gokuls's picture
End of training
27eeb55
{
"best_metric": 6.043306350708008,
"best_model_checkpoint": "HBERTv1_emb_compress_48_L12_H512_A8/checkpoint-270000",
"epoch": 2.580753386031485,
"eval_steps": 10000,
"global_step": 270001,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 10.2035,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 1.0000000000000002e-06,
"loss": 10.0751,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 9.9961,
"step": 1500
},
{
"epoch": 0.02,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.8837,
"step": 2000
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 9.7472,
"step": 2500
},
{
"epoch": 0.03,
"learning_rate": 3e-06,
"loss": 9.5906,
"step": 3000
},
{
"epoch": 0.03,
"learning_rate": 3.5e-06,
"loss": 9.405,
"step": 3500
},
{
"epoch": 0.04,
"learning_rate": 4.000000000000001e-06,
"loss": 9.2004,
"step": 4000
},
{
"epoch": 0.04,
"learning_rate": 4.5e-06,
"loss": 8.9751,
"step": 4500
},
{
"epoch": 0.05,
"learning_rate": 5e-06,
"loss": 8.738,
"step": 5000
},
{
"epoch": 0.05,
"learning_rate": 5.500000000000001e-06,
"loss": 8.4913,
"step": 5500
},
{
"epoch": 0.06,
"learning_rate": 6e-06,
"loss": 8.2458,
"step": 6000
},
{
"epoch": 0.06,
"learning_rate": 6.5000000000000004e-06,
"loss": 8.006,
"step": 6500
},
{
"epoch": 0.07,
"learning_rate": 7e-06,
"loss": 7.7753,
"step": 7000
},
{
"epoch": 0.07,
"learning_rate": 7.500000000000001e-06,
"loss": 7.5801,
"step": 7500
},
{
"epoch": 0.08,
"learning_rate": 8.000000000000001e-06,
"loss": 7.4169,
"step": 8000
},
{
"epoch": 0.08,
"learning_rate": 8.5e-06,
"loss": 7.2968,
"step": 8500
},
{
"epoch": 0.09,
"learning_rate": 9e-06,
"loss": 7.2141,
"step": 9000
},
{
"epoch": 0.09,
"learning_rate": 9.5e-06,
"loss": 7.1455,
"step": 9500
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 7.102,
"step": 10000
},
{
"epoch": 0.1,
"eval_accuracy": 0.08339668972188564,
"eval_loss": 7.082488059997559,
"eval_runtime": 1256.0156,
"eval_samples_per_second": 245.503,
"eval_steps_per_second": 4.384,
"step": 10000
},
{
"epoch": 0.1,
"learning_rate": 9.990255405813626e-06,
"loss": 7.0595,
"step": 10500
},
{
"epoch": 0.11,
"learning_rate": 9.98051081162725e-06,
"loss": 7.0192,
"step": 11000
},
{
"epoch": 0.11,
"learning_rate": 9.970766217440876e-06,
"loss": 6.9898,
"step": 11500
},
{
"epoch": 0.11,
"learning_rate": 9.9610216232545e-06,
"loss": 6.9603,
"step": 12000
},
{
"epoch": 0.12,
"learning_rate": 9.951277029068126e-06,
"loss": 6.9285,
"step": 12500
},
{
"epoch": 0.12,
"learning_rate": 9.94153243488175e-06,
"loss": 6.9038,
"step": 13000
},
{
"epoch": 0.13,
"learning_rate": 9.931787840695375e-06,
"loss": 6.8844,
"step": 13500
},
{
"epoch": 0.13,
"learning_rate": 9.922043246509e-06,
"loss": 6.8649,
"step": 14000
},
{
"epoch": 0.14,
"learning_rate": 9.912298652322625e-06,
"loss": 6.8373,
"step": 14500
},
{
"epoch": 0.14,
"learning_rate": 9.90255405813625e-06,
"loss": 6.8209,
"step": 15000
},
{
"epoch": 0.15,
"learning_rate": 9.892809463949875e-06,
"loss": 6.8021,
"step": 15500
},
{
"epoch": 0.15,
"learning_rate": 9.883064869763498e-06,
"loss": 6.7801,
"step": 16000
},
{
"epoch": 0.16,
"learning_rate": 9.873320275577123e-06,
"loss": 6.773,
"step": 16500
},
{
"epoch": 0.16,
"learning_rate": 9.863575681390748e-06,
"loss": 6.7522,
"step": 17000
},
{
"epoch": 0.17,
"learning_rate": 9.853831087204375e-06,
"loss": 6.7416,
"step": 17500
},
{
"epoch": 0.17,
"learning_rate": 9.844086493018e-06,
"loss": 6.7255,
"step": 18000
},
{
"epoch": 0.18,
"learning_rate": 9.834341898831625e-06,
"loss": 6.7083,
"step": 18500
},
{
"epoch": 0.18,
"learning_rate": 9.82459730464525e-06,
"loss": 6.6964,
"step": 19000
},
{
"epoch": 0.19,
"learning_rate": 9.814852710458875e-06,
"loss": 6.6911,
"step": 19500
},
{
"epoch": 0.19,
"learning_rate": 9.805108116272498e-06,
"loss": 6.6803,
"step": 20000
},
{
"epoch": 0.19,
"eval_accuracy": 0.10658781313805665,
"eval_loss": 6.675572395324707,
"eval_runtime": 1256.6676,
"eval_samples_per_second": 245.376,
"eval_steps_per_second": 4.382,
"step": 20000
},
{
"epoch": 0.2,
"learning_rate": 9.795363522086123e-06,
"loss": 6.6703,
"step": 20500
},
{
"epoch": 0.2,
"learning_rate": 9.785618927899748e-06,
"loss": 6.6566,
"step": 21000
},
{
"epoch": 0.21,
"learning_rate": 9.775874333713373e-06,
"loss": 6.6531,
"step": 21500
},
{
"epoch": 0.21,
"learning_rate": 9.766129739526998e-06,
"loss": 6.649,
"step": 22000
},
{
"epoch": 0.22,
"learning_rate": 9.756385145340623e-06,
"loss": 6.6367,
"step": 22500
},
{
"epoch": 0.22,
"learning_rate": 9.74664055115425e-06,
"loss": 6.6242,
"step": 23000
},
{
"epoch": 0.22,
"learning_rate": 9.736895956967874e-06,
"loss": 6.6141,
"step": 23500
},
{
"epoch": 0.23,
"learning_rate": 9.727151362781497e-06,
"loss": 6.6072,
"step": 24000
},
{
"epoch": 0.23,
"learning_rate": 9.717406768595122e-06,
"loss": 6.6,
"step": 24500
},
{
"epoch": 0.24,
"learning_rate": 9.707662174408747e-06,
"loss": 6.5972,
"step": 25000
},
{
"epoch": 0.24,
"learning_rate": 9.697917580222372e-06,
"loss": 6.5925,
"step": 25500
},
{
"epoch": 0.25,
"learning_rate": 9.688172986035997e-06,
"loss": 6.5825,
"step": 26000
},
{
"epoch": 0.25,
"learning_rate": 9.678428391849622e-06,
"loss": 6.5727,
"step": 26500
},
{
"epoch": 0.26,
"learning_rate": 9.668683797663247e-06,
"loss": 6.5625,
"step": 27000
},
{
"epoch": 0.26,
"learning_rate": 9.658939203476872e-06,
"loss": 6.5678,
"step": 27500
},
{
"epoch": 0.27,
"learning_rate": 9.649194609290497e-06,
"loss": 6.5558,
"step": 28000
},
{
"epoch": 0.27,
"learning_rate": 9.639450015104122e-06,
"loss": 6.545,
"step": 28500
},
{
"epoch": 0.28,
"learning_rate": 9.629705420917747e-06,
"loss": 6.5402,
"step": 29000
},
{
"epoch": 0.28,
"learning_rate": 9.619960826731372e-06,
"loss": 6.5335,
"step": 29500
},
{
"epoch": 0.29,
"learning_rate": 9.610216232544997e-06,
"loss": 6.5348,
"step": 30000
},
{
"epoch": 0.29,
"eval_accuracy": 0.1196010490788008,
"eval_loss": 6.529774188995361,
"eval_runtime": 1257.2805,
"eval_samples_per_second": 245.256,
"eval_steps_per_second": 4.38,
"step": 30000
},
{
"epoch": 0.29,
"learning_rate": 9.600471638358622e-06,
"loss": 6.5362,
"step": 30500
},
{
"epoch": 0.3,
"learning_rate": 9.590727044172246e-06,
"loss": 6.5205,
"step": 31000
},
{
"epoch": 0.3,
"learning_rate": 9.580982449985871e-06,
"loss": 6.519,
"step": 31500
},
{
"epoch": 0.31,
"learning_rate": 9.571237855799496e-06,
"loss": 6.5174,
"step": 32000
},
{
"epoch": 0.31,
"learning_rate": 9.561493261613121e-06,
"loss": 6.5018,
"step": 32500
},
{
"epoch": 0.32,
"learning_rate": 9.551748667426746e-06,
"loss": 6.5051,
"step": 33000
},
{
"epoch": 0.32,
"learning_rate": 9.542004073240371e-06,
"loss": 6.4986,
"step": 33500
},
{
"epoch": 0.32,
"learning_rate": 9.532259479053996e-06,
"loss": 6.4896,
"step": 34000
},
{
"epoch": 0.33,
"learning_rate": 9.522514884867621e-06,
"loss": 6.4844,
"step": 34500
},
{
"epoch": 0.33,
"learning_rate": 9.512770290681246e-06,
"loss": 6.4859,
"step": 35000
},
{
"epoch": 0.34,
"learning_rate": 9.50302569649487e-06,
"loss": 6.4829,
"step": 35500
},
{
"epoch": 0.34,
"learning_rate": 9.493281102308494e-06,
"loss": 6.4716,
"step": 36000
},
{
"epoch": 0.35,
"learning_rate": 9.483536508122119e-06,
"loss": 6.4757,
"step": 36500
},
{
"epoch": 0.35,
"learning_rate": 9.473791913935744e-06,
"loss": 6.4655,
"step": 37000
},
{
"epoch": 0.36,
"learning_rate": 9.46404731974937e-06,
"loss": 6.4576,
"step": 37500
},
{
"epoch": 0.36,
"learning_rate": 9.454302725562996e-06,
"loss": 6.4609,
"step": 38000
},
{
"epoch": 0.37,
"learning_rate": 9.44455813137662e-06,
"loss": 6.4573,
"step": 38500
},
{
"epoch": 0.37,
"learning_rate": 9.434813537190245e-06,
"loss": 6.4397,
"step": 39000
},
{
"epoch": 0.38,
"learning_rate": 9.425068943003869e-06,
"loss": 6.4453,
"step": 39500
},
{
"epoch": 0.38,
"learning_rate": 9.415324348817494e-06,
"loss": 6.4394,
"step": 40000
},
{
"epoch": 0.38,
"eval_accuracy": 0.12736710845990495,
"eval_loss": 6.4388580322265625,
"eval_runtime": 1278.38,
"eval_samples_per_second": 241.208,
"eval_steps_per_second": 4.308,
"step": 40000
},
{
"epoch": 0.39,
"learning_rate": 9.405579754631119e-06,
"loss": 6.4405,
"step": 40500
},
{
"epoch": 0.39,
"learning_rate": 9.395835160444744e-06,
"loss": 6.4418,
"step": 41000
},
{
"epoch": 0.4,
"learning_rate": 9.386090566258368e-06,
"loss": 6.4287,
"step": 41500
},
{
"epoch": 0.4,
"learning_rate": 9.376345972071993e-06,
"loss": 6.4244,
"step": 42000
},
{
"epoch": 0.41,
"learning_rate": 9.366601377885618e-06,
"loss": 6.4279,
"step": 42500
},
{
"epoch": 0.41,
"learning_rate": 9.356856783699245e-06,
"loss": 6.4201,
"step": 43000
},
{
"epoch": 0.42,
"learning_rate": 9.347112189512868e-06,
"loss": 6.4135,
"step": 43500
},
{
"epoch": 0.42,
"learning_rate": 9.337367595326493e-06,
"loss": 6.4136,
"step": 44000
},
{
"epoch": 0.43,
"learning_rate": 9.327623001140118e-06,
"loss": 6.4096,
"step": 44500
},
{
"epoch": 0.43,
"learning_rate": 9.317878406953743e-06,
"loss": 6.4073,
"step": 45000
},
{
"epoch": 0.43,
"learning_rate": 9.308133812767368e-06,
"loss": 6.3964,
"step": 45500
},
{
"epoch": 0.44,
"learning_rate": 9.298389218580993e-06,
"loss": 6.3988,
"step": 46000
},
{
"epoch": 0.44,
"learning_rate": 9.288644624394618e-06,
"loss": 6.3942,
"step": 46500
},
{
"epoch": 0.45,
"learning_rate": 9.278900030208243e-06,
"loss": 6.3913,
"step": 47000
},
{
"epoch": 0.45,
"learning_rate": 9.269155436021868e-06,
"loss": 6.3901,
"step": 47500
},
{
"epoch": 0.46,
"learning_rate": 9.259410841835493e-06,
"loss": 6.3888,
"step": 48000
},
{
"epoch": 0.46,
"learning_rate": 9.249666247649118e-06,
"loss": 6.3846,
"step": 48500
},
{
"epoch": 0.47,
"learning_rate": 9.239921653462742e-06,
"loss": 6.3881,
"step": 49000
},
{
"epoch": 0.47,
"learning_rate": 9.230177059276367e-06,
"loss": 6.377,
"step": 49500
},
{
"epoch": 0.48,
"learning_rate": 9.220432465089992e-06,
"loss": 6.3686,
"step": 50000
},
{
"epoch": 0.48,
"eval_accuracy": 0.13322074773674192,
"eval_loss": 6.3726043701171875,
"eval_runtime": 1278.2433,
"eval_samples_per_second": 241.234,
"eval_steps_per_second": 4.308,
"step": 50000
},
{
"epoch": 0.48,
"learning_rate": 9.210687870903617e-06,
"loss": 6.3726,
"step": 50500
},
{
"epoch": 0.49,
"learning_rate": 9.200943276717242e-06,
"loss": 6.3695,
"step": 51000
},
{
"epoch": 0.49,
"learning_rate": 9.191198682530867e-06,
"loss": 6.369,
"step": 51500
},
{
"epoch": 0.5,
"learning_rate": 9.181454088344492e-06,
"loss": 6.3654,
"step": 52000
},
{
"epoch": 0.5,
"learning_rate": 9.171709494158117e-06,
"loss": 6.3642,
"step": 52500
},
{
"epoch": 0.51,
"learning_rate": 9.161964899971742e-06,
"loss": 6.3539,
"step": 53000
},
{
"epoch": 0.51,
"learning_rate": 9.152220305785367e-06,
"loss": 6.3558,
"step": 53500
},
{
"epoch": 0.52,
"learning_rate": 9.142475711598992e-06,
"loss": 6.3497,
"step": 54000
},
{
"epoch": 0.52,
"learning_rate": 9.132731117412617e-06,
"loss": 6.3503,
"step": 54500
},
{
"epoch": 0.53,
"learning_rate": 9.12298652322624e-06,
"loss": 6.3482,
"step": 55000
},
{
"epoch": 0.53,
"learning_rate": 9.113241929039865e-06,
"loss": 6.3379,
"step": 55500
},
{
"epoch": 0.54,
"learning_rate": 9.10349733485349e-06,
"loss": 6.3529,
"step": 56000
},
{
"epoch": 0.54,
"learning_rate": 9.093752740667115e-06,
"loss": 6.3525,
"step": 56500
},
{
"epoch": 0.54,
"learning_rate": 9.08400814648074e-06,
"loss": 6.3367,
"step": 57000
},
{
"epoch": 0.55,
"learning_rate": 9.074263552294366e-06,
"loss": 6.3361,
"step": 57500
},
{
"epoch": 0.55,
"learning_rate": 9.064518958107991e-06,
"loss": 6.3296,
"step": 58000
},
{
"epoch": 0.56,
"learning_rate": 9.054774363921616e-06,
"loss": 6.3263,
"step": 58500
},
{
"epoch": 0.56,
"learning_rate": 9.04502976973524e-06,
"loss": 6.3234,
"step": 59000
},
{
"epoch": 0.57,
"learning_rate": 9.035285175548864e-06,
"loss": 6.3231,
"step": 59500
},
{
"epoch": 0.57,
"learning_rate": 9.02554058136249e-06,
"loss": 6.3213,
"step": 60000
},
{
"epoch": 0.57,
"eval_accuracy": 0.1357508721952323,
"eval_loss": 6.3189167976379395,
"eval_runtime": 1280.5846,
"eval_samples_per_second": 240.793,
"eval_steps_per_second": 4.3,
"step": 60000
},
{
"epoch": 0.58,
"learning_rate": 9.015795987176114e-06,
"loss": 6.3208,
"step": 60500
},
{
"epoch": 0.58,
"learning_rate": 9.00605139298974e-06,
"loss": 6.3226,
"step": 61000
},
{
"epoch": 0.59,
"learning_rate": 8.996306798803364e-06,
"loss": 6.3176,
"step": 61500
},
{
"epoch": 0.59,
"learning_rate": 8.986562204616989e-06,
"loss": 6.3158,
"step": 62000
},
{
"epoch": 0.6,
"learning_rate": 8.976817610430614e-06,
"loss": 6.3142,
"step": 62500
},
{
"epoch": 0.6,
"learning_rate": 8.967073016244239e-06,
"loss": 6.3071,
"step": 63000
},
{
"epoch": 0.61,
"learning_rate": 8.957328422057864e-06,
"loss": 6.3098,
"step": 63500
},
{
"epoch": 0.61,
"learning_rate": 8.947583827871489e-06,
"loss": 6.3039,
"step": 64000
},
{
"epoch": 0.62,
"learning_rate": 8.937839233685114e-06,
"loss": 6.3039,
"step": 64500
},
{
"epoch": 0.62,
"learning_rate": 8.928094639498739e-06,
"loss": 6.302,
"step": 65000
},
{
"epoch": 0.63,
"learning_rate": 8.918350045312364e-06,
"loss": 6.31,
"step": 65500
},
{
"epoch": 0.63,
"learning_rate": 8.908605451125989e-06,
"loss": 6.2953,
"step": 66000
},
{
"epoch": 0.64,
"learning_rate": 8.898860856939614e-06,
"loss": 6.2965,
"step": 66500
},
{
"epoch": 0.64,
"learning_rate": 8.889116262753239e-06,
"loss": 6.2916,
"step": 67000
},
{
"epoch": 0.65,
"learning_rate": 8.879371668566863e-06,
"loss": 6.2927,
"step": 67500
},
{
"epoch": 0.65,
"learning_rate": 8.869627074380488e-06,
"loss": 6.2903,
"step": 68000
},
{
"epoch": 0.65,
"learning_rate": 8.859882480194113e-06,
"loss": 6.2964,
"step": 68500
},
{
"epoch": 0.66,
"learning_rate": 8.850137886007738e-06,
"loss": 6.2899,
"step": 69000
},
{
"epoch": 0.66,
"learning_rate": 8.840393291821363e-06,
"loss": 6.2838,
"step": 69500
},
{
"epoch": 0.67,
"learning_rate": 8.830648697634988e-06,
"loss": 6.281,
"step": 70000
},
{
"epoch": 0.67,
"eval_accuracy": 0.13823981556068876,
"eval_loss": 6.281214714050293,
"eval_runtime": 1256.4444,
"eval_samples_per_second": 245.42,
"eval_steps_per_second": 4.383,
"step": 70000
},
{
"epoch": 0.67,
"learning_rate": 8.820904103448613e-06,
"loss": 6.2803,
"step": 70500
},
{
"epoch": 0.68,
"learning_rate": 8.811159509262236e-06,
"loss": 6.2762,
"step": 71000
},
{
"epoch": 0.68,
"learning_rate": 8.801414915075863e-06,
"loss": 6.2815,
"step": 71500
},
{
"epoch": 0.69,
"learning_rate": 8.791670320889488e-06,
"loss": 6.2754,
"step": 72000
},
{
"epoch": 0.69,
"learning_rate": 8.781925726703113e-06,
"loss": 6.2706,
"step": 72500
},
{
"epoch": 0.7,
"learning_rate": 8.772181132516738e-06,
"loss": 6.2714,
"step": 73000
},
{
"epoch": 0.7,
"learning_rate": 8.762436538330363e-06,
"loss": 6.2719,
"step": 73500
},
{
"epoch": 0.71,
"learning_rate": 8.752691944143988e-06,
"loss": 6.2696,
"step": 74000
},
{
"epoch": 0.71,
"learning_rate": 8.742947349957611e-06,
"loss": 6.2593,
"step": 74500
},
{
"epoch": 0.72,
"learning_rate": 8.733202755771236e-06,
"loss": 6.2642,
"step": 75000
},
{
"epoch": 0.72,
"learning_rate": 8.72345816158486e-06,
"loss": 6.2646,
"step": 75500
},
{
"epoch": 0.73,
"learning_rate": 8.713713567398486e-06,
"loss": 6.2644,
"step": 76000
},
{
"epoch": 0.73,
"learning_rate": 8.70396897321211e-06,
"loss": 6.2605,
"step": 76500
},
{
"epoch": 0.74,
"learning_rate": 8.694224379025736e-06,
"loss": 6.2537,
"step": 77000
},
{
"epoch": 0.74,
"learning_rate": 8.684479784839362e-06,
"loss": 6.2553,
"step": 77500
},
{
"epoch": 0.75,
"learning_rate": 8.674735190652987e-06,
"loss": 6.2582,
"step": 78000
},
{
"epoch": 0.75,
"learning_rate": 8.66499059646661e-06,
"loss": 6.2507,
"step": 78500
},
{
"epoch": 0.76,
"learning_rate": 8.655246002280235e-06,
"loss": 6.2468,
"step": 79000
},
{
"epoch": 0.76,
"learning_rate": 8.64550140809386e-06,
"loss": 6.2528,
"step": 79500
},
{
"epoch": 0.76,
"learning_rate": 8.635756813907485e-06,
"loss": 6.2506,
"step": 80000
},
{
"epoch": 0.76,
"eval_accuracy": 0.1401124982036124,
"eval_loss": 6.2467122077941895,
"eval_runtime": 1256.9658,
"eval_samples_per_second": 245.318,
"eval_steps_per_second": 4.381,
"step": 80000
},
{
"epoch": 0.77,
"learning_rate": 8.62601221972111e-06,
"loss": 6.2497,
"step": 80500
},
{
"epoch": 0.77,
"learning_rate": 8.616267625534735e-06,
"loss": 6.2465,
"step": 81000
},
{
"epoch": 0.78,
"learning_rate": 8.60652303134836e-06,
"loss": 6.2449,
"step": 81500
},
{
"epoch": 0.78,
"learning_rate": 8.596778437161985e-06,
"loss": 6.2471,
"step": 82000
},
{
"epoch": 0.79,
"learning_rate": 8.58703384297561e-06,
"loss": 6.2348,
"step": 82500
},
{
"epoch": 0.79,
"learning_rate": 8.577289248789235e-06,
"loss": 6.2394,
"step": 83000
},
{
"epoch": 0.8,
"learning_rate": 8.56754465460286e-06,
"loss": 6.2348,
"step": 83500
},
{
"epoch": 0.8,
"learning_rate": 8.557800060416485e-06,
"loss": 6.2359,
"step": 84000
},
{
"epoch": 0.81,
"learning_rate": 8.54805546623011e-06,
"loss": 6.2385,
"step": 84500
},
{
"epoch": 0.81,
"learning_rate": 8.538310872043735e-06,
"loss": 6.2404,
"step": 85000
},
{
"epoch": 0.82,
"learning_rate": 8.52856627785736e-06,
"loss": 6.2278,
"step": 85500
},
{
"epoch": 0.82,
"learning_rate": 8.518821683670984e-06,
"loss": 6.2362,
"step": 86000
},
{
"epoch": 0.83,
"learning_rate": 8.50907708948461e-06,
"loss": 6.2274,
"step": 86500
},
{
"epoch": 0.83,
"learning_rate": 8.499332495298234e-06,
"loss": 6.2272,
"step": 87000
},
{
"epoch": 0.84,
"learning_rate": 8.48958790111186e-06,
"loss": 6.226,
"step": 87500
},
{
"epoch": 0.84,
"learning_rate": 8.479843306925484e-06,
"loss": 6.2285,
"step": 88000
},
{
"epoch": 0.85,
"learning_rate": 8.470098712739109e-06,
"loss": 6.2263,
"step": 88500
},
{
"epoch": 0.85,
"learning_rate": 8.460354118552734e-06,
"loss": 6.2247,
"step": 89000
},
{
"epoch": 0.86,
"learning_rate": 8.450609524366359e-06,
"loss": 6.2225,
"step": 89500
},
{
"epoch": 0.86,
"learning_rate": 8.440864930179984e-06,
"loss": 6.221,
"step": 90000
},
{
"epoch": 0.86,
"eval_accuracy": 0.14228283910174983,
"eval_loss": 6.221618175506592,
"eval_runtime": 1257.2491,
"eval_samples_per_second": 245.262,
"eval_steps_per_second": 4.38,
"step": 90000
},
{
"epoch": 0.87,
"learning_rate": 8.431120335993607e-06,
"loss": 6.2195,
"step": 90500
},
{
"epoch": 0.87,
"learning_rate": 8.421375741807232e-06,
"loss": 6.2243,
"step": 91000
},
{
"epoch": 0.87,
"learning_rate": 8.411631147620857e-06,
"loss": 6.2216,
"step": 91500
},
{
"epoch": 0.88,
"learning_rate": 8.401886553434484e-06,
"loss": 6.2278,
"step": 92000
},
{
"epoch": 0.88,
"learning_rate": 8.392141959248109e-06,
"loss": 6.2139,
"step": 92500
},
{
"epoch": 0.89,
"learning_rate": 8.382397365061734e-06,
"loss": 6.214,
"step": 93000
},
{
"epoch": 0.89,
"learning_rate": 8.372652770875358e-06,
"loss": 6.2186,
"step": 93500
},
{
"epoch": 0.9,
"learning_rate": 8.362908176688983e-06,
"loss": 6.212,
"step": 94000
},
{
"epoch": 0.9,
"learning_rate": 8.353163582502607e-06,
"loss": 6.2108,
"step": 94500
},
{
"epoch": 0.91,
"learning_rate": 8.343418988316232e-06,
"loss": 6.2059,
"step": 95000
},
{
"epoch": 0.91,
"learning_rate": 8.333674394129857e-06,
"loss": 6.2109,
"step": 95500
},
{
"epoch": 0.92,
"learning_rate": 8.323929799943481e-06,
"loss": 6.2132,
"step": 96000
},
{
"epoch": 0.92,
"learning_rate": 8.314185205757106e-06,
"loss": 6.2086,
"step": 96500
},
{
"epoch": 0.93,
"learning_rate": 8.304440611570731e-06,
"loss": 6.2112,
"step": 97000
},
{
"epoch": 0.93,
"learning_rate": 8.294696017384358e-06,
"loss": 6.2077,
"step": 97500
},
{
"epoch": 0.94,
"learning_rate": 8.284951423197981e-06,
"loss": 6.2087,
"step": 98000
},
{
"epoch": 0.94,
"learning_rate": 8.275206829011606e-06,
"loss": 6.2076,
"step": 98500
},
{
"epoch": 0.95,
"learning_rate": 8.265462234825231e-06,
"loss": 6.2022,
"step": 99000
},
{
"epoch": 0.95,
"learning_rate": 8.255717640638856e-06,
"loss": 6.2094,
"step": 99500
},
{
"epoch": 0.96,
"learning_rate": 8.245973046452481e-06,
"loss": 6.206,
"step": 100000
},
{
"epoch": 0.96,
"eval_accuracy": 0.14311079234425433,
"eval_loss": 6.197844982147217,
"eval_runtime": 1258.8475,
"eval_samples_per_second": 244.951,
"eval_steps_per_second": 4.375,
"step": 100000
},
{
"epoch": 0.96,
"learning_rate": 8.236228452266106e-06,
"loss": 6.199,
"step": 100500
},
{
"epoch": 0.97,
"learning_rate": 8.22648385807973e-06,
"loss": 6.2008,
"step": 101000
},
{
"epoch": 0.97,
"learning_rate": 8.216739263893356e-06,
"loss": 6.1927,
"step": 101500
},
{
"epoch": 0.97,
"learning_rate": 8.20699466970698e-06,
"loss": 6.2063,
"step": 102000
},
{
"epoch": 0.98,
"learning_rate": 8.197250075520606e-06,
"loss": 6.1965,
"step": 102500
},
{
"epoch": 0.98,
"learning_rate": 8.18750548133423e-06,
"loss": 6.1926,
"step": 103000
},
{
"epoch": 0.99,
"learning_rate": 8.177760887147855e-06,
"loss": 6.1944,
"step": 103500
},
{
"epoch": 0.99,
"learning_rate": 8.16801629296148e-06,
"loss": 6.1868,
"step": 104000
},
{
"epoch": 1.0,
"learning_rate": 8.158271698775105e-06,
"loss": 6.1951,
"step": 104500
},
{
"epoch": 1.0,
"learning_rate": 8.14852710458873e-06,
"loss": 6.1843,
"step": 105000
},
{
"epoch": 1.01,
"learning_rate": 8.138782510402355e-06,
"loss": 6.1908,
"step": 105500
},
{
"epoch": 1.01,
"learning_rate": 8.12903791621598e-06,
"loss": 6.1824,
"step": 106000
},
{
"epoch": 1.02,
"learning_rate": 8.119293322029605e-06,
"loss": 6.1923,
"step": 106500
},
{
"epoch": 1.02,
"learning_rate": 8.10954872784323e-06,
"loss": 6.1817,
"step": 107000
},
{
"epoch": 1.03,
"learning_rate": 8.099804133656855e-06,
"loss": 6.1882,
"step": 107500
},
{
"epoch": 1.03,
"learning_rate": 8.09005953947048e-06,
"loss": 6.1839,
"step": 108000
},
{
"epoch": 1.04,
"learning_rate": 8.080314945284105e-06,
"loss": 6.1822,
"step": 108500
},
{
"epoch": 1.04,
"learning_rate": 8.07057035109773e-06,
"loss": 6.1775,
"step": 109000
},
{
"epoch": 1.05,
"learning_rate": 8.060825756911355e-06,
"loss": 6.1848,
"step": 109500
},
{
"epoch": 1.05,
"learning_rate": 8.051081162724978e-06,
"loss": 6.1831,
"step": 110000
},
{
"epoch": 1.05,
"eval_accuracy": 0.1449117921997742,
"eval_loss": 6.1796488761901855,
"eval_runtime": 1258.6951,
"eval_samples_per_second": 244.981,
"eval_steps_per_second": 4.375,
"step": 110000
},
{
"epoch": 1.06,
"learning_rate": 8.041336568538603e-06,
"loss": 6.1783,
"step": 110500
},
{
"epoch": 1.06,
"learning_rate": 8.031591974352228e-06,
"loss": 6.173,
"step": 111000
},
{
"epoch": 1.07,
"learning_rate": 8.021847380165853e-06,
"loss": 6.1811,
"step": 111500
},
{
"epoch": 1.07,
"learning_rate": 8.01210278597948e-06,
"loss": 6.1843,
"step": 112000
},
{
"epoch": 1.08,
"learning_rate": 8.002358191793104e-06,
"loss": 6.1781,
"step": 112500
},
{
"epoch": 1.08,
"learning_rate": 7.99261359760673e-06,
"loss": 6.1822,
"step": 113000
},
{
"epoch": 1.08,
"learning_rate": 7.982869003420354e-06,
"loss": 6.1703,
"step": 113500
},
{
"epoch": 1.09,
"learning_rate": 7.973124409233977e-06,
"loss": 6.1732,
"step": 114000
},
{
"epoch": 1.09,
"learning_rate": 7.963379815047602e-06,
"loss": 6.1772,
"step": 114500
},
{
"epoch": 1.1,
"learning_rate": 7.953635220861227e-06,
"loss": 6.1743,
"step": 115000
},
{
"epoch": 1.1,
"learning_rate": 7.943890626674852e-06,
"loss": 6.1747,
"step": 115500
},
{
"epoch": 1.11,
"learning_rate": 7.934146032488477e-06,
"loss": 6.1755,
"step": 116000
},
{
"epoch": 1.11,
"learning_rate": 7.924401438302102e-06,
"loss": 6.1751,
"step": 116500
},
{
"epoch": 1.12,
"learning_rate": 7.914656844115727e-06,
"loss": 6.1691,
"step": 117000
},
{
"epoch": 1.12,
"learning_rate": 7.904912249929352e-06,
"loss": 6.1718,
"step": 117500
},
{
"epoch": 1.13,
"learning_rate": 7.895167655742977e-06,
"loss": 6.1666,
"step": 118000
},
{
"epoch": 1.13,
"learning_rate": 7.885423061556602e-06,
"loss": 6.1749,
"step": 118500
},
{
"epoch": 1.14,
"learning_rate": 7.875678467370227e-06,
"loss": 6.1666,
"step": 119000
},
{
"epoch": 1.14,
"learning_rate": 7.865933873183852e-06,
"loss": 6.1728,
"step": 119500
},
{
"epoch": 1.15,
"learning_rate": 7.856189278997477e-06,
"loss": 6.1609,
"step": 120000
},
{
"epoch": 1.15,
"eval_accuracy": 0.14569243169265408,
"eval_loss": 6.162965774536133,
"eval_runtime": 1258.3298,
"eval_samples_per_second": 245.052,
"eval_steps_per_second": 4.376,
"step": 120000
},
{
"epoch": 1.15,
"learning_rate": 7.846444684811102e-06,
"loss": 6.1642,
"step": 120500
},
{
"epoch": 1.16,
"learning_rate": 7.836700090624727e-06,
"loss": 6.1629,
"step": 121000
},
{
"epoch": 1.16,
"learning_rate": 7.826955496438352e-06,
"loss": 6.1652,
"step": 121500
},
{
"epoch": 1.17,
"learning_rate": 7.817210902251976e-06,
"loss": 6.1584,
"step": 122000
},
{
"epoch": 1.17,
"learning_rate": 7.807466308065601e-06,
"loss": 6.1552,
"step": 122500
},
{
"epoch": 1.18,
"learning_rate": 7.797721713879226e-06,
"loss": 6.1598,
"step": 123000
},
{
"epoch": 1.18,
"learning_rate": 7.787977119692851e-06,
"loss": 6.1619,
"step": 123500
},
{
"epoch": 1.19,
"learning_rate": 7.778232525506476e-06,
"loss": 6.1594,
"step": 124000
},
{
"epoch": 1.19,
"learning_rate": 7.768487931320101e-06,
"loss": 6.162,
"step": 124500
},
{
"epoch": 1.19,
"learning_rate": 7.758743337133726e-06,
"loss": 6.1582,
"step": 125000
},
{
"epoch": 1.2,
"learning_rate": 7.74899874294735e-06,
"loss": 6.1543,
"step": 125500
},
{
"epoch": 1.2,
"learning_rate": 7.739254148760976e-06,
"loss": 6.1595,
"step": 126000
},
{
"epoch": 1.21,
"learning_rate": 7.729509554574601e-06,
"loss": 6.1566,
"step": 126500
},
{
"epoch": 1.21,
"learning_rate": 7.719764960388226e-06,
"loss": 6.1566,
"step": 127000
},
{
"epoch": 1.22,
"learning_rate": 7.71002036620185e-06,
"loss": 6.151,
"step": 127500
},
{
"epoch": 1.22,
"learning_rate": 7.700275772015476e-06,
"loss": 6.1534,
"step": 128000
},
{
"epoch": 1.23,
"learning_rate": 7.6905311778291e-06,
"loss": 6.1606,
"step": 128500
},
{
"epoch": 1.23,
"learning_rate": 7.680786583642726e-06,
"loss": 6.1534,
"step": 129000
},
{
"epoch": 1.24,
"learning_rate": 7.671041989456349e-06,
"loss": 6.1552,
"step": 129500
},
{
"epoch": 1.24,
"learning_rate": 7.661297395269974e-06,
"loss": 6.153,
"step": 130000
},
{
"epoch": 1.24,
"eval_accuracy": 0.1464052485172192,
"eval_loss": 6.150509834289551,
"eval_runtime": 1256.6046,
"eval_samples_per_second": 245.388,
"eval_steps_per_second": 4.382,
"step": 130000
},
{
"epoch": 1.25,
"learning_rate": 7.651552801083599e-06,
"loss": 6.1535,
"step": 130500
},
{
"epoch": 1.25,
"learning_rate": 7.641808206897224e-06,
"loss": 6.1544,
"step": 131000
},
{
"epoch": 1.26,
"learning_rate": 7.632063612710849e-06,
"loss": 6.1489,
"step": 131500
},
{
"epoch": 1.26,
"learning_rate": 7.622319018524474e-06,
"loss": 6.1475,
"step": 132000
},
{
"epoch": 1.27,
"learning_rate": 7.612574424338099e-06,
"loss": 6.151,
"step": 132500
},
{
"epoch": 1.27,
"learning_rate": 7.602829830151724e-06,
"loss": 6.1364,
"step": 133000
},
{
"epoch": 1.28,
"learning_rate": 7.593085235965348e-06,
"loss": 6.1427,
"step": 133500
},
{
"epoch": 1.28,
"learning_rate": 7.583340641778973e-06,
"loss": 6.1457,
"step": 134000
},
{
"epoch": 1.29,
"learning_rate": 7.573596047592598e-06,
"loss": 6.1515,
"step": 134500
},
{
"epoch": 1.29,
"learning_rate": 7.563851453406223e-06,
"loss": 6.1496,
"step": 135000
},
{
"epoch": 1.3,
"learning_rate": 7.554106859219849e-06,
"loss": 6.1438,
"step": 135500
},
{
"epoch": 1.3,
"learning_rate": 7.544362265033474e-06,
"loss": 6.1457,
"step": 136000
},
{
"epoch": 1.3,
"learning_rate": 7.534617670847099e-06,
"loss": 6.1441,
"step": 136500
},
{
"epoch": 1.31,
"learning_rate": 7.524873076660723e-06,
"loss": 6.1504,
"step": 137000
},
{
"epoch": 1.31,
"learning_rate": 7.515128482474348e-06,
"loss": 6.1389,
"step": 137500
},
{
"epoch": 1.32,
"learning_rate": 7.505383888287973e-06,
"loss": 6.1412,
"step": 138000
},
{
"epoch": 1.32,
"learning_rate": 7.495639294101598e-06,
"loss": 6.1351,
"step": 138500
},
{
"epoch": 1.33,
"learning_rate": 7.485894699915223e-06,
"loss": 6.1327,
"step": 139000
},
{
"epoch": 1.33,
"learning_rate": 7.4761501057288475e-06,
"loss": 6.1397,
"step": 139500
},
{
"epoch": 1.34,
"learning_rate": 7.4664055115424725e-06,
"loss": 6.142,
"step": 140000
},
{
"epoch": 1.34,
"eval_accuracy": 0.14705115677492606,
"eval_loss": 6.137972831726074,
"eval_runtime": 1277.1144,
"eval_samples_per_second": 241.447,
"eval_steps_per_second": 4.312,
"step": 140000
},
{
"epoch": 1.34,
"learning_rate": 7.456660917356097e-06,
"loss": 6.1414,
"step": 140500
},
{
"epoch": 1.35,
"learning_rate": 7.4469163231697215e-06,
"loss": 6.1369,
"step": 141000
},
{
"epoch": 1.35,
"learning_rate": 7.4371717289833464e-06,
"loss": 6.1377,
"step": 141500
},
{
"epoch": 1.36,
"learning_rate": 7.427427134796971e-06,
"loss": 6.1369,
"step": 142000
},
{
"epoch": 1.36,
"learning_rate": 7.417682540610597e-06,
"loss": 6.126,
"step": 142500
},
{
"epoch": 1.37,
"learning_rate": 7.407937946424222e-06,
"loss": 6.1332,
"step": 143000
},
{
"epoch": 1.37,
"learning_rate": 7.398193352237847e-06,
"loss": 6.1387,
"step": 143500
},
{
"epoch": 1.38,
"learning_rate": 7.388448758051472e-06,
"loss": 6.1333,
"step": 144000
},
{
"epoch": 1.38,
"learning_rate": 7.378704163865097e-06,
"loss": 6.1341,
"step": 144500
},
{
"epoch": 1.39,
"learning_rate": 7.368959569678721e-06,
"loss": 6.1395,
"step": 145000
},
{
"epoch": 1.39,
"learning_rate": 7.359214975492346e-06,
"loss": 6.1374,
"step": 145500
},
{
"epoch": 1.4,
"learning_rate": 7.349470381305971e-06,
"loss": 6.1306,
"step": 146000
},
{
"epoch": 1.4,
"learning_rate": 7.339725787119596e-06,
"loss": 6.1318,
"step": 146500
},
{
"epoch": 1.41,
"learning_rate": 7.329981192933221e-06,
"loss": 6.1314,
"step": 147000
},
{
"epoch": 1.41,
"learning_rate": 7.320236598746846e-06,
"loss": 6.1342,
"step": 147500
},
{
"epoch": 1.41,
"learning_rate": 7.310492004560471e-06,
"loss": 6.1313,
"step": 148000
},
{
"epoch": 1.42,
"learning_rate": 7.300747410374096e-06,
"loss": 6.1307,
"step": 148500
},
{
"epoch": 1.42,
"learning_rate": 7.29100281618772e-06,
"loss": 6.1264,
"step": 149000
},
{
"epoch": 1.43,
"learning_rate": 7.2812582220013454e-06,
"loss": 6.1328,
"step": 149500
},
{
"epoch": 1.43,
"learning_rate": 7.27151362781497e-06,
"loss": 6.1281,
"step": 150000
},
{
"epoch": 1.43,
"eval_accuracy": 0.1476555075167437,
"eval_loss": 6.1256866455078125,
"eval_runtime": 1266.4418,
"eval_samples_per_second": 243.482,
"eval_steps_per_second": 4.348,
"step": 150000
},
{
"epoch": 1.44,
"learning_rate": 7.261769033628595e-06,
"loss": 6.1309,
"step": 150500
},
{
"epoch": 1.44,
"learning_rate": 7.25202443944222e-06,
"loss": 6.1282,
"step": 151000
},
{
"epoch": 1.45,
"learning_rate": 7.242279845255845e-06,
"loss": 6.1302,
"step": 151500
},
{
"epoch": 1.45,
"learning_rate": 7.23253525106947e-06,
"loss": 6.1267,
"step": 152000
},
{
"epoch": 1.46,
"learning_rate": 7.222790656883095e-06,
"loss": 6.1229,
"step": 152500
},
{
"epoch": 1.46,
"learning_rate": 7.213046062696719e-06,
"loss": 6.1237,
"step": 153000
},
{
"epoch": 1.47,
"learning_rate": 7.203301468510344e-06,
"loss": 6.1166,
"step": 153500
},
{
"epoch": 1.47,
"learning_rate": 7.193556874323969e-06,
"loss": 6.1244,
"step": 154000
},
{
"epoch": 1.48,
"learning_rate": 7.183812280137594e-06,
"loss": 6.1238,
"step": 154500
},
{
"epoch": 1.48,
"learning_rate": 7.174067685951219e-06,
"loss": 6.1213,
"step": 155000
},
{
"epoch": 1.49,
"learning_rate": 7.164323091764845e-06,
"loss": 6.1163,
"step": 155500
},
{
"epoch": 1.49,
"learning_rate": 7.15457849757847e-06,
"loss": 6.1223,
"step": 156000
},
{
"epoch": 1.5,
"learning_rate": 7.1448339033920945e-06,
"loss": 6.1214,
"step": 156500
},
{
"epoch": 1.5,
"learning_rate": 7.135089309205719e-06,
"loss": 6.1184,
"step": 157000
},
{
"epoch": 1.51,
"learning_rate": 7.1253447150193436e-06,
"loss": 6.126,
"step": 157500
},
{
"epoch": 1.51,
"learning_rate": 7.1156001208329685e-06,
"loss": 6.1204,
"step": 158000
},
{
"epoch": 1.51,
"learning_rate": 7.1058555266465934e-06,
"loss": 6.1229,
"step": 158500
},
{
"epoch": 1.52,
"learning_rate": 7.096110932460218e-06,
"loss": 6.1129,
"step": 159000
},
{
"epoch": 1.52,
"learning_rate": 7.086366338273843e-06,
"loss": 6.1245,
"step": 159500
},
{
"epoch": 1.53,
"learning_rate": 7.076621744087468e-06,
"loss": 6.1173,
"step": 160000
},
{
"epoch": 1.53,
"eval_accuracy": 0.14805626641210368,
"eval_loss": 6.117273330688477,
"eval_runtime": 1261.818,
"eval_samples_per_second": 244.374,
"eval_steps_per_second": 4.364,
"step": 160000
},
{
"epoch": 1.53,
"learning_rate": 7.066877149901092e-06,
"loss": 6.1149,
"step": 160500
},
{
"epoch": 1.54,
"learning_rate": 7.057132555714717e-06,
"loss": 6.1183,
"step": 161000
},
{
"epoch": 1.54,
"learning_rate": 7.047387961528342e-06,
"loss": 6.1138,
"step": 161500
},
{
"epoch": 1.55,
"learning_rate": 7.037643367341967e-06,
"loss": 6.1181,
"step": 162000
},
{
"epoch": 1.55,
"learning_rate": 7.027898773155593e-06,
"loss": 6.1164,
"step": 162500
},
{
"epoch": 1.56,
"learning_rate": 7.018154178969218e-06,
"loss": 6.1172,
"step": 163000
},
{
"epoch": 1.56,
"learning_rate": 7.008409584782843e-06,
"loss": 6.1136,
"step": 163500
},
{
"epoch": 1.57,
"learning_rate": 6.998664990596468e-06,
"loss": 6.1127,
"step": 164000
},
{
"epoch": 1.57,
"learning_rate": 6.988920396410092e-06,
"loss": 6.1122,
"step": 164500
},
{
"epoch": 1.58,
"learning_rate": 6.979175802223717e-06,
"loss": 6.1147,
"step": 165000
},
{
"epoch": 1.58,
"learning_rate": 6.969431208037342e-06,
"loss": 6.1129,
"step": 165500
},
{
"epoch": 1.59,
"learning_rate": 6.959686613850967e-06,
"loss": 6.1144,
"step": 166000
},
{
"epoch": 1.59,
"learning_rate": 6.949942019664592e-06,
"loss": 6.1066,
"step": 166500
},
{
"epoch": 1.6,
"learning_rate": 6.9401974254782165e-06,
"loss": 6.1142,
"step": 167000
},
{
"epoch": 1.6,
"learning_rate": 6.9304528312918415e-06,
"loss": 6.1134,
"step": 167500
},
{
"epoch": 1.61,
"learning_rate": 6.920708237105466e-06,
"loss": 6.1143,
"step": 168000
},
{
"epoch": 1.61,
"learning_rate": 6.9109636429190905e-06,
"loss": 6.118,
"step": 168500
},
{
"epoch": 1.62,
"learning_rate": 6.901219048732715e-06,
"loss": 6.1147,
"step": 169000
},
{
"epoch": 1.62,
"learning_rate": 6.891474454546341e-06,
"loss": 6.1081,
"step": 169500
},
{
"epoch": 1.62,
"learning_rate": 6.881729860359966e-06,
"loss": 6.1102,
"step": 170000
},
{
"epoch": 1.62,
"eval_accuracy": 0.14886244392963902,
"eval_loss": 6.108332633972168,
"eval_runtime": 1264.5706,
"eval_samples_per_second": 243.842,
"eval_steps_per_second": 4.355,
"step": 170000
},
{
"epoch": 1.63,
"learning_rate": 6.871985266173591e-06,
"loss": 6.1099,
"step": 170500
},
{
"epoch": 1.63,
"learning_rate": 6.862240671987216e-06,
"loss": 6.1053,
"step": 171000
},
{
"epoch": 1.64,
"learning_rate": 6.852496077800841e-06,
"loss": 6.109,
"step": 171500
},
{
"epoch": 1.64,
"learning_rate": 6.842751483614466e-06,
"loss": 6.1096,
"step": 172000
},
{
"epoch": 1.65,
"learning_rate": 6.83300688942809e-06,
"loss": 6.1053,
"step": 172500
},
{
"epoch": 1.65,
"learning_rate": 6.823262295241715e-06,
"loss": 6.1078,
"step": 173000
},
{
"epoch": 1.66,
"learning_rate": 6.81351770105534e-06,
"loss": 6.1037,
"step": 173500
},
{
"epoch": 1.66,
"learning_rate": 6.803773106868965e-06,
"loss": 6.1046,
"step": 174000
},
{
"epoch": 1.67,
"learning_rate": 6.79402851268259e-06,
"loss": 6.1056,
"step": 174500
},
{
"epoch": 1.67,
"learning_rate": 6.784283918496215e-06,
"loss": 6.1012,
"step": 175000
},
{
"epoch": 1.68,
"learning_rate": 6.7745393243098404e-06,
"loss": 6.1036,
"step": 175500
},
{
"epoch": 1.68,
"learning_rate": 6.764794730123465e-06,
"loss": 6.1003,
"step": 176000
},
{
"epoch": 1.69,
"learning_rate": 6.755050135937089e-06,
"loss": 6.1039,
"step": 176500
},
{
"epoch": 1.69,
"learning_rate": 6.745305541750714e-06,
"loss": 6.1035,
"step": 177000
},
{
"epoch": 1.7,
"learning_rate": 6.735560947564339e-06,
"loss": 6.1052,
"step": 177500
},
{
"epoch": 1.7,
"learning_rate": 6.725816353377964e-06,
"loss": 6.1003,
"step": 178000
},
{
"epoch": 1.71,
"learning_rate": 6.716071759191589e-06,
"loss": 6.103,
"step": 178500
},
{
"epoch": 1.71,
"learning_rate": 6.706327165005214e-06,
"loss": 6.0978,
"step": 179000
},
{
"epoch": 1.72,
"learning_rate": 6.696582570818839e-06,
"loss": 6.0997,
"step": 179500
},
{
"epoch": 1.72,
"learning_rate": 6.686837976632463e-06,
"loss": 6.1011,
"step": 180000
},
{
"epoch": 1.72,
"eval_accuracy": 0.14866713307600812,
"eval_loss": 6.100050449371338,
"eval_runtime": 1263.9377,
"eval_samples_per_second": 243.965,
"eval_steps_per_second": 4.357,
"step": 180000
},
{
"epoch": 1.73,
"learning_rate": 6.677093382446088e-06,
"loss": 6.0977,
"step": 180500
},
{
"epoch": 1.73,
"learning_rate": 6.667348788259713e-06,
"loss": 6.0901,
"step": 181000
},
{
"epoch": 1.73,
"learning_rate": 6.657604194073338e-06,
"loss": 6.0949,
"step": 181500
},
{
"epoch": 1.74,
"learning_rate": 6.647859599886963e-06,
"loss": 6.0982,
"step": 182000
},
{
"epoch": 1.74,
"learning_rate": 6.638115005700589e-06,
"loss": 6.0934,
"step": 182500
},
{
"epoch": 1.75,
"learning_rate": 6.628370411514214e-06,
"loss": 6.1026,
"step": 183000
},
{
"epoch": 1.75,
"learning_rate": 6.618625817327839e-06,
"loss": 6.09,
"step": 183500
},
{
"epoch": 1.76,
"learning_rate": 6.608881223141463e-06,
"loss": 6.0941,
"step": 184000
},
{
"epoch": 1.76,
"learning_rate": 6.599136628955088e-06,
"loss": 6.0991,
"step": 184500
},
{
"epoch": 1.77,
"learning_rate": 6.5893920347687125e-06,
"loss": 6.0994,
"step": 185000
},
{
"epoch": 1.77,
"learning_rate": 6.5796474405823375e-06,
"loss": 6.0955,
"step": 185500
},
{
"epoch": 1.78,
"learning_rate": 6.569902846395962e-06,
"loss": 6.1052,
"step": 186000
},
{
"epoch": 1.78,
"learning_rate": 6.560158252209587e-06,
"loss": 6.0964,
"step": 186500
},
{
"epoch": 1.79,
"learning_rate": 6.550413658023212e-06,
"loss": 6.0988,
"step": 187000
},
{
"epoch": 1.79,
"learning_rate": 6.540669063836837e-06,
"loss": 6.0951,
"step": 187500
},
{
"epoch": 1.8,
"learning_rate": 6.530924469650461e-06,
"loss": 6.0929,
"step": 188000
},
{
"epoch": 1.8,
"learning_rate": 6.521179875464086e-06,
"loss": 6.0953,
"step": 188500
},
{
"epoch": 1.81,
"learning_rate": 6.511435281277711e-06,
"loss": 6.1033,
"step": 189000
},
{
"epoch": 1.81,
"learning_rate": 6.501690687091336e-06,
"loss": 6.0947,
"step": 189500
},
{
"epoch": 1.82,
"learning_rate": 6.491946092904962e-06,
"loss": 6.0869,
"step": 190000
},
{
"epoch": 1.82,
"eval_accuracy": 0.14932161334447816,
"eval_loss": 6.0932722091674805,
"eval_runtime": 1263.766,
"eval_samples_per_second": 243.998,
"eval_steps_per_second": 4.358,
"step": 190000
},
{
"epoch": 1.82,
"learning_rate": 6.482201498718587e-06,
"loss": 6.0959,
"step": 190500
},
{
"epoch": 1.83,
"learning_rate": 6.472456904532212e-06,
"loss": 6.0987,
"step": 191000
},
{
"epoch": 1.83,
"learning_rate": 6.462712310345837e-06,
"loss": 6.089,
"step": 191500
},
{
"epoch": 1.84,
"learning_rate": 6.452967716159461e-06,
"loss": 6.0887,
"step": 192000
},
{
"epoch": 1.84,
"learning_rate": 6.443223121973086e-06,
"loss": 6.0937,
"step": 192500
},
{
"epoch": 1.84,
"learning_rate": 6.433478527786711e-06,
"loss": 6.0862,
"step": 193000
},
{
"epoch": 1.85,
"learning_rate": 6.423733933600336e-06,
"loss": 6.0942,
"step": 193500
},
{
"epoch": 1.85,
"learning_rate": 6.4139893394139606e-06,
"loss": 6.087,
"step": 194000
},
{
"epoch": 1.86,
"learning_rate": 6.4042447452275855e-06,
"loss": 6.093,
"step": 194500
},
{
"epoch": 1.86,
"learning_rate": 6.3945001510412104e-06,
"loss": 6.0905,
"step": 195000
},
{
"epoch": 1.87,
"learning_rate": 6.384755556854836e-06,
"loss": 6.0929,
"step": 195500
},
{
"epoch": 1.87,
"learning_rate": 6.3750109626684595e-06,
"loss": 6.0922,
"step": 196000
},
{
"epoch": 1.88,
"learning_rate": 6.365266368482084e-06,
"loss": 6.0887,
"step": 196500
},
{
"epoch": 1.88,
"learning_rate": 6.35552177429571e-06,
"loss": 6.0905,
"step": 197000
},
{
"epoch": 1.89,
"learning_rate": 6.345777180109335e-06,
"loss": 6.0838,
"step": 197500
},
{
"epoch": 1.89,
"learning_rate": 6.33603258592296e-06,
"loss": 6.0906,
"step": 198000
},
{
"epoch": 1.9,
"learning_rate": 6.326287991736585e-06,
"loss": 6.0956,
"step": 198500
},
{
"epoch": 1.9,
"learning_rate": 6.31654339755021e-06,
"loss": 6.0854,
"step": 199000
},
{
"epoch": 1.91,
"learning_rate": 6.306798803363834e-06,
"loss": 6.0895,
"step": 199500
},
{
"epoch": 1.91,
"learning_rate": 6.297054209177459e-06,
"loss": 6.0838,
"step": 200000
},
{
"epoch": 1.91,
"eval_accuracy": 0.1494056548371956,
"eval_loss": 6.086362361907959,
"eval_runtime": 1264.6785,
"eval_samples_per_second": 243.822,
"eval_steps_per_second": 4.354,
"step": 200000
},
{
"epoch": 1.92,
"learning_rate": 6.287309614991084e-06,
"loss": 6.0885,
"step": 200500
},
{
"epoch": 1.92,
"learning_rate": 6.277565020804709e-06,
"loss": 6.0766,
"step": 201000
},
{
"epoch": 1.93,
"learning_rate": 6.267820426618334e-06,
"loss": 6.0811,
"step": 201500
},
{
"epoch": 1.93,
"learning_rate": 6.258075832431959e-06,
"loss": 6.0894,
"step": 202000
},
{
"epoch": 1.94,
"learning_rate": 6.2483312382455845e-06,
"loss": 6.0853,
"step": 202500
},
{
"epoch": 1.94,
"learning_rate": 6.238586644059209e-06,
"loss": 6.08,
"step": 203000
},
{
"epoch": 1.95,
"learning_rate": 6.228842049872833e-06,
"loss": 6.084,
"step": 203500
},
{
"epoch": 1.95,
"learning_rate": 6.2190974556864584e-06,
"loss": 6.0853,
"step": 204000
},
{
"epoch": 1.95,
"learning_rate": 6.209352861500083e-06,
"loss": 6.0782,
"step": 204500
},
{
"epoch": 1.96,
"learning_rate": 6.199608267313708e-06,
"loss": 6.0813,
"step": 205000
},
{
"epoch": 1.96,
"learning_rate": 6.189863673127333e-06,
"loss": 6.0819,
"step": 205500
},
{
"epoch": 1.97,
"learning_rate": 6.180119078940958e-06,
"loss": 6.0816,
"step": 206000
},
{
"epoch": 1.97,
"learning_rate": 6.170374484754583e-06,
"loss": 6.0792,
"step": 206500
},
{
"epoch": 1.98,
"learning_rate": 6.160629890568208e-06,
"loss": 6.0832,
"step": 207000
},
{
"epoch": 1.98,
"learning_rate": 6.150885296381832e-06,
"loss": 6.0823,
"step": 207500
},
{
"epoch": 1.99,
"learning_rate": 6.141140702195457e-06,
"loss": 6.0834,
"step": 208000
},
{
"epoch": 1.99,
"learning_rate": 6.131396108009082e-06,
"loss": 6.0869,
"step": 208500
},
{
"epoch": 2.0,
"learning_rate": 6.121651513822707e-06,
"loss": 6.0777,
"step": 209000
},
{
"epoch": 2.0,
"learning_rate": 6.111906919636332e-06,
"loss": 6.0789,
"step": 209500
},
{
"epoch": 2.01,
"learning_rate": 6.102162325449958e-06,
"loss": 6.0745,
"step": 210000
},
{
"epoch": 2.01,
"eval_accuracy": 0.14989810466180228,
"eval_loss": 6.0805253982543945,
"eval_runtime": 1262.4372,
"eval_samples_per_second": 244.255,
"eval_steps_per_second": 4.362,
"step": 210000
},
{
"epoch": 2.01,
"learning_rate": 6.092417731263583e-06,
"loss": 6.0807,
"step": 210500
},
{
"epoch": 2.02,
"learning_rate": 6.0826731370772076e-06,
"loss": 6.0779,
"step": 211000
},
{
"epoch": 2.02,
"learning_rate": 6.072928542890832e-06,
"loss": 6.0861,
"step": 211500
},
{
"epoch": 2.03,
"learning_rate": 6.063183948704457e-06,
"loss": 6.0769,
"step": 212000
},
{
"epoch": 2.03,
"learning_rate": 6.0534393545180815e-06,
"loss": 6.0766,
"step": 212500
},
{
"epoch": 2.04,
"learning_rate": 6.0436947603317065e-06,
"loss": 6.0789,
"step": 213000
},
{
"epoch": 2.04,
"learning_rate": 6.033950166145331e-06,
"loss": 6.0779,
"step": 213500
},
{
"epoch": 2.05,
"learning_rate": 6.024205571958956e-06,
"loss": 6.0747,
"step": 214000
},
{
"epoch": 2.05,
"learning_rate": 6.014460977772581e-06,
"loss": 6.0814,
"step": 214500
},
{
"epoch": 2.06,
"learning_rate": 6.004716383586206e-06,
"loss": 6.0792,
"step": 215000
},
{
"epoch": 2.06,
"learning_rate": 5.99497178939983e-06,
"loss": 6.0795,
"step": 215500
},
{
"epoch": 2.06,
"learning_rate": 5.985227195213455e-06,
"loss": 6.0777,
"step": 216000
},
{
"epoch": 2.07,
"learning_rate": 5.97548260102708e-06,
"loss": 6.0744,
"step": 216500
},
{
"epoch": 2.07,
"learning_rate": 5.965738006840706e-06,
"loss": 6.0796,
"step": 217000
},
{
"epoch": 2.08,
"learning_rate": 5.955993412654331e-06,
"loss": 6.0776,
"step": 217500
},
{
"epoch": 2.08,
"learning_rate": 5.946248818467956e-06,
"loss": 6.0787,
"step": 218000
},
{
"epoch": 2.09,
"learning_rate": 5.936504224281581e-06,
"loss": 6.0765,
"step": 218500
},
{
"epoch": 2.09,
"learning_rate": 5.926759630095206e-06,
"loss": 6.0771,
"step": 219000
},
{
"epoch": 2.1,
"learning_rate": 5.91701503590883e-06,
"loss": 6.0747,
"step": 219500
},
{
"epoch": 2.1,
"learning_rate": 5.907270441722455e-06,
"loss": 6.0757,
"step": 220000
},
{
"epoch": 2.1,
"eval_accuracy": 0.15026797990789822,
"eval_loss": 6.072300910949707,
"eval_runtime": 1262.4579,
"eval_samples_per_second": 244.251,
"eval_steps_per_second": 4.362,
"step": 220000
},
{
"epoch": 2.11,
"learning_rate": 5.89752584753608e-06,
"loss": 6.0756,
"step": 220500
},
{
"epoch": 2.11,
"learning_rate": 5.887781253349705e-06,
"loss": 6.073,
"step": 221000
},
{
"epoch": 2.12,
"learning_rate": 5.8780366591633295e-06,
"loss": 6.0707,
"step": 221500
},
{
"epoch": 2.12,
"learning_rate": 5.8682920649769545e-06,
"loss": 6.0748,
"step": 222000
},
{
"epoch": 2.13,
"learning_rate": 5.85854747079058e-06,
"loss": 6.0751,
"step": 222500
},
{
"epoch": 2.13,
"learning_rate": 5.8488028766042035e-06,
"loss": 6.076,
"step": 223000
},
{
"epoch": 2.14,
"learning_rate": 5.8390582824178284e-06,
"loss": 6.0771,
"step": 223500
},
{
"epoch": 2.14,
"learning_rate": 5.829313688231454e-06,
"loss": 6.0671,
"step": 224000
},
{
"epoch": 2.15,
"learning_rate": 5.819569094045079e-06,
"loss": 6.0676,
"step": 224500
},
{
"epoch": 2.15,
"learning_rate": 5.809824499858704e-06,
"loss": 6.0717,
"step": 225000
},
{
"epoch": 2.16,
"learning_rate": 5.800079905672329e-06,
"loss": 6.0753,
"step": 225500
},
{
"epoch": 2.16,
"learning_rate": 5.790335311485954e-06,
"loss": 6.0732,
"step": 226000
},
{
"epoch": 2.16,
"learning_rate": 5.780590717299579e-06,
"loss": 6.0717,
"step": 226500
},
{
"epoch": 2.17,
"learning_rate": 5.770846123113203e-06,
"loss": 6.0674,
"step": 227000
},
{
"epoch": 2.17,
"learning_rate": 5.761101528926828e-06,
"loss": 6.075,
"step": 227500
},
{
"epoch": 2.18,
"learning_rate": 5.751356934740453e-06,
"loss": 6.0689,
"step": 228000
},
{
"epoch": 2.18,
"learning_rate": 5.741612340554078e-06,
"loss": 6.0725,
"step": 228500
},
{
"epoch": 2.19,
"learning_rate": 5.731867746367703e-06,
"loss": 6.0701,
"step": 229000
},
{
"epoch": 2.19,
"learning_rate": 5.722123152181328e-06,
"loss": 6.0695,
"step": 229500
},
{
"epoch": 2.2,
"learning_rate": 5.7123785579949535e-06,
"loss": 6.0695,
"step": 230000
},
{
"epoch": 2.2,
"eval_accuracy": 0.15015909294832433,
"eval_loss": 6.070103645324707,
"eval_runtime": 1255.1552,
"eval_samples_per_second": 245.672,
"eval_steps_per_second": 4.388,
"step": 230000
},
{
"epoch": 2.2,
"learning_rate": 5.702633963808578e-06,
"loss": 6.0695,
"step": 230500
},
{
"epoch": 2.21,
"learning_rate": 5.6928893696222025e-06,
"loss": 6.0731,
"step": 231000
},
{
"epoch": 2.21,
"learning_rate": 5.683144775435827e-06,
"loss": 6.0664,
"step": 231500
},
{
"epoch": 2.22,
"learning_rate": 5.673400181249452e-06,
"loss": 6.0676,
"step": 232000
},
{
"epoch": 2.22,
"learning_rate": 5.663655587063077e-06,
"loss": 6.0653,
"step": 232500
},
{
"epoch": 2.23,
"learning_rate": 5.653910992876702e-06,
"loss": 6.0653,
"step": 233000
},
{
"epoch": 2.23,
"learning_rate": 5.644166398690327e-06,
"loss": 6.0663,
"step": 233500
},
{
"epoch": 2.24,
"learning_rate": 5.634421804503952e-06,
"loss": 6.0623,
"step": 234000
},
{
"epoch": 2.24,
"learning_rate": 5.624677210317577e-06,
"loss": 6.0663,
"step": 234500
},
{
"epoch": 2.25,
"learning_rate": 5.614932616131201e-06,
"loss": 6.0669,
"step": 235000
},
{
"epoch": 2.25,
"learning_rate": 5.605188021944826e-06,
"loss": 6.0577,
"step": 235500
},
{
"epoch": 2.26,
"learning_rate": 5.595443427758451e-06,
"loss": 6.0649,
"step": 236000
},
{
"epoch": 2.26,
"learning_rate": 5.585698833572076e-06,
"loss": 6.0627,
"step": 236500
},
{
"epoch": 2.27,
"learning_rate": 5.575954239385702e-06,
"loss": 6.0672,
"step": 237000
},
{
"epoch": 2.27,
"learning_rate": 5.566209645199327e-06,
"loss": 6.0626,
"step": 237500
},
{
"epoch": 2.27,
"learning_rate": 5.556465051012952e-06,
"loss": 6.0639,
"step": 238000
},
{
"epoch": 2.28,
"learning_rate": 5.5467204568265765e-06,
"loss": 6.0627,
"step": 238500
},
{
"epoch": 2.28,
"learning_rate": 5.536975862640201e-06,
"loss": 6.0678,
"step": 239000
},
{
"epoch": 2.29,
"learning_rate": 5.5272312684538256e-06,
"loss": 6.0652,
"step": 239500
},
{
"epoch": 2.29,
"learning_rate": 5.5174866742674505e-06,
"loss": 6.0595,
"step": 240000
},
{
"epoch": 2.29,
"eval_accuracy": 0.15061498048702113,
"eval_loss": 6.062320232391357,
"eval_runtime": 1257.639,
"eval_samples_per_second": 245.186,
"eval_steps_per_second": 4.379,
"step": 240000
},
{
"epoch": 2.3,
"learning_rate": 5.5077420800810754e-06,
"loss": 6.0641,
"step": 240500
},
{
"epoch": 2.3,
"learning_rate": 5.4979974858947e-06,
"loss": 6.0673,
"step": 241000
},
{
"epoch": 2.31,
"learning_rate": 5.488252891708325e-06,
"loss": 6.067,
"step": 241500
},
{
"epoch": 2.31,
"learning_rate": 5.47850829752195e-06,
"loss": 6.0643,
"step": 242000
},
{
"epoch": 2.32,
"learning_rate": 5.468763703335574e-06,
"loss": 6.0633,
"step": 242500
},
{
"epoch": 2.32,
"learning_rate": 5.459019109149199e-06,
"loss": 6.0615,
"step": 243000
},
{
"epoch": 2.33,
"learning_rate": 5.449274514962824e-06,
"loss": 6.0587,
"step": 243500
},
{
"epoch": 2.33,
"learning_rate": 5.43952992077645e-06,
"loss": 6.0637,
"step": 244000
},
{
"epoch": 2.34,
"learning_rate": 5.429785326590075e-06,
"loss": 6.062,
"step": 244500
},
{
"epoch": 2.34,
"learning_rate": 5.4200407324037e-06,
"loss": 6.0649,
"step": 245000
},
{
"epoch": 2.35,
"learning_rate": 5.410296138217325e-06,
"loss": 6.063,
"step": 245500
},
{
"epoch": 2.35,
"learning_rate": 5.40055154403095e-06,
"loss": 6.0683,
"step": 246000
},
{
"epoch": 2.36,
"learning_rate": 5.390806949844574e-06,
"loss": 6.0557,
"step": 246500
},
{
"epoch": 2.36,
"learning_rate": 5.381062355658199e-06,
"loss": 6.0544,
"step": 247000
},
{
"epoch": 2.37,
"learning_rate": 5.371317761471824e-06,
"loss": 6.0587,
"step": 247500
},
{
"epoch": 2.37,
"learning_rate": 5.361573167285449e-06,
"loss": 6.0521,
"step": 248000
},
{
"epoch": 2.38,
"learning_rate": 5.3518285730990736e-06,
"loss": 6.0639,
"step": 248500
},
{
"epoch": 2.38,
"learning_rate": 5.3420839789126985e-06,
"loss": 6.0537,
"step": 249000
},
{
"epoch": 2.38,
"learning_rate": 5.3323393847263234e-06,
"loss": 6.0514,
"step": 249500
},
{
"epoch": 2.39,
"learning_rate": 5.322594790539949e-06,
"loss": 6.0579,
"step": 250000
},
{
"epoch": 2.39,
"eval_accuracy": 0.15058644205297042,
"eval_loss": 6.058152675628662,
"eval_runtime": 1262.6732,
"eval_samples_per_second": 244.209,
"eval_steps_per_second": 4.361,
"step": 250000
},
{
"epoch": 2.39,
"learning_rate": 5.3128501963535725e-06,
"loss": 6.0545,
"step": 250500
},
{
"epoch": 2.4,
"learning_rate": 5.303105602167197e-06,
"loss": 6.0528,
"step": 251000
},
{
"epoch": 2.4,
"learning_rate": 5.293361007980823e-06,
"loss": 6.061,
"step": 251500
},
{
"epoch": 2.41,
"learning_rate": 5.283616413794448e-06,
"loss": 6.0573,
"step": 252000
},
{
"epoch": 2.41,
"learning_rate": 5.273871819608073e-06,
"loss": 6.0583,
"step": 252500
},
{
"epoch": 2.42,
"learning_rate": 5.264127225421698e-06,
"loss": 6.0572,
"step": 253000
},
{
"epoch": 2.42,
"learning_rate": 5.254382631235323e-06,
"loss": 6.0572,
"step": 253500
},
{
"epoch": 2.43,
"learning_rate": 5.244638037048948e-06,
"loss": 6.0553,
"step": 254000
},
{
"epoch": 2.43,
"learning_rate": 5.234893442862572e-06,
"loss": 6.0612,
"step": 254500
},
{
"epoch": 2.44,
"learning_rate": 5.225148848676197e-06,
"loss": 6.0576,
"step": 255000
},
{
"epoch": 2.44,
"learning_rate": 5.215404254489822e-06,
"loss": 6.053,
"step": 255500
},
{
"epoch": 2.45,
"learning_rate": 5.205659660303447e-06,
"loss": 6.0503,
"step": 256000
},
{
"epoch": 2.45,
"learning_rate": 5.195915066117072e-06,
"loss": 6.056,
"step": 256500
},
{
"epoch": 2.46,
"learning_rate": 5.1861704719306975e-06,
"loss": 6.055,
"step": 257000
},
{
"epoch": 2.46,
"learning_rate": 5.1764258777443224e-06,
"loss": 6.0532,
"step": 257500
},
{
"epoch": 2.47,
"learning_rate": 5.166681283557947e-06,
"loss": 6.0573,
"step": 258000
},
{
"epoch": 2.47,
"learning_rate": 5.1569366893715715e-06,
"loss": 6.0572,
"step": 258500
},
{
"epoch": 2.48,
"learning_rate": 5.147192095185196e-06,
"loss": 6.0548,
"step": 259000
},
{
"epoch": 2.48,
"learning_rate": 5.137447500998821e-06,
"loss": 6.0491,
"step": 259500
},
{
"epoch": 2.49,
"learning_rate": 5.127702906812446e-06,
"loss": 6.0534,
"step": 260000
},
{
"epoch": 2.49,
"eval_accuracy": 0.15091923598095108,
"eval_loss": 6.0526041984558105,
"eval_runtime": 1264.011,
"eval_samples_per_second": 243.95,
"eval_steps_per_second": 4.357,
"step": 260000
},
{
"epoch": 2.49,
"learning_rate": 5.117958312626071e-06,
"loss": 6.0461,
"step": 260500
},
{
"epoch": 2.49,
"learning_rate": 5.108213718439696e-06,
"loss": 6.0567,
"step": 261000
},
{
"epoch": 2.5,
"learning_rate": 5.098469124253321e-06,
"loss": 6.0543,
"step": 261500
},
{
"epoch": 2.5,
"learning_rate": 5.088724530066946e-06,
"loss": 6.0567,
"step": 262000
},
{
"epoch": 2.51,
"learning_rate": 5.07897993588057e-06,
"loss": 6.063,
"step": 262500
},
{
"epoch": 2.51,
"learning_rate": 5.069235341694195e-06,
"loss": 6.0551,
"step": 263000
},
{
"epoch": 2.52,
"learning_rate": 5.05949074750782e-06,
"loss": 6.0508,
"step": 263500
},
{
"epoch": 2.52,
"learning_rate": 5.049746153321446e-06,
"loss": 6.0539,
"step": 264000
},
{
"epoch": 2.53,
"learning_rate": 5.040001559135071e-06,
"loss": 6.0517,
"step": 264500
},
{
"epoch": 2.53,
"learning_rate": 5.030256964948696e-06,
"loss": 6.05,
"step": 265000
},
{
"epoch": 2.54,
"learning_rate": 5.0205123707623206e-06,
"loss": 6.0431,
"step": 265500
},
{
"epoch": 2.54,
"learning_rate": 5.010767776575945e-06,
"loss": 6.0507,
"step": 266000
},
{
"epoch": 2.55,
"learning_rate": 5.00102318238957e-06,
"loss": 6.0504,
"step": 266500
},
{
"epoch": 2.55,
"learning_rate": 4.9912785882031945e-06,
"loss": 6.0525,
"step": 267000
},
{
"epoch": 2.56,
"learning_rate": 4.9815339940168195e-06,
"loss": 6.046,
"step": 267500
},
{
"epoch": 2.56,
"learning_rate": 4.971789399830444e-06,
"loss": 6.0433,
"step": 268000
},
{
"epoch": 2.57,
"learning_rate": 4.962044805644069e-06,
"loss": 6.0478,
"step": 268500
},
{
"epoch": 2.57,
"learning_rate": 4.952300211457694e-06,
"loss": 6.0492,
"step": 269000
},
{
"epoch": 2.58,
"learning_rate": 4.942555617271319e-06,
"loss": 6.0465,
"step": 269500
},
{
"epoch": 2.58,
"learning_rate": 4.932811023084944e-06,
"loss": 6.0465,
"step": 270000
},
{
"epoch": 2.58,
"eval_accuracy": 0.15103269525406562,
"eval_loss": 6.043306350708008,
"eval_runtime": 1262.6283,
"eval_samples_per_second": 244.218,
"eval_steps_per_second": 4.362,
"step": 270000
},
{
"epoch": 2.58,
"step": 270001,
"total_flos": 1.9873932020343112e+18,
"train_loss": 6.298876106775028,
"train_runtime": 198451.5423,
"train_samples_per_second": 147.612,
"train_steps_per_second": 2.636
}
],
"logging_steps": 500,
"max_steps": 523105,
"num_train_epochs": 5,
"save_steps": 10000,
"total_flos": 1.9873932020343112e+18,
"trial_name": null,
"trial_params": null
}