clickbait_spoiling_passage / trainer_state.json
Tugay's picture
Initial
6637b0d
{
"best_metric": 0.24766209564477684,
"best_model_checkpoint": "t5-results/checkpoint-2552",
"epoch": 8.0,
"global_step": 2552,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.996865203761756e-05,
"loss": 0.9455,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.993730407523511e-05,
"loss": 1.6682,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 4.9905956112852665e-05,
"loss": 1.8287,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 4.987460815047022e-05,
"loss": 0.4417,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 4.9843260188087774e-05,
"loss": 0.4163,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 4.9811912225705335e-05,
"loss": 2.1209,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 4.978056426332289e-05,
"loss": 0.2798,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 4.9749216300940444e-05,
"loss": 1.947,
"step": 16
},
{
"epoch": 0.06,
"learning_rate": 4.971786833855799e-05,
"loss": 1.2442,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 4.968652037617555e-05,
"loss": 0.3761,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 4.9655172413793107e-05,
"loss": 0.9298,
"step": 22
},
{
"epoch": 0.08,
"learning_rate": 4.962382445141066e-05,
"loss": 1.3809,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 4.9592476489028215e-05,
"loss": 0.3682,
"step": 26
},
{
"epoch": 0.09,
"learning_rate": 4.956112852664577e-05,
"loss": 0.2959,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 4.9529780564263324e-05,
"loss": 0.2546,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 4.949843260188088e-05,
"loss": 0.4341,
"step": 32
},
{
"epoch": 0.11,
"learning_rate": 4.946708463949843e-05,
"loss": 0.1989,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 4.9435736677115994e-05,
"loss": 0.2539,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 4.940438871473355e-05,
"loss": 0.7307,
"step": 38
},
{
"epoch": 0.13,
"learning_rate": 4.93730407523511e-05,
"loss": 0.8249,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 4.934169278996865e-05,
"loss": 0.7287,
"step": 42
},
{
"epoch": 0.14,
"learning_rate": 4.931034482758621e-05,
"loss": 0.3686,
"step": 44
},
{
"epoch": 0.14,
"learning_rate": 4.9278996865203765e-05,
"loss": 1.3282,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 4.924764890282132e-05,
"loss": 0.4953,
"step": 48
},
{
"epoch": 0.16,
"learning_rate": 4.9216300940438874e-05,
"loss": 0.2742,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 4.918495297805643e-05,
"loss": 0.6305,
"step": 52
},
{
"epoch": 0.17,
"learning_rate": 4.915360501567398e-05,
"loss": 1.459,
"step": 54
},
{
"epoch": 0.18,
"learning_rate": 4.9122257053291537e-05,
"loss": 1.2348,
"step": 56
},
{
"epoch": 0.18,
"learning_rate": 4.909090909090909e-05,
"loss": 1.0512,
"step": 58
},
{
"epoch": 0.19,
"learning_rate": 4.905956112852665e-05,
"loss": 1.0997,
"step": 60
},
{
"epoch": 0.19,
"learning_rate": 4.9028213166144206e-05,
"loss": 0.2254,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 4.899686520376176e-05,
"loss": 0.5962,
"step": 64
},
{
"epoch": 0.21,
"learning_rate": 4.896551724137931e-05,
"loss": 0.94,
"step": 66
},
{
"epoch": 0.21,
"learning_rate": 4.893416927899687e-05,
"loss": 1.0733,
"step": 68
},
{
"epoch": 0.22,
"learning_rate": 4.8902821316614424e-05,
"loss": 0.6645,
"step": 70
},
{
"epoch": 0.23,
"learning_rate": 4.887147335423198e-05,
"loss": 1.1294,
"step": 72
},
{
"epoch": 0.23,
"learning_rate": 4.884012539184953e-05,
"loss": 1.0914,
"step": 74
},
{
"epoch": 0.24,
"learning_rate": 4.8808777429467086e-05,
"loss": 0.261,
"step": 76
},
{
"epoch": 0.24,
"learning_rate": 4.877742946708464e-05,
"loss": 0.2536,
"step": 78
},
{
"epoch": 0.25,
"learning_rate": 4.8746081504702195e-05,
"loss": 0.5267,
"step": 80
},
{
"epoch": 0.26,
"learning_rate": 4.871473354231975e-05,
"loss": 0.4753,
"step": 82
},
{
"epoch": 0.26,
"learning_rate": 4.868338557993731e-05,
"loss": 1.0177,
"step": 84
},
{
"epoch": 0.27,
"learning_rate": 4.8652037617554865e-05,
"loss": 0.2379,
"step": 86
},
{
"epoch": 0.28,
"learning_rate": 4.862068965517241e-05,
"loss": 0.495,
"step": 88
},
{
"epoch": 0.28,
"learning_rate": 4.858934169278997e-05,
"loss": 0.1808,
"step": 90
},
{
"epoch": 0.29,
"learning_rate": 4.855799373040753e-05,
"loss": 0.2945,
"step": 92
},
{
"epoch": 0.29,
"learning_rate": 4.852664576802508e-05,
"loss": 0.6358,
"step": 94
},
{
"epoch": 0.3,
"learning_rate": 4.8495297805642636e-05,
"loss": 0.6127,
"step": 96
},
{
"epoch": 0.31,
"learning_rate": 4.846394984326019e-05,
"loss": 0.4608,
"step": 98
},
{
"epoch": 0.31,
"learning_rate": 4.8432601880877745e-05,
"loss": 0.7172,
"step": 100
},
{
"epoch": 0.32,
"learning_rate": 4.84012539184953e-05,
"loss": 0.1879,
"step": 102
},
{
"epoch": 0.33,
"learning_rate": 4.8369905956112854e-05,
"loss": 1.0405,
"step": 104
},
{
"epoch": 0.33,
"learning_rate": 4.833855799373041e-05,
"loss": 0.6024,
"step": 106
},
{
"epoch": 0.34,
"learning_rate": 4.830721003134797e-05,
"loss": 1.1472,
"step": 108
},
{
"epoch": 0.34,
"learning_rate": 4.827586206896552e-05,
"loss": 0.7647,
"step": 110
},
{
"epoch": 0.35,
"learning_rate": 4.824451410658307e-05,
"loss": 0.9441,
"step": 112
},
{
"epoch": 0.36,
"learning_rate": 4.8213166144200625e-05,
"loss": 1.0265,
"step": 114
},
{
"epoch": 0.36,
"learning_rate": 4.8181818181818186e-05,
"loss": 0.1369,
"step": 116
},
{
"epoch": 0.37,
"learning_rate": 4.815047021943574e-05,
"loss": 0.6012,
"step": 118
},
{
"epoch": 0.38,
"learning_rate": 4.8119122257053295e-05,
"loss": 1.6127,
"step": 120
},
{
"epoch": 0.38,
"learning_rate": 4.808777429467085e-05,
"loss": 1.2571,
"step": 122
},
{
"epoch": 0.39,
"learning_rate": 4.8056426332288403e-05,
"loss": 0.8723,
"step": 124
},
{
"epoch": 0.39,
"learning_rate": 4.802507836990596e-05,
"loss": 0.8984,
"step": 126
},
{
"epoch": 0.4,
"learning_rate": 4.799373040752351e-05,
"loss": 1.1541,
"step": 128
},
{
"epoch": 0.41,
"learning_rate": 4.7962382445141066e-05,
"loss": 0.3226,
"step": 130
},
{
"epoch": 0.41,
"learning_rate": 4.793103448275863e-05,
"loss": 0.2267,
"step": 132
},
{
"epoch": 0.42,
"learning_rate": 4.789968652037618e-05,
"loss": 0.7902,
"step": 134
},
{
"epoch": 0.43,
"learning_rate": 4.786833855799373e-05,
"loss": 1.8272,
"step": 136
},
{
"epoch": 0.43,
"learning_rate": 4.7836990595611284e-05,
"loss": 0.396,
"step": 138
},
{
"epoch": 0.44,
"learning_rate": 4.7805642633228845e-05,
"loss": 0.6937,
"step": 140
},
{
"epoch": 0.45,
"learning_rate": 4.77742946708464e-05,
"loss": 1.0419,
"step": 142
},
{
"epoch": 0.45,
"learning_rate": 4.774294670846395e-05,
"loss": 0.413,
"step": 144
},
{
"epoch": 0.46,
"learning_rate": 4.771159874608151e-05,
"loss": 1.9694,
"step": 146
},
{
"epoch": 0.46,
"learning_rate": 4.768025078369906e-05,
"loss": 0.3958,
"step": 148
},
{
"epoch": 0.47,
"learning_rate": 4.7648902821316616e-05,
"loss": 0.2723,
"step": 150
},
{
"epoch": 0.48,
"learning_rate": 4.761755485893417e-05,
"loss": 0.2836,
"step": 152
},
{
"epoch": 0.48,
"learning_rate": 4.7586206896551725e-05,
"loss": 0.2555,
"step": 154
},
{
"epoch": 0.49,
"learning_rate": 4.7554858934169286e-05,
"loss": 0.2959,
"step": 156
},
{
"epoch": 0.5,
"learning_rate": 4.752351097178684e-05,
"loss": 0.1831,
"step": 158
},
{
"epoch": 0.5,
"learning_rate": 4.749216300940439e-05,
"loss": 0.5239,
"step": 160
},
{
"epoch": 0.51,
"learning_rate": 4.746081504702194e-05,
"loss": 0.5796,
"step": 162
},
{
"epoch": 0.51,
"learning_rate": 4.74294670846395e-05,
"loss": 0.993,
"step": 164
},
{
"epoch": 0.52,
"learning_rate": 4.739811912225706e-05,
"loss": 0.8317,
"step": 166
},
{
"epoch": 0.53,
"learning_rate": 4.736677115987461e-05,
"loss": 2.053,
"step": 168
},
{
"epoch": 0.53,
"learning_rate": 4.7335423197492166e-05,
"loss": 1.1727,
"step": 170
},
{
"epoch": 0.54,
"learning_rate": 4.730407523510972e-05,
"loss": 0.3161,
"step": 172
},
{
"epoch": 0.55,
"learning_rate": 4.7272727272727275e-05,
"loss": 1.2573,
"step": 174
},
{
"epoch": 0.55,
"learning_rate": 4.724137931034483e-05,
"loss": 1.0586,
"step": 176
},
{
"epoch": 0.56,
"learning_rate": 4.721003134796238e-05,
"loss": 0.3037,
"step": 178
},
{
"epoch": 0.56,
"learning_rate": 4.7178683385579944e-05,
"loss": 0.6061,
"step": 180
},
{
"epoch": 0.57,
"learning_rate": 4.714733542319749e-05,
"loss": 0.3963,
"step": 182
},
{
"epoch": 0.58,
"learning_rate": 4.7115987460815046e-05,
"loss": 0.8247,
"step": 184
},
{
"epoch": 0.58,
"learning_rate": 4.70846394984326e-05,
"loss": 1.1442,
"step": 186
},
{
"epoch": 0.59,
"learning_rate": 4.705329153605016e-05,
"loss": 0.6141,
"step": 188
},
{
"epoch": 0.6,
"learning_rate": 4.7021943573667716e-05,
"loss": 0.3434,
"step": 190
},
{
"epoch": 0.6,
"learning_rate": 4.699059561128527e-05,
"loss": 0.7776,
"step": 192
},
{
"epoch": 0.61,
"learning_rate": 4.695924764890282e-05,
"loss": 0.7379,
"step": 194
},
{
"epoch": 0.61,
"learning_rate": 4.692789968652038e-05,
"loss": 0.855,
"step": 196
},
{
"epoch": 0.62,
"learning_rate": 4.689655172413793e-05,
"loss": 0.1466,
"step": 198
},
{
"epoch": 0.63,
"learning_rate": 4.686520376175549e-05,
"loss": 0.3229,
"step": 200
},
{
"epoch": 0.63,
"learning_rate": 4.683385579937304e-05,
"loss": 0.2641,
"step": 202
},
{
"epoch": 0.64,
"learning_rate": 4.68025078369906e-05,
"loss": 0.1557,
"step": 204
},
{
"epoch": 0.65,
"learning_rate": 4.677115987460815e-05,
"loss": 0.4341,
"step": 206
},
{
"epoch": 0.65,
"learning_rate": 4.6739811912225705e-05,
"loss": 1.5467,
"step": 208
},
{
"epoch": 0.66,
"learning_rate": 4.670846394984326e-05,
"loss": 1.9732,
"step": 210
},
{
"epoch": 0.66,
"learning_rate": 4.667711598746082e-05,
"loss": 0.5423,
"step": 212
},
{
"epoch": 0.67,
"learning_rate": 4.6645768025078374e-05,
"loss": 1.1553,
"step": 214
},
{
"epoch": 0.68,
"learning_rate": 4.661442006269593e-05,
"loss": 0.2762,
"step": 216
},
{
"epoch": 0.68,
"learning_rate": 4.6583072100313476e-05,
"loss": 0.5309,
"step": 218
},
{
"epoch": 0.69,
"learning_rate": 4.655172413793104e-05,
"loss": 0.7831,
"step": 220
},
{
"epoch": 0.7,
"learning_rate": 4.652037617554859e-05,
"loss": 0.5252,
"step": 222
},
{
"epoch": 0.7,
"learning_rate": 4.6489028213166146e-05,
"loss": 0.8883,
"step": 224
},
{
"epoch": 0.71,
"learning_rate": 4.64576802507837e-05,
"loss": 0.9255,
"step": 226
},
{
"epoch": 0.71,
"learning_rate": 4.642633228840126e-05,
"loss": 0.619,
"step": 228
},
{
"epoch": 0.72,
"learning_rate": 4.639498432601881e-05,
"loss": 0.1687,
"step": 230
},
{
"epoch": 0.73,
"learning_rate": 4.636363636363636e-05,
"loss": 0.1271,
"step": 232
},
{
"epoch": 0.73,
"learning_rate": 4.633228840125392e-05,
"loss": 0.2336,
"step": 234
},
{
"epoch": 0.74,
"learning_rate": 4.630094043887148e-05,
"loss": 0.6617,
"step": 236
},
{
"epoch": 0.75,
"learning_rate": 4.626959247648903e-05,
"loss": 0.2228,
"step": 238
},
{
"epoch": 0.75,
"learning_rate": 4.623824451410659e-05,
"loss": 0.1894,
"step": 240
},
{
"epoch": 0.76,
"learning_rate": 4.6206896551724135e-05,
"loss": 0.235,
"step": 242
},
{
"epoch": 0.76,
"learning_rate": 4.6175548589341696e-05,
"loss": 0.4784,
"step": 244
},
{
"epoch": 0.77,
"learning_rate": 4.614420062695925e-05,
"loss": 0.1157,
"step": 246
},
{
"epoch": 0.78,
"learning_rate": 4.6112852664576805e-05,
"loss": 0.3989,
"step": 248
},
{
"epoch": 0.78,
"learning_rate": 4.608150470219436e-05,
"loss": 0.8925,
"step": 250
},
{
"epoch": 0.79,
"learning_rate": 4.605015673981192e-05,
"loss": 0.2321,
"step": 252
},
{
"epoch": 0.8,
"learning_rate": 4.601880877742947e-05,
"loss": 0.679,
"step": 254
},
{
"epoch": 0.8,
"learning_rate": 4.598746081504702e-05,
"loss": 0.2459,
"step": 256
},
{
"epoch": 0.81,
"learning_rate": 4.5956112852664576e-05,
"loss": 1.0986,
"step": 258
},
{
"epoch": 0.82,
"learning_rate": 4.592476489028214e-05,
"loss": 0.8269,
"step": 260
},
{
"epoch": 0.82,
"learning_rate": 4.589341692789969e-05,
"loss": 1.0066,
"step": 262
},
{
"epoch": 0.83,
"learning_rate": 4.586206896551724e-05,
"loss": 0.4048,
"step": 264
},
{
"epoch": 0.83,
"learning_rate": 4.583072100313479e-05,
"loss": 0.9815,
"step": 266
},
{
"epoch": 0.84,
"learning_rate": 4.5799373040752354e-05,
"loss": 0.2814,
"step": 268
},
{
"epoch": 0.85,
"learning_rate": 4.576802507836991e-05,
"loss": 0.169,
"step": 270
},
{
"epoch": 0.85,
"learning_rate": 4.573667711598746e-05,
"loss": 0.7363,
"step": 272
},
{
"epoch": 0.86,
"learning_rate": 4.570532915360502e-05,
"loss": 0.1314,
"step": 274
},
{
"epoch": 0.87,
"learning_rate": 4.567398119122257e-05,
"loss": 0.6374,
"step": 276
},
{
"epoch": 0.87,
"learning_rate": 4.5642633228840126e-05,
"loss": 0.9378,
"step": 278
},
{
"epoch": 0.88,
"learning_rate": 4.561128526645768e-05,
"loss": 0.3465,
"step": 280
},
{
"epoch": 0.88,
"learning_rate": 4.5579937304075235e-05,
"loss": 0.1601,
"step": 282
},
{
"epoch": 0.89,
"learning_rate": 4.5548589341692796e-05,
"loss": 0.318,
"step": 284
},
{
"epoch": 0.9,
"learning_rate": 4.551724137931035e-05,
"loss": 0.9829,
"step": 286
},
{
"epoch": 0.9,
"learning_rate": 4.54858934169279e-05,
"loss": 0.4091,
"step": 288
},
{
"epoch": 0.91,
"learning_rate": 4.545454545454546e-05,
"loss": 0.1917,
"step": 290
},
{
"epoch": 0.92,
"learning_rate": 4.542319749216301e-05,
"loss": 0.3441,
"step": 292
},
{
"epoch": 0.92,
"learning_rate": 4.539184952978057e-05,
"loss": 0.7346,
"step": 294
},
{
"epoch": 0.93,
"learning_rate": 4.536050156739812e-05,
"loss": 0.9984,
"step": 296
},
{
"epoch": 0.93,
"learning_rate": 4.5329153605015676e-05,
"loss": 0.8257,
"step": 298
},
{
"epoch": 0.94,
"learning_rate": 4.529780564263323e-05,
"loss": 0.265,
"step": 300
},
{
"epoch": 0.95,
"learning_rate": 4.5266457680250784e-05,
"loss": 0.4272,
"step": 302
},
{
"epoch": 0.95,
"learning_rate": 4.523510971786834e-05,
"loss": 0.4186,
"step": 304
},
{
"epoch": 0.96,
"learning_rate": 4.520376175548589e-05,
"loss": 0.2057,
"step": 306
},
{
"epoch": 0.97,
"learning_rate": 4.5172413793103454e-05,
"loss": 1.2554,
"step": 308
},
{
"epoch": 0.97,
"learning_rate": 4.514106583072101e-05,
"loss": 0.8404,
"step": 310
},
{
"epoch": 0.98,
"learning_rate": 4.5109717868338556e-05,
"loss": 0.2499,
"step": 312
},
{
"epoch": 0.98,
"learning_rate": 4.507836990595612e-05,
"loss": 1.1946,
"step": 314
},
{
"epoch": 0.99,
"learning_rate": 4.504702194357367e-05,
"loss": 0.3571,
"step": 316
},
{
"epoch": 1.0,
"learning_rate": 4.5015673981191226e-05,
"loss": 1.0764,
"step": 318
},
{
"epoch": 1.0,
"eval_bleu": 0.2125382422737567,
"eval_loss": 0.5874338746070862,
"eval_runtime": 76.4643,
"eval_samples_per_second": 4.211,
"eval_steps_per_second": 1.059,
"step": 319
},
{
"epoch": 1.0,
"learning_rate": 4.498432601880878e-05,
"loss": 1.09,
"step": 320
},
{
"epoch": 1.01,
"learning_rate": 4.4952978056426334e-05,
"loss": 0.3573,
"step": 322
},
{
"epoch": 1.02,
"learning_rate": 4.492163009404389e-05,
"loss": 0.8303,
"step": 324
},
{
"epoch": 1.02,
"learning_rate": 4.489028213166144e-05,
"loss": 0.1176,
"step": 326
},
{
"epoch": 1.03,
"learning_rate": 4.4858934169279e-05,
"loss": 0.0794,
"step": 328
},
{
"epoch": 1.03,
"learning_rate": 4.482758620689655e-05,
"loss": 1.3543,
"step": 330
},
{
"epoch": 1.04,
"learning_rate": 4.479623824451411e-05,
"loss": 0.1834,
"step": 332
},
{
"epoch": 1.05,
"learning_rate": 4.476489028213167e-05,
"loss": 0.9918,
"step": 334
},
{
"epoch": 1.05,
"learning_rate": 4.4733542319749214e-05,
"loss": 0.1363,
"step": 336
},
{
"epoch": 1.06,
"learning_rate": 4.4702194357366776e-05,
"loss": 0.7989,
"step": 338
},
{
"epoch": 1.07,
"learning_rate": 4.467084639498433e-05,
"loss": 0.9555,
"step": 340
},
{
"epoch": 1.07,
"learning_rate": 4.4639498432601884e-05,
"loss": 0.1831,
"step": 342
},
{
"epoch": 1.08,
"learning_rate": 4.460815047021944e-05,
"loss": 0.2329,
"step": 344
},
{
"epoch": 1.08,
"learning_rate": 4.457680250783699e-05,
"loss": 0.4434,
"step": 346
},
{
"epoch": 1.09,
"learning_rate": 4.454545454545455e-05,
"loss": 0.1666,
"step": 348
},
{
"epoch": 1.1,
"learning_rate": 4.45141065830721e-05,
"loss": 0.2148,
"step": 350
},
{
"epoch": 1.1,
"learning_rate": 4.4482758620689656e-05,
"loss": 1.0281,
"step": 352
},
{
"epoch": 1.11,
"learning_rate": 4.445141065830721e-05,
"loss": 0.3049,
"step": 354
},
{
"epoch": 1.12,
"learning_rate": 4.442006269592477e-05,
"loss": 1.0153,
"step": 356
},
{
"epoch": 1.12,
"learning_rate": 4.438871473354232e-05,
"loss": 0.1113,
"step": 358
},
{
"epoch": 1.13,
"learning_rate": 4.435736677115987e-05,
"loss": 0.5987,
"step": 360
},
{
"epoch": 1.13,
"learning_rate": 4.4326018808777434e-05,
"loss": 0.1614,
"step": 362
},
{
"epoch": 1.14,
"learning_rate": 4.429467084639499e-05,
"loss": 0.7884,
"step": 364
},
{
"epoch": 1.15,
"learning_rate": 4.426332288401254e-05,
"loss": 1.1267,
"step": 366
},
{
"epoch": 1.15,
"learning_rate": 4.42319749216301e-05,
"loss": 0.1548,
"step": 368
},
{
"epoch": 1.16,
"learning_rate": 4.420062695924765e-05,
"loss": 0.3899,
"step": 370
},
{
"epoch": 1.17,
"learning_rate": 4.4169278996865206e-05,
"loss": 0.3485,
"step": 372
},
{
"epoch": 1.17,
"learning_rate": 4.413793103448276e-05,
"loss": 0.4649,
"step": 374
},
{
"epoch": 1.18,
"learning_rate": 4.4106583072100314e-05,
"loss": 0.2558,
"step": 376
},
{
"epoch": 1.18,
"learning_rate": 4.407523510971787e-05,
"loss": 0.4263,
"step": 378
},
{
"epoch": 1.19,
"learning_rate": 4.404388714733543e-05,
"loss": 0.3739,
"step": 380
},
{
"epoch": 1.2,
"learning_rate": 4.401253918495298e-05,
"loss": 0.5223,
"step": 382
},
{
"epoch": 1.2,
"learning_rate": 4.398119122257053e-05,
"loss": 0.1385,
"step": 384
},
{
"epoch": 1.21,
"learning_rate": 4.394984326018809e-05,
"loss": 0.4854,
"step": 386
},
{
"epoch": 1.22,
"learning_rate": 4.391849529780565e-05,
"loss": 0.9741,
"step": 388
},
{
"epoch": 1.22,
"learning_rate": 4.38871473354232e-05,
"loss": 1.0183,
"step": 390
},
{
"epoch": 1.23,
"learning_rate": 4.3855799373040755e-05,
"loss": 1.0496,
"step": 392
},
{
"epoch": 1.24,
"learning_rate": 4.382445141065831e-05,
"loss": 0.2626,
"step": 394
},
{
"epoch": 1.24,
"learning_rate": 4.3793103448275864e-05,
"loss": 1.2788,
"step": 396
},
{
"epoch": 1.25,
"learning_rate": 4.376175548589342e-05,
"loss": 0.4179,
"step": 398
},
{
"epoch": 1.25,
"learning_rate": 4.373040752351097e-05,
"loss": 0.1952,
"step": 400
},
{
"epoch": 1.26,
"learning_rate": 4.369905956112853e-05,
"loss": 0.7785,
"step": 402
},
{
"epoch": 1.27,
"learning_rate": 4.366771159874609e-05,
"loss": 0.1975,
"step": 404
},
{
"epoch": 1.27,
"learning_rate": 4.3636363636363636e-05,
"loss": 0.488,
"step": 406
},
{
"epoch": 1.28,
"learning_rate": 4.360501567398119e-05,
"loss": 0.4872,
"step": 408
},
{
"epoch": 1.29,
"learning_rate": 4.357366771159875e-05,
"loss": 0.205,
"step": 410
},
{
"epoch": 1.29,
"learning_rate": 4.3542319749216305e-05,
"loss": 0.2869,
"step": 412
},
{
"epoch": 1.3,
"learning_rate": 4.351097178683386e-05,
"loss": 0.4398,
"step": 414
},
{
"epoch": 1.3,
"learning_rate": 4.3479623824451414e-05,
"loss": 0.8419,
"step": 416
},
{
"epoch": 1.31,
"learning_rate": 4.344827586206897e-05,
"loss": 0.7001,
"step": 418
},
{
"epoch": 1.32,
"learning_rate": 4.341692789968652e-05,
"loss": 0.1239,
"step": 420
},
{
"epoch": 1.32,
"learning_rate": 4.338557993730408e-05,
"loss": 0.542,
"step": 422
},
{
"epoch": 1.33,
"learning_rate": 4.335423197492163e-05,
"loss": 0.1033,
"step": 424
},
{
"epoch": 1.34,
"learning_rate": 4.3322884012539185e-05,
"loss": 0.6765,
"step": 426
},
{
"epoch": 1.34,
"learning_rate": 4.3291536050156747e-05,
"loss": 0.2388,
"step": 428
},
{
"epoch": 1.35,
"learning_rate": 4.3260188087774294e-05,
"loss": 1.0428,
"step": 430
},
{
"epoch": 1.35,
"learning_rate": 4.322884012539185e-05,
"loss": 1.0099,
"step": 432
},
{
"epoch": 1.36,
"learning_rate": 4.319749216300941e-05,
"loss": 0.4892,
"step": 434
},
{
"epoch": 1.37,
"learning_rate": 4.3166144200626964e-05,
"loss": 0.1608,
"step": 436
},
{
"epoch": 1.37,
"learning_rate": 4.313479623824452e-05,
"loss": 0.9799,
"step": 438
},
{
"epoch": 1.38,
"learning_rate": 4.3103448275862066e-05,
"loss": 0.0847,
"step": 440
},
{
"epoch": 1.39,
"learning_rate": 4.307210031347963e-05,
"loss": 0.6962,
"step": 442
},
{
"epoch": 1.39,
"learning_rate": 4.304075235109718e-05,
"loss": 0.5673,
"step": 444
},
{
"epoch": 1.4,
"learning_rate": 4.3009404388714735e-05,
"loss": 0.2379,
"step": 446
},
{
"epoch": 1.4,
"learning_rate": 4.297805642633229e-05,
"loss": 0.4849,
"step": 448
},
{
"epoch": 1.41,
"learning_rate": 4.294670846394985e-05,
"loss": 0.4408,
"step": 450
},
{
"epoch": 1.42,
"learning_rate": 4.29153605015674e-05,
"loss": 1.0882,
"step": 452
},
{
"epoch": 1.42,
"learning_rate": 4.288401253918495e-05,
"loss": 0.0825,
"step": 454
},
{
"epoch": 1.43,
"learning_rate": 4.285266457680251e-05,
"loss": 0.1645,
"step": 456
},
{
"epoch": 1.44,
"learning_rate": 4.282131661442007e-05,
"loss": 1.538,
"step": 458
},
{
"epoch": 1.44,
"learning_rate": 4.278996865203762e-05,
"loss": 0.1576,
"step": 460
},
{
"epoch": 1.45,
"learning_rate": 4.275862068965518e-05,
"loss": 0.3003,
"step": 462
},
{
"epoch": 1.45,
"learning_rate": 4.2727272727272724e-05,
"loss": 0.3405,
"step": 464
},
{
"epoch": 1.46,
"learning_rate": 4.2695924764890285e-05,
"loss": 0.8745,
"step": 466
},
{
"epoch": 1.47,
"learning_rate": 4.266457680250784e-05,
"loss": 0.8657,
"step": 468
},
{
"epoch": 1.47,
"learning_rate": 4.2633228840125394e-05,
"loss": 0.6039,
"step": 470
},
{
"epoch": 1.48,
"learning_rate": 4.260188087774295e-05,
"loss": 0.8955,
"step": 472
},
{
"epoch": 1.49,
"learning_rate": 4.257053291536051e-05,
"loss": 0.203,
"step": 474
},
{
"epoch": 1.49,
"learning_rate": 4.253918495297806e-05,
"loss": 0.4717,
"step": 476
},
{
"epoch": 1.5,
"learning_rate": 4.250783699059561e-05,
"loss": 0.4653,
"step": 478
},
{
"epoch": 1.5,
"learning_rate": 4.2476489028213165e-05,
"loss": 0.7486,
"step": 480
},
{
"epoch": 1.51,
"learning_rate": 4.2445141065830726e-05,
"loss": 0.2863,
"step": 482
},
{
"epoch": 1.52,
"learning_rate": 4.241379310344828e-05,
"loss": 0.1675,
"step": 484
},
{
"epoch": 1.52,
"learning_rate": 4.2382445141065835e-05,
"loss": 0.3746,
"step": 486
},
{
"epoch": 1.53,
"learning_rate": 4.235109717868338e-05,
"loss": 1.363,
"step": 488
},
{
"epoch": 1.54,
"learning_rate": 4.2319749216300944e-05,
"loss": 0.2312,
"step": 490
},
{
"epoch": 1.54,
"learning_rate": 4.22884012539185e-05,
"loss": 0.7131,
"step": 492
},
{
"epoch": 1.55,
"learning_rate": 4.225705329153605e-05,
"loss": 0.5815,
"step": 494
},
{
"epoch": 1.55,
"learning_rate": 4.222570532915361e-05,
"loss": 1.0779,
"step": 496
},
{
"epoch": 1.56,
"learning_rate": 4.219435736677117e-05,
"loss": 0.3242,
"step": 498
},
{
"epoch": 1.57,
"learning_rate": 4.2163009404388715e-05,
"loss": 0.1308,
"step": 500
},
{
"epoch": 1.57,
"learning_rate": 4.213166144200627e-05,
"loss": 0.2272,
"step": 502
},
{
"epoch": 1.58,
"learning_rate": 4.2100313479623824e-05,
"loss": 0.1048,
"step": 504
},
{
"epoch": 1.59,
"learning_rate": 4.2068965517241385e-05,
"loss": 0.8957,
"step": 506
},
{
"epoch": 1.59,
"learning_rate": 4.203761755485894e-05,
"loss": 0.277,
"step": 508
},
{
"epoch": 1.6,
"learning_rate": 4.2006269592476494e-05,
"loss": 0.3144,
"step": 510
},
{
"epoch": 1.61,
"learning_rate": 4.197492163009404e-05,
"loss": 0.1906,
"step": 512
},
{
"epoch": 1.61,
"learning_rate": 4.19435736677116e-05,
"loss": 1.434,
"step": 514
},
{
"epoch": 1.62,
"learning_rate": 4.1912225705329157e-05,
"loss": 0.5245,
"step": 516
},
{
"epoch": 1.62,
"learning_rate": 4.188087774294671e-05,
"loss": 0.4078,
"step": 518
},
{
"epoch": 1.63,
"learning_rate": 4.1849529780564265e-05,
"loss": 0.1577,
"step": 520
},
{
"epoch": 1.64,
"learning_rate": 4.181818181818182e-05,
"loss": 0.1034,
"step": 522
},
{
"epoch": 1.64,
"learning_rate": 4.1786833855799374e-05,
"loss": 0.1685,
"step": 524
},
{
"epoch": 1.65,
"learning_rate": 4.175548589341693e-05,
"loss": 0.2631,
"step": 526
},
{
"epoch": 1.66,
"learning_rate": 4.172413793103448e-05,
"loss": 1.1729,
"step": 528
},
{
"epoch": 1.66,
"learning_rate": 4.1692789968652043e-05,
"loss": 0.4821,
"step": 530
},
{
"epoch": 1.67,
"learning_rate": 4.16614420062696e-05,
"loss": 0.1952,
"step": 532
},
{
"epoch": 1.67,
"learning_rate": 4.1630094043887145e-05,
"loss": 0.1677,
"step": 534
},
{
"epoch": 1.68,
"learning_rate": 4.15987460815047e-05,
"loss": 0.7887,
"step": 536
},
{
"epoch": 1.69,
"learning_rate": 4.156739811912226e-05,
"loss": 0.8876,
"step": 538
},
{
"epoch": 1.69,
"learning_rate": 4.1536050156739815e-05,
"loss": 0.456,
"step": 540
},
{
"epoch": 1.7,
"learning_rate": 4.150470219435737e-05,
"loss": 0.3973,
"step": 542
},
{
"epoch": 1.71,
"learning_rate": 4.1473354231974924e-05,
"loss": 0.2558,
"step": 544
},
{
"epoch": 1.71,
"learning_rate": 4.144200626959248e-05,
"loss": 0.8648,
"step": 546
},
{
"epoch": 1.72,
"learning_rate": 4.141065830721003e-05,
"loss": 1.4092,
"step": 548
},
{
"epoch": 1.72,
"learning_rate": 4.1379310344827587e-05,
"loss": 0.2367,
"step": 550
},
{
"epoch": 1.73,
"learning_rate": 4.134796238244514e-05,
"loss": 0.1157,
"step": 552
},
{
"epoch": 1.74,
"learning_rate": 4.13166144200627e-05,
"loss": 0.2577,
"step": 554
},
{
"epoch": 1.74,
"learning_rate": 4.1285266457680256e-05,
"loss": 0.1873,
"step": 556
},
{
"epoch": 1.75,
"learning_rate": 4.1253918495297804e-05,
"loss": 1.9265,
"step": 558
},
{
"epoch": 1.76,
"learning_rate": 4.122257053291536e-05,
"loss": 0.7055,
"step": 560
},
{
"epoch": 1.76,
"learning_rate": 4.119122257053292e-05,
"loss": 0.5346,
"step": 562
},
{
"epoch": 1.77,
"learning_rate": 4.1159874608150473e-05,
"loss": 0.6616,
"step": 564
},
{
"epoch": 1.77,
"learning_rate": 4.112852664576803e-05,
"loss": 0.534,
"step": 566
},
{
"epoch": 1.78,
"learning_rate": 4.109717868338558e-05,
"loss": 0.8041,
"step": 568
},
{
"epoch": 1.79,
"learning_rate": 4.1065830721003136e-05,
"loss": 0.3751,
"step": 570
},
{
"epoch": 1.79,
"learning_rate": 4.103448275862069e-05,
"loss": 0.4831,
"step": 572
},
{
"epoch": 1.8,
"learning_rate": 4.1003134796238245e-05,
"loss": 0.8319,
"step": 574
},
{
"epoch": 1.81,
"learning_rate": 4.09717868338558e-05,
"loss": 0.3292,
"step": 576
},
{
"epoch": 1.81,
"learning_rate": 4.094043887147336e-05,
"loss": 0.1887,
"step": 578
},
{
"epoch": 1.82,
"learning_rate": 4.0909090909090915e-05,
"loss": 0.9955,
"step": 580
},
{
"epoch": 1.82,
"learning_rate": 4.087774294670846e-05,
"loss": 0.4777,
"step": 582
},
{
"epoch": 1.83,
"learning_rate": 4.0846394984326017e-05,
"loss": 0.9053,
"step": 584
},
{
"epoch": 1.84,
"learning_rate": 4.081504702194358e-05,
"loss": 0.928,
"step": 586
},
{
"epoch": 1.84,
"learning_rate": 4.078369905956113e-05,
"loss": 1.0885,
"step": 588
},
{
"epoch": 1.85,
"learning_rate": 4.0752351097178686e-05,
"loss": 0.2145,
"step": 590
},
{
"epoch": 1.86,
"learning_rate": 4.072100313479624e-05,
"loss": 0.1522,
"step": 592
},
{
"epoch": 1.86,
"learning_rate": 4.0689655172413795e-05,
"loss": 0.5739,
"step": 594
},
{
"epoch": 1.87,
"learning_rate": 4.065830721003135e-05,
"loss": 0.4077,
"step": 596
},
{
"epoch": 1.87,
"learning_rate": 4.0626959247648904e-05,
"loss": 0.3718,
"step": 598
},
{
"epoch": 1.88,
"learning_rate": 4.059561128526646e-05,
"loss": 0.2852,
"step": 600
},
{
"epoch": 1.89,
"learning_rate": 4.056426332288402e-05,
"loss": 0.4187,
"step": 602
},
{
"epoch": 1.89,
"learning_rate": 4.0532915360501566e-05,
"loss": 0.7516,
"step": 604
},
{
"epoch": 1.9,
"learning_rate": 4.050156739811912e-05,
"loss": 0.0868,
"step": 606
},
{
"epoch": 1.91,
"learning_rate": 4.0470219435736675e-05,
"loss": 0.4357,
"step": 608
},
{
"epoch": 1.91,
"learning_rate": 4.0438871473354236e-05,
"loss": 0.5593,
"step": 610
},
{
"epoch": 1.92,
"learning_rate": 4.040752351097179e-05,
"loss": 0.3828,
"step": 612
},
{
"epoch": 1.92,
"learning_rate": 4.0376175548589345e-05,
"loss": 0.638,
"step": 614
},
{
"epoch": 1.93,
"learning_rate": 4.03448275862069e-05,
"loss": 0.6698,
"step": 616
},
{
"epoch": 1.94,
"learning_rate": 4.0313479623824453e-05,
"loss": 0.3484,
"step": 618
},
{
"epoch": 1.94,
"learning_rate": 4.028213166144201e-05,
"loss": 1.1265,
"step": 620
},
{
"epoch": 1.95,
"learning_rate": 4.025078369905956e-05,
"loss": 0.7538,
"step": 622
},
{
"epoch": 1.96,
"learning_rate": 4.0219435736677116e-05,
"loss": 0.2539,
"step": 624
},
{
"epoch": 1.96,
"learning_rate": 4.018808777429468e-05,
"loss": 0.5086,
"step": 626
},
{
"epoch": 1.97,
"learning_rate": 4.0156739811912225e-05,
"loss": 0.8172,
"step": 628
},
{
"epoch": 1.97,
"learning_rate": 4.012539184952978e-05,
"loss": 0.4001,
"step": 630
},
{
"epoch": 1.98,
"learning_rate": 4.0094043887147334e-05,
"loss": 0.3098,
"step": 632
},
{
"epoch": 1.99,
"learning_rate": 4.0062695924764895e-05,
"loss": 0.9891,
"step": 634
},
{
"epoch": 1.99,
"learning_rate": 4.003134796238245e-05,
"loss": 0.5662,
"step": 636
},
{
"epoch": 2.0,
"learning_rate": 4e-05,
"loss": 0.598,
"step": 638
},
{
"epoch": 2.0,
"eval_bleu": 0.22143979906815262,
"eval_loss": 0.5837797522544861,
"eval_runtime": 76.2397,
"eval_samples_per_second": 4.224,
"eval_steps_per_second": 1.062,
"step": 638
},
{
"epoch": 2.01,
"learning_rate": 3.996865203761756e-05,
"loss": 0.4468,
"step": 640
},
{
"epoch": 2.01,
"learning_rate": 3.993730407523511e-05,
"loss": 1.2271,
"step": 642
},
{
"epoch": 2.02,
"learning_rate": 3.9905956112852666e-05,
"loss": 0.1244,
"step": 644
},
{
"epoch": 2.03,
"learning_rate": 3.987460815047022e-05,
"loss": 0.0909,
"step": 646
},
{
"epoch": 2.03,
"learning_rate": 3.9843260188087775e-05,
"loss": 0.9222,
"step": 648
},
{
"epoch": 2.04,
"learning_rate": 3.9811912225705336e-05,
"loss": 0.12,
"step": 650
},
{
"epoch": 2.04,
"learning_rate": 3.9780564263322883e-05,
"loss": 0.7242,
"step": 652
},
{
"epoch": 2.05,
"learning_rate": 3.974921630094044e-05,
"loss": 1.1717,
"step": 654
},
{
"epoch": 2.06,
"learning_rate": 3.971786833855799e-05,
"loss": 0.0869,
"step": 656
},
{
"epoch": 2.06,
"learning_rate": 3.968652037617555e-05,
"loss": 0.1233,
"step": 658
},
{
"epoch": 2.07,
"learning_rate": 3.965517241379311e-05,
"loss": 0.4636,
"step": 660
},
{
"epoch": 2.08,
"learning_rate": 3.962382445141066e-05,
"loss": 0.2821,
"step": 662
},
{
"epoch": 2.08,
"learning_rate": 3.9592476489028216e-05,
"loss": 0.0841,
"step": 664
},
{
"epoch": 2.09,
"learning_rate": 3.956112852664577e-05,
"loss": 0.1022,
"step": 666
},
{
"epoch": 2.09,
"learning_rate": 3.9529780564263325e-05,
"loss": 0.2407,
"step": 668
},
{
"epoch": 2.1,
"learning_rate": 3.949843260188088e-05,
"loss": 0.1577,
"step": 670
},
{
"epoch": 2.11,
"learning_rate": 3.946708463949843e-05,
"loss": 0.7505,
"step": 672
},
{
"epoch": 2.11,
"learning_rate": 3.9435736677115994e-05,
"loss": 1.743,
"step": 674
},
{
"epoch": 2.12,
"learning_rate": 3.940438871473354e-05,
"loss": 0.1138,
"step": 676
},
{
"epoch": 2.13,
"learning_rate": 3.9373040752351096e-05,
"loss": 0.074,
"step": 678
},
{
"epoch": 2.13,
"learning_rate": 3.934169278996865e-05,
"loss": 0.3786,
"step": 680
},
{
"epoch": 2.14,
"learning_rate": 3.931034482758621e-05,
"loss": 0.4062,
"step": 682
},
{
"epoch": 2.14,
"learning_rate": 3.9278996865203766e-05,
"loss": 0.0661,
"step": 684
},
{
"epoch": 2.15,
"learning_rate": 3.924764890282132e-05,
"loss": 0.9205,
"step": 686
},
{
"epoch": 2.16,
"learning_rate": 3.9216300940438875e-05,
"loss": 0.0813,
"step": 688
},
{
"epoch": 2.16,
"learning_rate": 3.918495297805643e-05,
"loss": 0.6916,
"step": 690
},
{
"epoch": 2.17,
"learning_rate": 3.915360501567398e-05,
"loss": 1.1737,
"step": 692
},
{
"epoch": 2.18,
"learning_rate": 3.912225705329154e-05,
"loss": 0.3149,
"step": 694
},
{
"epoch": 2.18,
"learning_rate": 3.909090909090909e-05,
"loss": 0.4842,
"step": 696
},
{
"epoch": 2.19,
"learning_rate": 3.9059561128526646e-05,
"loss": 0.636,
"step": 698
},
{
"epoch": 2.19,
"learning_rate": 3.90282131661442e-05,
"loss": 0.0862,
"step": 700
},
{
"epoch": 2.2,
"learning_rate": 3.8996865203761755e-05,
"loss": 0.5014,
"step": 702
},
{
"epoch": 2.21,
"learning_rate": 3.896551724137931e-05,
"loss": 0.5606,
"step": 704
},
{
"epoch": 2.21,
"learning_rate": 3.893416927899687e-05,
"loss": 0.2375,
"step": 706
},
{
"epoch": 2.22,
"learning_rate": 3.8902821316614424e-05,
"loss": 0.0881,
"step": 708
},
{
"epoch": 2.23,
"learning_rate": 3.887147335423197e-05,
"loss": 0.2358,
"step": 710
},
{
"epoch": 2.23,
"learning_rate": 3.884012539184953e-05,
"loss": 0.0943,
"step": 712
},
{
"epoch": 2.24,
"learning_rate": 3.880877742946709e-05,
"loss": 0.7039,
"step": 714
},
{
"epoch": 2.24,
"learning_rate": 3.877742946708464e-05,
"loss": 0.9661,
"step": 716
},
{
"epoch": 2.25,
"learning_rate": 3.8746081504702196e-05,
"loss": 0.7479,
"step": 718
},
{
"epoch": 2.26,
"learning_rate": 3.871473354231975e-05,
"loss": 0.1651,
"step": 720
},
{
"epoch": 2.26,
"learning_rate": 3.8683385579937305e-05,
"loss": 0.0789,
"step": 722
},
{
"epoch": 2.27,
"learning_rate": 3.865203761755486e-05,
"loss": 0.5148,
"step": 724
},
{
"epoch": 2.28,
"learning_rate": 3.862068965517241e-05,
"loss": 0.5988,
"step": 726
},
{
"epoch": 2.28,
"learning_rate": 3.8589341692789974e-05,
"loss": 0.1082,
"step": 728
},
{
"epoch": 2.29,
"learning_rate": 3.855799373040753e-05,
"loss": 1.2606,
"step": 730
},
{
"epoch": 2.29,
"learning_rate": 3.852664576802508e-05,
"loss": 0.321,
"step": 732
},
{
"epoch": 2.3,
"learning_rate": 3.849529780564263e-05,
"loss": 0.7046,
"step": 734
},
{
"epoch": 2.31,
"learning_rate": 3.846394984326019e-05,
"loss": 0.7642,
"step": 736
},
{
"epoch": 2.31,
"learning_rate": 3.8432601880877746e-05,
"loss": 0.4196,
"step": 738
},
{
"epoch": 2.32,
"learning_rate": 3.84012539184953e-05,
"loss": 0.7299,
"step": 740
},
{
"epoch": 2.33,
"learning_rate": 3.8369905956112854e-05,
"loss": 0.9111,
"step": 742
},
{
"epoch": 2.33,
"learning_rate": 3.833855799373041e-05,
"loss": 0.0798,
"step": 744
},
{
"epoch": 2.34,
"learning_rate": 3.830721003134796e-05,
"loss": 0.2813,
"step": 746
},
{
"epoch": 2.34,
"learning_rate": 3.827586206896552e-05,
"loss": 0.1674,
"step": 748
},
{
"epoch": 2.35,
"learning_rate": 3.824451410658307e-05,
"loss": 0.074,
"step": 750
},
{
"epoch": 2.36,
"learning_rate": 3.821316614420063e-05,
"loss": 0.6165,
"step": 752
},
{
"epoch": 2.36,
"learning_rate": 3.818181818181819e-05,
"loss": 0.6605,
"step": 754
},
{
"epoch": 2.37,
"learning_rate": 3.815047021943574e-05,
"loss": 0.3572,
"step": 756
},
{
"epoch": 2.38,
"learning_rate": 3.811912225705329e-05,
"loss": 1.0105,
"step": 758
},
{
"epoch": 2.38,
"learning_rate": 3.808777429467085e-05,
"loss": 0.0995,
"step": 760
},
{
"epoch": 2.39,
"learning_rate": 3.8056426332288404e-05,
"loss": 0.1342,
"step": 762
},
{
"epoch": 2.39,
"learning_rate": 3.802507836990596e-05,
"loss": 0.139,
"step": 764
},
{
"epoch": 2.4,
"learning_rate": 3.799373040752351e-05,
"loss": 0.5829,
"step": 766
},
{
"epoch": 2.41,
"learning_rate": 3.796238244514107e-05,
"loss": 0.6066,
"step": 768
},
{
"epoch": 2.41,
"learning_rate": 3.793103448275862e-05,
"loss": 0.6555,
"step": 770
},
{
"epoch": 2.42,
"learning_rate": 3.7899686520376176e-05,
"loss": 0.0645,
"step": 772
},
{
"epoch": 2.43,
"learning_rate": 3.786833855799373e-05,
"loss": 0.5722,
"step": 774
},
{
"epoch": 2.43,
"learning_rate": 3.783699059561129e-05,
"loss": 0.1646,
"step": 776
},
{
"epoch": 2.44,
"learning_rate": 3.7805642633228846e-05,
"loss": 0.2397,
"step": 778
},
{
"epoch": 2.45,
"learning_rate": 3.777429467084639e-05,
"loss": 0.1902,
"step": 780
},
{
"epoch": 2.45,
"learning_rate": 3.774294670846395e-05,
"loss": 0.175,
"step": 782
},
{
"epoch": 2.46,
"learning_rate": 3.771159874608151e-05,
"loss": 0.7741,
"step": 784
},
{
"epoch": 2.46,
"learning_rate": 3.768025078369906e-05,
"loss": 0.1346,
"step": 786
},
{
"epoch": 2.47,
"learning_rate": 3.764890282131662e-05,
"loss": 0.5639,
"step": 788
},
{
"epoch": 2.48,
"learning_rate": 3.761755485893417e-05,
"loss": 0.595,
"step": 790
},
{
"epoch": 2.48,
"learning_rate": 3.7586206896551726e-05,
"loss": 0.1199,
"step": 792
},
{
"epoch": 2.49,
"learning_rate": 3.755485893416928e-05,
"loss": 0.8169,
"step": 794
},
{
"epoch": 2.5,
"learning_rate": 3.7523510971786834e-05,
"loss": 0.1015,
"step": 796
},
{
"epoch": 2.5,
"learning_rate": 3.749216300940439e-05,
"loss": 0.0699,
"step": 798
},
{
"epoch": 2.51,
"learning_rate": 3.746081504702195e-05,
"loss": 0.5325,
"step": 800
},
{
"epoch": 2.51,
"learning_rate": 3.7429467084639504e-05,
"loss": 0.2893,
"step": 802
},
{
"epoch": 2.52,
"learning_rate": 3.739811912225705e-05,
"loss": 0.4056,
"step": 804
},
{
"epoch": 2.53,
"learning_rate": 3.7366771159874606e-05,
"loss": 0.3284,
"step": 806
},
{
"epoch": 2.53,
"learning_rate": 3.733542319749217e-05,
"loss": 0.1071,
"step": 808
},
{
"epoch": 2.54,
"learning_rate": 3.730407523510972e-05,
"loss": 0.1821,
"step": 810
},
{
"epoch": 2.55,
"learning_rate": 3.7272727272727276e-05,
"loss": 0.231,
"step": 812
},
{
"epoch": 2.55,
"learning_rate": 3.724137931034483e-05,
"loss": 0.2871,
"step": 814
},
{
"epoch": 2.56,
"learning_rate": 3.7210031347962384e-05,
"loss": 0.3931,
"step": 816
},
{
"epoch": 2.56,
"learning_rate": 3.717868338557994e-05,
"loss": 0.6065,
"step": 818
},
{
"epoch": 2.57,
"learning_rate": 3.714733542319749e-05,
"loss": 0.2118,
"step": 820
},
{
"epoch": 2.58,
"learning_rate": 3.711598746081505e-05,
"loss": 0.0835,
"step": 822
},
{
"epoch": 2.58,
"learning_rate": 3.708463949843261e-05,
"loss": 0.181,
"step": 824
},
{
"epoch": 2.59,
"learning_rate": 3.705329153605016e-05,
"loss": 0.0591,
"step": 826
},
{
"epoch": 2.6,
"learning_rate": 3.702194357366771e-05,
"loss": 0.1432,
"step": 828
},
{
"epoch": 2.6,
"learning_rate": 3.6990595611285264e-05,
"loss": 0.4398,
"step": 830
},
{
"epoch": 2.61,
"learning_rate": 3.6959247648902825e-05,
"loss": 0.3443,
"step": 832
},
{
"epoch": 2.61,
"learning_rate": 3.692789968652038e-05,
"loss": 0.0413,
"step": 834
},
{
"epoch": 2.62,
"learning_rate": 3.6896551724137934e-05,
"loss": 0.4842,
"step": 836
},
{
"epoch": 2.63,
"learning_rate": 3.686520376175549e-05,
"loss": 0.5001,
"step": 838
},
{
"epoch": 2.63,
"learning_rate": 3.683385579937304e-05,
"loss": 0.6096,
"step": 840
},
{
"epoch": 2.64,
"learning_rate": 3.68025078369906e-05,
"loss": 0.1528,
"step": 842
},
{
"epoch": 2.65,
"learning_rate": 3.677115987460815e-05,
"loss": 0.3878,
"step": 844
},
{
"epoch": 2.65,
"learning_rate": 3.6739811912225706e-05,
"loss": 0.0934,
"step": 846
},
{
"epoch": 2.66,
"learning_rate": 3.670846394984327e-05,
"loss": 0.3619,
"step": 848
},
{
"epoch": 2.66,
"learning_rate": 3.667711598746082e-05,
"loss": 0.8191,
"step": 850
},
{
"epoch": 2.67,
"learning_rate": 3.664576802507837e-05,
"loss": 0.2583,
"step": 852
},
{
"epoch": 2.68,
"learning_rate": 3.661442006269592e-05,
"loss": 0.4955,
"step": 854
},
{
"epoch": 2.68,
"learning_rate": 3.6583072100313484e-05,
"loss": 0.1636,
"step": 856
},
{
"epoch": 2.69,
"learning_rate": 3.655172413793104e-05,
"loss": 0.1809,
"step": 858
},
{
"epoch": 2.7,
"learning_rate": 3.652037617554859e-05,
"loss": 0.1182,
"step": 860
},
{
"epoch": 2.7,
"learning_rate": 3.648902821316615e-05,
"loss": 1.4724,
"step": 862
},
{
"epoch": 2.71,
"learning_rate": 3.64576802507837e-05,
"loss": 0.5265,
"step": 864
},
{
"epoch": 2.71,
"learning_rate": 3.6426332288401256e-05,
"loss": 0.1006,
"step": 866
},
{
"epoch": 2.72,
"learning_rate": 3.639498432601881e-05,
"loss": 0.9536,
"step": 868
},
{
"epoch": 2.73,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.7936,
"step": 870
},
{
"epoch": 2.73,
"learning_rate": 3.6332288401253925e-05,
"loss": 0.1084,
"step": 872
},
{
"epoch": 2.74,
"learning_rate": 3.630094043887147e-05,
"loss": 0.5039,
"step": 874
},
{
"epoch": 2.75,
"learning_rate": 3.626959247648903e-05,
"loss": 0.2569,
"step": 876
},
{
"epoch": 2.75,
"learning_rate": 3.623824451410658e-05,
"loss": 0.7229,
"step": 878
},
{
"epoch": 2.76,
"learning_rate": 3.620689655172414e-05,
"loss": 0.1591,
"step": 880
},
{
"epoch": 2.76,
"learning_rate": 3.61755485893417e-05,
"loss": 0.3813,
"step": 882
},
{
"epoch": 2.77,
"learning_rate": 3.614420062695925e-05,
"loss": 0.5446,
"step": 884
},
{
"epoch": 2.78,
"learning_rate": 3.61128526645768e-05,
"loss": 0.0682,
"step": 886
},
{
"epoch": 2.78,
"learning_rate": 3.608150470219436e-05,
"loss": 0.1326,
"step": 888
},
{
"epoch": 2.79,
"learning_rate": 3.6050156739811914e-05,
"loss": 0.2526,
"step": 890
},
{
"epoch": 2.8,
"learning_rate": 3.601880877742947e-05,
"loss": 0.1167,
"step": 892
},
{
"epoch": 2.8,
"learning_rate": 3.598746081504702e-05,
"loss": 0.2939,
"step": 894
},
{
"epoch": 2.81,
"learning_rate": 3.5956112852664584e-05,
"loss": 0.4313,
"step": 896
},
{
"epoch": 2.82,
"learning_rate": 3.592476489028213e-05,
"loss": 0.1435,
"step": 898
},
{
"epoch": 2.82,
"learning_rate": 3.5893416927899686e-05,
"loss": 0.4394,
"step": 900
},
{
"epoch": 2.83,
"learning_rate": 3.586206896551724e-05,
"loss": 0.4121,
"step": 902
},
{
"epoch": 2.83,
"learning_rate": 3.58307210031348e-05,
"loss": 0.1662,
"step": 904
},
{
"epoch": 2.84,
"learning_rate": 3.5799373040752355e-05,
"loss": 0.9565,
"step": 906
},
{
"epoch": 2.85,
"learning_rate": 3.576802507836991e-05,
"loss": 0.2431,
"step": 908
},
{
"epoch": 2.85,
"learning_rate": 3.573667711598746e-05,
"loss": 0.2913,
"step": 910
},
{
"epoch": 2.86,
"learning_rate": 3.570532915360502e-05,
"loss": 0.3142,
"step": 912
},
{
"epoch": 2.87,
"learning_rate": 3.567398119122257e-05,
"loss": 0.8352,
"step": 914
},
{
"epoch": 2.87,
"learning_rate": 3.564263322884013e-05,
"loss": 0.2264,
"step": 916
},
{
"epoch": 2.88,
"learning_rate": 3.561128526645768e-05,
"loss": 0.1313,
"step": 918
},
{
"epoch": 2.88,
"learning_rate": 3.557993730407524e-05,
"loss": 0.2702,
"step": 920
},
{
"epoch": 2.89,
"learning_rate": 3.554858934169279e-05,
"loss": 0.1185,
"step": 922
},
{
"epoch": 2.9,
"learning_rate": 3.5517241379310344e-05,
"loss": 0.8046,
"step": 924
},
{
"epoch": 2.9,
"learning_rate": 3.54858934169279e-05,
"loss": 0.8257,
"step": 926
},
{
"epoch": 2.91,
"learning_rate": 3.545454545454546e-05,
"loss": 0.1377,
"step": 928
},
{
"epoch": 2.92,
"learning_rate": 3.5423197492163014e-05,
"loss": 1.2093,
"step": 930
},
{
"epoch": 2.92,
"learning_rate": 3.539184952978057e-05,
"loss": 0.6203,
"step": 932
},
{
"epoch": 2.93,
"learning_rate": 3.5360501567398116e-05,
"loss": 0.5519,
"step": 934
},
{
"epoch": 2.93,
"learning_rate": 3.532915360501568e-05,
"loss": 0.8382,
"step": 936
},
{
"epoch": 2.94,
"learning_rate": 3.529780564263323e-05,
"loss": 0.3924,
"step": 938
},
{
"epoch": 2.95,
"learning_rate": 3.5266457680250785e-05,
"loss": 0.344,
"step": 940
},
{
"epoch": 2.95,
"learning_rate": 3.523510971786834e-05,
"loss": 0.1352,
"step": 942
},
{
"epoch": 2.96,
"learning_rate": 3.52037617554859e-05,
"loss": 0.4352,
"step": 944
},
{
"epoch": 2.97,
"learning_rate": 3.517241379310345e-05,
"loss": 0.3054,
"step": 946
},
{
"epoch": 2.97,
"learning_rate": 3.5141065830721e-05,
"loss": 0.1816,
"step": 948
},
{
"epoch": 2.98,
"learning_rate": 3.510971786833856e-05,
"loss": 0.1088,
"step": 950
},
{
"epoch": 2.98,
"learning_rate": 3.507836990595612e-05,
"loss": 0.0878,
"step": 952
},
{
"epoch": 2.99,
"learning_rate": 3.504702194357367e-05,
"loss": 0.5545,
"step": 954
},
{
"epoch": 3.0,
"learning_rate": 3.501567398119122e-05,
"loss": 0.105,
"step": 956
},
{
"epoch": 3.0,
"eval_bleu": 0.23230339252724816,
"eval_loss": 0.6111631989479065,
"eval_runtime": 76.2702,
"eval_samples_per_second": 4.222,
"eval_steps_per_second": 1.062,
"step": 957
},
{
"epoch": 3.0,
"learning_rate": 3.4984326018808774e-05,
"loss": 0.1126,
"step": 958
},
{
"epoch": 3.01,
"learning_rate": 3.4952978056426335e-05,
"loss": 0.0723,
"step": 960
},
{
"epoch": 3.02,
"learning_rate": 3.492163009404389e-05,
"loss": 0.108,
"step": 962
},
{
"epoch": 3.02,
"learning_rate": 3.4890282131661444e-05,
"loss": 0.3811,
"step": 964
},
{
"epoch": 3.03,
"learning_rate": 3.4858934169279e-05,
"loss": 0.3857,
"step": 966
},
{
"epoch": 3.03,
"learning_rate": 3.482758620689655e-05,
"loss": 0.8567,
"step": 968
},
{
"epoch": 3.04,
"learning_rate": 3.479623824451411e-05,
"loss": 0.0461,
"step": 970
},
{
"epoch": 3.05,
"learning_rate": 3.476489028213166e-05,
"loss": 0.6084,
"step": 972
},
{
"epoch": 3.05,
"learning_rate": 3.4733542319749215e-05,
"loss": 0.3917,
"step": 974
},
{
"epoch": 3.06,
"learning_rate": 3.4702194357366776e-05,
"loss": 0.1739,
"step": 976
},
{
"epoch": 3.07,
"learning_rate": 3.467084639498433e-05,
"loss": 0.0362,
"step": 978
},
{
"epoch": 3.07,
"learning_rate": 3.463949843260188e-05,
"loss": 0.1756,
"step": 980
},
{
"epoch": 3.08,
"learning_rate": 3.460815047021943e-05,
"loss": 0.0617,
"step": 982
},
{
"epoch": 3.08,
"learning_rate": 3.4576802507836994e-05,
"loss": 0.1196,
"step": 984
},
{
"epoch": 3.09,
"learning_rate": 3.454545454545455e-05,
"loss": 0.1394,
"step": 986
},
{
"epoch": 3.1,
"learning_rate": 3.45141065830721e-05,
"loss": 0.1394,
"step": 988
},
{
"epoch": 3.1,
"learning_rate": 3.4482758620689657e-05,
"loss": 0.1374,
"step": 990
},
{
"epoch": 3.11,
"learning_rate": 3.445141065830721e-05,
"loss": 0.3252,
"step": 992
},
{
"epoch": 3.12,
"learning_rate": 3.4420062695924765e-05,
"loss": 0.6278,
"step": 994
},
{
"epoch": 3.12,
"learning_rate": 3.438871473354232e-05,
"loss": 0.2991,
"step": 996
},
{
"epoch": 3.13,
"learning_rate": 3.4357366771159874e-05,
"loss": 0.036,
"step": 998
},
{
"epoch": 3.13,
"learning_rate": 3.4326018808777435e-05,
"loss": 0.1012,
"step": 1000
},
{
"epoch": 3.14,
"learning_rate": 3.429467084639499e-05,
"loss": 0.4556,
"step": 1002
},
{
"epoch": 3.15,
"learning_rate": 3.426332288401254e-05,
"loss": 0.3598,
"step": 1004
},
{
"epoch": 3.15,
"learning_rate": 3.423197492163009e-05,
"loss": 0.2032,
"step": 1006
},
{
"epoch": 3.16,
"learning_rate": 3.420062695924765e-05,
"loss": 0.3862,
"step": 1008
},
{
"epoch": 3.17,
"learning_rate": 3.4169278996865206e-05,
"loss": 1.1844,
"step": 1010
},
{
"epoch": 3.17,
"learning_rate": 3.413793103448276e-05,
"loss": 0.6972,
"step": 1012
},
{
"epoch": 3.18,
"learning_rate": 3.4106583072100315e-05,
"loss": 0.4301,
"step": 1014
},
{
"epoch": 3.18,
"learning_rate": 3.407523510971787e-05,
"loss": 0.2322,
"step": 1016
},
{
"epoch": 3.19,
"learning_rate": 3.4043887147335424e-05,
"loss": 0.1826,
"step": 1018
},
{
"epoch": 3.2,
"learning_rate": 3.401253918495298e-05,
"loss": 0.0967,
"step": 1020
},
{
"epoch": 3.2,
"learning_rate": 3.398119122257053e-05,
"loss": 0.22,
"step": 1022
},
{
"epoch": 3.21,
"learning_rate": 3.3949843260188093e-05,
"loss": 0.2791,
"step": 1024
},
{
"epoch": 3.22,
"learning_rate": 3.391849529780565e-05,
"loss": 0.0812,
"step": 1026
},
{
"epoch": 3.22,
"learning_rate": 3.3887147335423195e-05,
"loss": 0.2805,
"step": 1028
},
{
"epoch": 3.23,
"learning_rate": 3.3855799373040756e-05,
"loss": 0.3116,
"step": 1030
},
{
"epoch": 3.24,
"learning_rate": 3.382445141065831e-05,
"loss": 0.7543,
"step": 1032
},
{
"epoch": 3.24,
"learning_rate": 3.3793103448275865e-05,
"loss": 0.2767,
"step": 1034
},
{
"epoch": 3.25,
"learning_rate": 3.376175548589342e-05,
"loss": 0.3967,
"step": 1036
},
{
"epoch": 3.25,
"learning_rate": 3.3730407523510974e-05,
"loss": 0.3185,
"step": 1038
},
{
"epoch": 3.26,
"learning_rate": 3.369905956112853e-05,
"loss": 0.0727,
"step": 1040
},
{
"epoch": 3.27,
"learning_rate": 3.366771159874608e-05,
"loss": 0.7915,
"step": 1042
},
{
"epoch": 3.27,
"learning_rate": 3.3636363636363636e-05,
"loss": 0.288,
"step": 1044
},
{
"epoch": 3.28,
"learning_rate": 3.360501567398119e-05,
"loss": 0.2361,
"step": 1046
},
{
"epoch": 3.29,
"learning_rate": 3.357366771159875e-05,
"loss": 0.4873,
"step": 1048
},
{
"epoch": 3.29,
"learning_rate": 3.35423197492163e-05,
"loss": 0.3298,
"step": 1050
},
{
"epoch": 3.3,
"learning_rate": 3.3510971786833854e-05,
"loss": 0.4757,
"step": 1052
},
{
"epoch": 3.3,
"learning_rate": 3.3479623824451415e-05,
"loss": 0.0676,
"step": 1054
},
{
"epoch": 3.31,
"learning_rate": 3.344827586206897e-05,
"loss": 0.5626,
"step": 1056
},
{
"epoch": 3.32,
"learning_rate": 3.3416927899686523e-05,
"loss": 0.0133,
"step": 1058
},
{
"epoch": 3.32,
"learning_rate": 3.338557993730408e-05,
"loss": 0.0623,
"step": 1060
},
{
"epoch": 3.33,
"learning_rate": 3.335423197492163e-05,
"loss": 0.7427,
"step": 1062
},
{
"epoch": 3.34,
"learning_rate": 3.3322884012539186e-05,
"loss": 0.7643,
"step": 1064
},
{
"epoch": 3.34,
"learning_rate": 3.329153605015674e-05,
"loss": 0.5679,
"step": 1066
},
{
"epoch": 3.35,
"learning_rate": 3.3260188087774295e-05,
"loss": 0.0973,
"step": 1068
},
{
"epoch": 3.35,
"learning_rate": 3.322884012539185e-05,
"loss": 0.2743,
"step": 1070
},
{
"epoch": 3.36,
"learning_rate": 3.319749216300941e-05,
"loss": 0.1096,
"step": 1072
},
{
"epoch": 3.37,
"learning_rate": 3.316614420062696e-05,
"loss": 0.2269,
"step": 1074
},
{
"epoch": 3.37,
"learning_rate": 3.313479623824451e-05,
"loss": 0.087,
"step": 1076
},
{
"epoch": 3.38,
"learning_rate": 3.310344827586207e-05,
"loss": 0.0691,
"step": 1078
},
{
"epoch": 3.39,
"learning_rate": 3.307210031347963e-05,
"loss": 0.2738,
"step": 1080
},
{
"epoch": 3.39,
"learning_rate": 3.304075235109718e-05,
"loss": 0.1897,
"step": 1082
},
{
"epoch": 3.4,
"learning_rate": 3.3009404388714736e-05,
"loss": 0.0346,
"step": 1084
},
{
"epoch": 3.4,
"learning_rate": 3.297805642633229e-05,
"loss": 0.4387,
"step": 1086
},
{
"epoch": 3.41,
"learning_rate": 3.2946708463949845e-05,
"loss": 0.2304,
"step": 1088
},
{
"epoch": 3.42,
"learning_rate": 3.29153605015674e-05,
"loss": 0.0823,
"step": 1090
},
{
"epoch": 3.42,
"learning_rate": 3.2884012539184953e-05,
"loss": 0.2337,
"step": 1092
},
{
"epoch": 3.43,
"learning_rate": 3.285266457680251e-05,
"loss": 0.0941,
"step": 1094
},
{
"epoch": 3.44,
"learning_rate": 3.282131661442007e-05,
"loss": 0.277,
"step": 1096
},
{
"epoch": 3.44,
"learning_rate": 3.2789968652037616e-05,
"loss": 0.1885,
"step": 1098
},
{
"epoch": 3.45,
"learning_rate": 3.275862068965517e-05,
"loss": 0.7624,
"step": 1100
},
{
"epoch": 3.45,
"learning_rate": 3.272727272727273e-05,
"loss": 0.4512,
"step": 1102
},
{
"epoch": 3.46,
"learning_rate": 3.2695924764890286e-05,
"loss": 0.3692,
"step": 1104
},
{
"epoch": 3.47,
"learning_rate": 3.266457680250784e-05,
"loss": 0.0467,
"step": 1106
},
{
"epoch": 3.47,
"learning_rate": 3.2633228840125395e-05,
"loss": 0.1802,
"step": 1108
},
{
"epoch": 3.48,
"learning_rate": 3.260188087774295e-05,
"loss": 0.0781,
"step": 1110
},
{
"epoch": 3.49,
"learning_rate": 3.25705329153605e-05,
"loss": 0.3144,
"step": 1112
},
{
"epoch": 3.49,
"learning_rate": 3.253918495297806e-05,
"loss": 0.1413,
"step": 1114
},
{
"epoch": 3.5,
"learning_rate": 3.250783699059561e-05,
"loss": 0.5225,
"step": 1116
},
{
"epoch": 3.5,
"learning_rate": 3.2476489028213166e-05,
"loss": 0.4774,
"step": 1118
},
{
"epoch": 3.51,
"learning_rate": 3.244514106583073e-05,
"loss": 0.4574,
"step": 1120
},
{
"epoch": 3.52,
"learning_rate": 3.2413793103448275e-05,
"loss": 0.0705,
"step": 1122
},
{
"epoch": 3.52,
"learning_rate": 3.238244514106583e-05,
"loss": 0.7696,
"step": 1124
},
{
"epoch": 3.53,
"learning_rate": 3.235109717868339e-05,
"loss": 0.2546,
"step": 1126
},
{
"epoch": 3.54,
"learning_rate": 3.2319749216300945e-05,
"loss": 0.0952,
"step": 1128
},
{
"epoch": 3.54,
"learning_rate": 3.22884012539185e-05,
"loss": 0.1475,
"step": 1130
},
{
"epoch": 3.55,
"learning_rate": 3.2257053291536046e-05,
"loss": 0.0742,
"step": 1132
},
{
"epoch": 3.55,
"learning_rate": 3.222570532915361e-05,
"loss": 0.4851,
"step": 1134
},
{
"epoch": 3.56,
"learning_rate": 3.219435736677116e-05,
"loss": 0.0518,
"step": 1136
},
{
"epoch": 3.57,
"learning_rate": 3.2163009404388716e-05,
"loss": 0.0556,
"step": 1138
},
{
"epoch": 3.57,
"learning_rate": 3.213166144200627e-05,
"loss": 0.1462,
"step": 1140
},
{
"epoch": 3.58,
"learning_rate": 3.2100313479623825e-05,
"loss": 0.1303,
"step": 1142
},
{
"epoch": 3.59,
"learning_rate": 3.206896551724138e-05,
"loss": 0.4243,
"step": 1144
},
{
"epoch": 3.59,
"learning_rate": 3.203761755485893e-05,
"loss": 0.0866,
"step": 1146
},
{
"epoch": 3.6,
"learning_rate": 3.200626959247649e-05,
"loss": 0.2413,
"step": 1148
},
{
"epoch": 3.61,
"learning_rate": 3.197492163009405e-05,
"loss": 0.0898,
"step": 1150
},
{
"epoch": 3.61,
"learning_rate": 3.19435736677116e-05,
"loss": 0.0549,
"step": 1152
},
{
"epoch": 3.62,
"learning_rate": 3.191222570532916e-05,
"loss": 0.4616,
"step": 1154
},
{
"epoch": 3.62,
"learning_rate": 3.1880877742946705e-05,
"loss": 0.5832,
"step": 1156
},
{
"epoch": 3.63,
"learning_rate": 3.1849529780564266e-05,
"loss": 0.0782,
"step": 1158
},
{
"epoch": 3.64,
"learning_rate": 3.181818181818182e-05,
"loss": 0.1716,
"step": 1160
},
{
"epoch": 3.64,
"learning_rate": 3.1786833855799375e-05,
"loss": 0.0763,
"step": 1162
},
{
"epoch": 3.65,
"learning_rate": 3.175548589341693e-05,
"loss": 0.2826,
"step": 1164
},
{
"epoch": 3.66,
"learning_rate": 3.172413793103448e-05,
"loss": 0.3216,
"step": 1166
},
{
"epoch": 3.66,
"learning_rate": 3.169278996865204e-05,
"loss": 0.1686,
"step": 1168
},
{
"epoch": 3.67,
"learning_rate": 3.166144200626959e-05,
"loss": 0.2955,
"step": 1170
},
{
"epoch": 3.67,
"learning_rate": 3.1630094043887146e-05,
"loss": 0.4539,
"step": 1172
},
{
"epoch": 3.68,
"learning_rate": 3.159874608150471e-05,
"loss": 0.3451,
"step": 1174
},
{
"epoch": 3.69,
"learning_rate": 3.156739811912226e-05,
"loss": 0.1087,
"step": 1176
},
{
"epoch": 3.69,
"learning_rate": 3.1536050156739816e-05,
"loss": 0.5204,
"step": 1178
},
{
"epoch": 3.7,
"learning_rate": 3.1504702194357363e-05,
"loss": 0.5709,
"step": 1180
},
{
"epoch": 3.71,
"learning_rate": 3.1473354231974925e-05,
"loss": 0.2778,
"step": 1182
},
{
"epoch": 3.71,
"learning_rate": 3.144200626959248e-05,
"loss": 0.2798,
"step": 1184
},
{
"epoch": 3.72,
"learning_rate": 3.141065830721003e-05,
"loss": 0.2836,
"step": 1186
},
{
"epoch": 3.72,
"learning_rate": 3.137931034482759e-05,
"loss": 0.0983,
"step": 1188
},
{
"epoch": 3.73,
"learning_rate": 3.134796238244515e-05,
"loss": 0.069,
"step": 1190
},
{
"epoch": 3.74,
"learning_rate": 3.1316614420062696e-05,
"loss": 0.3286,
"step": 1192
},
{
"epoch": 3.74,
"learning_rate": 3.128526645768025e-05,
"loss": 0.0437,
"step": 1194
},
{
"epoch": 3.75,
"learning_rate": 3.1253918495297805e-05,
"loss": 0.2272,
"step": 1196
},
{
"epoch": 3.76,
"learning_rate": 3.1222570532915366e-05,
"loss": 0.8885,
"step": 1198
},
{
"epoch": 3.76,
"learning_rate": 3.119122257053292e-05,
"loss": 0.5747,
"step": 1200
},
{
"epoch": 3.77,
"learning_rate": 3.1159874608150474e-05,
"loss": 0.2236,
"step": 1202
},
{
"epoch": 3.77,
"learning_rate": 3.112852664576802e-05,
"loss": 0.1701,
"step": 1204
},
{
"epoch": 3.78,
"learning_rate": 3.109717868338558e-05,
"loss": 0.1269,
"step": 1206
},
{
"epoch": 3.79,
"learning_rate": 3.106583072100314e-05,
"loss": 0.6536,
"step": 1208
},
{
"epoch": 3.79,
"learning_rate": 3.103448275862069e-05,
"loss": 0.3657,
"step": 1210
},
{
"epoch": 3.8,
"learning_rate": 3.1003134796238246e-05,
"loss": 0.6285,
"step": 1212
},
{
"epoch": 3.81,
"learning_rate": 3.09717868338558e-05,
"loss": 1.1006,
"step": 1214
},
{
"epoch": 3.81,
"learning_rate": 3.0940438871473355e-05,
"loss": 0.2188,
"step": 1216
},
{
"epoch": 3.82,
"learning_rate": 3.090909090909091e-05,
"loss": 0.8207,
"step": 1218
},
{
"epoch": 3.82,
"learning_rate": 3.087774294670846e-05,
"loss": 0.4003,
"step": 1220
},
{
"epoch": 3.83,
"learning_rate": 3.0846394984326024e-05,
"loss": 0.1426,
"step": 1222
},
{
"epoch": 3.84,
"learning_rate": 3.081504702194358e-05,
"loss": 0.7219,
"step": 1224
},
{
"epoch": 3.84,
"learning_rate": 3.0783699059561126e-05,
"loss": 0.3991,
"step": 1226
},
{
"epoch": 3.85,
"learning_rate": 3.075235109717868e-05,
"loss": 0.1892,
"step": 1228
},
{
"epoch": 3.86,
"learning_rate": 3.072100313479624e-05,
"loss": 0.1499,
"step": 1230
},
{
"epoch": 3.86,
"learning_rate": 3.0689655172413796e-05,
"loss": 0.4832,
"step": 1232
},
{
"epoch": 3.87,
"learning_rate": 3.065830721003135e-05,
"loss": 0.6595,
"step": 1234
},
{
"epoch": 3.87,
"learning_rate": 3.0626959247648904e-05,
"loss": 0.3086,
"step": 1236
},
{
"epoch": 3.88,
"learning_rate": 3.059561128526646e-05,
"loss": 0.0469,
"step": 1238
},
{
"epoch": 3.89,
"learning_rate": 3.056426332288401e-05,
"loss": 0.2976,
"step": 1240
},
{
"epoch": 3.89,
"learning_rate": 3.053291536050157e-05,
"loss": 0.1056,
"step": 1242
},
{
"epoch": 3.9,
"learning_rate": 3.0501567398119125e-05,
"loss": 0.1464,
"step": 1244
},
{
"epoch": 3.91,
"learning_rate": 3.047021943573668e-05,
"loss": 0.324,
"step": 1246
},
{
"epoch": 3.91,
"learning_rate": 3.0438871473354237e-05,
"loss": 0.1886,
"step": 1248
},
{
"epoch": 3.92,
"learning_rate": 3.0407523510971785e-05,
"loss": 0.0803,
"step": 1250
},
{
"epoch": 3.92,
"learning_rate": 3.0376175548589342e-05,
"loss": 0.6133,
"step": 1252
},
{
"epoch": 3.93,
"learning_rate": 3.0344827586206897e-05,
"loss": 0.446,
"step": 1254
},
{
"epoch": 3.94,
"learning_rate": 3.0313479623824454e-05,
"loss": 0.5536,
"step": 1256
},
{
"epoch": 3.94,
"learning_rate": 3.028213166144201e-05,
"loss": 1.2157,
"step": 1258
},
{
"epoch": 3.95,
"learning_rate": 3.0250783699059566e-05,
"loss": 0.1825,
"step": 1260
},
{
"epoch": 3.96,
"learning_rate": 3.0219435736677114e-05,
"loss": 0.0522,
"step": 1262
},
{
"epoch": 3.96,
"learning_rate": 3.018808777429467e-05,
"loss": 0.6611,
"step": 1264
},
{
"epoch": 3.97,
"learning_rate": 3.0156739811912226e-05,
"loss": 0.6795,
"step": 1266
},
{
"epoch": 3.97,
"learning_rate": 3.0125391849529784e-05,
"loss": 0.4723,
"step": 1268
},
{
"epoch": 3.98,
"learning_rate": 3.0094043887147338e-05,
"loss": 0.29,
"step": 1270
},
{
"epoch": 3.99,
"learning_rate": 3.0062695924764896e-05,
"loss": 0.7305,
"step": 1272
},
{
"epoch": 3.99,
"learning_rate": 3.0031347962382443e-05,
"loss": 0.5894,
"step": 1274
},
{
"epoch": 4.0,
"learning_rate": 3e-05,
"loss": 0.9304,
"step": 1276
},
{
"epoch": 4.0,
"eval_bleu": 0.23021236407798268,
"eval_loss": 0.6479771733283997,
"eval_runtime": 76.2455,
"eval_samples_per_second": 4.223,
"eval_steps_per_second": 1.062,
"step": 1276
},
{
"epoch": 4.01,
"learning_rate": 2.9968652037617555e-05,
"loss": 0.5475,
"step": 1278
},
{
"epoch": 4.01,
"learning_rate": 2.9937304075235113e-05,
"loss": 0.1194,
"step": 1280
},
{
"epoch": 4.02,
"learning_rate": 2.9905956112852667e-05,
"loss": 0.0192,
"step": 1282
},
{
"epoch": 4.03,
"learning_rate": 2.9874608150470225e-05,
"loss": 0.0354,
"step": 1284
},
{
"epoch": 4.03,
"learning_rate": 2.9843260188087772e-05,
"loss": 0.1959,
"step": 1286
},
{
"epoch": 4.04,
"learning_rate": 2.981191222570533e-05,
"loss": 0.6525,
"step": 1288
},
{
"epoch": 4.04,
"learning_rate": 2.9780564263322884e-05,
"loss": 0.0693,
"step": 1290
},
{
"epoch": 4.05,
"learning_rate": 2.9749216300940442e-05,
"loss": 0.4917,
"step": 1292
},
{
"epoch": 4.06,
"learning_rate": 2.9717868338557996e-05,
"loss": 0.1523,
"step": 1294
},
{
"epoch": 4.06,
"learning_rate": 2.9686520376175547e-05,
"loss": 0.262,
"step": 1296
},
{
"epoch": 4.07,
"learning_rate": 2.96551724137931e-05,
"loss": 0.5281,
"step": 1298
},
{
"epoch": 4.08,
"learning_rate": 2.962382445141066e-05,
"loss": 0.0967,
"step": 1300
},
{
"epoch": 4.08,
"learning_rate": 2.9592476489028214e-05,
"loss": 0.1589,
"step": 1302
},
{
"epoch": 4.09,
"learning_rate": 2.956112852664577e-05,
"loss": 0.4952,
"step": 1304
},
{
"epoch": 4.09,
"learning_rate": 2.9529780564263326e-05,
"loss": 0.5283,
"step": 1306
},
{
"epoch": 4.1,
"learning_rate": 2.9498432601880876e-05,
"loss": 0.4887,
"step": 1308
},
{
"epoch": 4.11,
"learning_rate": 2.946708463949843e-05,
"loss": 0.341,
"step": 1310
},
{
"epoch": 4.11,
"learning_rate": 2.943573667711599e-05,
"loss": 0.0833,
"step": 1312
},
{
"epoch": 4.12,
"learning_rate": 2.9404388714733543e-05,
"loss": 0.2342,
"step": 1314
},
{
"epoch": 4.13,
"learning_rate": 2.93730407523511e-05,
"loss": 0.1071,
"step": 1316
},
{
"epoch": 4.13,
"learning_rate": 2.9341692789968655e-05,
"loss": 0.1208,
"step": 1318
},
{
"epoch": 4.14,
"learning_rate": 2.9310344827586206e-05,
"loss": 0.2908,
"step": 1320
},
{
"epoch": 4.14,
"learning_rate": 2.927899686520376e-05,
"loss": 0.0633,
"step": 1322
},
{
"epoch": 4.15,
"learning_rate": 2.9247648902821318e-05,
"loss": 0.3758,
"step": 1324
},
{
"epoch": 4.16,
"learning_rate": 2.9216300940438872e-05,
"loss": 0.0444,
"step": 1326
},
{
"epoch": 4.16,
"learning_rate": 2.918495297805643e-05,
"loss": 0.0413,
"step": 1328
},
{
"epoch": 4.17,
"learning_rate": 2.9153605015673984e-05,
"loss": 0.3736,
"step": 1330
},
{
"epoch": 4.18,
"learning_rate": 2.9122257053291535e-05,
"loss": 0.2654,
"step": 1332
},
{
"epoch": 4.18,
"learning_rate": 2.909090909090909e-05,
"loss": 0.0624,
"step": 1334
},
{
"epoch": 4.19,
"learning_rate": 2.9059561128526647e-05,
"loss": 0.4802,
"step": 1336
},
{
"epoch": 4.19,
"learning_rate": 2.90282131661442e-05,
"loss": 0.3167,
"step": 1338
},
{
"epoch": 4.2,
"learning_rate": 2.899686520376176e-05,
"loss": 0.0891,
"step": 1340
},
{
"epoch": 4.21,
"learning_rate": 2.8965517241379313e-05,
"loss": 0.1864,
"step": 1342
},
{
"epoch": 4.21,
"learning_rate": 2.8934169278996864e-05,
"loss": 0.202,
"step": 1344
},
{
"epoch": 4.22,
"learning_rate": 2.890282131661442e-05,
"loss": 0.0599,
"step": 1346
},
{
"epoch": 4.23,
"learning_rate": 2.8871473354231976e-05,
"loss": 0.4572,
"step": 1348
},
{
"epoch": 4.23,
"learning_rate": 2.884012539184953e-05,
"loss": 0.164,
"step": 1350
},
{
"epoch": 4.24,
"learning_rate": 2.8808777429467088e-05,
"loss": 0.1774,
"step": 1352
},
{
"epoch": 4.24,
"learning_rate": 2.8777429467084643e-05,
"loss": 0.2898,
"step": 1354
},
{
"epoch": 4.25,
"learning_rate": 2.8746081504702193e-05,
"loss": 0.098,
"step": 1356
},
{
"epoch": 4.26,
"learning_rate": 2.8714733542319748e-05,
"loss": 0.3329,
"step": 1358
},
{
"epoch": 4.26,
"learning_rate": 2.8683385579937305e-05,
"loss": 0.2385,
"step": 1360
},
{
"epoch": 4.27,
"learning_rate": 2.865203761755486e-05,
"loss": 0.3153,
"step": 1362
},
{
"epoch": 4.28,
"learning_rate": 2.8620689655172417e-05,
"loss": 0.4507,
"step": 1364
},
{
"epoch": 4.28,
"learning_rate": 2.8589341692789972e-05,
"loss": 0.1456,
"step": 1366
},
{
"epoch": 4.29,
"learning_rate": 2.8557993730407523e-05,
"loss": 0.3013,
"step": 1368
},
{
"epoch": 4.29,
"learning_rate": 2.8526645768025077e-05,
"loss": 0.7018,
"step": 1370
},
{
"epoch": 4.3,
"learning_rate": 2.8495297805642635e-05,
"loss": 0.3912,
"step": 1372
},
{
"epoch": 4.31,
"learning_rate": 2.846394984326019e-05,
"loss": 0.135,
"step": 1374
},
{
"epoch": 4.31,
"learning_rate": 2.8432601880877747e-05,
"loss": 0.2511,
"step": 1376
},
{
"epoch": 4.32,
"learning_rate": 2.84012539184953e-05,
"loss": 0.1477,
"step": 1378
},
{
"epoch": 4.33,
"learning_rate": 2.8369905956112852e-05,
"loss": 0.2851,
"step": 1380
},
{
"epoch": 4.33,
"learning_rate": 2.833855799373041e-05,
"loss": 0.0683,
"step": 1382
},
{
"epoch": 4.34,
"learning_rate": 2.8307210031347964e-05,
"loss": 0.0769,
"step": 1384
},
{
"epoch": 4.34,
"learning_rate": 2.8275862068965518e-05,
"loss": 0.8171,
"step": 1386
},
{
"epoch": 4.35,
"learning_rate": 2.8244514106583076e-05,
"loss": 0.0492,
"step": 1388
},
{
"epoch": 4.36,
"learning_rate": 2.8213166144200627e-05,
"loss": 0.067,
"step": 1390
},
{
"epoch": 4.36,
"learning_rate": 2.818181818181818e-05,
"loss": 0.4145,
"step": 1392
},
{
"epoch": 4.37,
"learning_rate": 2.815047021943574e-05,
"loss": 0.0523,
"step": 1394
},
{
"epoch": 4.38,
"learning_rate": 2.8119122257053293e-05,
"loss": 0.2317,
"step": 1396
},
{
"epoch": 4.38,
"learning_rate": 2.8087774294670848e-05,
"loss": 0.0684,
"step": 1398
},
{
"epoch": 4.39,
"learning_rate": 2.8056426332288405e-05,
"loss": 0.4624,
"step": 1400
},
{
"epoch": 4.39,
"learning_rate": 2.8025078369905956e-05,
"loss": 0.0585,
"step": 1402
},
{
"epoch": 4.4,
"learning_rate": 2.799373040752351e-05,
"loss": 0.1308,
"step": 1404
},
{
"epoch": 4.41,
"learning_rate": 2.7962382445141068e-05,
"loss": 0.8529,
"step": 1406
},
{
"epoch": 4.41,
"learning_rate": 2.7931034482758622e-05,
"loss": 0.1775,
"step": 1408
},
{
"epoch": 4.42,
"learning_rate": 2.7899686520376177e-05,
"loss": 0.0883,
"step": 1410
},
{
"epoch": 4.43,
"learning_rate": 2.7868338557993734e-05,
"loss": 0.3945,
"step": 1412
},
{
"epoch": 4.43,
"learning_rate": 2.7836990595611285e-05,
"loss": 0.5306,
"step": 1414
},
{
"epoch": 4.44,
"learning_rate": 2.780564263322884e-05,
"loss": 0.2451,
"step": 1416
},
{
"epoch": 4.45,
"learning_rate": 2.7774294670846397e-05,
"loss": 0.469,
"step": 1418
},
{
"epoch": 4.45,
"learning_rate": 2.774294670846395e-05,
"loss": 0.248,
"step": 1420
},
{
"epoch": 4.46,
"learning_rate": 2.7711598746081506e-05,
"loss": 1.7219,
"step": 1422
},
{
"epoch": 4.46,
"learning_rate": 2.7680250783699064e-05,
"loss": 0.1982,
"step": 1424
},
{
"epoch": 4.47,
"learning_rate": 2.7648902821316615e-05,
"loss": 0.6336,
"step": 1426
},
{
"epoch": 4.48,
"learning_rate": 2.761755485893417e-05,
"loss": 0.0537,
"step": 1428
},
{
"epoch": 4.48,
"learning_rate": 2.7586206896551727e-05,
"loss": 0.0902,
"step": 1430
},
{
"epoch": 4.49,
"learning_rate": 2.755485893416928e-05,
"loss": 0.5485,
"step": 1432
},
{
"epoch": 4.5,
"learning_rate": 2.7523510971786835e-05,
"loss": 0.2901,
"step": 1434
},
{
"epoch": 4.5,
"learning_rate": 2.7492163009404393e-05,
"loss": 0.1135,
"step": 1436
},
{
"epoch": 4.51,
"learning_rate": 2.7460815047021944e-05,
"loss": 0.0811,
"step": 1438
},
{
"epoch": 4.51,
"learning_rate": 2.7429467084639498e-05,
"loss": 0.0689,
"step": 1440
},
{
"epoch": 4.52,
"learning_rate": 2.7398119122257056e-05,
"loss": 0.5802,
"step": 1442
},
{
"epoch": 4.53,
"learning_rate": 2.736677115987461e-05,
"loss": 0.075,
"step": 1444
},
{
"epoch": 4.53,
"learning_rate": 2.7335423197492164e-05,
"loss": 0.3645,
"step": 1446
},
{
"epoch": 4.54,
"learning_rate": 2.7304075235109722e-05,
"loss": 0.0482,
"step": 1448
},
{
"epoch": 4.55,
"learning_rate": 2.7272727272727273e-05,
"loss": 0.4667,
"step": 1450
},
{
"epoch": 4.55,
"learning_rate": 2.7241379310344827e-05,
"loss": 0.5588,
"step": 1452
},
{
"epoch": 4.56,
"learning_rate": 2.7210031347962385e-05,
"loss": 0.0841,
"step": 1454
},
{
"epoch": 4.56,
"learning_rate": 2.717868338557994e-05,
"loss": 0.324,
"step": 1456
},
{
"epoch": 4.57,
"learning_rate": 2.7147335423197494e-05,
"loss": 0.394,
"step": 1458
},
{
"epoch": 4.58,
"learning_rate": 2.711598746081505e-05,
"loss": 0.6257,
"step": 1460
},
{
"epoch": 4.58,
"learning_rate": 2.7084639498432602e-05,
"loss": 0.4819,
"step": 1462
},
{
"epoch": 4.59,
"learning_rate": 2.7053291536050157e-05,
"loss": 0.5093,
"step": 1464
},
{
"epoch": 4.6,
"learning_rate": 2.7021943573667714e-05,
"loss": 0.0432,
"step": 1466
},
{
"epoch": 4.6,
"learning_rate": 2.699059561128527e-05,
"loss": 0.0653,
"step": 1468
},
{
"epoch": 4.61,
"learning_rate": 2.6959247648902823e-05,
"loss": 0.0196,
"step": 1470
},
{
"epoch": 4.61,
"learning_rate": 2.6927899686520374e-05,
"loss": 0.2154,
"step": 1472
},
{
"epoch": 4.62,
"learning_rate": 2.689655172413793e-05,
"loss": 0.2095,
"step": 1474
},
{
"epoch": 4.63,
"learning_rate": 2.6865203761755486e-05,
"loss": 0.0493,
"step": 1476
},
{
"epoch": 4.63,
"learning_rate": 2.6833855799373044e-05,
"loss": 0.9636,
"step": 1478
},
{
"epoch": 4.64,
"learning_rate": 2.6802507836990598e-05,
"loss": 0.181,
"step": 1480
},
{
"epoch": 4.65,
"learning_rate": 2.6771159874608152e-05,
"loss": 0.1509,
"step": 1482
},
{
"epoch": 4.65,
"learning_rate": 2.6739811912225703e-05,
"loss": 0.1301,
"step": 1484
},
{
"epoch": 4.66,
"learning_rate": 2.670846394984326e-05,
"loss": 0.0986,
"step": 1486
},
{
"epoch": 4.66,
"learning_rate": 2.6677115987460815e-05,
"loss": 0.2525,
"step": 1488
},
{
"epoch": 4.67,
"learning_rate": 2.6645768025078373e-05,
"loss": 0.0452,
"step": 1490
},
{
"epoch": 4.68,
"learning_rate": 2.6614420062695927e-05,
"loss": 0.0435,
"step": 1492
},
{
"epoch": 4.68,
"learning_rate": 2.658307210031348e-05,
"loss": 0.2368,
"step": 1494
},
{
"epoch": 4.69,
"learning_rate": 2.6551724137931032e-05,
"loss": 0.0974,
"step": 1496
},
{
"epoch": 4.7,
"learning_rate": 2.652037617554859e-05,
"loss": 0.0475,
"step": 1498
},
{
"epoch": 4.7,
"learning_rate": 2.6489028213166144e-05,
"loss": 0.1832,
"step": 1500
},
{
"epoch": 4.71,
"learning_rate": 2.6457680250783702e-05,
"loss": 0.4982,
"step": 1502
},
{
"epoch": 4.71,
"learning_rate": 2.6426332288401256e-05,
"loss": 0.2645,
"step": 1504
},
{
"epoch": 4.72,
"learning_rate": 2.639498432601881e-05,
"loss": 0.1578,
"step": 1506
},
{
"epoch": 4.73,
"learning_rate": 2.636363636363636e-05,
"loss": 0.1172,
"step": 1508
},
{
"epoch": 4.73,
"learning_rate": 2.633228840125392e-05,
"loss": 0.3035,
"step": 1510
},
{
"epoch": 4.74,
"learning_rate": 2.6300940438871474e-05,
"loss": 0.7947,
"step": 1512
},
{
"epoch": 4.75,
"learning_rate": 2.626959247648903e-05,
"loss": 0.0331,
"step": 1514
},
{
"epoch": 4.75,
"learning_rate": 2.6238244514106586e-05,
"loss": 0.04,
"step": 1516
},
{
"epoch": 4.76,
"learning_rate": 2.620689655172414e-05,
"loss": 0.2473,
"step": 1518
},
{
"epoch": 4.76,
"learning_rate": 2.617554858934169e-05,
"loss": 0.958,
"step": 1520
},
{
"epoch": 4.77,
"learning_rate": 2.614420062695925e-05,
"loss": 0.1583,
"step": 1522
},
{
"epoch": 4.78,
"learning_rate": 2.6112852664576803e-05,
"loss": 0.4548,
"step": 1524
},
{
"epoch": 4.78,
"learning_rate": 2.608150470219436e-05,
"loss": 0.3725,
"step": 1526
},
{
"epoch": 4.79,
"learning_rate": 2.6050156739811915e-05,
"loss": 0.302,
"step": 1528
},
{
"epoch": 4.8,
"learning_rate": 2.601880877742947e-05,
"loss": 0.0498,
"step": 1530
},
{
"epoch": 4.8,
"learning_rate": 2.598746081504702e-05,
"loss": 0.2619,
"step": 1532
},
{
"epoch": 4.81,
"learning_rate": 2.5956112852664578e-05,
"loss": 0.0683,
"step": 1534
},
{
"epoch": 4.82,
"learning_rate": 2.5924764890282132e-05,
"loss": 0.3522,
"step": 1536
},
{
"epoch": 4.82,
"learning_rate": 2.589341692789969e-05,
"loss": 0.533,
"step": 1538
},
{
"epoch": 4.83,
"learning_rate": 2.5862068965517244e-05,
"loss": 0.1604,
"step": 1540
},
{
"epoch": 4.83,
"learning_rate": 2.5830721003134802e-05,
"loss": 0.0985,
"step": 1542
},
{
"epoch": 4.84,
"learning_rate": 2.579937304075235e-05,
"loss": 0.5565,
"step": 1544
},
{
"epoch": 4.85,
"learning_rate": 2.5768025078369907e-05,
"loss": 0.045,
"step": 1546
},
{
"epoch": 4.85,
"learning_rate": 2.573667711598746e-05,
"loss": 0.0322,
"step": 1548
},
{
"epoch": 4.86,
"learning_rate": 2.570532915360502e-05,
"loss": 0.0435,
"step": 1550
},
{
"epoch": 4.87,
"learning_rate": 2.5673981191222573e-05,
"loss": 0.0321,
"step": 1552
},
{
"epoch": 4.87,
"learning_rate": 2.5642633228840124e-05,
"loss": 0.1644,
"step": 1554
},
{
"epoch": 4.88,
"learning_rate": 2.561128526645768e-05,
"loss": 0.0317,
"step": 1556
},
{
"epoch": 4.88,
"learning_rate": 2.5579937304075236e-05,
"loss": 0.0893,
"step": 1558
},
{
"epoch": 4.89,
"learning_rate": 2.554858934169279e-05,
"loss": 0.1798,
"step": 1560
},
{
"epoch": 4.9,
"learning_rate": 2.551724137931035e-05,
"loss": 0.2309,
"step": 1562
},
{
"epoch": 4.9,
"learning_rate": 2.5485893416927903e-05,
"loss": 0.142,
"step": 1564
},
{
"epoch": 4.91,
"learning_rate": 2.5454545454545454e-05,
"loss": 0.2153,
"step": 1566
},
{
"epoch": 4.92,
"learning_rate": 2.5423197492163008e-05,
"loss": 0.3906,
"step": 1568
},
{
"epoch": 4.92,
"learning_rate": 2.5391849529780566e-05,
"loss": 0.0391,
"step": 1570
},
{
"epoch": 4.93,
"learning_rate": 2.536050156739812e-05,
"loss": 0.2337,
"step": 1572
},
{
"epoch": 4.93,
"learning_rate": 2.5329153605015678e-05,
"loss": 0.0839,
"step": 1574
},
{
"epoch": 4.94,
"learning_rate": 2.5297805642633232e-05,
"loss": 0.0837,
"step": 1576
},
{
"epoch": 4.95,
"learning_rate": 2.5266457680250783e-05,
"loss": 0.1193,
"step": 1578
},
{
"epoch": 4.95,
"learning_rate": 2.5235109717868337e-05,
"loss": 0.6238,
"step": 1580
},
{
"epoch": 4.96,
"learning_rate": 2.5203761755485895e-05,
"loss": 0.2111,
"step": 1582
},
{
"epoch": 4.97,
"learning_rate": 2.517241379310345e-05,
"loss": 0.2726,
"step": 1584
},
{
"epoch": 4.97,
"learning_rate": 2.5141065830721007e-05,
"loss": 0.1368,
"step": 1586
},
{
"epoch": 4.98,
"learning_rate": 2.510971786833856e-05,
"loss": 0.3613,
"step": 1588
},
{
"epoch": 4.98,
"learning_rate": 2.5078369905956112e-05,
"loss": 0.2065,
"step": 1590
},
{
"epoch": 4.99,
"learning_rate": 2.5047021943573666e-05,
"loss": 0.4981,
"step": 1592
},
{
"epoch": 5.0,
"learning_rate": 2.5015673981191224e-05,
"loss": 0.0737,
"step": 1594
},
{
"epoch": 5.0,
"eval_bleu": 0.24300561580847288,
"eval_loss": 0.699813723564148,
"eval_runtime": 75.6288,
"eval_samples_per_second": 4.258,
"eval_steps_per_second": 1.071,
"step": 1595
},
{
"epoch": 5.0,
"learning_rate": 2.498432601880878e-05,
"loss": 0.165,
"step": 1596
},
{
"epoch": 5.01,
"learning_rate": 2.4952978056426333e-05,
"loss": 0.3377,
"step": 1598
},
{
"epoch": 5.02,
"learning_rate": 2.4921630094043887e-05,
"loss": 0.0247,
"step": 1600
},
{
"epoch": 5.02,
"learning_rate": 2.4890282131661445e-05,
"loss": 0.5538,
"step": 1602
},
{
"epoch": 5.03,
"learning_rate": 2.4858934169278996e-05,
"loss": 0.293,
"step": 1604
},
{
"epoch": 5.03,
"learning_rate": 2.4827586206896553e-05,
"loss": 0.4556,
"step": 1606
},
{
"epoch": 5.04,
"learning_rate": 2.4796238244514108e-05,
"loss": 0.1204,
"step": 1608
},
{
"epoch": 5.05,
"learning_rate": 2.4764890282131662e-05,
"loss": 0.0708,
"step": 1610
},
{
"epoch": 5.05,
"learning_rate": 2.4733542319749216e-05,
"loss": 0.1078,
"step": 1612
},
{
"epoch": 5.06,
"learning_rate": 2.4702194357366774e-05,
"loss": 0.0905,
"step": 1614
},
{
"epoch": 5.07,
"learning_rate": 2.4670846394984325e-05,
"loss": 0.1489,
"step": 1616
},
{
"epoch": 5.07,
"learning_rate": 2.4639498432601883e-05,
"loss": 0.0293,
"step": 1618
},
{
"epoch": 5.08,
"learning_rate": 2.4608150470219437e-05,
"loss": 0.1292,
"step": 1620
},
{
"epoch": 5.08,
"learning_rate": 2.457680250783699e-05,
"loss": 0.0614,
"step": 1622
},
{
"epoch": 5.09,
"learning_rate": 2.4545454545454545e-05,
"loss": 0.7514,
"step": 1624
},
{
"epoch": 5.1,
"learning_rate": 2.4514106583072103e-05,
"loss": 0.4222,
"step": 1626
},
{
"epoch": 5.1,
"learning_rate": 2.4482758620689654e-05,
"loss": 0.0385,
"step": 1628
},
{
"epoch": 5.11,
"learning_rate": 2.4451410658307212e-05,
"loss": 0.3357,
"step": 1630
},
{
"epoch": 5.12,
"learning_rate": 2.4420062695924766e-05,
"loss": 0.0195,
"step": 1632
},
{
"epoch": 5.12,
"learning_rate": 2.438871473354232e-05,
"loss": 0.0473,
"step": 1634
},
{
"epoch": 5.13,
"learning_rate": 2.4357366771159875e-05,
"loss": 0.2076,
"step": 1636
},
{
"epoch": 5.13,
"learning_rate": 2.4326018808777432e-05,
"loss": 0.034,
"step": 1638
},
{
"epoch": 5.14,
"learning_rate": 2.4294670846394983e-05,
"loss": 0.0428,
"step": 1640
},
{
"epoch": 5.15,
"learning_rate": 2.426332288401254e-05,
"loss": 0.1964,
"step": 1642
},
{
"epoch": 5.15,
"learning_rate": 2.4231974921630095e-05,
"loss": 0.0614,
"step": 1644
},
{
"epoch": 5.16,
"learning_rate": 2.420062695924765e-05,
"loss": 0.1043,
"step": 1646
},
{
"epoch": 5.17,
"learning_rate": 2.4169278996865204e-05,
"loss": 0.0978,
"step": 1648
},
{
"epoch": 5.17,
"learning_rate": 2.413793103448276e-05,
"loss": 0.085,
"step": 1650
},
{
"epoch": 5.18,
"learning_rate": 2.4106583072100313e-05,
"loss": 0.0285,
"step": 1652
},
{
"epoch": 5.18,
"learning_rate": 2.407523510971787e-05,
"loss": 0.1226,
"step": 1654
},
{
"epoch": 5.19,
"learning_rate": 2.4043887147335425e-05,
"loss": 0.0345,
"step": 1656
},
{
"epoch": 5.2,
"learning_rate": 2.401253918495298e-05,
"loss": 0.6952,
"step": 1658
},
{
"epoch": 5.2,
"learning_rate": 2.3981191222570533e-05,
"loss": 0.0175,
"step": 1660
},
{
"epoch": 5.21,
"learning_rate": 2.394984326018809e-05,
"loss": 0.083,
"step": 1662
},
{
"epoch": 5.22,
"learning_rate": 2.3918495297805642e-05,
"loss": 0.0958,
"step": 1664
},
{
"epoch": 5.22,
"learning_rate": 2.38871473354232e-05,
"loss": 0.1784,
"step": 1666
},
{
"epoch": 5.23,
"learning_rate": 2.3855799373040754e-05,
"loss": 0.2114,
"step": 1668
},
{
"epoch": 5.24,
"learning_rate": 2.3824451410658308e-05,
"loss": 0.0272,
"step": 1670
},
{
"epoch": 5.24,
"learning_rate": 2.3793103448275862e-05,
"loss": 0.3051,
"step": 1672
},
{
"epoch": 5.25,
"learning_rate": 2.376175548589342e-05,
"loss": 0.2488,
"step": 1674
},
{
"epoch": 5.25,
"learning_rate": 2.373040752351097e-05,
"loss": 0.1616,
"step": 1676
},
{
"epoch": 5.26,
"learning_rate": 2.369905956112853e-05,
"loss": 0.2637,
"step": 1678
},
{
"epoch": 5.27,
"learning_rate": 2.3667711598746083e-05,
"loss": 0.1391,
"step": 1680
},
{
"epoch": 5.27,
"learning_rate": 2.3636363636363637e-05,
"loss": 0.2688,
"step": 1682
},
{
"epoch": 5.28,
"learning_rate": 2.360501567398119e-05,
"loss": 0.3939,
"step": 1684
},
{
"epoch": 5.29,
"learning_rate": 2.3573667711598746e-05,
"loss": 0.4107,
"step": 1686
},
{
"epoch": 5.29,
"learning_rate": 2.35423197492163e-05,
"loss": 0.1479,
"step": 1688
},
{
"epoch": 5.3,
"learning_rate": 2.3510971786833858e-05,
"loss": 0.0166,
"step": 1690
},
{
"epoch": 5.3,
"learning_rate": 2.347962382445141e-05,
"loss": 0.0706,
"step": 1692
},
{
"epoch": 5.31,
"learning_rate": 2.3448275862068967e-05,
"loss": 0.1003,
"step": 1694
},
{
"epoch": 5.32,
"learning_rate": 2.341692789968652e-05,
"loss": 0.2357,
"step": 1696
},
{
"epoch": 5.32,
"learning_rate": 2.3385579937304075e-05,
"loss": 0.3832,
"step": 1698
},
{
"epoch": 5.33,
"learning_rate": 2.335423197492163e-05,
"loss": 0.1109,
"step": 1700
},
{
"epoch": 5.34,
"learning_rate": 2.3322884012539187e-05,
"loss": 0.0448,
"step": 1702
},
{
"epoch": 5.34,
"learning_rate": 2.3291536050156738e-05,
"loss": 0.5746,
"step": 1704
},
{
"epoch": 5.35,
"learning_rate": 2.3260188087774296e-05,
"loss": 0.1064,
"step": 1706
},
{
"epoch": 5.35,
"learning_rate": 2.322884012539185e-05,
"loss": 0.0285,
"step": 1708
},
{
"epoch": 5.36,
"learning_rate": 2.3197492163009404e-05,
"loss": 0.04,
"step": 1710
},
{
"epoch": 5.37,
"learning_rate": 2.316614420062696e-05,
"loss": 0.0147,
"step": 1712
},
{
"epoch": 5.37,
"learning_rate": 2.3134796238244516e-05,
"loss": 0.4445,
"step": 1714
},
{
"epoch": 5.38,
"learning_rate": 2.3103448275862067e-05,
"loss": 0.0545,
"step": 1716
},
{
"epoch": 5.39,
"learning_rate": 2.3072100313479625e-05,
"loss": 0.1816,
"step": 1718
},
{
"epoch": 5.39,
"learning_rate": 2.304075235109718e-05,
"loss": 0.3879,
"step": 1720
},
{
"epoch": 5.4,
"learning_rate": 2.3009404388714734e-05,
"loss": 0.095,
"step": 1722
},
{
"epoch": 5.4,
"learning_rate": 2.2978056426332288e-05,
"loss": 0.2232,
"step": 1724
},
{
"epoch": 5.41,
"learning_rate": 2.2946708463949846e-05,
"loss": 0.3626,
"step": 1726
},
{
"epoch": 5.42,
"learning_rate": 2.2915360501567397e-05,
"loss": 0.0528,
"step": 1728
},
{
"epoch": 5.42,
"learning_rate": 2.2884012539184954e-05,
"loss": 0.1118,
"step": 1730
},
{
"epoch": 5.43,
"learning_rate": 2.285266457680251e-05,
"loss": 0.2373,
"step": 1732
},
{
"epoch": 5.44,
"learning_rate": 2.2821316614420063e-05,
"loss": 0.2109,
"step": 1734
},
{
"epoch": 5.44,
"learning_rate": 2.2789968652037617e-05,
"loss": 0.7088,
"step": 1736
},
{
"epoch": 5.45,
"learning_rate": 2.2758620689655175e-05,
"loss": 0.1491,
"step": 1738
},
{
"epoch": 5.45,
"learning_rate": 2.272727272727273e-05,
"loss": 0.0294,
"step": 1740
},
{
"epoch": 5.46,
"learning_rate": 2.2695924764890284e-05,
"loss": 0.3541,
"step": 1742
},
{
"epoch": 5.47,
"learning_rate": 2.2664576802507838e-05,
"loss": 0.1801,
"step": 1744
},
{
"epoch": 5.47,
"learning_rate": 2.2633228840125392e-05,
"loss": 0.0257,
"step": 1746
},
{
"epoch": 5.48,
"learning_rate": 2.2601880877742947e-05,
"loss": 0.1626,
"step": 1748
},
{
"epoch": 5.49,
"learning_rate": 2.2570532915360504e-05,
"loss": 0.8919,
"step": 1750
},
{
"epoch": 5.49,
"learning_rate": 2.253918495297806e-05,
"loss": 0.0479,
"step": 1752
},
{
"epoch": 5.5,
"learning_rate": 2.2507836990595613e-05,
"loss": 0.3951,
"step": 1754
},
{
"epoch": 5.5,
"learning_rate": 2.2476489028213167e-05,
"loss": 0.0252,
"step": 1756
},
{
"epoch": 5.51,
"learning_rate": 2.244514106583072e-05,
"loss": 0.3512,
"step": 1758
},
{
"epoch": 5.52,
"learning_rate": 2.2413793103448276e-05,
"loss": 0.4041,
"step": 1760
},
{
"epoch": 5.52,
"learning_rate": 2.2382445141065833e-05,
"loss": 0.0835,
"step": 1762
},
{
"epoch": 5.53,
"learning_rate": 2.2351097178683388e-05,
"loss": 0.7581,
"step": 1764
},
{
"epoch": 5.54,
"learning_rate": 2.2319749216300942e-05,
"loss": 0.3331,
"step": 1766
},
{
"epoch": 5.54,
"learning_rate": 2.2288401253918496e-05,
"loss": 0.0736,
"step": 1768
},
{
"epoch": 5.55,
"learning_rate": 2.225705329153605e-05,
"loss": 0.1169,
"step": 1770
},
{
"epoch": 5.55,
"learning_rate": 2.2225705329153605e-05,
"loss": 0.1255,
"step": 1772
},
{
"epoch": 5.56,
"learning_rate": 2.219435736677116e-05,
"loss": 0.1737,
"step": 1774
},
{
"epoch": 5.57,
"learning_rate": 2.2163009404388717e-05,
"loss": 0.0969,
"step": 1776
},
{
"epoch": 5.57,
"learning_rate": 2.213166144200627e-05,
"loss": 0.0086,
"step": 1778
},
{
"epoch": 5.58,
"learning_rate": 2.2100313479623826e-05,
"loss": 0.0897,
"step": 1780
},
{
"epoch": 5.59,
"learning_rate": 2.206896551724138e-05,
"loss": 0.0578,
"step": 1782
},
{
"epoch": 5.59,
"learning_rate": 2.2037617554858934e-05,
"loss": 0.1835,
"step": 1784
},
{
"epoch": 5.6,
"learning_rate": 2.200626959247649e-05,
"loss": 0.6684,
"step": 1786
},
{
"epoch": 5.61,
"learning_rate": 2.1974921630094046e-05,
"loss": 0.1879,
"step": 1788
},
{
"epoch": 5.61,
"learning_rate": 2.19435736677116e-05,
"loss": 0.356,
"step": 1790
},
{
"epoch": 5.62,
"learning_rate": 2.1912225705329155e-05,
"loss": 0.4864,
"step": 1792
},
{
"epoch": 5.62,
"learning_rate": 2.188087774294671e-05,
"loss": 0.1917,
"step": 1794
},
{
"epoch": 5.63,
"learning_rate": 2.1849529780564264e-05,
"loss": 0.2009,
"step": 1796
},
{
"epoch": 5.64,
"learning_rate": 2.1818181818181818e-05,
"loss": 0.2977,
"step": 1798
},
{
"epoch": 5.64,
"learning_rate": 2.1786833855799376e-05,
"loss": 0.3496,
"step": 1800
},
{
"epoch": 5.65,
"learning_rate": 2.175548589341693e-05,
"loss": 0.3726,
"step": 1802
},
{
"epoch": 5.66,
"learning_rate": 2.1724137931034484e-05,
"loss": 0.2824,
"step": 1804
},
{
"epoch": 5.66,
"learning_rate": 2.169278996865204e-05,
"loss": 0.3257,
"step": 1806
},
{
"epoch": 5.67,
"learning_rate": 2.1661442006269593e-05,
"loss": 0.5496,
"step": 1808
},
{
"epoch": 5.67,
"learning_rate": 2.1630094043887147e-05,
"loss": 0.1033,
"step": 1810
},
{
"epoch": 5.68,
"learning_rate": 2.1598746081504705e-05,
"loss": 0.0302,
"step": 1812
},
{
"epoch": 5.69,
"learning_rate": 2.156739811912226e-05,
"loss": 0.2603,
"step": 1814
},
{
"epoch": 5.69,
"learning_rate": 2.1536050156739813e-05,
"loss": 0.1804,
"step": 1816
},
{
"epoch": 5.7,
"learning_rate": 2.1504702194357368e-05,
"loss": 0.1968,
"step": 1818
},
{
"epoch": 5.71,
"learning_rate": 2.1473354231974925e-05,
"loss": 0.1893,
"step": 1820
},
{
"epoch": 5.71,
"learning_rate": 2.1442006269592476e-05,
"loss": 0.0244,
"step": 1822
},
{
"epoch": 5.72,
"learning_rate": 2.1410658307210034e-05,
"loss": 0.1275,
"step": 1824
},
{
"epoch": 5.72,
"learning_rate": 2.137931034482759e-05,
"loss": 0.5424,
"step": 1826
},
{
"epoch": 5.73,
"learning_rate": 2.1347962382445143e-05,
"loss": 0.1437,
"step": 1828
},
{
"epoch": 5.74,
"learning_rate": 2.1316614420062697e-05,
"loss": 0.3937,
"step": 1830
},
{
"epoch": 5.74,
"learning_rate": 2.1285266457680255e-05,
"loss": 0.0505,
"step": 1832
},
{
"epoch": 5.75,
"learning_rate": 2.1253918495297806e-05,
"loss": 0.2163,
"step": 1834
},
{
"epoch": 5.76,
"learning_rate": 2.1222570532915363e-05,
"loss": 0.1776,
"step": 1836
},
{
"epoch": 5.76,
"learning_rate": 2.1191222570532918e-05,
"loss": 0.136,
"step": 1838
},
{
"epoch": 5.77,
"learning_rate": 2.1159874608150472e-05,
"loss": 0.2802,
"step": 1840
},
{
"epoch": 5.77,
"learning_rate": 2.1128526645768026e-05,
"loss": 0.3908,
"step": 1842
},
{
"epoch": 5.78,
"learning_rate": 2.1097178683385584e-05,
"loss": 0.1034,
"step": 1844
},
{
"epoch": 5.79,
"learning_rate": 2.1065830721003135e-05,
"loss": 0.3721,
"step": 1846
},
{
"epoch": 5.79,
"learning_rate": 2.1034482758620692e-05,
"loss": 0.0378,
"step": 1848
},
{
"epoch": 5.8,
"learning_rate": 2.1003134796238247e-05,
"loss": 0.1305,
"step": 1850
},
{
"epoch": 5.81,
"learning_rate": 2.09717868338558e-05,
"loss": 0.2223,
"step": 1852
},
{
"epoch": 5.81,
"learning_rate": 2.0940438871473355e-05,
"loss": 0.0197,
"step": 1854
},
{
"epoch": 5.82,
"learning_rate": 2.090909090909091e-05,
"loss": 0.0702,
"step": 1856
},
{
"epoch": 5.82,
"learning_rate": 2.0877742946708464e-05,
"loss": 0.0221,
"step": 1858
},
{
"epoch": 5.83,
"learning_rate": 2.0846394984326022e-05,
"loss": 0.0653,
"step": 1860
},
{
"epoch": 5.84,
"learning_rate": 2.0815047021943573e-05,
"loss": 0.0245,
"step": 1862
},
{
"epoch": 5.84,
"learning_rate": 2.078369905956113e-05,
"loss": 0.0709,
"step": 1864
},
{
"epoch": 5.85,
"learning_rate": 2.0752351097178685e-05,
"loss": 0.4767,
"step": 1866
},
{
"epoch": 5.86,
"learning_rate": 2.072100313479624e-05,
"loss": 0.2231,
"step": 1868
},
{
"epoch": 5.86,
"learning_rate": 2.0689655172413793e-05,
"loss": 0.0583,
"step": 1870
},
{
"epoch": 5.87,
"learning_rate": 2.065830721003135e-05,
"loss": 0.0712,
"step": 1872
},
{
"epoch": 5.87,
"learning_rate": 2.0626959247648902e-05,
"loss": 0.2551,
"step": 1874
},
{
"epoch": 5.88,
"learning_rate": 2.059561128526646e-05,
"loss": 0.3786,
"step": 1876
},
{
"epoch": 5.89,
"learning_rate": 2.0564263322884014e-05,
"loss": 0.2306,
"step": 1878
},
{
"epoch": 5.89,
"learning_rate": 2.0532915360501568e-05,
"loss": 0.3652,
"step": 1880
},
{
"epoch": 5.9,
"learning_rate": 2.0501567398119123e-05,
"loss": 0.2206,
"step": 1882
},
{
"epoch": 5.91,
"learning_rate": 2.047021943573668e-05,
"loss": 0.1188,
"step": 1884
},
{
"epoch": 5.91,
"learning_rate": 2.043887147335423e-05,
"loss": 0.1001,
"step": 1886
},
{
"epoch": 5.92,
"learning_rate": 2.040752351097179e-05,
"loss": 0.0433,
"step": 1888
},
{
"epoch": 5.92,
"learning_rate": 2.0376175548589343e-05,
"loss": 0.1335,
"step": 1890
},
{
"epoch": 5.93,
"learning_rate": 2.0344827586206897e-05,
"loss": 0.0358,
"step": 1892
},
{
"epoch": 5.94,
"learning_rate": 2.0313479623824452e-05,
"loss": 0.3613,
"step": 1894
},
{
"epoch": 5.94,
"learning_rate": 2.028213166144201e-05,
"loss": 0.1634,
"step": 1896
},
{
"epoch": 5.95,
"learning_rate": 2.025078369905956e-05,
"loss": 0.1517,
"step": 1898
},
{
"epoch": 5.96,
"learning_rate": 2.0219435736677118e-05,
"loss": 0.189,
"step": 1900
},
{
"epoch": 5.96,
"learning_rate": 2.0188087774294672e-05,
"loss": 0.2292,
"step": 1902
},
{
"epoch": 5.97,
"learning_rate": 2.0156739811912227e-05,
"loss": 0.2509,
"step": 1904
},
{
"epoch": 5.97,
"learning_rate": 2.012539184952978e-05,
"loss": 0.2649,
"step": 1906
},
{
"epoch": 5.98,
"learning_rate": 2.009404388714734e-05,
"loss": 0.1959,
"step": 1908
},
{
"epoch": 5.99,
"learning_rate": 2.006269592476489e-05,
"loss": 0.1861,
"step": 1910
},
{
"epoch": 5.99,
"learning_rate": 2.0031347962382447e-05,
"loss": 0.0846,
"step": 1912
},
{
"epoch": 6.0,
"learning_rate": 2e-05,
"loss": 0.0477,
"step": 1914
},
{
"epoch": 6.0,
"eval_bleu": 0.23437903354735942,
"eval_loss": 0.7554587721824646,
"eval_runtime": 76.4452,
"eval_samples_per_second": 4.212,
"eval_steps_per_second": 1.06,
"step": 1914
},
{
"epoch": 6.01,
"learning_rate": 1.9968652037617556e-05,
"loss": 0.1647,
"step": 1916
},
{
"epoch": 6.01,
"learning_rate": 1.993730407523511e-05,
"loss": 0.0463,
"step": 1918
},
{
"epoch": 6.02,
"learning_rate": 1.9905956112852668e-05,
"loss": 0.0195,
"step": 1920
},
{
"epoch": 6.03,
"learning_rate": 1.987460815047022e-05,
"loss": 0.3331,
"step": 1922
},
{
"epoch": 6.03,
"learning_rate": 1.9843260188087777e-05,
"loss": 0.4867,
"step": 1924
},
{
"epoch": 6.04,
"learning_rate": 1.981191222570533e-05,
"loss": 0.0199,
"step": 1926
},
{
"epoch": 6.04,
"learning_rate": 1.9780564263322885e-05,
"loss": 0.0144,
"step": 1928
},
{
"epoch": 6.05,
"learning_rate": 1.974921630094044e-05,
"loss": 0.3574,
"step": 1930
},
{
"epoch": 6.06,
"learning_rate": 1.9717868338557997e-05,
"loss": 0.1336,
"step": 1932
},
{
"epoch": 6.06,
"learning_rate": 1.9686520376175548e-05,
"loss": 0.0059,
"step": 1934
},
{
"epoch": 6.07,
"learning_rate": 1.9655172413793106e-05,
"loss": 0.2306,
"step": 1936
},
{
"epoch": 6.08,
"learning_rate": 1.962382445141066e-05,
"loss": 0.1109,
"step": 1938
},
{
"epoch": 6.08,
"learning_rate": 1.9592476489028214e-05,
"loss": 0.3211,
"step": 1940
},
{
"epoch": 6.09,
"learning_rate": 1.956112852664577e-05,
"loss": 0.0971,
"step": 1942
},
{
"epoch": 6.09,
"learning_rate": 1.9529780564263323e-05,
"loss": 0.0462,
"step": 1944
},
{
"epoch": 6.1,
"learning_rate": 1.9498432601880877e-05,
"loss": 0.0189,
"step": 1946
},
{
"epoch": 6.11,
"learning_rate": 1.9467084639498435e-05,
"loss": 0.1776,
"step": 1948
},
{
"epoch": 6.11,
"learning_rate": 1.9435736677115986e-05,
"loss": 0.1139,
"step": 1950
},
{
"epoch": 6.12,
"learning_rate": 1.9404388714733544e-05,
"loss": 0.1025,
"step": 1952
},
{
"epoch": 6.13,
"learning_rate": 1.9373040752351098e-05,
"loss": 0.4661,
"step": 1954
},
{
"epoch": 6.13,
"learning_rate": 1.9341692789968652e-05,
"loss": 0.1086,
"step": 1956
},
{
"epoch": 6.14,
"learning_rate": 1.9310344827586207e-05,
"loss": 0.1856,
"step": 1958
},
{
"epoch": 6.14,
"learning_rate": 1.9278996865203764e-05,
"loss": 0.6012,
"step": 1960
},
{
"epoch": 6.15,
"learning_rate": 1.9247648902821315e-05,
"loss": 0.2758,
"step": 1962
},
{
"epoch": 6.16,
"learning_rate": 1.9216300940438873e-05,
"loss": 0.0415,
"step": 1964
},
{
"epoch": 6.16,
"learning_rate": 1.9184952978056427e-05,
"loss": 0.1377,
"step": 1966
},
{
"epoch": 6.17,
"learning_rate": 1.915360501567398e-05,
"loss": 0.0566,
"step": 1968
},
{
"epoch": 6.18,
"learning_rate": 1.9122257053291536e-05,
"loss": 0.0282,
"step": 1970
},
{
"epoch": 6.18,
"learning_rate": 1.9090909090909094e-05,
"loss": 0.3328,
"step": 1972
},
{
"epoch": 6.19,
"learning_rate": 1.9059561128526644e-05,
"loss": 0.097,
"step": 1974
},
{
"epoch": 6.19,
"learning_rate": 1.9028213166144202e-05,
"loss": 0.0187,
"step": 1976
},
{
"epoch": 6.2,
"learning_rate": 1.8996865203761756e-05,
"loss": 0.0267,
"step": 1978
},
{
"epoch": 6.21,
"learning_rate": 1.896551724137931e-05,
"loss": 0.0944,
"step": 1980
},
{
"epoch": 6.21,
"learning_rate": 1.8934169278996865e-05,
"loss": 0.0204,
"step": 1982
},
{
"epoch": 6.22,
"learning_rate": 1.8902821316614423e-05,
"loss": 0.291,
"step": 1984
},
{
"epoch": 6.23,
"learning_rate": 1.8871473354231974e-05,
"loss": 0.1156,
"step": 1986
},
{
"epoch": 6.23,
"learning_rate": 1.884012539184953e-05,
"loss": 0.093,
"step": 1988
},
{
"epoch": 6.24,
"learning_rate": 1.8808777429467086e-05,
"loss": 0.4966,
"step": 1990
},
{
"epoch": 6.24,
"learning_rate": 1.877742946708464e-05,
"loss": 0.2578,
"step": 1992
},
{
"epoch": 6.25,
"learning_rate": 1.8746081504702194e-05,
"loss": 0.113,
"step": 1994
},
{
"epoch": 6.26,
"learning_rate": 1.8714733542319752e-05,
"loss": 0.0566,
"step": 1996
},
{
"epoch": 6.26,
"learning_rate": 1.8683385579937303e-05,
"loss": 0.0978,
"step": 1998
},
{
"epoch": 6.27,
"learning_rate": 1.865203761755486e-05,
"loss": 0.1104,
"step": 2000
},
{
"epoch": 6.28,
"learning_rate": 1.8620689655172415e-05,
"loss": 0.2492,
"step": 2002
},
{
"epoch": 6.28,
"learning_rate": 1.858934169278997e-05,
"loss": 0.2796,
"step": 2004
},
{
"epoch": 6.29,
"learning_rate": 1.8557993730407524e-05,
"loss": 0.0134,
"step": 2006
},
{
"epoch": 6.29,
"learning_rate": 1.852664576802508e-05,
"loss": 0.0916,
"step": 2008
},
{
"epoch": 6.3,
"learning_rate": 1.8495297805642632e-05,
"loss": 0.1723,
"step": 2010
},
{
"epoch": 6.31,
"learning_rate": 1.846394984326019e-05,
"loss": 0.0635,
"step": 2012
},
{
"epoch": 6.31,
"learning_rate": 1.8432601880877744e-05,
"loss": 0.054,
"step": 2014
},
{
"epoch": 6.32,
"learning_rate": 1.84012539184953e-05,
"loss": 0.2052,
"step": 2016
},
{
"epoch": 6.33,
"learning_rate": 1.8369905956112853e-05,
"loss": 0.4444,
"step": 2018
},
{
"epoch": 6.33,
"learning_rate": 1.833855799373041e-05,
"loss": 0.466,
"step": 2020
},
{
"epoch": 6.34,
"learning_rate": 1.830721003134796e-05,
"loss": 0.1776,
"step": 2022
},
{
"epoch": 6.34,
"learning_rate": 1.827586206896552e-05,
"loss": 0.4567,
"step": 2024
},
{
"epoch": 6.35,
"learning_rate": 1.8244514106583073e-05,
"loss": 0.5138,
"step": 2026
},
{
"epoch": 6.36,
"learning_rate": 1.8213166144200628e-05,
"loss": 0.1979,
"step": 2028
},
{
"epoch": 6.36,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.065,
"step": 2030
},
{
"epoch": 6.37,
"learning_rate": 1.8150470219435736e-05,
"loss": 0.1527,
"step": 2032
},
{
"epoch": 6.38,
"learning_rate": 1.811912225705329e-05,
"loss": 0.2589,
"step": 2034
},
{
"epoch": 6.38,
"learning_rate": 1.808777429467085e-05,
"loss": 0.0881,
"step": 2036
},
{
"epoch": 6.39,
"learning_rate": 1.80564263322884e-05,
"loss": 0.201,
"step": 2038
},
{
"epoch": 6.39,
"learning_rate": 1.8025078369905957e-05,
"loss": 0.1377,
"step": 2040
},
{
"epoch": 6.4,
"learning_rate": 1.799373040752351e-05,
"loss": 0.0685,
"step": 2042
},
{
"epoch": 6.41,
"learning_rate": 1.7962382445141066e-05,
"loss": 0.091,
"step": 2044
},
{
"epoch": 6.41,
"learning_rate": 1.793103448275862e-05,
"loss": 0.0452,
"step": 2046
},
{
"epoch": 6.42,
"learning_rate": 1.7899686520376178e-05,
"loss": 0.0162,
"step": 2048
},
{
"epoch": 6.43,
"learning_rate": 1.786833855799373e-05,
"loss": 0.2791,
"step": 2050
},
{
"epoch": 6.43,
"learning_rate": 1.7836990595611286e-05,
"loss": 0.1512,
"step": 2052
},
{
"epoch": 6.44,
"learning_rate": 1.780564263322884e-05,
"loss": 0.2821,
"step": 2054
},
{
"epoch": 6.45,
"learning_rate": 1.7774294670846395e-05,
"loss": 0.023,
"step": 2056
},
{
"epoch": 6.45,
"learning_rate": 1.774294670846395e-05,
"loss": 0.1239,
"step": 2058
},
{
"epoch": 6.46,
"learning_rate": 1.7711598746081507e-05,
"loss": 0.2945,
"step": 2060
},
{
"epoch": 6.46,
"learning_rate": 1.7680250783699058e-05,
"loss": 0.2291,
"step": 2062
},
{
"epoch": 6.47,
"learning_rate": 1.7648902821316615e-05,
"loss": 0.3298,
"step": 2064
},
{
"epoch": 6.48,
"learning_rate": 1.761755485893417e-05,
"loss": 0.0826,
"step": 2066
},
{
"epoch": 6.48,
"learning_rate": 1.7586206896551724e-05,
"loss": 0.3214,
"step": 2068
},
{
"epoch": 6.49,
"learning_rate": 1.755485893416928e-05,
"loss": 0.0856,
"step": 2070
},
{
"epoch": 6.5,
"learning_rate": 1.7523510971786836e-05,
"loss": 0.2695,
"step": 2072
},
{
"epoch": 6.5,
"learning_rate": 1.7492163009404387e-05,
"loss": 0.0738,
"step": 2074
},
{
"epoch": 6.51,
"learning_rate": 1.7460815047021945e-05,
"loss": 0.2538,
"step": 2076
},
{
"epoch": 6.51,
"learning_rate": 1.74294670846395e-05,
"loss": 0.0746,
"step": 2078
},
{
"epoch": 6.52,
"learning_rate": 1.7398119122257053e-05,
"loss": 0.0432,
"step": 2080
},
{
"epoch": 6.53,
"learning_rate": 1.7366771159874608e-05,
"loss": 0.0558,
"step": 2082
},
{
"epoch": 6.53,
"learning_rate": 1.7335423197492165e-05,
"loss": 0.0303,
"step": 2084
},
{
"epoch": 6.54,
"learning_rate": 1.7304075235109716e-05,
"loss": 0.0962,
"step": 2086
},
{
"epoch": 6.55,
"learning_rate": 1.7272727272727274e-05,
"loss": 0.1523,
"step": 2088
},
{
"epoch": 6.55,
"learning_rate": 1.7241379310344828e-05,
"loss": 0.0355,
"step": 2090
},
{
"epoch": 6.56,
"learning_rate": 1.7210031347962383e-05,
"loss": 0.0426,
"step": 2092
},
{
"epoch": 6.56,
"learning_rate": 1.7178683385579937e-05,
"loss": 0.0745,
"step": 2094
},
{
"epoch": 6.57,
"learning_rate": 1.7147335423197495e-05,
"loss": 0.0368,
"step": 2096
},
{
"epoch": 6.58,
"learning_rate": 1.7115987460815046e-05,
"loss": 0.2726,
"step": 2098
},
{
"epoch": 6.58,
"learning_rate": 1.7084639498432603e-05,
"loss": 0.1331,
"step": 2100
},
{
"epoch": 6.59,
"learning_rate": 1.7053291536050158e-05,
"loss": 0.085,
"step": 2102
},
{
"epoch": 6.6,
"learning_rate": 1.7021943573667712e-05,
"loss": 0.3728,
"step": 2104
},
{
"epoch": 6.6,
"learning_rate": 1.6990595611285266e-05,
"loss": 0.1302,
"step": 2106
},
{
"epoch": 6.61,
"learning_rate": 1.6959247648902824e-05,
"loss": 0.2245,
"step": 2108
},
{
"epoch": 6.61,
"learning_rate": 1.6927899686520378e-05,
"loss": 0.0219,
"step": 2110
},
{
"epoch": 6.62,
"learning_rate": 1.6896551724137932e-05,
"loss": 0.1656,
"step": 2112
},
{
"epoch": 6.63,
"learning_rate": 1.6865203761755487e-05,
"loss": 0.5374,
"step": 2114
},
{
"epoch": 6.63,
"learning_rate": 1.683385579937304e-05,
"loss": 0.0652,
"step": 2116
},
{
"epoch": 6.64,
"learning_rate": 1.6802507836990595e-05,
"loss": 0.1932,
"step": 2118
},
{
"epoch": 6.65,
"learning_rate": 1.677115987460815e-05,
"loss": 0.0171,
"step": 2120
},
{
"epoch": 6.65,
"learning_rate": 1.6739811912225707e-05,
"loss": 0.056,
"step": 2122
},
{
"epoch": 6.66,
"learning_rate": 1.6708463949843262e-05,
"loss": 0.1073,
"step": 2124
},
{
"epoch": 6.66,
"learning_rate": 1.6677115987460816e-05,
"loss": 0.1135,
"step": 2126
},
{
"epoch": 6.67,
"learning_rate": 1.664576802507837e-05,
"loss": 0.0908,
"step": 2128
},
{
"epoch": 6.68,
"learning_rate": 1.6614420062695925e-05,
"loss": 0.2566,
"step": 2130
},
{
"epoch": 6.68,
"learning_rate": 1.658307210031348e-05,
"loss": 0.4259,
"step": 2132
},
{
"epoch": 6.69,
"learning_rate": 1.6551724137931037e-05,
"loss": 0.1894,
"step": 2134
},
{
"epoch": 6.7,
"learning_rate": 1.652037617554859e-05,
"loss": 0.0222,
"step": 2136
},
{
"epoch": 6.7,
"learning_rate": 1.6489028213166145e-05,
"loss": 0.6408,
"step": 2138
},
{
"epoch": 6.71,
"learning_rate": 1.64576802507837e-05,
"loss": 0.1683,
"step": 2140
},
{
"epoch": 6.71,
"learning_rate": 1.6426332288401254e-05,
"loss": 0.1006,
"step": 2142
},
{
"epoch": 6.72,
"learning_rate": 1.6394984326018808e-05,
"loss": 0.0377,
"step": 2144
},
{
"epoch": 6.73,
"learning_rate": 1.6363636363636366e-05,
"loss": 0.7774,
"step": 2146
},
{
"epoch": 6.73,
"learning_rate": 1.633228840125392e-05,
"loss": 0.4139,
"step": 2148
},
{
"epoch": 6.74,
"learning_rate": 1.6300940438871475e-05,
"loss": 0.1705,
"step": 2150
},
{
"epoch": 6.75,
"learning_rate": 1.626959247648903e-05,
"loss": 0.1628,
"step": 2152
},
{
"epoch": 6.75,
"learning_rate": 1.6238244514106583e-05,
"loss": 0.077,
"step": 2154
},
{
"epoch": 6.76,
"learning_rate": 1.6206896551724137e-05,
"loss": 0.0139,
"step": 2156
},
{
"epoch": 6.76,
"learning_rate": 1.6175548589341695e-05,
"loss": 0.2951,
"step": 2158
},
{
"epoch": 6.77,
"learning_rate": 1.614420062695925e-05,
"loss": 0.1851,
"step": 2160
},
{
"epoch": 6.78,
"learning_rate": 1.6112852664576804e-05,
"loss": 0.0723,
"step": 2162
},
{
"epoch": 6.78,
"learning_rate": 1.6081504702194358e-05,
"loss": 0.2225,
"step": 2164
},
{
"epoch": 6.79,
"learning_rate": 1.6050156739811912e-05,
"loss": 0.7718,
"step": 2166
},
{
"epoch": 6.8,
"learning_rate": 1.6018808777429467e-05,
"loss": 0.1366,
"step": 2168
},
{
"epoch": 6.8,
"learning_rate": 1.5987460815047024e-05,
"loss": 0.1938,
"step": 2170
},
{
"epoch": 6.81,
"learning_rate": 1.595611285266458e-05,
"loss": 0.9167,
"step": 2172
},
{
"epoch": 6.82,
"learning_rate": 1.5924764890282133e-05,
"loss": 0.1728,
"step": 2174
},
{
"epoch": 6.82,
"learning_rate": 1.5893416927899687e-05,
"loss": 0.1459,
"step": 2176
},
{
"epoch": 6.83,
"learning_rate": 1.586206896551724e-05,
"loss": 0.2455,
"step": 2178
},
{
"epoch": 6.83,
"learning_rate": 1.5830721003134796e-05,
"loss": 0.1353,
"step": 2180
},
{
"epoch": 6.84,
"learning_rate": 1.5799373040752354e-05,
"loss": 0.6078,
"step": 2182
},
{
"epoch": 6.85,
"learning_rate": 1.5768025078369908e-05,
"loss": 0.1515,
"step": 2184
},
{
"epoch": 6.85,
"learning_rate": 1.5736677115987462e-05,
"loss": 0.0547,
"step": 2186
},
{
"epoch": 6.86,
"learning_rate": 1.5705329153605017e-05,
"loss": 0.4057,
"step": 2188
},
{
"epoch": 6.87,
"learning_rate": 1.5673981191222574e-05,
"loss": 0.3448,
"step": 2190
},
{
"epoch": 6.87,
"learning_rate": 1.5642633228840125e-05,
"loss": 0.1058,
"step": 2192
},
{
"epoch": 6.88,
"learning_rate": 1.5611285266457683e-05,
"loss": 0.3506,
"step": 2194
},
{
"epoch": 6.88,
"learning_rate": 1.5579937304075237e-05,
"loss": 0.0388,
"step": 2196
},
{
"epoch": 6.89,
"learning_rate": 1.554858934169279e-05,
"loss": 0.2267,
"step": 2198
},
{
"epoch": 6.9,
"learning_rate": 1.5517241379310346e-05,
"loss": 0.1389,
"step": 2200
},
{
"epoch": 6.9,
"learning_rate": 1.54858934169279e-05,
"loss": 0.0636,
"step": 2202
},
{
"epoch": 6.91,
"learning_rate": 1.5454545454545454e-05,
"loss": 0.0301,
"step": 2204
},
{
"epoch": 6.92,
"learning_rate": 1.5423197492163012e-05,
"loss": 0.3342,
"step": 2206
},
{
"epoch": 6.92,
"learning_rate": 1.5391849529780563e-05,
"loss": 0.0686,
"step": 2208
},
{
"epoch": 6.93,
"learning_rate": 1.536050156739812e-05,
"loss": 0.1338,
"step": 2210
},
{
"epoch": 6.93,
"learning_rate": 1.5329153605015675e-05,
"loss": 0.0855,
"step": 2212
},
{
"epoch": 6.94,
"learning_rate": 1.529780564263323e-05,
"loss": 0.192,
"step": 2214
},
{
"epoch": 6.95,
"learning_rate": 1.5266457680250784e-05,
"loss": 0.0585,
"step": 2216
},
{
"epoch": 6.95,
"learning_rate": 1.523510971786834e-05,
"loss": 0.0632,
"step": 2218
},
{
"epoch": 6.96,
"learning_rate": 1.5203761755485892e-05,
"loss": 0.0729,
"step": 2220
},
{
"epoch": 6.97,
"learning_rate": 1.5172413793103448e-05,
"loss": 0.1447,
"step": 2222
},
{
"epoch": 6.97,
"learning_rate": 1.5141065830721004e-05,
"loss": 0.2357,
"step": 2224
},
{
"epoch": 6.98,
"learning_rate": 1.5109717868338557e-05,
"loss": 0.2444,
"step": 2226
},
{
"epoch": 6.98,
"learning_rate": 1.5078369905956113e-05,
"loss": 0.1421,
"step": 2228
},
{
"epoch": 6.99,
"learning_rate": 1.5047021943573669e-05,
"loss": 0.0357,
"step": 2230
},
{
"epoch": 7.0,
"learning_rate": 1.5015673981191222e-05,
"loss": 0.1374,
"step": 2232
},
{
"epoch": 7.0,
"eval_bleu": 0.24644981466153415,
"eval_loss": 0.8383769989013672,
"eval_runtime": 75.2008,
"eval_samples_per_second": 4.282,
"eval_steps_per_second": 1.077,
"step": 2233
},
{
"epoch": 7.0,
"learning_rate": 1.4984326018808778e-05,
"loss": 0.0379,
"step": 2234
},
{
"epoch": 7.01,
"learning_rate": 1.4952978056426334e-05,
"loss": 0.2323,
"step": 2236
},
{
"epoch": 7.02,
"learning_rate": 1.4921630094043886e-05,
"loss": 0.1027,
"step": 2238
},
{
"epoch": 7.02,
"learning_rate": 1.4890282131661442e-05,
"loss": 0.0098,
"step": 2240
},
{
"epoch": 7.03,
"learning_rate": 1.4858934169278998e-05,
"loss": 0.1888,
"step": 2242
},
{
"epoch": 7.03,
"learning_rate": 1.482758620689655e-05,
"loss": 0.0321,
"step": 2244
},
{
"epoch": 7.04,
"learning_rate": 1.4796238244514107e-05,
"loss": 0.1494,
"step": 2246
},
{
"epoch": 7.05,
"learning_rate": 1.4764890282131663e-05,
"loss": 0.0946,
"step": 2248
},
{
"epoch": 7.05,
"learning_rate": 1.4733542319749215e-05,
"loss": 0.0561,
"step": 2250
},
{
"epoch": 7.06,
"learning_rate": 1.4702194357366771e-05,
"loss": 0.0507,
"step": 2252
},
{
"epoch": 7.07,
"learning_rate": 1.4670846394984327e-05,
"loss": 0.2675,
"step": 2254
},
{
"epoch": 7.07,
"learning_rate": 1.463949843260188e-05,
"loss": 0.0247,
"step": 2256
},
{
"epoch": 7.08,
"learning_rate": 1.4608150470219436e-05,
"loss": 0.1561,
"step": 2258
},
{
"epoch": 7.08,
"learning_rate": 1.4576802507836992e-05,
"loss": 0.0234,
"step": 2260
},
{
"epoch": 7.09,
"learning_rate": 1.4545454545454545e-05,
"loss": 0.0967,
"step": 2262
},
{
"epoch": 7.1,
"learning_rate": 1.45141065830721e-05,
"loss": 0.0608,
"step": 2264
},
{
"epoch": 7.1,
"learning_rate": 1.4482758620689657e-05,
"loss": 0.0862,
"step": 2266
},
{
"epoch": 7.11,
"learning_rate": 1.445141065830721e-05,
"loss": 0.106,
"step": 2268
},
{
"epoch": 7.12,
"learning_rate": 1.4420062695924765e-05,
"loss": 0.1607,
"step": 2270
},
{
"epoch": 7.12,
"learning_rate": 1.4388714733542321e-05,
"loss": 0.1719,
"step": 2272
},
{
"epoch": 7.13,
"learning_rate": 1.4357366771159874e-05,
"loss": 0.0395,
"step": 2274
},
{
"epoch": 7.13,
"learning_rate": 1.432601880877743e-05,
"loss": 0.1354,
"step": 2276
},
{
"epoch": 7.14,
"learning_rate": 1.4294670846394986e-05,
"loss": 0.1448,
"step": 2278
},
{
"epoch": 7.15,
"learning_rate": 1.4263322884012539e-05,
"loss": 0.0248,
"step": 2280
},
{
"epoch": 7.15,
"learning_rate": 1.4231974921630095e-05,
"loss": 0.0896,
"step": 2282
},
{
"epoch": 7.16,
"learning_rate": 1.420062695924765e-05,
"loss": 0.1104,
"step": 2284
},
{
"epoch": 7.17,
"learning_rate": 1.4169278996865205e-05,
"loss": 0.0603,
"step": 2286
},
{
"epoch": 7.17,
"learning_rate": 1.4137931034482759e-05,
"loss": 0.0674,
"step": 2288
},
{
"epoch": 7.18,
"learning_rate": 1.4106583072100313e-05,
"loss": 0.0872,
"step": 2290
},
{
"epoch": 7.18,
"learning_rate": 1.407523510971787e-05,
"loss": 0.0838,
"step": 2292
},
{
"epoch": 7.19,
"learning_rate": 1.4043887147335424e-05,
"loss": 0.0341,
"step": 2294
},
{
"epoch": 7.2,
"learning_rate": 1.4012539184952978e-05,
"loss": 0.5187,
"step": 2296
},
{
"epoch": 7.2,
"learning_rate": 1.3981191222570534e-05,
"loss": 0.0174,
"step": 2298
},
{
"epoch": 7.21,
"learning_rate": 1.3949843260188088e-05,
"loss": 0.193,
"step": 2300
},
{
"epoch": 7.22,
"learning_rate": 1.3918495297805643e-05,
"loss": 0.2255,
"step": 2302
},
{
"epoch": 7.22,
"learning_rate": 1.3887147335423199e-05,
"loss": 0.9768,
"step": 2304
},
{
"epoch": 7.23,
"learning_rate": 1.3855799373040753e-05,
"loss": 0.0174,
"step": 2306
},
{
"epoch": 7.24,
"learning_rate": 1.3824451410658307e-05,
"loss": 0.0791,
"step": 2308
},
{
"epoch": 7.24,
"learning_rate": 1.3793103448275863e-05,
"loss": 0.1198,
"step": 2310
},
{
"epoch": 7.25,
"learning_rate": 1.3761755485893418e-05,
"loss": 0.3075,
"step": 2312
},
{
"epoch": 7.25,
"learning_rate": 1.3730407523510972e-05,
"loss": 0.029,
"step": 2314
},
{
"epoch": 7.26,
"learning_rate": 1.3699059561128528e-05,
"loss": 0.0898,
"step": 2316
},
{
"epoch": 7.27,
"learning_rate": 1.3667711598746082e-05,
"loss": 0.4643,
"step": 2318
},
{
"epoch": 7.27,
"learning_rate": 1.3636363636363637e-05,
"loss": 0.1251,
"step": 2320
},
{
"epoch": 7.28,
"learning_rate": 1.3605015673981193e-05,
"loss": 0.1889,
"step": 2322
},
{
"epoch": 7.29,
"learning_rate": 1.3573667711598747e-05,
"loss": 0.2009,
"step": 2324
},
{
"epoch": 7.29,
"learning_rate": 1.3542319749216301e-05,
"loss": 0.0354,
"step": 2326
},
{
"epoch": 7.3,
"learning_rate": 1.3510971786833857e-05,
"loss": 0.0464,
"step": 2328
},
{
"epoch": 7.3,
"learning_rate": 1.3479623824451411e-05,
"loss": 0.0486,
"step": 2330
},
{
"epoch": 7.31,
"learning_rate": 1.3448275862068966e-05,
"loss": 0.044,
"step": 2332
},
{
"epoch": 7.32,
"learning_rate": 1.3416927899686522e-05,
"loss": 0.0158,
"step": 2334
},
{
"epoch": 7.32,
"learning_rate": 1.3385579937304076e-05,
"loss": 0.1485,
"step": 2336
},
{
"epoch": 7.33,
"learning_rate": 1.335423197492163e-05,
"loss": 0.0245,
"step": 2338
},
{
"epoch": 7.34,
"learning_rate": 1.3322884012539186e-05,
"loss": 0.16,
"step": 2340
},
{
"epoch": 7.34,
"learning_rate": 1.329153605015674e-05,
"loss": 0.2687,
"step": 2342
},
{
"epoch": 7.35,
"learning_rate": 1.3260188087774295e-05,
"loss": 0.1404,
"step": 2344
},
{
"epoch": 7.35,
"learning_rate": 1.3228840125391851e-05,
"loss": 0.1259,
"step": 2346
},
{
"epoch": 7.36,
"learning_rate": 1.3197492163009405e-05,
"loss": 0.1368,
"step": 2348
},
{
"epoch": 7.37,
"learning_rate": 1.316614420062696e-05,
"loss": 0.0172,
"step": 2350
},
{
"epoch": 7.37,
"learning_rate": 1.3134796238244516e-05,
"loss": 0.0425,
"step": 2352
},
{
"epoch": 7.38,
"learning_rate": 1.310344827586207e-05,
"loss": 0.5538,
"step": 2354
},
{
"epoch": 7.39,
"learning_rate": 1.3072100313479624e-05,
"loss": 0.0253,
"step": 2356
},
{
"epoch": 7.39,
"learning_rate": 1.304075235109718e-05,
"loss": 0.0093,
"step": 2358
},
{
"epoch": 7.4,
"learning_rate": 1.3009404388714735e-05,
"loss": 0.1181,
"step": 2360
},
{
"epoch": 7.4,
"learning_rate": 1.2978056426332289e-05,
"loss": 0.1287,
"step": 2362
},
{
"epoch": 7.41,
"learning_rate": 1.2946708463949845e-05,
"loss": 0.2848,
"step": 2364
},
{
"epoch": 7.42,
"learning_rate": 1.2915360501567401e-05,
"loss": 0.2026,
"step": 2366
},
{
"epoch": 7.42,
"learning_rate": 1.2884012539184954e-05,
"loss": 0.0273,
"step": 2368
},
{
"epoch": 7.43,
"learning_rate": 1.285266457680251e-05,
"loss": 0.242,
"step": 2370
},
{
"epoch": 7.44,
"learning_rate": 1.2821316614420062e-05,
"loss": 0.0237,
"step": 2372
},
{
"epoch": 7.44,
"learning_rate": 1.2789968652037618e-05,
"loss": 0.0859,
"step": 2374
},
{
"epoch": 7.45,
"learning_rate": 1.2758620689655174e-05,
"loss": 0.0282,
"step": 2376
},
{
"epoch": 7.45,
"learning_rate": 1.2727272727272727e-05,
"loss": 0.0694,
"step": 2378
},
{
"epoch": 7.46,
"learning_rate": 1.2695924764890283e-05,
"loss": 0.4857,
"step": 2380
},
{
"epoch": 7.47,
"learning_rate": 1.2664576802507839e-05,
"loss": 0.246,
"step": 2382
},
{
"epoch": 7.47,
"learning_rate": 1.2633228840125391e-05,
"loss": 0.247,
"step": 2384
},
{
"epoch": 7.48,
"learning_rate": 1.2601880877742947e-05,
"loss": 0.4204,
"step": 2386
},
{
"epoch": 7.49,
"learning_rate": 1.2570532915360503e-05,
"loss": 0.3749,
"step": 2388
},
{
"epoch": 7.49,
"learning_rate": 1.2539184952978056e-05,
"loss": 0.1052,
"step": 2390
},
{
"epoch": 7.5,
"learning_rate": 1.2507836990595612e-05,
"loss": 0.0413,
"step": 2392
},
{
"epoch": 7.5,
"learning_rate": 1.2476489028213166e-05,
"loss": 0.078,
"step": 2394
},
{
"epoch": 7.51,
"learning_rate": 1.2445141065830722e-05,
"loss": 0.137,
"step": 2396
},
{
"epoch": 7.52,
"learning_rate": 1.2413793103448277e-05,
"loss": 0.0713,
"step": 2398
},
{
"epoch": 7.52,
"learning_rate": 1.2382445141065831e-05,
"loss": 0.3123,
"step": 2400
},
{
"epoch": 7.53,
"learning_rate": 1.2351097178683387e-05,
"loss": 0.0858,
"step": 2402
},
{
"epoch": 7.54,
"learning_rate": 1.2319749216300941e-05,
"loss": 0.0449,
"step": 2404
},
{
"epoch": 7.54,
"learning_rate": 1.2288401253918496e-05,
"loss": 0.3001,
"step": 2406
},
{
"epoch": 7.55,
"learning_rate": 1.2257053291536052e-05,
"loss": 0.2863,
"step": 2408
},
{
"epoch": 7.55,
"learning_rate": 1.2225705329153606e-05,
"loss": 0.0359,
"step": 2410
},
{
"epoch": 7.56,
"learning_rate": 1.219435736677116e-05,
"loss": 0.056,
"step": 2412
},
{
"epoch": 7.57,
"learning_rate": 1.2163009404388716e-05,
"loss": 0.3254,
"step": 2414
},
{
"epoch": 7.57,
"learning_rate": 1.213166144200627e-05,
"loss": 0.2419,
"step": 2416
},
{
"epoch": 7.58,
"learning_rate": 1.2100313479623825e-05,
"loss": 0.1454,
"step": 2418
},
{
"epoch": 7.59,
"learning_rate": 1.206896551724138e-05,
"loss": 0.0976,
"step": 2420
},
{
"epoch": 7.59,
"learning_rate": 1.2037617554858935e-05,
"loss": 0.0717,
"step": 2422
},
{
"epoch": 7.6,
"learning_rate": 1.200626959247649e-05,
"loss": 0.0459,
"step": 2424
},
{
"epoch": 7.61,
"learning_rate": 1.1974921630094045e-05,
"loss": 0.0737,
"step": 2426
},
{
"epoch": 7.61,
"learning_rate": 1.19435736677116e-05,
"loss": 0.1952,
"step": 2428
},
{
"epoch": 7.62,
"learning_rate": 1.1912225705329154e-05,
"loss": 0.1624,
"step": 2430
},
{
"epoch": 7.62,
"learning_rate": 1.188087774294671e-05,
"loss": 0.0889,
"step": 2432
},
{
"epoch": 7.63,
"learning_rate": 1.1849529780564264e-05,
"loss": 0.1397,
"step": 2434
},
{
"epoch": 7.64,
"learning_rate": 1.1818181818181819e-05,
"loss": 0.1465,
"step": 2436
},
{
"epoch": 7.64,
"learning_rate": 1.1786833855799373e-05,
"loss": 0.2865,
"step": 2438
},
{
"epoch": 7.65,
"learning_rate": 1.1755485893416929e-05,
"loss": 0.1885,
"step": 2440
},
{
"epoch": 7.66,
"learning_rate": 1.1724137931034483e-05,
"loss": 0.2347,
"step": 2442
},
{
"epoch": 7.66,
"learning_rate": 1.1692789968652038e-05,
"loss": 0.1205,
"step": 2444
},
{
"epoch": 7.67,
"learning_rate": 1.1661442006269594e-05,
"loss": 0.5764,
"step": 2446
},
{
"epoch": 7.67,
"learning_rate": 1.1630094043887148e-05,
"loss": 0.0105,
"step": 2448
},
{
"epoch": 7.68,
"learning_rate": 1.1598746081504702e-05,
"loss": 0.0425,
"step": 2450
},
{
"epoch": 7.69,
"learning_rate": 1.1567398119122258e-05,
"loss": 0.1366,
"step": 2452
},
{
"epoch": 7.69,
"learning_rate": 1.1536050156739813e-05,
"loss": 0.0739,
"step": 2454
},
{
"epoch": 7.7,
"learning_rate": 1.1504702194357367e-05,
"loss": 0.0658,
"step": 2456
},
{
"epoch": 7.71,
"learning_rate": 1.1473354231974923e-05,
"loss": 0.4401,
"step": 2458
},
{
"epoch": 7.71,
"learning_rate": 1.1442006269592477e-05,
"loss": 0.2505,
"step": 2460
},
{
"epoch": 7.72,
"learning_rate": 1.1410658307210031e-05,
"loss": 0.0542,
"step": 2462
},
{
"epoch": 7.72,
"learning_rate": 1.1379310344827587e-05,
"loss": 0.0149,
"step": 2464
},
{
"epoch": 7.73,
"learning_rate": 1.1347962382445142e-05,
"loss": 0.0453,
"step": 2466
},
{
"epoch": 7.74,
"learning_rate": 1.1316614420062696e-05,
"loss": 0.0549,
"step": 2468
},
{
"epoch": 7.74,
"learning_rate": 1.1285266457680252e-05,
"loss": 0.0744,
"step": 2470
},
{
"epoch": 7.75,
"learning_rate": 1.1253918495297806e-05,
"loss": 0.1326,
"step": 2472
},
{
"epoch": 7.76,
"learning_rate": 1.122257053291536e-05,
"loss": 0.0853,
"step": 2474
},
{
"epoch": 7.76,
"learning_rate": 1.1191222570532917e-05,
"loss": 0.0393,
"step": 2476
},
{
"epoch": 7.77,
"learning_rate": 1.1159874608150471e-05,
"loss": 0.3383,
"step": 2478
},
{
"epoch": 7.77,
"learning_rate": 1.1128526645768025e-05,
"loss": 0.2691,
"step": 2480
},
{
"epoch": 7.78,
"learning_rate": 1.109717868338558e-05,
"loss": 0.2155,
"step": 2482
},
{
"epoch": 7.79,
"learning_rate": 1.1065830721003136e-05,
"loss": 0.106,
"step": 2484
},
{
"epoch": 7.79,
"learning_rate": 1.103448275862069e-05,
"loss": 0.0392,
"step": 2486
},
{
"epoch": 7.8,
"learning_rate": 1.1003134796238244e-05,
"loss": 0.0198,
"step": 2488
},
{
"epoch": 7.81,
"learning_rate": 1.09717868338558e-05,
"loss": 0.3101,
"step": 2490
},
{
"epoch": 7.81,
"learning_rate": 1.0940438871473355e-05,
"loss": 0.0062,
"step": 2492
},
{
"epoch": 7.82,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.0064,
"step": 2494
},
{
"epoch": 7.82,
"learning_rate": 1.0877742946708465e-05,
"loss": 0.263,
"step": 2496
},
{
"epoch": 7.83,
"learning_rate": 1.084639498432602e-05,
"loss": 0.5857,
"step": 2498
},
{
"epoch": 7.84,
"learning_rate": 1.0815047021943574e-05,
"loss": 0.3092,
"step": 2500
},
{
"epoch": 7.84,
"learning_rate": 1.078369905956113e-05,
"loss": 0.3466,
"step": 2502
},
{
"epoch": 7.85,
"learning_rate": 1.0752351097178684e-05,
"loss": 0.0788,
"step": 2504
},
{
"epoch": 7.86,
"learning_rate": 1.0721003134796238e-05,
"loss": 0.2137,
"step": 2506
},
{
"epoch": 7.86,
"learning_rate": 1.0689655172413794e-05,
"loss": 0.192,
"step": 2508
},
{
"epoch": 7.87,
"learning_rate": 1.0658307210031348e-05,
"loss": 0.0373,
"step": 2510
},
{
"epoch": 7.87,
"learning_rate": 1.0626959247648903e-05,
"loss": 0.0247,
"step": 2512
},
{
"epoch": 7.88,
"learning_rate": 1.0595611285266459e-05,
"loss": 0.0209,
"step": 2514
},
{
"epoch": 7.89,
"learning_rate": 1.0564263322884013e-05,
"loss": 0.0277,
"step": 2516
},
{
"epoch": 7.89,
"learning_rate": 1.0532915360501567e-05,
"loss": 0.0101,
"step": 2518
},
{
"epoch": 7.9,
"learning_rate": 1.0501567398119123e-05,
"loss": 0.1634,
"step": 2520
},
{
"epoch": 7.91,
"learning_rate": 1.0470219435736678e-05,
"loss": 0.1656,
"step": 2522
},
{
"epoch": 7.91,
"learning_rate": 1.0438871473354232e-05,
"loss": 0.3494,
"step": 2524
},
{
"epoch": 7.92,
"learning_rate": 1.0407523510971786e-05,
"loss": 0.0274,
"step": 2526
},
{
"epoch": 7.92,
"learning_rate": 1.0376175548589342e-05,
"loss": 0.3793,
"step": 2528
},
{
"epoch": 7.93,
"learning_rate": 1.0344827586206897e-05,
"loss": 0.0542,
"step": 2530
},
{
"epoch": 7.94,
"learning_rate": 1.0313479623824451e-05,
"loss": 0.0107,
"step": 2532
},
{
"epoch": 7.94,
"learning_rate": 1.0282131661442007e-05,
"loss": 0.0499,
"step": 2534
},
{
"epoch": 7.95,
"learning_rate": 1.0250783699059561e-05,
"loss": 0.1235,
"step": 2536
},
{
"epoch": 7.96,
"learning_rate": 1.0219435736677116e-05,
"loss": 0.3413,
"step": 2538
},
{
"epoch": 7.96,
"learning_rate": 1.0188087774294672e-05,
"loss": 0.4199,
"step": 2540
},
{
"epoch": 7.97,
"learning_rate": 1.0156739811912226e-05,
"loss": 0.0375,
"step": 2542
},
{
"epoch": 7.97,
"learning_rate": 1.012539184952978e-05,
"loss": 0.0116,
"step": 2544
},
{
"epoch": 7.98,
"learning_rate": 1.0094043887147336e-05,
"loss": 0.0703,
"step": 2546
},
{
"epoch": 7.99,
"learning_rate": 1.006269592476489e-05,
"loss": 0.4828,
"step": 2548
},
{
"epoch": 7.99,
"learning_rate": 1.0031347962382445e-05,
"loss": 0.1091,
"step": 2550
},
{
"epoch": 8.0,
"learning_rate": 1e-05,
"loss": 0.2584,
"step": 2552
},
{
"epoch": 8.0,
"eval_bleu": 0.24766209564477684,
"eval_loss": 0.868782639503479,
"eval_runtime": 76.7494,
"eval_samples_per_second": 4.195,
"eval_steps_per_second": 1.055,
"step": 2552
}
],
"max_steps": 3190,
"num_train_epochs": 10,
"total_flos": 2.3300870872080384e+16,
"trial_name": null,
"trial_params": null
}