clickbait_spoiling_phrase / trainer_state.json
Tugay's picture
bugs fixed
a22536d
Raw History Blame Contribute Delete
294 kB
{
"best_metric": 0.5452640266452384,
"best_model_checkpoint": "t5-results/checkpoint-4788",
"epoch": 14.0,
"global_step": 4788,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.998538011695907e-05,
"loss": 0.8167,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.9970760233918126e-05,
"loss": 0.8178,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 4.9956140350877195e-05,
"loss": 0.6583,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 4.9941520467836264e-05,
"loss": 1.2227,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 4.992690058479532e-05,
"loss": 1.6131,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 4.991228070175439e-05,
"loss": 0.8521,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 4.989766081871346e-05,
"loss": 1.1587,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 4.988304093567251e-05,
"loss": 1.4706,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 4.986842105263158e-05,
"loss": 0.3401,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 4.985380116959065e-05,
"loss": 1.4927,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 4.9839181286549705e-05,
"loss": 1.0663,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 4.9824561403508773e-05,
"loss": 0.5169,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 4.980994152046784e-05,
"loss": 0.4457,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 4.97953216374269e-05,
"loss": 0.5518,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 4.9780701754385966e-05,
"loss": 0.4647,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 4.9766081871345035e-05,
"loss": 0.2822,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 4.975146198830409e-05,
"loss": 0.4731,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 4.973684210526316e-05,
"loss": 0.2812,
"step": 36
},
{
"epoch": 0.11,
"learning_rate": 4.972222222222223e-05,
"loss": 0.7638,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 4.970760233918128e-05,
"loss": 1.5065,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 4.969298245614035e-05,
"loss": 0.8609,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 4.967836257309942e-05,
"loss": 1.4817,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 4.966374269005848e-05,
"loss": 0.7912,
"step": 46
},
{
"epoch": 0.14,
"learning_rate": 4.9649122807017544e-05,
"loss": 0.2792,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 4.963450292397661e-05,
"loss": 0.4871,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 4.9619883040935675e-05,
"loss": 0.7597,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 4.960526315789474e-05,
"loss": 0.6813,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 4.9590643274853806e-05,
"loss": 0.4779,
"step": 56
},
{
"epoch": 0.17,
"learning_rate": 4.957602339181287e-05,
"loss": 0.0836,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 4.956140350877193e-05,
"loss": 0.3489,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 4.9546783625731e-05,
"loss": 1.3094,
"step": 62
},
{
"epoch": 0.19,
"learning_rate": 4.953216374269006e-05,
"loss": 0.8406,
"step": 64
},
{
"epoch": 0.19,
"learning_rate": 4.951754385964912e-05,
"loss": 0.45,
"step": 66
},
{
"epoch": 0.2,
"learning_rate": 4.950292397660819e-05,
"loss": 0.7461,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 4.948830409356725e-05,
"loss": 0.8788,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 4.9473684210526315e-05,
"loss": 0.4855,
"step": 72
},
{
"epoch": 0.22,
"learning_rate": 4.9459064327485384e-05,
"loss": 1.1018,
"step": 74
},
{
"epoch": 0.22,
"learning_rate": 4.9444444444444446e-05,
"loss": 1.0476,
"step": 76
},
{
"epoch": 0.23,
"learning_rate": 4.942982456140351e-05,
"loss": 0.6935,
"step": 78
},
{
"epoch": 0.23,
"learning_rate": 4.941520467836258e-05,
"loss": 1.0094,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 4.940058479532164e-05,
"loss": 1.2433,
"step": 82
},
{
"epoch": 0.25,
"learning_rate": 4.93859649122807e-05,
"loss": 1.0101,
"step": 84
},
{
"epoch": 0.25,
"learning_rate": 4.937134502923977e-05,
"loss": 0.4951,
"step": 86
},
{
"epoch": 0.26,
"learning_rate": 4.935672514619883e-05,
"loss": 0.7381,
"step": 88
},
{
"epoch": 0.26,
"learning_rate": 4.9342105263157894e-05,
"loss": 1.0627,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 4.932748538011696e-05,
"loss": 0.8034,
"step": 92
},
{
"epoch": 0.27,
"learning_rate": 4.9312865497076024e-05,
"loss": 0.2821,
"step": 94
},
{
"epoch": 0.28,
"learning_rate": 4.9298245614035086e-05,
"loss": 0.7447,
"step": 96
},
{
"epoch": 0.29,
"learning_rate": 4.9283625730994155e-05,
"loss": 0.3698,
"step": 98
},
{
"epoch": 0.29,
"learning_rate": 4.926900584795322e-05,
"loss": 1.3887,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 4.925438596491228e-05,
"loss": 1.6016,
"step": 102
},
{
"epoch": 0.3,
"learning_rate": 4.923976608187135e-05,
"loss": 0.7631,
"step": 104
},
{
"epoch": 0.31,
"learning_rate": 4.922514619883041e-05,
"loss": 0.8626,
"step": 106
},
{
"epoch": 0.32,
"learning_rate": 4.921052631578947e-05,
"loss": 0.4676,
"step": 108
},
{
"epoch": 0.32,
"learning_rate": 4.919590643274854e-05,
"loss": 0.688,
"step": 110
},
{
"epoch": 0.33,
"learning_rate": 4.91812865497076e-05,
"loss": 0.2453,
"step": 112
},
{
"epoch": 0.33,
"learning_rate": 4.9166666666666665e-05,
"loss": 1.4003,
"step": 114
},
{
"epoch": 0.34,
"learning_rate": 4.915204678362573e-05,
"loss": 0.9229,
"step": 116
},
{
"epoch": 0.35,
"learning_rate": 4.9137426900584795e-05,
"loss": 0.3714,
"step": 118
},
{
"epoch": 0.35,
"learning_rate": 4.912280701754386e-05,
"loss": 2.1677,
"step": 120
},
{
"epoch": 0.36,
"learning_rate": 4.9108187134502926e-05,
"loss": 0.6421,
"step": 122
},
{
"epoch": 0.36,
"learning_rate": 4.9093567251461995e-05,
"loss": 1.444,
"step": 124
},
{
"epoch": 0.37,
"learning_rate": 4.907894736842106e-05,
"loss": 1.0284,
"step": 126
},
{
"epoch": 0.37,
"learning_rate": 4.906432748538012e-05,
"loss": 0.8126,
"step": 128
},
{
"epoch": 0.38,
"learning_rate": 4.904970760233919e-05,
"loss": 1.0447,
"step": 130
},
{
"epoch": 0.39,
"learning_rate": 4.903508771929825e-05,
"loss": 0.2614,
"step": 132
},
{
"epoch": 0.39,
"learning_rate": 4.902046783625731e-05,
"loss": 0.5198,
"step": 134
},
{
"epoch": 0.4,
"learning_rate": 4.900584795321638e-05,
"loss": 1.0012,
"step": 136
},
{
"epoch": 0.4,
"learning_rate": 4.899122807017544e-05,
"loss": 0.8052,
"step": 138
},
{
"epoch": 0.41,
"learning_rate": 4.8976608187134504e-05,
"loss": 1.3284,
"step": 140
},
{
"epoch": 0.42,
"learning_rate": 4.896198830409357e-05,
"loss": 1.5859,
"step": 142
},
{
"epoch": 0.42,
"learning_rate": 4.8947368421052635e-05,
"loss": 0.5418,
"step": 144
},
{
"epoch": 0.43,
"learning_rate": 4.89327485380117e-05,
"loss": 1.0927,
"step": 146
},
{
"epoch": 0.43,
"learning_rate": 4.8918128654970766e-05,
"loss": 0.5404,
"step": 148
},
{
"epoch": 0.44,
"learning_rate": 4.890350877192983e-05,
"loss": 0.3727,
"step": 150
},
{
"epoch": 0.44,
"learning_rate": 4.888888888888889e-05,
"loss": 0.2769,
"step": 152
},
{
"epoch": 0.45,
"learning_rate": 4.887426900584796e-05,
"loss": 0.98,
"step": 154
},
{
"epoch": 0.46,
"learning_rate": 4.885964912280702e-05,
"loss": 1.2246,
"step": 156
},
{
"epoch": 0.46,
"learning_rate": 4.884502923976608e-05,
"loss": 0.7864,
"step": 158
},
{
"epoch": 0.47,
"learning_rate": 4.883040935672515e-05,
"loss": 0.3525,
"step": 160
},
{
"epoch": 0.47,
"learning_rate": 4.881578947368421e-05,
"loss": 1.2076,
"step": 162
},
{
"epoch": 0.48,
"learning_rate": 4.8801169590643275e-05,
"loss": 0.2688,
"step": 164
},
{
"epoch": 0.49,
"learning_rate": 4.8786549707602344e-05,
"loss": 0.7645,
"step": 166
},
{
"epoch": 0.49,
"learning_rate": 4.8771929824561406e-05,
"loss": 1.4945,
"step": 168
},
{
"epoch": 0.5,
"learning_rate": 4.875730994152047e-05,
"loss": 0.4794,
"step": 170
},
{
"epoch": 0.5,
"learning_rate": 4.874269005847954e-05,
"loss": 0.5095,
"step": 172
},
{
"epoch": 0.51,
"learning_rate": 4.87280701754386e-05,
"loss": 0.8295,
"step": 174
},
{
"epoch": 0.51,
"learning_rate": 4.871345029239766e-05,
"loss": 0.3884,
"step": 176
},
{
"epoch": 0.52,
"learning_rate": 4.869883040935673e-05,
"loss": 1.9631,
"step": 178
},
{
"epoch": 0.53,
"learning_rate": 4.868421052631579e-05,
"loss": 0.3481,
"step": 180
},
{
"epoch": 0.53,
"learning_rate": 4.8669590643274854e-05,
"loss": 0.4553,
"step": 182
},
{
"epoch": 0.54,
"learning_rate": 4.865497076023392e-05,
"loss": 2.0804,
"step": 184
},
{
"epoch": 0.54,
"learning_rate": 4.8640350877192984e-05,
"loss": 0.5014,
"step": 186
},
{
"epoch": 0.55,
"learning_rate": 4.8625730994152046e-05,
"loss": 1.0465,
"step": 188
},
{
"epoch": 0.56,
"learning_rate": 4.8611111111111115e-05,
"loss": 0.833,
"step": 190
},
{
"epoch": 0.56,
"learning_rate": 4.859649122807018e-05,
"loss": 0.7675,
"step": 192
},
{
"epoch": 0.57,
"learning_rate": 4.858187134502924e-05,
"loss": 0.7615,
"step": 194
},
{
"epoch": 0.57,
"learning_rate": 4.856725146198831e-05,
"loss": 0.4617,
"step": 196
},
{
"epoch": 0.58,
"learning_rate": 4.855263157894737e-05,
"loss": 0.3755,
"step": 198
},
{
"epoch": 0.58,
"learning_rate": 4.853801169590643e-05,
"loss": 1.291,
"step": 200
},
{
"epoch": 0.59,
"learning_rate": 4.85233918128655e-05,
"loss": 0.9418,
"step": 202
},
{
"epoch": 0.6,
"learning_rate": 4.850877192982456e-05,
"loss": 1.0443,
"step": 204
},
{
"epoch": 0.6,
"learning_rate": 4.849415204678363e-05,
"loss": 0.3599,
"step": 206
},
{
"epoch": 0.61,
"learning_rate": 4.847953216374269e-05,
"loss": 0.8948,
"step": 208
},
{
"epoch": 0.61,
"learning_rate": 4.8464912280701755e-05,
"loss": 0.5743,
"step": 210
},
{
"epoch": 0.62,
"learning_rate": 4.8450292397660824e-05,
"loss": 0.3386,
"step": 212
},
{
"epoch": 0.63,
"learning_rate": 4.8435672514619886e-05,
"loss": 0.4024,
"step": 214
},
{
"epoch": 0.63,
"learning_rate": 4.842105263157895e-05,
"loss": 0.8287,
"step": 216
},
{
"epoch": 0.64,
"learning_rate": 4.840643274853802e-05,
"loss": 1.1272,
"step": 218
},
{
"epoch": 0.64,
"learning_rate": 4.839181286549708e-05,
"loss": 0.8172,
"step": 220
},
{
"epoch": 0.65,
"learning_rate": 4.837719298245614e-05,
"loss": 1.2611,
"step": 222
},
{
"epoch": 0.65,
"learning_rate": 4.836257309941521e-05,
"loss": 0.4171,
"step": 224
},
{
"epoch": 0.66,
"learning_rate": 4.834795321637427e-05,
"loss": 0.4866,
"step": 226
},
{
"epoch": 0.67,
"learning_rate": 4.8333333333333334e-05,
"loss": 0.5757,
"step": 228
},
{
"epoch": 0.67,
"learning_rate": 4.83187134502924e-05,
"loss": 0.1278,
"step": 230
},
{
"epoch": 0.68,
"learning_rate": 4.8304093567251464e-05,
"loss": 0.9079,
"step": 232
},
{
"epoch": 0.68,
"learning_rate": 4.8289473684210526e-05,
"loss": 0.8343,
"step": 234
},
{
"epoch": 0.69,
"learning_rate": 4.8274853801169595e-05,
"loss": 1.4098,
"step": 236
},
{
"epoch": 0.7,
"learning_rate": 4.826023391812866e-05,
"loss": 0.8841,
"step": 238
},
{
"epoch": 0.7,
"learning_rate": 4.824561403508772e-05,
"loss": 0.4075,
"step": 240
},
{
"epoch": 0.71,
"learning_rate": 4.823099415204679e-05,
"loss": 2.0634,
"step": 242
},
{
"epoch": 0.71,
"learning_rate": 4.821637426900585e-05,
"loss": 0.5665,
"step": 244
},
{
"epoch": 0.72,
"learning_rate": 4.820175438596491e-05,
"loss": 1.0069,
"step": 246
},
{
"epoch": 0.73,
"learning_rate": 4.818713450292398e-05,
"loss": 0.513,
"step": 248
},
{
"epoch": 0.73,
"learning_rate": 4.817251461988304e-05,
"loss": 0.9733,
"step": 250
},
{
"epoch": 0.74,
"learning_rate": 4.8157894736842105e-05,
"loss": 0.7916,
"step": 252
},
{
"epoch": 0.74,
"learning_rate": 4.814327485380117e-05,
"loss": 1.9786,
"step": 254
},
{
"epoch": 0.75,
"learning_rate": 4.8128654970760235e-05,
"loss": 0.9457,
"step": 256
},
{
"epoch": 0.75,
"learning_rate": 4.81140350877193e-05,
"loss": 1.393,
"step": 258
},
{
"epoch": 0.76,
"learning_rate": 4.8099415204678366e-05,
"loss": 0.7752,
"step": 260
},
{
"epoch": 0.77,
"learning_rate": 4.808479532163743e-05,
"loss": 0.7507,
"step": 262
},
{
"epoch": 0.77,
"learning_rate": 4.807017543859649e-05,
"loss": 0.8003,
"step": 264
},
{
"epoch": 0.78,
"learning_rate": 4.805555555555556e-05,
"loss": 0.6331,
"step": 266
},
{
"epoch": 0.78,
"learning_rate": 4.804093567251462e-05,
"loss": 1.0682,
"step": 268
},
{
"epoch": 0.79,
"learning_rate": 4.802631578947368e-05,
"loss": 1.0493,
"step": 270
},
{
"epoch": 0.8,
"learning_rate": 4.801169590643275e-05,
"loss": 0.3974,
"step": 272
},
{
"epoch": 0.8,
"learning_rate": 4.7997076023391814e-05,
"loss": 0.6729,
"step": 274
},
{
"epoch": 0.81,
"learning_rate": 4.7982456140350876e-05,
"loss": 1.6679,
"step": 276
},
{
"epoch": 0.81,
"learning_rate": 4.7967836257309944e-05,
"loss": 1.2976,
"step": 278
},
{
"epoch": 0.82,
"learning_rate": 4.7953216374269006e-05,
"loss": 0.7214,
"step": 280
},
{
"epoch": 0.82,
"learning_rate": 4.793859649122807e-05,
"loss": 0.6523,
"step": 282
},
{
"epoch": 0.83,
"learning_rate": 4.792397660818714e-05,
"loss": 0.4036,
"step": 284
},
{
"epoch": 0.84,
"learning_rate": 4.7909356725146206e-05,
"loss": 1.0771,
"step": 286
},
{
"epoch": 0.84,
"learning_rate": 4.789473684210526e-05,
"loss": 0.6246,
"step": 288
},
{
"epoch": 0.85,
"learning_rate": 4.788011695906433e-05,
"loss": 0.727,
"step": 290
},
{
"epoch": 0.85,
"learning_rate": 4.78654970760234e-05,
"loss": 0.5842,
"step": 292
},
{
"epoch": 0.86,
"learning_rate": 4.785087719298246e-05,
"loss": 0.4629,
"step": 294
},
{
"epoch": 0.87,
"learning_rate": 4.783625730994152e-05,
"loss": 0.7222,
"step": 296
},
{
"epoch": 0.87,
"learning_rate": 4.782163742690059e-05,
"loss": 0.8718,
"step": 298
},
{
"epoch": 0.88,
"learning_rate": 4.780701754385965e-05,
"loss": 0.6316,
"step": 300
},
{
"epoch": 0.88,
"learning_rate": 4.7792397660818715e-05,
"loss": 0.2735,
"step": 302
},
{
"epoch": 0.89,
"learning_rate": 4.7777777777777784e-05,
"loss": 1.0585,
"step": 304
},
{
"epoch": 0.89,
"learning_rate": 4.7763157894736846e-05,
"loss": 1.3033,
"step": 306
},
{
"epoch": 0.9,
"learning_rate": 4.774853801169591e-05,
"loss": 0.4653,
"step": 308
},
{
"epoch": 0.91,
"learning_rate": 4.773391812865498e-05,
"loss": 0.9894,
"step": 310
},
{
"epoch": 0.91,
"learning_rate": 4.771929824561404e-05,
"loss": 0.3296,
"step": 312
},
{
"epoch": 0.92,
"learning_rate": 4.77046783625731e-05,
"loss": 1.5788,
"step": 314
},
{
"epoch": 0.92,
"learning_rate": 4.769005847953217e-05,
"loss": 1.0333,
"step": 316
},
{
"epoch": 0.93,
"learning_rate": 4.767543859649123e-05,
"loss": 0.9684,
"step": 318
},
{
"epoch": 0.94,
"learning_rate": 4.7660818713450294e-05,
"loss": 0.4795,
"step": 320
},
{
"epoch": 0.94,
"learning_rate": 4.764619883040936e-05,
"loss": 1.0113,
"step": 322
},
{
"epoch": 0.95,
"learning_rate": 4.7631578947368424e-05,
"loss": 0.5751,
"step": 324
},
{
"epoch": 0.95,
"learning_rate": 4.7616959064327486e-05,
"loss": 0.556,
"step": 326
},
{
"epoch": 0.96,
"learning_rate": 4.7602339181286555e-05,
"loss": 0.622,
"step": 328
},
{
"epoch": 0.96,
"learning_rate": 4.758771929824562e-05,
"loss": 1.2535,
"step": 330
},
{
"epoch": 0.97,
"learning_rate": 4.757309941520468e-05,
"loss": 0.5097,
"step": 332
},
{
"epoch": 0.98,
"learning_rate": 4.755847953216375e-05,
"loss": 0.497,
"step": 334
},
{
"epoch": 0.98,
"learning_rate": 4.754385964912281e-05,
"loss": 0.7043,
"step": 336
},
{
"epoch": 0.99,
"learning_rate": 4.752923976608187e-05,
"loss": 1.0435,
"step": 338
},
{
"epoch": 0.99,
"learning_rate": 4.751461988304094e-05,
"loss": 0.4572,
"step": 340
},
{
"epoch": 1.0,
"learning_rate": 4.75e-05,
"loss": 0.6859,
"step": 342
},
{
"epoch": 1.0,
"eval_bleu": 0.5263307853559898,
"eval_loss": 0.6152855157852173,
"eval_runtime": 35.5665,
"eval_samples_per_second": 9.419,
"eval_steps_per_second": 2.362,
"step": 342
},
{
"epoch": 1.01,
"learning_rate": 4.7485380116959065e-05,
"loss": 0.8108,
"step": 344
},
{
"epoch": 1.01,
"learning_rate": 4.747076023391813e-05,
"loss": 0.4426,
"step": 346
},
{
"epoch": 1.02,
"learning_rate": 4.7456140350877195e-05,
"loss": 0.0714,
"step": 348
},
{
"epoch": 1.02,
"learning_rate": 4.744152046783626e-05,
"loss": 0.1527,
"step": 350
},
{
"epoch": 1.03,
"learning_rate": 4.7426900584795326e-05,
"loss": 0.3439,
"step": 352
},
{
"epoch": 1.04,
"learning_rate": 4.741228070175439e-05,
"loss": 0.5955,
"step": 354
},
{
"epoch": 1.04,
"learning_rate": 4.739766081871345e-05,
"loss": 0.1117,
"step": 356
},
{
"epoch": 1.05,
"learning_rate": 4.738304093567252e-05,
"loss": 0.5978,
"step": 358
},
{
"epoch": 1.05,
"learning_rate": 4.736842105263158e-05,
"loss": 0.2297,
"step": 360
},
{
"epoch": 1.06,
"learning_rate": 4.735380116959064e-05,
"loss": 0.4509,
"step": 362
},
{
"epoch": 1.06,
"learning_rate": 4.733918128654971e-05,
"loss": 0.346,
"step": 364
},
{
"epoch": 1.07,
"learning_rate": 4.7324561403508774e-05,
"loss": 0.2712,
"step": 366
},
{
"epoch": 1.08,
"learning_rate": 4.7309941520467836e-05,
"loss": 0.1036,
"step": 368
},
{
"epoch": 1.08,
"learning_rate": 4.7295321637426904e-05,
"loss": 0.2359,
"step": 370
},
{
"epoch": 1.09,
"learning_rate": 4.728070175438597e-05,
"loss": 0.6245,
"step": 372
},
{
"epoch": 1.09,
"learning_rate": 4.726608187134503e-05,
"loss": 0.1696,
"step": 374
},
{
"epoch": 1.1,
"learning_rate": 4.72514619883041e-05,
"loss": 0.0893,
"step": 376
},
{
"epoch": 1.11,
"learning_rate": 4.7236842105263166e-05,
"loss": 0.3049,
"step": 378
},
{
"epoch": 1.11,
"learning_rate": 4.722222222222222e-05,
"loss": 0.516,
"step": 380
},
{
"epoch": 1.12,
"learning_rate": 4.720760233918129e-05,
"loss": 0.5239,
"step": 382
},
{
"epoch": 1.12,
"learning_rate": 4.719298245614036e-05,
"loss": 0.0343,
"step": 384
},
{
"epoch": 1.13,
"learning_rate": 4.7178362573099414e-05,
"loss": 0.1278,
"step": 386
},
{
"epoch": 1.13,
"learning_rate": 4.716374269005848e-05,
"loss": 0.8969,
"step": 388
},
{
"epoch": 1.14,
"learning_rate": 4.714912280701755e-05,
"loss": 0.2649,
"step": 390
},
{
"epoch": 1.15,
"learning_rate": 4.7134502923976607e-05,
"loss": 0.391,
"step": 392
},
{
"epoch": 1.15,
"learning_rate": 4.7119883040935675e-05,
"loss": 0.164,
"step": 394
},
{
"epoch": 1.16,
"learning_rate": 4.7105263157894744e-05,
"loss": 0.3404,
"step": 396
},
{
"epoch": 1.16,
"learning_rate": 4.70906432748538e-05,
"loss": 0.6764,
"step": 398
},
{
"epoch": 1.17,
"learning_rate": 4.707602339181287e-05,
"loss": 0.2289,
"step": 400
},
{
"epoch": 1.18,
"learning_rate": 4.706140350877194e-05,
"loss": 0.0959,
"step": 402
},
{
"epoch": 1.18,
"learning_rate": 4.704678362573099e-05,
"loss": 0.4099,
"step": 404
},
{
"epoch": 1.19,
"learning_rate": 4.703216374269006e-05,
"loss": 0.6917,
"step": 406
},
{
"epoch": 1.19,
"learning_rate": 4.701754385964913e-05,
"loss": 0.1088,
"step": 408
},
{
"epoch": 1.2,
"learning_rate": 4.7002923976608185e-05,
"loss": 0.0851,
"step": 410
},
{
"epoch": 1.2,
"learning_rate": 4.6988304093567254e-05,
"loss": 0.5001,
"step": 412
},
{
"epoch": 1.21,
"learning_rate": 4.697368421052632e-05,
"loss": 0.606,
"step": 414
},
{
"epoch": 1.22,
"learning_rate": 4.695906432748538e-05,
"loss": 0.9455,
"step": 416
},
{
"epoch": 1.22,
"learning_rate": 4.6944444444444446e-05,
"loss": 0.6595,
"step": 418
},
{
"epoch": 1.23,
"learning_rate": 4.6929824561403515e-05,
"loss": 0.3845,
"step": 420
},
{
"epoch": 1.23,
"learning_rate": 4.691520467836257e-05,
"loss": 0.2321,
"step": 422
},
{
"epoch": 1.24,
"learning_rate": 4.690058479532164e-05,
"loss": 0.1846,
"step": 424
},
{
"epoch": 1.25,
"learning_rate": 4.688596491228071e-05,
"loss": 0.9272,
"step": 426
},
{
"epoch": 1.25,
"learning_rate": 4.687134502923976e-05,
"loss": 0.2065,
"step": 428
},
{
"epoch": 1.26,
"learning_rate": 4.685672514619883e-05,
"loss": 0.1257,
"step": 430
},
{
"epoch": 1.26,
"learning_rate": 4.68421052631579e-05,
"loss": 0.3412,
"step": 432
},
{
"epoch": 1.27,
"learning_rate": 4.6827485380116956e-05,
"loss": 0.0776,
"step": 434
},
{
"epoch": 1.27,
"learning_rate": 4.6812865497076025e-05,
"loss": 0.2499,
"step": 436
},
{
"epoch": 1.28,
"learning_rate": 4.679824561403509e-05,
"loss": 0.2121,
"step": 438
},
{
"epoch": 1.29,
"learning_rate": 4.678362573099415e-05,
"loss": 0.8954,
"step": 440
},
{
"epoch": 1.29,
"learning_rate": 4.676900584795322e-05,
"loss": 0.2103,
"step": 442
},
{
"epoch": 1.3,
"learning_rate": 4.6754385964912286e-05,
"loss": 0.5637,
"step": 444
},
{
"epoch": 1.3,
"learning_rate": 4.673976608187134e-05,
"loss": 0.6701,
"step": 446
},
{
"epoch": 1.31,
"learning_rate": 4.672514619883041e-05,
"loss": 0.5005,
"step": 448
},
{
"epoch": 1.32,
"learning_rate": 4.671052631578948e-05,
"loss": 1.2959,
"step": 450
},
{
"epoch": 1.32,
"learning_rate": 4.669590643274854e-05,
"loss": 0.5449,
"step": 452
},
{
"epoch": 1.33,
"learning_rate": 4.66812865497076e-05,
"loss": 0.2334,
"step": 454
},
{
"epoch": 1.33,
"learning_rate": 4.666666666666667e-05,
"loss": 0.6444,
"step": 456
},
{
"epoch": 1.34,
"learning_rate": 4.6652046783625734e-05,
"loss": 0.7184,
"step": 458
},
{
"epoch": 1.35,
"learning_rate": 4.6637426900584796e-05,
"loss": 0.9452,
"step": 460
},
{
"epoch": 1.35,
"learning_rate": 4.6622807017543864e-05,
"loss": 0.6433,
"step": 462
},
{
"epoch": 1.36,
"learning_rate": 4.6608187134502926e-05,
"loss": 0.5115,
"step": 464
},
{
"epoch": 1.36,
"learning_rate": 4.659356725146199e-05,
"loss": 0.0493,
"step": 466
},
{
"epoch": 1.37,
"learning_rate": 4.657894736842106e-05,
"loss": 0.9007,
"step": 468
},
{
"epoch": 1.37,
"learning_rate": 4.656432748538012e-05,
"loss": 0.0391,
"step": 470
},
{
"epoch": 1.38,
"learning_rate": 4.654970760233918e-05,
"loss": 0.4622,
"step": 472
},
{
"epoch": 1.39,
"learning_rate": 4.653508771929825e-05,
"loss": 0.7779,
"step": 474
},
{
"epoch": 1.39,
"learning_rate": 4.652046783625731e-05,
"loss": 0.6104,
"step": 476
},
{
"epoch": 1.4,
"learning_rate": 4.6505847953216374e-05,
"loss": 0.0701,
"step": 478
},
{
"epoch": 1.4,
"learning_rate": 4.649122807017544e-05,
"loss": 0.133,
"step": 480
},
{
"epoch": 1.41,
"learning_rate": 4.6476608187134505e-05,
"loss": 0.1668,
"step": 482
},
{
"epoch": 1.42,
"learning_rate": 4.6461988304093567e-05,
"loss": 0.3449,
"step": 484
},
{
"epoch": 1.42,
"learning_rate": 4.6447368421052635e-05,
"loss": 0.1383,
"step": 486
},
{
"epoch": 1.43,
"learning_rate": 4.64327485380117e-05,
"loss": 0.2053,
"step": 488
},
{
"epoch": 1.43,
"learning_rate": 4.641812865497076e-05,
"loss": 0.0624,
"step": 490
},
{
"epoch": 1.44,
"learning_rate": 4.640350877192983e-05,
"loss": 0.0211,
"step": 492
},
{
"epoch": 1.44,
"learning_rate": 4.638888888888889e-05,
"loss": 0.1512,
"step": 494
},
{
"epoch": 1.45,
"learning_rate": 4.637426900584795e-05,
"loss": 0.3669,
"step": 496
},
{
"epoch": 1.46,
"learning_rate": 4.635964912280702e-05,
"loss": 0.3664,
"step": 498
},
{
"epoch": 1.46,
"learning_rate": 4.634502923976608e-05,
"loss": 0.7642,
"step": 500
},
{
"epoch": 1.47,
"learning_rate": 4.6330409356725145e-05,
"loss": 0.1744,
"step": 502
},
{
"epoch": 1.47,
"learning_rate": 4.6315789473684214e-05,
"loss": 1.3048,
"step": 504
},
{
"epoch": 1.48,
"learning_rate": 4.6301169590643276e-05,
"loss": 0.6229,
"step": 506
},
{
"epoch": 1.49,
"learning_rate": 4.628654970760234e-05,
"loss": 0.35,
"step": 508
},
{
"epoch": 1.49,
"learning_rate": 4.6271929824561406e-05,
"loss": 0.0375,
"step": 510
},
{
"epoch": 1.5,
"learning_rate": 4.625730994152047e-05,
"loss": 0.1096,
"step": 512
},
{
"epoch": 1.5,
"learning_rate": 4.624269005847953e-05,
"loss": 0.559,
"step": 514
},
{
"epoch": 1.51,
"learning_rate": 4.62280701754386e-05,
"loss": 0.4215,
"step": 516
},
{
"epoch": 1.51,
"learning_rate": 4.621345029239766e-05,
"loss": 0.6064,
"step": 518
},
{
"epoch": 1.52,
"learning_rate": 4.619883040935672e-05,
"loss": 0.5993,
"step": 520
},
{
"epoch": 1.53,
"learning_rate": 4.618421052631579e-05,
"loss": 0.4341,
"step": 522
},
{
"epoch": 1.53,
"learning_rate": 4.6169590643274854e-05,
"loss": 0.8019,
"step": 524
},
{
"epoch": 1.54,
"learning_rate": 4.6154970760233916e-05,
"loss": 0.0486,
"step": 526
},
{
"epoch": 1.54,
"learning_rate": 4.6140350877192985e-05,
"loss": 0.4728,
"step": 528
},
{
"epoch": 1.55,
"learning_rate": 4.6125730994152047e-05,
"loss": 0.3263,
"step": 530
},
{
"epoch": 1.56,
"learning_rate": 4.6111111111111115e-05,
"loss": 0.6592,
"step": 532
},
{
"epoch": 1.56,
"learning_rate": 4.609649122807018e-05,
"loss": 0.0759,
"step": 534
},
{
"epoch": 1.57,
"learning_rate": 4.6081871345029246e-05,
"loss": 0.5624,
"step": 536
},
{
"epoch": 1.57,
"learning_rate": 4.606725146198831e-05,
"loss": 0.3394,
"step": 538
},
{
"epoch": 1.58,
"learning_rate": 4.605263157894737e-05,
"loss": 0.1943,
"step": 540
},
{
"epoch": 1.58,
"learning_rate": 4.603801169590644e-05,
"loss": 0.2539,
"step": 542
},
{
"epoch": 1.59,
"learning_rate": 4.60233918128655e-05,
"loss": 0.4366,
"step": 544
},
{
"epoch": 1.6,
"learning_rate": 4.600877192982456e-05,
"loss": 0.448,
"step": 546
},
{
"epoch": 1.6,
"learning_rate": 4.599415204678363e-05,
"loss": 0.4135,
"step": 548
},
{
"epoch": 1.61,
"learning_rate": 4.5979532163742694e-05,
"loss": 0.0708,
"step": 550
},
{
"epoch": 1.61,
"learning_rate": 4.5964912280701756e-05,
"loss": 0.3858,
"step": 552
},
{
"epoch": 1.62,
"learning_rate": 4.5950292397660824e-05,
"loss": 1.3497,
"step": 554
},
{
"epoch": 1.63,
"learning_rate": 4.5935672514619886e-05,
"loss": 0.285,
"step": 556
},
{
"epoch": 1.63,
"learning_rate": 4.592105263157895e-05,
"loss": 0.8647,
"step": 558
},
{
"epoch": 1.64,
"learning_rate": 4.590643274853802e-05,
"loss": 0.4423,
"step": 560
},
{
"epoch": 1.64,
"learning_rate": 4.589181286549708e-05,
"loss": 0.6297,
"step": 562
},
{
"epoch": 1.65,
"learning_rate": 4.587719298245614e-05,
"loss": 0.2327,
"step": 564
},
{
"epoch": 1.65,
"learning_rate": 4.586257309941521e-05,
"loss": 0.1697,
"step": 566
},
{
"epoch": 1.66,
"learning_rate": 4.584795321637427e-05,
"loss": 0.3207,
"step": 568
},
{
"epoch": 1.67,
"learning_rate": 4.5833333333333334e-05,
"loss": 0.3581,
"step": 570
},
{
"epoch": 1.67,
"learning_rate": 4.58187134502924e-05,
"loss": 0.6179,
"step": 572
},
{
"epoch": 1.68,
"learning_rate": 4.5804093567251465e-05,
"loss": 0.2073,
"step": 574
},
{
"epoch": 1.68,
"learning_rate": 4.5789473684210527e-05,
"loss": 0.2053,
"step": 576
},
{
"epoch": 1.69,
"learning_rate": 4.5774853801169595e-05,
"loss": 0.655,
"step": 578
},
{
"epoch": 1.7,
"learning_rate": 4.576023391812866e-05,
"loss": 0.4072,
"step": 580
},
{
"epoch": 1.7,
"learning_rate": 4.574561403508772e-05,
"loss": 0.1967,
"step": 582
},
{
"epoch": 1.71,
"learning_rate": 4.573099415204679e-05,
"loss": 0.483,
"step": 584
},
{
"epoch": 1.71,
"learning_rate": 4.571637426900585e-05,
"loss": 0.7497,
"step": 586
},
{
"epoch": 1.72,
"learning_rate": 4.570175438596491e-05,
"loss": 0.241,
"step": 588
},
{
"epoch": 1.73,
"learning_rate": 4.568713450292398e-05,
"loss": 0.1218,
"step": 590
},
{
"epoch": 1.73,
"learning_rate": 4.567251461988304e-05,
"loss": 0.0548,
"step": 592
},
{
"epoch": 1.74,
"learning_rate": 4.5657894736842105e-05,
"loss": 0.1139,
"step": 594
},
{
"epoch": 1.74,
"learning_rate": 4.5643274853801174e-05,
"loss": 0.1125,
"step": 596
},
{
"epoch": 1.75,
"learning_rate": 4.5628654970760236e-05,
"loss": 0.4772,
"step": 598
},
{
"epoch": 1.75,
"learning_rate": 4.56140350877193e-05,
"loss": 0.0136,
"step": 600
},
{
"epoch": 1.76,
"learning_rate": 4.5599415204678366e-05,
"loss": 0.0577,
"step": 602
},
{
"epoch": 1.77,
"learning_rate": 4.558479532163743e-05,
"loss": 0.1975,
"step": 604
},
{
"epoch": 1.77,
"learning_rate": 4.557017543859649e-05,
"loss": 0.1911,
"step": 606
},
{
"epoch": 1.78,
"learning_rate": 4.555555555555556e-05,
"loss": 0.0067,
"step": 608
},
{
"epoch": 1.78,
"learning_rate": 4.554093567251462e-05,
"loss": 0.3065,
"step": 610
},
{
"epoch": 1.79,
"learning_rate": 4.552631578947369e-05,
"loss": 0.6154,
"step": 612
},
{
"epoch": 1.8,
"learning_rate": 4.551169590643275e-05,
"loss": 0.2049,
"step": 614
},
{
"epoch": 1.8,
"learning_rate": 4.5497076023391814e-05,
"loss": 0.0275,
"step": 616
},
{
"epoch": 1.81,
"learning_rate": 4.548245614035088e-05,
"loss": 0.1954,
"step": 618
},
{
"epoch": 1.81,
"learning_rate": 4.5467836257309945e-05,
"loss": 0.1028,
"step": 620
},
{
"epoch": 1.82,
"learning_rate": 4.5453216374269007e-05,
"loss": 0.5081,
"step": 622
},
{
"epoch": 1.82,
"learning_rate": 4.5438596491228075e-05,
"loss": 0.435,
"step": 624
},
{
"epoch": 1.83,
"learning_rate": 4.542397660818714e-05,
"loss": 0.4657,
"step": 626
},
{
"epoch": 1.84,
"learning_rate": 4.54093567251462e-05,
"loss": 0.0542,
"step": 628
},
{
"epoch": 1.84,
"learning_rate": 4.539473684210527e-05,
"loss": 0.3461,
"step": 630
},
{
"epoch": 1.85,
"learning_rate": 4.538011695906433e-05,
"loss": 0.2947,
"step": 632
},
{
"epoch": 1.85,
"learning_rate": 4.536549707602339e-05,
"loss": 0.0609,
"step": 634
},
{
"epoch": 1.86,
"learning_rate": 4.535087719298246e-05,
"loss": 0.6259,
"step": 636
},
{
"epoch": 1.87,
"learning_rate": 4.533625730994152e-05,
"loss": 0.4511,
"step": 638
},
{
"epoch": 1.87,
"learning_rate": 4.5321637426900585e-05,
"loss": 0.6193,
"step": 640
},
{
"epoch": 1.88,
"learning_rate": 4.5307017543859654e-05,
"loss": 0.2334,
"step": 642
},
{
"epoch": 1.88,
"learning_rate": 4.5292397660818716e-05,
"loss": 0.5565,
"step": 644
},
{
"epoch": 1.89,
"learning_rate": 4.527777777777778e-05,
"loss": 0.9064,
"step": 646
},
{
"epoch": 1.89,
"learning_rate": 4.5263157894736846e-05,
"loss": 0.2996,
"step": 648
},
{
"epoch": 1.9,
"learning_rate": 4.524853801169591e-05,
"loss": 0.9017,
"step": 650
},
{
"epoch": 1.91,
"learning_rate": 4.523391812865497e-05,
"loss": 0.3582,
"step": 652
},
{
"epoch": 1.91,
"learning_rate": 4.521929824561404e-05,
"loss": 0.148,
"step": 654
},
{
"epoch": 1.92,
"learning_rate": 4.52046783625731e-05,
"loss": 0.2039,
"step": 656
},
{
"epoch": 1.92,
"learning_rate": 4.519005847953216e-05,
"loss": 0.1892,
"step": 658
},
{
"epoch": 1.93,
"learning_rate": 4.517543859649123e-05,
"loss": 0.0973,
"step": 660
},
{
"epoch": 1.94,
"learning_rate": 4.5160818713450294e-05,
"loss": 0.4039,
"step": 662
},
{
"epoch": 1.94,
"learning_rate": 4.5146198830409356e-05,
"loss": 0.1619,
"step": 664
},
{
"epoch": 1.95,
"learning_rate": 4.5131578947368425e-05,
"loss": 0.1039,
"step": 666
},
{
"epoch": 1.95,
"learning_rate": 4.5116959064327487e-05,
"loss": 1.5008,
"step": 668
},
{
"epoch": 1.96,
"learning_rate": 4.510233918128655e-05,
"loss": 0.0843,
"step": 670
},
{
"epoch": 1.96,
"learning_rate": 4.508771929824562e-05,
"loss": 0.7469,
"step": 672
},
{
"epoch": 1.97,
"learning_rate": 4.507309941520468e-05,
"loss": 0.3297,
"step": 674
},
{
"epoch": 1.98,
"learning_rate": 4.505847953216374e-05,
"loss": 0.4485,
"step": 676
},
{
"epoch": 1.98,
"learning_rate": 4.504385964912281e-05,
"loss": 0.6894,
"step": 678
},
{
"epoch": 1.99,
"learning_rate": 4.502923976608187e-05,
"loss": 0.276,
"step": 680
},
{
"epoch": 1.99,
"learning_rate": 4.5014619883040934e-05,
"loss": 0.7757,
"step": 682
},
{
"epoch": 2.0,
"learning_rate": 4.5e-05,
"loss": 0.9594,
"step": 684
},
{
"epoch": 2.0,
"eval_bleu": 0.4968869990994432,
"eval_loss": 0.688098132610321,
"eval_runtime": 37.2168,
"eval_samples_per_second": 9.001,
"eval_steps_per_second": 2.257,
"step": 684
},
{
"epoch": 2.01,
"learning_rate": 4.4985380116959065e-05,
"loss": 0.1367,
"step": 686
},
{
"epoch": 2.01,
"learning_rate": 4.497076023391813e-05,
"loss": 0.4026,
"step": 688
},
{
"epoch": 2.02,
"learning_rate": 4.4956140350877196e-05,
"loss": 0.1066,
"step": 690
},
{
"epoch": 2.02,
"learning_rate": 4.494152046783626e-05,
"loss": 0.1517,
"step": 692
},
{
"epoch": 2.03,
"learning_rate": 4.492690058479532e-05,
"loss": 0.7912,
"step": 694
},
{
"epoch": 2.04,
"learning_rate": 4.491228070175439e-05,
"loss": 0.0636,
"step": 696
},
{
"epoch": 2.04,
"learning_rate": 4.489766081871346e-05,
"loss": 0.4316,
"step": 698
},
{
"epoch": 2.05,
"learning_rate": 4.488304093567251e-05,
"loss": 0.0263,
"step": 700
},
{
"epoch": 2.05,
"learning_rate": 4.486842105263158e-05,
"loss": 0.0203,
"step": 702
},
{
"epoch": 2.06,
"learning_rate": 4.485380116959065e-05,
"loss": 0.0699,
"step": 704
},
{
"epoch": 2.06,
"learning_rate": 4.483918128654971e-05,
"loss": 0.328,
"step": 706
},
{
"epoch": 2.07,
"learning_rate": 4.4824561403508774e-05,
"loss": 0.1817,
"step": 708
},
{
"epoch": 2.08,
"learning_rate": 4.480994152046784e-05,
"loss": 0.4908,
"step": 710
},
{
"epoch": 2.08,
"learning_rate": 4.4795321637426905e-05,
"loss": 0.036,
"step": 712
},
{
"epoch": 2.09,
"learning_rate": 4.4780701754385967e-05,
"loss": 0.1806,
"step": 714
},
{
"epoch": 2.09,
"learning_rate": 4.4766081871345035e-05,
"loss": 0.1746,
"step": 716
},
{
"epoch": 2.1,
"learning_rate": 4.47514619883041e-05,
"loss": 0.3132,
"step": 718
},
{
"epoch": 2.11,
"learning_rate": 4.473684210526316e-05,
"loss": 0.4823,
"step": 720
},
{
"epoch": 2.11,
"learning_rate": 4.472222222222223e-05,
"loss": 0.2957,
"step": 722
},
{
"epoch": 2.12,
"learning_rate": 4.470760233918129e-05,
"loss": 0.068,
"step": 724
},
{
"epoch": 2.12,
"learning_rate": 4.469298245614035e-05,
"loss": 0.2587,
"step": 726
},
{
"epoch": 2.13,
"learning_rate": 4.467836257309942e-05,
"loss": 0.0409,
"step": 728
},
{
"epoch": 2.13,
"learning_rate": 4.466374269005848e-05,
"loss": 0.2195,
"step": 730
},
{
"epoch": 2.14,
"learning_rate": 4.4649122807017545e-05,
"loss": 0.1696,
"step": 732
},
{
"epoch": 2.15,
"learning_rate": 4.4634502923976614e-05,
"loss": 0.0157,
"step": 734
},
{
"epoch": 2.15,
"learning_rate": 4.4619883040935676e-05,
"loss": 0.0345,
"step": 736
},
{
"epoch": 2.16,
"learning_rate": 4.460526315789474e-05,
"loss": 0.1948,
"step": 738
},
{
"epoch": 2.16,
"learning_rate": 4.4590643274853806e-05,
"loss": 0.2997,
"step": 740
},
{
"epoch": 2.17,
"learning_rate": 4.457602339181287e-05,
"loss": 0.3632,
"step": 742
},
{
"epoch": 2.18,
"learning_rate": 4.456140350877193e-05,
"loss": 0.2202,
"step": 744
},
{
"epoch": 2.18,
"learning_rate": 4.4546783625731e-05,
"loss": 0.0775,
"step": 746
},
{
"epoch": 2.19,
"learning_rate": 4.453216374269006e-05,
"loss": 0.0089,
"step": 748
},
{
"epoch": 2.19,
"learning_rate": 4.451754385964912e-05,
"loss": 0.1039,
"step": 750
},
{
"epoch": 2.2,
"learning_rate": 4.450292397660819e-05,
"loss": 0.0069,
"step": 752
},
{
"epoch": 2.2,
"learning_rate": 4.4488304093567254e-05,
"loss": 0.4134,
"step": 754
},
{
"epoch": 2.21,
"learning_rate": 4.4473684210526316e-05,
"loss": 0.2336,
"step": 756
},
{
"epoch": 2.22,
"learning_rate": 4.4459064327485385e-05,
"loss": 0.0495,
"step": 758
},
{
"epoch": 2.22,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.006,
"step": 760
},
{
"epoch": 2.23,
"learning_rate": 4.442982456140351e-05,
"loss": 0.6604,
"step": 762
},
{
"epoch": 2.23,
"learning_rate": 4.441520467836258e-05,
"loss": 0.1419,
"step": 764
},
{
"epoch": 2.24,
"learning_rate": 4.440058479532164e-05,
"loss": 0.211,
"step": 766
},
{
"epoch": 2.25,
"learning_rate": 4.43859649122807e-05,
"loss": 0.2647,
"step": 768
},
{
"epoch": 2.25,
"learning_rate": 4.437134502923977e-05,
"loss": 0.3349,
"step": 770
},
{
"epoch": 2.26,
"learning_rate": 4.435672514619883e-05,
"loss": 0.0323,
"step": 772
},
{
"epoch": 2.26,
"learning_rate": 4.4342105263157894e-05,
"loss": 0.2041,
"step": 774
},
{
"epoch": 2.27,
"learning_rate": 4.432748538011696e-05,
"loss": 0.4073,
"step": 776
},
{
"epoch": 2.27,
"learning_rate": 4.4312865497076025e-05,
"loss": 0.0627,
"step": 778
},
{
"epoch": 2.28,
"learning_rate": 4.429824561403509e-05,
"loss": 0.5988,
"step": 780
},
{
"epoch": 2.29,
"learning_rate": 4.4283625730994156e-05,
"loss": 0.0372,
"step": 782
},
{
"epoch": 2.29,
"learning_rate": 4.4269005847953224e-05,
"loss": 0.0172,
"step": 784
},
{
"epoch": 2.3,
"learning_rate": 4.425438596491228e-05,
"loss": 0.0408,
"step": 786
},
{
"epoch": 2.3,
"learning_rate": 4.423976608187135e-05,
"loss": 0.273,
"step": 788
},
{
"epoch": 2.31,
"learning_rate": 4.422514619883042e-05,
"loss": 0.0269,
"step": 790
},
{
"epoch": 2.32,
"learning_rate": 4.421052631578947e-05,
"loss": 0.3813,
"step": 792
},
{
"epoch": 2.32,
"learning_rate": 4.419590643274854e-05,
"loss": 1.0685,
"step": 794
},
{
"epoch": 2.33,
"learning_rate": 4.418128654970761e-05,
"loss": 0.0149,
"step": 796
},
{
"epoch": 2.33,
"learning_rate": 4.4166666666666665e-05,
"loss": 0.2711,
"step": 798
},
{
"epoch": 2.34,
"learning_rate": 4.4152046783625734e-05,
"loss": 0.1867,
"step": 800
},
{
"epoch": 2.35,
"learning_rate": 4.41374269005848e-05,
"loss": 0.4221,
"step": 802
},
{
"epoch": 2.35,
"learning_rate": 4.412280701754386e-05,
"loss": 0.1857,
"step": 804
},
{
"epoch": 2.36,
"learning_rate": 4.4108187134502927e-05,
"loss": 0.2577,
"step": 806
},
{
"epoch": 2.36,
"learning_rate": 4.4093567251461995e-05,
"loss": 0.3916,
"step": 808
},
{
"epoch": 2.37,
"learning_rate": 4.407894736842105e-05,
"loss": 0.2095,
"step": 810
},
{
"epoch": 2.37,
"learning_rate": 4.406432748538012e-05,
"loss": 0.0669,
"step": 812
},
{
"epoch": 2.38,
"learning_rate": 4.404970760233919e-05,
"loss": 0.0592,
"step": 814
},
{
"epoch": 2.39,
"learning_rate": 4.403508771929824e-05,
"loss": 0.1785,
"step": 816
},
{
"epoch": 2.39,
"learning_rate": 4.402046783625731e-05,
"loss": 0.3322,
"step": 818
},
{
"epoch": 2.4,
"learning_rate": 4.400584795321638e-05,
"loss": 0.4306,
"step": 820
},
{
"epoch": 2.4,
"learning_rate": 4.3991228070175436e-05,
"loss": 0.185,
"step": 822
},
{
"epoch": 2.41,
"learning_rate": 4.3976608187134505e-05,
"loss": 0.0166,
"step": 824
},
{
"epoch": 2.42,
"learning_rate": 4.3961988304093574e-05,
"loss": 0.278,
"step": 826
},
{
"epoch": 2.42,
"learning_rate": 4.394736842105263e-05,
"loss": 0.0304,
"step": 828
},
{
"epoch": 2.43,
"learning_rate": 4.39327485380117e-05,
"loss": 0.0183,
"step": 830
},
{
"epoch": 2.43,
"learning_rate": 4.3918128654970766e-05,
"loss": 0.138,
"step": 832
},
{
"epoch": 2.44,
"learning_rate": 4.390350877192982e-05,
"loss": 0.3052,
"step": 834
},
{
"epoch": 2.44,
"learning_rate": 4.388888888888889e-05,
"loss": 0.0529,
"step": 836
},
{
"epoch": 2.45,
"learning_rate": 4.387426900584796e-05,
"loss": 0.1001,
"step": 838
},
{
"epoch": 2.46,
"learning_rate": 4.3859649122807014e-05,
"loss": 0.0396,
"step": 840
},
{
"epoch": 2.46,
"learning_rate": 4.384502923976608e-05,
"loss": 0.0205,
"step": 842
},
{
"epoch": 2.47,
"learning_rate": 4.383040935672515e-05,
"loss": 0.07,
"step": 844
},
{
"epoch": 2.47,
"learning_rate": 4.381578947368421e-05,
"loss": 0.0011,
"step": 846
},
{
"epoch": 2.48,
"learning_rate": 4.3801169590643276e-05,
"loss": 0.4012,
"step": 848
},
{
"epoch": 2.49,
"learning_rate": 4.3786549707602345e-05,
"loss": 0.0803,
"step": 850
},
{
"epoch": 2.49,
"learning_rate": 4.37719298245614e-05,
"loss": 0.2227,
"step": 852
},
{
"epoch": 2.5,
"learning_rate": 4.375730994152047e-05,
"loss": 0.5534,
"step": 854
},
{
"epoch": 2.5,
"learning_rate": 4.374269005847954e-05,
"loss": 0.2611,
"step": 856
},
{
"epoch": 2.51,
"learning_rate": 4.37280701754386e-05,
"loss": 0.0869,
"step": 858
},
{
"epoch": 2.51,
"learning_rate": 4.371345029239766e-05,
"loss": 0.0758,
"step": 860
},
{
"epoch": 2.52,
"learning_rate": 4.369883040935673e-05,
"loss": 0.6195,
"step": 862
},
{
"epoch": 2.53,
"learning_rate": 4.368421052631579e-05,
"loss": 0.0229,
"step": 864
},
{
"epoch": 2.53,
"learning_rate": 4.3669590643274854e-05,
"loss": 0.0196,
"step": 866
},
{
"epoch": 2.54,
"learning_rate": 4.365497076023392e-05,
"loss": 0.0277,
"step": 868
},
{
"epoch": 2.54,
"learning_rate": 4.3640350877192985e-05,
"loss": 0.0503,
"step": 870
},
{
"epoch": 2.55,
"learning_rate": 4.362573099415205e-05,
"loss": 0.1951,
"step": 872
},
{
"epoch": 2.56,
"learning_rate": 4.3611111111111116e-05,
"loss": 0.376,
"step": 874
},
{
"epoch": 2.56,
"learning_rate": 4.359649122807018e-05,
"loss": 0.0539,
"step": 876
},
{
"epoch": 2.57,
"learning_rate": 4.358187134502924e-05,
"loss": 0.2401,
"step": 878
},
{
"epoch": 2.57,
"learning_rate": 4.356725146198831e-05,
"loss": 0.1868,
"step": 880
},
{
"epoch": 2.58,
"learning_rate": 4.355263157894737e-05,
"loss": 0.3675,
"step": 882
},
{
"epoch": 2.58,
"learning_rate": 4.353801169590643e-05,
"loss": 0.219,
"step": 884
},
{
"epoch": 2.59,
"learning_rate": 4.35233918128655e-05,
"loss": 0.2102,
"step": 886
},
{
"epoch": 2.6,
"learning_rate": 4.350877192982456e-05,
"loss": 0.1682,
"step": 888
},
{
"epoch": 2.6,
"learning_rate": 4.3494152046783625e-05,
"loss": 0.0098,
"step": 890
},
{
"epoch": 2.61,
"learning_rate": 4.3479532163742694e-05,
"loss": 0.085,
"step": 892
},
{
"epoch": 2.61,
"learning_rate": 4.3464912280701756e-05,
"loss": 0.0094,
"step": 894
},
{
"epoch": 2.62,
"learning_rate": 4.345029239766082e-05,
"loss": 0.2675,
"step": 896
},
{
"epoch": 2.63,
"learning_rate": 4.3435672514619887e-05,
"loss": 0.2811,
"step": 898
},
{
"epoch": 2.63,
"learning_rate": 4.342105263157895e-05,
"loss": 0.3214,
"step": 900
},
{
"epoch": 2.64,
"learning_rate": 4.340643274853801e-05,
"loss": 0.0037,
"step": 902
},
{
"epoch": 2.64,
"learning_rate": 4.339181286549708e-05,
"loss": 0.2272,
"step": 904
},
{
"epoch": 2.65,
"learning_rate": 4.337719298245614e-05,
"loss": 0.4622,
"step": 906
},
{
"epoch": 2.65,
"learning_rate": 4.33625730994152e-05,
"loss": 0.2988,
"step": 908
},
{
"epoch": 2.66,
"learning_rate": 4.334795321637427e-05,
"loss": 0.3439,
"step": 910
},
{
"epoch": 2.67,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.0679,
"step": 912
},
{
"epoch": 2.67,
"learning_rate": 4.3318713450292396e-05,
"loss": 0.0118,
"step": 914
},
{
"epoch": 2.68,
"learning_rate": 4.3304093567251465e-05,
"loss": 0.0826,
"step": 916
},
{
"epoch": 2.68,
"learning_rate": 4.328947368421053e-05,
"loss": 0.5045,
"step": 918
},
{
"epoch": 2.69,
"learning_rate": 4.327485380116959e-05,
"loss": 0.1637,
"step": 920
},
{
"epoch": 2.7,
"learning_rate": 4.326023391812866e-05,
"loss": 0.3997,
"step": 922
},
{
"epoch": 2.7,
"learning_rate": 4.324561403508772e-05,
"loss": 0.0403,
"step": 924
},
{
"epoch": 2.71,
"learning_rate": 4.323099415204678e-05,
"loss": 0.2226,
"step": 926
},
{
"epoch": 2.71,
"learning_rate": 4.321637426900585e-05,
"loss": 0.3761,
"step": 928
},
{
"epoch": 2.72,
"learning_rate": 4.320175438596491e-05,
"loss": 0.2154,
"step": 930
},
{
"epoch": 2.73,
"learning_rate": 4.3187134502923974e-05,
"loss": 0.4742,
"step": 932
},
{
"epoch": 2.73,
"learning_rate": 4.317251461988304e-05,
"loss": 0.1359,
"step": 934
},
{
"epoch": 2.74,
"learning_rate": 4.3157894736842105e-05,
"loss": 0.1784,
"step": 936
},
{
"epoch": 2.74,
"learning_rate": 4.3143274853801174e-05,
"loss": 0.5816,
"step": 938
},
{
"epoch": 2.75,
"learning_rate": 4.3128654970760236e-05,
"loss": 0.1001,
"step": 940
},
{
"epoch": 2.75,
"learning_rate": 4.31140350877193e-05,
"loss": 0.0177,
"step": 942
},
{
"epoch": 2.76,
"learning_rate": 4.3099415204678367e-05,
"loss": 0.0243,
"step": 944
},
{
"epoch": 2.77,
"learning_rate": 4.308479532163743e-05,
"loss": 0.0797,
"step": 946
},
{
"epoch": 2.77,
"learning_rate": 4.30701754385965e-05,
"loss": 1.0042,
"step": 948
},
{
"epoch": 2.78,
"learning_rate": 4.305555555555556e-05,
"loss": 0.0104,
"step": 950
},
{
"epoch": 2.78,
"learning_rate": 4.304093567251462e-05,
"loss": 0.308,
"step": 952
},
{
"epoch": 2.79,
"learning_rate": 4.302631578947369e-05,
"loss": 0.0708,
"step": 954
},
{
"epoch": 2.8,
"learning_rate": 4.301169590643275e-05,
"loss": 0.2511,
"step": 956
},
{
"epoch": 2.8,
"learning_rate": 4.2997076023391814e-05,
"loss": 0.2792,
"step": 958
},
{
"epoch": 2.81,
"learning_rate": 4.298245614035088e-05,
"loss": 0.0155,
"step": 960
},
{
"epoch": 2.81,
"learning_rate": 4.2967836257309945e-05,
"loss": 0.1183,
"step": 962
},
{
"epoch": 2.82,
"learning_rate": 4.295321637426901e-05,
"loss": 0.2006,
"step": 964
},
{
"epoch": 2.82,
"learning_rate": 4.2938596491228076e-05,
"loss": 0.0438,
"step": 966
},
{
"epoch": 2.83,
"learning_rate": 4.292397660818714e-05,
"loss": 0.5169,
"step": 968
},
{
"epoch": 2.84,
"learning_rate": 4.29093567251462e-05,
"loss": 0.2378,
"step": 970
},
{
"epoch": 2.84,
"learning_rate": 4.289473684210527e-05,
"loss": 0.0281,
"step": 972
},
{
"epoch": 2.85,
"learning_rate": 4.288011695906433e-05,
"loss": 0.0049,
"step": 974
},
{
"epoch": 2.85,
"learning_rate": 4.286549707602339e-05,
"loss": 0.3161,
"step": 976
},
{
"epoch": 2.86,
"learning_rate": 4.285087719298246e-05,
"loss": 0.331,
"step": 978
},
{
"epoch": 2.87,
"learning_rate": 4.283625730994152e-05,
"loss": 0.3509,
"step": 980
},
{
"epoch": 2.87,
"learning_rate": 4.2821637426900585e-05,
"loss": 0.3139,
"step": 982
},
{
"epoch": 2.88,
"learning_rate": 4.2807017543859654e-05,
"loss": 0.9779,
"step": 984
},
{
"epoch": 2.88,
"learning_rate": 4.2792397660818716e-05,
"loss": 0.2647,
"step": 986
},
{
"epoch": 2.89,
"learning_rate": 4.277777777777778e-05,
"loss": 0.1281,
"step": 988
},
{
"epoch": 2.89,
"learning_rate": 4.2763157894736847e-05,
"loss": 0.2245,
"step": 990
},
{
"epoch": 2.9,
"learning_rate": 4.274853801169591e-05,
"loss": 0.2801,
"step": 992
},
{
"epoch": 2.91,
"learning_rate": 4.273391812865497e-05,
"loss": 0.0615,
"step": 994
},
{
"epoch": 2.91,
"learning_rate": 4.271929824561404e-05,
"loss": 0.671,
"step": 996
},
{
"epoch": 2.92,
"learning_rate": 4.27046783625731e-05,
"loss": 0.0097,
"step": 998
},
{
"epoch": 2.92,
"learning_rate": 4.269005847953216e-05,
"loss": 0.1268,
"step": 1000
},
{
"epoch": 2.93,
"learning_rate": 4.267543859649123e-05,
"loss": 0.0252,
"step": 1002
},
{
"epoch": 2.94,
"learning_rate": 4.2660818713450294e-05,
"loss": 0.0667,
"step": 1004
},
{
"epoch": 2.94,
"learning_rate": 4.2646198830409356e-05,
"loss": 0.1346,
"step": 1006
},
{
"epoch": 2.95,
"learning_rate": 4.2631578947368425e-05,
"loss": 0.1512,
"step": 1008
},
{
"epoch": 2.95,
"learning_rate": 4.261695906432749e-05,
"loss": 0.1037,
"step": 1010
},
{
"epoch": 2.96,
"learning_rate": 4.260233918128655e-05,
"loss": 0.4586,
"step": 1012
},
{
"epoch": 2.96,
"learning_rate": 4.258771929824562e-05,
"loss": 0.0881,
"step": 1014
},
{
"epoch": 2.97,
"learning_rate": 4.257309941520468e-05,
"loss": 0.4883,
"step": 1016
},
{
"epoch": 2.98,
"learning_rate": 4.255847953216375e-05,
"loss": 0.5389,
"step": 1018
},
{
"epoch": 2.98,
"learning_rate": 4.254385964912281e-05,
"loss": 0.0774,
"step": 1020
},
{
"epoch": 2.99,
"learning_rate": 4.252923976608187e-05,
"loss": 0.0513,
"step": 1022
},
{
"epoch": 2.99,
"learning_rate": 4.251461988304094e-05,
"loss": 0.9817,
"step": 1024
},
{
"epoch": 3.0,
"learning_rate": 4.25e-05,
"loss": 0.1095,
"step": 1026
},
{
"epoch": 3.0,
"eval_bleu": 0.49117424878427407,
"eval_loss": 0.8695371747016907,
"eval_runtime": 35.8936,
"eval_samples_per_second": 9.333,
"eval_steps_per_second": 2.34,
"step": 1026
},
{
"epoch": 3.01,
"learning_rate": 4.2485380116959065e-05,
"loss": 0.0686,
"step": 1028
},
{
"epoch": 3.01,
"learning_rate": 4.2470760233918134e-05,
"loss": 0.3169,
"step": 1030
},
{
"epoch": 3.02,
"learning_rate": 4.2456140350877196e-05,
"loss": 0.0121,
"step": 1032
},
{
"epoch": 3.02,
"learning_rate": 4.244152046783626e-05,
"loss": 0.0276,
"step": 1034
},
{
"epoch": 3.03,
"learning_rate": 4.2426900584795327e-05,
"loss": 0.1847,
"step": 1036
},
{
"epoch": 3.04,
"learning_rate": 4.241228070175439e-05,
"loss": 0.0888,
"step": 1038
},
{
"epoch": 3.04,
"learning_rate": 4.239766081871345e-05,
"loss": 0.039,
"step": 1040
},
{
"epoch": 3.05,
"learning_rate": 4.238304093567252e-05,
"loss": 0.0251,
"step": 1042
},
{
"epoch": 3.05,
"learning_rate": 4.236842105263158e-05,
"loss": 0.7449,
"step": 1044
},
{
"epoch": 3.06,
"learning_rate": 4.235380116959064e-05,
"loss": 0.0048,
"step": 1046
},
{
"epoch": 3.06,
"learning_rate": 4.233918128654971e-05,
"loss": 0.1331,
"step": 1048
},
{
"epoch": 3.07,
"learning_rate": 4.2324561403508774e-05,
"loss": 0.2155,
"step": 1050
},
{
"epoch": 3.08,
"learning_rate": 4.2309941520467836e-05,
"loss": 0.0346,
"step": 1052
},
{
"epoch": 3.08,
"learning_rate": 4.2295321637426905e-05,
"loss": 0.0035,
"step": 1054
},
{
"epoch": 3.09,
"learning_rate": 4.228070175438597e-05,
"loss": 0.0824,
"step": 1056
},
{
"epoch": 3.09,
"learning_rate": 4.226608187134503e-05,
"loss": 0.0151,
"step": 1058
},
{
"epoch": 3.1,
"learning_rate": 4.22514619883041e-05,
"loss": 0.2945,
"step": 1060
},
{
"epoch": 3.11,
"learning_rate": 4.223684210526316e-05,
"loss": 0.014,
"step": 1062
},
{
"epoch": 3.11,
"learning_rate": 4.222222222222222e-05,
"loss": 0.0016,
"step": 1064
},
{
"epoch": 3.12,
"learning_rate": 4.220760233918129e-05,
"loss": 0.001,
"step": 1066
},
{
"epoch": 3.12,
"learning_rate": 4.219298245614035e-05,
"loss": 0.0414,
"step": 1068
},
{
"epoch": 3.13,
"learning_rate": 4.2178362573099414e-05,
"loss": 0.4737,
"step": 1070
},
{
"epoch": 3.13,
"learning_rate": 4.216374269005848e-05,
"loss": 0.6829,
"step": 1072
},
{
"epoch": 3.14,
"learning_rate": 4.2149122807017545e-05,
"loss": 0.0122,
"step": 1074
},
{
"epoch": 3.15,
"learning_rate": 4.213450292397661e-05,
"loss": 0.0029,
"step": 1076
},
{
"epoch": 3.15,
"learning_rate": 4.2119883040935676e-05,
"loss": 0.0806,
"step": 1078
},
{
"epoch": 3.16,
"learning_rate": 4.210526315789474e-05,
"loss": 0.2209,
"step": 1080
},
{
"epoch": 3.16,
"learning_rate": 4.20906432748538e-05,
"loss": 0.0049,
"step": 1082
},
{
"epoch": 3.17,
"learning_rate": 4.207602339181287e-05,
"loss": 0.1225,
"step": 1084
},
{
"epoch": 3.18,
"learning_rate": 4.206140350877193e-05,
"loss": 0.6612,
"step": 1086
},
{
"epoch": 3.18,
"learning_rate": 4.204678362573099e-05,
"loss": 0.5263,
"step": 1088
},
{
"epoch": 3.19,
"learning_rate": 4.203216374269006e-05,
"loss": 0.323,
"step": 1090
},
{
"epoch": 3.19,
"learning_rate": 4.201754385964912e-05,
"loss": 0.1397,
"step": 1092
},
{
"epoch": 3.2,
"learning_rate": 4.2002923976608185e-05,
"loss": 0.0347,
"step": 1094
},
{
"epoch": 3.2,
"learning_rate": 4.1988304093567254e-05,
"loss": 0.0879,
"step": 1096
},
{
"epoch": 3.21,
"learning_rate": 4.1973684210526316e-05,
"loss": 0.0043,
"step": 1098
},
{
"epoch": 3.22,
"learning_rate": 4.195906432748538e-05,
"loss": 0.2206,
"step": 1100
},
{
"epoch": 3.22,
"learning_rate": 4.194444444444445e-05,
"loss": 0.2116,
"step": 1102
},
{
"epoch": 3.23,
"learning_rate": 4.1929824561403516e-05,
"loss": 0.0047,
"step": 1104
},
{
"epoch": 3.23,
"learning_rate": 4.191520467836257e-05,
"loss": 0.3167,
"step": 1106
},
{
"epoch": 3.24,
"learning_rate": 4.190058479532164e-05,
"loss": 0.2827,
"step": 1108
},
{
"epoch": 3.25,
"learning_rate": 4.188596491228071e-05,
"loss": 0.1936,
"step": 1110
},
{
"epoch": 3.25,
"learning_rate": 4.1871345029239764e-05,
"loss": 0.0571,
"step": 1112
},
{
"epoch": 3.26,
"learning_rate": 4.185672514619883e-05,
"loss": 0.0338,
"step": 1114
},
{
"epoch": 3.26,
"learning_rate": 4.18421052631579e-05,
"loss": 0.3763,
"step": 1116
},
{
"epoch": 3.27,
"learning_rate": 4.182748538011696e-05,
"loss": 0.0225,
"step": 1118
},
{
"epoch": 3.27,
"learning_rate": 4.1812865497076025e-05,
"loss": 0.0095,
"step": 1120
},
{
"epoch": 3.28,
"learning_rate": 4.1798245614035094e-05,
"loss": 0.0014,
"step": 1122
},
{
"epoch": 3.29,
"learning_rate": 4.1783625730994156e-05,
"loss": 0.1323,
"step": 1124
},
{
"epoch": 3.29,
"learning_rate": 4.176900584795322e-05,
"loss": 0.2101,
"step": 1126
},
{
"epoch": 3.3,
"learning_rate": 4.1754385964912287e-05,
"loss": 0.066,
"step": 1128
},
{
"epoch": 3.3,
"learning_rate": 4.173976608187135e-05,
"loss": 0.0569,
"step": 1130
},
{
"epoch": 3.31,
"learning_rate": 4.172514619883041e-05,
"loss": 0.1135,
"step": 1132
},
{
"epoch": 3.32,
"learning_rate": 4.171052631578948e-05,
"loss": 0.0016,
"step": 1134
},
{
"epoch": 3.32,
"learning_rate": 4.169590643274854e-05,
"loss": 0.0357,
"step": 1136
},
{
"epoch": 3.33,
"learning_rate": 4.16812865497076e-05,
"loss": 0.4321,
"step": 1138
},
{
"epoch": 3.33,
"learning_rate": 4.166666666666667e-05,
"loss": 0.2578,
"step": 1140
},
{
"epoch": 3.34,
"learning_rate": 4.1652046783625734e-05,
"loss": 0.466,
"step": 1142
},
{
"epoch": 3.35,
"learning_rate": 4.1637426900584796e-05,
"loss": 0.023,
"step": 1144
},
{
"epoch": 3.35,
"learning_rate": 4.1622807017543865e-05,
"loss": 0.0072,
"step": 1146
},
{
"epoch": 3.36,
"learning_rate": 4.160818713450293e-05,
"loss": 0.2669,
"step": 1148
},
{
"epoch": 3.36,
"learning_rate": 4.159356725146199e-05,
"loss": 0.0108,
"step": 1150
},
{
"epoch": 3.37,
"learning_rate": 4.157894736842106e-05,
"loss": 0.0087,
"step": 1152
},
{
"epoch": 3.37,
"learning_rate": 4.156432748538012e-05,
"loss": 0.1986,
"step": 1154
},
{
"epoch": 3.38,
"learning_rate": 4.154970760233918e-05,
"loss": 0.0053,
"step": 1156
},
{
"epoch": 3.39,
"learning_rate": 4.153508771929825e-05,
"loss": 0.0141,
"step": 1158
},
{
"epoch": 3.39,
"learning_rate": 4.152046783625731e-05,
"loss": 0.0996,
"step": 1160
},
{
"epoch": 3.4,
"learning_rate": 4.1505847953216374e-05,
"loss": 0.1708,
"step": 1162
},
{
"epoch": 3.4,
"learning_rate": 4.149122807017544e-05,
"loss": 0.207,
"step": 1164
},
{
"epoch": 3.41,
"learning_rate": 4.1476608187134505e-05,
"loss": 0.0012,
"step": 1166
},
{
"epoch": 3.42,
"learning_rate": 4.146198830409357e-05,
"loss": 0.2327,
"step": 1168
},
{
"epoch": 3.42,
"learning_rate": 4.1447368421052636e-05,
"loss": 0.0795,
"step": 1170
},
{
"epoch": 3.43,
"learning_rate": 4.14327485380117e-05,
"loss": 0.0515,
"step": 1172
},
{
"epoch": 3.43,
"learning_rate": 4.141812865497076e-05,
"loss": 0.3565,
"step": 1174
},
{
"epoch": 3.44,
"learning_rate": 4.140350877192983e-05,
"loss": 0.0892,
"step": 1176
},
{
"epoch": 3.44,
"learning_rate": 4.138888888888889e-05,
"loss": 0.0138,
"step": 1178
},
{
"epoch": 3.45,
"learning_rate": 4.137426900584795e-05,
"loss": 0.0476,
"step": 1180
},
{
"epoch": 3.46,
"learning_rate": 4.135964912280702e-05,
"loss": 0.0081,
"step": 1182
},
{
"epoch": 3.46,
"learning_rate": 4.134502923976608e-05,
"loss": 0.382,
"step": 1184
},
{
"epoch": 3.47,
"learning_rate": 4.1330409356725145e-05,
"loss": 0.0564,
"step": 1186
},
{
"epoch": 3.47,
"learning_rate": 4.1315789473684214e-05,
"loss": 0.1754,
"step": 1188
},
{
"epoch": 3.48,
"learning_rate": 4.1301169590643276e-05,
"loss": 0.0468,
"step": 1190
},
{
"epoch": 3.49,
"learning_rate": 4.128654970760234e-05,
"loss": 0.0045,
"step": 1192
},
{
"epoch": 3.49,
"learning_rate": 4.127192982456141e-05,
"loss": 0.0013,
"step": 1194
},
{
"epoch": 3.5,
"learning_rate": 4.1257309941520476e-05,
"loss": 0.0174,
"step": 1196
},
{
"epoch": 3.5,
"learning_rate": 4.124269005847953e-05,
"loss": 0.2056,
"step": 1198
},
{
"epoch": 3.51,
"learning_rate": 4.12280701754386e-05,
"loss": 0.0982,
"step": 1200
},
{
"epoch": 3.51,
"learning_rate": 4.121345029239767e-05,
"loss": 0.7155,
"step": 1202
},
{
"epoch": 3.52,
"learning_rate": 4.1198830409356724e-05,
"loss": 0.3202,
"step": 1204
},
{
"epoch": 3.53,
"learning_rate": 4.118421052631579e-05,
"loss": 0.3673,
"step": 1206
},
{
"epoch": 3.53,
"learning_rate": 4.116959064327486e-05,
"loss": 0.0054,
"step": 1208
},
{
"epoch": 3.54,
"learning_rate": 4.1154970760233916e-05,
"loss": 0.0207,
"step": 1210
},
{
"epoch": 3.54,
"learning_rate": 4.1140350877192985e-05,
"loss": 0.27,
"step": 1212
},
{
"epoch": 3.55,
"learning_rate": 4.1125730994152054e-05,
"loss": 0.0104,
"step": 1214
},
{
"epoch": 3.56,
"learning_rate": 4.111111111111111e-05,
"loss": 0.0372,
"step": 1216
},
{
"epoch": 3.56,
"learning_rate": 4.109649122807018e-05,
"loss": 0.1251,
"step": 1218
},
{
"epoch": 3.57,
"learning_rate": 4.1081871345029247e-05,
"loss": 0.1246,
"step": 1220
},
{
"epoch": 3.57,
"learning_rate": 4.10672514619883e-05,
"loss": 0.0066,
"step": 1222
},
{
"epoch": 3.58,
"learning_rate": 4.105263157894737e-05,
"loss": 0.0139,
"step": 1224
},
{
"epoch": 3.58,
"learning_rate": 4.103801169590644e-05,
"loss": 0.0007,
"step": 1226
},
{
"epoch": 3.59,
"learning_rate": 4.1023391812865495e-05,
"loss": 0.065,
"step": 1228
},
{
"epoch": 3.6,
"learning_rate": 4.100877192982456e-05,
"loss": 0.0954,
"step": 1230
},
{
"epoch": 3.6,
"learning_rate": 4.099415204678363e-05,
"loss": 0.0015,
"step": 1232
},
{
"epoch": 3.61,
"learning_rate": 4.097953216374269e-05,
"loss": 0.5998,
"step": 1234
},
{
"epoch": 3.61,
"learning_rate": 4.0964912280701756e-05,
"loss": 0.2944,
"step": 1236
},
{
"epoch": 3.62,
"learning_rate": 4.0950292397660825e-05,
"loss": 0.1902,
"step": 1238
},
{
"epoch": 3.63,
"learning_rate": 4.093567251461988e-05,
"loss": 0.0832,
"step": 1240
},
{
"epoch": 3.63,
"learning_rate": 4.092105263157895e-05,
"loss": 0.0315,
"step": 1242
},
{
"epoch": 3.64,
"learning_rate": 4.090643274853802e-05,
"loss": 0.3533,
"step": 1244
},
{
"epoch": 3.64,
"learning_rate": 4.089181286549707e-05,
"loss": 0.0035,
"step": 1246
},
{
"epoch": 3.65,
"learning_rate": 4.087719298245614e-05,
"loss": 0.2336,
"step": 1248
},
{
"epoch": 3.65,
"learning_rate": 4.086257309941521e-05,
"loss": 0.0546,
"step": 1250
},
{
"epoch": 3.66,
"learning_rate": 4.0847953216374266e-05,
"loss": 0.2229,
"step": 1252
},
{
"epoch": 3.67,
"learning_rate": 4.0833333333333334e-05,
"loss": 0.3132,
"step": 1254
},
{
"epoch": 3.67,
"learning_rate": 4.08187134502924e-05,
"loss": 0.1729,
"step": 1256
},
{
"epoch": 3.68,
"learning_rate": 4.080409356725146e-05,
"loss": 0.2196,
"step": 1258
},
{
"epoch": 3.68,
"learning_rate": 4.078947368421053e-05,
"loss": 0.0844,
"step": 1260
},
{
"epoch": 3.69,
"learning_rate": 4.0774853801169596e-05,
"loss": 0.0027,
"step": 1262
},
{
"epoch": 3.7,
"learning_rate": 4.076023391812866e-05,
"loss": 0.0613,
"step": 1264
},
{
"epoch": 3.7,
"learning_rate": 4.074561403508772e-05,
"loss": 0.1158,
"step": 1266
},
{
"epoch": 3.71,
"learning_rate": 4.073099415204679e-05,
"loss": 0.0023,
"step": 1268
},
{
"epoch": 3.71,
"learning_rate": 4.071637426900585e-05,
"loss": 0.0759,
"step": 1270
},
{
"epoch": 3.72,
"learning_rate": 4.070175438596491e-05,
"loss": 0.0154,
"step": 1272
},
{
"epoch": 3.73,
"learning_rate": 4.068713450292398e-05,
"loss": 0.2122,
"step": 1274
},
{
"epoch": 3.73,
"learning_rate": 4.067251461988304e-05,
"loss": 0.034,
"step": 1276
},
{
"epoch": 3.74,
"learning_rate": 4.0657894736842105e-05,
"loss": 0.1608,
"step": 1278
},
{
"epoch": 3.74,
"learning_rate": 4.0643274853801174e-05,
"loss": 0.0675,
"step": 1280
},
{
"epoch": 3.75,
"learning_rate": 4.0628654970760236e-05,
"loss": 0.0723,
"step": 1282
},
{
"epoch": 3.75,
"learning_rate": 4.06140350877193e-05,
"loss": 0.4441,
"step": 1284
},
{
"epoch": 3.76,
"learning_rate": 4.059941520467837e-05,
"loss": 0.0077,
"step": 1286
},
{
"epoch": 3.77,
"learning_rate": 4.058479532163743e-05,
"loss": 0.0045,
"step": 1288
},
{
"epoch": 3.77,
"learning_rate": 4.057017543859649e-05,
"loss": 0.0263,
"step": 1290
},
{
"epoch": 3.78,
"learning_rate": 4.055555555555556e-05,
"loss": 0.1303,
"step": 1292
},
{
"epoch": 3.78,
"learning_rate": 4.054093567251462e-05,
"loss": 0.3736,
"step": 1294
},
{
"epoch": 3.79,
"learning_rate": 4.0526315789473684e-05,
"loss": 0.2265,
"step": 1296
},
{
"epoch": 3.8,
"learning_rate": 4.051169590643275e-05,
"loss": 0.0099,
"step": 1298
},
{
"epoch": 3.8,
"learning_rate": 4.0497076023391814e-05,
"loss": 0.0574,
"step": 1300
},
{
"epoch": 3.81,
"learning_rate": 4.0482456140350876e-05,
"loss": 0.0055,
"step": 1302
},
{
"epoch": 3.81,
"learning_rate": 4.0467836257309945e-05,
"loss": 0.2848,
"step": 1304
},
{
"epoch": 3.82,
"learning_rate": 4.045321637426901e-05,
"loss": 0.1304,
"step": 1306
},
{
"epoch": 3.82,
"learning_rate": 4.043859649122807e-05,
"loss": 0.034,
"step": 1308
},
{
"epoch": 3.83,
"learning_rate": 4.042397660818714e-05,
"loss": 0.0041,
"step": 1310
},
{
"epoch": 3.84,
"learning_rate": 4.04093567251462e-05,
"loss": 0.0135,
"step": 1312
},
{
"epoch": 3.84,
"learning_rate": 4.039473684210526e-05,
"loss": 0.4561,
"step": 1314
},
{
"epoch": 3.85,
"learning_rate": 4.038011695906433e-05,
"loss": 0.6276,
"step": 1316
},
{
"epoch": 3.85,
"learning_rate": 4.036549707602339e-05,
"loss": 0.1391,
"step": 1318
},
{
"epoch": 3.86,
"learning_rate": 4.0350877192982455e-05,
"loss": 0.0254,
"step": 1320
},
{
"epoch": 3.87,
"learning_rate": 4.033625730994152e-05,
"loss": 0.0654,
"step": 1322
},
{
"epoch": 3.87,
"learning_rate": 4.0321637426900585e-05,
"loss": 0.0385,
"step": 1324
},
{
"epoch": 3.88,
"learning_rate": 4.030701754385965e-05,
"loss": 0.0323,
"step": 1326
},
{
"epoch": 3.88,
"learning_rate": 4.0292397660818716e-05,
"loss": 0.0302,
"step": 1328
},
{
"epoch": 3.89,
"learning_rate": 4.027777777777778e-05,
"loss": 0.0047,
"step": 1330
},
{
"epoch": 3.89,
"learning_rate": 4.026315789473684e-05,
"loss": 0.3089,
"step": 1332
},
{
"epoch": 3.9,
"learning_rate": 4.024853801169591e-05,
"loss": 0.0233,
"step": 1334
},
{
"epoch": 3.91,
"learning_rate": 4.023391812865497e-05,
"loss": 0.2607,
"step": 1336
},
{
"epoch": 3.91,
"learning_rate": 4.021929824561403e-05,
"loss": 0.4284,
"step": 1338
},
{
"epoch": 3.92,
"learning_rate": 4.02046783625731e-05,
"loss": 0.1709,
"step": 1340
},
{
"epoch": 3.92,
"learning_rate": 4.0190058479532164e-05,
"loss": 0.0056,
"step": 1342
},
{
"epoch": 3.93,
"learning_rate": 4.017543859649123e-05,
"loss": 0.2293,
"step": 1344
},
{
"epoch": 3.94,
"learning_rate": 4.0160818713450294e-05,
"loss": 0.1244,
"step": 1346
},
{
"epoch": 3.94,
"learning_rate": 4.0146198830409356e-05,
"loss": 0.2427,
"step": 1348
},
{
"epoch": 3.95,
"learning_rate": 4.0131578947368425e-05,
"loss": 0.1636,
"step": 1350
},
{
"epoch": 3.95,
"learning_rate": 4.011695906432749e-05,
"loss": 0.226,
"step": 1352
},
{
"epoch": 3.96,
"learning_rate": 4.010233918128655e-05,
"loss": 0.1133,
"step": 1354
},
{
"epoch": 3.96,
"learning_rate": 4.008771929824562e-05,
"loss": 0.3705,
"step": 1356
},
{
"epoch": 3.97,
"learning_rate": 4.007309941520468e-05,
"loss": 0.1536,
"step": 1358
},
{
"epoch": 3.98,
"learning_rate": 4.005847953216375e-05,
"loss": 0.0321,
"step": 1360
},
{
"epoch": 3.98,
"learning_rate": 4.004385964912281e-05,
"loss": 0.1925,
"step": 1362
},
{
"epoch": 3.99,
"learning_rate": 4.002923976608187e-05,
"loss": 0.4587,
"step": 1364
},
{
"epoch": 3.99,
"learning_rate": 4.001461988304094e-05,
"loss": 0.1871,
"step": 1366
},
{
"epoch": 4.0,
"learning_rate": 4e-05,
"loss": 0.0115,
"step": 1368
},
{
"epoch": 4.0,
"eval_bleu": 0.5357975894031317,
"eval_loss": 0.9746851921081543,
"eval_runtime": 36.0745,
"eval_samples_per_second": 9.286,
"eval_steps_per_second": 2.329,
"step": 1368
},
{
"epoch": 4.01,
"learning_rate": 3.9985380116959065e-05,
"loss": 0.3043,
"step": 1370
},
{
"epoch": 4.01,
"learning_rate": 3.9970760233918134e-05,
"loss": 0.1021,
"step": 1372
},
{
"epoch": 4.02,
"learning_rate": 3.9956140350877196e-05,
"loss": 0.0048,
"step": 1374
},
{
"epoch": 4.02,
"learning_rate": 3.994152046783626e-05,
"loss": 0.1889,
"step": 1376
},
{
"epoch": 4.03,
"learning_rate": 3.992690058479533e-05,
"loss": 0.0028,
"step": 1378
},
{
"epoch": 4.04,
"learning_rate": 3.991228070175439e-05,
"loss": 0.2885,
"step": 1380
},
{
"epoch": 4.04,
"learning_rate": 3.989766081871345e-05,
"loss": 0.1783,
"step": 1382
},
{
"epoch": 4.05,
"learning_rate": 3.988304093567252e-05,
"loss": 0.0083,
"step": 1384
},
{
"epoch": 4.05,
"learning_rate": 3.986842105263158e-05,
"loss": 0.0137,
"step": 1386
},
{
"epoch": 4.06,
"learning_rate": 3.9853801169590644e-05,
"loss": 0.02,
"step": 1388
},
{
"epoch": 4.06,
"learning_rate": 3.983918128654971e-05,
"loss": 0.1026,
"step": 1390
},
{
"epoch": 4.07,
"learning_rate": 3.9824561403508774e-05,
"loss": 0.0012,
"step": 1392
},
{
"epoch": 4.08,
"learning_rate": 3.9809941520467836e-05,
"loss": 0.0266,
"step": 1394
},
{
"epoch": 4.08,
"learning_rate": 3.9795321637426905e-05,
"loss": 0.1508,
"step": 1396
},
{
"epoch": 4.09,
"learning_rate": 3.978070175438597e-05,
"loss": 0.0022,
"step": 1398
},
{
"epoch": 4.09,
"learning_rate": 3.976608187134503e-05,
"loss": 0.1858,
"step": 1400
},
{
"epoch": 4.1,
"learning_rate": 3.97514619883041e-05,
"loss": 0.002,
"step": 1402
},
{
"epoch": 4.11,
"learning_rate": 3.973684210526316e-05,
"loss": 0.1603,
"step": 1404
},
{
"epoch": 4.11,
"learning_rate": 3.972222222222222e-05,
"loss": 0.2909,
"step": 1406
},
{
"epoch": 4.12,
"learning_rate": 3.970760233918129e-05,
"loss": 0.0241,
"step": 1408
},
{
"epoch": 4.12,
"learning_rate": 3.969298245614035e-05,
"loss": 0.0015,
"step": 1410
},
{
"epoch": 4.13,
"learning_rate": 3.9678362573099415e-05,
"loss": 0.0075,
"step": 1412
},
{
"epoch": 4.13,
"learning_rate": 3.966374269005848e-05,
"loss": 0.0001,
"step": 1414
},
{
"epoch": 4.14,
"learning_rate": 3.9649122807017545e-05,
"loss": 0.057,
"step": 1416
},
{
"epoch": 4.15,
"learning_rate": 3.963450292397661e-05,
"loss": 0.158,
"step": 1418
},
{
"epoch": 4.15,
"learning_rate": 3.9619883040935676e-05,
"loss": 0.0023,
"step": 1420
},
{
"epoch": 4.16,
"learning_rate": 3.960526315789474e-05,
"loss": 0.2292,
"step": 1422
},
{
"epoch": 4.16,
"learning_rate": 3.95906432748538e-05,
"loss": 0.0538,
"step": 1424
},
{
"epoch": 4.17,
"learning_rate": 3.957602339181287e-05,
"loss": 0.001,
"step": 1426
},
{
"epoch": 4.18,
"learning_rate": 3.956140350877193e-05,
"loss": 0.0253,
"step": 1428
},
{
"epoch": 4.18,
"learning_rate": 3.9546783625731e-05,
"loss": 0.1037,
"step": 1430
},
{
"epoch": 4.19,
"learning_rate": 3.953216374269006e-05,
"loss": 0.0015,
"step": 1432
},
{
"epoch": 4.19,
"learning_rate": 3.9517543859649124e-05,
"loss": 0.1533,
"step": 1434
},
{
"epoch": 4.2,
"learning_rate": 3.950292397660819e-05,
"loss": 0.0005,
"step": 1436
},
{
"epoch": 4.2,
"learning_rate": 3.9488304093567254e-05,
"loss": 0.0525,
"step": 1438
},
{
"epoch": 4.21,
"learning_rate": 3.9473684210526316e-05,
"loss": 0.0006,
"step": 1440
},
{
"epoch": 4.22,
"learning_rate": 3.9459064327485385e-05,
"loss": 0.4061,
"step": 1442
},
{
"epoch": 4.22,
"learning_rate": 3.944444444444445e-05,
"loss": 0.0006,
"step": 1444
},
{
"epoch": 4.23,
"learning_rate": 3.942982456140351e-05,
"loss": 0.2372,
"step": 1446
},
{
"epoch": 4.23,
"learning_rate": 3.941520467836258e-05,
"loss": 0.0036,
"step": 1448
},
{
"epoch": 4.24,
"learning_rate": 3.940058479532164e-05,
"loss": 0.0066,
"step": 1450
},
{
"epoch": 4.25,
"learning_rate": 3.93859649122807e-05,
"loss": 0.0396,
"step": 1452
},
{
"epoch": 4.25,
"learning_rate": 3.937134502923977e-05,
"loss": 0.0454,
"step": 1454
},
{
"epoch": 4.26,
"learning_rate": 3.935672514619883e-05,
"loss": 0.1252,
"step": 1456
},
{
"epoch": 4.26,
"learning_rate": 3.9342105263157895e-05,
"loss": 0.0022,
"step": 1458
},
{
"epoch": 4.27,
"learning_rate": 3.932748538011696e-05,
"loss": 0.0754,
"step": 1460
},
{
"epoch": 4.27,
"learning_rate": 3.9312865497076025e-05,
"loss": 0.0349,
"step": 1462
},
{
"epoch": 4.28,
"learning_rate": 3.929824561403509e-05,
"loss": 0.0247,
"step": 1464
},
{
"epoch": 4.29,
"learning_rate": 3.9283625730994156e-05,
"loss": 0.2908,
"step": 1466
},
{
"epoch": 4.29,
"learning_rate": 3.926900584795322e-05,
"loss": 0.0007,
"step": 1468
},
{
"epoch": 4.3,
"learning_rate": 3.925438596491228e-05,
"loss": 0.0352,
"step": 1470
},
{
"epoch": 4.3,
"learning_rate": 3.923976608187135e-05,
"loss": 0.0173,
"step": 1472
},
{
"epoch": 4.31,
"learning_rate": 3.922514619883041e-05,
"loss": 0.0866,
"step": 1474
},
{
"epoch": 4.32,
"learning_rate": 3.921052631578947e-05,
"loss": 0.5181,
"step": 1476
},
{
"epoch": 4.32,
"learning_rate": 3.919590643274854e-05,
"loss": 0.003,
"step": 1478
},
{
"epoch": 4.33,
"learning_rate": 3.9181286549707604e-05,
"loss": 0.2397,
"step": 1480
},
{
"epoch": 4.33,
"learning_rate": 3.9166666666666665e-05,
"loss": 0.088,
"step": 1482
},
{
"epoch": 4.34,
"learning_rate": 3.9152046783625734e-05,
"loss": 0.001,
"step": 1484
},
{
"epoch": 4.35,
"learning_rate": 3.9137426900584796e-05,
"loss": 0.0006,
"step": 1486
},
{
"epoch": 4.35,
"learning_rate": 3.912280701754386e-05,
"loss": 0.0093,
"step": 1488
},
{
"epoch": 4.36,
"learning_rate": 3.910818713450293e-05,
"loss": 0.0104,
"step": 1490
},
{
"epoch": 4.36,
"learning_rate": 3.909356725146199e-05,
"loss": 0.1765,
"step": 1492
},
{
"epoch": 4.37,
"learning_rate": 3.907894736842105e-05,
"loss": 0.0816,
"step": 1494
},
{
"epoch": 4.37,
"learning_rate": 3.906432748538012e-05,
"loss": 0.219,
"step": 1496
},
{
"epoch": 4.38,
"learning_rate": 3.904970760233918e-05,
"loss": 0.0353,
"step": 1498
},
{
"epoch": 4.39,
"learning_rate": 3.9035087719298244e-05,
"loss": 0.0026,
"step": 1500
},
{
"epoch": 4.39,
"learning_rate": 3.902046783625731e-05,
"loss": 0.0881,
"step": 1502
},
{
"epoch": 4.4,
"learning_rate": 3.9005847953216374e-05,
"loss": 0.2328,
"step": 1504
},
{
"epoch": 4.4,
"learning_rate": 3.8991228070175436e-05,
"loss": 0.3861,
"step": 1506
},
{
"epoch": 4.41,
"learning_rate": 3.8976608187134505e-05,
"loss": 0.2472,
"step": 1508
},
{
"epoch": 4.42,
"learning_rate": 3.8961988304093574e-05,
"loss": 0.0002,
"step": 1510
},
{
"epoch": 4.42,
"learning_rate": 3.894736842105263e-05,
"loss": 0.0008,
"step": 1512
},
{
"epoch": 4.43,
"learning_rate": 3.89327485380117e-05,
"loss": 0.1563,
"step": 1514
},
{
"epoch": 4.43,
"learning_rate": 3.891812865497077e-05,
"loss": 0.0013,
"step": 1516
},
{
"epoch": 4.44,
"learning_rate": 3.890350877192982e-05,
"loss": 0.0003,
"step": 1518
},
{
"epoch": 4.44,
"learning_rate": 3.888888888888889e-05,
"loss": 0.0021,
"step": 1520
},
{
"epoch": 4.45,
"learning_rate": 3.887426900584796e-05,
"loss": 0.0203,
"step": 1522
},
{
"epoch": 4.46,
"learning_rate": 3.8859649122807015e-05,
"loss": 0.2019,
"step": 1524
},
{
"epoch": 4.46,
"learning_rate": 3.8845029239766084e-05,
"loss": 0.0083,
"step": 1526
},
{
"epoch": 4.47,
"learning_rate": 3.883040935672515e-05,
"loss": 0.1509,
"step": 1528
},
{
"epoch": 4.47,
"learning_rate": 3.8815789473684214e-05,
"loss": 0.2225,
"step": 1530
},
{
"epoch": 4.48,
"learning_rate": 3.8801169590643276e-05,
"loss": 0.0078,
"step": 1532
},
{
"epoch": 4.49,
"learning_rate": 3.8786549707602345e-05,
"loss": 0.0527,
"step": 1534
},
{
"epoch": 4.49,
"learning_rate": 3.877192982456141e-05,
"loss": 0.0674,
"step": 1536
},
{
"epoch": 4.5,
"learning_rate": 3.875730994152047e-05,
"loss": 0.0011,
"step": 1538
},
{
"epoch": 4.5,
"learning_rate": 3.874269005847954e-05,
"loss": 0.0035,
"step": 1540
},
{
"epoch": 4.51,
"learning_rate": 3.87280701754386e-05,
"loss": 0.0036,
"step": 1542
},
{
"epoch": 4.51,
"learning_rate": 3.871345029239766e-05,
"loss": 0.0016,
"step": 1544
},
{
"epoch": 4.52,
"learning_rate": 3.869883040935673e-05,
"loss": 0.3341,
"step": 1546
},
{
"epoch": 4.53,
"learning_rate": 3.868421052631579e-05,
"loss": 0.801,
"step": 1548
},
{
"epoch": 4.53,
"learning_rate": 3.8669590643274854e-05,
"loss": 0.0077,
"step": 1550
},
{
"epoch": 4.54,
"learning_rate": 3.865497076023392e-05,
"loss": 0.1788,
"step": 1552
},
{
"epoch": 4.54,
"learning_rate": 3.8640350877192985e-05,
"loss": 0.0046,
"step": 1554
},
{
"epoch": 4.55,
"learning_rate": 3.862573099415205e-05,
"loss": 0.001,
"step": 1556
},
{
"epoch": 4.56,
"learning_rate": 3.8611111111111116e-05,
"loss": 0.0085,
"step": 1558
},
{
"epoch": 4.56,
"learning_rate": 3.859649122807018e-05,
"loss": 0.0528,
"step": 1560
},
{
"epoch": 4.57,
"learning_rate": 3.858187134502924e-05,
"loss": 0.1608,
"step": 1562
},
{
"epoch": 4.57,
"learning_rate": 3.856725146198831e-05,
"loss": 0.0062,
"step": 1564
},
{
"epoch": 4.58,
"learning_rate": 3.855263157894737e-05,
"loss": 0.0005,
"step": 1566
},
{
"epoch": 4.58,
"learning_rate": 3.853801169590643e-05,
"loss": 0.0332,
"step": 1568
},
{
"epoch": 4.59,
"learning_rate": 3.85233918128655e-05,
"loss": 0.0327,
"step": 1570
},
{
"epoch": 4.6,
"learning_rate": 3.8508771929824563e-05,
"loss": 0.033,
"step": 1572
},
{
"epoch": 4.6,
"learning_rate": 3.8494152046783625e-05,
"loss": 0.0041,
"step": 1574
},
{
"epoch": 4.61,
"learning_rate": 3.8479532163742694e-05,
"loss": 0.0058,
"step": 1576
},
{
"epoch": 4.61,
"learning_rate": 3.8464912280701756e-05,
"loss": 0.2849,
"step": 1578
},
{
"epoch": 4.62,
"learning_rate": 3.845029239766082e-05,
"loss": 0.0139,
"step": 1580
},
{
"epoch": 4.63,
"learning_rate": 3.843567251461989e-05,
"loss": 0.1407,
"step": 1582
},
{
"epoch": 4.63,
"learning_rate": 3.842105263157895e-05,
"loss": 0.0022,
"step": 1584
},
{
"epoch": 4.64,
"learning_rate": 3.840643274853801e-05,
"loss": 0.0715,
"step": 1586
},
{
"epoch": 4.64,
"learning_rate": 3.839181286549708e-05,
"loss": 0.1225,
"step": 1588
},
{
"epoch": 4.65,
"learning_rate": 3.837719298245614e-05,
"loss": 0.0824,
"step": 1590
},
{
"epoch": 4.65,
"learning_rate": 3.8362573099415204e-05,
"loss": 0.0033,
"step": 1592
},
{
"epoch": 4.66,
"learning_rate": 3.834795321637427e-05,
"loss": 0.0012,
"step": 1594
},
{
"epoch": 4.67,
"learning_rate": 3.8333333333333334e-05,
"loss": 0.0183,
"step": 1596
},
{
"epoch": 4.67,
"learning_rate": 3.8318713450292396e-05,
"loss": 0.024,
"step": 1598
},
{
"epoch": 4.68,
"learning_rate": 3.8304093567251465e-05,
"loss": 0.0707,
"step": 1600
},
{
"epoch": 4.68,
"learning_rate": 3.828947368421053e-05,
"loss": 0.0008,
"step": 1602
},
{
"epoch": 4.69,
"learning_rate": 3.827485380116959e-05,
"loss": 0.0006,
"step": 1604
},
{
"epoch": 4.7,
"learning_rate": 3.826023391812866e-05,
"loss": 0.0016,
"step": 1606
},
{
"epoch": 4.7,
"learning_rate": 3.824561403508773e-05,
"loss": 0.1917,
"step": 1608
},
{
"epoch": 4.71,
"learning_rate": 3.823099415204678e-05,
"loss": 0.0056,
"step": 1610
},
{
"epoch": 4.71,
"learning_rate": 3.821637426900585e-05,
"loss": 0.0009,
"step": 1612
},
{
"epoch": 4.72,
"learning_rate": 3.820175438596492e-05,
"loss": 0.2069,
"step": 1614
},
{
"epoch": 4.73,
"learning_rate": 3.8187134502923975e-05,
"loss": 0.0506,
"step": 1616
},
{
"epoch": 4.73,
"learning_rate": 3.8172514619883043e-05,
"loss": 0.0038,
"step": 1618
},
{
"epoch": 4.74,
"learning_rate": 3.815789473684211e-05,
"loss": 0.3956,
"step": 1620
},
{
"epoch": 4.74,
"learning_rate": 3.814327485380117e-05,
"loss": 0.3181,
"step": 1622
},
{
"epoch": 4.75,
"learning_rate": 3.8128654970760236e-05,
"loss": 0.0006,
"step": 1624
},
{
"epoch": 4.75,
"learning_rate": 3.8114035087719305e-05,
"loss": 0.0003,
"step": 1626
},
{
"epoch": 4.76,
"learning_rate": 3.809941520467836e-05,
"loss": 0.0008,
"step": 1628
},
{
"epoch": 4.77,
"learning_rate": 3.808479532163743e-05,
"loss": 0.0008,
"step": 1630
},
{
"epoch": 4.77,
"learning_rate": 3.80701754385965e-05,
"loss": 0.187,
"step": 1632
},
{
"epoch": 4.78,
"learning_rate": 3.805555555555555e-05,
"loss": 0.0006,
"step": 1634
},
{
"epoch": 4.78,
"learning_rate": 3.804093567251462e-05,
"loss": 0.0424,
"step": 1636
},
{
"epoch": 4.79,
"learning_rate": 3.802631578947369e-05,
"loss": 0.0395,
"step": 1638
},
{
"epoch": 4.8,
"learning_rate": 3.8011695906432746e-05,
"loss": 0.3714,
"step": 1640
},
{
"epoch": 4.8,
"learning_rate": 3.7997076023391814e-05,
"loss": 0.0055,
"step": 1642
},
{
"epoch": 4.81,
"learning_rate": 3.798245614035088e-05,
"loss": 0.0256,
"step": 1644
},
{
"epoch": 4.81,
"learning_rate": 3.796783625730994e-05,
"loss": 0.3395,
"step": 1646
},
{
"epoch": 4.82,
"learning_rate": 3.795321637426901e-05,
"loss": 0.054,
"step": 1648
},
{
"epoch": 4.82,
"learning_rate": 3.7938596491228076e-05,
"loss": 0.7263,
"step": 1650
},
{
"epoch": 4.83,
"learning_rate": 3.792397660818713e-05,
"loss": 0.0741,
"step": 1652
},
{
"epoch": 4.84,
"learning_rate": 3.79093567251462e-05,
"loss": 0.0009,
"step": 1654
},
{
"epoch": 4.84,
"learning_rate": 3.789473684210527e-05,
"loss": 0.0186,
"step": 1656
},
{
"epoch": 4.85,
"learning_rate": 3.7880116959064324e-05,
"loss": 0.0013,
"step": 1658
},
{
"epoch": 4.85,
"learning_rate": 3.786549707602339e-05,
"loss": 0.5244,
"step": 1660
},
{
"epoch": 4.86,
"learning_rate": 3.785087719298246e-05,
"loss": 0.0095,
"step": 1662
},
{
"epoch": 4.87,
"learning_rate": 3.783625730994152e-05,
"loss": 0.0046,
"step": 1664
},
{
"epoch": 4.87,
"learning_rate": 3.7821637426900585e-05,
"loss": 0.0002,
"step": 1666
},
{
"epoch": 4.88,
"learning_rate": 3.7807017543859654e-05,
"loss": 0.0426,
"step": 1668
},
{
"epoch": 4.88,
"learning_rate": 3.7792397660818716e-05,
"loss": 0.001,
"step": 1670
},
{
"epoch": 4.89,
"learning_rate": 3.777777777777778e-05,
"loss": 0.0447,
"step": 1672
},
{
"epoch": 4.89,
"learning_rate": 3.776315789473685e-05,
"loss": 0.1628,
"step": 1674
},
{
"epoch": 4.9,
"learning_rate": 3.774853801169591e-05,
"loss": 0.2864,
"step": 1676
},
{
"epoch": 4.91,
"learning_rate": 3.773391812865497e-05,
"loss": 0.0152,
"step": 1678
},
{
"epoch": 4.91,
"learning_rate": 3.771929824561404e-05,
"loss": 0.183,
"step": 1680
},
{
"epoch": 4.92,
"learning_rate": 3.77046783625731e-05,
"loss": 0.3452,
"step": 1682
},
{
"epoch": 4.92,
"learning_rate": 3.7690058479532164e-05,
"loss": 0.0084,
"step": 1684
},
{
"epoch": 4.93,
"learning_rate": 3.767543859649123e-05,
"loss": 0.0029,
"step": 1686
},
{
"epoch": 4.94,
"learning_rate": 3.7660818713450294e-05,
"loss": 0.0274,
"step": 1688
},
{
"epoch": 4.94,
"learning_rate": 3.7646198830409356e-05,
"loss": 0.0002,
"step": 1690
},
{
"epoch": 4.95,
"learning_rate": 3.7631578947368425e-05,
"loss": 0.1806,
"step": 1692
},
{
"epoch": 4.95,
"learning_rate": 3.761695906432749e-05,
"loss": 0.0005,
"step": 1694
},
{
"epoch": 4.96,
"learning_rate": 3.760233918128655e-05,
"loss": 0.1386,
"step": 1696
},
{
"epoch": 4.96,
"learning_rate": 3.758771929824562e-05,
"loss": 0.0003,
"step": 1698
},
{
"epoch": 4.97,
"learning_rate": 3.757309941520468e-05,
"loss": 0.1172,
"step": 1700
},
{
"epoch": 4.98,
"learning_rate": 3.755847953216374e-05,
"loss": 0.1988,
"step": 1702
},
{
"epoch": 4.98,
"learning_rate": 3.754385964912281e-05,
"loss": 0.0178,
"step": 1704
},
{
"epoch": 4.99,
"learning_rate": 3.752923976608187e-05,
"loss": 0.2569,
"step": 1706
},
{
"epoch": 4.99,
"learning_rate": 3.7514619883040935e-05,
"loss": 0.0342,
"step": 1708
},
{
"epoch": 5.0,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0058,
"step": 1710
},
{
"epoch": 5.0,
"eval_bleu": 0.5011604458041059,
"eval_loss": 1.0964770317077637,
"eval_runtime": 36.6348,
"eval_samples_per_second": 9.144,
"eval_steps_per_second": 2.293,
"step": 1710
},
{
"epoch": 5.01,
"learning_rate": 3.7485380116959065e-05,
"loss": 0.0001,
"step": 1712
},
{
"epoch": 5.01,
"learning_rate": 3.747076023391813e-05,
"loss": 0.0353,
"step": 1714
},
{
"epoch": 5.02,
"learning_rate": 3.7456140350877196e-05,
"loss": 0.3111,
"step": 1716
},
{
"epoch": 5.02,
"learning_rate": 3.744152046783626e-05,
"loss": 0.0788,
"step": 1718
},
{
"epoch": 5.03,
"learning_rate": 3.742690058479532e-05,
"loss": 0.0769,
"step": 1720
},
{
"epoch": 5.04,
"learning_rate": 3.741228070175439e-05,
"loss": 0.0011,
"step": 1722
},
{
"epoch": 5.04,
"learning_rate": 3.739766081871345e-05,
"loss": 0.3037,
"step": 1724
},
{
"epoch": 5.05,
"learning_rate": 3.738304093567251e-05,
"loss": 0.3267,
"step": 1726
},
{
"epoch": 5.05,
"learning_rate": 3.736842105263158e-05,
"loss": 0.0006,
"step": 1728
},
{
"epoch": 5.06,
"learning_rate": 3.7353801169590644e-05,
"loss": 0.006,
"step": 1730
},
{
"epoch": 5.06,
"learning_rate": 3.7339181286549706e-05,
"loss": 0.0344,
"step": 1732
},
{
"epoch": 5.07,
"learning_rate": 3.7324561403508774e-05,
"loss": 0.002,
"step": 1734
},
{
"epoch": 5.08,
"learning_rate": 3.7309941520467836e-05,
"loss": 0.0029,
"step": 1736
},
{
"epoch": 5.08,
"learning_rate": 3.72953216374269e-05,
"loss": 0.0765,
"step": 1738
},
{
"epoch": 5.09,
"learning_rate": 3.728070175438597e-05,
"loss": 0.086,
"step": 1740
},
{
"epoch": 5.09,
"learning_rate": 3.726608187134503e-05,
"loss": 0.0009,
"step": 1742
},
{
"epoch": 5.1,
"learning_rate": 3.725146198830409e-05,
"loss": 0.0011,
"step": 1744
},
{
"epoch": 5.11,
"learning_rate": 3.723684210526316e-05,
"loss": 0.0127,
"step": 1746
},
{
"epoch": 5.11,
"learning_rate": 3.722222222222222e-05,
"loss": 0.0061,
"step": 1748
},
{
"epoch": 5.12,
"learning_rate": 3.7207602339181284e-05,
"loss": 0.0004,
"step": 1750
},
{
"epoch": 5.12,
"learning_rate": 3.719298245614035e-05,
"loss": 0.0066,
"step": 1752
},
{
"epoch": 5.13,
"learning_rate": 3.7178362573099415e-05,
"loss": 0.164,
"step": 1754
},
{
"epoch": 5.13,
"learning_rate": 3.7163742690058483e-05,
"loss": 0.1327,
"step": 1756
},
{
"epoch": 5.14,
"learning_rate": 3.7149122807017545e-05,
"loss": 0.0939,
"step": 1758
},
{
"epoch": 5.15,
"learning_rate": 3.713450292397661e-05,
"loss": 0.0025,
"step": 1760
},
{
"epoch": 5.15,
"learning_rate": 3.7119883040935676e-05,
"loss": 0.0005,
"step": 1762
},
{
"epoch": 5.16,
"learning_rate": 3.710526315789474e-05,
"loss": 0.0093,
"step": 1764
},
{
"epoch": 5.16,
"learning_rate": 3.70906432748538e-05,
"loss": 0.0102,
"step": 1766
},
{
"epoch": 5.17,
"learning_rate": 3.707602339181287e-05,
"loss": 0.1213,
"step": 1768
},
{
"epoch": 5.18,
"learning_rate": 3.706140350877193e-05,
"loss": 0.0066,
"step": 1770
},
{
"epoch": 5.18,
"learning_rate": 3.7046783625731e-05,
"loss": 0.1739,
"step": 1772
},
{
"epoch": 5.19,
"learning_rate": 3.703216374269006e-05,
"loss": 0.0012,
"step": 1774
},
{
"epoch": 5.19,
"learning_rate": 3.7017543859649124e-05,
"loss": 0.077,
"step": 1776
},
{
"epoch": 5.2,
"learning_rate": 3.700292397660819e-05,
"loss": 0.0498,
"step": 1778
},
{
"epoch": 5.2,
"learning_rate": 3.6988304093567254e-05,
"loss": 0.001,
"step": 1780
},
{
"epoch": 5.21,
"learning_rate": 3.6973684210526316e-05,
"loss": 0.0007,
"step": 1782
},
{
"epoch": 5.22,
"learning_rate": 3.6959064327485385e-05,
"loss": 0.0184,
"step": 1784
},
{
"epoch": 5.22,
"learning_rate": 3.694444444444445e-05,
"loss": 0.2038,
"step": 1786
},
{
"epoch": 5.23,
"learning_rate": 3.692982456140351e-05,
"loss": 0.001,
"step": 1788
},
{
"epoch": 5.23,
"learning_rate": 3.691520467836258e-05,
"loss": 0.0433,
"step": 1790
},
{
"epoch": 5.24,
"learning_rate": 3.690058479532164e-05,
"loss": 0.0173,
"step": 1792
},
{
"epoch": 5.25,
"learning_rate": 3.68859649122807e-05,
"loss": 0.0001,
"step": 1794
},
{
"epoch": 5.25,
"learning_rate": 3.687134502923977e-05,
"loss": 0.1124,
"step": 1796
},
{
"epoch": 5.26,
"learning_rate": 3.685672514619883e-05,
"loss": 0.0029,
"step": 1798
},
{
"epoch": 5.26,
"learning_rate": 3.6842105263157895e-05,
"loss": 0.1925,
"step": 1800
},
{
"epoch": 5.27,
"learning_rate": 3.6827485380116963e-05,
"loss": 0.0401,
"step": 1802
},
{
"epoch": 5.27,
"learning_rate": 3.6812865497076025e-05,
"loss": 0.0003,
"step": 1804
},
{
"epoch": 5.28,
"learning_rate": 3.679824561403509e-05,
"loss": 0.1754,
"step": 1806
},
{
"epoch": 5.29,
"learning_rate": 3.6783625730994156e-05,
"loss": 0.0459,
"step": 1808
},
{
"epoch": 5.29,
"learning_rate": 3.676900584795322e-05,
"loss": 0.1996,
"step": 1810
},
{
"epoch": 5.3,
"learning_rate": 3.675438596491228e-05,
"loss": 0.0003,
"step": 1812
},
{
"epoch": 5.3,
"learning_rate": 3.673976608187135e-05,
"loss": 0.0338,
"step": 1814
},
{
"epoch": 5.31,
"learning_rate": 3.672514619883041e-05,
"loss": 0.0008,
"step": 1816
},
{
"epoch": 5.32,
"learning_rate": 3.671052631578947e-05,
"loss": 0.0037,
"step": 1818
},
{
"epoch": 5.32,
"learning_rate": 3.669590643274854e-05,
"loss": 0.0026,
"step": 1820
},
{
"epoch": 5.33,
"learning_rate": 3.6681286549707604e-05,
"loss": 0.0019,
"step": 1822
},
{
"epoch": 5.33,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.0023,
"step": 1824
},
{
"epoch": 5.34,
"learning_rate": 3.6652046783625734e-05,
"loss": 0.1753,
"step": 1826
},
{
"epoch": 5.35,
"learning_rate": 3.6637426900584796e-05,
"loss": 0.0001,
"step": 1828
},
{
"epoch": 5.35,
"learning_rate": 3.662280701754386e-05,
"loss": 0.0154,
"step": 1830
},
{
"epoch": 5.36,
"learning_rate": 3.660818713450293e-05,
"loss": 0.0338,
"step": 1832
},
{
"epoch": 5.36,
"learning_rate": 3.659356725146199e-05,
"loss": 0.0002,
"step": 1834
},
{
"epoch": 5.37,
"learning_rate": 3.657894736842106e-05,
"loss": 0.0006,
"step": 1836
},
{
"epoch": 5.37,
"learning_rate": 3.656432748538012e-05,
"loss": 0.0001,
"step": 1838
},
{
"epoch": 5.38,
"learning_rate": 3.654970760233918e-05,
"loss": 0.0074,
"step": 1840
},
{
"epoch": 5.39,
"learning_rate": 3.653508771929825e-05,
"loss": 0.0855,
"step": 1842
},
{
"epoch": 5.39,
"learning_rate": 3.652046783625731e-05,
"loss": 0.0042,
"step": 1844
},
{
"epoch": 5.4,
"learning_rate": 3.6505847953216375e-05,
"loss": 0.0016,
"step": 1846
},
{
"epoch": 5.4,
"learning_rate": 3.6491228070175443e-05,
"loss": 0.0005,
"step": 1848
},
{
"epoch": 5.41,
"learning_rate": 3.6476608187134505e-05,
"loss": 0.0575,
"step": 1850
},
{
"epoch": 5.42,
"learning_rate": 3.646198830409357e-05,
"loss": 0.0002,
"step": 1852
},
{
"epoch": 5.42,
"learning_rate": 3.6447368421052636e-05,
"loss": 0.083,
"step": 1854
},
{
"epoch": 5.43,
"learning_rate": 3.64327485380117e-05,
"loss": 0.0979,
"step": 1856
},
{
"epoch": 5.43,
"learning_rate": 3.641812865497076e-05,
"loss": 0.0486,
"step": 1858
},
{
"epoch": 5.44,
"learning_rate": 3.640350877192983e-05,
"loss": 0.0382,
"step": 1860
},
{
"epoch": 5.44,
"learning_rate": 3.638888888888889e-05,
"loss": 0.0558,
"step": 1862
},
{
"epoch": 5.45,
"learning_rate": 3.637426900584795e-05,
"loss": 0.003,
"step": 1864
},
{
"epoch": 5.46,
"learning_rate": 3.635964912280702e-05,
"loss": 0.0757,
"step": 1866
},
{
"epoch": 5.46,
"learning_rate": 3.6345029239766084e-05,
"loss": 0.0123,
"step": 1868
},
{
"epoch": 5.47,
"learning_rate": 3.6330409356725146e-05,
"loss": 0.1504,
"step": 1870
},
{
"epoch": 5.47,
"learning_rate": 3.6315789473684214e-05,
"loss": 0.0002,
"step": 1872
},
{
"epoch": 5.48,
"learning_rate": 3.6301169590643276e-05,
"loss": 0.2835,
"step": 1874
},
{
"epoch": 5.49,
"learning_rate": 3.628654970760234e-05,
"loss": 0.0308,
"step": 1876
},
{
"epoch": 5.49,
"learning_rate": 3.627192982456141e-05,
"loss": 0.1686,
"step": 1878
},
{
"epoch": 5.5,
"learning_rate": 3.625730994152047e-05,
"loss": 0.0051,
"step": 1880
},
{
"epoch": 5.5,
"learning_rate": 3.624269005847953e-05,
"loss": 0.1522,
"step": 1882
},
{
"epoch": 5.51,
"learning_rate": 3.62280701754386e-05,
"loss": 0.043,
"step": 1884
},
{
"epoch": 5.51,
"learning_rate": 3.621345029239766e-05,
"loss": 0.0353,
"step": 1886
},
{
"epoch": 5.52,
"learning_rate": 3.6198830409356724e-05,
"loss": 0.0505,
"step": 1888
},
{
"epoch": 5.53,
"learning_rate": 3.618421052631579e-05,
"loss": 0.0114,
"step": 1890
},
{
"epoch": 5.53,
"learning_rate": 3.6169590643274855e-05,
"loss": 0.0319,
"step": 1892
},
{
"epoch": 5.54,
"learning_rate": 3.615497076023392e-05,
"loss": 0.0366,
"step": 1894
},
{
"epoch": 5.54,
"learning_rate": 3.6140350877192985e-05,
"loss": 0.3758,
"step": 1896
},
{
"epoch": 5.55,
"learning_rate": 3.612573099415205e-05,
"loss": 0.2406,
"step": 1898
},
{
"epoch": 5.56,
"learning_rate": 3.611111111111111e-05,
"loss": 0.2275,
"step": 1900
},
{
"epoch": 5.56,
"learning_rate": 3.609649122807018e-05,
"loss": 0.0005,
"step": 1902
},
{
"epoch": 5.57,
"learning_rate": 3.608187134502924e-05,
"loss": 0.0099,
"step": 1904
},
{
"epoch": 5.57,
"learning_rate": 3.60672514619883e-05,
"loss": 0.0295,
"step": 1906
},
{
"epoch": 5.58,
"learning_rate": 3.605263157894737e-05,
"loss": 0.0067,
"step": 1908
},
{
"epoch": 5.58,
"learning_rate": 3.603801169590643e-05,
"loss": 0.0009,
"step": 1910
},
{
"epoch": 5.59,
"learning_rate": 3.6023391812865495e-05,
"loss": 0.0229,
"step": 1912
},
{
"epoch": 5.6,
"learning_rate": 3.6008771929824564e-05,
"loss": 0.0016,
"step": 1914
},
{
"epoch": 5.6,
"learning_rate": 3.599415204678363e-05,
"loss": 0.0002,
"step": 1916
},
{
"epoch": 5.61,
"learning_rate": 3.597953216374269e-05,
"loss": 0.0038,
"step": 1918
},
{
"epoch": 5.61,
"learning_rate": 3.5964912280701756e-05,
"loss": 0.0248,
"step": 1920
},
{
"epoch": 5.62,
"learning_rate": 3.5950292397660825e-05,
"loss": 0.2206,
"step": 1922
},
{
"epoch": 5.63,
"learning_rate": 3.593567251461988e-05,
"loss": 0.0183,
"step": 1924
},
{
"epoch": 5.63,
"learning_rate": 3.592105263157895e-05,
"loss": 0.1735,
"step": 1926
},
{
"epoch": 5.64,
"learning_rate": 3.590643274853802e-05,
"loss": 0.0147,
"step": 1928
},
{
"epoch": 5.64,
"learning_rate": 3.589181286549707e-05,
"loss": 0.0007,
"step": 1930
},
{
"epoch": 5.65,
"learning_rate": 3.587719298245614e-05,
"loss": 0.1233,
"step": 1932
},
{
"epoch": 5.65,
"learning_rate": 3.586257309941521e-05,
"loss": 0.0023,
"step": 1934
},
{
"epoch": 5.66,
"learning_rate": 3.5847953216374266e-05,
"loss": 0.0001,
"step": 1936
},
{
"epoch": 5.67,
"learning_rate": 3.5833333333333335e-05,
"loss": 0.0006,
"step": 1938
},
{
"epoch": 5.67,
"learning_rate": 3.5818713450292403e-05,
"loss": 0.0065,
"step": 1940
},
{
"epoch": 5.68,
"learning_rate": 3.5804093567251465e-05,
"loss": 0.0032,
"step": 1942
},
{
"epoch": 5.68,
"learning_rate": 3.578947368421053e-05,
"loss": 0.1814,
"step": 1944
},
{
"epoch": 5.69,
"learning_rate": 3.5774853801169596e-05,
"loss": 0.0001,
"step": 1946
},
{
"epoch": 5.7,
"learning_rate": 3.576023391812866e-05,
"loss": 0.0008,
"step": 1948
},
{
"epoch": 5.7,
"learning_rate": 3.574561403508772e-05,
"loss": 0.0541,
"step": 1950
},
{
"epoch": 5.71,
"learning_rate": 3.573099415204679e-05,
"loss": 0.0001,
"step": 1952
},
{
"epoch": 5.71,
"learning_rate": 3.571637426900585e-05,
"loss": 0.0204,
"step": 1954
},
{
"epoch": 5.72,
"learning_rate": 3.570175438596491e-05,
"loss": 0.0037,
"step": 1956
},
{
"epoch": 5.73,
"learning_rate": 3.568713450292398e-05,
"loss": 0.0002,
"step": 1958
},
{
"epoch": 5.73,
"learning_rate": 3.5672514619883044e-05,
"loss": 0.0024,
"step": 1960
},
{
"epoch": 5.74,
"learning_rate": 3.5657894736842106e-05,
"loss": 0.0501,
"step": 1962
},
{
"epoch": 5.74,
"learning_rate": 3.5643274853801174e-05,
"loss": 0.0014,
"step": 1964
},
{
"epoch": 5.75,
"learning_rate": 3.5628654970760236e-05,
"loss": 0.0385,
"step": 1966
},
{
"epoch": 5.75,
"learning_rate": 3.56140350877193e-05,
"loss": 0.0101,
"step": 1968
},
{
"epoch": 5.76,
"learning_rate": 3.559941520467837e-05,
"loss": 0.2126,
"step": 1970
},
{
"epoch": 5.77,
"learning_rate": 3.558479532163743e-05,
"loss": 0.1272,
"step": 1972
},
{
"epoch": 5.77,
"learning_rate": 3.557017543859649e-05,
"loss": 0.005,
"step": 1974
},
{
"epoch": 5.78,
"learning_rate": 3.555555555555556e-05,
"loss": 0.0404,
"step": 1976
},
{
"epoch": 5.78,
"learning_rate": 3.554093567251462e-05,
"loss": 0.0009,
"step": 1978
},
{
"epoch": 5.79,
"learning_rate": 3.5526315789473684e-05,
"loss": 0.0747,
"step": 1980
},
{
"epoch": 5.8,
"learning_rate": 3.551169590643275e-05,
"loss": 0.0066,
"step": 1982
},
{
"epoch": 5.8,
"learning_rate": 3.5497076023391815e-05,
"loss": 0.1092,
"step": 1984
},
{
"epoch": 5.81,
"learning_rate": 3.548245614035088e-05,
"loss": 0.0044,
"step": 1986
},
{
"epoch": 5.81,
"learning_rate": 3.5467836257309945e-05,
"loss": 0.1041,
"step": 1988
},
{
"epoch": 5.82,
"learning_rate": 3.545321637426901e-05,
"loss": 0.005,
"step": 1990
},
{
"epoch": 5.82,
"learning_rate": 3.543859649122807e-05,
"loss": 0.0004,
"step": 1992
},
{
"epoch": 5.83,
"learning_rate": 3.542397660818714e-05,
"loss": 0.2162,
"step": 1994
},
{
"epoch": 5.84,
"learning_rate": 3.54093567251462e-05,
"loss": 0.157,
"step": 1996
},
{
"epoch": 5.84,
"learning_rate": 3.539473684210526e-05,
"loss": 0.6307,
"step": 1998
},
{
"epoch": 5.85,
"learning_rate": 3.538011695906433e-05,
"loss": 0.4674,
"step": 2000
},
{
"epoch": 5.85,
"learning_rate": 3.536549707602339e-05,
"loss": 0.0014,
"step": 2002
},
{
"epoch": 5.86,
"learning_rate": 3.5350877192982455e-05,
"loss": 0.1796,
"step": 2004
},
{
"epoch": 5.87,
"learning_rate": 3.5336257309941524e-05,
"loss": 0.0003,
"step": 2006
},
{
"epoch": 5.87,
"learning_rate": 3.5321637426900586e-05,
"loss": 0.0116,
"step": 2008
},
{
"epoch": 5.88,
"learning_rate": 3.530701754385965e-05,
"loss": 0.035,
"step": 2010
},
{
"epoch": 5.88,
"learning_rate": 3.5292397660818716e-05,
"loss": 0.0133,
"step": 2012
},
{
"epoch": 5.89,
"learning_rate": 3.527777777777778e-05,
"loss": 0.0127,
"step": 2014
},
{
"epoch": 5.89,
"learning_rate": 3.526315789473684e-05,
"loss": 0.0112,
"step": 2016
},
{
"epoch": 5.9,
"learning_rate": 3.524853801169591e-05,
"loss": 0.0002,
"step": 2018
},
{
"epoch": 5.91,
"learning_rate": 3.523391812865498e-05,
"loss": 0.0082,
"step": 2020
},
{
"epoch": 5.91,
"learning_rate": 3.521929824561403e-05,
"loss": 0.0021,
"step": 2022
},
{
"epoch": 5.92,
"learning_rate": 3.52046783625731e-05,
"loss": 0.3352,
"step": 2024
},
{
"epoch": 5.92,
"learning_rate": 3.519005847953217e-05,
"loss": 0.0004,
"step": 2026
},
{
"epoch": 5.93,
"learning_rate": 3.5175438596491226e-05,
"loss": 0.1076,
"step": 2028
},
{
"epoch": 5.94,
"learning_rate": 3.5160818713450295e-05,
"loss": 0.0521,
"step": 2030
},
{
"epoch": 5.94,
"learning_rate": 3.5146198830409363e-05,
"loss": 0.0965,
"step": 2032
},
{
"epoch": 5.95,
"learning_rate": 3.513157894736842e-05,
"loss": 0.0045,
"step": 2034
},
{
"epoch": 5.95,
"learning_rate": 3.511695906432749e-05,
"loss": 0.0007,
"step": 2036
},
{
"epoch": 5.96,
"learning_rate": 3.5102339181286556e-05,
"loss": 0.0002,
"step": 2038
},
{
"epoch": 5.96,
"learning_rate": 3.508771929824561e-05,
"loss": 0.0007,
"step": 2040
},
{
"epoch": 5.97,
"learning_rate": 3.507309941520468e-05,
"loss": 0.0603,
"step": 2042
},
{
"epoch": 5.98,
"learning_rate": 3.505847953216375e-05,
"loss": 0.0019,
"step": 2044
},
{
"epoch": 5.98,
"learning_rate": 3.5043859649122804e-05,
"loss": 0.0619,
"step": 2046
},
{
"epoch": 5.99,
"learning_rate": 3.502923976608187e-05,
"loss": 0.071,
"step": 2048
},
{
"epoch": 5.99,
"learning_rate": 3.501461988304094e-05,
"loss": 0.0003,
"step": 2050
},
{
"epoch": 6.0,
"learning_rate": 3.5e-05,
"loss": 0.0291,
"step": 2052
},
{
"epoch": 6.0,
"eval_bleu": 0.5125799539218449,
"eval_loss": 1.232753038406372,
"eval_runtime": 35.8504,
"eval_samples_per_second": 9.344,
"eval_steps_per_second": 2.343,
"step": 2052
},
{
"epoch": 6.01,
"learning_rate": 3.4985380116959066e-05,
"loss": 0.0025,
"step": 2054
},
{
"epoch": 6.01,
"learning_rate": 3.4970760233918134e-05,
"loss": 0.0693,
"step": 2056
},
{
"epoch": 6.02,
"learning_rate": 3.495614035087719e-05,
"loss": 0.0679,
"step": 2058
},
{
"epoch": 6.02,
"learning_rate": 3.494152046783626e-05,
"loss": 0.0002,
"step": 2060
},
{
"epoch": 6.03,
"learning_rate": 3.492690058479533e-05,
"loss": 0.001,
"step": 2062
},
{
"epoch": 6.04,
"learning_rate": 3.491228070175438e-05,
"loss": 0.0083,
"step": 2064
},
{
"epoch": 6.04,
"learning_rate": 3.489766081871345e-05,
"loss": 0.0014,
"step": 2066
},
{
"epoch": 6.05,
"learning_rate": 3.488304093567252e-05,
"loss": 0.0002,
"step": 2068
},
{
"epoch": 6.05,
"learning_rate": 3.4868421052631575e-05,
"loss": 0.0164,
"step": 2070
},
{
"epoch": 6.06,
"learning_rate": 3.4853801169590644e-05,
"loss": 0.0511,
"step": 2072
},
{
"epoch": 6.06,
"learning_rate": 3.483918128654971e-05,
"loss": 0.1135,
"step": 2074
},
{
"epoch": 6.07,
"learning_rate": 3.482456140350877e-05,
"loss": 0.0071,
"step": 2076
},
{
"epoch": 6.08,
"learning_rate": 3.480994152046784e-05,
"loss": 0.0597,
"step": 2078
},
{
"epoch": 6.08,
"learning_rate": 3.4795321637426905e-05,
"loss": 0.0001,
"step": 2080
},
{
"epoch": 6.09,
"learning_rate": 3.478070175438597e-05,
"loss": 0.0002,
"step": 2082
},
{
"epoch": 6.09,
"learning_rate": 3.476608187134503e-05,
"loss": 0.0,
"step": 2084
},
{
"epoch": 6.1,
"learning_rate": 3.47514619883041e-05,
"loss": 0.0013,
"step": 2086
},
{
"epoch": 6.11,
"learning_rate": 3.473684210526316e-05,
"loss": 0.0001,
"step": 2088
},
{
"epoch": 6.11,
"learning_rate": 3.472222222222222e-05,
"loss": 0.1731,
"step": 2090
},
{
"epoch": 6.12,
"learning_rate": 3.470760233918129e-05,
"loss": 0.0097,
"step": 2092
},
{
"epoch": 6.12,
"learning_rate": 3.469298245614035e-05,
"loss": 0.0016,
"step": 2094
},
{
"epoch": 6.13,
"learning_rate": 3.4678362573099415e-05,
"loss": 0.1214,
"step": 2096
},
{
"epoch": 6.13,
"learning_rate": 3.4663742690058484e-05,
"loss": 0.1574,
"step": 2098
},
{
"epoch": 6.14,
"learning_rate": 3.4649122807017546e-05,
"loss": 0.0069,
"step": 2100
},
{
"epoch": 6.15,
"learning_rate": 3.463450292397661e-05,
"loss": 0.024,
"step": 2102
},
{
"epoch": 6.15,
"learning_rate": 3.4619883040935676e-05,
"loss": 0.0008,
"step": 2104
},
{
"epoch": 6.16,
"learning_rate": 3.460526315789474e-05,
"loss": 0.0,
"step": 2106
},
{
"epoch": 6.16,
"learning_rate": 3.45906432748538e-05,
"loss": 0.0046,
"step": 2108
},
{
"epoch": 6.17,
"learning_rate": 3.457602339181287e-05,
"loss": 0.0009,
"step": 2110
},
{
"epoch": 6.18,
"learning_rate": 3.456140350877193e-05,
"loss": 0.0008,
"step": 2112
},
{
"epoch": 6.18,
"learning_rate": 3.454678362573099e-05,
"loss": 0.2156,
"step": 2114
},
{
"epoch": 6.19,
"learning_rate": 3.453216374269006e-05,
"loss": 0.1992,
"step": 2116
},
{
"epoch": 6.19,
"learning_rate": 3.4517543859649124e-05,
"loss": 0.2427,
"step": 2118
},
{
"epoch": 6.2,
"learning_rate": 3.4502923976608186e-05,
"loss": 0.0003,
"step": 2120
},
{
"epoch": 6.2,
"learning_rate": 3.4488304093567255e-05,
"loss": 0.028,
"step": 2122
},
{
"epoch": 6.21,
"learning_rate": 3.447368421052632e-05,
"loss": 0.0003,
"step": 2124
},
{
"epoch": 6.22,
"learning_rate": 3.445906432748538e-05,
"loss": 0.0034,
"step": 2126
},
{
"epoch": 6.22,
"learning_rate": 3.444444444444445e-05,
"loss": 0.0001,
"step": 2128
},
{
"epoch": 6.23,
"learning_rate": 3.442982456140351e-05,
"loss": 0.0007,
"step": 2130
},
{
"epoch": 6.23,
"learning_rate": 3.441520467836257e-05,
"loss": 0.0006,
"step": 2132
},
{
"epoch": 6.24,
"learning_rate": 3.440058479532164e-05,
"loss": 0.014,
"step": 2134
},
{
"epoch": 6.25,
"learning_rate": 3.43859649122807e-05,
"loss": 0.0367,
"step": 2136
},
{
"epoch": 6.25,
"learning_rate": 3.4371345029239764e-05,
"loss": 0.0178,
"step": 2138
},
{
"epoch": 6.26,
"learning_rate": 3.435672514619883e-05,
"loss": 0.1223,
"step": 2140
},
{
"epoch": 6.26,
"learning_rate": 3.4342105263157895e-05,
"loss": 0.0371,
"step": 2142
},
{
"epoch": 6.27,
"learning_rate": 3.432748538011696e-05,
"loss": 0.0001,
"step": 2144
},
{
"epoch": 6.27,
"learning_rate": 3.4312865497076026e-05,
"loss": 0.0783,
"step": 2146
},
{
"epoch": 6.28,
"learning_rate": 3.429824561403509e-05,
"loss": 0.1064,
"step": 2148
},
{
"epoch": 6.29,
"learning_rate": 3.428362573099415e-05,
"loss": 0.334,
"step": 2150
},
{
"epoch": 6.29,
"learning_rate": 3.426900584795322e-05,
"loss": 0.0012,
"step": 2152
},
{
"epoch": 6.3,
"learning_rate": 3.425438596491228e-05,
"loss": 0.0265,
"step": 2154
},
{
"epoch": 6.3,
"learning_rate": 3.423976608187134e-05,
"loss": 0.1773,
"step": 2156
},
{
"epoch": 6.31,
"learning_rate": 3.422514619883041e-05,
"loss": 0.0013,
"step": 2158
},
{
"epoch": 6.32,
"learning_rate": 3.421052631578947e-05,
"loss": 0.0008,
"step": 2160
},
{
"epoch": 6.32,
"learning_rate": 3.419590643274854e-05,
"loss": 0.0163,
"step": 2162
},
{
"epoch": 6.33,
"learning_rate": 3.4181286549707604e-05,
"loss": 0.0017,
"step": 2164
},
{
"epoch": 6.33,
"learning_rate": 3.4166666666666666e-05,
"loss": 0.0049,
"step": 2166
},
{
"epoch": 6.34,
"learning_rate": 3.4152046783625735e-05,
"loss": 0.0055,
"step": 2168
},
{
"epoch": 6.35,
"learning_rate": 3.41374269005848e-05,
"loss": 0.002,
"step": 2170
},
{
"epoch": 6.35,
"learning_rate": 3.412280701754386e-05,
"loss": 0.0615,
"step": 2172
},
{
"epoch": 6.36,
"learning_rate": 3.410818713450293e-05,
"loss": 0.0005,
"step": 2174
},
{
"epoch": 6.36,
"learning_rate": 3.409356725146199e-05,
"loss": 0.0015,
"step": 2176
},
{
"epoch": 6.37,
"learning_rate": 3.407894736842105e-05,
"loss": 0.0965,
"step": 2178
},
{
"epoch": 6.37,
"learning_rate": 3.406432748538012e-05,
"loss": 0.0725,
"step": 2180
},
{
"epoch": 6.38,
"learning_rate": 3.404970760233918e-05,
"loss": 0.0007,
"step": 2182
},
{
"epoch": 6.39,
"learning_rate": 3.403508771929825e-05,
"loss": 0.0019,
"step": 2184
},
{
"epoch": 6.39,
"learning_rate": 3.402046783625731e-05,
"loss": 0.0109,
"step": 2186
},
{
"epoch": 6.4,
"learning_rate": 3.4005847953216375e-05,
"loss": 0.1223,
"step": 2188
},
{
"epoch": 6.4,
"learning_rate": 3.3991228070175444e-05,
"loss": 0.0064,
"step": 2190
},
{
"epoch": 6.41,
"learning_rate": 3.3976608187134506e-05,
"loss": 0.0192,
"step": 2192
},
{
"epoch": 6.42,
"learning_rate": 3.396198830409357e-05,
"loss": 0.0005,
"step": 2194
},
{
"epoch": 6.42,
"learning_rate": 3.3947368421052636e-05,
"loss": 0.0016,
"step": 2196
},
{
"epoch": 6.43,
"learning_rate": 3.39327485380117e-05,
"loss": 0.0018,
"step": 2198
},
{
"epoch": 6.43,
"learning_rate": 3.391812865497076e-05,
"loss": 0.0163,
"step": 2200
},
{
"epoch": 6.44,
"learning_rate": 3.390350877192983e-05,
"loss": 0.0029,
"step": 2202
},
{
"epoch": 6.44,
"learning_rate": 3.388888888888889e-05,
"loss": 0.0818,
"step": 2204
},
{
"epoch": 6.45,
"learning_rate": 3.387426900584795e-05,
"loss": 0.0072,
"step": 2206
},
{
"epoch": 6.46,
"learning_rate": 3.385964912280702e-05,
"loss": 0.0755,
"step": 2208
},
{
"epoch": 6.46,
"learning_rate": 3.3845029239766084e-05,
"loss": 0.3126,
"step": 2210
},
{
"epoch": 6.47,
"learning_rate": 3.3830409356725146e-05,
"loss": 0.2012,
"step": 2212
},
{
"epoch": 6.47,
"learning_rate": 3.3815789473684215e-05,
"loss": 0.0023,
"step": 2214
},
{
"epoch": 6.48,
"learning_rate": 3.380116959064328e-05,
"loss": 0.0328,
"step": 2216
},
{
"epoch": 6.49,
"learning_rate": 3.378654970760234e-05,
"loss": 0.0146,
"step": 2218
},
{
"epoch": 6.49,
"learning_rate": 3.377192982456141e-05,
"loss": 0.0003,
"step": 2220
},
{
"epoch": 6.5,
"learning_rate": 3.375730994152047e-05,
"loss": 0.0028,
"step": 2222
},
{
"epoch": 6.5,
"learning_rate": 3.374269005847953e-05,
"loss": 0.0104,
"step": 2224
},
{
"epoch": 6.51,
"learning_rate": 3.37280701754386e-05,
"loss": 0.064,
"step": 2226
},
{
"epoch": 6.51,
"learning_rate": 3.371345029239766e-05,
"loss": 0.0539,
"step": 2228
},
{
"epoch": 6.52,
"learning_rate": 3.3698830409356724e-05,
"loss": 0.0104,
"step": 2230
},
{
"epoch": 6.53,
"learning_rate": 3.368421052631579e-05,
"loss": 0.0433,
"step": 2232
},
{
"epoch": 6.53,
"learning_rate": 3.3669590643274855e-05,
"loss": 0.0877,
"step": 2234
},
{
"epoch": 6.54,
"learning_rate": 3.365497076023392e-05,
"loss": 0.0041,
"step": 2236
},
{
"epoch": 6.54,
"learning_rate": 3.3640350877192986e-05,
"loss": 0.0011,
"step": 2238
},
{
"epoch": 6.55,
"learning_rate": 3.362573099415205e-05,
"loss": 0.0007,
"step": 2240
},
{
"epoch": 6.56,
"learning_rate": 3.3611111111111116e-05,
"loss": 0.0045,
"step": 2242
},
{
"epoch": 6.56,
"learning_rate": 3.359649122807018e-05,
"loss": 0.0045,
"step": 2244
},
{
"epoch": 6.57,
"learning_rate": 3.358187134502924e-05,
"loss": 0.0493,
"step": 2246
},
{
"epoch": 6.57,
"learning_rate": 3.356725146198831e-05,
"loss": 0.0032,
"step": 2248
},
{
"epoch": 6.58,
"learning_rate": 3.355263157894737e-05,
"loss": 0.0591,
"step": 2250
},
{
"epoch": 6.58,
"learning_rate": 3.353801169590643e-05,
"loss": 0.0017,
"step": 2252
},
{
"epoch": 6.59,
"learning_rate": 3.35233918128655e-05,
"loss": 0.0008,
"step": 2254
},
{
"epoch": 6.6,
"learning_rate": 3.3508771929824564e-05,
"loss": 0.0002,
"step": 2256
},
{
"epoch": 6.6,
"learning_rate": 3.3494152046783626e-05,
"loss": 0.0187,
"step": 2258
},
{
"epoch": 6.61,
"learning_rate": 3.3479532163742695e-05,
"loss": 0.0011,
"step": 2260
},
{
"epoch": 6.61,
"learning_rate": 3.346491228070176e-05,
"loss": 0.0036,
"step": 2262
},
{
"epoch": 6.62,
"learning_rate": 3.345029239766082e-05,
"loss": 0.0265,
"step": 2264
},
{
"epoch": 6.63,
"learning_rate": 3.343567251461989e-05,
"loss": 0.0134,
"step": 2266
},
{
"epoch": 6.63,
"learning_rate": 3.342105263157895e-05,
"loss": 0.2247,
"step": 2268
},
{
"epoch": 6.64,
"learning_rate": 3.340643274853801e-05,
"loss": 0.0565,
"step": 2270
},
{
"epoch": 6.64,
"learning_rate": 3.339181286549708e-05,
"loss": 0.0001,
"step": 2272
},
{
"epoch": 6.65,
"learning_rate": 3.337719298245614e-05,
"loss": 0.0011,
"step": 2274
},
{
"epoch": 6.65,
"learning_rate": 3.3362573099415204e-05,
"loss": 0.1321,
"step": 2276
},
{
"epoch": 6.66,
"learning_rate": 3.334795321637427e-05,
"loss": 0.0013,
"step": 2278
},
{
"epoch": 6.67,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.0032,
"step": 2280
},
{
"epoch": 6.67,
"learning_rate": 3.33187134502924e-05,
"loss": 0.0079,
"step": 2282
},
{
"epoch": 6.68,
"learning_rate": 3.3304093567251466e-05,
"loss": 0.0243,
"step": 2284
},
{
"epoch": 6.68,
"learning_rate": 3.328947368421053e-05,
"loss": 0.005,
"step": 2286
},
{
"epoch": 6.69,
"learning_rate": 3.327485380116959e-05,
"loss": 0.0247,
"step": 2288
},
{
"epoch": 6.7,
"learning_rate": 3.326023391812866e-05,
"loss": 0.0435,
"step": 2290
},
{
"epoch": 6.7,
"learning_rate": 3.324561403508772e-05,
"loss": 0.0002,
"step": 2292
},
{
"epoch": 6.71,
"learning_rate": 3.323099415204678e-05,
"loss": 0.0001,
"step": 2294
},
{
"epoch": 6.71,
"learning_rate": 3.321637426900585e-05,
"loss": 0.151,
"step": 2296
},
{
"epoch": 6.72,
"learning_rate": 3.320175438596491e-05,
"loss": 0.0012,
"step": 2298
},
{
"epoch": 6.73,
"learning_rate": 3.3187134502923975e-05,
"loss": 0.2481,
"step": 2300
},
{
"epoch": 6.73,
"learning_rate": 3.3172514619883044e-05,
"loss": 0.0001,
"step": 2302
},
{
"epoch": 6.74,
"learning_rate": 3.3157894736842106e-05,
"loss": 0.0129,
"step": 2304
},
{
"epoch": 6.74,
"learning_rate": 3.314327485380117e-05,
"loss": 0.0002,
"step": 2306
},
{
"epoch": 6.75,
"learning_rate": 3.312865497076024e-05,
"loss": 0.025,
"step": 2308
},
{
"epoch": 6.75,
"learning_rate": 3.31140350877193e-05,
"loss": 0.0015,
"step": 2310
},
{
"epoch": 6.76,
"learning_rate": 3.309941520467836e-05,
"loss": 0.008,
"step": 2312
},
{
"epoch": 6.77,
"learning_rate": 3.308479532163743e-05,
"loss": 0.0005,
"step": 2314
},
{
"epoch": 6.77,
"learning_rate": 3.307017543859649e-05,
"loss": 0.0117,
"step": 2316
},
{
"epoch": 6.78,
"learning_rate": 3.3055555555555553e-05,
"loss": 0.0005,
"step": 2318
},
{
"epoch": 6.78,
"learning_rate": 3.304093567251462e-05,
"loss": 0.1768,
"step": 2320
},
{
"epoch": 6.79,
"learning_rate": 3.302631578947369e-05,
"loss": 0.0001,
"step": 2322
},
{
"epoch": 6.8,
"learning_rate": 3.3011695906432746e-05,
"loss": 0.0,
"step": 2324
},
{
"epoch": 6.8,
"learning_rate": 3.2997076023391815e-05,
"loss": 0.0019,
"step": 2326
},
{
"epoch": 6.81,
"learning_rate": 3.2982456140350884e-05,
"loss": 0.0776,
"step": 2328
},
{
"epoch": 6.81,
"learning_rate": 3.296783625730994e-05,
"loss": 0.0099,
"step": 2330
},
{
"epoch": 6.82,
"learning_rate": 3.295321637426901e-05,
"loss": 0.0048,
"step": 2332
},
{
"epoch": 6.82,
"learning_rate": 3.2938596491228076e-05,
"loss": 0.0004,
"step": 2334
},
{
"epoch": 6.83,
"learning_rate": 3.292397660818713e-05,
"loss": 0.0001,
"step": 2336
},
{
"epoch": 6.84,
"learning_rate": 3.29093567251462e-05,
"loss": 0.0173,
"step": 2338
},
{
"epoch": 6.84,
"learning_rate": 3.289473684210527e-05,
"loss": 0.0018,
"step": 2340
},
{
"epoch": 6.85,
"learning_rate": 3.2880116959064324e-05,
"loss": 0.0001,
"step": 2342
},
{
"epoch": 6.85,
"learning_rate": 3.286549707602339e-05,
"loss": 0.0006,
"step": 2344
},
{
"epoch": 6.86,
"learning_rate": 3.285087719298246e-05,
"loss": 0.5343,
"step": 2346
},
{
"epoch": 6.87,
"learning_rate": 3.283625730994152e-05,
"loss": 0.0145,
"step": 2348
},
{
"epoch": 6.87,
"learning_rate": 3.2821637426900586e-05,
"loss": 0.1496,
"step": 2350
},
{
"epoch": 6.88,
"learning_rate": 3.2807017543859655e-05,
"loss": 0.1282,
"step": 2352
},
{
"epoch": 6.88,
"learning_rate": 3.279239766081872e-05,
"loss": 0.0803,
"step": 2354
},
{
"epoch": 6.89,
"learning_rate": 3.277777777777778e-05,
"loss": 0.0423,
"step": 2356
},
{
"epoch": 6.89,
"learning_rate": 3.276315789473685e-05,
"loss": 0.0002,
"step": 2358
},
{
"epoch": 6.9,
"learning_rate": 3.274853801169591e-05,
"loss": 0.0037,
"step": 2360
},
{
"epoch": 6.91,
"learning_rate": 3.273391812865497e-05,
"loss": 0.0453,
"step": 2362
},
{
"epoch": 6.91,
"learning_rate": 3.271929824561404e-05,
"loss": 0.0114,
"step": 2364
},
{
"epoch": 6.92,
"learning_rate": 3.27046783625731e-05,
"loss": 0.1457,
"step": 2366
},
{
"epoch": 6.92,
"learning_rate": 3.2690058479532164e-05,
"loss": 0.0012,
"step": 2368
},
{
"epoch": 6.93,
"learning_rate": 3.267543859649123e-05,
"loss": 0.0005,
"step": 2370
},
{
"epoch": 6.94,
"learning_rate": 3.2660818713450295e-05,
"loss": 0.0001,
"step": 2372
},
{
"epoch": 6.94,
"learning_rate": 3.264619883040936e-05,
"loss": 0.038,
"step": 2374
},
{
"epoch": 6.95,
"learning_rate": 3.2631578947368426e-05,
"loss": 0.0002,
"step": 2376
},
{
"epoch": 6.95,
"learning_rate": 3.261695906432749e-05,
"loss": 0.0629,
"step": 2378
},
{
"epoch": 6.96,
"learning_rate": 3.260233918128655e-05,
"loss": 0.0707,
"step": 2380
},
{
"epoch": 6.96,
"learning_rate": 3.258771929824562e-05,
"loss": 0.0009,
"step": 2382
},
{
"epoch": 6.97,
"learning_rate": 3.257309941520468e-05,
"loss": 0.0065,
"step": 2384
},
{
"epoch": 6.98,
"learning_rate": 3.255847953216374e-05,
"loss": 0.0155,
"step": 2386
},
{
"epoch": 6.98,
"learning_rate": 3.254385964912281e-05,
"loss": 0.0821,
"step": 2388
},
{
"epoch": 6.99,
"learning_rate": 3.252923976608187e-05,
"loss": 0.0001,
"step": 2390
},
{
"epoch": 6.99,
"learning_rate": 3.2514619883040935e-05,
"loss": 0.0067,
"step": 2392
},
{
"epoch": 7.0,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0002,
"step": 2394
},
{
"epoch": 7.0,
"eval_bleu": 0.4857180997296596,
"eval_loss": 1.315371036529541,
"eval_runtime": 36.268,
"eval_samples_per_second": 9.237,
"eval_steps_per_second": 2.316,
"step": 2394
},
{
"epoch": 7.01,
"learning_rate": 3.2485380116959066e-05,
"loss": 0.0,
"step": 2396
},
{
"epoch": 7.01,
"learning_rate": 3.247076023391813e-05,
"loss": 0.0011,
"step": 2398
},
{
"epoch": 7.02,
"learning_rate": 3.24561403508772e-05,
"loss": 0.0014,
"step": 2400
},
{
"epoch": 7.02,
"learning_rate": 3.244152046783626e-05,
"loss": 0.0011,
"step": 2402
},
{
"epoch": 7.03,
"learning_rate": 3.242690058479532e-05,
"loss": 0.0004,
"step": 2404
},
{
"epoch": 7.04,
"learning_rate": 3.241228070175439e-05,
"loss": 0.0008,
"step": 2406
},
{
"epoch": 7.04,
"learning_rate": 3.239766081871345e-05,
"loss": 0.0021,
"step": 2408
},
{
"epoch": 7.05,
"learning_rate": 3.2383040935672513e-05,
"loss": 0.0001,
"step": 2410
},
{
"epoch": 7.05,
"learning_rate": 3.236842105263158e-05,
"loss": 0.0092,
"step": 2412
},
{
"epoch": 7.06,
"learning_rate": 3.2353801169590644e-05,
"loss": 0.0639,
"step": 2414
},
{
"epoch": 7.06,
"learning_rate": 3.2339181286549706e-05,
"loss": 0.0005,
"step": 2416
},
{
"epoch": 7.07,
"learning_rate": 3.2324561403508775e-05,
"loss": 0.0003,
"step": 2418
},
{
"epoch": 7.08,
"learning_rate": 3.230994152046784e-05,
"loss": 0.0089,
"step": 2420
},
{
"epoch": 7.08,
"learning_rate": 3.22953216374269e-05,
"loss": 0.0339,
"step": 2422
},
{
"epoch": 7.09,
"learning_rate": 3.228070175438597e-05,
"loss": 0.001,
"step": 2424
},
{
"epoch": 7.09,
"learning_rate": 3.226608187134503e-05,
"loss": 0.0054,
"step": 2426
},
{
"epoch": 7.1,
"learning_rate": 3.225146198830409e-05,
"loss": 0.0023,
"step": 2428
},
{
"epoch": 7.11,
"learning_rate": 3.223684210526316e-05,
"loss": 0.0006,
"step": 2430
},
{
"epoch": 7.11,
"learning_rate": 3.222222222222223e-05,
"loss": 0.1938,
"step": 2432
},
{
"epoch": 7.12,
"learning_rate": 3.2207602339181284e-05,
"loss": 0.0002,
"step": 2434
},
{
"epoch": 7.12,
"learning_rate": 3.219298245614035e-05,
"loss": 0.3159,
"step": 2436
},
{
"epoch": 7.13,
"learning_rate": 3.217836257309942e-05,
"loss": 0.0005,
"step": 2438
},
{
"epoch": 7.13,
"learning_rate": 3.216374269005848e-05,
"loss": 0.0001,
"step": 2440
},
{
"epoch": 7.14,
"learning_rate": 3.2149122807017546e-05,
"loss": 0.0,
"step": 2442
},
{
"epoch": 7.15,
"learning_rate": 3.2134502923976615e-05,
"loss": 0.0007,
"step": 2444
},
{
"epoch": 7.15,
"learning_rate": 3.211988304093567e-05,
"loss": 0.0,
"step": 2446
},
{
"epoch": 7.16,
"learning_rate": 3.210526315789474e-05,
"loss": 0.0894,
"step": 2448
},
{
"epoch": 7.16,
"learning_rate": 3.209064327485381e-05,
"loss": 0.0004,
"step": 2450
},
{
"epoch": 7.17,
"learning_rate": 3.207602339181286e-05,
"loss": 0.0011,
"step": 2452
},
{
"epoch": 7.18,
"learning_rate": 3.206140350877193e-05,
"loss": 0.0007,
"step": 2454
},
{
"epoch": 7.18,
"learning_rate": 3.2046783625731e-05,
"loss": 0.0002,
"step": 2456
},
{
"epoch": 7.19,
"learning_rate": 3.2032163742690055e-05,
"loss": 0.0002,
"step": 2458
},
{
"epoch": 7.19,
"learning_rate": 3.2017543859649124e-05,
"loss": 0.0003,
"step": 2460
},
{
"epoch": 7.2,
"learning_rate": 3.200292397660819e-05,
"loss": 0.0061,
"step": 2462
},
{
"epoch": 7.2,
"learning_rate": 3.198830409356725e-05,
"loss": 0.0156,
"step": 2464
},
{
"epoch": 7.21,
"learning_rate": 3.197368421052632e-05,
"loss": 0.0288,
"step": 2466
},
{
"epoch": 7.22,
"learning_rate": 3.1959064327485386e-05,
"loss": 0.0006,
"step": 2468
},
{
"epoch": 7.22,
"learning_rate": 3.194444444444444e-05,
"loss": 0.1188,
"step": 2470
},
{
"epoch": 7.23,
"learning_rate": 3.192982456140351e-05,
"loss": 0.0003,
"step": 2472
},
{
"epoch": 7.23,
"learning_rate": 3.191520467836258e-05,
"loss": 0.0114,
"step": 2474
},
{
"epoch": 7.24,
"learning_rate": 3.1900584795321634e-05,
"loss": 0.0006,
"step": 2476
},
{
"epoch": 7.25,
"learning_rate": 3.18859649122807e-05,
"loss": 0.0062,
"step": 2478
},
{
"epoch": 7.25,
"learning_rate": 3.187134502923977e-05,
"loss": 0.0135,
"step": 2480
},
{
"epoch": 7.26,
"learning_rate": 3.1856725146198826e-05,
"loss": 0.0842,
"step": 2482
},
{
"epoch": 7.26,
"learning_rate": 3.1842105263157895e-05,
"loss": 0.0003,
"step": 2484
},
{
"epoch": 7.27,
"learning_rate": 3.1827485380116964e-05,
"loss": 0.0004,
"step": 2486
},
{
"epoch": 7.27,
"learning_rate": 3.1812865497076026e-05,
"loss": 0.0785,
"step": 2488
},
{
"epoch": 7.28,
"learning_rate": 3.179824561403509e-05,
"loss": 0.1105,
"step": 2490
},
{
"epoch": 7.29,
"learning_rate": 3.178362573099416e-05,
"loss": 0.0018,
"step": 2492
},
{
"epoch": 7.29,
"learning_rate": 3.176900584795322e-05,
"loss": 0.0012,
"step": 2494
},
{
"epoch": 7.3,
"learning_rate": 3.175438596491228e-05,
"loss": 0.0003,
"step": 2496
},
{
"epoch": 7.3,
"learning_rate": 3.173976608187135e-05,
"loss": 0.0008,
"step": 2498
},
{
"epoch": 7.31,
"learning_rate": 3.172514619883041e-05,
"loss": 0.0002,
"step": 2500
},
{
"epoch": 7.32,
"learning_rate": 3.1710526315789473e-05,
"loss": 0.0247,
"step": 2502
},
{
"epoch": 7.32,
"learning_rate": 3.169590643274854e-05,
"loss": 0.0006,
"step": 2504
},
{
"epoch": 7.33,
"learning_rate": 3.1681286549707604e-05,
"loss": 0.054,
"step": 2506
},
{
"epoch": 7.33,
"learning_rate": 3.1666666666666666e-05,
"loss": 0.0453,
"step": 2508
},
{
"epoch": 7.34,
"learning_rate": 3.1652046783625735e-05,
"loss": 0.0011,
"step": 2510
},
{
"epoch": 7.35,
"learning_rate": 3.16374269005848e-05,
"loss": 0.0181,
"step": 2512
},
{
"epoch": 7.35,
"learning_rate": 3.162280701754386e-05,
"loss": 0.0005,
"step": 2514
},
{
"epoch": 7.36,
"learning_rate": 3.160818713450293e-05,
"loss": 0.0002,
"step": 2516
},
{
"epoch": 7.36,
"learning_rate": 3.159356725146199e-05,
"loss": 0.0215,
"step": 2518
},
{
"epoch": 7.37,
"learning_rate": 3.157894736842105e-05,
"loss": 0.0048,
"step": 2520
},
{
"epoch": 7.37,
"learning_rate": 3.156432748538012e-05,
"loss": 0.0082,
"step": 2522
},
{
"epoch": 7.38,
"learning_rate": 3.154970760233918e-05,
"loss": 0.0758,
"step": 2524
},
{
"epoch": 7.39,
"learning_rate": 3.1535087719298244e-05,
"loss": 0.2155,
"step": 2526
},
{
"epoch": 7.39,
"learning_rate": 3.152046783625731e-05,
"loss": 0.0211,
"step": 2528
},
{
"epoch": 7.4,
"learning_rate": 3.1505847953216375e-05,
"loss": 0.0087,
"step": 2530
},
{
"epoch": 7.4,
"learning_rate": 3.149122807017544e-05,
"loss": 0.0081,
"step": 2532
},
{
"epoch": 7.41,
"learning_rate": 3.1476608187134506e-05,
"loss": 0.088,
"step": 2534
},
{
"epoch": 7.42,
"learning_rate": 3.146198830409357e-05,
"loss": 0.0,
"step": 2536
},
{
"epoch": 7.42,
"learning_rate": 3.144736842105263e-05,
"loss": 0.0005,
"step": 2538
},
{
"epoch": 7.43,
"learning_rate": 3.14327485380117e-05,
"loss": 0.0,
"step": 2540
},
{
"epoch": 7.43,
"learning_rate": 3.141812865497076e-05,
"loss": 0.0008,
"step": 2542
},
{
"epoch": 7.44,
"learning_rate": 3.140350877192982e-05,
"loss": 0.0032,
"step": 2544
},
{
"epoch": 7.44,
"learning_rate": 3.138888888888889e-05,
"loss": 0.0147,
"step": 2546
},
{
"epoch": 7.45,
"learning_rate": 3.1374269005847953e-05,
"loss": 0.0005,
"step": 2548
},
{
"epoch": 7.46,
"learning_rate": 3.1359649122807015e-05,
"loss": 0.0093,
"step": 2550
},
{
"epoch": 7.46,
"learning_rate": 3.1345029239766084e-05,
"loss": 0.0037,
"step": 2552
},
{
"epoch": 7.47,
"learning_rate": 3.1330409356725146e-05,
"loss": 0.0103,
"step": 2554
},
{
"epoch": 7.47,
"learning_rate": 3.131578947368421e-05,
"loss": 0.0004,
"step": 2556
},
{
"epoch": 7.48,
"learning_rate": 3.130116959064328e-05,
"loss": 0.1245,
"step": 2558
},
{
"epoch": 7.49,
"learning_rate": 3.128654970760234e-05,
"loss": 0.0005,
"step": 2560
},
{
"epoch": 7.49,
"learning_rate": 3.12719298245614e-05,
"loss": 0.0023,
"step": 2562
},
{
"epoch": 7.5,
"learning_rate": 3.125730994152047e-05,
"loss": 0.0017,
"step": 2564
},
{
"epoch": 7.5,
"learning_rate": 3.124269005847953e-05,
"loss": 0.0,
"step": 2566
},
{
"epoch": 7.51,
"learning_rate": 3.12280701754386e-05,
"loss": 0.0014,
"step": 2568
},
{
"epoch": 7.51,
"learning_rate": 3.121345029239766e-05,
"loss": 0.0115,
"step": 2570
},
{
"epoch": 7.52,
"learning_rate": 3.1198830409356724e-05,
"loss": 0.0017,
"step": 2572
},
{
"epoch": 7.53,
"learning_rate": 3.118421052631579e-05,
"loss": 0.0596,
"step": 2574
},
{
"epoch": 7.53,
"learning_rate": 3.1169590643274855e-05,
"loss": 0.0008,
"step": 2576
},
{
"epoch": 7.54,
"learning_rate": 3.115497076023392e-05,
"loss": 0.0002,
"step": 2578
},
{
"epoch": 7.54,
"learning_rate": 3.1140350877192986e-05,
"loss": 0.0004,
"step": 2580
},
{
"epoch": 7.55,
"learning_rate": 3.112573099415205e-05,
"loss": 0.0007,
"step": 2582
},
{
"epoch": 7.56,
"learning_rate": 3.111111111111111e-05,
"loss": 0.0017,
"step": 2584
},
{
"epoch": 7.56,
"learning_rate": 3.109649122807018e-05,
"loss": 0.0009,
"step": 2586
},
{
"epoch": 7.57,
"learning_rate": 3.108187134502924e-05,
"loss": 0.1024,
"step": 2588
},
{
"epoch": 7.57,
"learning_rate": 3.10672514619883e-05,
"loss": 0.0059,
"step": 2590
},
{
"epoch": 7.58,
"learning_rate": 3.105263157894737e-05,
"loss": 0.008,
"step": 2592
},
{
"epoch": 7.58,
"learning_rate": 3.1038011695906433e-05,
"loss": 0.0023,
"step": 2594
},
{
"epoch": 7.59,
"learning_rate": 3.10233918128655e-05,
"loss": 0.0006,
"step": 2596
},
{
"epoch": 7.6,
"learning_rate": 3.1008771929824564e-05,
"loss": 0.028,
"step": 2598
},
{
"epoch": 7.6,
"learning_rate": 3.0994152046783626e-05,
"loss": 0.0002,
"step": 2600
},
{
"epoch": 7.61,
"learning_rate": 3.0979532163742695e-05,
"loss": 0.001,
"step": 2602
},
{
"epoch": 7.61,
"learning_rate": 3.096491228070176e-05,
"loss": 0.0295,
"step": 2604
},
{
"epoch": 7.62,
"learning_rate": 3.095029239766082e-05,
"loss": 0.0013,
"step": 2606
},
{
"epoch": 7.63,
"learning_rate": 3.093567251461989e-05,
"loss": 0.2043,
"step": 2608
},
{
"epoch": 7.63,
"learning_rate": 3.092105263157895e-05,
"loss": 0.0021,
"step": 2610
},
{
"epoch": 7.64,
"learning_rate": 3.090643274853801e-05,
"loss": 0.0009,
"step": 2612
},
{
"epoch": 7.64,
"learning_rate": 3.089181286549708e-05,
"loss": 0.0092,
"step": 2614
},
{
"epoch": 7.65,
"learning_rate": 3.087719298245614e-05,
"loss": 0.028,
"step": 2616
},
{
"epoch": 7.65,
"learning_rate": 3.0862573099415204e-05,
"loss": 0.0001,
"step": 2618
},
{
"epoch": 7.66,
"learning_rate": 3.084795321637427e-05,
"loss": 0.0007,
"step": 2620
},
{
"epoch": 7.67,
"learning_rate": 3.0833333333333335e-05,
"loss": 0.0005,
"step": 2622
},
{
"epoch": 7.67,
"learning_rate": 3.08187134502924e-05,
"loss": 0.0002,
"step": 2624
},
{
"epoch": 7.68,
"learning_rate": 3.0804093567251466e-05,
"loss": 0.041,
"step": 2626
},
{
"epoch": 7.68,
"learning_rate": 3.078947368421053e-05,
"loss": 0.0175,
"step": 2628
},
{
"epoch": 7.69,
"learning_rate": 3.077485380116959e-05,
"loss": 0.0901,
"step": 2630
},
{
"epoch": 7.7,
"learning_rate": 3.076023391812866e-05,
"loss": 0.0011,
"step": 2632
},
{
"epoch": 7.7,
"learning_rate": 3.074561403508772e-05,
"loss": 0.0,
"step": 2634
},
{
"epoch": 7.71,
"learning_rate": 3.073099415204678e-05,
"loss": 0.0004,
"step": 2636
},
{
"epoch": 7.71,
"learning_rate": 3.071637426900585e-05,
"loss": 0.0003,
"step": 2638
},
{
"epoch": 7.72,
"learning_rate": 3.0701754385964913e-05,
"loss": 0.0341,
"step": 2640
},
{
"epoch": 7.73,
"learning_rate": 3.0687134502923975e-05,
"loss": 0.0002,
"step": 2642
},
{
"epoch": 7.73,
"learning_rate": 3.0672514619883044e-05,
"loss": 0.0002,
"step": 2644
},
{
"epoch": 7.74,
"learning_rate": 3.0657894736842106e-05,
"loss": 0.0014,
"step": 2646
},
{
"epoch": 7.74,
"learning_rate": 3.0643274853801175e-05,
"loss": 0.0197,
"step": 2648
},
{
"epoch": 7.75,
"learning_rate": 3.062865497076024e-05,
"loss": 0.0158,
"step": 2650
},
{
"epoch": 7.75,
"learning_rate": 3.06140350877193e-05,
"loss": 0.0006,
"step": 2652
},
{
"epoch": 7.76,
"learning_rate": 3.059941520467837e-05,
"loss": 0.0007,
"step": 2654
},
{
"epoch": 7.77,
"learning_rate": 3.058479532163743e-05,
"loss": 0.0,
"step": 2656
},
{
"epoch": 7.77,
"learning_rate": 3.057017543859649e-05,
"loss": 0.0002,
"step": 2658
},
{
"epoch": 7.78,
"learning_rate": 3.055555555555556e-05,
"loss": 0.0052,
"step": 2660
},
{
"epoch": 7.78,
"learning_rate": 3.054093567251462e-05,
"loss": 0.0084,
"step": 2662
},
{
"epoch": 7.79,
"learning_rate": 3.0526315789473684e-05,
"loss": 0.0002,
"step": 2664
},
{
"epoch": 7.8,
"learning_rate": 3.0511695906432753e-05,
"loss": 0.0038,
"step": 2666
},
{
"epoch": 7.8,
"learning_rate": 3.0497076023391812e-05,
"loss": 0.0004,
"step": 2668
},
{
"epoch": 7.81,
"learning_rate": 3.048245614035088e-05,
"loss": 0.0001,
"step": 2670
},
{
"epoch": 7.81,
"learning_rate": 3.0467836257309946e-05,
"loss": 0.0009,
"step": 2672
},
{
"epoch": 7.82,
"learning_rate": 3.0453216374269005e-05,
"loss": 0.0291,
"step": 2674
},
{
"epoch": 7.82,
"learning_rate": 3.0438596491228073e-05,
"loss": 0.0054,
"step": 2676
},
{
"epoch": 7.83,
"learning_rate": 3.042397660818714e-05,
"loss": 0.0414,
"step": 2678
},
{
"epoch": 7.84,
"learning_rate": 3.0409356725146197e-05,
"loss": 0.5572,
"step": 2680
},
{
"epoch": 7.84,
"learning_rate": 3.0394736842105266e-05,
"loss": 0.0002,
"step": 2682
},
{
"epoch": 7.85,
"learning_rate": 3.038011695906433e-05,
"loss": 0.0478,
"step": 2684
},
{
"epoch": 7.85,
"learning_rate": 3.036549707602339e-05,
"loss": 0.0003,
"step": 2686
},
{
"epoch": 7.86,
"learning_rate": 3.035087719298246e-05,
"loss": 0.002,
"step": 2688
},
{
"epoch": 7.87,
"learning_rate": 3.0336257309941524e-05,
"loss": 0.0001,
"step": 2690
},
{
"epoch": 7.87,
"learning_rate": 3.0321637426900583e-05,
"loss": 0.0072,
"step": 2692
},
{
"epoch": 7.88,
"learning_rate": 3.030701754385965e-05,
"loss": 0.0814,
"step": 2694
},
{
"epoch": 7.88,
"learning_rate": 3.0292397660818717e-05,
"loss": 0.0037,
"step": 2696
},
{
"epoch": 7.89,
"learning_rate": 3.0277777777777776e-05,
"loss": 0.0297,
"step": 2698
},
{
"epoch": 7.89,
"learning_rate": 3.0263157894736844e-05,
"loss": 0.003,
"step": 2700
},
{
"epoch": 7.9,
"learning_rate": 3.024853801169591e-05,
"loss": 0.0009,
"step": 2702
},
{
"epoch": 7.91,
"learning_rate": 3.023391812865497e-05,
"loss": 0.0001,
"step": 2704
},
{
"epoch": 7.91,
"learning_rate": 3.0219298245614037e-05,
"loss": 0.0018,
"step": 2706
},
{
"epoch": 7.92,
"learning_rate": 3.0204678362573102e-05,
"loss": 0.0005,
"step": 2708
},
{
"epoch": 7.92,
"learning_rate": 3.0190058479532164e-05,
"loss": 0.0002,
"step": 2710
},
{
"epoch": 7.93,
"learning_rate": 3.017543859649123e-05,
"loss": 0.0313,
"step": 2712
},
{
"epoch": 7.94,
"learning_rate": 3.0160818713450295e-05,
"loss": 0.0001,
"step": 2714
},
{
"epoch": 7.94,
"learning_rate": 3.0146198830409357e-05,
"loss": 0.1735,
"step": 2716
},
{
"epoch": 7.95,
"learning_rate": 3.0131578947368423e-05,
"loss": 0.0003,
"step": 2718
},
{
"epoch": 7.95,
"learning_rate": 3.0116959064327488e-05,
"loss": 0.0027,
"step": 2720
},
{
"epoch": 7.96,
"learning_rate": 3.010233918128655e-05,
"loss": 0.0015,
"step": 2722
},
{
"epoch": 7.96,
"learning_rate": 3.0087719298245615e-05,
"loss": 0.0176,
"step": 2724
},
{
"epoch": 7.97,
"learning_rate": 3.007309941520468e-05,
"loss": 0.0001,
"step": 2726
},
{
"epoch": 7.98,
"learning_rate": 3.0058479532163746e-05,
"loss": 0.0008,
"step": 2728
},
{
"epoch": 7.98,
"learning_rate": 3.0043859649122808e-05,
"loss": 0.2544,
"step": 2730
},
{
"epoch": 7.99,
"learning_rate": 3.0029239766081873e-05,
"loss": 0.0003,
"step": 2732
},
{
"epoch": 7.99,
"learning_rate": 3.001461988304094e-05,
"loss": 0.0034,
"step": 2734
},
{
"epoch": 8.0,
"learning_rate": 3e-05,
"loss": 0.0001,
"step": 2736
},
{
"epoch": 8.0,
"eval_bleu": 0.4451016819486545,
"eval_loss": 1.4097394943237305,
"eval_runtime": 37.2049,
"eval_samples_per_second": 9.004,
"eval_steps_per_second": 2.258,
"step": 2736
},
{
"epoch": 8.01,
"learning_rate": 2.9985380116959066e-05,
"loss": 0.0002,
"step": 2738
},
{
"epoch": 8.01,
"learning_rate": 2.997076023391813e-05,
"loss": 0.0003,
"step": 2740
},
{
"epoch": 8.02,
"learning_rate": 2.9956140350877194e-05,
"loss": 0.0002,
"step": 2742
},
{
"epoch": 8.02,
"learning_rate": 2.994152046783626e-05,
"loss": 0.0002,
"step": 2744
},
{
"epoch": 8.03,
"learning_rate": 2.9926900584795324e-05,
"loss": 0.0044,
"step": 2746
},
{
"epoch": 8.04,
"learning_rate": 2.9912280701754386e-05,
"loss": 0.0001,
"step": 2748
},
{
"epoch": 8.04,
"learning_rate": 2.989766081871345e-05,
"loss": 0.0008,
"step": 2750
},
{
"epoch": 8.05,
"learning_rate": 2.9883040935672517e-05,
"loss": 0.0001,
"step": 2752
},
{
"epoch": 8.05,
"learning_rate": 2.986842105263158e-05,
"loss": 0.0023,
"step": 2754
},
{
"epoch": 8.06,
"learning_rate": 2.9853801169590644e-05,
"loss": 0.0005,
"step": 2756
},
{
"epoch": 8.06,
"learning_rate": 2.983918128654971e-05,
"loss": 0.0023,
"step": 2758
},
{
"epoch": 8.07,
"learning_rate": 2.9824561403508772e-05,
"loss": 0.063,
"step": 2760
},
{
"epoch": 8.08,
"learning_rate": 2.9809941520467837e-05,
"loss": 0.0241,
"step": 2762
},
{
"epoch": 8.08,
"learning_rate": 2.9795321637426903e-05,
"loss": 0.002,
"step": 2764
},
{
"epoch": 8.09,
"learning_rate": 2.9780701754385965e-05,
"loss": 0.0216,
"step": 2766
},
{
"epoch": 8.09,
"learning_rate": 2.976608187134503e-05,
"loss": 0.0005,
"step": 2768
},
{
"epoch": 8.1,
"learning_rate": 2.9751461988304095e-05,
"loss": 0.0034,
"step": 2770
},
{
"epoch": 8.11,
"learning_rate": 2.9736842105263157e-05,
"loss": 0.0029,
"step": 2772
},
{
"epoch": 8.11,
"learning_rate": 2.9722222222222223e-05,
"loss": 0.0004,
"step": 2774
},
{
"epoch": 8.12,
"learning_rate": 2.9707602339181288e-05,
"loss": 0.0,
"step": 2776
},
{
"epoch": 8.12,
"learning_rate": 2.969298245614035e-05,
"loss": 0.0001,
"step": 2778
},
{
"epoch": 8.13,
"learning_rate": 2.9678362573099415e-05,
"loss": 0.0006,
"step": 2780
},
{
"epoch": 8.13,
"learning_rate": 2.9663742690058484e-05,
"loss": 0.0,
"step": 2782
},
{
"epoch": 8.14,
"learning_rate": 2.9649122807017543e-05,
"loss": 0.0002,
"step": 2784
},
{
"epoch": 8.15,
"learning_rate": 2.9634502923976608e-05,
"loss": 0.0003,
"step": 2786
},
{
"epoch": 8.15,
"learning_rate": 2.9619883040935677e-05,
"loss": 0.0011,
"step": 2788
},
{
"epoch": 8.16,
"learning_rate": 2.9605263157894735e-05,
"loss": 0.0016,
"step": 2790
},
{
"epoch": 8.16,
"learning_rate": 2.95906432748538e-05,
"loss": 0.0228,
"step": 2792
},
{
"epoch": 8.17,
"learning_rate": 2.957602339181287e-05,
"loss": 0.0006,
"step": 2794
},
{
"epoch": 8.18,
"learning_rate": 2.9561403508771928e-05,
"loss": 0.0053,
"step": 2796
},
{
"epoch": 8.18,
"learning_rate": 2.9546783625730994e-05,
"loss": 0.0001,
"step": 2798
},
{
"epoch": 8.19,
"learning_rate": 2.9532163742690062e-05,
"loss": 0.0005,
"step": 2800
},
{
"epoch": 8.19,
"learning_rate": 2.951754385964912e-05,
"loss": 0.0011,
"step": 2802
},
{
"epoch": 8.2,
"learning_rate": 2.9502923976608186e-05,
"loss": 0.001,
"step": 2804
},
{
"epoch": 8.2,
"learning_rate": 2.9488304093567255e-05,
"loss": 0.0003,
"step": 2806
},
{
"epoch": 8.21,
"learning_rate": 2.9473684210526314e-05,
"loss": 0.0003,
"step": 2808
},
{
"epoch": 8.22,
"learning_rate": 2.945906432748538e-05,
"loss": 0.0003,
"step": 2810
},
{
"epoch": 8.22,
"learning_rate": 2.9444444444444448e-05,
"loss": 0.0116,
"step": 2812
},
{
"epoch": 8.23,
"learning_rate": 2.9429824561403513e-05,
"loss": 0.0072,
"step": 2814
},
{
"epoch": 8.23,
"learning_rate": 2.9415204678362572e-05,
"loss": 0.0891,
"step": 2816
},
{
"epoch": 8.24,
"learning_rate": 2.940058479532164e-05,
"loss": 0.0001,
"step": 2818
},
{
"epoch": 8.25,
"learning_rate": 2.9385964912280706e-05,
"loss": 0.0068,
"step": 2820
},
{
"epoch": 8.25,
"learning_rate": 2.9371345029239765e-05,
"loss": 0.0021,
"step": 2822
},
{
"epoch": 8.26,
"learning_rate": 2.9356725146198833e-05,
"loss": 0.0013,
"step": 2824
},
{
"epoch": 8.26,
"learning_rate": 2.93421052631579e-05,
"loss": 0.0002,
"step": 2826
},
{
"epoch": 8.27,
"learning_rate": 2.932748538011696e-05,
"loss": 0.0,
"step": 2828
},
{
"epoch": 8.27,
"learning_rate": 2.9312865497076026e-05,
"loss": 0.0015,
"step": 2830
},
{
"epoch": 8.28,
"learning_rate": 2.929824561403509e-05,
"loss": 0.003,
"step": 2832
},
{
"epoch": 8.29,
"learning_rate": 2.9283625730994154e-05,
"loss": 0.0102,
"step": 2834
},
{
"epoch": 8.29,
"learning_rate": 2.926900584795322e-05,
"loss": 0.0173,
"step": 2836
},
{
"epoch": 8.3,
"learning_rate": 2.9254385964912284e-05,
"loss": 0.0001,
"step": 2838
},
{
"epoch": 8.3,
"learning_rate": 2.9239766081871346e-05,
"loss": 0.0358,
"step": 2840
},
{
"epoch": 8.31,
"learning_rate": 2.922514619883041e-05,
"loss": 0.0045,
"step": 2842
},
{
"epoch": 8.32,
"learning_rate": 2.9210526315789477e-05,
"loss": 0.0003,
"step": 2844
},
{
"epoch": 8.32,
"learning_rate": 2.919590643274854e-05,
"loss": 0.0282,
"step": 2846
},
{
"epoch": 8.33,
"learning_rate": 2.9181286549707604e-05,
"loss": 0.0078,
"step": 2848
},
{
"epoch": 8.33,
"learning_rate": 2.916666666666667e-05,
"loss": 0.0001,
"step": 2850
},
{
"epoch": 8.34,
"learning_rate": 2.9152046783625732e-05,
"loss": 0.1327,
"step": 2852
},
{
"epoch": 8.35,
"learning_rate": 2.9137426900584797e-05,
"loss": 0.2603,
"step": 2854
},
{
"epoch": 8.35,
"learning_rate": 2.9122807017543863e-05,
"loss": 0.019,
"step": 2856
},
{
"epoch": 8.36,
"learning_rate": 2.9108187134502924e-05,
"loss": 0.0009,
"step": 2858
},
{
"epoch": 8.36,
"learning_rate": 2.909356725146199e-05,
"loss": 0.0203,
"step": 2860
},
{
"epoch": 8.37,
"learning_rate": 2.9078947368421055e-05,
"loss": 0.0007,
"step": 2862
},
{
"epoch": 8.37,
"learning_rate": 2.9064327485380117e-05,
"loss": 0.0002,
"step": 2864
},
{
"epoch": 8.38,
"learning_rate": 2.9049707602339183e-05,
"loss": 0.0003,
"step": 2866
},
{
"epoch": 8.39,
"learning_rate": 2.9035087719298248e-05,
"loss": 0.0004,
"step": 2868
},
{
"epoch": 8.39,
"learning_rate": 2.902046783625731e-05,
"loss": 0.017,
"step": 2870
},
{
"epoch": 8.4,
"learning_rate": 2.9005847953216375e-05,
"loss": 0.0015,
"step": 2872
},
{
"epoch": 8.4,
"learning_rate": 2.899122807017544e-05,
"loss": 0.0019,
"step": 2874
},
{
"epoch": 8.41,
"learning_rate": 2.8976608187134503e-05,
"loss": 0.0017,
"step": 2876
},
{
"epoch": 8.42,
"learning_rate": 2.8961988304093568e-05,
"loss": 0.0145,
"step": 2878
},
{
"epoch": 8.42,
"learning_rate": 2.8947368421052634e-05,
"loss": 0.0004,
"step": 2880
},
{
"epoch": 8.43,
"learning_rate": 2.8932748538011695e-05,
"loss": 0.001,
"step": 2882
},
{
"epoch": 8.43,
"learning_rate": 2.891812865497076e-05,
"loss": 0.0023,
"step": 2884
},
{
"epoch": 8.44,
"learning_rate": 2.8903508771929826e-05,
"loss": 0.0001,
"step": 2886
},
{
"epoch": 8.44,
"learning_rate": 2.8888888888888888e-05,
"loss": 0.0014,
"step": 2888
},
{
"epoch": 8.45,
"learning_rate": 2.8874269005847954e-05,
"loss": 0.0,
"step": 2890
},
{
"epoch": 8.46,
"learning_rate": 2.885964912280702e-05,
"loss": 0.0003,
"step": 2892
},
{
"epoch": 8.46,
"learning_rate": 2.8845029239766084e-05,
"loss": 0.0,
"step": 2894
},
{
"epoch": 8.47,
"learning_rate": 2.8830409356725146e-05,
"loss": 0.0001,
"step": 2896
},
{
"epoch": 8.47,
"learning_rate": 2.8815789473684212e-05,
"loss": 0.0004,
"step": 2898
},
{
"epoch": 8.48,
"learning_rate": 2.8801169590643277e-05,
"loss": 0.0001,
"step": 2900
},
{
"epoch": 8.49,
"learning_rate": 2.878654970760234e-05,
"loss": 0.0,
"step": 2902
},
{
"epoch": 8.49,
"learning_rate": 2.8771929824561404e-05,
"loss": 0.0001,
"step": 2904
},
{
"epoch": 8.5,
"learning_rate": 2.8757309941520473e-05,
"loss": 0.0004,
"step": 2906
},
{
"epoch": 8.5,
"learning_rate": 2.8742690058479532e-05,
"loss": 0.0002,
"step": 2908
},
{
"epoch": 8.51,
"learning_rate": 2.8728070175438597e-05,
"loss": 0.0017,
"step": 2910
},
{
"epoch": 8.51,
"learning_rate": 2.8713450292397666e-05,
"loss": 0.0001,
"step": 2912
},
{
"epoch": 8.52,
"learning_rate": 2.8698830409356725e-05,
"loss": 0.0501,
"step": 2914
},
{
"epoch": 8.53,
"learning_rate": 2.868421052631579e-05,
"loss": 0.0,
"step": 2916
},
{
"epoch": 8.53,
"learning_rate": 2.866959064327486e-05,
"loss": 0.0002,
"step": 2918
},
{
"epoch": 8.54,
"learning_rate": 2.8654970760233917e-05,
"loss": 0.0008,
"step": 2920
},
{
"epoch": 8.54,
"learning_rate": 2.8640350877192983e-05,
"loss": 0.0,
"step": 2922
},
{
"epoch": 8.55,
"learning_rate": 2.862573099415205e-05,
"loss": 0.0008,
"step": 2924
},
{
"epoch": 8.56,
"learning_rate": 2.861111111111111e-05,
"loss": 0.0002,
"step": 2926
},
{
"epoch": 8.56,
"learning_rate": 2.8596491228070175e-05,
"loss": 0.0001,
"step": 2928
},
{
"epoch": 8.57,
"learning_rate": 2.8581871345029244e-05,
"loss": 0.1903,
"step": 2930
},
{
"epoch": 8.57,
"learning_rate": 2.8567251461988303e-05,
"loss": 0.0027,
"step": 2932
},
{
"epoch": 8.58,
"learning_rate": 2.8552631578947368e-05,
"loss": 0.0016,
"step": 2934
},
{
"epoch": 8.58,
"learning_rate": 2.8538011695906437e-05,
"loss": 0.0347,
"step": 2936
},
{
"epoch": 8.59,
"learning_rate": 2.8523391812865496e-05,
"loss": 0.0002,
"step": 2938
},
{
"epoch": 8.6,
"learning_rate": 2.850877192982456e-05,
"loss": 0.0,
"step": 2940
},
{
"epoch": 8.6,
"learning_rate": 2.849415204678363e-05,
"loss": 0.0811,
"step": 2942
},
{
"epoch": 8.61,
"learning_rate": 2.847953216374269e-05,
"loss": 0.0004,
"step": 2944
},
{
"epoch": 8.61,
"learning_rate": 2.8464912280701754e-05,
"loss": 0.035,
"step": 2946
},
{
"epoch": 8.62,
"learning_rate": 2.8450292397660823e-05,
"loss": 0.1327,
"step": 2948
},
{
"epoch": 8.63,
"learning_rate": 2.843567251461988e-05,
"loss": 0.0009,
"step": 2950
},
{
"epoch": 8.63,
"learning_rate": 2.842105263157895e-05,
"loss": 0.0063,
"step": 2952
},
{
"epoch": 8.64,
"learning_rate": 2.8406432748538015e-05,
"loss": 0.0033,
"step": 2954
},
{
"epoch": 8.64,
"learning_rate": 2.8391812865497074e-05,
"loss": 0.0001,
"step": 2956
},
{
"epoch": 8.65,
"learning_rate": 2.8377192982456143e-05,
"loss": 0.072,
"step": 2958
},
{
"epoch": 8.65,
"learning_rate": 2.8362573099415208e-05,
"loss": 0.0004,
"step": 2960
},
{
"epoch": 8.66,
"learning_rate": 2.8347953216374267e-05,
"loss": 0.0005,
"step": 2962
},
{
"epoch": 8.67,
"learning_rate": 2.8333333333333335e-05,
"loss": 0.2246,
"step": 2964
},
{
"epoch": 8.67,
"learning_rate": 2.83187134502924e-05,
"loss": 0.0001,
"step": 2966
},
{
"epoch": 8.68,
"learning_rate": 2.830409356725146e-05,
"loss": 0.0001,
"step": 2968
},
{
"epoch": 8.68,
"learning_rate": 2.8289473684210528e-05,
"loss": 0.0001,
"step": 2970
},
{
"epoch": 8.69,
"learning_rate": 2.8274853801169593e-05,
"loss": 0.006,
"step": 2972
},
{
"epoch": 8.7,
"learning_rate": 2.826023391812866e-05,
"loss": 0.0001,
"step": 2974
},
{
"epoch": 8.7,
"learning_rate": 2.824561403508772e-05,
"loss": 0.0047,
"step": 2976
},
{
"epoch": 8.71,
"learning_rate": 2.8230994152046786e-05,
"loss": 0.0124,
"step": 2978
},
{
"epoch": 8.71,
"learning_rate": 2.821637426900585e-05,
"loss": 0.019,
"step": 2980
},
{
"epoch": 8.72,
"learning_rate": 2.8201754385964914e-05,
"loss": 0.0012,
"step": 2982
},
{
"epoch": 8.73,
"learning_rate": 2.818713450292398e-05,
"loss": 0.0007,
"step": 2984
},
{
"epoch": 8.73,
"learning_rate": 2.8172514619883044e-05,
"loss": 0.0001,
"step": 2986
},
{
"epoch": 8.74,
"learning_rate": 2.8157894736842106e-05,
"loss": 0.0454,
"step": 2988
},
{
"epoch": 8.74,
"learning_rate": 2.8143274853801172e-05,
"loss": 0.0327,
"step": 2990
},
{
"epoch": 8.75,
"learning_rate": 2.8128654970760237e-05,
"loss": 0.0377,
"step": 2992
},
{
"epoch": 8.75,
"learning_rate": 2.81140350877193e-05,
"loss": 0.0,
"step": 2994
},
{
"epoch": 8.76,
"learning_rate": 2.8099415204678364e-05,
"loss": 0.0127,
"step": 2996
},
{
"epoch": 8.77,
"learning_rate": 2.808479532163743e-05,
"loss": 0.0559,
"step": 2998
},
{
"epoch": 8.77,
"learning_rate": 2.8070175438596492e-05,
"loss": 0.003,
"step": 3000
},
{
"epoch": 8.78,
"learning_rate": 2.8055555555555557e-05,
"loss": 0.0058,
"step": 3002
},
{
"epoch": 8.78,
"learning_rate": 2.8040935672514623e-05,
"loss": 0.0688,
"step": 3004
},
{
"epoch": 8.79,
"learning_rate": 2.8026315789473685e-05,
"loss": 0.0071,
"step": 3006
},
{
"epoch": 8.8,
"learning_rate": 2.801169590643275e-05,
"loss": 0.1582,
"step": 3008
},
{
"epoch": 8.8,
"learning_rate": 2.7997076023391815e-05,
"loss": 0.0056,
"step": 3010
},
{
"epoch": 8.81,
"learning_rate": 2.7982456140350877e-05,
"loss": 0.0012,
"step": 3012
},
{
"epoch": 8.81,
"learning_rate": 2.7967836257309943e-05,
"loss": 0.0357,
"step": 3014
},
{
"epoch": 8.82,
"learning_rate": 2.7953216374269008e-05,
"loss": 0.0,
"step": 3016
},
{
"epoch": 8.82,
"learning_rate": 2.793859649122807e-05,
"loss": 0.0701,
"step": 3018
},
{
"epoch": 8.83,
"learning_rate": 2.7923976608187135e-05,
"loss": 0.0001,
"step": 3020
},
{
"epoch": 8.84,
"learning_rate": 2.79093567251462e-05,
"loss": 0.0036,
"step": 3022
},
{
"epoch": 8.84,
"learning_rate": 2.7894736842105263e-05,
"loss": 0.002,
"step": 3024
},
{
"epoch": 8.85,
"learning_rate": 2.7880116959064328e-05,
"loss": 0.0473,
"step": 3026
},
{
"epoch": 8.85,
"learning_rate": 2.7865497076023394e-05,
"loss": 0.0001,
"step": 3028
},
{
"epoch": 8.86,
"learning_rate": 2.7850877192982456e-05,
"loss": 0.2105,
"step": 3030
},
{
"epoch": 8.87,
"learning_rate": 2.783625730994152e-05,
"loss": 0.0001,
"step": 3032
},
{
"epoch": 8.87,
"learning_rate": 2.7821637426900586e-05,
"loss": 0.0171,
"step": 3034
},
{
"epoch": 8.88,
"learning_rate": 2.780701754385965e-05,
"loss": 0.0217,
"step": 3036
},
{
"epoch": 8.88,
"learning_rate": 2.7792397660818714e-05,
"loss": 0.0003,
"step": 3038
},
{
"epoch": 8.89,
"learning_rate": 2.777777777777778e-05,
"loss": 0.0001,
"step": 3040
},
{
"epoch": 8.89,
"learning_rate": 2.776315789473684e-05,
"loss": 0.0001,
"step": 3042
},
{
"epoch": 8.9,
"learning_rate": 2.7748538011695906e-05,
"loss": 0.0013,
"step": 3044
},
{
"epoch": 8.91,
"learning_rate": 2.7733918128654972e-05,
"loss": 0.0995,
"step": 3046
},
{
"epoch": 8.91,
"learning_rate": 2.7719298245614034e-05,
"loss": 0.0362,
"step": 3048
},
{
"epoch": 8.92,
"learning_rate": 2.77046783625731e-05,
"loss": 0.0003,
"step": 3050
},
{
"epoch": 8.92,
"learning_rate": 2.7690058479532165e-05,
"loss": 0.0004,
"step": 3052
},
{
"epoch": 8.93,
"learning_rate": 2.7675438596491233e-05,
"loss": 0.0063,
"step": 3054
},
{
"epoch": 8.94,
"learning_rate": 2.7660818713450292e-05,
"loss": 0.0001,
"step": 3056
},
{
"epoch": 8.94,
"learning_rate": 2.7646198830409357e-05,
"loss": 0.0065,
"step": 3058
},
{
"epoch": 8.95,
"learning_rate": 2.7631578947368426e-05,
"loss": 0.0,
"step": 3060
},
{
"epoch": 8.95,
"learning_rate": 2.7616959064327485e-05,
"loss": 0.0003,
"step": 3062
},
{
"epoch": 8.96,
"learning_rate": 2.760233918128655e-05,
"loss": 0.0001,
"step": 3064
},
{
"epoch": 8.96,
"learning_rate": 2.758771929824562e-05,
"loss": 0.0004,
"step": 3066
},
{
"epoch": 8.97,
"learning_rate": 2.7573099415204677e-05,
"loss": 0.0002,
"step": 3068
},
{
"epoch": 8.98,
"learning_rate": 2.7558479532163746e-05,
"loss": 0.0002,
"step": 3070
},
{
"epoch": 8.98,
"learning_rate": 2.754385964912281e-05,
"loss": 0.0002,
"step": 3072
},
{
"epoch": 8.99,
"learning_rate": 2.752923976608187e-05,
"loss": 0.0004,
"step": 3074
},
{
"epoch": 8.99,
"learning_rate": 2.751461988304094e-05,
"loss": 0.0004,
"step": 3076
},
{
"epoch": 9.0,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0003,
"step": 3078
},
{
"epoch": 9.0,
"eval_bleu": 0.5039349338756257,
"eval_loss": 1.4240442514419556,
"eval_runtime": 36.5251,
"eval_samples_per_second": 9.172,
"eval_steps_per_second": 2.3,
"step": 3078
},
{
"epoch": 9.01,
"learning_rate": 2.7485380116959063e-05,
"loss": 0.0,
"step": 3080
},
{
"epoch": 9.01,
"learning_rate": 2.7470760233918132e-05,
"loss": 0.0036,
"step": 3082
},
{
"epoch": 9.02,
"learning_rate": 2.7456140350877197e-05,
"loss": 0.0005,
"step": 3084
},
{
"epoch": 9.02,
"learning_rate": 2.7441520467836256e-05,
"loss": 0.0369,
"step": 3086
},
{
"epoch": 9.03,
"learning_rate": 2.7426900584795324e-05,
"loss": 0.0253,
"step": 3088
},
{
"epoch": 9.04,
"learning_rate": 2.741228070175439e-05,
"loss": 0.0465,
"step": 3090
},
{
"epoch": 9.04,
"learning_rate": 2.739766081871345e-05,
"loss": 0.0002,
"step": 3092
},
{
"epoch": 9.05,
"learning_rate": 2.7383040935672517e-05,
"loss": 0.0004,
"step": 3094
},
{
"epoch": 9.05,
"learning_rate": 2.7368421052631583e-05,
"loss": 0.0001,
"step": 3096
},
{
"epoch": 9.06,
"learning_rate": 2.735380116959064e-05,
"loss": 0.004,
"step": 3098
},
{
"epoch": 9.06,
"learning_rate": 2.733918128654971e-05,
"loss": 0.014,
"step": 3100
},
{
"epoch": 9.07,
"learning_rate": 2.7324561403508775e-05,
"loss": 0.0069,
"step": 3102
},
{
"epoch": 9.08,
"learning_rate": 2.7309941520467834e-05,
"loss": 0.0,
"step": 3104
},
{
"epoch": 9.08,
"learning_rate": 2.7295321637426903e-05,
"loss": 0.0,
"step": 3106
},
{
"epoch": 9.09,
"learning_rate": 2.7280701754385968e-05,
"loss": 0.0001,
"step": 3108
},
{
"epoch": 9.09,
"learning_rate": 2.7266081871345027e-05,
"loss": 0.0051,
"step": 3110
},
{
"epoch": 9.1,
"learning_rate": 2.7251461988304095e-05,
"loss": 0.0,
"step": 3112
},
{
"epoch": 9.11,
"learning_rate": 2.723684210526316e-05,
"loss": 0.0002,
"step": 3114
},
{
"epoch": 9.11,
"learning_rate": 2.7222222222222223e-05,
"loss": 0.0002,
"step": 3116
},
{
"epoch": 9.12,
"learning_rate": 2.7207602339181288e-05,
"loss": 0.0006,
"step": 3118
},
{
"epoch": 9.12,
"learning_rate": 2.7192982456140354e-05,
"loss": 0.0017,
"step": 3120
},
{
"epoch": 9.13,
"learning_rate": 2.7178362573099416e-05,
"loss": 0.0005,
"step": 3122
},
{
"epoch": 9.13,
"learning_rate": 2.716374269005848e-05,
"loss": 0.0092,
"step": 3124
},
{
"epoch": 9.14,
"learning_rate": 2.7149122807017546e-05,
"loss": 0.005,
"step": 3126
},
{
"epoch": 9.15,
"learning_rate": 2.713450292397661e-05,
"loss": 0.0008,
"step": 3128
},
{
"epoch": 9.15,
"learning_rate": 2.7119883040935674e-05,
"loss": 0.0002,
"step": 3130
},
{
"epoch": 9.16,
"learning_rate": 2.710526315789474e-05,
"loss": 0.0004,
"step": 3132
},
{
"epoch": 9.16,
"learning_rate": 2.70906432748538e-05,
"loss": 0.0044,
"step": 3134
},
{
"epoch": 9.17,
"learning_rate": 2.7076023391812866e-05,
"loss": 0.0001,
"step": 3136
},
{
"epoch": 9.18,
"learning_rate": 2.7061403508771932e-05,
"loss": 0.2657,
"step": 3138
},
{
"epoch": 9.18,
"learning_rate": 2.7046783625730997e-05,
"loss": 0.0109,
"step": 3140
},
{
"epoch": 9.19,
"learning_rate": 2.703216374269006e-05,
"loss": 0.0032,
"step": 3142
},
{
"epoch": 9.19,
"learning_rate": 2.7017543859649125e-05,
"loss": 0.0003,
"step": 3144
},
{
"epoch": 9.2,
"learning_rate": 2.700292397660819e-05,
"loss": 0.0,
"step": 3146
},
{
"epoch": 9.2,
"learning_rate": 2.6988304093567252e-05,
"loss": 0.0007,
"step": 3148
},
{
"epoch": 9.21,
"learning_rate": 2.6973684210526317e-05,
"loss": 0.0002,
"step": 3150
},
{
"epoch": 9.22,
"learning_rate": 2.6959064327485383e-05,
"loss": 0.0126,
"step": 3152
},
{
"epoch": 9.22,
"learning_rate": 2.6944444444444445e-05,
"loss": 0.0019,
"step": 3154
},
{
"epoch": 9.23,
"learning_rate": 2.692982456140351e-05,
"loss": 0.0244,
"step": 3156
},
{
"epoch": 9.23,
"learning_rate": 2.6915204678362575e-05,
"loss": 0.0462,
"step": 3158
},
{
"epoch": 9.24,
"learning_rate": 2.6900584795321637e-05,
"loss": 0.0002,
"step": 3160
},
{
"epoch": 9.25,
"learning_rate": 2.6885964912280703e-05,
"loss": 0.015,
"step": 3162
},
{
"epoch": 9.25,
"learning_rate": 2.6871345029239768e-05,
"loss": 0.0003,
"step": 3164
},
{
"epoch": 9.26,
"learning_rate": 2.685672514619883e-05,
"loss": 0.0101,
"step": 3166
},
{
"epoch": 9.26,
"learning_rate": 2.6842105263157896e-05,
"loss": 0.0003,
"step": 3168
},
{
"epoch": 9.27,
"learning_rate": 2.682748538011696e-05,
"loss": 0.002,
"step": 3170
},
{
"epoch": 9.27,
"learning_rate": 2.6812865497076023e-05,
"loss": 0.0023,
"step": 3172
},
{
"epoch": 9.28,
"learning_rate": 2.679824561403509e-05,
"loss": 0.1328,
"step": 3174
},
{
"epoch": 9.29,
"learning_rate": 2.6783625730994154e-05,
"loss": 0.0015,
"step": 3176
},
{
"epoch": 9.29,
"learning_rate": 2.6769005847953216e-05,
"loss": 0.0001,
"step": 3178
},
{
"epoch": 9.3,
"learning_rate": 2.675438596491228e-05,
"loss": 0.0189,
"step": 3180
},
{
"epoch": 9.3,
"learning_rate": 2.6739766081871346e-05,
"loss": 0.0004,
"step": 3182
},
{
"epoch": 9.31,
"learning_rate": 2.672514619883041e-05,
"loss": 0.0022,
"step": 3184
},
{
"epoch": 9.32,
"learning_rate": 2.6710526315789474e-05,
"loss": 0.0,
"step": 3186
},
{
"epoch": 9.32,
"learning_rate": 2.669590643274854e-05,
"loss": 0.016,
"step": 3188
},
{
"epoch": 9.33,
"learning_rate": 2.66812865497076e-05,
"loss": 0.0002,
"step": 3190
},
{
"epoch": 9.33,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.0079,
"step": 3192
},
{
"epoch": 9.34,
"learning_rate": 2.6652046783625735e-05,
"loss": 0.0001,
"step": 3194
},
{
"epoch": 9.35,
"learning_rate": 2.6637426900584794e-05,
"loss": 0.0008,
"step": 3196
},
{
"epoch": 9.35,
"learning_rate": 2.662280701754386e-05,
"loss": 0.0009,
"step": 3198
},
{
"epoch": 9.36,
"learning_rate": 2.6608187134502928e-05,
"loss": 0.0002,
"step": 3200
},
{
"epoch": 9.36,
"learning_rate": 2.6593567251461987e-05,
"loss": 0.0045,
"step": 3202
},
{
"epoch": 9.37,
"learning_rate": 2.6578947368421052e-05,
"loss": 0.0002,
"step": 3204
},
{
"epoch": 9.37,
"learning_rate": 2.656432748538012e-05,
"loss": 0.0001,
"step": 3206
},
{
"epoch": 9.38,
"learning_rate": 2.654970760233918e-05,
"loss": 0.0049,
"step": 3208
},
{
"epoch": 9.39,
"learning_rate": 2.6535087719298245e-05,
"loss": 0.0056,
"step": 3210
},
{
"epoch": 9.39,
"learning_rate": 2.6520467836257314e-05,
"loss": 0.0001,
"step": 3212
},
{
"epoch": 9.4,
"learning_rate": 2.6505847953216372e-05,
"loss": 0.0,
"step": 3214
},
{
"epoch": 9.4,
"learning_rate": 2.6491228070175438e-05,
"loss": 0.0001,
"step": 3216
},
{
"epoch": 9.41,
"learning_rate": 2.6476608187134506e-05,
"loss": 0.0,
"step": 3218
},
{
"epoch": 9.42,
"learning_rate": 2.6461988304093572e-05,
"loss": 0.0004,
"step": 3220
},
{
"epoch": 9.42,
"learning_rate": 2.644736842105263e-05,
"loss": 0.0114,
"step": 3222
},
{
"epoch": 9.43,
"learning_rate": 2.64327485380117e-05,
"loss": 0.0004,
"step": 3224
},
{
"epoch": 9.43,
"learning_rate": 2.6418128654970764e-05,
"loss": 0.0003,
"step": 3226
},
{
"epoch": 9.44,
"learning_rate": 2.6403508771929823e-05,
"loss": 0.0018,
"step": 3228
},
{
"epoch": 9.44,
"learning_rate": 2.6388888888888892e-05,
"loss": 0.0001,
"step": 3230
},
{
"epoch": 9.45,
"learning_rate": 2.6374269005847957e-05,
"loss": 0.0017,
"step": 3232
},
{
"epoch": 9.46,
"learning_rate": 2.6359649122807016e-05,
"loss": 0.0,
"step": 3234
},
{
"epoch": 9.46,
"learning_rate": 2.6345029239766085e-05,
"loss": 0.0,
"step": 3236
},
{
"epoch": 9.47,
"learning_rate": 2.633040935672515e-05,
"loss": 0.0034,
"step": 3238
},
{
"epoch": 9.47,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.0001,
"step": 3240
},
{
"epoch": 9.48,
"learning_rate": 2.6301169590643277e-05,
"loss": 0.0006,
"step": 3242
},
{
"epoch": 9.49,
"learning_rate": 2.6286549707602343e-05,
"loss": 0.0026,
"step": 3244
},
{
"epoch": 9.49,
"learning_rate": 2.6271929824561405e-05,
"loss": 0.0001,
"step": 3246
},
{
"epoch": 9.5,
"learning_rate": 2.625730994152047e-05,
"loss": 0.0067,
"step": 3248
},
{
"epoch": 9.5,
"learning_rate": 2.6242690058479535e-05,
"loss": 0.0052,
"step": 3250
},
{
"epoch": 9.51,
"learning_rate": 2.6228070175438597e-05,
"loss": 0.0023,
"step": 3252
},
{
"epoch": 9.51,
"learning_rate": 2.6213450292397663e-05,
"loss": 0.0002,
"step": 3254
},
{
"epoch": 9.52,
"learning_rate": 2.6198830409356728e-05,
"loss": 0.0002,
"step": 3256
},
{
"epoch": 9.53,
"learning_rate": 2.618421052631579e-05,
"loss": 0.0272,
"step": 3258
},
{
"epoch": 9.53,
"learning_rate": 2.6169590643274856e-05,
"loss": 0.0003,
"step": 3260
},
{
"epoch": 9.54,
"learning_rate": 2.615497076023392e-05,
"loss": 0.0,
"step": 3262
},
{
"epoch": 9.54,
"learning_rate": 2.6140350877192983e-05,
"loss": 0.0003,
"step": 3264
},
{
"epoch": 9.55,
"learning_rate": 2.612573099415205e-05,
"loss": 0.0009,
"step": 3266
},
{
"epoch": 9.56,
"learning_rate": 2.6111111111111114e-05,
"loss": 0.0004,
"step": 3268
},
{
"epoch": 9.56,
"learning_rate": 2.6096491228070176e-05,
"loss": 0.0011,
"step": 3270
},
{
"epoch": 9.57,
"learning_rate": 2.608187134502924e-05,
"loss": 0.0082,
"step": 3272
},
{
"epoch": 9.57,
"learning_rate": 2.6067251461988306e-05,
"loss": 0.0451,
"step": 3274
},
{
"epoch": 9.58,
"learning_rate": 2.605263157894737e-05,
"loss": 0.0012,
"step": 3276
},
{
"epoch": 9.58,
"learning_rate": 2.6038011695906434e-05,
"loss": 0.0281,
"step": 3278
},
{
"epoch": 9.59,
"learning_rate": 2.60233918128655e-05,
"loss": 0.0002,
"step": 3280
},
{
"epoch": 9.6,
"learning_rate": 2.600877192982456e-05,
"loss": 0.0002,
"step": 3282
},
{
"epoch": 9.6,
"learning_rate": 2.5994152046783627e-05,
"loss": 0.0,
"step": 3284
},
{
"epoch": 9.61,
"learning_rate": 2.5979532163742692e-05,
"loss": 0.0839,
"step": 3286
},
{
"epoch": 9.61,
"learning_rate": 2.5964912280701754e-05,
"loss": 0.0191,
"step": 3288
},
{
"epoch": 9.62,
"learning_rate": 2.595029239766082e-05,
"loss": 0.0117,
"step": 3290
},
{
"epoch": 9.63,
"learning_rate": 2.5935672514619885e-05,
"loss": 0.0,
"step": 3292
},
{
"epoch": 9.63,
"learning_rate": 2.5921052631578947e-05,
"loss": 0.0011,
"step": 3294
},
{
"epoch": 9.64,
"learning_rate": 2.5906432748538012e-05,
"loss": 0.0012,
"step": 3296
},
{
"epoch": 9.64,
"learning_rate": 2.5891812865497077e-05,
"loss": 0.0002,
"step": 3298
},
{
"epoch": 9.65,
"learning_rate": 2.5877192982456143e-05,
"loss": 0.0003,
"step": 3300
},
{
"epoch": 9.65,
"learning_rate": 2.5862573099415205e-05,
"loss": 0.0012,
"step": 3302
},
{
"epoch": 9.66,
"learning_rate": 2.584795321637427e-05,
"loss": 0.0021,
"step": 3304
},
{
"epoch": 9.67,
"learning_rate": 2.5833333333333336e-05,
"loss": 0.0003,
"step": 3306
},
{
"epoch": 9.67,
"learning_rate": 2.5818713450292398e-05,
"loss": 0.0032,
"step": 3308
},
{
"epoch": 9.68,
"learning_rate": 2.5804093567251463e-05,
"loss": 0.0006,
"step": 3310
},
{
"epoch": 9.68,
"learning_rate": 2.578947368421053e-05,
"loss": 0.0002,
"step": 3312
},
{
"epoch": 9.69,
"learning_rate": 2.577485380116959e-05,
"loss": 0.0428,
"step": 3314
},
{
"epoch": 9.7,
"learning_rate": 2.5760233918128656e-05,
"loss": 0.0082,
"step": 3316
},
{
"epoch": 9.7,
"learning_rate": 2.5745614035087724e-05,
"loss": 0.0004,
"step": 3318
},
{
"epoch": 9.71,
"learning_rate": 2.5730994152046783e-05,
"loss": 0.018,
"step": 3320
},
{
"epoch": 9.71,
"learning_rate": 2.571637426900585e-05,
"loss": 0.0001,
"step": 3322
},
{
"epoch": 9.72,
"learning_rate": 2.5701754385964917e-05,
"loss": 0.0002,
"step": 3324
},
{
"epoch": 9.73,
"learning_rate": 2.5687134502923976e-05,
"loss": 0.0012,
"step": 3326
},
{
"epoch": 9.73,
"learning_rate": 2.567251461988304e-05,
"loss": 0.0114,
"step": 3328
},
{
"epoch": 9.74,
"learning_rate": 2.565789473684211e-05,
"loss": 0.0011,
"step": 3330
},
{
"epoch": 9.74,
"learning_rate": 2.564327485380117e-05,
"loss": 0.0002,
"step": 3332
},
{
"epoch": 9.75,
"learning_rate": 2.5628654970760234e-05,
"loss": 0.0137,
"step": 3334
},
{
"epoch": 9.75,
"learning_rate": 2.5614035087719303e-05,
"loss": 0.4712,
"step": 3336
},
{
"epoch": 9.76,
"learning_rate": 2.559941520467836e-05,
"loss": 0.2991,
"step": 3338
},
{
"epoch": 9.77,
"learning_rate": 2.5584795321637427e-05,
"loss": 0.0008,
"step": 3340
},
{
"epoch": 9.77,
"learning_rate": 2.5570175438596495e-05,
"loss": 0.0937,
"step": 3342
},
{
"epoch": 9.78,
"learning_rate": 2.5555555555555554e-05,
"loss": 0.0005,
"step": 3344
},
{
"epoch": 9.78,
"learning_rate": 2.554093567251462e-05,
"loss": 0.0081,
"step": 3346
},
{
"epoch": 9.79,
"learning_rate": 2.5526315789473688e-05,
"loss": 0.0003,
"step": 3348
},
{
"epoch": 9.8,
"learning_rate": 2.5511695906432747e-05,
"loss": 0.0002,
"step": 3350
},
{
"epoch": 9.8,
"learning_rate": 2.5497076023391812e-05,
"loss": 0.0026,
"step": 3352
},
{
"epoch": 9.81,
"learning_rate": 2.548245614035088e-05,
"loss": 0.0006,
"step": 3354
},
{
"epoch": 9.81,
"learning_rate": 2.546783625730994e-05,
"loss": 0.0001,
"step": 3356
},
{
"epoch": 9.82,
"learning_rate": 2.5453216374269005e-05,
"loss": 0.0023,
"step": 3358
},
{
"epoch": 9.82,
"learning_rate": 2.5438596491228074e-05,
"loss": 0.0061,
"step": 3360
},
{
"epoch": 9.83,
"learning_rate": 2.5423976608187132e-05,
"loss": 0.0002,
"step": 3362
},
{
"epoch": 9.84,
"learning_rate": 2.54093567251462e-05,
"loss": 0.0002,
"step": 3364
},
{
"epoch": 9.84,
"learning_rate": 2.5394736842105266e-05,
"loss": 0.0002,
"step": 3366
},
{
"epoch": 9.85,
"learning_rate": 2.5380116959064325e-05,
"loss": 0.0363,
"step": 3368
},
{
"epoch": 9.85,
"learning_rate": 2.5365497076023394e-05,
"loss": 0.001,
"step": 3370
},
{
"epoch": 9.86,
"learning_rate": 2.535087719298246e-05,
"loss": 0.0001,
"step": 3372
},
{
"epoch": 9.87,
"learning_rate": 2.5336257309941518e-05,
"loss": 0.0,
"step": 3374
},
{
"epoch": 9.87,
"learning_rate": 2.5321637426900587e-05,
"loss": 0.0013,
"step": 3376
},
{
"epoch": 9.88,
"learning_rate": 2.5307017543859652e-05,
"loss": 0.0001,
"step": 3378
},
{
"epoch": 9.88,
"learning_rate": 2.5292397660818717e-05,
"loss": 0.0003,
"step": 3380
},
{
"epoch": 9.89,
"learning_rate": 2.527777777777778e-05,
"loss": 0.001,
"step": 3382
},
{
"epoch": 9.89,
"learning_rate": 2.5263157894736845e-05,
"loss": 0.0,
"step": 3384
},
{
"epoch": 9.9,
"learning_rate": 2.524853801169591e-05,
"loss": 0.001,
"step": 3386
},
{
"epoch": 9.91,
"learning_rate": 2.5233918128654972e-05,
"loss": 0.0012,
"step": 3388
},
{
"epoch": 9.91,
"learning_rate": 2.5219298245614037e-05,
"loss": 0.0249,
"step": 3390
},
{
"epoch": 9.92,
"learning_rate": 2.5204678362573103e-05,
"loss": 0.0088,
"step": 3392
},
{
"epoch": 9.92,
"learning_rate": 2.5190058479532165e-05,
"loss": 0.0027,
"step": 3394
},
{
"epoch": 9.93,
"learning_rate": 2.517543859649123e-05,
"loss": 0.0001,
"step": 3396
},
{
"epoch": 9.94,
"learning_rate": 2.5160818713450296e-05,
"loss": 0.0012,
"step": 3398
},
{
"epoch": 9.94,
"learning_rate": 2.5146198830409358e-05,
"loss": 0.0002,
"step": 3400
},
{
"epoch": 9.95,
"learning_rate": 2.5131578947368423e-05,
"loss": 0.0005,
"step": 3402
},
{
"epoch": 9.95,
"learning_rate": 2.511695906432749e-05,
"loss": 0.0001,
"step": 3404
},
{
"epoch": 9.96,
"learning_rate": 2.510233918128655e-05,
"loss": 0.0093,
"step": 3406
},
{
"epoch": 9.96,
"learning_rate": 2.5087719298245616e-05,
"loss": 0.0001,
"step": 3408
},
{
"epoch": 9.97,
"learning_rate": 2.507309941520468e-05,
"loss": 0.001,
"step": 3410
},
{
"epoch": 9.98,
"learning_rate": 2.5058479532163743e-05,
"loss": 0.0024,
"step": 3412
},
{
"epoch": 9.98,
"learning_rate": 2.504385964912281e-05,
"loss": 0.0001,
"step": 3414
},
{
"epoch": 9.99,
"learning_rate": 2.5029239766081874e-05,
"loss": 0.0013,
"step": 3416
},
{
"epoch": 9.99,
"learning_rate": 2.5014619883040936e-05,
"loss": 0.0007,
"step": 3418
},
{
"epoch": 10.0,
"learning_rate": 2.5e-05,
"loss": 0.0001,
"step": 3420
},
{
"epoch": 10.0,
"eval_bleu": 0.5262672325830657,
"eval_loss": 1.5510716438293457,
"eval_runtime": 36.9005,
"eval_samples_per_second": 9.078,
"eval_steps_per_second": 2.276,
"step": 3420
},
{
"epoch": 10.01,
"learning_rate": 2.4985380116959063e-05,
"loss": 0.0002,
"step": 3422
},
{
"epoch": 10.01,
"learning_rate": 2.4970760233918132e-05,
"loss": 0.0003,
"step": 3424
},
{
"epoch": 10.02,
"learning_rate": 2.4956140350877194e-05,
"loss": 0.0037,
"step": 3426
},
{
"epoch": 10.02,
"learning_rate": 2.4941520467836256e-05,
"loss": 0.0801,
"step": 3428
},
{
"epoch": 10.03,
"learning_rate": 2.4926900584795325e-05,
"loss": 0.0009,
"step": 3430
},
{
"epoch": 10.04,
"learning_rate": 2.4912280701754387e-05,
"loss": 0.0001,
"step": 3432
},
{
"epoch": 10.04,
"learning_rate": 2.489766081871345e-05,
"loss": 0.0001,
"step": 3434
},
{
"epoch": 10.05,
"learning_rate": 2.4883040935672517e-05,
"loss": 0.0,
"step": 3436
},
{
"epoch": 10.05,
"learning_rate": 2.486842105263158e-05,
"loss": 0.0098,
"step": 3438
},
{
"epoch": 10.06,
"learning_rate": 2.485380116959064e-05,
"loss": 0.0042,
"step": 3440
},
{
"epoch": 10.06,
"learning_rate": 2.483918128654971e-05,
"loss": 0.0023,
"step": 3442
},
{
"epoch": 10.07,
"learning_rate": 2.4824561403508772e-05,
"loss": 0.0005,
"step": 3444
},
{
"epoch": 10.08,
"learning_rate": 2.4809941520467838e-05,
"loss": 0.0078,
"step": 3446
},
{
"epoch": 10.08,
"learning_rate": 2.4795321637426903e-05,
"loss": 0.1048,
"step": 3448
},
{
"epoch": 10.09,
"learning_rate": 2.4780701754385965e-05,
"loss": 0.0003,
"step": 3450
},
{
"epoch": 10.09,
"learning_rate": 2.476608187134503e-05,
"loss": 0.0001,
"step": 3452
},
{
"epoch": 10.1,
"learning_rate": 2.4751461988304096e-05,
"loss": 0.0006,
"step": 3454
},
{
"epoch": 10.11,
"learning_rate": 2.4736842105263158e-05,
"loss": 0.0001,
"step": 3456
},
{
"epoch": 10.11,
"learning_rate": 2.4722222222222223e-05,
"loss": 0.0038,
"step": 3458
},
{
"epoch": 10.12,
"learning_rate": 2.470760233918129e-05,
"loss": 0.0001,
"step": 3460
},
{
"epoch": 10.12,
"learning_rate": 2.469298245614035e-05,
"loss": 0.0,
"step": 3462
},
{
"epoch": 10.13,
"learning_rate": 2.4678362573099416e-05,
"loss": 0.0069,
"step": 3464
},
{
"epoch": 10.13,
"learning_rate": 2.466374269005848e-05,
"loss": 0.0002,
"step": 3466
},
{
"epoch": 10.14,
"learning_rate": 2.4649122807017543e-05,
"loss": 0.0001,
"step": 3468
},
{
"epoch": 10.15,
"learning_rate": 2.463450292397661e-05,
"loss": 0.0024,
"step": 3470
},
{
"epoch": 10.15,
"learning_rate": 2.4619883040935674e-05,
"loss": 0.0001,
"step": 3472
},
{
"epoch": 10.16,
"learning_rate": 2.4605263157894736e-05,
"loss": 0.0004,
"step": 3474
},
{
"epoch": 10.16,
"learning_rate": 2.45906432748538e-05,
"loss": 0.0007,
"step": 3476
},
{
"epoch": 10.17,
"learning_rate": 2.4576023391812867e-05,
"loss": 0.0227,
"step": 3478
},
{
"epoch": 10.18,
"learning_rate": 2.456140350877193e-05,
"loss": 0.0001,
"step": 3480
},
{
"epoch": 10.18,
"learning_rate": 2.4546783625730997e-05,
"loss": 0.0001,
"step": 3482
},
{
"epoch": 10.19,
"learning_rate": 2.453216374269006e-05,
"loss": 0.0002,
"step": 3484
},
{
"epoch": 10.19,
"learning_rate": 2.4517543859649125e-05,
"loss": 0.0022,
"step": 3486
},
{
"epoch": 10.2,
"learning_rate": 2.450292397660819e-05,
"loss": 0.0014,
"step": 3488
},
{
"epoch": 10.2,
"learning_rate": 2.4488304093567252e-05,
"loss": 0.0,
"step": 3490
},
{
"epoch": 10.21,
"learning_rate": 2.4473684210526318e-05,
"loss": 0.0017,
"step": 3492
},
{
"epoch": 10.22,
"learning_rate": 2.4459064327485383e-05,
"loss": 0.0,
"step": 3494
},
{
"epoch": 10.22,
"learning_rate": 2.4444444444444445e-05,
"loss": 0.0,
"step": 3496
},
{
"epoch": 10.23,
"learning_rate": 2.442982456140351e-05,
"loss": 0.0003,
"step": 3498
},
{
"epoch": 10.23,
"learning_rate": 2.4415204678362576e-05,
"loss": 0.0001,
"step": 3500
},
{
"epoch": 10.24,
"learning_rate": 2.4400584795321638e-05,
"loss": 0.0002,
"step": 3502
},
{
"epoch": 10.25,
"learning_rate": 2.4385964912280703e-05,
"loss": 0.0031,
"step": 3504
},
{
"epoch": 10.25,
"learning_rate": 2.437134502923977e-05,
"loss": 0.0018,
"step": 3506
},
{
"epoch": 10.26,
"learning_rate": 2.435672514619883e-05,
"loss": 0.0024,
"step": 3508
},
{
"epoch": 10.26,
"learning_rate": 2.4342105263157896e-05,
"loss": 0.006,
"step": 3510
},
{
"epoch": 10.27,
"learning_rate": 2.432748538011696e-05,
"loss": 0.0144,
"step": 3512
},
{
"epoch": 10.27,
"learning_rate": 2.4312865497076023e-05,
"loss": 0.0001,
"step": 3514
},
{
"epoch": 10.28,
"learning_rate": 2.429824561403509e-05,
"loss": 0.0012,
"step": 3516
},
{
"epoch": 10.29,
"learning_rate": 2.4283625730994154e-05,
"loss": 0.0004,
"step": 3518
},
{
"epoch": 10.29,
"learning_rate": 2.4269005847953216e-05,
"loss": 0.0001,
"step": 3520
},
{
"epoch": 10.3,
"learning_rate": 2.425438596491228e-05,
"loss": 0.0004,
"step": 3522
},
{
"epoch": 10.3,
"learning_rate": 2.4239766081871347e-05,
"loss": 0.0002,
"step": 3524
},
{
"epoch": 10.31,
"learning_rate": 2.4225146198830412e-05,
"loss": 0.0069,
"step": 3526
},
{
"epoch": 10.32,
"learning_rate": 2.4210526315789474e-05,
"loss": 0.0001,
"step": 3528
},
{
"epoch": 10.32,
"learning_rate": 2.419590643274854e-05,
"loss": 0.0001,
"step": 3530
},
{
"epoch": 10.33,
"learning_rate": 2.4181286549707605e-05,
"loss": 0.0005,
"step": 3532
},
{
"epoch": 10.33,
"learning_rate": 2.4166666666666667e-05,
"loss": 0.005,
"step": 3534
},
{
"epoch": 10.34,
"learning_rate": 2.4152046783625732e-05,
"loss": 0.0003,
"step": 3536
},
{
"epoch": 10.35,
"learning_rate": 2.4137426900584798e-05,
"loss": 0.2362,
"step": 3538
},
{
"epoch": 10.35,
"learning_rate": 2.412280701754386e-05,
"loss": 0.0003,
"step": 3540
},
{
"epoch": 10.36,
"learning_rate": 2.4108187134502925e-05,
"loss": 0.0024,
"step": 3542
},
{
"epoch": 10.36,
"learning_rate": 2.409356725146199e-05,
"loss": 0.0001,
"step": 3544
},
{
"epoch": 10.37,
"learning_rate": 2.4078947368421052e-05,
"loss": 0.0006,
"step": 3546
},
{
"epoch": 10.37,
"learning_rate": 2.4064327485380118e-05,
"loss": 0.0004,
"step": 3548
},
{
"epoch": 10.38,
"learning_rate": 2.4049707602339183e-05,
"loss": 0.0002,
"step": 3550
},
{
"epoch": 10.39,
"learning_rate": 2.4035087719298245e-05,
"loss": 0.0045,
"step": 3552
},
{
"epoch": 10.39,
"learning_rate": 2.402046783625731e-05,
"loss": 0.0001,
"step": 3554
},
{
"epoch": 10.4,
"learning_rate": 2.4005847953216376e-05,
"loss": 0.0321,
"step": 3556
},
{
"epoch": 10.4,
"learning_rate": 2.3991228070175438e-05,
"loss": 0.0006,
"step": 3558
},
{
"epoch": 10.41,
"learning_rate": 2.3976608187134503e-05,
"loss": 0.0001,
"step": 3560
},
{
"epoch": 10.42,
"learning_rate": 2.396198830409357e-05,
"loss": 0.0015,
"step": 3562
},
{
"epoch": 10.42,
"learning_rate": 2.394736842105263e-05,
"loss": 0.0008,
"step": 3564
},
{
"epoch": 10.43,
"learning_rate": 2.39327485380117e-05,
"loss": 0.0002,
"step": 3566
},
{
"epoch": 10.43,
"learning_rate": 2.391812865497076e-05,
"loss": 0.0011,
"step": 3568
},
{
"epoch": 10.44,
"learning_rate": 2.3903508771929827e-05,
"loss": 0.2571,
"step": 3570
},
{
"epoch": 10.44,
"learning_rate": 2.3888888888888892e-05,
"loss": 0.0,
"step": 3572
},
{
"epoch": 10.45,
"learning_rate": 2.3874269005847954e-05,
"loss": 0.0007,
"step": 3574
},
{
"epoch": 10.46,
"learning_rate": 2.385964912280702e-05,
"loss": 0.0007,
"step": 3576
},
{
"epoch": 10.46,
"learning_rate": 2.3845029239766085e-05,
"loss": 0.0618,
"step": 3578
},
{
"epoch": 10.47,
"learning_rate": 2.3830409356725147e-05,
"loss": 0.0,
"step": 3580
},
{
"epoch": 10.47,
"learning_rate": 2.3815789473684212e-05,
"loss": 0.0327,
"step": 3582
},
{
"epoch": 10.48,
"learning_rate": 2.3801169590643278e-05,
"loss": 0.0004,
"step": 3584
},
{
"epoch": 10.49,
"learning_rate": 2.378654970760234e-05,
"loss": 0.002,
"step": 3586
},
{
"epoch": 10.49,
"learning_rate": 2.3771929824561405e-05,
"loss": 0.0,
"step": 3588
},
{
"epoch": 10.5,
"learning_rate": 2.375730994152047e-05,
"loss": 0.0002,
"step": 3590
},
{
"epoch": 10.5,
"learning_rate": 2.3742690058479532e-05,
"loss": 0.0001,
"step": 3592
},
{
"epoch": 10.51,
"learning_rate": 2.3728070175438598e-05,
"loss": 0.0001,
"step": 3594
},
{
"epoch": 10.51,
"learning_rate": 2.3713450292397663e-05,
"loss": 0.0011,
"step": 3596
},
{
"epoch": 10.52,
"learning_rate": 2.3698830409356725e-05,
"loss": 0.0023,
"step": 3598
},
{
"epoch": 10.53,
"learning_rate": 2.368421052631579e-05,
"loss": 0.0009,
"step": 3600
},
{
"epoch": 10.53,
"learning_rate": 2.3669590643274856e-05,
"loss": 0.0027,
"step": 3602
},
{
"epoch": 10.54,
"learning_rate": 2.3654970760233918e-05,
"loss": 0.0007,
"step": 3604
},
{
"epoch": 10.54,
"learning_rate": 2.3640350877192987e-05,
"loss": 0.0001,
"step": 3606
},
{
"epoch": 10.55,
"learning_rate": 2.362573099415205e-05,
"loss": 0.0001,
"step": 3608
},
{
"epoch": 10.56,
"learning_rate": 2.361111111111111e-05,
"loss": 0.0012,
"step": 3610
},
{
"epoch": 10.56,
"learning_rate": 2.359649122807018e-05,
"loss": 0.0011,
"step": 3612
},
{
"epoch": 10.57,
"learning_rate": 2.358187134502924e-05,
"loss": 0.0005,
"step": 3614
},
{
"epoch": 10.57,
"learning_rate": 2.3567251461988303e-05,
"loss": 0.0,
"step": 3616
},
{
"epoch": 10.58,
"learning_rate": 2.3552631578947372e-05,
"loss": 0.0057,
"step": 3618
},
{
"epoch": 10.58,
"learning_rate": 2.3538011695906434e-05,
"loss": 0.0621,
"step": 3620
},
{
"epoch": 10.59,
"learning_rate": 2.3523391812865496e-05,
"loss": 0.0254,
"step": 3622
},
{
"epoch": 10.6,
"learning_rate": 2.3508771929824565e-05,
"loss": 0.0001,
"step": 3624
},
{
"epoch": 10.6,
"learning_rate": 2.3494152046783627e-05,
"loss": 0.0046,
"step": 3626
},
{
"epoch": 10.61,
"learning_rate": 2.347953216374269e-05,
"loss": 0.0,
"step": 3628
},
{
"epoch": 10.61,
"learning_rate": 2.3464912280701758e-05,
"loss": 0.0001,
"step": 3630
},
{
"epoch": 10.62,
"learning_rate": 2.345029239766082e-05,
"loss": 0.0006,
"step": 3632
},
{
"epoch": 10.63,
"learning_rate": 2.343567251461988e-05,
"loss": 0.0006,
"step": 3634
},
{
"epoch": 10.63,
"learning_rate": 2.342105263157895e-05,
"loss": 0.006,
"step": 3636
},
{
"epoch": 10.64,
"learning_rate": 2.3406432748538012e-05,
"loss": 0.0258,
"step": 3638
},
{
"epoch": 10.64,
"learning_rate": 2.3391812865497074e-05,
"loss": 0.0003,
"step": 3640
},
{
"epoch": 10.65,
"learning_rate": 2.3377192982456143e-05,
"loss": 0.0011,
"step": 3642
},
{
"epoch": 10.65,
"learning_rate": 2.3362573099415205e-05,
"loss": 0.0005,
"step": 3644
},
{
"epoch": 10.66,
"learning_rate": 2.334795321637427e-05,
"loss": 0.0008,
"step": 3646
},
{
"epoch": 10.67,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.0002,
"step": 3648
},
{
"epoch": 10.67,
"learning_rate": 2.3318713450292398e-05,
"loss": 0.0001,
"step": 3650
},
{
"epoch": 10.68,
"learning_rate": 2.3304093567251463e-05,
"loss": 0.0001,
"step": 3652
},
{
"epoch": 10.68,
"learning_rate": 2.328947368421053e-05,
"loss": 0.0008,
"step": 3654
},
{
"epoch": 10.69,
"learning_rate": 2.327485380116959e-05,
"loss": 0.0003,
"step": 3656
},
{
"epoch": 10.7,
"learning_rate": 2.3260233918128656e-05,
"loss": 0.0177,
"step": 3658
},
{
"epoch": 10.7,
"learning_rate": 2.324561403508772e-05,
"loss": 0.0004,
"step": 3660
},
{
"epoch": 10.71,
"learning_rate": 2.3230994152046783e-05,
"loss": 0.0,
"step": 3662
},
{
"epoch": 10.71,
"learning_rate": 2.321637426900585e-05,
"loss": 0.0909,
"step": 3664
},
{
"epoch": 10.72,
"learning_rate": 2.3201754385964914e-05,
"loss": 0.0012,
"step": 3666
},
{
"epoch": 10.73,
"learning_rate": 2.3187134502923976e-05,
"loss": 0.0,
"step": 3668
},
{
"epoch": 10.73,
"learning_rate": 2.317251461988304e-05,
"loss": 0.0002,
"step": 3670
},
{
"epoch": 10.74,
"learning_rate": 2.3157894736842107e-05,
"loss": 0.0001,
"step": 3672
},
{
"epoch": 10.74,
"learning_rate": 2.314327485380117e-05,
"loss": 0.0018,
"step": 3674
},
{
"epoch": 10.75,
"learning_rate": 2.3128654970760234e-05,
"loss": 0.0004,
"step": 3676
},
{
"epoch": 10.75,
"learning_rate": 2.31140350877193e-05,
"loss": 0.0,
"step": 3678
},
{
"epoch": 10.76,
"learning_rate": 2.309941520467836e-05,
"loss": 0.0011,
"step": 3680
},
{
"epoch": 10.77,
"learning_rate": 2.3084795321637427e-05,
"loss": 0.0018,
"step": 3682
},
{
"epoch": 10.77,
"learning_rate": 2.3070175438596492e-05,
"loss": 0.0002,
"step": 3684
},
{
"epoch": 10.78,
"learning_rate": 2.3055555555555558e-05,
"loss": 0.0004,
"step": 3686
},
{
"epoch": 10.78,
"learning_rate": 2.3040935672514623e-05,
"loss": 0.0039,
"step": 3688
},
{
"epoch": 10.79,
"learning_rate": 2.3026315789473685e-05,
"loss": 0.0,
"step": 3690
},
{
"epoch": 10.8,
"learning_rate": 2.301169590643275e-05,
"loss": 0.0136,
"step": 3692
},
{
"epoch": 10.8,
"learning_rate": 2.2997076023391816e-05,
"loss": 0.0001,
"step": 3694
},
{
"epoch": 10.81,
"learning_rate": 2.2982456140350878e-05,
"loss": 0.0031,
"step": 3696
},
{
"epoch": 10.81,
"learning_rate": 2.2967836257309943e-05,
"loss": 0.0,
"step": 3698
},
{
"epoch": 10.82,
"learning_rate": 2.295321637426901e-05,
"loss": 0.0001,
"step": 3700
},
{
"epoch": 10.82,
"learning_rate": 2.293859649122807e-05,
"loss": 0.0005,
"step": 3702
},
{
"epoch": 10.83,
"learning_rate": 2.2923976608187136e-05,
"loss": 0.0095,
"step": 3704
},
{
"epoch": 10.84,
"learning_rate": 2.29093567251462e-05,
"loss": 0.0002,
"step": 3706
},
{
"epoch": 10.84,
"learning_rate": 2.2894736842105263e-05,
"loss": 0.0,
"step": 3708
},
{
"epoch": 10.85,
"learning_rate": 2.288011695906433e-05,
"loss": 0.0037,
"step": 3710
},
{
"epoch": 10.85,
"learning_rate": 2.2865497076023394e-05,
"loss": 0.0,
"step": 3712
},
{
"epoch": 10.86,
"learning_rate": 2.2850877192982456e-05,
"loss": 0.0074,
"step": 3714
},
{
"epoch": 10.87,
"learning_rate": 2.283625730994152e-05,
"loss": 0.0075,
"step": 3716
},
{
"epoch": 10.87,
"learning_rate": 2.2821637426900587e-05,
"loss": 0.0006,
"step": 3718
},
{
"epoch": 10.88,
"learning_rate": 2.280701754385965e-05,
"loss": 0.0004,
"step": 3720
},
{
"epoch": 10.88,
"learning_rate": 2.2792397660818714e-05,
"loss": 0.0222,
"step": 3722
},
{
"epoch": 10.89,
"learning_rate": 2.277777777777778e-05,
"loss": 0.0,
"step": 3724
},
{
"epoch": 10.89,
"learning_rate": 2.2763157894736845e-05,
"loss": 0.0009,
"step": 3726
},
{
"epoch": 10.9,
"learning_rate": 2.2748538011695907e-05,
"loss": 0.0008,
"step": 3728
},
{
"epoch": 10.91,
"learning_rate": 2.2733918128654972e-05,
"loss": 0.0001,
"step": 3730
},
{
"epoch": 10.91,
"learning_rate": 2.2719298245614038e-05,
"loss": 0.0026,
"step": 3732
},
{
"epoch": 10.92,
"learning_rate": 2.27046783625731e-05,
"loss": 0.0002,
"step": 3734
},
{
"epoch": 10.92,
"learning_rate": 2.2690058479532165e-05,
"loss": 0.0001,
"step": 3736
},
{
"epoch": 10.93,
"learning_rate": 2.267543859649123e-05,
"loss": 0.0355,
"step": 3738
},
{
"epoch": 10.94,
"learning_rate": 2.2660818713450292e-05,
"loss": 0.0051,
"step": 3740
},
{
"epoch": 10.94,
"learning_rate": 2.2646198830409358e-05,
"loss": 0.0001,
"step": 3742
},
{
"epoch": 10.95,
"learning_rate": 2.2631578947368423e-05,
"loss": 0.0001,
"step": 3744
},
{
"epoch": 10.95,
"learning_rate": 2.2616959064327485e-05,
"loss": 0.0157,
"step": 3746
},
{
"epoch": 10.96,
"learning_rate": 2.260233918128655e-05,
"loss": 0.0003,
"step": 3748
},
{
"epoch": 10.96,
"learning_rate": 2.2587719298245616e-05,
"loss": 0.0002,
"step": 3750
},
{
"epoch": 10.97,
"learning_rate": 2.2573099415204678e-05,
"loss": 0.001,
"step": 3752
},
{
"epoch": 10.98,
"learning_rate": 2.2558479532163743e-05,
"loss": 0.0002,
"step": 3754
},
{
"epoch": 10.98,
"learning_rate": 2.254385964912281e-05,
"loss": 0.0025,
"step": 3756
},
{
"epoch": 10.99,
"learning_rate": 2.252923976608187e-05,
"loss": 0.0001,
"step": 3758
},
{
"epoch": 10.99,
"learning_rate": 2.2514619883040936e-05,
"loss": 0.0117,
"step": 3760
},
{
"epoch": 11.0,
"learning_rate": 2.25e-05,
"loss": 0.0001,
"step": 3762
},
{
"epoch": 11.0,
"eval_bleu": 0.530107675830313,
"eval_loss": 1.4396569728851318,
"eval_runtime": 36.3259,
"eval_samples_per_second": 9.222,
"eval_steps_per_second": 2.312,
"step": 3762
},
{
"epoch": 11.01,
"learning_rate": 2.2485380116959063e-05,
"loss": 0.0008,
"step": 3764
},
{
"epoch": 11.01,
"learning_rate": 2.247076023391813e-05,
"loss": 0.0004,
"step": 3766
},
{
"epoch": 11.02,
"learning_rate": 2.2456140350877194e-05,
"loss": 0.0002,
"step": 3768
},
{
"epoch": 11.02,
"learning_rate": 2.2441520467836256e-05,
"loss": 0.0005,
"step": 3770
},
{
"epoch": 11.03,
"learning_rate": 2.2426900584795325e-05,
"loss": 0.0002,
"step": 3772
},
{
"epoch": 11.04,
"learning_rate": 2.2412280701754387e-05,
"loss": 0.0,
"step": 3774
},
{
"epoch": 11.04,
"learning_rate": 2.2397660818713452e-05,
"loss": 0.0003,
"step": 3776
},
{
"epoch": 11.05,
"learning_rate": 2.2383040935672518e-05,
"loss": 0.0002,
"step": 3778
},
{
"epoch": 11.05,
"learning_rate": 2.236842105263158e-05,
"loss": 0.047,
"step": 3780
},
{
"epoch": 11.06,
"learning_rate": 2.2353801169590645e-05,
"loss": 0.0005,
"step": 3782
},
{
"epoch": 11.06,
"learning_rate": 2.233918128654971e-05,
"loss": 0.0018,
"step": 3784
},
{
"epoch": 11.07,
"learning_rate": 2.2324561403508772e-05,
"loss": 0.0614,
"step": 3786
},
{
"epoch": 11.08,
"learning_rate": 2.2309941520467838e-05,
"loss": 0.0001,
"step": 3788
},
{
"epoch": 11.08,
"learning_rate": 2.2295321637426903e-05,
"loss": 0.1925,
"step": 3790
},
{
"epoch": 11.09,
"learning_rate": 2.2280701754385965e-05,
"loss": 0.0008,
"step": 3792
},
{
"epoch": 11.09,
"learning_rate": 2.226608187134503e-05,
"loss": 0.0008,
"step": 3794
},
{
"epoch": 11.1,
"learning_rate": 2.2251461988304096e-05,
"loss": 0.0003,
"step": 3796
},
{
"epoch": 11.11,
"learning_rate": 2.2236842105263158e-05,
"loss": 0.0002,
"step": 3798
},
{
"epoch": 11.11,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.0001,
"step": 3800
},
{
"epoch": 11.12,
"learning_rate": 2.220760233918129e-05,
"loss": 0.0001,
"step": 3802
},
{
"epoch": 11.12,
"learning_rate": 2.219298245614035e-05,
"loss": 0.0005,
"step": 3804
},
{
"epoch": 11.13,
"learning_rate": 2.2178362573099416e-05,
"loss": 0.0008,
"step": 3806
},
{
"epoch": 11.13,
"learning_rate": 2.216374269005848e-05,
"loss": 0.0,
"step": 3808
},
{
"epoch": 11.14,
"learning_rate": 2.2149122807017543e-05,
"loss": 0.0014,
"step": 3810
},
{
"epoch": 11.15,
"learning_rate": 2.2134502923976612e-05,
"loss": 0.0003,
"step": 3812
},
{
"epoch": 11.15,
"learning_rate": 2.2119883040935674e-05,
"loss": 0.0002,
"step": 3814
},
{
"epoch": 11.16,
"learning_rate": 2.2105263157894736e-05,
"loss": 0.0007,
"step": 3816
},
{
"epoch": 11.16,
"learning_rate": 2.2090643274853805e-05,
"loss": 0.0001,
"step": 3818
},
{
"epoch": 11.17,
"learning_rate": 2.2076023391812867e-05,
"loss": 0.001,
"step": 3820
},
{
"epoch": 11.18,
"learning_rate": 2.206140350877193e-05,
"loss": 0.0,
"step": 3822
},
{
"epoch": 11.18,
"learning_rate": 2.2046783625730998e-05,
"loss": 0.0004,
"step": 3824
},
{
"epoch": 11.19,
"learning_rate": 2.203216374269006e-05,
"loss": 0.0006,
"step": 3826
},
{
"epoch": 11.19,
"learning_rate": 2.201754385964912e-05,
"loss": 0.0,
"step": 3828
},
{
"epoch": 11.2,
"learning_rate": 2.200292397660819e-05,
"loss": 0.0109,
"step": 3830
},
{
"epoch": 11.2,
"learning_rate": 2.1988304093567252e-05,
"loss": 0.0,
"step": 3832
},
{
"epoch": 11.21,
"learning_rate": 2.1973684210526314e-05,
"loss": 0.0114,
"step": 3834
},
{
"epoch": 11.22,
"learning_rate": 2.1959064327485383e-05,
"loss": 0.0179,
"step": 3836
},
{
"epoch": 11.22,
"learning_rate": 2.1944444444444445e-05,
"loss": 0.0,
"step": 3838
},
{
"epoch": 11.23,
"learning_rate": 2.1929824561403507e-05,
"loss": 0.0003,
"step": 3840
},
{
"epoch": 11.23,
"learning_rate": 2.1915204678362576e-05,
"loss": 0.003,
"step": 3842
},
{
"epoch": 11.24,
"learning_rate": 2.1900584795321638e-05,
"loss": 0.0003,
"step": 3844
},
{
"epoch": 11.25,
"learning_rate": 2.18859649122807e-05,
"loss": 0.001,
"step": 3846
},
{
"epoch": 11.25,
"learning_rate": 2.187134502923977e-05,
"loss": 0.0008,
"step": 3848
},
{
"epoch": 11.26,
"learning_rate": 2.185672514619883e-05,
"loss": 0.0001,
"step": 3850
},
{
"epoch": 11.26,
"learning_rate": 2.1842105263157896e-05,
"loss": 0.0,
"step": 3852
},
{
"epoch": 11.27,
"learning_rate": 2.182748538011696e-05,
"loss": 0.0,
"step": 3854
},
{
"epoch": 11.27,
"learning_rate": 2.1812865497076023e-05,
"loss": 0.0001,
"step": 3856
},
{
"epoch": 11.28,
"learning_rate": 2.179824561403509e-05,
"loss": 0.0018,
"step": 3858
},
{
"epoch": 11.29,
"learning_rate": 2.1783625730994154e-05,
"loss": 0.0,
"step": 3860
},
{
"epoch": 11.29,
"learning_rate": 2.1769005847953216e-05,
"loss": 0.0005,
"step": 3862
},
{
"epoch": 11.3,
"learning_rate": 2.175438596491228e-05,
"loss": 0.0935,
"step": 3864
},
{
"epoch": 11.3,
"learning_rate": 2.1739766081871347e-05,
"loss": 0.0006,
"step": 3866
},
{
"epoch": 11.31,
"learning_rate": 2.172514619883041e-05,
"loss": 0.0059,
"step": 3868
},
{
"epoch": 11.32,
"learning_rate": 2.1710526315789474e-05,
"loss": 0.004,
"step": 3870
},
{
"epoch": 11.32,
"learning_rate": 2.169590643274854e-05,
"loss": 0.0122,
"step": 3872
},
{
"epoch": 11.33,
"learning_rate": 2.16812865497076e-05,
"loss": 0.0001,
"step": 3874
},
{
"epoch": 11.33,
"learning_rate": 2.1666666666666667e-05,
"loss": 0.0003,
"step": 3876
},
{
"epoch": 11.34,
"learning_rate": 2.1652046783625732e-05,
"loss": 0.0001,
"step": 3878
},
{
"epoch": 11.35,
"learning_rate": 2.1637426900584794e-05,
"loss": 0.0001,
"step": 3880
},
{
"epoch": 11.35,
"learning_rate": 2.162280701754386e-05,
"loss": 0.0,
"step": 3882
},
{
"epoch": 11.36,
"learning_rate": 2.1608187134502925e-05,
"loss": 0.0338,
"step": 3884
},
{
"epoch": 11.36,
"learning_rate": 2.1593567251461987e-05,
"loss": 0.0001,
"step": 3886
},
{
"epoch": 11.37,
"learning_rate": 2.1578947368421053e-05,
"loss": 0.0009,
"step": 3888
},
{
"epoch": 11.37,
"learning_rate": 2.1564327485380118e-05,
"loss": 0.0001,
"step": 3890
},
{
"epoch": 11.38,
"learning_rate": 2.1549707602339183e-05,
"loss": 0.0205,
"step": 3892
},
{
"epoch": 11.39,
"learning_rate": 2.153508771929825e-05,
"loss": 0.0001,
"step": 3894
},
{
"epoch": 11.39,
"learning_rate": 2.152046783625731e-05,
"loss": 0.0031,
"step": 3896
},
{
"epoch": 11.4,
"learning_rate": 2.1505847953216376e-05,
"loss": 0.0131,
"step": 3898
},
{
"epoch": 11.4,
"learning_rate": 2.149122807017544e-05,
"loss": 0.0001,
"step": 3900
},
{
"epoch": 11.41,
"learning_rate": 2.1476608187134503e-05,
"loss": 0.0002,
"step": 3902
},
{
"epoch": 11.42,
"learning_rate": 2.146198830409357e-05,
"loss": 0.0,
"step": 3904
},
{
"epoch": 11.42,
"learning_rate": 2.1447368421052634e-05,
"loss": 0.0001,
"step": 3906
},
{
"epoch": 11.43,
"learning_rate": 2.1432748538011696e-05,
"loss": 0.006,
"step": 3908
},
{
"epoch": 11.43,
"learning_rate": 2.141812865497076e-05,
"loss": 0.0001,
"step": 3910
},
{
"epoch": 11.44,
"learning_rate": 2.1403508771929827e-05,
"loss": 0.0015,
"step": 3912
},
{
"epoch": 11.44,
"learning_rate": 2.138888888888889e-05,
"loss": 0.0001,
"step": 3914
},
{
"epoch": 11.45,
"learning_rate": 2.1374269005847954e-05,
"loss": 0.0001,
"step": 3916
},
{
"epoch": 11.46,
"learning_rate": 2.135964912280702e-05,
"loss": 0.0004,
"step": 3918
},
{
"epoch": 11.46,
"learning_rate": 2.134502923976608e-05,
"loss": 0.0041,
"step": 3920
},
{
"epoch": 11.47,
"learning_rate": 2.1330409356725147e-05,
"loss": 0.0057,
"step": 3922
},
{
"epoch": 11.47,
"learning_rate": 2.1315789473684212e-05,
"loss": 0.0009,
"step": 3924
},
{
"epoch": 11.48,
"learning_rate": 2.1301169590643274e-05,
"loss": 0.0001,
"step": 3926
},
{
"epoch": 11.49,
"learning_rate": 2.128654970760234e-05,
"loss": 0.0009,
"step": 3928
},
{
"epoch": 11.49,
"learning_rate": 2.1271929824561405e-05,
"loss": 0.0022,
"step": 3930
},
{
"epoch": 11.5,
"learning_rate": 2.125730994152047e-05,
"loss": 0.0001,
"step": 3932
},
{
"epoch": 11.5,
"learning_rate": 2.1242690058479533e-05,
"loss": 0.0032,
"step": 3934
},
{
"epoch": 11.51,
"learning_rate": 2.1228070175438598e-05,
"loss": 0.0002,
"step": 3936
},
{
"epoch": 11.51,
"learning_rate": 2.1213450292397663e-05,
"loss": 0.0011,
"step": 3938
},
{
"epoch": 11.52,
"learning_rate": 2.1198830409356725e-05,
"loss": 0.0005,
"step": 3940
},
{
"epoch": 11.53,
"learning_rate": 2.118421052631579e-05,
"loss": 0.0006,
"step": 3942
},
{
"epoch": 11.53,
"learning_rate": 2.1169590643274856e-05,
"loss": 0.0,
"step": 3944
},
{
"epoch": 11.54,
"learning_rate": 2.1154970760233918e-05,
"loss": 0.0002,
"step": 3946
},
{
"epoch": 11.54,
"learning_rate": 2.1140350877192983e-05,
"loss": 0.09,
"step": 3948
},
{
"epoch": 11.55,
"learning_rate": 2.112573099415205e-05,
"loss": 0.0064,
"step": 3950
},
{
"epoch": 11.56,
"learning_rate": 2.111111111111111e-05,
"loss": 0.0003,
"step": 3952
},
{
"epoch": 11.56,
"learning_rate": 2.1096491228070176e-05,
"loss": 0.0001,
"step": 3954
},
{
"epoch": 11.57,
"learning_rate": 2.108187134502924e-05,
"loss": 0.0001,
"step": 3956
},
{
"epoch": 11.57,
"learning_rate": 2.1067251461988304e-05,
"loss": 0.0017,
"step": 3958
},
{
"epoch": 11.58,
"learning_rate": 2.105263157894737e-05,
"loss": 0.0097,
"step": 3960
},
{
"epoch": 11.58,
"learning_rate": 2.1038011695906434e-05,
"loss": 0.0001,
"step": 3962
},
{
"epoch": 11.59,
"learning_rate": 2.1023391812865496e-05,
"loss": 0.0001,
"step": 3964
},
{
"epoch": 11.6,
"learning_rate": 2.100877192982456e-05,
"loss": 0.0105,
"step": 3966
},
{
"epoch": 11.6,
"learning_rate": 2.0994152046783627e-05,
"loss": 0.0001,
"step": 3968
},
{
"epoch": 11.61,
"learning_rate": 2.097953216374269e-05,
"loss": 0.0001,
"step": 3970
},
{
"epoch": 11.61,
"learning_rate": 2.0964912280701758e-05,
"loss": 0.0218,
"step": 3972
},
{
"epoch": 11.62,
"learning_rate": 2.095029239766082e-05,
"loss": 0.0001,
"step": 3974
},
{
"epoch": 11.63,
"learning_rate": 2.0935672514619882e-05,
"loss": 0.0008,
"step": 3976
},
{
"epoch": 11.63,
"learning_rate": 2.092105263157895e-05,
"loss": 0.0008,
"step": 3978
},
{
"epoch": 11.64,
"learning_rate": 2.0906432748538013e-05,
"loss": 0.0005,
"step": 3980
},
{
"epoch": 11.64,
"learning_rate": 2.0891812865497078e-05,
"loss": 0.0,
"step": 3982
},
{
"epoch": 11.65,
"learning_rate": 2.0877192982456143e-05,
"loss": 0.0002,
"step": 3984
},
{
"epoch": 11.65,
"learning_rate": 2.0862573099415205e-05,
"loss": 0.0035,
"step": 3986
},
{
"epoch": 11.66,
"learning_rate": 2.084795321637427e-05,
"loss": 0.061,
"step": 3988
},
{
"epoch": 11.67,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.0334,
"step": 3990
},
{
"epoch": 11.67,
"learning_rate": 2.0818713450292398e-05,
"loss": 0.0002,
"step": 3992
},
{
"epoch": 11.68,
"learning_rate": 2.0804093567251463e-05,
"loss": 0.0004,
"step": 3994
},
{
"epoch": 11.68,
"learning_rate": 2.078947368421053e-05,
"loss": 0.0096,
"step": 3996
},
{
"epoch": 11.69,
"learning_rate": 2.077485380116959e-05,
"loss": 0.0141,
"step": 3998
},
{
"epoch": 11.7,
"learning_rate": 2.0760233918128656e-05,
"loss": 0.0026,
"step": 4000
},
{
"epoch": 11.7,
"learning_rate": 2.074561403508772e-05,
"loss": 0.0002,
"step": 4002
},
{
"epoch": 11.71,
"learning_rate": 2.0730994152046784e-05,
"loss": 0.0001,
"step": 4004
},
{
"epoch": 11.71,
"learning_rate": 2.071637426900585e-05,
"loss": 0.0001,
"step": 4006
},
{
"epoch": 11.72,
"learning_rate": 2.0701754385964914e-05,
"loss": 0.0005,
"step": 4008
},
{
"epoch": 11.73,
"learning_rate": 2.0687134502923976e-05,
"loss": 0.0118,
"step": 4010
},
{
"epoch": 11.73,
"learning_rate": 2.067251461988304e-05,
"loss": 0.0001,
"step": 4012
},
{
"epoch": 11.74,
"learning_rate": 2.0657894736842107e-05,
"loss": 0.0002,
"step": 4014
},
{
"epoch": 11.74,
"learning_rate": 2.064327485380117e-05,
"loss": 0.0002,
"step": 4016
},
{
"epoch": 11.75,
"learning_rate": 2.0628654970760238e-05,
"loss": 0.0,
"step": 4018
},
{
"epoch": 11.75,
"learning_rate": 2.06140350877193e-05,
"loss": 0.0017,
"step": 4020
},
{
"epoch": 11.76,
"learning_rate": 2.0599415204678362e-05,
"loss": 0.0001,
"step": 4022
},
{
"epoch": 11.77,
"learning_rate": 2.058479532163743e-05,
"loss": 0.0,
"step": 4024
},
{
"epoch": 11.77,
"learning_rate": 2.0570175438596493e-05,
"loss": 0.0003,
"step": 4026
},
{
"epoch": 11.78,
"learning_rate": 2.0555555555555555e-05,
"loss": 0.0001,
"step": 4028
},
{
"epoch": 11.78,
"learning_rate": 2.0540935672514623e-05,
"loss": 0.0003,
"step": 4030
},
{
"epoch": 11.79,
"learning_rate": 2.0526315789473685e-05,
"loss": 0.05,
"step": 4032
},
{
"epoch": 11.8,
"learning_rate": 2.0511695906432747e-05,
"loss": 0.0,
"step": 4034
},
{
"epoch": 11.8,
"learning_rate": 2.0497076023391816e-05,
"loss": 0.0028,
"step": 4036
},
{
"epoch": 11.81,
"learning_rate": 2.0482456140350878e-05,
"loss": 0.0008,
"step": 4038
},
{
"epoch": 11.81,
"learning_rate": 2.046783625730994e-05,
"loss": 0.0003,
"step": 4040
},
{
"epoch": 11.82,
"learning_rate": 2.045321637426901e-05,
"loss": 0.0003,
"step": 4042
},
{
"epoch": 11.82,
"learning_rate": 2.043859649122807e-05,
"loss": 0.029,
"step": 4044
},
{
"epoch": 11.83,
"learning_rate": 2.0423976608187133e-05,
"loss": 0.3816,
"step": 4046
},
{
"epoch": 11.84,
"learning_rate": 2.04093567251462e-05,
"loss": 0.1211,
"step": 4048
},
{
"epoch": 11.84,
"learning_rate": 2.0394736842105264e-05,
"loss": 0.0005,
"step": 4050
},
{
"epoch": 11.85,
"learning_rate": 2.038011695906433e-05,
"loss": 0.0002,
"step": 4052
},
{
"epoch": 11.85,
"learning_rate": 2.0365497076023394e-05,
"loss": 0.0,
"step": 4054
},
{
"epoch": 11.86,
"learning_rate": 2.0350877192982456e-05,
"loss": 0.0001,
"step": 4056
},
{
"epoch": 11.87,
"learning_rate": 2.033625730994152e-05,
"loss": 0.0005,
"step": 4058
},
{
"epoch": 11.87,
"learning_rate": 2.0321637426900587e-05,
"loss": 0.0039,
"step": 4060
},
{
"epoch": 11.88,
"learning_rate": 2.030701754385965e-05,
"loss": 0.0,
"step": 4062
},
{
"epoch": 11.88,
"learning_rate": 2.0292397660818714e-05,
"loss": 0.0,
"step": 4064
},
{
"epoch": 11.89,
"learning_rate": 2.027777777777778e-05,
"loss": 0.0001,
"step": 4066
},
{
"epoch": 11.89,
"learning_rate": 2.0263157894736842e-05,
"loss": 0.0002,
"step": 4068
},
{
"epoch": 11.9,
"learning_rate": 2.0248538011695907e-05,
"loss": 0.0003,
"step": 4070
},
{
"epoch": 11.91,
"learning_rate": 2.0233918128654973e-05,
"loss": 0.0002,
"step": 4072
},
{
"epoch": 11.91,
"learning_rate": 2.0219298245614035e-05,
"loss": 0.0,
"step": 4074
},
{
"epoch": 11.92,
"learning_rate": 2.02046783625731e-05,
"loss": 0.0026,
"step": 4076
},
{
"epoch": 11.92,
"learning_rate": 2.0190058479532165e-05,
"loss": 0.0001,
"step": 4078
},
{
"epoch": 11.93,
"learning_rate": 2.0175438596491227e-05,
"loss": 0.0001,
"step": 4080
},
{
"epoch": 11.94,
"learning_rate": 2.0160818713450293e-05,
"loss": 0.0001,
"step": 4082
},
{
"epoch": 11.94,
"learning_rate": 2.0146198830409358e-05,
"loss": 0.0002,
"step": 4084
},
{
"epoch": 11.95,
"learning_rate": 2.013157894736842e-05,
"loss": 0.0007,
"step": 4086
},
{
"epoch": 11.95,
"learning_rate": 2.0116959064327485e-05,
"loss": 0.0001,
"step": 4088
},
{
"epoch": 11.96,
"learning_rate": 2.010233918128655e-05,
"loss": 0.009,
"step": 4090
},
{
"epoch": 11.96,
"learning_rate": 2.0087719298245616e-05,
"loss": 0.0015,
"step": 4092
},
{
"epoch": 11.97,
"learning_rate": 2.0073099415204678e-05,
"loss": 0.0003,
"step": 4094
},
{
"epoch": 11.98,
"learning_rate": 2.0058479532163744e-05,
"loss": 0.0002,
"step": 4096
},
{
"epoch": 11.98,
"learning_rate": 2.004385964912281e-05,
"loss": 0.0002,
"step": 4098
},
{
"epoch": 11.99,
"learning_rate": 2.0029239766081874e-05,
"loss": 0.0004,
"step": 4100
},
{
"epoch": 11.99,
"learning_rate": 2.0014619883040936e-05,
"loss": 0.0,
"step": 4102
},
{
"epoch": 12.0,
"learning_rate": 2e-05,
"loss": 0.0001,
"step": 4104
},
{
"epoch": 12.0,
"eval_bleu": 0.48972797068460366,
"eval_loss": 1.4625047445297241,
"eval_runtime": 37.1841,
"eval_samples_per_second": 9.009,
"eval_steps_per_second": 2.259,
"step": 4104
},
{
"epoch": 12.01,
"learning_rate": 1.9985380116959067e-05,
"loss": 0.0,
"step": 4106
},
{
"epoch": 12.01,
"learning_rate": 1.997076023391813e-05,
"loss": 0.0001,
"step": 4108
},
{
"epoch": 12.02,
"learning_rate": 1.9956140350877194e-05,
"loss": 0.0001,
"step": 4110
},
{
"epoch": 12.02,
"learning_rate": 1.994152046783626e-05,
"loss": 0.0003,
"step": 4112
},
{
"epoch": 12.03,
"learning_rate": 1.9926900584795322e-05,
"loss": 0.0001,
"step": 4114
},
{
"epoch": 12.04,
"learning_rate": 1.9912280701754387e-05,
"loss": 0.0008,
"step": 4116
},
{
"epoch": 12.04,
"learning_rate": 1.9897660818713453e-05,
"loss": 0.0107,
"step": 4118
},
{
"epoch": 12.05,
"learning_rate": 1.9883040935672515e-05,
"loss": 0.0003,
"step": 4120
},
{
"epoch": 12.05,
"learning_rate": 1.986842105263158e-05,
"loss": 0.0005,
"step": 4122
},
{
"epoch": 12.06,
"learning_rate": 1.9853801169590645e-05,
"loss": 0.0,
"step": 4124
},
{
"epoch": 12.06,
"learning_rate": 1.9839181286549707e-05,
"loss": 0.0,
"step": 4126
},
{
"epoch": 12.07,
"learning_rate": 1.9824561403508773e-05,
"loss": 0.0003,
"step": 4128
},
{
"epoch": 12.08,
"learning_rate": 1.9809941520467838e-05,
"loss": 0.0052,
"step": 4130
},
{
"epoch": 12.08,
"learning_rate": 1.97953216374269e-05,
"loss": 0.0487,
"step": 4132
},
{
"epoch": 12.09,
"learning_rate": 1.9780701754385965e-05,
"loss": 0.0002,
"step": 4134
},
{
"epoch": 12.09,
"learning_rate": 1.976608187134503e-05,
"loss": 0.0058,
"step": 4136
},
{
"epoch": 12.1,
"learning_rate": 1.9751461988304096e-05,
"loss": 0.0002,
"step": 4138
},
{
"epoch": 12.11,
"learning_rate": 1.9736842105263158e-05,
"loss": 0.0,
"step": 4140
},
{
"epoch": 12.11,
"learning_rate": 1.9722222222222224e-05,
"loss": 0.0,
"step": 4142
},
{
"epoch": 12.12,
"learning_rate": 1.970760233918129e-05,
"loss": 0.0001,
"step": 4144
},
{
"epoch": 12.12,
"learning_rate": 1.969298245614035e-05,
"loss": 0.0001,
"step": 4146
},
{
"epoch": 12.13,
"learning_rate": 1.9678362573099416e-05,
"loss": 0.0001,
"step": 4148
},
{
"epoch": 12.13,
"learning_rate": 1.966374269005848e-05,
"loss": 0.0001,
"step": 4150
},
{
"epoch": 12.14,
"learning_rate": 1.9649122807017544e-05,
"loss": 0.0001,
"step": 4152
},
{
"epoch": 12.15,
"learning_rate": 1.963450292397661e-05,
"loss": 0.0416,
"step": 4154
},
{
"epoch": 12.15,
"learning_rate": 1.9619883040935674e-05,
"loss": 0.0004,
"step": 4156
},
{
"epoch": 12.16,
"learning_rate": 1.9605263157894736e-05,
"loss": 0.0003,
"step": 4158
},
{
"epoch": 12.16,
"learning_rate": 1.9590643274853802e-05,
"loss": 0.0005,
"step": 4160
},
{
"epoch": 12.17,
"learning_rate": 1.9576023391812867e-05,
"loss": 0.0035,
"step": 4162
},
{
"epoch": 12.18,
"learning_rate": 1.956140350877193e-05,
"loss": 0.0005,
"step": 4164
},
{
"epoch": 12.18,
"learning_rate": 1.9546783625730995e-05,
"loss": 0.0001,
"step": 4166
},
{
"epoch": 12.19,
"learning_rate": 1.953216374269006e-05,
"loss": 0.0001,
"step": 4168
},
{
"epoch": 12.19,
"learning_rate": 1.9517543859649122e-05,
"loss": 0.0018,
"step": 4170
},
{
"epoch": 12.2,
"learning_rate": 1.9502923976608187e-05,
"loss": 0.0005,
"step": 4172
},
{
"epoch": 12.2,
"learning_rate": 1.9488304093567253e-05,
"loss": 0.0059,
"step": 4174
},
{
"epoch": 12.21,
"learning_rate": 1.9473684210526315e-05,
"loss": 0.0146,
"step": 4176
},
{
"epoch": 12.22,
"learning_rate": 1.9459064327485383e-05,
"loss": 0.0001,
"step": 4178
},
{
"epoch": 12.22,
"learning_rate": 1.9444444444444445e-05,
"loss": 0.0004,
"step": 4180
},
{
"epoch": 12.23,
"learning_rate": 1.9429824561403507e-05,
"loss": 0.0595,
"step": 4182
},
{
"epoch": 12.23,
"learning_rate": 1.9415204678362576e-05,
"loss": 0.0004,
"step": 4184
},
{
"epoch": 12.24,
"learning_rate": 1.9400584795321638e-05,
"loss": 0.0003,
"step": 4186
},
{
"epoch": 12.25,
"learning_rate": 1.9385964912280704e-05,
"loss": 0.0001,
"step": 4188
},
{
"epoch": 12.25,
"learning_rate": 1.937134502923977e-05,
"loss": 0.0009,
"step": 4190
},
{
"epoch": 12.26,
"learning_rate": 1.935672514619883e-05,
"loss": 0.0011,
"step": 4192
},
{
"epoch": 12.26,
"learning_rate": 1.9342105263157896e-05,
"loss": 0.0002,
"step": 4194
},
{
"epoch": 12.27,
"learning_rate": 1.932748538011696e-05,
"loss": 0.0,
"step": 4196
},
{
"epoch": 12.27,
"learning_rate": 1.9312865497076024e-05,
"loss": 0.001,
"step": 4198
},
{
"epoch": 12.28,
"learning_rate": 1.929824561403509e-05,
"loss": 0.0001,
"step": 4200
},
{
"epoch": 12.29,
"learning_rate": 1.9283625730994154e-05,
"loss": 0.0012,
"step": 4202
},
{
"epoch": 12.29,
"learning_rate": 1.9269005847953216e-05,
"loss": 0.0001,
"step": 4204
},
{
"epoch": 12.3,
"learning_rate": 1.9254385964912282e-05,
"loss": 0.0005,
"step": 4206
},
{
"epoch": 12.3,
"learning_rate": 1.9239766081871347e-05,
"loss": 0.0003,
"step": 4208
},
{
"epoch": 12.31,
"learning_rate": 1.922514619883041e-05,
"loss": 0.003,
"step": 4210
},
{
"epoch": 12.32,
"learning_rate": 1.9210526315789474e-05,
"loss": 0.0001,
"step": 4212
},
{
"epoch": 12.32,
"learning_rate": 1.919590643274854e-05,
"loss": 0.0003,
"step": 4214
},
{
"epoch": 12.33,
"learning_rate": 1.9181286549707602e-05,
"loss": 0.0016,
"step": 4216
},
{
"epoch": 12.33,
"learning_rate": 1.9166666666666667e-05,
"loss": 0.0196,
"step": 4218
},
{
"epoch": 12.34,
"learning_rate": 1.9152046783625733e-05,
"loss": 0.0001,
"step": 4220
},
{
"epoch": 12.35,
"learning_rate": 1.9137426900584795e-05,
"loss": 0.0001,
"step": 4222
},
{
"epoch": 12.35,
"learning_rate": 1.9122807017543863e-05,
"loss": 0.0018,
"step": 4224
},
{
"epoch": 12.36,
"learning_rate": 1.9108187134502925e-05,
"loss": 0.0001,
"step": 4226
},
{
"epoch": 12.36,
"learning_rate": 1.9093567251461987e-05,
"loss": 0.0003,
"step": 4228
},
{
"epoch": 12.37,
"learning_rate": 1.9078947368421056e-05,
"loss": 0.0001,
"step": 4230
},
{
"epoch": 12.37,
"learning_rate": 1.9064327485380118e-05,
"loss": 0.0007,
"step": 4232
},
{
"epoch": 12.38,
"learning_rate": 1.904970760233918e-05,
"loss": 0.0001,
"step": 4234
},
{
"epoch": 12.39,
"learning_rate": 1.903508771929825e-05,
"loss": 0.0003,
"step": 4236
},
{
"epoch": 12.39,
"learning_rate": 1.902046783625731e-05,
"loss": 0.0,
"step": 4238
},
{
"epoch": 12.4,
"learning_rate": 1.9005847953216373e-05,
"loss": 0.0,
"step": 4240
},
{
"epoch": 12.4,
"learning_rate": 1.899122807017544e-05,
"loss": 0.0031,
"step": 4242
},
{
"epoch": 12.41,
"learning_rate": 1.8976608187134504e-05,
"loss": 0.0012,
"step": 4244
},
{
"epoch": 12.42,
"learning_rate": 1.8961988304093566e-05,
"loss": 0.0001,
"step": 4246
},
{
"epoch": 12.42,
"learning_rate": 1.8947368421052634e-05,
"loss": 0.0135,
"step": 4248
},
{
"epoch": 12.43,
"learning_rate": 1.8932748538011696e-05,
"loss": 0.0001,
"step": 4250
},
{
"epoch": 12.43,
"learning_rate": 1.891812865497076e-05,
"loss": 0.0,
"step": 4252
},
{
"epoch": 12.44,
"learning_rate": 1.8903508771929827e-05,
"loss": 0.001,
"step": 4254
},
{
"epoch": 12.44,
"learning_rate": 1.888888888888889e-05,
"loss": 0.0004,
"step": 4256
},
{
"epoch": 12.45,
"learning_rate": 1.8874269005847954e-05,
"loss": 0.002,
"step": 4258
},
{
"epoch": 12.46,
"learning_rate": 1.885964912280702e-05,
"loss": 0.0001,
"step": 4260
},
{
"epoch": 12.46,
"learning_rate": 1.8845029239766082e-05,
"loss": 0.0,
"step": 4262
},
{
"epoch": 12.47,
"learning_rate": 1.8830409356725147e-05,
"loss": 0.0,
"step": 4264
},
{
"epoch": 12.47,
"learning_rate": 1.8815789473684213e-05,
"loss": 0.0003,
"step": 4266
},
{
"epoch": 12.48,
"learning_rate": 1.8801169590643275e-05,
"loss": 0.0072,
"step": 4268
},
{
"epoch": 12.49,
"learning_rate": 1.878654970760234e-05,
"loss": 0.0,
"step": 4270
},
{
"epoch": 12.49,
"learning_rate": 1.8771929824561405e-05,
"loss": 0.0002,
"step": 4272
},
{
"epoch": 12.5,
"learning_rate": 1.8757309941520467e-05,
"loss": 0.0001,
"step": 4274
},
{
"epoch": 12.5,
"learning_rate": 1.8742690058479533e-05,
"loss": 0.0001,
"step": 4276
},
{
"epoch": 12.51,
"learning_rate": 1.8728070175438598e-05,
"loss": 0.0011,
"step": 4278
},
{
"epoch": 12.51,
"learning_rate": 1.871345029239766e-05,
"loss": 0.0003,
"step": 4280
},
{
"epoch": 12.52,
"learning_rate": 1.8698830409356725e-05,
"loss": 0.0002,
"step": 4282
},
{
"epoch": 12.53,
"learning_rate": 1.868421052631579e-05,
"loss": 0.0,
"step": 4284
},
{
"epoch": 12.53,
"learning_rate": 1.8669590643274853e-05,
"loss": 0.0019,
"step": 4286
},
{
"epoch": 12.54,
"learning_rate": 1.8654970760233918e-05,
"loss": 0.0001,
"step": 4288
},
{
"epoch": 12.54,
"learning_rate": 1.8640350877192984e-05,
"loss": 0.0001,
"step": 4290
},
{
"epoch": 12.55,
"learning_rate": 1.8625730994152046e-05,
"loss": 0.0002,
"step": 4292
},
{
"epoch": 12.56,
"learning_rate": 1.861111111111111e-05,
"loss": 0.0297,
"step": 4294
},
{
"epoch": 12.56,
"learning_rate": 1.8596491228070176e-05,
"loss": 0.0007,
"step": 4296
},
{
"epoch": 12.57,
"learning_rate": 1.8581871345029242e-05,
"loss": 0.0018,
"step": 4298
},
{
"epoch": 12.57,
"learning_rate": 1.8567251461988304e-05,
"loss": 0.0022,
"step": 4300
},
{
"epoch": 12.58,
"learning_rate": 1.855263157894737e-05,
"loss": 0.0418,
"step": 4302
},
{
"epoch": 12.58,
"learning_rate": 1.8538011695906434e-05,
"loss": 0.0051,
"step": 4304
},
{
"epoch": 12.59,
"learning_rate": 1.85233918128655e-05,
"loss": 0.0,
"step": 4306
},
{
"epoch": 12.6,
"learning_rate": 1.8508771929824562e-05,
"loss": 0.0159,
"step": 4308
},
{
"epoch": 12.6,
"learning_rate": 1.8494152046783627e-05,
"loss": 0.0244,
"step": 4310
},
{
"epoch": 12.61,
"learning_rate": 1.8479532163742693e-05,
"loss": 0.0001,
"step": 4312
},
{
"epoch": 12.61,
"learning_rate": 1.8464912280701755e-05,
"loss": 0.0001,
"step": 4314
},
{
"epoch": 12.62,
"learning_rate": 1.845029239766082e-05,
"loss": 0.0462,
"step": 4316
},
{
"epoch": 12.63,
"learning_rate": 1.8435672514619885e-05,
"loss": 0.0001,
"step": 4318
},
{
"epoch": 12.63,
"learning_rate": 1.8421052631578947e-05,
"loss": 0.0001,
"step": 4320
},
{
"epoch": 12.64,
"learning_rate": 1.8406432748538013e-05,
"loss": 0.0001,
"step": 4322
},
{
"epoch": 12.64,
"learning_rate": 1.8391812865497078e-05,
"loss": 0.001,
"step": 4324
},
{
"epoch": 12.65,
"learning_rate": 1.837719298245614e-05,
"loss": 0.0,
"step": 4326
},
{
"epoch": 12.65,
"learning_rate": 1.8362573099415205e-05,
"loss": 0.0018,
"step": 4328
},
{
"epoch": 12.66,
"learning_rate": 1.834795321637427e-05,
"loss": 0.0167,
"step": 4330
},
{
"epoch": 12.67,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.0,
"step": 4332
},
{
"epoch": 12.67,
"learning_rate": 1.8318713450292398e-05,
"loss": 0.0003,
"step": 4334
},
{
"epoch": 12.68,
"learning_rate": 1.8304093567251464e-05,
"loss": 0.0004,
"step": 4336
},
{
"epoch": 12.68,
"learning_rate": 1.828947368421053e-05,
"loss": 0.0006,
"step": 4338
},
{
"epoch": 12.69,
"learning_rate": 1.827485380116959e-05,
"loss": 0.0023,
"step": 4340
},
{
"epoch": 12.7,
"learning_rate": 1.8260233918128656e-05,
"loss": 0.0001,
"step": 4342
},
{
"epoch": 12.7,
"learning_rate": 1.8245614035087722e-05,
"loss": 0.001,
"step": 4344
},
{
"epoch": 12.71,
"learning_rate": 1.8230994152046784e-05,
"loss": 0.0,
"step": 4346
},
{
"epoch": 12.71,
"learning_rate": 1.821637426900585e-05,
"loss": 0.0002,
"step": 4348
},
{
"epoch": 12.72,
"learning_rate": 1.8201754385964914e-05,
"loss": 0.0002,
"step": 4350
},
{
"epoch": 12.73,
"learning_rate": 1.8187134502923976e-05,
"loss": 0.0001,
"step": 4352
},
{
"epoch": 12.73,
"learning_rate": 1.8172514619883042e-05,
"loss": 0.2037,
"step": 4354
},
{
"epoch": 12.74,
"learning_rate": 1.8157894736842107e-05,
"loss": 0.0003,
"step": 4356
},
{
"epoch": 12.74,
"learning_rate": 1.814327485380117e-05,
"loss": 0.0003,
"step": 4358
},
{
"epoch": 12.75,
"learning_rate": 1.8128654970760235e-05,
"loss": 0.0895,
"step": 4360
},
{
"epoch": 12.75,
"learning_rate": 1.81140350877193e-05,
"loss": 0.0001,
"step": 4362
},
{
"epoch": 12.76,
"learning_rate": 1.8099415204678362e-05,
"loss": 0.0001,
"step": 4364
},
{
"epoch": 12.77,
"learning_rate": 1.8084795321637427e-05,
"loss": 0.0282,
"step": 4366
},
{
"epoch": 12.77,
"learning_rate": 1.8070175438596493e-05,
"loss": 0.0001,
"step": 4368
},
{
"epoch": 12.78,
"learning_rate": 1.8055555555555555e-05,
"loss": 0.0001,
"step": 4370
},
{
"epoch": 12.78,
"learning_rate": 1.804093567251462e-05,
"loss": 0.0074,
"step": 4372
},
{
"epoch": 12.79,
"learning_rate": 1.8026315789473685e-05,
"loss": 0.0004,
"step": 4374
},
{
"epoch": 12.8,
"learning_rate": 1.8011695906432747e-05,
"loss": 0.0015,
"step": 4376
},
{
"epoch": 12.8,
"learning_rate": 1.7997076023391816e-05,
"loss": 0.0,
"step": 4378
},
{
"epoch": 12.81,
"learning_rate": 1.7982456140350878e-05,
"loss": 0.0001,
"step": 4380
},
{
"epoch": 12.81,
"learning_rate": 1.796783625730994e-05,
"loss": 0.0,
"step": 4382
},
{
"epoch": 12.82,
"learning_rate": 1.795321637426901e-05,
"loss": 0.0109,
"step": 4384
},
{
"epoch": 12.82,
"learning_rate": 1.793859649122807e-05,
"loss": 0.0,
"step": 4386
},
{
"epoch": 12.83,
"learning_rate": 1.7923976608187133e-05,
"loss": 0.0001,
"step": 4388
},
{
"epoch": 12.84,
"learning_rate": 1.7909356725146202e-05,
"loss": 0.0001,
"step": 4390
},
{
"epoch": 12.84,
"learning_rate": 1.7894736842105264e-05,
"loss": 0.0001,
"step": 4392
},
{
"epoch": 12.85,
"learning_rate": 1.788011695906433e-05,
"loss": 0.0,
"step": 4394
},
{
"epoch": 12.85,
"learning_rate": 1.7865497076023394e-05,
"loss": 0.0023,
"step": 4396
},
{
"epoch": 12.86,
"learning_rate": 1.7850877192982456e-05,
"loss": 0.01,
"step": 4398
},
{
"epoch": 12.87,
"learning_rate": 1.7836257309941522e-05,
"loss": 0.0002,
"step": 4400
},
{
"epoch": 12.87,
"learning_rate": 1.7821637426900587e-05,
"loss": 0.0006,
"step": 4402
},
{
"epoch": 12.88,
"learning_rate": 1.780701754385965e-05,
"loss": 0.0,
"step": 4404
},
{
"epoch": 12.88,
"learning_rate": 1.7792397660818715e-05,
"loss": 0.0013,
"step": 4406
},
{
"epoch": 12.89,
"learning_rate": 1.777777777777778e-05,
"loss": 0.0002,
"step": 4408
},
{
"epoch": 12.89,
"learning_rate": 1.7763157894736842e-05,
"loss": 0.0001,
"step": 4410
},
{
"epoch": 12.9,
"learning_rate": 1.7748538011695907e-05,
"loss": 0.0012,
"step": 4412
},
{
"epoch": 12.91,
"learning_rate": 1.7733918128654973e-05,
"loss": 0.0001,
"step": 4414
},
{
"epoch": 12.91,
"learning_rate": 1.7719298245614035e-05,
"loss": 0.0002,
"step": 4416
},
{
"epoch": 12.92,
"learning_rate": 1.77046783625731e-05,
"loss": 0.0,
"step": 4418
},
{
"epoch": 12.92,
"learning_rate": 1.7690058479532165e-05,
"loss": 0.0,
"step": 4420
},
{
"epoch": 12.93,
"learning_rate": 1.7675438596491227e-05,
"loss": 0.0001,
"step": 4422
},
{
"epoch": 12.94,
"learning_rate": 1.7660818713450293e-05,
"loss": 0.0032,
"step": 4424
},
{
"epoch": 12.94,
"learning_rate": 1.7646198830409358e-05,
"loss": 0.0004,
"step": 4426
},
{
"epoch": 12.95,
"learning_rate": 1.763157894736842e-05,
"loss": 0.0028,
"step": 4428
},
{
"epoch": 12.95,
"learning_rate": 1.761695906432749e-05,
"loss": 0.0,
"step": 4430
},
{
"epoch": 12.96,
"learning_rate": 1.760233918128655e-05,
"loss": 0.0,
"step": 4432
},
{
"epoch": 12.96,
"learning_rate": 1.7587719298245613e-05,
"loss": 0.0,
"step": 4434
},
{
"epoch": 12.97,
"learning_rate": 1.7573099415204682e-05,
"loss": 0.0001,
"step": 4436
},
{
"epoch": 12.98,
"learning_rate": 1.7558479532163744e-05,
"loss": 0.0,
"step": 4438
},
{
"epoch": 12.98,
"learning_rate": 1.7543859649122806e-05,
"loss": 0.0002,
"step": 4440
},
{
"epoch": 12.99,
"learning_rate": 1.7529239766081874e-05,
"loss": 0.1006,
"step": 4442
},
{
"epoch": 12.99,
"learning_rate": 1.7514619883040936e-05,
"loss": 0.0039,
"step": 4444
},
{
"epoch": 13.0,
"learning_rate": 1.75e-05,
"loss": 0.0001,
"step": 4446
},
{
"epoch": 13.0,
"eval_bleu": 0.5378866135227707,
"eval_loss": 1.4970338344573975,
"eval_runtime": 36.5071,
"eval_samples_per_second": 9.176,
"eval_steps_per_second": 2.301,
"step": 4446
},
{
"epoch": 13.01,
"learning_rate": 1.7485380116959067e-05,
"loss": 0.0002,
"step": 4448
},
{
"epoch": 13.01,
"learning_rate": 1.747076023391813e-05,
"loss": 0.0002,
"step": 4450
},
{
"epoch": 13.02,
"learning_rate": 1.745614035087719e-05,
"loss": 0.0012,
"step": 4452
},
{
"epoch": 13.02,
"learning_rate": 1.744152046783626e-05,
"loss": 0.0002,
"step": 4454
},
{
"epoch": 13.03,
"learning_rate": 1.7426900584795322e-05,
"loss": 0.0014,
"step": 4456
},
{
"epoch": 13.04,
"learning_rate": 1.7412280701754384e-05,
"loss": 0.0,
"step": 4458
},
{
"epoch": 13.04,
"learning_rate": 1.7397660818713453e-05,
"loss": 0.001,
"step": 4460
},
{
"epoch": 13.05,
"learning_rate": 1.7383040935672515e-05,
"loss": 0.0,
"step": 4462
},
{
"epoch": 13.05,
"learning_rate": 1.736842105263158e-05,
"loss": 0.0,
"step": 4464
},
{
"epoch": 13.06,
"learning_rate": 1.7353801169590645e-05,
"loss": 0.0002,
"step": 4466
},
{
"epoch": 13.06,
"learning_rate": 1.7339181286549707e-05,
"loss": 0.0006,
"step": 4468
},
{
"epoch": 13.07,
"learning_rate": 1.7324561403508773e-05,
"loss": 0.0001,
"step": 4470
},
{
"epoch": 13.08,
"learning_rate": 1.7309941520467838e-05,
"loss": 0.0,
"step": 4472
},
{
"epoch": 13.08,
"learning_rate": 1.72953216374269e-05,
"loss": 0.0056,
"step": 4474
},
{
"epoch": 13.09,
"learning_rate": 1.7280701754385966e-05,
"loss": 0.0001,
"step": 4476
},
{
"epoch": 13.09,
"learning_rate": 1.726608187134503e-05,
"loss": 0.0004,
"step": 4478
},
{
"epoch": 13.1,
"learning_rate": 1.7251461988304093e-05,
"loss": 0.0,
"step": 4480
},
{
"epoch": 13.11,
"learning_rate": 1.723684210526316e-05,
"loss": 0.0001,
"step": 4482
},
{
"epoch": 13.11,
"learning_rate": 1.7222222222222224e-05,
"loss": 0.0004,
"step": 4484
},
{
"epoch": 13.12,
"learning_rate": 1.7207602339181286e-05,
"loss": 0.0001,
"step": 4486
},
{
"epoch": 13.12,
"learning_rate": 1.719298245614035e-05,
"loss": 0.0161,
"step": 4488
},
{
"epoch": 13.13,
"learning_rate": 1.7178362573099416e-05,
"loss": 0.0001,
"step": 4490
},
{
"epoch": 13.13,
"learning_rate": 1.716374269005848e-05,
"loss": 0.0002,
"step": 4492
},
{
"epoch": 13.14,
"learning_rate": 1.7149122807017544e-05,
"loss": 0.0001,
"step": 4494
},
{
"epoch": 13.15,
"learning_rate": 1.713450292397661e-05,
"loss": 0.0,
"step": 4496
},
{
"epoch": 13.15,
"learning_rate": 1.711988304093567e-05,
"loss": 0.0001,
"step": 4498
},
{
"epoch": 13.16,
"learning_rate": 1.7105263157894737e-05,
"loss": 0.002,
"step": 4500
},
{
"epoch": 13.16,
"learning_rate": 1.7090643274853802e-05,
"loss": 0.0085,
"step": 4502
},
{
"epoch": 13.17,
"learning_rate": 1.7076023391812867e-05,
"loss": 0.0001,
"step": 4504
},
{
"epoch": 13.18,
"learning_rate": 1.706140350877193e-05,
"loss": 0.0004,
"step": 4506
},
{
"epoch": 13.18,
"learning_rate": 1.7046783625730995e-05,
"loss": 0.0001,
"step": 4508
},
{
"epoch": 13.19,
"learning_rate": 1.703216374269006e-05,
"loss": 0.0,
"step": 4510
},
{
"epoch": 13.19,
"learning_rate": 1.7017543859649125e-05,
"loss": 0.0006,
"step": 4512
},
{
"epoch": 13.2,
"learning_rate": 1.7002923976608187e-05,
"loss": 0.0005,
"step": 4514
},
{
"epoch": 13.2,
"learning_rate": 1.6988304093567253e-05,
"loss": 0.0005,
"step": 4516
},
{
"epoch": 13.21,
"learning_rate": 1.6973684210526318e-05,
"loss": 0.0205,
"step": 4518
},
{
"epoch": 13.22,
"learning_rate": 1.695906432748538e-05,
"loss": 0.0,
"step": 4520
},
{
"epoch": 13.22,
"learning_rate": 1.6944444444444446e-05,
"loss": 0.0001,
"step": 4522
},
{
"epoch": 13.23,
"learning_rate": 1.692982456140351e-05,
"loss": 0.0,
"step": 4524
},
{
"epoch": 13.23,
"learning_rate": 1.6915204678362573e-05,
"loss": 0.0014,
"step": 4526
},
{
"epoch": 13.24,
"learning_rate": 1.690058479532164e-05,
"loss": 0.0001,
"step": 4528
},
{
"epoch": 13.25,
"learning_rate": 1.6885964912280704e-05,
"loss": 0.0194,
"step": 4530
},
{
"epoch": 13.25,
"learning_rate": 1.6871345029239766e-05,
"loss": 0.0,
"step": 4532
},
{
"epoch": 13.26,
"learning_rate": 1.685672514619883e-05,
"loss": 0.0042,
"step": 4534
},
{
"epoch": 13.26,
"learning_rate": 1.6842105263157896e-05,
"loss": 0.0001,
"step": 4536
},
{
"epoch": 13.27,
"learning_rate": 1.682748538011696e-05,
"loss": 0.0001,
"step": 4538
},
{
"epoch": 13.27,
"learning_rate": 1.6812865497076024e-05,
"loss": 0.0001,
"step": 4540
},
{
"epoch": 13.28,
"learning_rate": 1.679824561403509e-05,
"loss": 0.0001,
"step": 4542
},
{
"epoch": 13.29,
"learning_rate": 1.6783625730994155e-05,
"loss": 0.0,
"step": 4544
},
{
"epoch": 13.29,
"learning_rate": 1.6769005847953217e-05,
"loss": 0.0001,
"step": 4546
},
{
"epoch": 13.3,
"learning_rate": 1.6754385964912282e-05,
"loss": 0.0002,
"step": 4548
},
{
"epoch": 13.3,
"learning_rate": 1.6739766081871347e-05,
"loss": 0.0002,
"step": 4550
},
{
"epoch": 13.31,
"learning_rate": 1.672514619883041e-05,
"loss": 0.0002,
"step": 4552
},
{
"epoch": 13.32,
"learning_rate": 1.6710526315789475e-05,
"loss": 0.0006,
"step": 4554
},
{
"epoch": 13.32,
"learning_rate": 1.669590643274854e-05,
"loss": 0.0003,
"step": 4556
},
{
"epoch": 13.33,
"learning_rate": 1.6681286549707602e-05,
"loss": 0.0006,
"step": 4558
},
{
"epoch": 13.33,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.0003,
"step": 4560
},
{
"epoch": 13.34,
"learning_rate": 1.6652046783625733e-05,
"loss": 0.0005,
"step": 4562
},
{
"epoch": 13.35,
"learning_rate": 1.6637426900584795e-05,
"loss": 0.0,
"step": 4564
},
{
"epoch": 13.35,
"learning_rate": 1.662280701754386e-05,
"loss": 0.003,
"step": 4566
},
{
"epoch": 13.36,
"learning_rate": 1.6608187134502926e-05,
"loss": 0.0002,
"step": 4568
},
{
"epoch": 13.36,
"learning_rate": 1.6593567251461988e-05,
"loss": 0.0663,
"step": 4570
},
{
"epoch": 13.37,
"learning_rate": 1.6578947368421053e-05,
"loss": 0.0006,
"step": 4572
},
{
"epoch": 13.37,
"learning_rate": 1.656432748538012e-05,
"loss": 0.0,
"step": 4574
},
{
"epoch": 13.38,
"learning_rate": 1.654970760233918e-05,
"loss": 0.0002,
"step": 4576
},
{
"epoch": 13.39,
"learning_rate": 1.6535087719298246e-05,
"loss": 0.0002,
"step": 4578
},
{
"epoch": 13.39,
"learning_rate": 1.652046783625731e-05,
"loss": 0.0058,
"step": 4580
},
{
"epoch": 13.4,
"learning_rate": 1.6505847953216373e-05,
"loss": 0.001,
"step": 4582
},
{
"epoch": 13.4,
"learning_rate": 1.6491228070175442e-05,
"loss": 0.0,
"step": 4584
},
{
"epoch": 13.41,
"learning_rate": 1.6476608187134504e-05,
"loss": 0.0002,
"step": 4586
},
{
"epoch": 13.42,
"learning_rate": 1.6461988304093566e-05,
"loss": 0.0001,
"step": 4588
},
{
"epoch": 13.42,
"learning_rate": 1.6447368421052635e-05,
"loss": 0.0001,
"step": 4590
},
{
"epoch": 13.43,
"learning_rate": 1.6432748538011697e-05,
"loss": 0.0034,
"step": 4592
},
{
"epoch": 13.43,
"learning_rate": 1.641812865497076e-05,
"loss": 0.0006,
"step": 4594
},
{
"epoch": 13.44,
"learning_rate": 1.6403508771929827e-05,
"loss": 0.0054,
"step": 4596
},
{
"epoch": 13.44,
"learning_rate": 1.638888888888889e-05,
"loss": 0.0,
"step": 4598
},
{
"epoch": 13.45,
"learning_rate": 1.6374269005847955e-05,
"loss": 0.0,
"step": 4600
},
{
"epoch": 13.46,
"learning_rate": 1.635964912280702e-05,
"loss": 0.0004,
"step": 4602
},
{
"epoch": 13.46,
"learning_rate": 1.6345029239766082e-05,
"loss": 0.0007,
"step": 4604
},
{
"epoch": 13.47,
"learning_rate": 1.6330409356725147e-05,
"loss": 0.0038,
"step": 4606
},
{
"epoch": 13.47,
"learning_rate": 1.6315789473684213e-05,
"loss": 0.0003,
"step": 4608
},
{
"epoch": 13.48,
"learning_rate": 1.6301169590643275e-05,
"loss": 0.0001,
"step": 4610
},
{
"epoch": 13.49,
"learning_rate": 1.628654970760234e-05,
"loss": 0.0115,
"step": 4612
},
{
"epoch": 13.49,
"learning_rate": 1.6271929824561406e-05,
"loss": 0.001,
"step": 4614
},
{
"epoch": 13.5,
"learning_rate": 1.6257309941520468e-05,
"loss": 0.0004,
"step": 4616
},
{
"epoch": 13.5,
"learning_rate": 1.6242690058479533e-05,
"loss": 0.0015,
"step": 4618
},
{
"epoch": 13.51,
"learning_rate": 1.62280701754386e-05,
"loss": 0.0002,
"step": 4620
},
{
"epoch": 13.51,
"learning_rate": 1.621345029239766e-05,
"loss": 0.0,
"step": 4622
},
{
"epoch": 13.52,
"learning_rate": 1.6198830409356726e-05,
"loss": 0.0,
"step": 4624
},
{
"epoch": 13.53,
"learning_rate": 1.618421052631579e-05,
"loss": 0.0001,
"step": 4626
},
{
"epoch": 13.53,
"learning_rate": 1.6169590643274853e-05,
"loss": 0.0001,
"step": 4628
},
{
"epoch": 13.54,
"learning_rate": 1.615497076023392e-05,
"loss": 0.0001,
"step": 4630
},
{
"epoch": 13.54,
"learning_rate": 1.6140350877192984e-05,
"loss": 0.0,
"step": 4632
},
{
"epoch": 13.55,
"learning_rate": 1.6125730994152046e-05,
"loss": 0.0,
"step": 4634
},
{
"epoch": 13.56,
"learning_rate": 1.6111111111111115e-05,
"loss": 0.0,
"step": 4636
},
{
"epoch": 13.56,
"learning_rate": 1.6096491228070177e-05,
"loss": 0.0018,
"step": 4638
},
{
"epoch": 13.57,
"learning_rate": 1.608187134502924e-05,
"loss": 0.0002,
"step": 4640
},
{
"epoch": 13.57,
"learning_rate": 1.6067251461988307e-05,
"loss": 0.0142,
"step": 4642
},
{
"epoch": 13.58,
"learning_rate": 1.605263157894737e-05,
"loss": 0.0003,
"step": 4644
},
{
"epoch": 13.58,
"learning_rate": 1.603801169590643e-05,
"loss": 0.0003,
"step": 4646
},
{
"epoch": 13.59,
"learning_rate": 1.60233918128655e-05,
"loss": 0.0001,
"step": 4648
},
{
"epoch": 13.6,
"learning_rate": 1.6008771929824562e-05,
"loss": 0.0003,
"step": 4650
},
{
"epoch": 13.6,
"learning_rate": 1.5994152046783624e-05,
"loss": 0.0293,
"step": 4652
},
{
"epoch": 13.61,
"learning_rate": 1.5979532163742693e-05,
"loss": 0.0,
"step": 4654
},
{
"epoch": 13.61,
"learning_rate": 1.5964912280701755e-05,
"loss": 0.0009,
"step": 4656
},
{
"epoch": 13.62,
"learning_rate": 1.5950292397660817e-05,
"loss": 0.0032,
"step": 4658
},
{
"epoch": 13.63,
"learning_rate": 1.5935672514619886e-05,
"loss": 0.0001,
"step": 4660
},
{
"epoch": 13.63,
"learning_rate": 1.5921052631578948e-05,
"loss": 0.0,
"step": 4662
},
{
"epoch": 13.64,
"learning_rate": 1.5906432748538013e-05,
"loss": 0.0002,
"step": 4664
},
{
"epoch": 13.64,
"learning_rate": 1.589181286549708e-05,
"loss": 0.0,
"step": 4666
},
{
"epoch": 13.65,
"learning_rate": 1.587719298245614e-05,
"loss": 0.0001,
"step": 4668
},
{
"epoch": 13.65,
"learning_rate": 1.5862573099415206e-05,
"loss": 0.0001,
"step": 4670
},
{
"epoch": 13.66,
"learning_rate": 1.584795321637427e-05,
"loss": 0.0,
"step": 4672
},
{
"epoch": 13.67,
"learning_rate": 1.5833333333333333e-05,
"loss": 0.0002,
"step": 4674
},
{
"epoch": 13.67,
"learning_rate": 1.58187134502924e-05,
"loss": 0.0002,
"step": 4676
},
{
"epoch": 13.68,
"learning_rate": 1.5804093567251464e-05,
"loss": 0.0004,
"step": 4678
},
{
"epoch": 13.68,
"learning_rate": 1.5789473684210526e-05,
"loss": 0.0001,
"step": 4680
},
{
"epoch": 13.69,
"learning_rate": 1.577485380116959e-05,
"loss": 0.0,
"step": 4682
},
{
"epoch": 13.7,
"learning_rate": 1.5760233918128657e-05,
"loss": 0.0,
"step": 4684
},
{
"epoch": 13.7,
"learning_rate": 1.574561403508772e-05,
"loss": 0.0001,
"step": 4686
},
{
"epoch": 13.71,
"learning_rate": 1.5730994152046784e-05,
"loss": 0.0,
"step": 4688
},
{
"epoch": 13.71,
"learning_rate": 1.571637426900585e-05,
"loss": 0.0001,
"step": 4690
},
{
"epoch": 13.72,
"learning_rate": 1.570175438596491e-05,
"loss": 0.0,
"step": 4692
},
{
"epoch": 13.73,
"learning_rate": 1.5687134502923977e-05,
"loss": 0.0003,
"step": 4694
},
{
"epoch": 13.73,
"learning_rate": 1.5672514619883042e-05,
"loss": 0.1528,
"step": 4696
},
{
"epoch": 13.74,
"learning_rate": 1.5657894736842104e-05,
"loss": 0.0001,
"step": 4698
},
{
"epoch": 13.74,
"learning_rate": 1.564327485380117e-05,
"loss": 0.0003,
"step": 4700
},
{
"epoch": 13.75,
"learning_rate": 1.5628654970760235e-05,
"loss": 0.0025,
"step": 4702
},
{
"epoch": 13.75,
"learning_rate": 1.56140350877193e-05,
"loss": 0.0012,
"step": 4704
},
{
"epoch": 13.76,
"learning_rate": 1.5599415204678362e-05,
"loss": 0.0007,
"step": 4706
},
{
"epoch": 13.77,
"learning_rate": 1.5584795321637428e-05,
"loss": 0.001,
"step": 4708
},
{
"epoch": 13.77,
"learning_rate": 1.5570175438596493e-05,
"loss": 0.0123,
"step": 4710
},
{
"epoch": 13.78,
"learning_rate": 1.5555555555555555e-05,
"loss": 0.0,
"step": 4712
},
{
"epoch": 13.78,
"learning_rate": 1.554093567251462e-05,
"loss": 0.0019,
"step": 4714
},
{
"epoch": 13.79,
"learning_rate": 1.5526315789473686e-05,
"loss": 0.0013,
"step": 4716
},
{
"epoch": 13.8,
"learning_rate": 1.551169590643275e-05,
"loss": 0.0001,
"step": 4718
},
{
"epoch": 13.8,
"learning_rate": 1.5497076023391813e-05,
"loss": 0.0,
"step": 4720
},
{
"epoch": 13.81,
"learning_rate": 1.548245614035088e-05,
"loss": 0.0002,
"step": 4722
},
{
"epoch": 13.81,
"learning_rate": 1.5467836257309944e-05,
"loss": 0.0006,
"step": 4724
},
{
"epoch": 13.82,
"learning_rate": 1.5453216374269006e-05,
"loss": 0.0001,
"step": 4726
},
{
"epoch": 13.82,
"learning_rate": 1.543859649122807e-05,
"loss": 0.0002,
"step": 4728
},
{
"epoch": 13.83,
"learning_rate": 1.5423976608187137e-05,
"loss": 0.0,
"step": 4730
},
{
"epoch": 13.84,
"learning_rate": 1.54093567251462e-05,
"loss": 0.0003,
"step": 4732
},
{
"epoch": 13.84,
"learning_rate": 1.5394736842105264e-05,
"loss": 0.0001,
"step": 4734
},
{
"epoch": 13.85,
"learning_rate": 1.538011695906433e-05,
"loss": 0.0,
"step": 4736
},
{
"epoch": 13.85,
"learning_rate": 1.536549707602339e-05,
"loss": 0.002,
"step": 4738
},
{
"epoch": 13.86,
"learning_rate": 1.5350877192982457e-05,
"loss": 0.0001,
"step": 4740
},
{
"epoch": 13.87,
"learning_rate": 1.5336257309941522e-05,
"loss": 0.0001,
"step": 4742
},
{
"epoch": 13.87,
"learning_rate": 1.5321637426900587e-05,
"loss": 0.0,
"step": 4744
},
{
"epoch": 13.88,
"learning_rate": 1.530701754385965e-05,
"loss": 0.0013,
"step": 4746
},
{
"epoch": 13.88,
"learning_rate": 1.5292397660818715e-05,
"loss": 0.0,
"step": 4748
},
{
"epoch": 13.89,
"learning_rate": 1.527777777777778e-05,
"loss": 0.0,
"step": 4750
},
{
"epoch": 13.89,
"learning_rate": 1.5263157894736842e-05,
"loss": 0.0001,
"step": 4752
},
{
"epoch": 13.9,
"learning_rate": 1.5248538011695906e-05,
"loss": 0.0053,
"step": 4754
},
{
"epoch": 13.91,
"learning_rate": 1.5233918128654973e-05,
"loss": 0.0,
"step": 4756
},
{
"epoch": 13.91,
"learning_rate": 1.5219298245614037e-05,
"loss": 0.0002,
"step": 4758
},
{
"epoch": 13.92,
"learning_rate": 1.5204678362573099e-05,
"loss": 0.0002,
"step": 4760
},
{
"epoch": 13.92,
"learning_rate": 1.5190058479532166e-05,
"loss": 0.0001,
"step": 4762
},
{
"epoch": 13.93,
"learning_rate": 1.517543859649123e-05,
"loss": 0.0003,
"step": 4764
},
{
"epoch": 13.94,
"learning_rate": 1.5160818713450291e-05,
"loss": 0.0024,
"step": 4766
},
{
"epoch": 13.94,
"learning_rate": 1.5146198830409358e-05,
"loss": 0.0043,
"step": 4768
},
{
"epoch": 13.95,
"learning_rate": 1.5131578947368422e-05,
"loss": 0.0002,
"step": 4770
},
{
"epoch": 13.95,
"learning_rate": 1.5116959064327486e-05,
"loss": 0.0002,
"step": 4772
},
{
"epoch": 13.96,
"learning_rate": 1.5102339181286551e-05,
"loss": 0.0295,
"step": 4774
},
{
"epoch": 13.96,
"learning_rate": 1.5087719298245615e-05,
"loss": 0.0173,
"step": 4776
},
{
"epoch": 13.97,
"learning_rate": 1.5073099415204679e-05,
"loss": 0.0005,
"step": 4778
},
{
"epoch": 13.98,
"learning_rate": 1.5058479532163744e-05,
"loss": 0.0034,
"step": 4780
},
{
"epoch": 13.98,
"learning_rate": 1.5043859649122808e-05,
"loss": 0.0,
"step": 4782
},
{
"epoch": 13.99,
"learning_rate": 1.5029239766081873e-05,
"loss": 0.0002,
"step": 4784
},
{
"epoch": 13.99,
"learning_rate": 1.5014619883040937e-05,
"loss": 0.035,
"step": 4786
},
{
"epoch": 14.0,
"learning_rate": 1.5e-05,
"loss": 0.0001,
"step": 4788
},
{
"epoch": 14.0,
"eval_bleu": 0.5452640266452384,
"eval_loss": 1.5289764404296875,
"eval_runtime": 36.2527,
"eval_samples_per_second": 9.241,
"eval_steps_per_second": 2.317,
"step": 4788
}
],
"max_steps": 6840,
"num_train_epochs": 20,
"total_flos": 4.0718568843264e+16,
"trial_name": null,
"trial_params": null
}