legal-question-filter-koelectra / trainer_state.json
kfkas's picture
Upload 7 files
b961616
{
"best_metric": 0.00564388744533062,
"best_model_checkpoint": "output_dir\\checkpoint-9188",
"epoch": 10.0,
"global_step": 22970,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 9.978232477144103e-06,
"loss": 0.5997,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 9.956464954288203e-06,
"loss": 0.5077,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 9.934697431432305e-06,
"loss": 0.4455,
"step": 150
},
{
"epoch": 0.09,
"learning_rate": 9.912929908576405e-06,
"loss": 0.3683,
"step": 200
},
{
"epoch": 0.11,
"learning_rate": 9.891162385720507e-06,
"loss": 0.2864,
"step": 250
},
{
"epoch": 0.13,
"learning_rate": 9.869394862864606e-06,
"loss": 0.2272,
"step": 300
},
{
"epoch": 0.15,
"learning_rate": 9.847627340008708e-06,
"loss": 0.1793,
"step": 350
},
{
"epoch": 0.17,
"learning_rate": 9.825859817152808e-06,
"loss": 0.1467,
"step": 400
},
{
"epoch": 0.2,
"learning_rate": 9.80409229429691e-06,
"loss": 0.1229,
"step": 450
},
{
"epoch": 0.22,
"learning_rate": 9.782324771441012e-06,
"loss": 0.0996,
"step": 500
},
{
"epoch": 0.24,
"learning_rate": 9.760557248585112e-06,
"loss": 0.092,
"step": 550
},
{
"epoch": 0.26,
"learning_rate": 9.738789725729214e-06,
"loss": 0.0771,
"step": 600
},
{
"epoch": 0.28,
"learning_rate": 9.717022202873314e-06,
"loss": 0.0597,
"step": 650
},
{
"epoch": 0.3,
"learning_rate": 9.695254680017416e-06,
"loss": 0.0536,
"step": 700
},
{
"epoch": 0.33,
"learning_rate": 9.673487157161516e-06,
"loss": 0.0514,
"step": 750
},
{
"epoch": 0.35,
"learning_rate": 9.651719634305616e-06,
"loss": 0.0447,
"step": 800
},
{
"epoch": 0.37,
"learning_rate": 9.629952111449717e-06,
"loss": 0.0444,
"step": 850
},
{
"epoch": 0.39,
"learning_rate": 9.608184588593819e-06,
"loss": 0.0363,
"step": 900
},
{
"epoch": 0.41,
"learning_rate": 9.58641706573792e-06,
"loss": 0.0395,
"step": 950
},
{
"epoch": 0.44,
"learning_rate": 9.56464954288202e-06,
"loss": 0.0444,
"step": 1000
},
{
"epoch": 0.46,
"learning_rate": 9.542882020026123e-06,
"loss": 0.0328,
"step": 1050
},
{
"epoch": 0.48,
"learning_rate": 9.521114497170223e-06,
"loss": 0.0337,
"step": 1100
},
{
"epoch": 0.5,
"learning_rate": 9.499346974314325e-06,
"loss": 0.0347,
"step": 1150
},
{
"epoch": 0.52,
"learning_rate": 9.477579451458425e-06,
"loss": 0.0262,
"step": 1200
},
{
"epoch": 0.54,
"learning_rate": 9.455811928602527e-06,
"loss": 0.0239,
"step": 1250
},
{
"epoch": 0.57,
"learning_rate": 9.434044405746625e-06,
"loss": 0.0259,
"step": 1300
},
{
"epoch": 0.59,
"learning_rate": 9.412276882890727e-06,
"loss": 0.021,
"step": 1350
},
{
"epoch": 0.61,
"learning_rate": 9.390509360034828e-06,
"loss": 0.0186,
"step": 1400
},
{
"epoch": 0.63,
"learning_rate": 9.36874183717893e-06,
"loss": 0.0207,
"step": 1450
},
{
"epoch": 0.65,
"learning_rate": 9.346974314323032e-06,
"loss": 0.017,
"step": 1500
},
{
"epoch": 0.67,
"learning_rate": 9.325206791467132e-06,
"loss": 0.0259,
"step": 1550
},
{
"epoch": 0.7,
"learning_rate": 9.303439268611234e-06,
"loss": 0.0299,
"step": 1600
},
{
"epoch": 0.72,
"learning_rate": 9.281671745755334e-06,
"loss": 0.0124,
"step": 1650
},
{
"epoch": 0.74,
"learning_rate": 9.259904222899436e-06,
"loss": 0.0155,
"step": 1700
},
{
"epoch": 0.76,
"learning_rate": 9.238136700043536e-06,
"loss": 0.0264,
"step": 1750
},
{
"epoch": 0.78,
"learning_rate": 9.216369177187638e-06,
"loss": 0.018,
"step": 1800
},
{
"epoch": 0.81,
"learning_rate": 9.194601654331737e-06,
"loss": 0.0163,
"step": 1850
},
{
"epoch": 0.83,
"learning_rate": 9.172834131475838e-06,
"loss": 0.0219,
"step": 1900
},
{
"epoch": 0.85,
"learning_rate": 9.15106660861994e-06,
"loss": 0.0164,
"step": 1950
},
{
"epoch": 0.87,
"learning_rate": 9.12929908576404e-06,
"loss": 0.026,
"step": 2000
},
{
"epoch": 0.89,
"learning_rate": 9.107531562908143e-06,
"loss": 0.0179,
"step": 2050
},
{
"epoch": 0.91,
"learning_rate": 9.085764040052243e-06,
"loss": 0.0177,
"step": 2100
},
{
"epoch": 0.94,
"learning_rate": 9.063996517196345e-06,
"loss": 0.0138,
"step": 2150
},
{
"epoch": 0.96,
"learning_rate": 9.042228994340445e-06,
"loss": 0.0134,
"step": 2200
},
{
"epoch": 0.98,
"learning_rate": 9.020461471484547e-06,
"loss": 0.0175,
"step": 2250
},
{
"epoch": 1.0,
"eval_f1": 0.998025618014196,
"eval_loss": 0.015513530932366848,
"eval_runtime": 36.185,
"eval_samples_per_second": 1015.282,
"eval_steps_per_second": 15.891,
"step": 2297
},
{
"epoch": 1.0,
"learning_rate": 8.998693948628647e-06,
"loss": 0.0105,
"step": 2300
},
{
"epoch": 1.02,
"learning_rate": 8.976926425772747e-06,
"loss": 0.0151,
"step": 2350
},
{
"epoch": 1.04,
"learning_rate": 8.95515890291685e-06,
"loss": 0.0155,
"step": 2400
},
{
"epoch": 1.07,
"learning_rate": 8.93339138006095e-06,
"loss": 0.016,
"step": 2450
},
{
"epoch": 1.09,
"learning_rate": 8.911623857205051e-06,
"loss": 0.0142,
"step": 2500
},
{
"epoch": 1.11,
"learning_rate": 8.889856334349152e-06,
"loss": 0.0211,
"step": 2550
},
{
"epoch": 1.13,
"learning_rate": 8.868088811493254e-06,
"loss": 0.0166,
"step": 2600
},
{
"epoch": 1.15,
"learning_rate": 8.846321288637354e-06,
"loss": 0.0195,
"step": 2650
},
{
"epoch": 1.18,
"learning_rate": 8.824553765781456e-06,
"loss": 0.0181,
"step": 2700
},
{
"epoch": 1.2,
"learning_rate": 8.802786242925556e-06,
"loss": 0.0137,
"step": 2750
},
{
"epoch": 1.22,
"learning_rate": 8.781018720069658e-06,
"loss": 0.0092,
"step": 2800
},
{
"epoch": 1.24,
"learning_rate": 8.759251197213758e-06,
"loss": 0.0153,
"step": 2850
},
{
"epoch": 1.26,
"learning_rate": 8.737483674357858e-06,
"loss": 0.0098,
"step": 2900
},
{
"epoch": 1.28,
"learning_rate": 8.71571615150196e-06,
"loss": 0.0116,
"step": 2950
},
{
"epoch": 1.31,
"learning_rate": 8.69394862864606e-06,
"loss": 0.0125,
"step": 3000
},
{
"epoch": 1.33,
"learning_rate": 8.672181105790162e-06,
"loss": 0.0169,
"step": 3050
},
{
"epoch": 1.35,
"learning_rate": 8.650413582934263e-06,
"loss": 0.0191,
"step": 3100
},
{
"epoch": 1.37,
"learning_rate": 8.628646060078365e-06,
"loss": 0.0135,
"step": 3150
},
{
"epoch": 1.39,
"learning_rate": 8.606878537222465e-06,
"loss": 0.0104,
"step": 3200
},
{
"epoch": 1.41,
"learning_rate": 8.585111014366567e-06,
"loss": 0.0074,
"step": 3250
},
{
"epoch": 1.44,
"learning_rate": 8.563343491510667e-06,
"loss": 0.0165,
"step": 3300
},
{
"epoch": 1.46,
"learning_rate": 8.541575968654767e-06,
"loss": 0.01,
"step": 3350
},
{
"epoch": 1.48,
"learning_rate": 8.519808445798869e-06,
"loss": 0.0092,
"step": 3400
},
{
"epoch": 1.5,
"learning_rate": 8.49804092294297e-06,
"loss": 0.0127,
"step": 3450
},
{
"epoch": 1.52,
"learning_rate": 8.476273400087071e-06,
"loss": 0.0123,
"step": 3500
},
{
"epoch": 1.55,
"learning_rate": 8.454505877231172e-06,
"loss": 0.0096,
"step": 3550
},
{
"epoch": 1.57,
"learning_rate": 8.432738354375273e-06,
"loss": 0.0095,
"step": 3600
},
{
"epoch": 1.59,
"learning_rate": 8.410970831519374e-06,
"loss": 0.0109,
"step": 3650
},
{
"epoch": 1.61,
"learning_rate": 8.389203308663476e-06,
"loss": 0.0086,
"step": 3700
},
{
"epoch": 1.63,
"learning_rate": 8.367435785807576e-06,
"loss": 0.0108,
"step": 3750
},
{
"epoch": 1.65,
"learning_rate": 8.345668262951678e-06,
"loss": 0.0077,
"step": 3800
},
{
"epoch": 1.68,
"learning_rate": 8.323900740095778e-06,
"loss": 0.0091,
"step": 3850
},
{
"epoch": 1.7,
"learning_rate": 8.302133217239878e-06,
"loss": 0.013,
"step": 3900
},
{
"epoch": 1.72,
"learning_rate": 8.28036569438398e-06,
"loss": 0.0147,
"step": 3950
},
{
"epoch": 1.74,
"learning_rate": 8.25859817152808e-06,
"loss": 0.0153,
"step": 4000
},
{
"epoch": 1.76,
"learning_rate": 8.236830648672182e-06,
"loss": 0.0103,
"step": 4050
},
{
"epoch": 1.78,
"learning_rate": 8.215063125816283e-06,
"loss": 0.0101,
"step": 4100
},
{
"epoch": 1.81,
"learning_rate": 8.193295602960384e-06,
"loss": 0.0049,
"step": 4150
},
{
"epoch": 1.83,
"learning_rate": 8.171528080104485e-06,
"loss": 0.008,
"step": 4200
},
{
"epoch": 1.85,
"learning_rate": 8.149760557248587e-06,
"loss": 0.0126,
"step": 4250
},
{
"epoch": 1.87,
"learning_rate": 8.127993034392687e-06,
"loss": 0.0124,
"step": 4300
},
{
"epoch": 1.89,
"learning_rate": 8.106225511536789e-06,
"loss": 0.0111,
"step": 4350
},
{
"epoch": 1.92,
"learning_rate": 8.084457988680889e-06,
"loss": 0.0137,
"step": 4400
},
{
"epoch": 1.94,
"learning_rate": 8.06269046582499e-06,
"loss": 0.0148,
"step": 4450
},
{
"epoch": 1.96,
"learning_rate": 8.040922942969091e-06,
"loss": 0.0154,
"step": 4500
},
{
"epoch": 1.98,
"learning_rate": 8.019155420113191e-06,
"loss": 0.0104,
"step": 4550
},
{
"epoch": 2.0,
"eval_f1": 0.9987417272652994,
"eval_loss": 0.008711813017725945,
"eval_runtime": 35.665,
"eval_samples_per_second": 1030.086,
"eval_steps_per_second": 16.122,
"step": 4594
},
{
"epoch": 2.0,
"learning_rate": 7.997387897257293e-06,
"loss": 0.0077,
"step": 4600
},
{
"epoch": 2.02,
"learning_rate": 7.975620374401394e-06,
"loss": 0.0081,
"step": 4650
},
{
"epoch": 2.05,
"learning_rate": 7.953852851545496e-06,
"loss": 0.0071,
"step": 4700
},
{
"epoch": 2.07,
"learning_rate": 7.932085328689596e-06,
"loss": 0.0164,
"step": 4750
},
{
"epoch": 2.09,
"learning_rate": 7.910317805833698e-06,
"loss": 0.0096,
"step": 4800
},
{
"epoch": 2.11,
"learning_rate": 7.888550282977798e-06,
"loss": 0.0139,
"step": 4850
},
{
"epoch": 2.13,
"learning_rate": 7.866782760121898e-06,
"loss": 0.0068,
"step": 4900
},
{
"epoch": 2.15,
"learning_rate": 7.845015237266e-06,
"loss": 0.0079,
"step": 4950
},
{
"epoch": 2.18,
"learning_rate": 7.8232477144101e-06,
"loss": 0.0084,
"step": 5000
},
{
"epoch": 2.2,
"learning_rate": 7.801480191554202e-06,
"loss": 0.0008,
"step": 5050
},
{
"epoch": 2.22,
"learning_rate": 7.779712668698302e-06,
"loss": 0.01,
"step": 5100
},
{
"epoch": 2.24,
"learning_rate": 7.757945145842404e-06,
"loss": 0.0094,
"step": 5150
},
{
"epoch": 2.26,
"learning_rate": 7.736177622986505e-06,
"loss": 0.0094,
"step": 5200
},
{
"epoch": 2.29,
"learning_rate": 7.714410100130607e-06,
"loss": 0.0116,
"step": 5250
},
{
"epoch": 2.31,
"learning_rate": 7.692642577274707e-06,
"loss": 0.0055,
"step": 5300
},
{
"epoch": 2.33,
"learning_rate": 7.670875054418809e-06,
"loss": 0.0047,
"step": 5350
},
{
"epoch": 2.35,
"learning_rate": 7.649107531562909e-06,
"loss": 0.0102,
"step": 5400
},
{
"epoch": 2.37,
"learning_rate": 7.627340008707009e-06,
"loss": 0.0095,
"step": 5450
},
{
"epoch": 2.39,
"learning_rate": 7.60557248585111e-06,
"loss": 0.0136,
"step": 5500
},
{
"epoch": 2.42,
"learning_rate": 7.583804962995211e-06,
"loss": 0.0086,
"step": 5550
},
{
"epoch": 2.44,
"learning_rate": 7.562037440139312e-06,
"loss": 0.0024,
"step": 5600
},
{
"epoch": 2.46,
"learning_rate": 7.5402699172834135e-06,
"loss": 0.0064,
"step": 5650
},
{
"epoch": 2.48,
"learning_rate": 7.5185023944275146e-06,
"loss": 0.0091,
"step": 5700
},
{
"epoch": 2.5,
"learning_rate": 7.496734871571616e-06,
"loss": 0.0045,
"step": 5750
},
{
"epoch": 2.53,
"learning_rate": 7.474967348715717e-06,
"loss": 0.0031,
"step": 5800
},
{
"epoch": 2.55,
"learning_rate": 7.453199825859818e-06,
"loss": 0.0098,
"step": 5850
},
{
"epoch": 2.57,
"learning_rate": 7.431432303003919e-06,
"loss": 0.0055,
"step": 5900
},
{
"epoch": 2.59,
"learning_rate": 7.409664780148019e-06,
"loss": 0.0064,
"step": 5950
},
{
"epoch": 2.61,
"learning_rate": 7.38789725729212e-06,
"loss": 0.0085,
"step": 6000
},
{
"epoch": 2.63,
"learning_rate": 7.366129734436221e-06,
"loss": 0.0096,
"step": 6050
},
{
"epoch": 2.66,
"learning_rate": 7.344362211580322e-06,
"loss": 0.0102,
"step": 6100
},
{
"epoch": 2.68,
"learning_rate": 7.3225946887244234e-06,
"loss": 0.0069,
"step": 6150
},
{
"epoch": 2.7,
"learning_rate": 7.3008271658685245e-06,
"loss": 0.0069,
"step": 6200
},
{
"epoch": 2.72,
"learning_rate": 7.279059643012626e-06,
"loss": 0.0071,
"step": 6250
},
{
"epoch": 2.74,
"learning_rate": 7.257292120156727e-06,
"loss": 0.0114,
"step": 6300
},
{
"epoch": 2.76,
"learning_rate": 7.235524597300828e-06,
"loss": 0.0083,
"step": 6350
},
{
"epoch": 2.79,
"learning_rate": 7.213757074444929e-06,
"loss": 0.0101,
"step": 6400
},
{
"epoch": 2.81,
"learning_rate": 7.191989551589029e-06,
"loss": 0.0109,
"step": 6450
},
{
"epoch": 2.83,
"learning_rate": 7.17022202873313e-06,
"loss": 0.0064,
"step": 6500
},
{
"epoch": 2.85,
"learning_rate": 7.148454505877231e-06,
"loss": 0.0047,
"step": 6550
},
{
"epoch": 2.87,
"learning_rate": 7.126686983021332e-06,
"loss": 0.0076,
"step": 6600
},
{
"epoch": 2.9,
"learning_rate": 7.104919460165433e-06,
"loss": 0.0133,
"step": 6650
},
{
"epoch": 2.92,
"learning_rate": 7.0831519373095345e-06,
"loss": 0.0054,
"step": 6700
},
{
"epoch": 2.94,
"learning_rate": 7.0613844144536355e-06,
"loss": 0.0108,
"step": 6750
},
{
"epoch": 2.96,
"learning_rate": 7.039616891597737e-06,
"loss": 0.0047,
"step": 6800
},
{
"epoch": 2.98,
"learning_rate": 7.017849368741838e-06,
"loss": 0.0088,
"step": 6850
},
{
"epoch": 3.0,
"eval_f1": 0.9989708741035986,
"eval_loss": 0.007210045587271452,
"eval_runtime": 34.5277,
"eval_samples_per_second": 1064.015,
"eval_steps_per_second": 16.653,
"step": 6891
},
{
"epoch": 3.0,
"learning_rate": 6.996081845885939e-06,
"loss": 0.0043,
"step": 6900
},
{
"epoch": 3.03,
"learning_rate": 6.974314323030041e-06,
"loss": 0.0019,
"step": 6950
},
{
"epoch": 3.05,
"learning_rate": 6.95254680017414e-06,
"loss": 0.0081,
"step": 7000
},
{
"epoch": 3.07,
"learning_rate": 6.930779277318241e-06,
"loss": 0.0078,
"step": 7050
},
{
"epoch": 3.09,
"learning_rate": 6.909011754462342e-06,
"loss": 0.0062,
"step": 7100
},
{
"epoch": 3.11,
"learning_rate": 6.887244231606443e-06,
"loss": 0.007,
"step": 7150
},
{
"epoch": 3.13,
"learning_rate": 6.865476708750544e-06,
"loss": 0.0047,
"step": 7200
},
{
"epoch": 3.16,
"learning_rate": 6.8437091858946455e-06,
"loss": 0.005,
"step": 7250
},
{
"epoch": 3.18,
"learning_rate": 6.8219416630387466e-06,
"loss": 0.0056,
"step": 7300
},
{
"epoch": 3.2,
"learning_rate": 6.800174140182848e-06,
"loss": 0.0024,
"step": 7350
},
{
"epoch": 3.22,
"learning_rate": 6.77840661732695e-06,
"loss": 0.005,
"step": 7400
},
{
"epoch": 3.24,
"learning_rate": 6.756639094471051e-06,
"loss": 0.0042,
"step": 7450
},
{
"epoch": 3.27,
"learning_rate": 6.73487157161515e-06,
"loss": 0.0057,
"step": 7500
},
{
"epoch": 3.29,
"learning_rate": 6.713104048759251e-06,
"loss": 0.0015,
"step": 7550
},
{
"epoch": 3.31,
"learning_rate": 6.691336525903352e-06,
"loss": 0.0017,
"step": 7600
},
{
"epoch": 3.33,
"learning_rate": 6.669569003047453e-06,
"loss": 0.0057,
"step": 7650
},
{
"epoch": 3.35,
"learning_rate": 6.647801480191554e-06,
"loss": 0.0025,
"step": 7700
},
{
"epoch": 3.37,
"learning_rate": 6.6260339573356554e-06,
"loss": 0.0075,
"step": 7750
},
{
"epoch": 3.4,
"learning_rate": 6.6042664344797565e-06,
"loss": 0.0059,
"step": 7800
},
{
"epoch": 3.42,
"learning_rate": 6.582498911623858e-06,
"loss": 0.006,
"step": 7850
},
{
"epoch": 3.44,
"learning_rate": 6.5607313887679595e-06,
"loss": 0.0053,
"step": 7900
},
{
"epoch": 3.46,
"learning_rate": 6.538963865912061e-06,
"loss": 0.0116,
"step": 7950
},
{
"epoch": 3.48,
"learning_rate": 6.51719634305616e-06,
"loss": 0.0038,
"step": 8000
},
{
"epoch": 3.5,
"learning_rate": 6.495428820200261e-06,
"loss": 0.0078,
"step": 8050
},
{
"epoch": 3.53,
"learning_rate": 6.473661297344362e-06,
"loss": 0.0071,
"step": 8100
},
{
"epoch": 3.55,
"learning_rate": 6.451893774488463e-06,
"loss": 0.0105,
"step": 8150
},
{
"epoch": 3.57,
"learning_rate": 6.430126251632564e-06,
"loss": 0.0116,
"step": 8200
},
{
"epoch": 3.59,
"learning_rate": 6.408358728776665e-06,
"loss": 0.0076,
"step": 8250
},
{
"epoch": 3.61,
"learning_rate": 6.3865912059207665e-06,
"loss": 0.0029,
"step": 8300
},
{
"epoch": 3.64,
"learning_rate": 6.364823683064868e-06,
"loss": 0.0098,
"step": 8350
},
{
"epoch": 3.66,
"learning_rate": 6.3430561602089695e-06,
"loss": 0.0084,
"step": 8400
},
{
"epoch": 3.68,
"learning_rate": 6.3212886373530706e-06,
"loss": 0.0068,
"step": 8450
},
{
"epoch": 3.7,
"learning_rate": 6.29952111449717e-06,
"loss": 0.0071,
"step": 8500
},
{
"epoch": 3.72,
"learning_rate": 6.277753591641271e-06,
"loss": 0.0056,
"step": 8550
},
{
"epoch": 3.74,
"learning_rate": 6.255986068785372e-06,
"loss": 0.0085,
"step": 8600
},
{
"epoch": 3.77,
"learning_rate": 6.234218545929473e-06,
"loss": 0.0014,
"step": 8650
},
{
"epoch": 3.79,
"learning_rate": 6.212451023073574e-06,
"loss": 0.0068,
"step": 8700
},
{
"epoch": 3.81,
"learning_rate": 6.190683500217675e-06,
"loss": 0.0091,
"step": 8750
},
{
"epoch": 3.83,
"learning_rate": 6.168915977361776e-06,
"loss": 0.0043,
"step": 8800
},
{
"epoch": 3.85,
"learning_rate": 6.147148454505878e-06,
"loss": 0.0068,
"step": 8850
},
{
"epoch": 3.87,
"learning_rate": 6.1253809316499794e-06,
"loss": 0.0046,
"step": 8900
},
{
"epoch": 3.9,
"learning_rate": 6.1036134087940805e-06,
"loss": 0.008,
"step": 8950
},
{
"epoch": 3.92,
"learning_rate": 6.081845885938182e-06,
"loss": 0.0076,
"step": 9000
},
{
"epoch": 3.94,
"learning_rate": 6.060078363082281e-06,
"loss": 0.0049,
"step": 9050
},
{
"epoch": 3.96,
"learning_rate": 6.038310840226382e-06,
"loss": 0.0073,
"step": 9100
},
{
"epoch": 3.98,
"learning_rate": 6.016543317370483e-06,
"loss": 0.0073,
"step": 9150
},
{
"epoch": 4.0,
"eval_f1": 0.9991011162501838,
"eval_loss": 0.00564388744533062,
"eval_runtime": 36.1615,
"eval_samples_per_second": 1015.942,
"eval_steps_per_second": 15.901,
"step": 9188
},
{
"epoch": 4.01,
"learning_rate": 5.994775794514584e-06,
"loss": 0.004,
"step": 9200
},
{
"epoch": 4.03,
"learning_rate": 5.973008271658685e-06,
"loss": 0.0011,
"step": 9250
},
{
"epoch": 4.05,
"learning_rate": 5.951240748802787e-06,
"loss": 0.0039,
"step": 9300
},
{
"epoch": 4.07,
"learning_rate": 5.929473225946888e-06,
"loss": 0.0087,
"step": 9350
},
{
"epoch": 4.09,
"learning_rate": 5.907705703090989e-06,
"loss": 0.0047,
"step": 9400
},
{
"epoch": 4.11,
"learning_rate": 5.8859381802350905e-06,
"loss": 0.0026,
"step": 9450
},
{
"epoch": 4.14,
"learning_rate": 5.8641706573791915e-06,
"loss": 0.0054,
"step": 9500
},
{
"epoch": 4.16,
"learning_rate": 5.842403134523291e-06,
"loss": 0.0049,
"step": 9550
},
{
"epoch": 4.18,
"learning_rate": 5.820635611667392e-06,
"loss": 0.003,
"step": 9600
},
{
"epoch": 4.2,
"learning_rate": 5.798868088811493e-06,
"loss": 0.0053,
"step": 9650
},
{
"epoch": 4.22,
"learning_rate": 5.777100565955594e-06,
"loss": 0.0002,
"step": 9700
},
{
"epoch": 4.24,
"learning_rate": 5.755333043099695e-06,
"loss": 0.003,
"step": 9750
},
{
"epoch": 4.27,
"learning_rate": 5.733565520243797e-06,
"loss": 0.0095,
"step": 9800
},
{
"epoch": 4.29,
"learning_rate": 5.711797997387898e-06,
"loss": 0.0023,
"step": 9850
},
{
"epoch": 4.31,
"learning_rate": 5.690030474531999e-06,
"loss": 0.0033,
"step": 9900
},
{
"epoch": 4.33,
"learning_rate": 5.6682629516761e-06,
"loss": 0.0036,
"step": 9950
},
{
"epoch": 4.35,
"learning_rate": 5.6464954288202015e-06,
"loss": 0.0078,
"step": 10000
},
{
"epoch": 4.38,
"learning_rate": 5.624727905964301e-06,
"loss": 0.0092,
"step": 10050
},
{
"epoch": 4.4,
"learning_rate": 5.602960383108402e-06,
"loss": 0.0052,
"step": 10100
},
{
"epoch": 4.42,
"learning_rate": 5.581192860252503e-06,
"loss": 0.0018,
"step": 10150
},
{
"epoch": 4.44,
"learning_rate": 5.559425337396604e-06,
"loss": 0.0033,
"step": 10200
},
{
"epoch": 4.46,
"learning_rate": 5.537657814540706e-06,
"loss": 0.0054,
"step": 10250
},
{
"epoch": 4.48,
"learning_rate": 5.515890291684807e-06,
"loss": 0.0069,
"step": 10300
},
{
"epoch": 4.51,
"learning_rate": 5.494122768828908e-06,
"loss": 0.0062,
"step": 10350
},
{
"epoch": 4.53,
"learning_rate": 5.472355245973009e-06,
"loss": 0.0014,
"step": 10400
},
{
"epoch": 4.55,
"learning_rate": 5.45058772311711e-06,
"loss": 0.0048,
"step": 10450
},
{
"epoch": 4.57,
"learning_rate": 5.4288202002612114e-06,
"loss": 0.0037,
"step": 10500
},
{
"epoch": 4.59,
"learning_rate": 5.4070526774053125e-06,
"loss": 0.0037,
"step": 10550
},
{
"epoch": 4.61,
"learning_rate": 5.385285154549412e-06,
"loss": 0.0042,
"step": 10600
},
{
"epoch": 4.64,
"learning_rate": 5.363517631693513e-06,
"loss": 0.0011,
"step": 10650
},
{
"epoch": 4.66,
"learning_rate": 5.341750108837614e-06,
"loss": 0.0035,
"step": 10700
},
{
"epoch": 4.68,
"learning_rate": 5.319982585981716e-06,
"loss": 0.0036,
"step": 10750
},
{
"epoch": 4.7,
"learning_rate": 5.298215063125817e-06,
"loss": 0.0063,
"step": 10800
},
{
"epoch": 4.72,
"learning_rate": 5.276447540269918e-06,
"loss": 0.0048,
"step": 10850
},
{
"epoch": 4.75,
"learning_rate": 5.254680017414019e-06,
"loss": 0.004,
"step": 10900
},
{
"epoch": 4.77,
"learning_rate": 5.23291249455812e-06,
"loss": 0.0055,
"step": 10950
},
{
"epoch": 4.79,
"learning_rate": 5.211144971702221e-06,
"loss": 0.006,
"step": 11000
},
{
"epoch": 4.81,
"learning_rate": 5.1893774488463225e-06,
"loss": 0.0068,
"step": 11050
},
{
"epoch": 4.83,
"learning_rate": 5.167609925990422e-06,
"loss": 0.0043,
"step": 11100
},
{
"epoch": 4.85,
"learning_rate": 5.145842403134523e-06,
"loss": 0.0036,
"step": 11150
},
{
"epoch": 4.88,
"learning_rate": 5.124074880278625e-06,
"loss": 0.0007,
"step": 11200
},
{
"epoch": 4.9,
"learning_rate": 5.102307357422726e-06,
"loss": 0.0034,
"step": 11250
},
{
"epoch": 4.92,
"learning_rate": 5.080539834566827e-06,
"loss": 0.0063,
"step": 11300
},
{
"epoch": 4.94,
"learning_rate": 5.058772311710928e-06,
"loss": 0.0003,
"step": 11350
},
{
"epoch": 4.96,
"learning_rate": 5.037004788855029e-06,
"loss": 0.0042,
"step": 11400
},
{
"epoch": 4.98,
"learning_rate": 5.01523726599913e-06,
"loss": 0.0086,
"step": 11450
},
{
"epoch": 5.0,
"eval_f1": 0.9988390915482595,
"eval_loss": 0.008038449101150036,
"eval_runtime": 35.4168,
"eval_samples_per_second": 1037.303,
"eval_steps_per_second": 16.235,
"step": 11485
},
{
"epoch": 5.01,
"learning_rate": 4.9934697431432305e-06,
"loss": 0.0026,
"step": 11500
},
{
"epoch": 5.03,
"learning_rate": 4.9717022202873316e-06,
"loss": 0.0005,
"step": 11550
},
{
"epoch": 5.05,
"learning_rate": 4.949934697431433e-06,
"loss": 0.0009,
"step": 11600
},
{
"epoch": 5.07,
"learning_rate": 4.928167174575534e-06,
"loss": 0.0026,
"step": 11650
},
{
"epoch": 5.09,
"learning_rate": 4.906399651719635e-06,
"loss": 0.0026,
"step": 11700
},
{
"epoch": 5.12,
"learning_rate": 4.884632128863736e-06,
"loss": 0.0095,
"step": 11750
},
{
"epoch": 5.14,
"learning_rate": 4.862864606007837e-06,
"loss": 0.0036,
"step": 11800
},
{
"epoch": 5.16,
"learning_rate": 4.841097083151938e-06,
"loss": 0.0001,
"step": 11850
},
{
"epoch": 5.18,
"learning_rate": 4.819329560296039e-06,
"loss": 0.0036,
"step": 11900
},
{
"epoch": 5.2,
"learning_rate": 4.79756203744014e-06,
"loss": 0.0086,
"step": 11950
},
{
"epoch": 5.22,
"learning_rate": 4.7757945145842404e-06,
"loss": 0.0046,
"step": 12000
},
{
"epoch": 5.25,
"learning_rate": 4.7540269917283415e-06,
"loss": 0.0015,
"step": 12050
},
{
"epoch": 5.27,
"learning_rate": 4.732259468872443e-06,
"loss": 0.0018,
"step": 12100
},
{
"epoch": 5.29,
"learning_rate": 4.710491946016544e-06,
"loss": 0.0041,
"step": 12150
},
{
"epoch": 5.31,
"learning_rate": 4.688724423160645e-06,
"loss": 0.0036,
"step": 12200
},
{
"epoch": 5.33,
"learning_rate": 4.666956900304746e-06,
"loss": 0.0063,
"step": 12250
},
{
"epoch": 5.35,
"learning_rate": 4.645189377448847e-06,
"loss": 0.0036,
"step": 12300
},
{
"epoch": 5.38,
"learning_rate": 4.623421854592948e-06,
"loss": 0.002,
"step": 12350
},
{
"epoch": 5.4,
"learning_rate": 4.601654331737049e-06,
"loss": 0.0006,
"step": 12400
},
{
"epoch": 5.42,
"learning_rate": 4.57988680888115e-06,
"loss": 0.0041,
"step": 12450
},
{
"epoch": 5.44,
"learning_rate": 4.55811928602525e-06,
"loss": 0.002,
"step": 12500
},
{
"epoch": 5.46,
"learning_rate": 4.5363517631693515e-06,
"loss": 0.0053,
"step": 12550
},
{
"epoch": 5.49,
"learning_rate": 4.5145842403134525e-06,
"loss": 0.0027,
"step": 12600
},
{
"epoch": 5.51,
"learning_rate": 4.492816717457554e-06,
"loss": 0.0056,
"step": 12650
},
{
"epoch": 5.53,
"learning_rate": 4.471049194601655e-06,
"loss": 0.002,
"step": 12700
},
{
"epoch": 5.55,
"learning_rate": 4.449281671745756e-06,
"loss": 0.0007,
"step": 12750
},
{
"epoch": 5.57,
"learning_rate": 4.427514148889857e-06,
"loss": 0.0026,
"step": 12800
},
{
"epoch": 5.59,
"learning_rate": 4.405746626033958e-06,
"loss": 0.0021,
"step": 12850
},
{
"epoch": 5.62,
"learning_rate": 4.383979103178059e-06,
"loss": 0.001,
"step": 12900
},
{
"epoch": 5.64,
"learning_rate": 4.36221158032216e-06,
"loss": 0.0043,
"step": 12950
},
{
"epoch": 5.66,
"learning_rate": 4.340444057466261e-06,
"loss": 0.0009,
"step": 13000
},
{
"epoch": 5.68,
"learning_rate": 4.318676534610361e-06,
"loss": 0.0073,
"step": 13050
},
{
"epoch": 5.7,
"learning_rate": 4.2969090117544625e-06,
"loss": 0.0039,
"step": 13100
},
{
"epoch": 5.72,
"learning_rate": 4.2751414888985636e-06,
"loss": 0.004,
"step": 13150
},
{
"epoch": 5.75,
"learning_rate": 4.253373966042665e-06,
"loss": 0.0024,
"step": 13200
},
{
"epoch": 5.77,
"learning_rate": 4.231606443186766e-06,
"loss": 0.0015,
"step": 13250
},
{
"epoch": 5.79,
"learning_rate": 4.209838920330867e-06,
"loss": 0.0015,
"step": 13300
},
{
"epoch": 5.81,
"learning_rate": 4.188071397474968e-06,
"loss": 0.0061,
"step": 13350
},
{
"epoch": 5.83,
"learning_rate": 4.166303874619069e-06,
"loss": 0.0027,
"step": 13400
},
{
"epoch": 5.86,
"learning_rate": 4.14453635176317e-06,
"loss": 0.0044,
"step": 13450
},
{
"epoch": 5.88,
"learning_rate": 4.122768828907271e-06,
"loss": 0.004,
"step": 13500
},
{
"epoch": 5.9,
"learning_rate": 4.101001306051371e-06,
"loss": 0.0018,
"step": 13550
},
{
"epoch": 5.92,
"learning_rate": 4.0792337831954724e-06,
"loss": 0.003,
"step": 13600
},
{
"epoch": 5.94,
"learning_rate": 4.0574662603395735e-06,
"loss": 0.0015,
"step": 13650
},
{
"epoch": 5.96,
"learning_rate": 4.035698737483675e-06,
"loss": 0.0072,
"step": 13700
},
{
"epoch": 5.99,
"learning_rate": 4.013931214627776e-06,
"loss": 0.001,
"step": 13750
},
{
"epoch": 6.0,
"eval_f1": 0.9992156862745099,
"eval_loss": 0.006630082614719868,
"eval_runtime": 34.2419,
"eval_samples_per_second": 1072.896,
"eval_steps_per_second": 16.792,
"step": 13782
},
{
"epoch": 6.01,
"learning_rate": 3.992163691771877e-06,
"loss": 0.0017,
"step": 13800
},
{
"epoch": 6.03,
"learning_rate": 3.970396168915978e-06,
"loss": 0.0016,
"step": 13850
},
{
"epoch": 6.05,
"learning_rate": 3.948628646060079e-06,
"loss": 0.0068,
"step": 13900
},
{
"epoch": 6.07,
"learning_rate": 3.92686112320418e-06,
"loss": 0.006,
"step": 13950
},
{
"epoch": 6.09,
"learning_rate": 3.905093600348281e-06,
"loss": 0.0032,
"step": 14000
},
{
"epoch": 6.12,
"learning_rate": 3.883326077492381e-06,
"loss": 0.0055,
"step": 14050
},
{
"epoch": 6.14,
"learning_rate": 3.861558554636482e-06,
"loss": 0.0002,
"step": 14100
},
{
"epoch": 6.16,
"learning_rate": 3.8397910317805835e-06,
"loss": 0.0009,
"step": 14150
},
{
"epoch": 6.18,
"learning_rate": 3.8180235089246845e-06,
"loss": 0.0022,
"step": 14200
},
{
"epoch": 6.2,
"learning_rate": 3.796255986068786e-06,
"loss": 0.0039,
"step": 14250
},
{
"epoch": 6.23,
"learning_rate": 3.7744884632128863e-06,
"loss": 0.0039,
"step": 14300
},
{
"epoch": 6.25,
"learning_rate": 3.7527209403569874e-06,
"loss": 0.0045,
"step": 14350
},
{
"epoch": 6.27,
"learning_rate": 3.7309534175010884e-06,
"loss": 0.0024,
"step": 14400
},
{
"epoch": 6.29,
"learning_rate": 3.70918589464519e-06,
"loss": 0.0027,
"step": 14450
},
{
"epoch": 6.31,
"learning_rate": 3.687418371789291e-06,
"loss": 0.0054,
"step": 14500
},
{
"epoch": 6.33,
"learning_rate": 3.6656508489333912e-06,
"loss": 0.0038,
"step": 14550
},
{
"epoch": 6.36,
"learning_rate": 3.6438833260774923e-06,
"loss": 0.001,
"step": 14600
},
{
"epoch": 6.38,
"learning_rate": 3.6221158032215934e-06,
"loss": 0.0039,
"step": 14650
},
{
"epoch": 6.4,
"learning_rate": 3.600348280365695e-06,
"loss": 0.0018,
"step": 14700
},
{
"epoch": 6.42,
"learning_rate": 3.578580757509796e-06,
"loss": 0.0002,
"step": 14750
},
{
"epoch": 6.44,
"learning_rate": 3.556813234653897e-06,
"loss": 0.0009,
"step": 14800
},
{
"epoch": 6.46,
"learning_rate": 3.5350457117979973e-06,
"loss": 0.0008,
"step": 14850
},
{
"epoch": 6.49,
"learning_rate": 3.513278188942099e-06,
"loss": 0.0032,
"step": 14900
},
{
"epoch": 6.51,
"learning_rate": 3.4915106660862e-06,
"loss": 0.0004,
"step": 14950
},
{
"epoch": 6.53,
"learning_rate": 3.469743143230301e-06,
"loss": 0.0003,
"step": 15000
},
{
"epoch": 6.55,
"learning_rate": 3.447975620374402e-06,
"loss": 0.0012,
"step": 15050
},
{
"epoch": 6.57,
"learning_rate": 3.4262080975185023e-06,
"loss": 0.0014,
"step": 15100
},
{
"epoch": 6.6,
"learning_rate": 3.4044405746626038e-06,
"loss": 0.0003,
"step": 15150
},
{
"epoch": 6.62,
"learning_rate": 3.382673051806705e-06,
"loss": 0.0063,
"step": 15200
},
{
"epoch": 6.64,
"learning_rate": 3.360905528950806e-06,
"loss": 0.0043,
"step": 15250
},
{
"epoch": 6.66,
"learning_rate": 3.339138006094907e-06,
"loss": 0.003,
"step": 15300
},
{
"epoch": 6.68,
"learning_rate": 3.3173704832390073e-06,
"loss": 0.0061,
"step": 15350
},
{
"epoch": 6.7,
"learning_rate": 3.2956029603831088e-06,
"loss": 0.0005,
"step": 15400
},
{
"epoch": 6.73,
"learning_rate": 3.27383543752721e-06,
"loss": 0.003,
"step": 15450
},
{
"epoch": 6.75,
"learning_rate": 3.252067914671311e-06,
"loss": 0.0057,
"step": 15500
},
{
"epoch": 6.77,
"learning_rate": 3.230300391815412e-06,
"loss": 0.0017,
"step": 15550
},
{
"epoch": 6.79,
"learning_rate": 3.2085328689595122e-06,
"loss": 0.0041,
"step": 15600
},
{
"epoch": 6.81,
"learning_rate": 3.1867653461036137e-06,
"loss": 0.0009,
"step": 15650
},
{
"epoch": 6.84,
"learning_rate": 3.164997823247715e-06,
"loss": 0.0026,
"step": 15700
},
{
"epoch": 6.86,
"learning_rate": 3.143230300391816e-06,
"loss": 0.0034,
"step": 15750
},
{
"epoch": 6.88,
"learning_rate": 3.121462777535917e-06,
"loss": 0.0008,
"step": 15800
},
{
"epoch": 6.9,
"learning_rate": 3.0996952546800176e-06,
"loss": 0.0012,
"step": 15850
},
{
"epoch": 6.92,
"learning_rate": 3.0779277318241187e-06,
"loss": 0.0012,
"step": 15900
},
{
"epoch": 6.94,
"learning_rate": 3.0561602089682198e-06,
"loss": 0.0034,
"step": 15950
},
{
"epoch": 6.97,
"learning_rate": 3.034392686112321e-06,
"loss": 0.0039,
"step": 16000
},
{
"epoch": 6.99,
"learning_rate": 3.012625163256422e-06,
"loss": 0.0001,
"step": 16050
},
{
"epoch": 7.0,
"eval_f1": 0.9990852961353762,
"eval_loss": 0.007986071519553661,
"eval_runtime": 33.4792,
"eval_samples_per_second": 1097.337,
"eval_steps_per_second": 17.175,
"step": 16079
},
{
"epoch": 7.01,
"learning_rate": 2.9908576404005226e-06,
"loss": 0.0021,
"step": 16100
},
{
"epoch": 7.03,
"learning_rate": 2.9690901175446237e-06,
"loss": 0.001,
"step": 16150
},
{
"epoch": 7.05,
"learning_rate": 2.9473225946887248e-06,
"loss": 0.0024,
"step": 16200
},
{
"epoch": 7.07,
"learning_rate": 2.925555071832826e-06,
"loss": 0.0024,
"step": 16250
},
{
"epoch": 7.1,
"learning_rate": 2.903787548976927e-06,
"loss": 0.0028,
"step": 16300
},
{
"epoch": 7.12,
"learning_rate": 2.882020026121028e-06,
"loss": 0.0004,
"step": 16350
},
{
"epoch": 7.14,
"learning_rate": 2.8602525032651287e-06,
"loss": 0.0013,
"step": 16400
},
{
"epoch": 7.16,
"learning_rate": 2.8384849804092297e-06,
"loss": 0.0007,
"step": 16450
},
{
"epoch": 7.18,
"learning_rate": 2.816717457553331e-06,
"loss": 0.0001,
"step": 16500
},
{
"epoch": 7.21,
"learning_rate": 2.794949934697432e-06,
"loss": 0.0056,
"step": 16550
},
{
"epoch": 7.23,
"learning_rate": 2.773182411841533e-06,
"loss": 0.0041,
"step": 16600
},
{
"epoch": 7.25,
"learning_rate": 2.7514148889856336e-06,
"loss": 0.0022,
"step": 16650
},
{
"epoch": 7.27,
"learning_rate": 2.7296473661297347e-06,
"loss": 0.0003,
"step": 16700
},
{
"epoch": 7.29,
"learning_rate": 2.7078798432738358e-06,
"loss": 0.0012,
"step": 16750
},
{
"epoch": 7.31,
"learning_rate": 2.686112320417937e-06,
"loss": 0.0006,
"step": 16800
},
{
"epoch": 7.34,
"learning_rate": 2.664344797562038e-06,
"loss": 0.0019,
"step": 16850
},
{
"epoch": 7.36,
"learning_rate": 2.6425772747061386e-06,
"loss": 0.0014,
"step": 16900
},
{
"epoch": 7.38,
"learning_rate": 2.6208097518502397e-06,
"loss": 0.0001,
"step": 16950
},
{
"epoch": 7.4,
"learning_rate": 2.5990422289943408e-06,
"loss": 0.0048,
"step": 17000
},
{
"epoch": 7.42,
"learning_rate": 2.577274706138442e-06,
"loss": 0.0032,
"step": 17050
},
{
"epoch": 7.44,
"learning_rate": 2.555507183282543e-06,
"loss": 0.0001,
"step": 17100
},
{
"epoch": 7.47,
"learning_rate": 2.5337396604266436e-06,
"loss": 0.0013,
"step": 17150
},
{
"epoch": 7.49,
"learning_rate": 2.5119721375707447e-06,
"loss": 0.0023,
"step": 17200
},
{
"epoch": 7.51,
"learning_rate": 2.4902046147148457e-06,
"loss": 0.0003,
"step": 17250
},
{
"epoch": 7.53,
"learning_rate": 2.468437091858947e-06,
"loss": 0.0029,
"step": 17300
},
{
"epoch": 7.55,
"learning_rate": 2.4466695690030475e-06,
"loss": 0.0001,
"step": 17350
},
{
"epoch": 7.58,
"learning_rate": 2.4249020461471485e-06,
"loss": 0.0001,
"step": 17400
},
{
"epoch": 7.6,
"learning_rate": 2.4031345232912496e-06,
"loss": 0.0009,
"step": 17450
},
{
"epoch": 7.62,
"learning_rate": 2.3813670004353507e-06,
"loss": 0.0043,
"step": 17500
},
{
"epoch": 7.64,
"learning_rate": 2.3595994775794518e-06,
"loss": 0.001,
"step": 17550
},
{
"epoch": 7.66,
"learning_rate": 2.3378319547235524e-06,
"loss": 0.0011,
"step": 17600
},
{
"epoch": 7.68,
"learning_rate": 2.3160644318676535e-06,
"loss": 0.0005,
"step": 17650
},
{
"epoch": 7.71,
"learning_rate": 2.2942969090117546e-06,
"loss": 0.0051,
"step": 17700
},
{
"epoch": 7.73,
"learning_rate": 2.2725293861558557e-06,
"loss": 0.003,
"step": 17750
},
{
"epoch": 7.75,
"learning_rate": 2.2507618632999568e-06,
"loss": 0.0053,
"step": 17800
},
{
"epoch": 7.77,
"learning_rate": 2.2289943404440574e-06,
"loss": 0.0024,
"step": 17850
},
{
"epoch": 7.79,
"learning_rate": 2.2072268175881585e-06,
"loss": 0.0035,
"step": 17900
},
{
"epoch": 7.81,
"learning_rate": 2.1854592947322596e-06,
"loss": 0.0033,
"step": 17950
},
{
"epoch": 7.84,
"learning_rate": 2.1636917718763607e-06,
"loss": 0.0017,
"step": 18000
},
{
"epoch": 7.86,
"learning_rate": 2.1419242490204617e-06,
"loss": 0.0054,
"step": 18050
},
{
"epoch": 7.88,
"learning_rate": 2.1201567261645624e-06,
"loss": 0.0047,
"step": 18100
},
{
"epoch": 7.9,
"learning_rate": 2.0983892033086635e-06,
"loss": 0.0027,
"step": 18150
},
{
"epoch": 7.92,
"learning_rate": 2.0766216804527645e-06,
"loss": 0.0033,
"step": 18200
},
{
"epoch": 7.95,
"learning_rate": 2.0548541575968656e-06,
"loss": 0.0019,
"step": 18250
},
{
"epoch": 7.97,
"learning_rate": 2.0330866347409667e-06,
"loss": 0.0008,
"step": 18300
},
{
"epoch": 7.99,
"learning_rate": 2.0113191118850674e-06,
"loss": 0.0013,
"step": 18350
},
{
"epoch": 8.0,
"eval_f1": 0.9992646458043959,
"eval_loss": 0.006770425010472536,
"eval_runtime": 35.137,
"eval_samples_per_second": 1045.565,
"eval_steps_per_second": 16.365,
"step": 18376
},
{
"epoch": 8.01,
"learning_rate": 1.9895515890291684e-06,
"loss": 0.0007,
"step": 18400
},
{
"epoch": 8.03,
"learning_rate": 1.9677840661732695e-06,
"loss": 0.0041,
"step": 18450
},
{
"epoch": 8.05,
"learning_rate": 1.9460165433173706e-06,
"loss": 0.001,
"step": 18500
},
{
"epoch": 8.08,
"learning_rate": 1.9242490204614717e-06,
"loss": 0.0001,
"step": 18550
},
{
"epoch": 8.1,
"learning_rate": 1.9024814976055728e-06,
"loss": 0.0001,
"step": 18600
},
{
"epoch": 8.12,
"learning_rate": 1.8807139747496736e-06,
"loss": 0.0002,
"step": 18650
},
{
"epoch": 8.14,
"learning_rate": 1.8589464518937747e-06,
"loss": 0.0014,
"step": 18700
},
{
"epoch": 8.16,
"learning_rate": 1.8371789290378756e-06,
"loss": 0.0015,
"step": 18750
},
{
"epoch": 8.18,
"learning_rate": 1.8154114061819767e-06,
"loss": 0.0052,
"step": 18800
},
{
"epoch": 8.21,
"learning_rate": 1.7936438833260777e-06,
"loss": 0.0001,
"step": 18850
},
{
"epoch": 8.23,
"learning_rate": 1.7718763604701786e-06,
"loss": 0.0001,
"step": 18900
},
{
"epoch": 8.25,
"learning_rate": 1.7501088376142797e-06,
"loss": 0.0013,
"step": 18950
},
{
"epoch": 8.27,
"learning_rate": 1.7283413147583806e-06,
"loss": 0.0016,
"step": 19000
},
{
"epoch": 8.29,
"learning_rate": 1.7065737919024816e-06,
"loss": 0.0005,
"step": 19050
},
{
"epoch": 8.32,
"learning_rate": 1.6848062690465827e-06,
"loss": 0.0016,
"step": 19100
},
{
"epoch": 8.34,
"learning_rate": 1.6630387461906836e-06,
"loss": 0.0012,
"step": 19150
},
{
"epoch": 8.36,
"learning_rate": 1.6412712233347847e-06,
"loss": 0.0026,
"step": 19200
},
{
"epoch": 8.38,
"learning_rate": 1.6195037004788855e-06,
"loss": 0.0015,
"step": 19250
},
{
"epoch": 8.4,
"learning_rate": 1.5977361776229866e-06,
"loss": 0.0011,
"step": 19300
},
{
"epoch": 8.42,
"learning_rate": 1.5759686547670877e-06,
"loss": 0.006,
"step": 19350
},
{
"epoch": 8.45,
"learning_rate": 1.5542011319111886e-06,
"loss": 0.0031,
"step": 19400
},
{
"epoch": 8.47,
"learning_rate": 1.5324336090552896e-06,
"loss": 0.0018,
"step": 19450
},
{
"epoch": 8.49,
"learning_rate": 1.5106660861993907e-06,
"loss": 0.0001,
"step": 19500
},
{
"epoch": 8.51,
"learning_rate": 1.4888985633434916e-06,
"loss": 0.0001,
"step": 19550
},
{
"epoch": 8.53,
"learning_rate": 1.4671310404875927e-06,
"loss": 0.0,
"step": 19600
},
{
"epoch": 8.55,
"learning_rate": 1.4453635176316935e-06,
"loss": 0.0011,
"step": 19650
},
{
"epoch": 8.58,
"learning_rate": 1.4235959947757946e-06,
"loss": 0.0001,
"step": 19700
},
{
"epoch": 8.6,
"learning_rate": 1.4018284719198957e-06,
"loss": 0.0019,
"step": 19750
},
{
"epoch": 8.62,
"learning_rate": 1.3800609490639966e-06,
"loss": 0.0027,
"step": 19800
},
{
"epoch": 8.64,
"learning_rate": 1.3582934262080976e-06,
"loss": 0.0018,
"step": 19850
},
{
"epoch": 8.66,
"learning_rate": 1.3365259033521985e-06,
"loss": 0.0013,
"step": 19900
},
{
"epoch": 8.69,
"learning_rate": 1.3147583804962996e-06,
"loss": 0.0001,
"step": 19950
},
{
"epoch": 8.71,
"learning_rate": 1.2929908576404007e-06,
"loss": 0.0003,
"step": 20000
},
{
"epoch": 8.73,
"learning_rate": 1.2712233347845015e-06,
"loss": 0.0005,
"step": 20050
},
{
"epoch": 8.75,
"learning_rate": 1.2494558119286026e-06,
"loss": 0.0049,
"step": 20100
},
{
"epoch": 8.77,
"learning_rate": 1.2276882890727037e-06,
"loss": 0.0026,
"step": 20150
},
{
"epoch": 8.79,
"learning_rate": 1.2059207662168046e-06,
"loss": 0.0014,
"step": 20200
},
{
"epoch": 8.82,
"learning_rate": 1.1841532433609056e-06,
"loss": 0.0003,
"step": 20250
},
{
"epoch": 8.84,
"learning_rate": 1.1623857205050067e-06,
"loss": 0.0006,
"step": 20300
},
{
"epoch": 8.86,
"learning_rate": 1.1406181976491076e-06,
"loss": 0.0,
"step": 20350
},
{
"epoch": 8.88,
"learning_rate": 1.1188506747932087e-06,
"loss": 0.0025,
"step": 20400
},
{
"epoch": 8.9,
"learning_rate": 1.0970831519373095e-06,
"loss": 0.0,
"step": 20450
},
{
"epoch": 8.92,
"learning_rate": 1.0753156290814106e-06,
"loss": 0.0001,
"step": 20500
},
{
"epoch": 8.95,
"learning_rate": 1.0535481062255117e-06,
"loss": 0.0023,
"step": 20550
},
{
"epoch": 8.97,
"learning_rate": 1.0317805833696126e-06,
"loss": 0.0018,
"step": 20600
},
{
"epoch": 8.99,
"learning_rate": 1.0100130605137136e-06,
"loss": 0.0055,
"step": 20650
},
{
"epoch": 9.0,
"eval_f1": 0.9991502434879236,
"eval_loss": 0.007731999270617962,
"eval_runtime": 34.7727,
"eval_samples_per_second": 1056.52,
"eval_steps_per_second": 16.536,
"step": 20673
},
{
"epoch": 9.01,
"learning_rate": 9.882455376578145e-07,
"loss": 0.0019,
"step": 20700
},
{
"epoch": 9.03,
"learning_rate": 9.664780148019156e-07,
"loss": 0.0024,
"step": 20750
},
{
"epoch": 9.06,
"learning_rate": 9.447104919460167e-07,
"loss": 0.0044,
"step": 20800
},
{
"epoch": 9.08,
"learning_rate": 9.229429690901176e-07,
"loss": 0.0006,
"step": 20850
},
{
"epoch": 9.1,
"learning_rate": 9.011754462342186e-07,
"loss": 0.0001,
"step": 20900
},
{
"epoch": 9.12,
"learning_rate": 8.794079233783197e-07,
"loss": 0.0004,
"step": 20950
},
{
"epoch": 9.14,
"learning_rate": 8.576404005224207e-07,
"loss": 0.0013,
"step": 21000
},
{
"epoch": 9.16,
"learning_rate": 8.358728776665216e-07,
"loss": 0.0004,
"step": 21050
},
{
"epoch": 9.19,
"learning_rate": 8.141053548106226e-07,
"loss": 0.001,
"step": 21100
},
{
"epoch": 9.21,
"learning_rate": 7.923378319547236e-07,
"loss": 0.0005,
"step": 21150
},
{
"epoch": 9.23,
"learning_rate": 7.705703090988247e-07,
"loss": 0.0008,
"step": 21200
},
{
"epoch": 9.25,
"learning_rate": 7.488027862429256e-07,
"loss": 0.0004,
"step": 21250
},
{
"epoch": 9.27,
"learning_rate": 7.270352633870266e-07,
"loss": 0.0019,
"step": 21300
},
{
"epoch": 9.29,
"learning_rate": 7.052677405311276e-07,
"loss": 0.0003,
"step": 21350
},
{
"epoch": 9.32,
"learning_rate": 6.835002176752287e-07,
"loss": 0.0003,
"step": 21400
},
{
"epoch": 9.34,
"learning_rate": 6.617326948193296e-07,
"loss": 0.0001,
"step": 21450
},
{
"epoch": 9.36,
"learning_rate": 6.399651719634306e-07,
"loss": 0.0006,
"step": 21500
},
{
"epoch": 9.38,
"learning_rate": 6.181976491075317e-07,
"loss": 0.0017,
"step": 21550
},
{
"epoch": 9.4,
"learning_rate": 5.964301262516327e-07,
"loss": 0.0,
"step": 21600
},
{
"epoch": 9.43,
"learning_rate": 5.746626033957335e-07,
"loss": 0.0,
"step": 21650
},
{
"epoch": 9.45,
"learning_rate": 5.528950805398346e-07,
"loss": 0.0,
"step": 21700
},
{
"epoch": 9.47,
"learning_rate": 5.311275576839356e-07,
"loss": 0.0006,
"step": 21750
},
{
"epoch": 9.49,
"learning_rate": 5.093600348280367e-07,
"loss": 0.0,
"step": 21800
},
{
"epoch": 9.51,
"learning_rate": 4.875925119721376e-07,
"loss": 0.0032,
"step": 21850
},
{
"epoch": 9.53,
"learning_rate": 4.658249891162386e-07,
"loss": 0.0016,
"step": 21900
},
{
"epoch": 9.56,
"learning_rate": 4.440574662603396e-07,
"loss": 0.0024,
"step": 21950
},
{
"epoch": 9.58,
"learning_rate": 4.2228994340444067e-07,
"loss": 0.0001,
"step": 22000
},
{
"epoch": 9.6,
"learning_rate": 4.005224205485416e-07,
"loss": 0.0001,
"step": 22050
},
{
"epoch": 9.62,
"learning_rate": 3.7875489769264256e-07,
"loss": 0.002,
"step": 22100
},
{
"epoch": 9.64,
"learning_rate": 3.5698737483674364e-07,
"loss": 0.0,
"step": 22150
},
{
"epoch": 9.66,
"learning_rate": 3.3521985198084456e-07,
"loss": 0.0001,
"step": 22200
},
{
"epoch": 9.69,
"learning_rate": 3.1345232912494564e-07,
"loss": 0.0038,
"step": 22250
},
{
"epoch": 9.71,
"learning_rate": 2.916848062690466e-07,
"loss": 0.0027,
"step": 22300
},
{
"epoch": 9.73,
"learning_rate": 2.699172834131476e-07,
"loss": 0.003,
"step": 22350
},
{
"epoch": 9.75,
"learning_rate": 2.481497605572486e-07,
"loss": 0.0001,
"step": 22400
},
{
"epoch": 9.77,
"learning_rate": 2.263822377013496e-07,
"loss": 0.0001,
"step": 22450
},
{
"epoch": 9.8,
"learning_rate": 2.0461471484545061e-07,
"loss": 0.0054,
"step": 22500
},
{
"epoch": 9.82,
"learning_rate": 1.8284719198955161e-07,
"loss": 0.0015,
"step": 22550
},
{
"epoch": 9.84,
"learning_rate": 1.6107966913365261e-07,
"loss": 0.0016,
"step": 22600
},
{
"epoch": 9.86,
"learning_rate": 1.393121462777536e-07,
"loss": 0.0,
"step": 22650
},
{
"epoch": 9.88,
"learning_rate": 1.175446234218546e-07,
"loss": 0.0012,
"step": 22700
},
{
"epoch": 9.9,
"learning_rate": 9.57771005659556e-08,
"loss": 0.0,
"step": 22750
},
{
"epoch": 9.93,
"learning_rate": 7.40095777100566e-08,
"loss": 0.0001,
"step": 22800
},
{
"epoch": 9.95,
"learning_rate": 5.22420548541576e-08,
"loss": 0.0053,
"step": 22850
},
{
"epoch": 9.97,
"learning_rate": 3.04745319982586e-08,
"loss": 0.0015,
"step": 22900
},
{
"epoch": 9.99,
"learning_rate": 8.7070091423596e-09,
"loss": 0.0001,
"step": 22950
},
{
"epoch": 10.0,
"eval_f1": 0.9991828997254544,
"eval_loss": 0.008167621679604053,
"eval_runtime": 35.0331,
"eval_samples_per_second": 1048.665,
"eval_steps_per_second": 16.413,
"step": 22970
}
],
"max_steps": 22970,
"num_train_epochs": 10,
"total_flos": 2.161637529772032e+16,
"trial_name": null,
"trial_params": null
}