch": 21.26,
"learning_rate": 2.3420868522312727e-05,
"loss": 1.6934,
"step": 425500
},
{
"epoch": 21.29,
"learning_rate": 2.33896357003648e-05,
"loss": 1.6908,
"step": 426000
},
{
"epoch": 21.31,
"learning_rate": 2.3358402878416872e-05,
"loss": 1.6943,
"step": 426500
},
{
"epoch": 21.34,
"learning_rate": 2.3327170056468943e-05,
"loss": 1.6936,
"step": 427000
},
{
"epoch": 21.36,
"learning_rate": 2.3295937234521014e-05,
"loss": 1.6953,
"step": 427500
},
{
"epoch": 21.39,
"learning_rate": 2.3264704412573084e-05,
"loss": 1.692,
"step": 428000
},
{
"epoch": 21.41,
"learning_rate": 2.323347159062516e-05,
"loss": 1.6906,
"step": 428500
},
{
"epoch": 21.44,
"learning_rate": 2.320223876867723e-05,
"loss": 1.6909,
"step": 429000
},
{
"epoch": 21.46,
"learning_rate": 2.31710059467293e-05,
"loss": 1.6895,
"step": 429500
},
{
"epoch": 21.49,
"learning_rate": 2.313977312478137e-05,
"loss": 1.6903,
"step": 430000
},
{
"epoch": 21.51,
"learning_rate": 2.3108540302833442e-05,
"loss": 1.697,
"step": 430500
},
{
"epoch": 21.54,
"learning_rate": 2.3077307480885513e-05,
"loss": 1.6977,
"step": 431000
},
{
"epoch": 21.56,
"learning_rate": 2.3046074658937587e-05,
"loss": 1.696,
"step": 431500
},
{
"epoch": 21.59,
"learning_rate": 2.3014841836989655e-05,
"loss": 1.6947,
"step": 432000
},
{
"epoch": 21.61,
"learning_rate": 2.298360901504173e-05,
"loss": 1.6943,
"step": 432500
},
{
"epoch": 21.64,
"learning_rate": 2.29523761930938e-05,
"loss": 1.6925,
"step": 433000
},
{
"epoch": 21.66,
"learning_rate": 2.292114337114587e-05,
"loss": 1.6864,
"step": 433500
},
{
"epoch": 21.69,
"learning_rate": 2.2889910549197945e-05,
"loss": 1.6937,
"step": 434000
},
{
"epoch": 21.71,
"learning_rate": 2.2858677727250012e-05,
"loss": 1.6911,
"step": 434500
},
{
"epoch": 21.74,
"learning_rate": 2.2827444905302083e-05,
"loss": 1.6931,
"step": 435000
},
{
"epoch": 21.76,
"learning_rate": 2.2796212083354157e-05,
"loss": 1.6948,
"step": 435500
},
{
"epoch": 21.79,
"learning_rate": 2.276497926140623e-05,
"loss": 1.6903,
"step": 436000
},
{
"epoch": 21.81,
"learning_rate": 2.27337464394583e-05,
"loss": 1.688,
"step": 436500
},
{
"epoch": 21.84,
"learning_rate": 2.270251361751037e-05,
"loss": 1.6923,
"step": 437000
},
{
"epoch": 21.86,
"learning_rate": 2.267128079556244e-05,
"loss": 1.6938,
"step": 437500
},
{
"epoch": 21.89,
"learning_rate": 2.2640047973614515e-05,
"loss": 1.6896,
"step": 438000
},
{
"epoch": 21.91,
"learning_rate": 2.2608815151666586e-05,
"loss": 1.6928,
"step": 438500
},
{
"epoch": 21.94,
"learning_rate": 2.2577582329718653e-05,
"loss": 1.6937,
"step": 439000
},
{
"epoch": 21.96,
"learning_rate": 2.2546349507770728e-05,
"loss": 1.6927,
"step": 439500
},
{
"epoch": 21.99,
"learning_rate": 2.25151166858228e-05,
"loss": 1.6888,
"step": 440000
},
{
"epoch": 22.0,
"eval_loss": 1.6455161571502686,
"eval_runtime": 80.986,
"eval_samples_per_second": 522.806,
"eval_steps_per_second": 65.357,
"step": 440242
},
{
"epoch": 22.01,
"learning_rate": 2.248388386387487e-05,
"loss": 1.6879,
"step": 440500
},
{
"epoch": 22.04,
"learning_rate": 2.2452651041926944e-05,
"loss": 1.6818,
"step": 441000
},
{
"epoch": 22.06,
"learning_rate": 2.242141821997901e-05,
"loss": 1.6868,
"step": 441500
},
{
"epoch": 22.09,
"learning_rate": 2.2390185398031082e-05,
"loss": 1.6893,
"step": 442000
},
{
"epoch": 22.11,
"learning_rate": 2.2358952576083156e-05,
"loss": 1.6842,
"step": 442500
},
{
"epoch": 22.14,
"learning_rate": 2.2327719754135227e-05,
"loss": 1.68,
"step": 443000
},
{
"epoch": 22.16,
"learning_rate": 2.2296486932187298e-05,
"loss": 1.6808,
"step": 443500
},
{
"epoch": 22.19,
"learning_rate": 2.226525411023937e-05,
"loss": 1.6838,
"step": 444000
},
{
"epoch": 22.21,
"learning_rate": 2.223402128829144e-05,
"loss": 1.6857,
"step": 444500
},
{
"epoch": 22.24,
"learning_rate": 2.2202788466343514e-05,
"loss": 1.6842,
"step": 445000
},
{
"epoch": 22.26,
"learning_rate": 2.2171555644395585e-05,
"loss": 1.6853,
"step": 445500
},
{
"epoch": 22.29,
"learning_rate": 2.2140322822447652e-05,
"loss": 1.6787,
"step": 446000
},
{
"epoch": 22.31,
"learning_rate": 2.2109090000499727e-05,
"loss": 1.6864,
"step": 446500
},
{
"epoch": 22.34,
"learning_rate": 2.2077857178551797e-05,
"loss": 1.6873,
"step": 447000
},
{
"epoch": 22.36,
"learning_rate": 2.2046624356603868e-05,
"loss": 1.6844,
"step": 447500
},
{
"epoch": 22.39,
"learning_rate": 2.2015391534655942e-05,
"loss": 1.6841,
"step": 448000
},
{
"epoch": 22.41,
"learning_rate": 2.198415871270801e-05,
"loss": 1.6821,
"step": 448500
},
{
"epoch": 22.44,
"learning_rate": 2.1952925890760084e-05,
"loss": 1.6766,
"step": 449000
},
{
"epoch": 22.46,
"learning_rate": 2.1921693068812155e-05,
"loss": 1.6859,
"step": 449500
},
{
"epoch": 22.49,
"learning_rate": 2.1890460246864226e-05,
"loss": 1.6884,
"step": 450000
},
{
"epoch": 22.51,
"learning_rate": 2.1859227424916297e-05,
"loss": 1.6822,
"step": 450500
},
{
"epoch": 22.54,
"learning_rate": 2.1827994602968368e-05,
"loss": 1.6804,
"step": 451000
},
{
"epoch": 22.56,
"learning_rate": 2.179676178102044e-05,
"loss": 1.6891,
"step": 451500
},
{
"epoch": 22.59,
"learning_rate": 2.1765528959072513e-05,
"loss": 1.6805,
"step": 452000
},
{
"epoch": 22.61,
"learning_rate": 2.1734296137124584e-05,
"loss": 1.6832,
"step": 452500
},
{
"epoch": 22.64,
"learning_rate": 2.170306331517665e-05,
"loss": 1.6883,
"step": 453000
},
{
"epoch": 22.66,
"learning_rate": 2.1671830493228725e-05,
"loss": 1.6839,
"step": 453500
},
{
"epoch": 22.69,
"learning_rate": 2.1640597671280796e-05,
"loss": 1.6789,
"step": 454000
},
{
"epoch": 22.71,
"learning_rate": 2.160936484933287e-05,
"loss": 1.6784,
"step": 454500
},
{
"epoch": 22.74,
"learning_rate": 2.157813202738494e-05,
"loss": 1.6866,
"step": 455000
},
{
"epoch": 22.76,
"learning_rate": 2.154689920543701e-05,
"loss": 1.686,
"step": 455500
},
{
"epoch": 22.79,
"learning_rate": 2.1515666383489083e-05,
"loss": 1.678,
"step": 456000
},
{
"epoch": 22.81,
"learning_rate": 2.1484433561541154e-05,
"loss": 1.6805,
"step": 456500
},
{
"epoch": 22.84,
"learning_rate": 2.1453200739593225e-05,
"loss": 1.6813,
"step": 457000
},
{
"epoch": 22.86,
"learning_rate": 2.1421967917645296e-05,
"loss": 1.6801,
"step": 457500
},
{
"epoch": 22.89,
"learning_rate": 2.1390735095697366e-05,
"loss": 1.6793,
"step": 458000
},
{
"epoch": 22.91,
"learning_rate": 2.1359502273749437e-05,
"loss": 1.6779,
"step": 458500
},
{
"epoch": 22.94,
"learning_rate": 2.132826945180151e-05,
"loss": 1.682,
"step": 459000
},
{
"epoch": 22.96,
"learning_rate": 2.1297036629853582e-05,
"loss": 1.6775,
"step": 459500
},
{
"epoch": 22.99,
"learning_rate": 2.1265803807905653e-05,
"loss": 1.6842,
"step": 460000
},
{
"epoch": 23.0,
"eval_loss": 1.6366124153137207,
"eval_runtime": 80.8824,
"eval_samples_per_second": 523.476,
"eval_steps_per_second": 65.441,
"step": 460253
},
{
"epoch": 23.01,
"learning_rate": 2.1234570985957724e-05,
"loss": 1.6808,
"step": 460500
},
{
"epoch": 23.04,
"learning_rate": 2.1203338164009795e-05,
"loss": 1.6717,
"step": 461000
},
{
"epoch": 23.06,
"learning_rate": 2.117210534206187e-05,
"loss": 1.6832,
"step": 461500
},
{
"epoch": 23.09,
"learning_rate": 2.114087252011394e-05,
"loss": 1.6793,
"step": 462000
},
{
"epoch": 23.11,
"learning_rate": 2.1109639698166008e-05,
"loss": 1.6747,
"step": 462500
},
{
"epoch": 23.14,
"learning_rate": 2.1078406876218082e-05,
"loss": 1.6707,
"step": 463000
},
{
"epoch": 23.16,
"learning_rate": 2.1047174054270153e-05,
"loss": 1.6722,
"step": 463500
},
{
"epoch": 23.19,
"learning_rate": 2.1015941232322224e-05,
"loss": 1.6745,
"step": 464000
},
{
"epoch": 23.21,
"learning_rate": 2.0984708410374294e-05,
"loss": 1.672,
"step": 464500
},
{
"epoch": 23.24,
"learning_rate": 2.0953475588426365e-05,
"loss": 1.6773,
"step": 465000
},
{
"epoch": 23.26,
"learning_rate": 2.0922242766478436e-05,
"loss": 1.6828,
"step": 465500
},
{
"epoch": 23.29,
"learning_rate": 2.089100994453051e-05,
"loss": 1.6781,
"step": 466000
},
{
"epoch": 23.31,
"learning_rate": 2.085977712258258e-05,
"loss": 1.677,
"step": 466500
},
{
"epoch": 23.34,
"learning_rate": 2.0828544300634652e-05,
"loss": 1.6723,
"step": 467000
},
{
"epoch": 23.36,
"learning_rate": 2.0797311478686723e-05,
"loss": 1.6697,
"step": 467500
},
{
"epoch": 23.39,
"learning_rate": 2.0766078656738794e-05,
"loss": 1.672,
"step": 468000
},
{
"epoch": 23.41,
"learning_rate": 2.0734845834790868e-05,
"loss": 1.6741,
"step": 468500
},
{
"epoch": 23.44,
"learning_rate": 2.070361301284294e-05,
"loss": 1.6794,
"step": 469000
},
{
"epoch": 23.46,
"learning_rate": 2.0672380190895006e-05,
"loss": 1.6753,
"step": 469500
},
{
"epoch": 23.49,
"learning_rate": 2.064114736894708e-05,
"loss": 1.6751,
"step": 470000
},
{
"epoch": 23.51,
"learning_rate": 2.060991454699915e-05,
"loss": 1.679,
"step": 470500
},
{
"epoch": 23.54,
"learning_rate": 2.0578681725051222e-05,
"loss": 1.6737,
"step": 471000
},
{
"epoch": 23.56,
"learning_rate": 2.0547448903103293e-05,
"loss": 1.6741,
"step": 471500
},
{
"epoch": 23.59,
"learning_rate": 2.0516216081155364e-05,
"loss": 1.6702,
"step": 472000
},
{
"epoch": 23.61,
"learning_rate": 2.0484983259207438e-05,
"loss": 1.6739,
"step": 472500
},
{
"epoch": 23.64,
"learning_rate": 2.045375043725951e-05,
"loss": 1.6741,
"step": 473000
},
{
"epoch": 23.66,
"learning_rate": 2.042251761531158e-05,
"loss": 1.6715,
"step": 473500
},
{
"epoch": 23.69,
"learning_rate": 2.039128479336365e-05,
"loss": 1.6668,
"step": 474000
},
{
"epoch": 23.71,
"learning_rate": 2.0360051971415722e-05,
"loss": 1.6735,
"step": 474500
},
{
"epoch": 23.74,
"learning_rate": 2.0328819149467793e-05,
"loss": 1.6743,
"step": 475000
},
{
"epoch": 23.76,
"learning_rate": 2.0297586327519867e-05,
"loss": 1.6767,
"step": 475500
},
{
"epoch": 23.79,
"learning_rate": 2.0266353505571938e-05,
"loss": 1.6715,
"step": 476000
},
{
"epoch": 23.81,
"learning_rate": 2.0235120683624005e-05,
"loss": 1.6719,
"step": 476500
},
{
"epoch": 23.84,
"learning_rate": 2.020388786167608e-05,
"loss": 1.6729,
"step": 477000
},
{
"epoch": 23.86,
"learning_rate": 2.017265503972815e-05,
"loss": 1.6687,
"step": 477500
},
{
"epoch": 23.89,
"learning_rate": 2.0141422217780224e-05,
"loss": 1.6717,
"step": 478000
},
{
"epoch": 23.91,
"learning_rate": 2.0110189395832292e-05,
"loss": 1.6753,
"step": 478500
},
{
"epoch": 23.94,
"learning_rate": 2.0078956573884363e-05,
"loss": 1.6676,
"step": 479000
},
{
"epoch": 23.96,
"learning_rate": 2.0047723751936437e-05,
"loss": 1.6697,
"step": 479500
},
{
"epoch": 23.99,
"learning_rate": 2.0016490929988508e-05,
"loss": 1.6739,
"step": 480000
},
{
"epoch": 24.0,
"eval_loss": 1.632072925567627,
"eval_runtime": 80.8697,
"eval_samples_per_second": 523.558,
"eval_steps_per_second": 65.451,
"step": 480264
},
{
"epoch": 24.01,
"learning_rate": 1.998525810804058e-05,
"loss": 1.6704,
"step": 480500
},
{
"epoch": 24.04,
"learning_rate": 1.995402528609265e-05,
"loss": 1.6638,
"step": 481000
},
{
"epoch": 24.06,
"learning_rate": 1.992279246414472e-05,
"loss": 1.6659,
"step": 481500
},
{
"epoch": 24.09,
"learning_rate": 1.989155964219679e-05,
"loss": 1.6674,
"step": 482000
},
{
"epoch": 24.11,
"learning_rate": 1.9860326820248866e-05,
"loss": 1.6713,
"step": 482500
},
{
"epoch": 24.14,
"learning_rate": 1.9829093998300936e-05,
"loss": 1.6616,
"step": 483000
},
{
"epoch": 24.16,
"learning_rate": 1.9797861176353007e-05,
"loss": 1.6652,
"step": 483500
},
{
"epoch": 24.19,
"learning_rate": 1.9766628354405078e-05,
"loss": 1.6678,
"step": 484000
},
{
"epoch": 24.21,
"learning_rate": 1.973539553245715e-05,
"loss": 1.6647,
"step": 484500
},
{
"epoch": 24.24,
"learning_rate": 1.9704162710509223e-05,
"loss": 1.6639,
"step": 485000
},
{
"epoch": 24.26,
"learning_rate": 1.967292988856129e-05,
"loss": 1.666,
"step": 485500
},
{
"epoch": 24.29,
"learning_rate": 1.964169706661336e-05,
"loss": 1.6695,
"step": 486000
},
{
"epoch": 24.31,
"learning_rate": 1.9610464244665436e-05,
"loss": 1.6625,
"step": 486500
},
{
"epoch": 24.34,
"learning_rate": 1.9579231422717507e-05,
"loss": 1.6762,
"step": 487000
},
{
"epoch": 24.36,
"learning_rate": 1.9547998600769578e-05,
"loss": 1.6669,
"step": 487500
},
{
"epoch": 24.39,
"learning_rate": 1.951676577882165e-05,
"loss": 1.6687,
"step": 488000
},
{
"epoch": 24.41,
"learning_rate": 1.948553295687372e-05,
"loss": 1.6615,
"step": 488500
},
{
"epoch": 24.44,
"learning_rate": 1.9454300134925794e-05,
"loss": 1.669,
"step": 489000
},
{
"epoch": 24.46,
"learning_rate": 1.9423067312977864e-05,
"loss": 1.6619,
"step": 489500
},
{
"epoch": 24.49,
"learning_rate": 1.9391834491029935e-05,
"loss": 1.6677,
"step": 490000
},
{
"epoch": 24.51,
"learning_rate": 1.9360601669082006e-05,
"loss": 1.6676,
"step": 490500
},
{
"epoch": 24.54,
"learning_rate": 1.9329368847134077e-05,
"loss": 1.6669,
"step": 491000
},
{
"epoch": 24.56,
"learning_rate": 1.9298136025186148e-05,
"loss": 1.6583,
"step": 491500
},
{
"epoch": 24.59,
"learning_rate": 1.9266903203238222e-05,
"loss": 1.6601,
"step": 492000
},
{
"epoch": 24.61,
"learning_rate": 1.923567038129029e-05,
"loss": 1.6636,
"step": 492500
},
{
"epoch": 24.64,
"learning_rate": 1.920443755934236e-05,
"loss": 1.6713,
"step": 493000
},
{
"epoch": 24.66,
"learning_rate": 1.9173204737394435e-05,
"loss": 1.6602,
"step": 493500
},
{
"epoch": 24.69,
"learning_rate": 1.9141971915446506e-05,
"loss": 1.6571,
"step": 494000
},
{
"epoch": 24.71,
"learning_rate": 1.9110739093498576e-05,
"loss": 1.6606,
"step": 494500
},
{
"epoch": 24.74,
"learning_rate": 1.9079506271550647e-05,
"loss": 1.6678,
"step": 495000
},
{
"epoch": 24.76,
"learning_rate": 1.9048273449602718e-05,
"loss": 1.66,
"step": 495500
},
{
"epoch": 24.79,
"learning_rate": 1.9017040627654792e-05,
"loss": 1.6611,
"step": 496000
},
{
"epoch": 24.81,
"learning_rate": 1.8985807805706863e-05,
"loss": 1.6649,
"step": 496500
},
{
"epoch": 24.84,
"learning_rate": 1.8954574983758934e-05,
"loss": 1.6679,
"step": 497000
},
{
"epoch": 24.86,
"learning_rate": 1.8923342161811005e-05,
"loss": 1.6628,
"step": 497500
},
{
"epoch": 24.89,
"learning_rate": 1.8892109339863076e-05,
"loss": 1.6653,
"step": 498000
},
{
"epoch": 24.91,
"learning_rate": 1.8860876517915147e-05,
"loss": 1.6655,
"step": 498500
},
{
"epoch": 24.94,
"learning_rate": 1.882964369596722e-05,
"loss": 1.6636,
"step": 499000
},
{
"epoch": 24.96,
"learning_rate": 1.879841087401929e-05,
"loss": 1.6654,
"step": 499500
},
{
"epoch": 24.99,
"learning_rate": 1.8767178052071363e-05,
"loss": 1.6648,
"step": 500000
},
{
"epoch": 25.0,
"eval_loss": 1.6190860271453857,
"eval_runtime": 80.9079,
"eval_samples_per_second": 523.311,
"eval_steps_per_second": 65.42,
"step": 500275
},
{
"epoch": 25.01,
"learning_rate": 1.8735945230123433e-05,
"loss": 1.6648,
"step": 500500
},
{
"epoch": 25.04,
"learning_rate": 1.8704712408175504e-05,
"loss": 1.6547,
"step": 501000
},
{
"epoch": 25.06,
"learning_rate": 1.8673479586227575e-05,
"loss": 1.6612,
"step": 501500
},
{
"epoch": 25.09,
"learning_rate": 1.8642246764279646e-05,
"loss": 1.655,
"step": 502000
},
{
"epoch": 25.11,
"learning_rate": 1.8611013942331717e-05,
"loss": 1.6591,
"step": 502500
},
{
"epoch": 25.14,
"learning_rate": 1.857978112038379e-05,
"loss": 1.6652,
"step": 503000
},
{
"epoch": 25.16,
"learning_rate": 1.8548548298435862e-05,
"loss": 1.6603,
"step": 503500
},
{
"epoch": 25.19,
"learning_rate": 1.8517315476487933e-05,
"loss": 1.6549,
"step": 504000
},
{
"epoch": 25.21,
"learning_rate": 1.8486082654540004e-05,
"loss": 1.6578,
"step": 504500
},
{
"epoch": 25.24,
"learning_rate": 1.8454849832592075e-05,
"loss": 1.6561,
"step": 505000
},
{
"epoch": 25.26,
"learning_rate": 1.8423617010644145e-05,
"loss": 1.6636,
"step": 505500
},
{
"epoch": 25.29,
"learning_rate": 1.839238418869622e-05,
"loss": 1.6587,
"step": 506000
},
{
"epoch": 25.31,
"learning_rate": 1.8361151366748287e-05,
"loss": 1.6587,
"step": 506500
},
{
"epoch": 25.34,
"learning_rate": 1.832991854480036e-05,
"loss": 1.6606,
"step": 507000
},
{
"epoch": 25.36,
"learning_rate": 1.8298685722852432e-05,
"loss": 1.6547,
"step": 507500
},
{
"epoch": 25.39,
"learning_rate": 1.8267452900904503e-05,
"loss": 1.6543,
"step": 508000
},
{
"epoch": 25.41,
"learning_rate": 1.8236220078956577e-05,
"loss": 1.659,
"step": 508500
},
{
"epoch": 25.44,
"learning_rate": 1.8204987257008645e-05,
"loss": 1.6603,
"step": 509000
},
{
"epoch": 25.46,
"learning_rate": 1.8173754435060716e-05,
"loss": 1.6597,
"step": 509500
},
{
"epoch": 25.49,
"learning_rate": 1.814252161311279e-05,
"loss": 1.6632,
"step": 510000
},
{
"epoch": 25.51,
"learning_rate": 1.811128879116486e-05,
"loss": 1.6531,
"step": 510500
},
{
"epoch": 25.54,
"learning_rate": 1.808005596921693e-05,
"loss": 1.6546,
"step": 511000
},
{
"epoch": 25.56,
"learning_rate": 1.8048823147269003e-05,
"loss": 1.6525,
"step": 511500
},
{
"epoch": 25.59,
"learning_rate": 1.8017590325321073e-05,
"loss": 1.6532,
"step": 512000
},
{
"epoch": 25.61,
"learning_rate": 1.7986357503373148e-05,
"loss": 1.6542,
"step": 512500
},
{
"epoch": 25.64,
"learning_rate": 1.795512468142522e-05,
"loss": 1.6598,
"step": 513000
},
{
"epoch": 25.66,
"learning_rate": 1.7923891859477286e-05,
"loss": 1.6618,
"step": 513500
},
{
"epoch": 25.69,
"learning_rate": 1.789265903752936e-05,
"loss": 1.6576,
"step": 514000
},
{
"epoch": 25.71,
"learning_rate": 1.786142621558143e-05,
"loss": 1.6603,
"step": 514500
},
{
"epoch": 25.74,
"learning_rate": 1.7830193393633502e-05,
"loss": 1.6559,
"step": 515000
},
{
"epoch": 25.76,
"learning_rate": 1.7798960571685576e-05,
"loss": 1.6562,
"step": 515500
},
{
"epoch": 25.79,
"learning_rate": 1.7767727749737644e-05,
"loss": 1.657,
"step": 516000
},
{
"epoch": 25.81,
"learning_rate": 1.7736494927789714e-05,
"loss": 1.6526,
"step": 516500
},
{
"epoch": 25.84,
"learning_rate": 1.770526210584179e-05,
"loss": 1.6514,
"step": 517000
},
{
"epoch": 25.86,
"learning_rate": 1.767402928389386e-05,
"loss": 1.6567,
"step": 517500
},
{
"epoch": 25.89,
"learning_rate": 1.764279646194593e-05,
"loss": 1.6524,
"step": 518000
},
{
"epoch": 25.91,
"learning_rate": 1.7611563639998e-05,
"loss": 1.6558,
"step": 518500
},
{
"epoch": 25.94,
"learning_rate": 1.7580330818050072e-05,
"loss": 1.6501,
"step": 519000
},
{
"epoch": 25.96,
"learning_rate": 1.7549097996102146e-05,
"loss": 1.6522,
"step": 519500
},
{
"epoch": 25.99,
"learning_rate": 1.7517865174154217e-05,
"loss": 1.6541,
"step": 520000
},
{
"epoch": 26.0,
"eval_loss": 1.6134978532791138,
"eval_runtime": 80.814,
"eval_samples_per_second": 523.919,
"eval_steps_per_second": 65.496,
"step": 520286
},
{
"epoch": 26.01,
"learning_rate": 1.7486632352206285e-05,
"loss": 1.6544,
"step": 520500
},
{
"epoch": 26.04,
"learning_rate": 1.745539953025836e-05,
"loss": 1.6469,
"step": 521000
},
{
"epoch": 26.06,
"learning_rate": 1.742416670831043e-05,
"loss": 1.6509,
"step": 521500
},
{
"epoch": 26.09,
"learning_rate": 1.73929338863625e-05,
"loss": 1.6488,
"step": 522000
},
{
"epoch": 26.11,
"learning_rate": 1.7361701064414575e-05,
"loss": 1.6514,
"step": 522500
},
{
"epoch": 26.14,
"learning_rate": 1.7330468242466642e-05,
"loss": 1.6529,
"step": 523000
},
{
"epoch": 26.16,
"learning_rate": 1.7299235420518717e-05,
"loss": 1.652,
"step": 523500
},
{
"epoch": 26.19,
"learning_rate": 1.7268002598570788e-05,
"loss": 1.6534,
"step": 524000
},
{
"epoch": 26.21,
"learning_rate": 1.723676977662286e-05,
"loss": 1.661,
"step": 524500
},
{
"epoch": 26.24,
"learning_rate": 1.720553695467493e-05,
"loss": 1.654,
"step": 525000
},
{
"epoch": 26.26,
"learning_rate": 1.7174304132727e-05,
"loss": 1.6522,
"step": 525500
},
{
"epoch": 26.29,
"learning_rate": 1.714307131077907e-05,
"loss": 1.6492,
"step": 526000
},
{
"epoch": 26.31,
"learning_rate": 1.7111838488831145e-05,
"loss": 1.6486,
"step": 526500
},
{
"epoch": 26.34,
"learning_rate": 1.7080605666883216e-05,
"loss": 1.6522,
"step": 527000
},
{
"epoch": 26.36,
"learning_rate": 1.7049372844935284e-05,
"loss": 1.6504,
"step": 527500
},
{
"epoch": 26.39,
"learning_rate": 1.7018140022987358e-05,
"loss": 1.6508,
"step": 528000
},
{
"epoch": 26.41,
"learning_rate": 1.698690720103943e-05,
"loss": 1.6495,
"step": 528500
},
{
"epoch": 26.44,
"learning_rate": 1.6955674379091503e-05,
"loss": 1.6536,
"step": 529000
},
{
"epoch": 26.46,
"learning_rate": 1.6924441557143574e-05,
"loss": 1.6523,
"step": 529500
},
{
"epoch": 26.49,
"learning_rate": 1.689320873519564e-05,
"loss": 1.6483,
"step": 530000
},
{
"epoch": 26.51,
"learning_rate": 1.6861975913247715e-05,
"loss": 1.6522,
"step": 530500
},
{
"epoch": 26.54,
"learning_rate": 1.6830743091299786e-05,
"loss": 1.6539,
"step": 531000
},
{
"epoch": 26.56,
"learning_rate": 1.6799510269351857e-05,
"loss": 1.6528,
"step": 531500
},
{
"epoch": 26.59,
"learning_rate": 1.6768277447403928e-05,
"loss": 1.6418,
"step": 532000
},
{
"epoch": 26.61,
"learning_rate": 1.6737044625456e-05,
"loss": 1.6485,
"step": 532500
},
{
"epoch": 26.64,
"learning_rate": 1.670581180350807e-05,
"loss": 1.6508,
"step": 533000
},
{
"epoch": 26.66,
"learning_rate": 1.6674578981560144e-05,
"loss": 1.6524,
"step": 533500
},
{
"epoch": 26.69,
"learning_rate": 1.6643346159612215e-05,
"loss": 1.6505,
"step": 534000
},
{
"epoch": 26.71,
"learning_rate": 1.6612113337664286e-05,
"loss": 1.6494,
"step": 534500
},
{
"epoch": 26.74,
"learning_rate": 1.6580880515716357e-05,
"loss": 1.6485,
"step": 535000
},
{
"epoch": 26.76,
"learning_rate": 1.6549647693768427e-05,
"loss": 1.6427,
"step": 535500
},
{
"epoch": 26.79,
"learning_rate": 1.6518414871820502e-05,
"loss": 1.6424,
"step": 536000
},
{
"epoch": 26.81,
"learning_rate": 1.6487182049872573e-05,
"loss": 1.6543,
"step": 536500
},
{
"epoch": 26.84,
"learning_rate": 1.645594922792464e-05,
"loss": 1.6471,
"step": 537000
},
{
"epoch": 26.86,
"learning_rate": 1.6424716405976714e-05,
"loss": 1.6454,
"step": 537500
},
{
"epoch": 26.89,
"learning_rate": 1.6393483584028785e-05,
"loss": 1.6516,
"step": 538000
},
{
"epoch": 26.91,
"learning_rate": 1.6362250762080856e-05,
"loss": 1.6434,
"step": 538500
},
{
"epoch": 26.94,
"learning_rate": 1.6331017940132927e-05,
"loss": 1.6453,
"step": 539000
},
{
"epoch": 26.96,
"learning_rate": 1.6299785118184998e-05,
"loss": 1.6504,
"step": 539500
},
{
"epoch": 26.99,
"learning_rate": 1.6268552296237072e-05,
"loss": 1.6457,
"step": 540000
},
{
"epoch": 27.0,
"eval_loss": 1.6034142971038818,
"eval_runtime": 81.7077,
"eval_samples_per_second": 518.189,
"eval_steps_per_second": 64.78,
"step": 540297
},
{
"epoch": 27.01,
"learning_rate": 1.6237319474289143e-05,
"loss": 1.6449,
"step": 540500
},
{
"epoch": 27.04,
"learning_rate": 1.6206086652341214e-05,
"loss": 1.6407,
"step": 541000
},
{
"epoch": 27.06,
"learning_rate": 1.6174853830393285e-05,
"loss": 1.6462,
"step": 541500
},
{
"epoch": 27.09,
"learning_rate": 1.6143621008445355e-05,
"loss": 1.649,
"step": 542000
},
{
"epoch": 27.11,
"learning_rate": 1.6112388186497426e-05,
"loss": 1.6426,
"step": 542500
},
{
"epoch": 27.14,
"learning_rate": 1.60811553645495e-05,
"loss": 1.641,
"step": 543000
},
{
"epoch": 27.16,
"learning_rate": 1.604992254260157e-05,
"loss": 1.6443,
"step": 543500
},
{
"epoch": 27.19,
"learning_rate": 1.601868972065364e-05,
"loss": 1.641,
"step": 544000
},
{
"epoch": 27.21,
"learning_rate": 1.5987456898705713e-05,
"loss": 1.6475,
"step": 544500
},
{
"epoch": 27.24,
"learning_rate": 1.5956224076757784e-05,
"loss": 1.6413,
"step": 545000
},
{
"epoch": 27.26,
"learning_rate": 1.5924991254809855e-05,
"loss": 1.6382,
"step": 545500
},
{
"epoch": 27.28,
"learning_rate": 1.5893758432861926e-05,
"loss": 1.638,
"step": 546000
},
{
"epoch": 27.31,
"learning_rate": 1.5862525610913997e-05,
"loss": 1.6422,
"step": 546500
},
{
"epoch": 27.33,
"learning_rate": 1.583129278896607e-05,
"loss": 1.6467,
"step": 547000
},
{
"epoch": 27.36,
"learning_rate": 1.580005996701814e-05,
"loss": 1.6412,
"step": 547500
},
{
"epoch": 27.38,
"learning_rate": 1.5768827145070212e-05,
"loss": 1.645,
"step": 548000
},
{
"epoch": 27.41,
"learning_rate": 1.5737594323122283e-05,
"loss": 1.6427,
"step": 548500
},
{
"epoch": 27.43,
"learning_rate": 1.5706361501174354e-05,
"loss": 1.6436,
"step": 549000
},
{
"epoch": 27.46,
"learning_rate": 1.5675128679226425e-05,
"loss": 1.6413,
"step": 549500
},
{
"epoch": 27.48,
"learning_rate": 1.56438958572785e-05,
"loss": 1.6444,
"step": 550000
},
{
"epoch": 27.51,
"learning_rate": 1.561266303533057e-05,
"loss": 1.6466,
"step": 550500
},
{
"epoch": 27.53,
"learning_rate": 1.5581430213382638e-05,
"loss": 1.6401,
"step": 551000
},
{
"epoch": 27.56,
"learning_rate": 1.5550197391434712e-05,
"loss": 1.6414,
"step": 551500
},
{
"epoch": 27.58,
"learning_rate": 1.5518964569486783e-05,
"loss": 1.6419,
"step": 552000
},
{
"epoch": 27.61,
"learning_rate": 1.5487731747538857e-05,
"loss": 1.6402,
"step": 552500
},
{
"epoch": 27.63,
"learning_rate": 1.5456498925590924e-05,
"loss": 1.6361,
"step": 553000
},
{
"epoch": 27.66,
"learning_rate": 1.5425266103642995e-05,
"loss": 1.6455,
"step": 553500
},
{
"epoch": 27.68,
"learning_rate": 1.539403328169507e-05,
"loss": 1.6411,
"step": 554000
},
{
"epoch": 27.71,
"learning_rate": 1.536280045974714e-05,
"loss": 1.6443,
"step": 554500
},
{
"epoch": 27.73,
"learning_rate": 1.533156763779921e-05,
"loss": 1.6412,
"step": 555000
},
{
"epoch": 27.76,
"learning_rate": 1.5300334815851282e-05,
"loss": 1.6413,
"step": 555500
},
{
"epoch": 27.78,
"learning_rate": 1.5269101993903353e-05,
"loss": 1.6384,
"step": 556000
},
{
"epoch": 27.81,
"learning_rate": 1.5237869171955424e-05,
"loss": 1.6474,
"step": 556500
},
{
"epoch": 27.83,
"learning_rate": 1.5206636350007496e-05,
"loss": 1.6401,
"step": 557000
},
{
"epoch": 27.86,
"learning_rate": 1.5175403528059567e-05,
"loss": 1.6418,
"step": 557500
},
{
"epoch": 27.88,
"learning_rate": 1.514417070611164e-05,
"loss": 1.6387,
"step": 558000
},
{
"epoch": 27.91,
"learning_rate": 1.511293788416371e-05,
"loss": 1.6474,
"step": 558500
},
{
"epoch": 27.93,
"learning_rate": 1.5081705062215782e-05,
"loss": 1.6415,
"step": 559000
},
{
"epoch": 27.96,
"learning_rate": 1.5050472240267854e-05,
"loss": 1.6414,
"step": 559500
},
{
"epoch": 27.98,
"learning_rate": 1.5019239418319925e-05,
"loss": 1.6382,
"step": 560000
}
],
"max_steps": 800440,
"num_train_epochs": 40,
"total_flos": 3.7120332229015634e+18,
"trial_name": null,
"trial_params": null
}