coqui / last-checkpoint /trainer_state.json
dq158's picture
Training in progress, epoch 5, checkpoint
45891c1
raw
history blame
No virus
52 kB
{
"best_metric": 2.995251417160034,
"best_model_checkpoint": "dq158/coqui/checkpoint-201740",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 201740,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 4.5486,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 7.999996629129878e-05,
"loss": 3.9512,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 7.999986516525194e-05,
"loss": 3.7313,
"step": 1500
},
{
"epoch": 0.05,
"learning_rate": 7.999969662202991e-05,
"loss": 3.6577,
"step": 2000
},
{
"epoch": 0.06,
"learning_rate": 7.999946066191677e-05,
"loss": 3.5469,
"step": 2500
},
{
"epoch": 0.07,
"learning_rate": 7.999915728531019e-05,
"loss": 3.7429,
"step": 3000
},
{
"epoch": 0.09,
"learning_rate": 7.999878649272152e-05,
"loss": 3.5995,
"step": 3500
},
{
"epoch": 0.1,
"learning_rate": 7.99983482847757e-05,
"loss": 3.4906,
"step": 4000
},
{
"epoch": 0.11,
"learning_rate": 7.999784266221129e-05,
"loss": 3.6012,
"step": 4500
},
{
"epoch": 0.12,
"learning_rate": 7.99972696258805e-05,
"loss": 3.4275,
"step": 5000
},
{
"epoch": 0.14,
"learning_rate": 7.999662917674914e-05,
"loss": 3.5431,
"step": 5500
},
{
"epoch": 0.15,
"learning_rate": 7.999592131589664e-05,
"loss": 3.4628,
"step": 6000
},
{
"epoch": 0.16,
"learning_rate": 7.999514604451606e-05,
"loss": 3.5663,
"step": 6500
},
{
"epoch": 0.17,
"learning_rate": 7.999430336391406e-05,
"loss": 3.4909,
"step": 7000
},
{
"epoch": 0.19,
"learning_rate": 7.999339327551093e-05,
"loss": 3.4715,
"step": 7500
},
{
"epoch": 0.2,
"learning_rate": 7.999241578084059e-05,
"loss": 3.4117,
"step": 8000
},
{
"epoch": 0.21,
"learning_rate": 7.999137088155049e-05,
"loss": 3.5166,
"step": 8500
},
{
"epoch": 0.22,
"learning_rate": 7.999025857940177e-05,
"loss": 3.4116,
"step": 9000
},
{
"epoch": 0.24,
"learning_rate": 7.998907887626916e-05,
"loss": 3.4845,
"step": 9500
},
{
"epoch": 0.25,
"learning_rate": 7.998783177414093e-05,
"loss": 3.5398,
"step": 10000
},
{
"epoch": 0.26,
"learning_rate": 7.998651727511902e-05,
"loss": 3.4251,
"step": 10500
},
{
"epoch": 0.27,
"learning_rate": 7.998513538141894e-05,
"loss": 3.4268,
"step": 11000
},
{
"epoch": 0.29,
"learning_rate": 7.998368609536976e-05,
"loss": 3.4133,
"step": 11500
},
{
"epoch": 0.3,
"learning_rate": 7.998216941941417e-05,
"loss": 3.4393,
"step": 12000
},
{
"epoch": 0.31,
"learning_rate": 7.998058535610842e-05,
"loss": 3.3059,
"step": 12500
},
{
"epoch": 0.32,
"learning_rate": 7.997893390812236e-05,
"loss": 3.3631,
"step": 13000
},
{
"epoch": 0.33,
"learning_rate": 7.997721507823938e-05,
"loss": 3.391,
"step": 13500
},
{
"epoch": 0.35,
"learning_rate": 7.997542886935647e-05,
"loss": 3.3573,
"step": 14000
},
{
"epoch": 0.36,
"learning_rate": 7.997357528448417e-05,
"loss": 3.3698,
"step": 14500
},
{
"epoch": 0.37,
"learning_rate": 7.997165432674656e-05,
"loss": 3.2463,
"step": 15000
},
{
"epoch": 0.38,
"learning_rate": 7.996966599938132e-05,
"loss": 3.3657,
"step": 15500
},
{
"epoch": 0.4,
"learning_rate": 7.996761030573961e-05,
"loss": 3.404,
"step": 16000
},
{
"epoch": 0.41,
"learning_rate": 7.99654872492862e-05,
"loss": 3.3893,
"step": 16500
},
{
"epoch": 0.42,
"learning_rate": 7.996329683359935e-05,
"loss": 3.3423,
"step": 17000
},
{
"epoch": 0.43,
"learning_rate": 7.996103906237084e-05,
"loss": 3.238,
"step": 17500
},
{
"epoch": 0.45,
"learning_rate": 7.995871393940603e-05,
"loss": 3.2994,
"step": 18000
},
{
"epoch": 0.46,
"learning_rate": 7.995632146862375e-05,
"loss": 3.2948,
"step": 18500
},
{
"epoch": 0.47,
"learning_rate": 7.995386165405639e-05,
"loss": 3.2603,
"step": 19000
},
{
"epoch": 0.48,
"learning_rate": 7.995133449984973e-05,
"loss": 3.3748,
"step": 19500
},
{
"epoch": 0.5,
"learning_rate": 7.99487400102632e-05,
"loss": 3.3827,
"step": 20000
},
{
"epoch": 0.51,
"learning_rate": 7.99460781896696e-05,
"loss": 3.2538,
"step": 20500
},
{
"epoch": 0.52,
"learning_rate": 7.994334904255528e-05,
"loss": 3.2942,
"step": 21000
},
{
"epoch": 0.53,
"learning_rate": 7.994055257352003e-05,
"loss": 3.439,
"step": 21500
},
{
"epoch": 0.55,
"learning_rate": 7.993768878727711e-05,
"loss": 3.2844,
"step": 22000
},
{
"epoch": 0.56,
"learning_rate": 7.993475768865324e-05,
"loss": 3.4043,
"step": 22500
},
{
"epoch": 0.57,
"learning_rate": 7.993175928258863e-05,
"loss": 3.2896,
"step": 23000
},
{
"epoch": 0.58,
"learning_rate": 7.992869357413687e-05,
"loss": 3.3379,
"step": 23500
},
{
"epoch": 0.59,
"learning_rate": 7.992556056846502e-05,
"loss": 3.3279,
"step": 24000
},
{
"epoch": 0.61,
"learning_rate": 7.992236027085355e-05,
"loss": 3.3186,
"step": 24500
},
{
"epoch": 0.62,
"learning_rate": 7.991909268669638e-05,
"loss": 3.2858,
"step": 25000
},
{
"epoch": 0.63,
"learning_rate": 7.991575782150078e-05,
"loss": 3.366,
"step": 25500
},
{
"epoch": 0.64,
"learning_rate": 7.991235568088746e-05,
"loss": 3.2549,
"step": 26000
},
{
"epoch": 0.66,
"learning_rate": 7.990888627059051e-05,
"loss": 3.3427,
"step": 26500
},
{
"epoch": 0.67,
"learning_rate": 7.990534959645739e-05,
"loss": 3.2713,
"step": 27000
},
{
"epoch": 0.68,
"learning_rate": 7.990174566444893e-05,
"loss": 3.2461,
"step": 27500
},
{
"epoch": 0.69,
"learning_rate": 7.989807448063936e-05,
"loss": 3.2944,
"step": 28000
},
{
"epoch": 0.71,
"learning_rate": 7.989433605121617e-05,
"loss": 3.3129,
"step": 28500
},
{
"epoch": 0.72,
"learning_rate": 7.989053038248027e-05,
"loss": 3.268,
"step": 29000
},
{
"epoch": 0.73,
"learning_rate": 7.988665748084586e-05,
"loss": 3.3362,
"step": 29500
},
{
"epoch": 0.74,
"learning_rate": 7.988271735284046e-05,
"loss": 3.2817,
"step": 30000
},
{
"epoch": 0.76,
"learning_rate": 7.987871000510492e-05,
"loss": 3.359,
"step": 30500
},
{
"epoch": 0.77,
"learning_rate": 7.987463544439334e-05,
"loss": 3.2771,
"step": 31000
},
{
"epoch": 0.78,
"learning_rate": 7.987049367757314e-05,
"loss": 3.3784,
"step": 31500
},
{
"epoch": 0.79,
"learning_rate": 7.9866284711625e-05,
"loss": 3.3053,
"step": 32000
},
{
"epoch": 0.81,
"learning_rate": 7.986200855364284e-05,
"loss": 3.3062,
"step": 32500
},
{
"epoch": 0.82,
"learning_rate": 7.985766521083388e-05,
"loss": 3.2485,
"step": 33000
},
{
"epoch": 0.83,
"learning_rate": 7.985325469051851e-05,
"loss": 3.2577,
"step": 33500
},
{
"epoch": 0.84,
"learning_rate": 7.98487770001304e-05,
"loss": 3.3197,
"step": 34000
},
{
"epoch": 0.86,
"learning_rate": 7.984423214721638e-05,
"loss": 3.206,
"step": 34500
},
{
"epoch": 0.87,
"learning_rate": 7.983962013943654e-05,
"loss": 3.3556,
"step": 35000
},
{
"epoch": 0.88,
"learning_rate": 7.983494098456408e-05,
"loss": 3.3232,
"step": 35500
},
{
"epoch": 0.89,
"learning_rate": 7.983019469048544e-05,
"loss": 3.2438,
"step": 36000
},
{
"epoch": 0.9,
"learning_rate": 7.982538126520019e-05,
"loss": 3.3,
"step": 36500
},
{
"epoch": 0.92,
"learning_rate": 7.982050071682102e-05,
"loss": 3.3622,
"step": 37000
},
{
"epoch": 0.93,
"learning_rate": 7.981555305357381e-05,
"loss": 3.2414,
"step": 37500
},
{
"epoch": 0.94,
"learning_rate": 7.981053828379751e-05,
"loss": 3.3854,
"step": 38000
},
{
"epoch": 0.95,
"learning_rate": 7.980545641594418e-05,
"loss": 3.2529,
"step": 38500
},
{
"epoch": 0.97,
"learning_rate": 7.9800307458579e-05,
"loss": 3.3274,
"step": 39000
},
{
"epoch": 0.98,
"learning_rate": 7.979509142038018e-05,
"loss": 3.2614,
"step": 39500
},
{
"epoch": 0.99,
"learning_rate": 7.978980831013903e-05,
"loss": 3.3069,
"step": 40000
},
{
"epoch": 1.0,
"eval_bleu": 1.0,
"eval_brevity_penalty": 1.0,
"eval_length_ratio": 1.0,
"eval_loss": 3.12583589553833,
"eval_precisions": [
1.0,
1.0,
1.0,
1.0
],
"eval_reference_length": 4591104,
"eval_runtime": 8030.2897,
"eval_samples_per_second": 1.117,
"eval_steps_per_second": 0.558,
"eval_translation_length": 4591104,
"step": 40348
},
{
"epoch": 1.0,
"learning_rate": 7.978445813675987e-05,
"loss": 3.2673,
"step": 40500
},
{
"epoch": 1.02,
"learning_rate": 7.977904090926009e-05,
"loss": 3.3218,
"step": 41000
},
{
"epoch": 1.03,
"learning_rate": 7.977355663677008e-05,
"loss": 3.1583,
"step": 41500
},
{
"epoch": 1.04,
"learning_rate": 7.97680053285332e-05,
"loss": 3.2518,
"step": 42000
},
{
"epoch": 1.05,
"learning_rate": 7.976238699390583e-05,
"loss": 3.2414,
"step": 42500
},
{
"epoch": 1.07,
"learning_rate": 7.975670164235732e-05,
"loss": 3.2775,
"step": 43000
},
{
"epoch": 1.08,
"learning_rate": 7.975094928346996e-05,
"loss": 3.1861,
"step": 43500
},
{
"epoch": 1.09,
"learning_rate": 7.974512992693896e-05,
"loss": 3.1894,
"step": 44000
},
{
"epoch": 1.1,
"learning_rate": 7.973924358257246e-05,
"loss": 3.2074,
"step": 44500
},
{
"epoch": 1.12,
"learning_rate": 7.973329026029155e-05,
"loss": 3.2695,
"step": 45000
},
{
"epoch": 1.13,
"learning_rate": 7.972726997013014e-05,
"loss": 3.3168,
"step": 45500
},
{
"epoch": 1.14,
"learning_rate": 7.972118272223505e-05,
"loss": 3.2341,
"step": 46000
},
{
"epoch": 1.15,
"learning_rate": 7.971502852686593e-05,
"loss": 3.2581,
"step": 46500
},
{
"epoch": 1.16,
"learning_rate": 7.970880739439528e-05,
"loss": 3.2041,
"step": 47000
},
{
"epoch": 1.18,
"learning_rate": 7.970251933530842e-05,
"loss": 3.2144,
"step": 47500
},
{
"epoch": 1.19,
"learning_rate": 7.969616436020346e-05,
"loss": 3.2718,
"step": 48000
},
{
"epoch": 1.2,
"learning_rate": 7.96897424797913e-05,
"loss": 3.186,
"step": 48500
},
{
"epoch": 1.21,
"learning_rate": 7.968325370489561e-05,
"loss": 3.1968,
"step": 49000
},
{
"epoch": 1.23,
"learning_rate": 7.967669804645278e-05,
"loss": 3.2777,
"step": 49500
},
{
"epoch": 1.24,
"learning_rate": 7.967007551551196e-05,
"loss": 3.2775,
"step": 50000
},
{
"epoch": 1.25,
"learning_rate": 7.9663386123235e-05,
"loss": 3.2174,
"step": 50500
},
{
"epoch": 1.26,
"learning_rate": 7.965662988089642e-05,
"loss": 3.2144,
"step": 51000
},
{
"epoch": 1.28,
"learning_rate": 7.964980679988345e-05,
"loss": 3.3125,
"step": 51500
},
{
"epoch": 1.29,
"learning_rate": 7.964291689169593e-05,
"loss": 3.1662,
"step": 52000
},
{
"epoch": 1.3,
"learning_rate": 7.963596016794635e-05,
"loss": 3.223,
"step": 52500
},
{
"epoch": 1.31,
"learning_rate": 7.962893664035984e-05,
"loss": 3.1838,
"step": 53000
},
{
"epoch": 1.33,
"learning_rate": 7.962184632077407e-05,
"loss": 3.3471,
"step": 53500
},
{
"epoch": 1.34,
"learning_rate": 7.961468922113935e-05,
"loss": 3.1718,
"step": 54000
},
{
"epoch": 1.35,
"learning_rate": 7.960746535351847e-05,
"loss": 3.2135,
"step": 54500
},
{
"epoch": 1.36,
"learning_rate": 7.96001747300868e-05,
"loss": 3.1969,
"step": 55000
},
{
"epoch": 1.38,
"learning_rate": 7.959281736313223e-05,
"loss": 3.2402,
"step": 55500
},
{
"epoch": 1.39,
"learning_rate": 7.958539326505511e-05,
"loss": 3.2797,
"step": 56000
},
{
"epoch": 1.4,
"learning_rate": 7.957790244836829e-05,
"loss": 3.2674,
"step": 56500
},
{
"epoch": 1.41,
"learning_rate": 7.957034492569703e-05,
"loss": 3.1757,
"step": 57000
},
{
"epoch": 1.43,
"learning_rate": 7.956272070977906e-05,
"loss": 3.2459,
"step": 57500
},
{
"epoch": 1.44,
"learning_rate": 7.955502981346449e-05,
"loss": 3.2732,
"step": 58000
},
{
"epoch": 1.45,
"learning_rate": 7.954727224971583e-05,
"loss": 3.1479,
"step": 58500
},
{
"epoch": 1.46,
"learning_rate": 7.953944803160796e-05,
"loss": 3.2534,
"step": 59000
},
{
"epoch": 1.47,
"learning_rate": 7.953155717232809e-05,
"loss": 3.26,
"step": 59500
},
{
"epoch": 1.49,
"learning_rate": 7.952359968517573e-05,
"loss": 3.1955,
"step": 60000
},
{
"epoch": 1.5,
"learning_rate": 7.951557558356275e-05,
"loss": 3.1423,
"step": 60500
},
{
"epoch": 1.51,
"learning_rate": 7.95074848810132e-05,
"loss": 3.2203,
"step": 61000
},
{
"epoch": 1.52,
"learning_rate": 7.949932759116346e-05,
"loss": 3.2274,
"step": 61500
},
{
"epoch": 1.54,
"learning_rate": 7.949110372776213e-05,
"loss": 3.2456,
"step": 62000
},
{
"epoch": 1.55,
"learning_rate": 7.948281330466996e-05,
"loss": 3.2285,
"step": 62500
},
{
"epoch": 1.56,
"learning_rate": 7.947445633585995e-05,
"loss": 3.1965,
"step": 63000
},
{
"epoch": 1.57,
"learning_rate": 7.946603283541722e-05,
"loss": 3.2021,
"step": 63500
},
{
"epoch": 1.59,
"learning_rate": 7.945754281753901e-05,
"loss": 3.1108,
"step": 64000
},
{
"epoch": 1.6,
"learning_rate": 7.944898629653475e-05,
"loss": 3.1778,
"step": 64500
},
{
"epoch": 1.61,
"learning_rate": 7.944036328682583e-05,
"loss": 3.2267,
"step": 65000
},
{
"epoch": 1.62,
"learning_rate": 7.943167380294583e-05,
"loss": 3.1233,
"step": 65500
},
{
"epoch": 1.64,
"learning_rate": 7.942291785954028e-05,
"loss": 3.3035,
"step": 66000
},
{
"epoch": 1.65,
"learning_rate": 7.941409547136677e-05,
"loss": 3.1858,
"step": 66500
},
{
"epoch": 1.66,
"learning_rate": 7.940520665329483e-05,
"loss": 3.122,
"step": 67000
},
{
"epoch": 1.67,
"learning_rate": 7.939625142030604e-05,
"loss": 3.2538,
"step": 67500
},
{
"epoch": 1.69,
"learning_rate": 7.93872297874938e-05,
"loss": 3.1382,
"step": 68000
},
{
"epoch": 1.7,
"learning_rate": 7.937814177006355e-05,
"loss": 3.169,
"step": 68500
},
{
"epoch": 1.71,
"learning_rate": 7.936898738333253e-05,
"loss": 3.0855,
"step": 69000
},
{
"epoch": 1.72,
"learning_rate": 7.935976664272985e-05,
"loss": 3.2122,
"step": 69500
},
{
"epoch": 1.73,
"learning_rate": 7.935047956379646e-05,
"loss": 3.1769,
"step": 70000
},
{
"epoch": 1.75,
"learning_rate": 7.934112616218515e-05,
"loss": 3.2102,
"step": 70500
},
{
"epoch": 1.76,
"learning_rate": 7.933170645366047e-05,
"loss": 3.2092,
"step": 71000
},
{
"epoch": 1.77,
"learning_rate": 7.932222045409874e-05,
"loss": 3.195,
"step": 71500
},
{
"epoch": 1.78,
"learning_rate": 7.931266817948795e-05,
"loss": 3.1975,
"step": 72000
},
{
"epoch": 1.8,
"learning_rate": 7.930304964592788e-05,
"loss": 3.3457,
"step": 72500
},
{
"epoch": 1.81,
"learning_rate": 7.929336486962994e-05,
"loss": 3.0512,
"step": 73000
},
{
"epoch": 1.82,
"learning_rate": 7.928361386691718e-05,
"loss": 3.2071,
"step": 73500
},
{
"epoch": 1.83,
"learning_rate": 7.927379665422429e-05,
"loss": 3.2991,
"step": 74000
},
{
"epoch": 1.85,
"learning_rate": 7.926391324809754e-05,
"loss": 3.1947,
"step": 74500
},
{
"epoch": 1.86,
"learning_rate": 7.925396366519476e-05,
"loss": 3.2052,
"step": 75000
},
{
"epoch": 1.87,
"learning_rate": 7.924394792228533e-05,
"loss": 3.1196,
"step": 75500
},
{
"epoch": 1.88,
"learning_rate": 7.923386603625016e-05,
"loss": 3.1718,
"step": 76000
},
{
"epoch": 1.9,
"learning_rate": 7.922371802408158e-05,
"loss": 3.1563,
"step": 76500
},
{
"epoch": 1.91,
"learning_rate": 7.921350390288342e-05,
"loss": 3.2303,
"step": 77000
},
{
"epoch": 1.92,
"learning_rate": 7.920322368987093e-05,
"loss": 3.1139,
"step": 77500
},
{
"epoch": 1.93,
"learning_rate": 7.919287740237071e-05,
"loss": 3.207,
"step": 78000
},
{
"epoch": 1.95,
"learning_rate": 7.918246505782079e-05,
"loss": 3.1756,
"step": 78500
},
{
"epoch": 1.96,
"learning_rate": 7.917198667377047e-05,
"loss": 3.0951,
"step": 79000
},
{
"epoch": 1.97,
"learning_rate": 7.916144226788041e-05,
"loss": 3.2165,
"step": 79500
},
{
"epoch": 1.98,
"learning_rate": 7.915083185792251e-05,
"loss": 3.1236,
"step": 80000
},
{
"epoch": 2.0,
"learning_rate": 7.914015546177993e-05,
"loss": 3.1342,
"step": 80500
},
{
"epoch": 2.0,
"eval_bleu": 1.0,
"eval_brevity_penalty": 1.0,
"eval_length_ratio": 1.0,
"eval_loss": 3.0691702365875244,
"eval_precisions": [
1.0,
1.0,
1.0,
1.0
],
"eval_reference_length": 4591104,
"eval_runtime": 8264.3842,
"eval_samples_per_second": 1.085,
"eval_steps_per_second": 0.543,
"eval_translation_length": 4591104,
"step": 80696
},
{
"epoch": 2.01,
"learning_rate": 7.912941309744704e-05,
"loss": 3.1234,
"step": 81000
},
{
"epoch": 2.02,
"learning_rate": 7.91186047830294e-05,
"loss": 3.1118,
"step": 81500
},
{
"epoch": 2.03,
"learning_rate": 7.910773053674371e-05,
"loss": 3.1879,
"step": 82000
},
{
"epoch": 2.04,
"learning_rate": 7.909679037691783e-05,
"loss": 3.2032,
"step": 82500
},
{
"epoch": 2.06,
"learning_rate": 7.908578432199069e-05,
"loss": 3.1009,
"step": 83000
},
{
"epoch": 2.07,
"learning_rate": 7.907471239051224e-05,
"loss": 3.0688,
"step": 83500
},
{
"epoch": 2.08,
"learning_rate": 7.906357460114355e-05,
"loss": 3.0835,
"step": 84000
},
{
"epoch": 2.09,
"learning_rate": 7.90523709726566e-05,
"loss": 3.1157,
"step": 84500
},
{
"epoch": 2.11,
"learning_rate": 7.90411015239344e-05,
"loss": 3.0581,
"step": 85000
},
{
"epoch": 2.12,
"learning_rate": 7.902976627397088e-05,
"loss": 3.206,
"step": 85500
},
{
"epoch": 2.13,
"learning_rate": 7.901836524187085e-05,
"loss": 3.2185,
"step": 86000
},
{
"epoch": 2.14,
"learning_rate": 7.900689844685002e-05,
"loss": 3.1204,
"step": 86500
},
{
"epoch": 2.16,
"learning_rate": 7.899536590823493e-05,
"loss": 3.2066,
"step": 87000
},
{
"epoch": 2.17,
"learning_rate": 7.898376764546293e-05,
"loss": 3.1684,
"step": 87500
},
{
"epoch": 2.18,
"learning_rate": 7.89721036780821e-05,
"loss": 3.1742,
"step": 88000
},
{
"epoch": 2.19,
"learning_rate": 7.896037402575136e-05,
"loss": 3.1598,
"step": 88500
},
{
"epoch": 2.21,
"learning_rate": 7.894857870824023e-05,
"loss": 3.0966,
"step": 89000
},
{
"epoch": 2.22,
"learning_rate": 7.893671774542899e-05,
"loss": 3.2035,
"step": 89500
},
{
"epoch": 2.23,
"learning_rate": 7.892479115730848e-05,
"loss": 3.215,
"step": 90000
},
{
"epoch": 2.24,
"learning_rate": 7.891279896398023e-05,
"loss": 3.153,
"step": 90500
},
{
"epoch": 2.26,
"learning_rate": 7.890074118565626e-05,
"loss": 3.1019,
"step": 91000
},
{
"epoch": 2.27,
"learning_rate": 7.88886178426592e-05,
"loss": 3.1509,
"step": 91500
},
{
"epoch": 2.28,
"learning_rate": 7.887642895542218e-05,
"loss": 3.1699,
"step": 92000
},
{
"epoch": 2.29,
"learning_rate": 7.886417454448872e-05,
"loss": 3.1162,
"step": 92500
},
{
"epoch": 2.3,
"learning_rate": 7.885185463051289e-05,
"loss": 3.1782,
"step": 93000
},
{
"epoch": 2.32,
"learning_rate": 7.883946923425907e-05,
"loss": 3.1546,
"step": 93500
},
{
"epoch": 2.33,
"learning_rate": 7.882701837660205e-05,
"loss": 3.1551,
"step": 94000
},
{
"epoch": 2.34,
"learning_rate": 7.881450207852696e-05,
"loss": 3.1327,
"step": 94500
},
{
"epoch": 2.35,
"learning_rate": 7.880192036112917e-05,
"loss": 3.0316,
"step": 95000
},
{
"epoch": 2.37,
"learning_rate": 7.878927324561437e-05,
"loss": 3.1897,
"step": 95500
},
{
"epoch": 2.38,
"learning_rate": 7.877656075329846e-05,
"loss": 3.1447,
"step": 96000
},
{
"epoch": 2.39,
"learning_rate": 7.876378290560751e-05,
"loss": 3.1764,
"step": 96500
},
{
"epoch": 2.4,
"learning_rate": 7.875093972407774e-05,
"loss": 3.1213,
"step": 97000
},
{
"epoch": 2.42,
"learning_rate": 7.873803123035553e-05,
"loss": 3.0774,
"step": 97500
},
{
"epoch": 2.43,
"learning_rate": 7.872505744619728e-05,
"loss": 3.1127,
"step": 98000
},
{
"epoch": 2.44,
"learning_rate": 7.871201839346947e-05,
"loss": 3.2621,
"step": 98500
},
{
"epoch": 2.45,
"learning_rate": 7.869891409414858e-05,
"loss": 3.2113,
"step": 99000
},
{
"epoch": 2.47,
"learning_rate": 7.868574457032106e-05,
"loss": 3.1218,
"step": 99500
},
{
"epoch": 2.48,
"learning_rate": 7.867250984418328e-05,
"loss": 3.1409,
"step": 100000
},
{
"epoch": 2.49,
"learning_rate": 7.86592099380415e-05,
"loss": 3.073,
"step": 100500
},
{
"epoch": 2.5,
"learning_rate": 7.864584487431186e-05,
"loss": 3.1624,
"step": 101000
},
{
"epoch": 2.52,
"learning_rate": 7.863241467552032e-05,
"loss": 3.2052,
"step": 101500
},
{
"epoch": 2.53,
"learning_rate": 7.861891936430258e-05,
"loss": 3.1714,
"step": 102000
},
{
"epoch": 2.54,
"learning_rate": 7.860535896340414e-05,
"loss": 3.1728,
"step": 102500
},
{
"epoch": 2.55,
"learning_rate": 7.859173349568015e-05,
"loss": 3.1564,
"step": 103000
},
{
"epoch": 2.57,
"learning_rate": 7.857804298409547e-05,
"loss": 3.0868,
"step": 103500
},
{
"epoch": 2.58,
"learning_rate": 7.856428745172455e-05,
"loss": 3.1485,
"step": 104000
},
{
"epoch": 2.59,
"learning_rate": 7.855046692175145e-05,
"loss": 3.2001,
"step": 104500
},
{
"epoch": 2.6,
"learning_rate": 7.853658141746979e-05,
"loss": 3.0651,
"step": 105000
},
{
"epoch": 2.61,
"learning_rate": 7.852263096228267e-05,
"loss": 3.1709,
"step": 105500
},
{
"epoch": 2.63,
"learning_rate": 7.850861557970269e-05,
"loss": 3.1635,
"step": 106000
},
{
"epoch": 2.64,
"learning_rate": 7.849453529335188e-05,
"loss": 3.1123,
"step": 106500
},
{
"epoch": 2.65,
"learning_rate": 7.848039012696161e-05,
"loss": 3.1162,
"step": 107000
},
{
"epoch": 2.66,
"learning_rate": 7.846618010437265e-05,
"loss": 3.1275,
"step": 107500
},
{
"epoch": 2.68,
"learning_rate": 7.84519052495351e-05,
"loss": 3.1035,
"step": 108000
},
{
"epoch": 2.69,
"learning_rate": 7.843756558650827e-05,
"loss": 3.0308,
"step": 108500
},
{
"epoch": 2.7,
"learning_rate": 7.842316113946073e-05,
"loss": 3.1311,
"step": 109000
},
{
"epoch": 2.71,
"learning_rate": 7.840869193267027e-05,
"loss": 3.1477,
"step": 109500
},
{
"epoch": 2.73,
"learning_rate": 7.839415799052378e-05,
"loss": 3.1221,
"step": 110000
},
{
"epoch": 2.74,
"learning_rate": 7.837955933751725e-05,
"loss": 3.1322,
"step": 110500
},
{
"epoch": 2.75,
"learning_rate": 7.83648959982558e-05,
"loss": 3.1488,
"step": 111000
},
{
"epoch": 2.76,
"learning_rate": 7.835016799745353e-05,
"loss": 3.0619,
"step": 111500
},
{
"epoch": 2.78,
"learning_rate": 7.833537535993351e-05,
"loss": 3.237,
"step": 112000
},
{
"epoch": 2.79,
"learning_rate": 7.83205181106278e-05,
"loss": 3.1022,
"step": 112500
},
{
"epoch": 2.8,
"learning_rate": 7.83055962745773e-05,
"loss": 3.066,
"step": 113000
},
{
"epoch": 2.81,
"learning_rate": 7.829060987693179e-05,
"loss": 3.1903,
"step": 113500
},
{
"epoch": 2.83,
"learning_rate": 7.827555894294991e-05,
"loss": 3.2208,
"step": 114000
},
{
"epoch": 2.84,
"learning_rate": 7.8260443497999e-05,
"loss": 3.2005,
"step": 114500
},
{
"epoch": 2.85,
"learning_rate": 7.824526356755516e-05,
"loss": 3.184,
"step": 115000
},
{
"epoch": 2.86,
"learning_rate": 7.82300191772032e-05,
"loss": 3.1185,
"step": 115500
},
{
"epoch": 2.87,
"learning_rate": 7.821471035263653e-05,
"loss": 3.1077,
"step": 116000
},
{
"epoch": 2.89,
"learning_rate": 7.819933711965718e-05,
"loss": 3.1901,
"step": 116500
},
{
"epoch": 2.9,
"learning_rate": 7.818389950417574e-05,
"loss": 3.1149,
"step": 117000
},
{
"epoch": 2.91,
"learning_rate": 7.816839753221132e-05,
"loss": 3.1393,
"step": 117500
},
{
"epoch": 2.92,
"learning_rate": 7.815283122989147e-05,
"loss": 3.0862,
"step": 118000
},
{
"epoch": 2.94,
"learning_rate": 7.813720062345219e-05,
"loss": 3.072,
"step": 118500
},
{
"epoch": 2.95,
"learning_rate": 7.812150573923785e-05,
"loss": 3.1103,
"step": 119000
},
{
"epoch": 2.96,
"learning_rate": 7.810574660370116e-05,
"loss": 3.2114,
"step": 119500
},
{
"epoch": 2.97,
"learning_rate": 7.808992324340312e-05,
"loss": 3.1425,
"step": 120000
},
{
"epoch": 2.99,
"learning_rate": 7.807403568501297e-05,
"loss": 3.1051,
"step": 120500
},
{
"epoch": 3.0,
"learning_rate": 7.805808395530816e-05,
"loss": 3.1355,
"step": 121000
},
{
"epoch": 3.0,
"eval_bleu": 1.0,
"eval_brevity_penalty": 1.0,
"eval_length_ratio": 1.0,
"eval_loss": 3.0360162258148193,
"eval_precisions": [
1.0,
1.0,
1.0,
1.0
],
"eval_reference_length": 4591104,
"eval_runtime": 8117.2024,
"eval_samples_per_second": 1.105,
"eval_steps_per_second": 0.552,
"eval_translation_length": 4591104,
"step": 121044
},
{
"epoch": 3.01,
"learning_rate": 7.80420680811743e-05,
"loss": 3.0822,
"step": 121500
},
{
"epoch": 3.02,
"learning_rate": 7.80259880896051e-05,
"loss": 3.0585,
"step": 122000
},
{
"epoch": 3.04,
"learning_rate": 7.800984400770236e-05,
"loss": 3.1003,
"step": 122500
},
{
"epoch": 3.05,
"learning_rate": 7.799363586267584e-05,
"loss": 2.9734,
"step": 123000
},
{
"epoch": 3.06,
"learning_rate": 7.797736368184335e-05,
"loss": 3.1722,
"step": 123500
},
{
"epoch": 3.07,
"learning_rate": 7.79610274926306e-05,
"loss": 3.1007,
"step": 124000
},
{
"epoch": 3.09,
"learning_rate": 7.794462732257115e-05,
"loss": 3.0796,
"step": 124500
},
{
"epoch": 3.1,
"learning_rate": 7.792816319930645e-05,
"loss": 3.0691,
"step": 125000
},
{
"epoch": 3.11,
"learning_rate": 7.791163515058568e-05,
"loss": 3.1111,
"step": 125500
},
{
"epoch": 3.12,
"learning_rate": 7.78950432042658e-05,
"loss": 3.0355,
"step": 126000
},
{
"epoch": 3.14,
"learning_rate": 7.787838738831148e-05,
"loss": 3.0751,
"step": 126500
},
{
"epoch": 3.15,
"learning_rate": 7.786166773079499e-05,
"loss": 3.1197,
"step": 127000
},
{
"epoch": 3.16,
"learning_rate": 7.784488425989624e-05,
"loss": 3.0997,
"step": 127500
},
{
"epoch": 3.17,
"learning_rate": 7.782803700390268e-05,
"loss": 3.2085,
"step": 128000
},
{
"epoch": 3.18,
"learning_rate": 7.781112599120928e-05,
"loss": 3.1391,
"step": 128500
},
{
"epoch": 3.2,
"learning_rate": 7.779415125031842e-05,
"loss": 3.1137,
"step": 129000
},
{
"epoch": 3.21,
"learning_rate": 7.777711280983994e-05,
"loss": 3.1373,
"step": 129500
},
{
"epoch": 3.22,
"learning_rate": 7.776001069849104e-05,
"loss": 3.1228,
"step": 130000
},
{
"epoch": 3.23,
"learning_rate": 7.774284494509619e-05,
"loss": 3.0356,
"step": 130500
},
{
"epoch": 3.25,
"learning_rate": 7.772561557858717e-05,
"loss": 3.074,
"step": 131000
},
{
"epoch": 3.26,
"learning_rate": 7.770832262800298e-05,
"loss": 3.101,
"step": 131500
},
{
"epoch": 3.27,
"learning_rate": 7.769096612248972e-05,
"loss": 3.0026,
"step": 132000
},
{
"epoch": 3.28,
"learning_rate": 7.767354609130067e-05,
"loss": 2.9642,
"step": 132500
},
{
"epoch": 3.3,
"learning_rate": 7.765606256379617e-05,
"loss": 3.1591,
"step": 133000
},
{
"epoch": 3.31,
"learning_rate": 7.763851556944357e-05,
"loss": 3.1563,
"step": 133500
},
{
"epoch": 3.32,
"learning_rate": 7.762090513781717e-05,
"loss": 3.0032,
"step": 134000
},
{
"epoch": 3.33,
"learning_rate": 7.760323129859824e-05,
"loss": 3.0752,
"step": 134500
},
{
"epoch": 3.35,
"learning_rate": 7.758549408157487e-05,
"loss": 3.1228,
"step": 135000
},
{
"epoch": 3.36,
"learning_rate": 7.7567693516642e-05,
"loss": 3.1929,
"step": 135500
},
{
"epoch": 3.37,
"learning_rate": 7.754982963380129e-05,
"loss": 3.0963,
"step": 136000
},
{
"epoch": 3.38,
"learning_rate": 7.75319024631612e-05,
"loss": 3.1731,
"step": 136500
},
{
"epoch": 3.4,
"learning_rate": 7.751391203493678e-05,
"loss": 3.1822,
"step": 137000
},
{
"epoch": 3.41,
"learning_rate": 7.749585837944974e-05,
"loss": 3.0849,
"step": 137500
},
{
"epoch": 3.42,
"learning_rate": 7.747774152712836e-05,
"loss": 3.1609,
"step": 138000
},
{
"epoch": 3.43,
"learning_rate": 7.745956150850738e-05,
"loss": 3.0784,
"step": 138500
},
{
"epoch": 3.45,
"learning_rate": 7.744131835422808e-05,
"loss": 3.1391,
"step": 139000
},
{
"epoch": 3.46,
"learning_rate": 7.74230120950381e-05,
"loss": 3.1141,
"step": 139500
},
{
"epoch": 3.47,
"learning_rate": 7.740464276179143e-05,
"loss": 3.092,
"step": 140000
},
{
"epoch": 3.48,
"learning_rate": 7.738621038544842e-05,
"loss": 3.0634,
"step": 140500
},
{
"epoch": 3.49,
"learning_rate": 7.736771499707562e-05,
"loss": 3.1131,
"step": 141000
},
{
"epoch": 3.51,
"learning_rate": 7.734915662784582e-05,
"loss": 3.1014,
"step": 141500
},
{
"epoch": 3.52,
"learning_rate": 7.733053530903793e-05,
"loss": 3.1118,
"step": 142000
},
{
"epoch": 3.53,
"learning_rate": 7.7311851072037e-05,
"loss": 3.0762,
"step": 142500
},
{
"epoch": 3.54,
"learning_rate": 7.729310394833408e-05,
"loss": 3.0613,
"step": 143000
},
{
"epoch": 3.56,
"learning_rate": 7.727429396952622e-05,
"loss": 3.1007,
"step": 143500
},
{
"epoch": 3.57,
"learning_rate": 7.725542116731643e-05,
"loss": 3.0766,
"step": 144000
},
{
"epoch": 3.58,
"learning_rate": 7.72364855735136e-05,
"loss": 3.0842,
"step": 144500
},
{
"epoch": 3.59,
"learning_rate": 7.721748722003242e-05,
"loss": 3.1643,
"step": 145000
},
{
"epoch": 3.61,
"learning_rate": 7.719842613889342e-05,
"loss": 3.0702,
"step": 145500
},
{
"epoch": 3.62,
"learning_rate": 7.717930236222277e-05,
"loss": 3.2394,
"step": 146000
},
{
"epoch": 3.63,
"learning_rate": 7.716011592225239e-05,
"loss": 3.0847,
"step": 146500
},
{
"epoch": 3.64,
"learning_rate": 7.714086685131975e-05,
"loss": 3.1536,
"step": 147000
},
{
"epoch": 3.66,
"learning_rate": 7.712155518186792e-05,
"loss": 3.0908,
"step": 147500
},
{
"epoch": 3.67,
"learning_rate": 7.710218094644548e-05,
"loss": 3.0379,
"step": 148000
},
{
"epoch": 3.68,
"learning_rate": 7.708274417770644e-05,
"loss": 3.0513,
"step": 148500
},
{
"epoch": 3.69,
"learning_rate": 7.706324490841019e-05,
"loss": 3.1075,
"step": 149000
},
{
"epoch": 3.71,
"learning_rate": 7.704368317142151e-05,
"loss": 3.1261,
"step": 149500
},
{
"epoch": 3.72,
"learning_rate": 7.702405899971042e-05,
"loss": 3.164,
"step": 150000
},
{
"epoch": 3.73,
"learning_rate": 7.700437242635218e-05,
"loss": 3.0038,
"step": 150500
},
{
"epoch": 3.74,
"learning_rate": 7.698462348452724e-05,
"loss": 3.1165,
"step": 151000
},
{
"epoch": 3.75,
"learning_rate": 7.696481220752119e-05,
"loss": 3.048,
"step": 151500
},
{
"epoch": 3.77,
"learning_rate": 7.694493862872459e-05,
"loss": 3.0922,
"step": 152000
},
{
"epoch": 3.78,
"learning_rate": 7.69250027816331e-05,
"loss": 3.1324,
"step": 152500
},
{
"epoch": 3.79,
"learning_rate": 7.69050046998473e-05,
"loss": 3.1076,
"step": 153000
},
{
"epoch": 3.8,
"learning_rate": 7.688494441707267e-05,
"loss": 3.0944,
"step": 153500
},
{
"epoch": 3.82,
"learning_rate": 7.686482196711948e-05,
"loss": 3.0502,
"step": 154000
},
{
"epoch": 3.83,
"learning_rate": 7.684463738390284e-05,
"loss": 3.0757,
"step": 154500
},
{
"epoch": 3.84,
"learning_rate": 7.682439070144252e-05,
"loss": 3.0951,
"step": 155000
},
{
"epoch": 3.85,
"learning_rate": 7.680408195386303e-05,
"loss": 3.0857,
"step": 155500
},
{
"epoch": 3.87,
"learning_rate": 7.678371117539342e-05,
"loss": 3.0341,
"step": 156000
},
{
"epoch": 3.88,
"learning_rate": 7.676327840036733e-05,
"loss": 3.0872,
"step": 156500
},
{
"epoch": 3.89,
"learning_rate": 7.674278366322286e-05,
"loss": 3.0744,
"step": 157000
},
{
"epoch": 3.9,
"learning_rate": 7.672222699850256e-05,
"loss": 3.0927,
"step": 157500
},
{
"epoch": 3.92,
"learning_rate": 7.670160844085336e-05,
"loss": 3.0717,
"step": 158000
},
{
"epoch": 3.93,
"learning_rate": 7.668092802502651e-05,
"loss": 2.964,
"step": 158500
},
{
"epoch": 3.94,
"learning_rate": 7.666018578587749e-05,
"loss": 2.9958,
"step": 159000
},
{
"epoch": 3.95,
"learning_rate": 7.663938175836599e-05,
"loss": 3.1135,
"step": 159500
},
{
"epoch": 3.97,
"learning_rate": 7.661851597755588e-05,
"loss": 3.0903,
"step": 160000
},
{
"epoch": 3.98,
"learning_rate": 7.659758847861505e-05,
"loss": 3.1399,
"step": 160500
},
{
"epoch": 3.99,
"learning_rate": 7.657659929681545e-05,
"loss": 3.0583,
"step": 161000
},
{
"epoch": 4.0,
"eval_bleu": 1.0,
"eval_brevity_penalty": 1.0,
"eval_length_ratio": 1.0,
"eval_loss": 3.0066018104553223,
"eval_precisions": [
1.0,
1.0,
1.0,
1.0
],
"eval_reference_length": 4591104,
"eval_runtime": 8243.7716,
"eval_samples_per_second": 1.088,
"eval_steps_per_second": 0.544,
"eval_translation_length": 4591104,
"step": 161392
},
{
"epoch": 4.0,
"learning_rate": 7.655554846753297e-05,
"loss": 3.1442,
"step": 161500
},
{
"epoch": 4.02,
"learning_rate": 7.653443602624745e-05,
"loss": 3.079,
"step": 162000
},
{
"epoch": 4.03,
"learning_rate": 7.651326200854252e-05,
"loss": 3.1155,
"step": 162500
},
{
"epoch": 4.04,
"learning_rate": 7.64920264501056e-05,
"loss": 3.034,
"step": 163000
},
{
"epoch": 4.05,
"learning_rate": 7.647072938672785e-05,
"loss": 3.1226,
"step": 163500
},
{
"epoch": 4.06,
"learning_rate": 7.644937085430409e-05,
"loss": 3.1027,
"step": 164000
},
{
"epoch": 4.08,
"learning_rate": 7.642795088883274e-05,
"loss": 3.1736,
"step": 164500
},
{
"epoch": 4.09,
"learning_rate": 7.640646952641577e-05,
"loss": 2.9279,
"step": 165000
},
{
"epoch": 4.1,
"learning_rate": 7.638492680325862e-05,
"loss": 3.0596,
"step": 165500
},
{
"epoch": 4.11,
"learning_rate": 7.636332275567012e-05,
"loss": 3.0027,
"step": 166000
},
{
"epoch": 4.13,
"learning_rate": 7.634165742006251e-05,
"loss": 3.1487,
"step": 166500
},
{
"epoch": 4.14,
"learning_rate": 7.631993083295134e-05,
"loss": 3.04,
"step": 167000
},
{
"epoch": 4.15,
"learning_rate": 7.62981430309553e-05,
"loss": 3.0355,
"step": 167500
},
{
"epoch": 4.16,
"learning_rate": 7.627629405079637e-05,
"loss": 3.1222,
"step": 168000
},
{
"epoch": 4.18,
"learning_rate": 7.625438392929956e-05,
"loss": 3.0185,
"step": 168500
},
{
"epoch": 4.19,
"learning_rate": 7.623241270339294e-05,
"loss": 3.036,
"step": 169000
},
{
"epoch": 4.2,
"learning_rate": 7.621038041010763e-05,
"loss": 3.0182,
"step": 169500
},
{
"epoch": 4.21,
"learning_rate": 7.61882870865776e-05,
"loss": 3.0501,
"step": 170000
},
{
"epoch": 4.23,
"learning_rate": 7.61661327700397e-05,
"loss": 3.0935,
"step": 170500
},
{
"epoch": 4.24,
"learning_rate": 7.614391749783361e-05,
"loss": 2.9745,
"step": 171000
},
{
"epoch": 4.25,
"learning_rate": 7.612164130740175e-05,
"loss": 3.0497,
"step": 171500
},
{
"epoch": 4.26,
"learning_rate": 7.609930423628915e-05,
"loss": 3.0207,
"step": 172000
},
{
"epoch": 4.28,
"learning_rate": 7.607690632214351e-05,
"loss": 3.0059,
"step": 172500
},
{
"epoch": 4.29,
"learning_rate": 7.605444760271507e-05,
"loss": 3.113,
"step": 173000
},
{
"epoch": 4.3,
"learning_rate": 7.603192811585654e-05,
"loss": 3.0989,
"step": 173500
},
{
"epoch": 4.31,
"learning_rate": 7.600934789952304e-05,
"loss": 3.1174,
"step": 174000
},
{
"epoch": 4.32,
"learning_rate": 7.598670699177207e-05,
"loss": 3.0884,
"step": 174500
},
{
"epoch": 4.34,
"learning_rate": 7.596400543076339e-05,
"loss": 2.973,
"step": 175000
},
{
"epoch": 4.35,
"learning_rate": 7.594124325475904e-05,
"loss": 3.0956,
"step": 175500
},
{
"epoch": 4.36,
"learning_rate": 7.591842050212317e-05,
"loss": 2.9274,
"step": 176000
},
{
"epoch": 4.37,
"learning_rate": 7.589553721132205e-05,
"loss": 3.0128,
"step": 176500
},
{
"epoch": 4.39,
"learning_rate": 7.587259342092397e-05,
"loss": 3.0429,
"step": 177000
},
{
"epoch": 4.4,
"learning_rate": 7.584958916959923e-05,
"loss": 3.0955,
"step": 177500
},
{
"epoch": 4.41,
"learning_rate": 7.582652449611996e-05,
"loss": 3.1124,
"step": 178000
},
{
"epoch": 4.42,
"learning_rate": 7.58033994393602e-05,
"loss": 2.9723,
"step": 178500
},
{
"epoch": 4.44,
"learning_rate": 7.578021403829572e-05,
"loss": 2.981,
"step": 179000
},
{
"epoch": 4.45,
"learning_rate": 7.5756968332004e-05,
"loss": 3.1174,
"step": 179500
},
{
"epoch": 4.46,
"learning_rate": 7.57336623596642e-05,
"loss": 3.0292,
"step": 180000
},
{
"epoch": 4.47,
"learning_rate": 7.5710296160557e-05,
"loss": 3.0106,
"step": 180500
},
{
"epoch": 4.49,
"learning_rate": 7.568686977406459e-05,
"loss": 2.9749,
"step": 181000
},
{
"epoch": 4.5,
"learning_rate": 7.566338323967065e-05,
"loss": 3.0591,
"step": 181500
},
{
"epoch": 4.51,
"learning_rate": 7.563983659696022e-05,
"loss": 3.0228,
"step": 182000
},
{
"epoch": 4.52,
"learning_rate": 7.56162298856196e-05,
"loss": 3.0134,
"step": 182500
},
{
"epoch": 4.54,
"learning_rate": 7.559256314543639e-05,
"loss": 3.0624,
"step": 183000
},
{
"epoch": 4.55,
"learning_rate": 7.556883641629936e-05,
"loss": 3.0205,
"step": 183500
},
{
"epoch": 4.56,
"learning_rate": 7.554504973819835e-05,
"loss": 3.0067,
"step": 184000
},
{
"epoch": 4.57,
"learning_rate": 7.552120315122426e-05,
"loss": 3.0488,
"step": 184500
},
{
"epoch": 4.59,
"learning_rate": 7.549729669556898e-05,
"loss": 3.0992,
"step": 185000
},
{
"epoch": 4.6,
"learning_rate": 7.547333041152526e-05,
"loss": 3.0137,
"step": 185500
},
{
"epoch": 4.61,
"learning_rate": 7.544930433948676e-05,
"loss": 3.1379,
"step": 186000
},
{
"epoch": 4.62,
"learning_rate": 7.542521851994781e-05,
"loss": 3.0818,
"step": 186500
},
{
"epoch": 4.63,
"learning_rate": 7.540107299350354e-05,
"loss": 3.0634,
"step": 187000
},
{
"epoch": 4.65,
"learning_rate": 7.537686780084966e-05,
"loss": 3.0984,
"step": 187500
},
{
"epoch": 4.66,
"learning_rate": 7.53526029827824e-05,
"loss": 3.1238,
"step": 188000
},
{
"epoch": 4.67,
"learning_rate": 7.532827858019862e-05,
"loss": 3.0431,
"step": 188500
},
{
"epoch": 4.68,
"learning_rate": 7.530389463409545e-05,
"loss": 3.0216,
"step": 189000
},
{
"epoch": 4.7,
"learning_rate": 7.527945118557048e-05,
"loss": 3.0448,
"step": 189500
},
{
"epoch": 4.71,
"learning_rate": 7.525494827582155e-05,
"loss": 3.1713,
"step": 190000
},
{
"epoch": 4.72,
"learning_rate": 7.523038594614671e-05,
"loss": 3.0396,
"step": 190500
},
{
"epoch": 4.73,
"learning_rate": 7.52057642379442e-05,
"loss": 3.1008,
"step": 191000
},
{
"epoch": 4.75,
"learning_rate": 7.518108319271228e-05,
"loss": 3.0965,
"step": 191500
},
{
"epoch": 4.76,
"learning_rate": 7.515634285204928e-05,
"loss": 3.0407,
"step": 192000
},
{
"epoch": 4.77,
"learning_rate": 7.51315432576534e-05,
"loss": 3.0669,
"step": 192500
},
{
"epoch": 4.78,
"learning_rate": 7.510668445132279e-05,
"loss": 3.0752,
"step": 193000
},
{
"epoch": 4.8,
"learning_rate": 7.508176647495532e-05,
"loss": 2.9414,
"step": 193500
},
{
"epoch": 4.81,
"learning_rate": 7.505678937054863e-05,
"loss": 3.0746,
"step": 194000
},
{
"epoch": 4.82,
"learning_rate": 7.503175318019999e-05,
"loss": 2.9645,
"step": 194500
},
{
"epoch": 4.83,
"learning_rate": 7.500665794610632e-05,
"loss": 3.0942,
"step": 195000
},
{
"epoch": 4.85,
"learning_rate": 7.498150371056396e-05,
"loss": 3.0586,
"step": 195500
},
{
"epoch": 4.86,
"learning_rate": 7.495629051596876e-05,
"loss": 3.0251,
"step": 196000
},
{
"epoch": 4.87,
"learning_rate": 7.493101840481594e-05,
"loss": 3.0769,
"step": 196500
},
{
"epoch": 4.88,
"learning_rate": 7.490568741969997e-05,
"loss": 3.0701,
"step": 197000
},
{
"epoch": 4.89,
"learning_rate": 7.488029760331459e-05,
"loss": 3.0893,
"step": 197500
},
{
"epoch": 4.91,
"learning_rate": 7.48548489984527e-05,
"loss": 3.1527,
"step": 198000
},
{
"epoch": 4.92,
"learning_rate": 7.482934164800626e-05,
"loss": 3.0497,
"step": 198500
},
{
"epoch": 4.93,
"learning_rate": 7.480377559496624e-05,
"loss": 3.0665,
"step": 199000
},
{
"epoch": 4.94,
"learning_rate": 7.47781508824226e-05,
"loss": 3.0842,
"step": 199500
},
{
"epoch": 4.96,
"learning_rate": 7.47524675535641e-05,
"loss": 3.0961,
"step": 200000
},
{
"epoch": 4.97,
"learning_rate": 7.472672565167833e-05,
"loss": 3.0756,
"step": 200500
},
{
"epoch": 4.98,
"learning_rate": 7.470092522015158e-05,
"loss": 3.1524,
"step": 201000
},
{
"epoch": 4.99,
"learning_rate": 7.467506630246882e-05,
"loss": 3.1614,
"step": 201500
},
{
"epoch": 5.0,
"eval_bleu": 1.0,
"eval_brevity_penalty": 1.0,
"eval_length_ratio": 1.0,
"eval_loss": 2.995251417160034,
"eval_precisions": [
1.0,
1.0,
1.0,
1.0
],
"eval_reference_length": 4591104,
"eval_runtime": 8351.4463,
"eval_samples_per_second": 1.074,
"eval_steps_per_second": 0.537,
"eval_translation_length": 4591104,
"step": 201740
}
],
"logging_steps": 500,
"max_steps": 1210440,
"num_train_epochs": 30,
"save_steps": 1000,
"total_flos": 3.462342804976435e+18,
"trial_name": null,
"trial_params": null
}