codeart-26m-ti-O1 / trainer_state.json
sheepy928's picture
Upload 11 files
5d1fe6d verified
{
"best_metric": 0.9480086057353725,
"best_model_checkpoint": "../save/marinda-default-ep0.4-26m-ti-dbgonly-O1-shuffle/checkpoint-800",
"epoch": 4.3478260869565215,
"global_step": 800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 9.978260869565218e-05,
"loss": 3.7941,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 9.956521739130435e-05,
"loss": 3.3761,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 9.934782608695653e-05,
"loss": 2.6042,
"step": 6
},
{
"epoch": 0.04,
"learning_rate": 9.91304347826087e-05,
"loss": 1.3506,
"step": 8
},
{
"epoch": 0.05,
"learning_rate": 9.891304347826087e-05,
"loss": 0.6191,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 9.869565217391305e-05,
"loss": 0.4785,
"step": 12
},
{
"epoch": 0.08,
"learning_rate": 9.847826086956522e-05,
"loss": 0.4405,
"step": 14
},
{
"epoch": 0.09,
"learning_rate": 9.82608695652174e-05,
"loss": 0.3909,
"step": 16
},
{
"epoch": 0.1,
"learning_rate": 9.804347826086957e-05,
"loss": 0.3607,
"step": 18
},
{
"epoch": 0.11,
"learning_rate": 9.782608695652174e-05,
"loss": 0.3224,
"step": 20
},
{
"epoch": 0.12,
"learning_rate": 9.760869565217392e-05,
"loss": 0.3123,
"step": 22
},
{
"epoch": 0.13,
"learning_rate": 9.739130434782609e-05,
"loss": 0.3061,
"step": 24
},
{
"epoch": 0.14,
"learning_rate": 9.717391304347827e-05,
"loss": 0.2739,
"step": 26
},
{
"epoch": 0.15,
"learning_rate": 9.695652173913044e-05,
"loss": 0.266,
"step": 28
},
{
"epoch": 0.16,
"learning_rate": 9.673913043478261e-05,
"loss": 0.246,
"step": 30
},
{
"epoch": 0.17,
"learning_rate": 9.652173913043479e-05,
"loss": 0.2488,
"step": 32
},
{
"epoch": 0.18,
"learning_rate": 9.630434782608696e-05,
"loss": 0.233,
"step": 34
},
{
"epoch": 0.2,
"learning_rate": 9.608695652173914e-05,
"loss": 0.1973,
"step": 36
},
{
"epoch": 0.21,
"learning_rate": 9.586956521739131e-05,
"loss": 0.1989,
"step": 38
},
{
"epoch": 0.22,
"learning_rate": 9.565217391304348e-05,
"loss": 0.2195,
"step": 40
},
{
"epoch": 0.23,
"learning_rate": 9.543478260869566e-05,
"loss": 0.1891,
"step": 42
},
{
"epoch": 0.24,
"learning_rate": 9.521739130434783e-05,
"loss": 0.1964,
"step": 44
},
{
"epoch": 0.25,
"learning_rate": 9.5e-05,
"loss": 0.1911,
"step": 46
},
{
"epoch": 0.26,
"learning_rate": 9.478260869565218e-05,
"loss": 0.1747,
"step": 48
},
{
"epoch": 0.27,
"learning_rate": 9.456521739130435e-05,
"loss": 0.1626,
"step": 50
},
{
"epoch": 0.27,
"eval_f1": 0.3964671547979424,
"eval_loss": 0.1601678729057312,
"eval_precision": 0.4276477142864008,
"eval_recall": 0.36953310617845153,
"eval_runtime": 13.7757,
"eval_samples_per_second": 134.73,
"eval_steps_per_second": 0.581,
"step": 50
},
{
"epoch": 0.28,
"learning_rate": 9.434782608695653e-05,
"loss": 0.1717,
"step": 52
},
{
"epoch": 0.29,
"learning_rate": 9.41304347826087e-05,
"loss": 0.1846,
"step": 54
},
{
"epoch": 0.3,
"learning_rate": 9.391304347826087e-05,
"loss": 0.1602,
"step": 56
},
{
"epoch": 0.32,
"learning_rate": 9.369565217391305e-05,
"loss": 0.1815,
"step": 58
},
{
"epoch": 0.33,
"learning_rate": 9.347826086956522e-05,
"loss": 0.1604,
"step": 60
},
{
"epoch": 0.34,
"learning_rate": 9.32608695652174e-05,
"loss": 0.1519,
"step": 62
},
{
"epoch": 0.35,
"learning_rate": 9.304347826086957e-05,
"loss": 0.1486,
"step": 64
},
{
"epoch": 0.36,
"learning_rate": 9.282608695652174e-05,
"loss": 0.1454,
"step": 66
},
{
"epoch": 0.37,
"learning_rate": 9.260869565217392e-05,
"loss": 0.1415,
"step": 68
},
{
"epoch": 0.38,
"learning_rate": 9.239130434782609e-05,
"loss": 0.129,
"step": 70
},
{
"epoch": 0.39,
"learning_rate": 9.217391304347827e-05,
"loss": 0.1269,
"step": 72
},
{
"epoch": 0.4,
"learning_rate": 9.195652173913044e-05,
"loss": 0.1261,
"step": 74
},
{
"epoch": 0.41,
"learning_rate": 9.173913043478261e-05,
"loss": 0.1232,
"step": 76
},
{
"epoch": 0.42,
"learning_rate": 9.152173913043479e-05,
"loss": 0.1203,
"step": 78
},
{
"epoch": 0.43,
"learning_rate": 9.130434782608696e-05,
"loss": 0.1202,
"step": 80
},
{
"epoch": 0.45,
"learning_rate": 9.108695652173914e-05,
"loss": 0.1348,
"step": 82
},
{
"epoch": 0.46,
"learning_rate": 9.086956521739131e-05,
"loss": 0.1151,
"step": 84
},
{
"epoch": 0.47,
"learning_rate": 9.065217391304348e-05,
"loss": 0.1143,
"step": 86
},
{
"epoch": 0.48,
"learning_rate": 9.043478260869566e-05,
"loss": 0.1099,
"step": 88
},
{
"epoch": 0.49,
"learning_rate": 9.021739130434783e-05,
"loss": 0.1174,
"step": 90
},
{
"epoch": 0.5,
"learning_rate": 9e-05,
"loss": 0.1049,
"step": 92
},
{
"epoch": 0.51,
"learning_rate": 8.978260869565218e-05,
"loss": 0.0966,
"step": 94
},
{
"epoch": 0.52,
"learning_rate": 8.956521739130435e-05,
"loss": 0.1063,
"step": 96
},
{
"epoch": 0.53,
"learning_rate": 8.934782608695653e-05,
"loss": 0.1049,
"step": 98
},
{
"epoch": 0.54,
"learning_rate": 8.91304347826087e-05,
"loss": 0.1005,
"step": 100
},
{
"epoch": 0.54,
"eval_f1": 0.6856549592604718,
"eval_loss": 0.08935681730508804,
"eval_precision": 0.6768018013783773,
"eval_recall": 0.6947530661519793,
"eval_runtime": 14.0272,
"eval_samples_per_second": 132.314,
"eval_steps_per_second": 0.57,
"step": 100
},
{
"epoch": 0.55,
"learning_rate": 8.891304347826088e-05,
"loss": 0.1007,
"step": 102
},
{
"epoch": 0.57,
"learning_rate": 8.869565217391305e-05,
"loss": 0.0943,
"step": 104
},
{
"epoch": 0.58,
"learning_rate": 8.847826086956522e-05,
"loss": 0.0872,
"step": 106
},
{
"epoch": 0.59,
"learning_rate": 8.82608695652174e-05,
"loss": 0.0936,
"step": 108
},
{
"epoch": 0.6,
"learning_rate": 8.804347826086957e-05,
"loss": 0.0862,
"step": 110
},
{
"epoch": 0.61,
"learning_rate": 8.782608695652174e-05,
"loss": 0.0871,
"step": 112
},
{
"epoch": 0.62,
"learning_rate": 8.760869565217392e-05,
"loss": 0.0922,
"step": 114
},
{
"epoch": 0.63,
"learning_rate": 8.739130434782609e-05,
"loss": 0.0862,
"step": 116
},
{
"epoch": 0.64,
"learning_rate": 8.717391304347827e-05,
"loss": 0.0824,
"step": 118
},
{
"epoch": 0.65,
"learning_rate": 8.695652173913044e-05,
"loss": 0.0713,
"step": 120
},
{
"epoch": 0.66,
"learning_rate": 8.673913043478261e-05,
"loss": 0.0847,
"step": 122
},
{
"epoch": 0.67,
"learning_rate": 8.652173913043479e-05,
"loss": 0.0896,
"step": 124
},
{
"epoch": 0.68,
"learning_rate": 8.630434782608696e-05,
"loss": 0.0806,
"step": 126
},
{
"epoch": 0.7,
"learning_rate": 8.608695652173914e-05,
"loss": 0.0859,
"step": 128
},
{
"epoch": 0.71,
"learning_rate": 8.586956521739131e-05,
"loss": 0.0898,
"step": 130
},
{
"epoch": 0.72,
"learning_rate": 8.565217391304348e-05,
"loss": 0.0699,
"step": 132
},
{
"epoch": 0.73,
"learning_rate": 8.543478260869566e-05,
"loss": 0.0748,
"step": 134
},
{
"epoch": 0.74,
"learning_rate": 8.521739130434783e-05,
"loss": 0.0767,
"step": 136
},
{
"epoch": 0.75,
"learning_rate": 8.5e-05,
"loss": 0.0794,
"step": 138
},
{
"epoch": 0.76,
"learning_rate": 8.478260869565218e-05,
"loss": 0.0775,
"step": 140
},
{
"epoch": 0.77,
"learning_rate": 8.456521739130435e-05,
"loss": 0.0727,
"step": 142
},
{
"epoch": 0.78,
"learning_rate": 8.434782608695653e-05,
"loss": 0.0723,
"step": 144
},
{
"epoch": 0.79,
"learning_rate": 8.41304347826087e-05,
"loss": 0.0765,
"step": 146
},
{
"epoch": 0.8,
"learning_rate": 8.391304347826088e-05,
"loss": 0.0721,
"step": 148
},
{
"epoch": 0.82,
"learning_rate": 8.369565217391305e-05,
"loss": 0.0691,
"step": 150
},
{
"epoch": 0.82,
"eval_f1": 0.7960363629529713,
"eval_loss": 0.06118812412023544,
"eval_precision": 0.7864619236687798,
"eval_recall": 0.805857041419397,
"eval_runtime": 13.4485,
"eval_samples_per_second": 138.008,
"eval_steps_per_second": 0.595,
"step": 150
},
{
"epoch": 0.83,
"learning_rate": 8.347826086956521e-05,
"loss": 0.0603,
"step": 152
},
{
"epoch": 0.84,
"learning_rate": 8.32608695652174e-05,
"loss": 0.0689,
"step": 154
},
{
"epoch": 0.85,
"learning_rate": 8.304347826086957e-05,
"loss": 0.0703,
"step": 156
},
{
"epoch": 0.86,
"learning_rate": 8.282608695652175e-05,
"loss": 0.06,
"step": 158
},
{
"epoch": 0.87,
"learning_rate": 8.260869565217392e-05,
"loss": 0.0679,
"step": 160
},
{
"epoch": 0.88,
"learning_rate": 8.23913043478261e-05,
"loss": 0.0649,
"step": 162
},
{
"epoch": 0.89,
"learning_rate": 8.217391304347827e-05,
"loss": 0.0658,
"step": 164
},
{
"epoch": 0.9,
"learning_rate": 8.195652173913044e-05,
"loss": 0.062,
"step": 166
},
{
"epoch": 0.91,
"learning_rate": 8.173913043478262e-05,
"loss": 0.0676,
"step": 168
},
{
"epoch": 0.92,
"learning_rate": 8.152173913043478e-05,
"loss": 0.0577,
"step": 170
},
{
"epoch": 0.93,
"learning_rate": 8.130434782608696e-05,
"loss": 0.0659,
"step": 172
},
{
"epoch": 0.95,
"learning_rate": 8.108695652173914e-05,
"loss": 0.0555,
"step": 174
},
{
"epoch": 0.96,
"learning_rate": 8.086956521739131e-05,
"loss": 0.0581,
"step": 176
},
{
"epoch": 0.97,
"learning_rate": 8.065217391304348e-05,
"loss": 0.0509,
"step": 178
},
{
"epoch": 0.98,
"learning_rate": 8.043478260869566e-05,
"loss": 0.0651,
"step": 180
},
{
"epoch": 0.99,
"learning_rate": 8.021739130434783e-05,
"loss": 0.0618,
"step": 182
},
{
"epoch": 1.0,
"learning_rate": 8e-05,
"loss": 0.0583,
"step": 184
},
{
"epoch": 1.01,
"learning_rate": 7.978260869565217e-05,
"loss": 0.0548,
"step": 186
},
{
"epoch": 1.02,
"learning_rate": 7.956521739130434e-05,
"loss": 0.0541,
"step": 188
},
{
"epoch": 1.03,
"learning_rate": 7.934782608695653e-05,
"loss": 0.0568,
"step": 190
},
{
"epoch": 1.04,
"learning_rate": 7.91304347826087e-05,
"loss": 0.0516,
"step": 192
},
{
"epoch": 1.05,
"learning_rate": 7.891304347826088e-05,
"loss": 0.0547,
"step": 194
},
{
"epoch": 1.07,
"learning_rate": 7.869565217391305e-05,
"loss": 0.0472,
"step": 196
},
{
"epoch": 1.08,
"learning_rate": 7.847826086956522e-05,
"loss": 0.0474,
"step": 198
},
{
"epoch": 1.09,
"learning_rate": 7.82608695652174e-05,
"loss": 0.0529,
"step": 200
},
{
"epoch": 1.09,
"eval_f1": 0.855353337621845,
"eval_loss": 0.04639717563986778,
"eval_precision": 0.8488931050924142,
"eval_recall": 0.8619228046612788,
"eval_runtime": 13.5842,
"eval_samples_per_second": 136.629,
"eval_steps_per_second": 0.589,
"step": 200
},
{
"epoch": 1.1,
"learning_rate": 7.804347826086957e-05,
"loss": 0.0595,
"step": 202
},
{
"epoch": 1.11,
"learning_rate": 7.782608695652173e-05,
"loss": 0.0462,
"step": 204
},
{
"epoch": 1.12,
"learning_rate": 7.76086956521739e-05,
"loss": 0.0543,
"step": 206
},
{
"epoch": 1.13,
"learning_rate": 7.73913043478261e-05,
"loss": 0.0541,
"step": 208
},
{
"epoch": 1.14,
"learning_rate": 7.717391304347827e-05,
"loss": 0.0634,
"step": 210
},
{
"epoch": 1.15,
"learning_rate": 7.695652173913044e-05,
"loss": 0.0547,
"step": 212
},
{
"epoch": 1.16,
"learning_rate": 7.673913043478262e-05,
"loss": 0.0568,
"step": 214
},
{
"epoch": 1.17,
"learning_rate": 7.652173913043479e-05,
"loss": 0.0521,
"step": 216
},
{
"epoch": 1.18,
"learning_rate": 7.630434782608696e-05,
"loss": 0.0565,
"step": 218
},
{
"epoch": 1.2,
"learning_rate": 7.608695652173914e-05,
"loss": 0.048,
"step": 220
},
{
"epoch": 1.21,
"learning_rate": 7.58695652173913e-05,
"loss": 0.0467,
"step": 222
},
{
"epoch": 1.22,
"learning_rate": 7.565217391304347e-05,
"loss": 0.0522,
"step": 224
},
{
"epoch": 1.23,
"learning_rate": 7.543478260869566e-05,
"loss": 0.0504,
"step": 226
},
{
"epoch": 1.24,
"learning_rate": 7.521739130434783e-05,
"loss": 0.053,
"step": 228
},
{
"epoch": 1.25,
"learning_rate": 7.500000000000001e-05,
"loss": 0.0519,
"step": 230
},
{
"epoch": 1.26,
"learning_rate": 7.478260869565218e-05,
"loss": 0.0441,
"step": 232
},
{
"epoch": 1.27,
"learning_rate": 7.456521739130435e-05,
"loss": 0.0469,
"step": 234
},
{
"epoch": 1.28,
"learning_rate": 7.434782608695653e-05,
"loss": 0.0409,
"step": 236
},
{
"epoch": 1.29,
"learning_rate": 7.41304347826087e-05,
"loss": 0.0471,
"step": 238
},
{
"epoch": 1.3,
"learning_rate": 7.391304347826086e-05,
"loss": 0.0523,
"step": 240
},
{
"epoch": 1.32,
"learning_rate": 7.369565217391304e-05,
"loss": 0.0455,
"step": 242
},
{
"epoch": 1.33,
"learning_rate": 7.347826086956522e-05,
"loss": 0.0498,
"step": 244
},
{
"epoch": 1.34,
"learning_rate": 7.32608695652174e-05,
"loss": 0.0468,
"step": 246
},
{
"epoch": 1.35,
"learning_rate": 7.304347826086957e-05,
"loss": 0.0441,
"step": 248
},
{
"epoch": 1.36,
"learning_rate": 7.282608695652175e-05,
"loss": 0.0379,
"step": 250
},
{
"epoch": 1.36,
"eval_f1": 0.8870407621848339,
"eval_loss": 0.0366128571331501,
"eval_precision": 0.8915342193373116,
"eval_recall": 0.8826022728902433,
"eval_runtime": 13.3791,
"eval_samples_per_second": 138.724,
"eval_steps_per_second": 0.598,
"step": 250
},
{
"epoch": 1.37,
"learning_rate": 7.260869565217392e-05,
"loss": 0.0467,
"step": 252
},
{
"epoch": 1.38,
"learning_rate": 7.23913043478261e-05,
"loss": 0.0469,
"step": 254
},
{
"epoch": 1.39,
"learning_rate": 7.217391304347827e-05,
"loss": 0.0396,
"step": 256
},
{
"epoch": 1.4,
"learning_rate": 7.195652173913043e-05,
"loss": 0.0449,
"step": 258
},
{
"epoch": 1.41,
"learning_rate": 7.17391304347826e-05,
"loss": 0.0476,
"step": 260
},
{
"epoch": 1.42,
"learning_rate": 7.152173913043479e-05,
"loss": 0.0442,
"step": 262
},
{
"epoch": 1.43,
"learning_rate": 7.130434782608696e-05,
"loss": 0.0504,
"step": 264
},
{
"epoch": 1.45,
"learning_rate": 7.108695652173914e-05,
"loss": 0.0464,
"step": 266
},
{
"epoch": 1.46,
"learning_rate": 7.086956521739131e-05,
"loss": 0.0433,
"step": 268
},
{
"epoch": 1.47,
"learning_rate": 7.065217391304349e-05,
"loss": 0.0388,
"step": 270
},
{
"epoch": 1.48,
"learning_rate": 7.043478260869566e-05,
"loss": 0.0496,
"step": 272
},
{
"epoch": 1.49,
"learning_rate": 7.021739130434783e-05,
"loss": 0.0383,
"step": 274
},
{
"epoch": 1.5,
"learning_rate": 7e-05,
"loss": 0.032,
"step": 276
},
{
"epoch": 1.51,
"learning_rate": 6.978260869565217e-05,
"loss": 0.0368,
"step": 278
},
{
"epoch": 1.52,
"learning_rate": 6.956521739130436e-05,
"loss": 0.0427,
"step": 280
},
{
"epoch": 1.53,
"learning_rate": 6.934782608695653e-05,
"loss": 0.0399,
"step": 282
},
{
"epoch": 1.54,
"learning_rate": 6.91304347826087e-05,
"loss": 0.0409,
"step": 284
},
{
"epoch": 1.55,
"learning_rate": 6.891304347826088e-05,
"loss": 0.0428,
"step": 286
},
{
"epoch": 1.57,
"learning_rate": 6.869565217391305e-05,
"loss": 0.034,
"step": 288
},
{
"epoch": 1.58,
"learning_rate": 6.847826086956522e-05,
"loss": 0.0385,
"step": 290
},
{
"epoch": 1.59,
"learning_rate": 6.826086956521739e-05,
"loss": 0.0325,
"step": 292
},
{
"epoch": 1.6,
"learning_rate": 6.804347826086956e-05,
"loss": 0.041,
"step": 294
},
{
"epoch": 1.61,
"learning_rate": 6.782608695652173e-05,
"loss": 0.0352,
"step": 296
},
{
"epoch": 1.62,
"learning_rate": 6.760869565217392e-05,
"loss": 0.0459,
"step": 298
},
{
"epoch": 1.63,
"learning_rate": 6.73913043478261e-05,
"loss": 0.0336,
"step": 300
},
{
"epoch": 1.63,
"eval_f1": 0.9004441256217653,
"eval_loss": 0.03201919421553612,
"eval_precision": 0.9060996222486022,
"eval_recall": 0.8948686655353744,
"eval_runtime": 13.4043,
"eval_samples_per_second": 138.463,
"eval_steps_per_second": 0.597,
"step": 300
},
{
"epoch": 1.64,
"learning_rate": 6.717391304347827e-05,
"loss": 0.0463,
"step": 302
},
{
"epoch": 1.65,
"learning_rate": 6.695652173913044e-05,
"loss": 0.0369,
"step": 304
},
{
"epoch": 1.66,
"learning_rate": 6.673913043478262e-05,
"loss": 0.0374,
"step": 306
},
{
"epoch": 1.67,
"learning_rate": 6.652173913043479e-05,
"loss": 0.0407,
"step": 308
},
{
"epoch": 1.68,
"learning_rate": 6.630434782608695e-05,
"loss": 0.0375,
"step": 310
},
{
"epoch": 1.7,
"learning_rate": 6.608695652173912e-05,
"loss": 0.0326,
"step": 312
},
{
"epoch": 1.71,
"learning_rate": 6.58695652173913e-05,
"loss": 0.0434,
"step": 314
},
{
"epoch": 1.72,
"learning_rate": 6.565217391304349e-05,
"loss": 0.0352,
"step": 316
},
{
"epoch": 1.73,
"learning_rate": 6.543478260869566e-05,
"loss": 0.0374,
"step": 318
},
{
"epoch": 1.74,
"learning_rate": 6.521739130434783e-05,
"loss": 0.031,
"step": 320
},
{
"epoch": 1.75,
"learning_rate": 6.500000000000001e-05,
"loss": 0.0328,
"step": 322
},
{
"epoch": 1.76,
"learning_rate": 6.478260869565218e-05,
"loss": 0.0318,
"step": 324
},
{
"epoch": 1.77,
"learning_rate": 6.456521739130436e-05,
"loss": 0.0367,
"step": 326
},
{
"epoch": 1.78,
"learning_rate": 6.434782608695652e-05,
"loss": 0.0379,
"step": 328
},
{
"epoch": 1.79,
"learning_rate": 6.413043478260869e-05,
"loss": 0.0331,
"step": 330
},
{
"epoch": 1.8,
"learning_rate": 6.391304347826086e-05,
"loss": 0.0296,
"step": 332
},
{
"epoch": 1.82,
"learning_rate": 6.369565217391305e-05,
"loss": 0.0317,
"step": 334
},
{
"epoch": 1.83,
"learning_rate": 6.347826086956523e-05,
"loss": 0.0328,
"step": 336
},
{
"epoch": 1.84,
"learning_rate": 6.32608695652174e-05,
"loss": 0.0349,
"step": 338
},
{
"epoch": 1.85,
"learning_rate": 6.304347826086957e-05,
"loss": 0.0471,
"step": 340
},
{
"epoch": 1.86,
"learning_rate": 6.282608695652175e-05,
"loss": 0.0321,
"step": 342
},
{
"epoch": 1.87,
"learning_rate": 6.260869565217392e-05,
"loss": 0.0323,
"step": 344
},
{
"epoch": 1.88,
"learning_rate": 6.239130434782608e-05,
"loss": 0.0341,
"step": 346
},
{
"epoch": 1.89,
"learning_rate": 6.217391304347826e-05,
"loss": 0.0312,
"step": 348
},
{
"epoch": 1.9,
"learning_rate": 6.195652173913043e-05,
"loss": 0.032,
"step": 350
},
{
"epoch": 1.9,
"eval_f1": 0.9094130772705891,
"eval_loss": 0.028529103845357895,
"eval_precision": 0.9100321537556063,
"eval_recall": 0.9088048289070677,
"eval_runtime": 13.367,
"eval_samples_per_second": 138.849,
"eval_steps_per_second": 0.598,
"step": 350
},
{
"epoch": 1.91,
"learning_rate": 6.173913043478262e-05,
"loss": 0.0305,
"step": 352
},
{
"epoch": 1.92,
"learning_rate": 6.152173913043479e-05,
"loss": 0.0287,
"step": 354
},
{
"epoch": 1.93,
"learning_rate": 6.130434782608696e-05,
"loss": 0.038,
"step": 356
},
{
"epoch": 1.95,
"learning_rate": 6.108695652173914e-05,
"loss": 0.0336,
"step": 358
},
{
"epoch": 1.96,
"learning_rate": 6.086956521739131e-05,
"loss": 0.0276,
"step": 360
},
{
"epoch": 1.97,
"learning_rate": 6.0652173913043487e-05,
"loss": 0.0377,
"step": 362
},
{
"epoch": 1.98,
"learning_rate": 6.0434782608695654e-05,
"loss": 0.0331,
"step": 364
},
{
"epoch": 1.99,
"learning_rate": 6.021739130434783e-05,
"loss": 0.0357,
"step": 366
},
{
"epoch": 2.0,
"learning_rate": 6e-05,
"loss": 0.032,
"step": 368
},
{
"epoch": 2.01,
"learning_rate": 5.9782608695652175e-05,
"loss": 0.0243,
"step": 370
},
{
"epoch": 2.02,
"learning_rate": 5.956521739130435e-05,
"loss": 0.0259,
"step": 372
},
{
"epoch": 2.03,
"learning_rate": 5.934782608695652e-05,
"loss": 0.0396,
"step": 374
},
{
"epoch": 2.04,
"learning_rate": 5.9130434782608704e-05,
"loss": 0.0308,
"step": 376
},
{
"epoch": 2.05,
"learning_rate": 5.891304347826088e-05,
"loss": 0.0324,
"step": 378
},
{
"epoch": 2.07,
"learning_rate": 5.869565217391305e-05,
"loss": 0.034,
"step": 380
},
{
"epoch": 2.08,
"learning_rate": 5.847826086956521e-05,
"loss": 0.0316,
"step": 382
},
{
"epoch": 2.09,
"learning_rate": 5.826086956521739e-05,
"loss": 0.0307,
"step": 384
},
{
"epoch": 2.1,
"learning_rate": 5.804347826086957e-05,
"loss": 0.028,
"step": 386
},
{
"epoch": 2.11,
"learning_rate": 5.782608695652174e-05,
"loss": 0.0347,
"step": 388
},
{
"epoch": 2.12,
"learning_rate": 5.7608695652173915e-05,
"loss": 0.0344,
"step": 390
},
{
"epoch": 2.13,
"learning_rate": 5.739130434782609e-05,
"loss": 0.0318,
"step": 392
},
{
"epoch": 2.14,
"learning_rate": 5.717391304347827e-05,
"loss": 0.0309,
"step": 394
},
{
"epoch": 2.15,
"learning_rate": 5.695652173913044e-05,
"loss": 0.0254,
"step": 396
},
{
"epoch": 2.16,
"learning_rate": 5.673913043478262e-05,
"loss": 0.0307,
"step": 398
},
{
"epoch": 2.17,
"learning_rate": 5.652173913043478e-05,
"loss": 0.0306,
"step": 400
},
{
"epoch": 2.17,
"eval_f1": 0.9192225608721214,
"eval_loss": 0.026507139205932617,
"eval_precision": 0.9182849446143146,
"eval_recall": 0.920172114237896,
"eval_runtime": 13.382,
"eval_samples_per_second": 138.694,
"eval_steps_per_second": 0.598,
"step": 400
},
{
"epoch": 2.18,
"learning_rate": 5.630434782608696e-05,
"loss": 0.03,
"step": 402
},
{
"epoch": 2.2,
"learning_rate": 5.608695652173913e-05,
"loss": 0.03,
"step": 404
},
{
"epoch": 2.21,
"learning_rate": 5.5869565217391306e-05,
"loss": 0.0265,
"step": 406
},
{
"epoch": 2.22,
"learning_rate": 5.565217391304348e-05,
"loss": 0.0254,
"step": 408
},
{
"epoch": 2.23,
"learning_rate": 5.5434782608695654e-05,
"loss": 0.031,
"step": 410
},
{
"epoch": 2.24,
"learning_rate": 5.5217391304347835e-05,
"loss": 0.025,
"step": 412
},
{
"epoch": 2.25,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0278,
"step": 414
},
{
"epoch": 2.26,
"learning_rate": 5.478260869565217e-05,
"loss": 0.0311,
"step": 416
},
{
"epoch": 2.27,
"learning_rate": 5.456521739130434e-05,
"loss": 0.0294,
"step": 418
},
{
"epoch": 2.28,
"learning_rate": 5.4347826086956524e-05,
"loss": 0.0324,
"step": 420
},
{
"epoch": 2.29,
"learning_rate": 5.41304347826087e-05,
"loss": 0.025,
"step": 422
},
{
"epoch": 2.3,
"learning_rate": 5.391304347826087e-05,
"loss": 0.0372,
"step": 424
},
{
"epoch": 2.32,
"learning_rate": 5.3695652173913046e-05,
"loss": 0.0259,
"step": 426
},
{
"epoch": 2.33,
"learning_rate": 5.347826086956522e-05,
"loss": 0.0371,
"step": 428
},
{
"epoch": 2.34,
"learning_rate": 5.32608695652174e-05,
"loss": 0.0273,
"step": 430
},
{
"epoch": 2.35,
"learning_rate": 5.3043478260869574e-05,
"loss": 0.036,
"step": 432
},
{
"epoch": 2.36,
"learning_rate": 5.2826086956521735e-05,
"loss": 0.0287,
"step": 434
},
{
"epoch": 2.37,
"learning_rate": 5.260869565217391e-05,
"loss": 0.0269,
"step": 436
},
{
"epoch": 2.38,
"learning_rate": 5.239130434782609e-05,
"loss": 0.0252,
"step": 438
},
{
"epoch": 2.39,
"learning_rate": 5.217391304347826e-05,
"loss": 0.029,
"step": 440
},
{
"epoch": 2.4,
"learning_rate": 5.195652173913044e-05,
"loss": 0.0306,
"step": 442
},
{
"epoch": 2.41,
"learning_rate": 5.173913043478261e-05,
"loss": 0.0277,
"step": 444
},
{
"epoch": 2.42,
"learning_rate": 5.1521739130434785e-05,
"loss": 0.0263,
"step": 446
},
{
"epoch": 2.43,
"learning_rate": 5.1304347826086966e-05,
"loss": 0.0271,
"step": 448
},
{
"epoch": 2.45,
"learning_rate": 5.108695652173914e-05,
"loss": 0.0293,
"step": 450
},
{
"epoch": 2.45,
"eval_f1": 0.9251812311308268,
"eval_loss": 0.024492362514138222,
"eval_precision": 0.9251268214697702,
"eval_recall": 0.9252456483686047,
"eval_runtime": 13.5649,
"eval_samples_per_second": 136.823,
"eval_steps_per_second": 0.59,
"step": 450
},
{
"epoch": 2.46,
"learning_rate": 5.08695652173913e-05,
"loss": 0.0271,
"step": 452
},
{
"epoch": 2.47,
"learning_rate": 5.0652173913043474e-05,
"loss": 0.0246,
"step": 454
},
{
"epoch": 2.48,
"learning_rate": 5.0434782608695655e-05,
"loss": 0.0219,
"step": 456
},
{
"epoch": 2.49,
"learning_rate": 5.021739130434783e-05,
"loss": 0.0282,
"step": 458
},
{
"epoch": 2.5,
"learning_rate": 5e-05,
"loss": 0.0319,
"step": 460
},
{
"epoch": 2.51,
"learning_rate": 4.9782608695652176e-05,
"loss": 0.026,
"step": 462
},
{
"epoch": 2.52,
"learning_rate": 4.956521739130435e-05,
"loss": 0.0285,
"step": 464
},
{
"epoch": 2.53,
"learning_rate": 4.9347826086956524e-05,
"loss": 0.0299,
"step": 466
},
{
"epoch": 2.54,
"learning_rate": 4.91304347826087e-05,
"loss": 0.0311,
"step": 468
},
{
"epoch": 2.55,
"learning_rate": 4.891304347826087e-05,
"loss": 0.0283,
"step": 470
},
{
"epoch": 2.57,
"learning_rate": 4.8695652173913046e-05,
"loss": 0.0291,
"step": 472
},
{
"epoch": 2.58,
"learning_rate": 4.847826086956522e-05,
"loss": 0.0287,
"step": 474
},
{
"epoch": 2.59,
"learning_rate": 4.8260869565217394e-05,
"loss": 0.0262,
"step": 476
},
{
"epoch": 2.6,
"learning_rate": 4.804347826086957e-05,
"loss": 0.0308,
"step": 478
},
{
"epoch": 2.61,
"learning_rate": 4.782608695652174e-05,
"loss": 0.0252,
"step": 480
},
{
"epoch": 2.62,
"learning_rate": 4.7608695652173916e-05,
"loss": 0.029,
"step": 482
},
{
"epoch": 2.63,
"learning_rate": 4.739130434782609e-05,
"loss": 0.027,
"step": 484
},
{
"epoch": 2.64,
"learning_rate": 4.7173913043478264e-05,
"loss": 0.0253,
"step": 486
},
{
"epoch": 2.65,
"learning_rate": 4.695652173913044e-05,
"loss": 0.0271,
"step": 488
},
{
"epoch": 2.66,
"learning_rate": 4.673913043478261e-05,
"loss": 0.0264,
"step": 490
},
{
"epoch": 2.67,
"learning_rate": 4.6521739130434785e-05,
"loss": 0.0276,
"step": 492
},
{
"epoch": 2.68,
"learning_rate": 4.630434782608696e-05,
"loss": 0.0277,
"step": 494
},
{
"epoch": 2.7,
"learning_rate": 4.608695652173913e-05,
"loss": 0.0259,
"step": 496
},
{
"epoch": 2.71,
"learning_rate": 4.586956521739131e-05,
"loss": 0.0314,
"step": 498
},
{
"epoch": 2.72,
"learning_rate": 4.565217391304348e-05,
"loss": 0.0271,
"step": 500
},
{
"epoch": 2.72,
"eval_f1": 0.9348680681377384,
"eval_loss": 0.02203366905450821,
"eval_precision": 0.9391445230465687,
"eval_recall": 0.9306402922544215,
"eval_runtime": 13.4883,
"eval_samples_per_second": 137.601,
"eval_steps_per_second": 0.593,
"step": 500
},
{
"epoch": 2.73,
"learning_rate": 4.5434782608695655e-05,
"loss": 0.0282,
"step": 502
},
{
"epoch": 2.74,
"learning_rate": 4.521739130434783e-05,
"loss": 0.0275,
"step": 504
},
{
"epoch": 2.75,
"learning_rate": 4.5e-05,
"loss": 0.0211,
"step": 506
},
{
"epoch": 2.76,
"learning_rate": 4.478260869565218e-05,
"loss": 0.0287,
"step": 508
},
{
"epoch": 2.77,
"learning_rate": 4.456521739130435e-05,
"loss": 0.0215,
"step": 510
},
{
"epoch": 2.78,
"learning_rate": 4.4347826086956525e-05,
"loss": 0.0257,
"step": 512
},
{
"epoch": 2.79,
"learning_rate": 4.41304347826087e-05,
"loss": 0.0333,
"step": 514
},
{
"epoch": 2.8,
"learning_rate": 4.391304347826087e-05,
"loss": 0.0285,
"step": 516
},
{
"epoch": 2.82,
"learning_rate": 4.3695652173913046e-05,
"loss": 0.0211,
"step": 518
},
{
"epoch": 2.83,
"learning_rate": 4.347826086956522e-05,
"loss": 0.0253,
"step": 520
},
{
"epoch": 2.84,
"learning_rate": 4.3260869565217394e-05,
"loss": 0.0222,
"step": 522
},
{
"epoch": 2.85,
"learning_rate": 4.304347826086957e-05,
"loss": 0.0274,
"step": 524
},
{
"epoch": 2.86,
"learning_rate": 4.282608695652174e-05,
"loss": 0.0244,
"step": 526
},
{
"epoch": 2.87,
"learning_rate": 4.2608695652173916e-05,
"loss": 0.0313,
"step": 528
},
{
"epoch": 2.88,
"learning_rate": 4.239130434782609e-05,
"loss": 0.0236,
"step": 530
},
{
"epoch": 2.89,
"learning_rate": 4.2173913043478264e-05,
"loss": 0.0241,
"step": 532
},
{
"epoch": 2.9,
"learning_rate": 4.195652173913044e-05,
"loss": 0.0228,
"step": 534
},
{
"epoch": 2.91,
"learning_rate": 4.1739130434782605e-05,
"loss": 0.03,
"step": 536
},
{
"epoch": 2.92,
"learning_rate": 4.1521739130434786e-05,
"loss": 0.0232,
"step": 538
},
{
"epoch": 2.93,
"learning_rate": 4.130434782608696e-05,
"loss": 0.0242,
"step": 540
},
{
"epoch": 2.95,
"learning_rate": 4.1086956521739134e-05,
"loss": 0.0235,
"step": 542
},
{
"epoch": 2.96,
"learning_rate": 4.086956521739131e-05,
"loss": 0.0235,
"step": 544
},
{
"epoch": 2.97,
"learning_rate": 4.065217391304348e-05,
"loss": 0.0262,
"step": 546
},
{
"epoch": 2.98,
"learning_rate": 4.0434782608695655e-05,
"loss": 0.0227,
"step": 548
},
{
"epoch": 2.99,
"learning_rate": 4.021739130434783e-05,
"loss": 0.0189,
"step": 550
},
{
"epoch": 2.99,
"eval_f1": 0.9353923823099244,
"eval_loss": 0.0210172887891531,
"eval_precision": 0.9298178812552713,
"eval_recall": 0.9410442483199254,
"eval_runtime": 13.8124,
"eval_samples_per_second": 134.372,
"eval_steps_per_second": 0.579,
"step": 550
},
{
"epoch": 3.0,
"learning_rate": 4e-05,
"loss": 0.0232,
"step": 552
},
{
"epoch": 3.01,
"learning_rate": 3.978260869565217e-05,
"loss": 0.0251,
"step": 554
},
{
"epoch": 3.02,
"learning_rate": 3.956521739130435e-05,
"loss": 0.0249,
"step": 556
},
{
"epoch": 3.03,
"learning_rate": 3.9347826086956525e-05,
"loss": 0.0289,
"step": 558
},
{
"epoch": 3.04,
"learning_rate": 3.91304347826087e-05,
"loss": 0.0201,
"step": 560
},
{
"epoch": 3.05,
"learning_rate": 3.8913043478260866e-05,
"loss": 0.023,
"step": 562
},
{
"epoch": 3.07,
"learning_rate": 3.869565217391305e-05,
"loss": 0.0241,
"step": 564
},
{
"epoch": 3.08,
"learning_rate": 3.847826086956522e-05,
"loss": 0.0266,
"step": 566
},
{
"epoch": 3.09,
"learning_rate": 3.8260869565217395e-05,
"loss": 0.0212,
"step": 568
},
{
"epoch": 3.1,
"learning_rate": 3.804347826086957e-05,
"loss": 0.024,
"step": 570
},
{
"epoch": 3.11,
"learning_rate": 3.7826086956521736e-05,
"loss": 0.0214,
"step": 572
},
{
"epoch": 3.12,
"learning_rate": 3.7608695652173917e-05,
"loss": 0.0294,
"step": 574
},
{
"epoch": 3.13,
"learning_rate": 3.739130434782609e-05,
"loss": 0.0233,
"step": 576
},
{
"epoch": 3.14,
"learning_rate": 3.7173913043478264e-05,
"loss": 0.0268,
"step": 578
},
{
"epoch": 3.15,
"learning_rate": 3.695652173913043e-05,
"loss": 0.0189,
"step": 580
},
{
"epoch": 3.16,
"learning_rate": 3.673913043478261e-05,
"loss": 0.0217,
"step": 582
},
{
"epoch": 3.17,
"learning_rate": 3.6521739130434786e-05,
"loss": 0.0242,
"step": 584
},
{
"epoch": 3.18,
"learning_rate": 3.630434782608696e-05,
"loss": 0.0234,
"step": 586
},
{
"epoch": 3.2,
"learning_rate": 3.6086956521739134e-05,
"loss": 0.0209,
"step": 588
},
{
"epoch": 3.21,
"learning_rate": 3.58695652173913e-05,
"loss": 0.0257,
"step": 590
},
{
"epoch": 3.22,
"learning_rate": 3.565217391304348e-05,
"loss": 0.0243,
"step": 592
},
{
"epoch": 3.23,
"learning_rate": 3.5434782608695656e-05,
"loss": 0.0268,
"step": 594
},
{
"epoch": 3.24,
"learning_rate": 3.521739130434783e-05,
"loss": 0.0228,
"step": 596
},
{
"epoch": 3.25,
"learning_rate": 3.5e-05,
"loss": 0.0201,
"step": 598
},
{
"epoch": 3.26,
"learning_rate": 3.478260869565218e-05,
"loss": 0.0224,
"step": 600
},
{
"epoch": 3.26,
"eval_f1": 0.9388881585680969,
"eval_loss": 0.019923681393265724,
"eval_precision": 0.9364339098342593,
"eval_recall": 0.9413653580750335,
"eval_runtime": 13.3913,
"eval_samples_per_second": 138.598,
"eval_steps_per_second": 0.597,
"step": 600
},
{
"epoch": 3.27,
"learning_rate": 3.456521739130435e-05,
"loss": 0.0245,
"step": 602
},
{
"epoch": 3.28,
"learning_rate": 3.4347826086956526e-05,
"loss": 0.0213,
"step": 604
},
{
"epoch": 3.29,
"learning_rate": 3.413043478260869e-05,
"loss": 0.0236,
"step": 606
},
{
"epoch": 3.3,
"learning_rate": 3.3913043478260867e-05,
"loss": 0.0189,
"step": 608
},
{
"epoch": 3.32,
"learning_rate": 3.369565217391305e-05,
"loss": 0.0242,
"step": 610
},
{
"epoch": 3.33,
"learning_rate": 3.347826086956522e-05,
"loss": 0.025,
"step": 612
},
{
"epoch": 3.34,
"learning_rate": 3.3260869565217395e-05,
"loss": 0.0255,
"step": 614
},
{
"epoch": 3.35,
"learning_rate": 3.304347826086956e-05,
"loss": 0.0203,
"step": 616
},
{
"epoch": 3.36,
"learning_rate": 3.282608695652174e-05,
"loss": 0.0263,
"step": 618
},
{
"epoch": 3.37,
"learning_rate": 3.260869565217392e-05,
"loss": 0.0227,
"step": 620
},
{
"epoch": 3.38,
"learning_rate": 3.239130434782609e-05,
"loss": 0.0225,
"step": 622
},
{
"epoch": 3.39,
"learning_rate": 3.217391304347826e-05,
"loss": 0.0172,
"step": 624
},
{
"epoch": 3.4,
"learning_rate": 3.195652173913043e-05,
"loss": 0.0176,
"step": 626
},
{
"epoch": 3.41,
"learning_rate": 3.173913043478261e-05,
"loss": 0.0202,
"step": 628
},
{
"epoch": 3.42,
"learning_rate": 3.152173913043479e-05,
"loss": 0.0223,
"step": 630
},
{
"epoch": 3.43,
"learning_rate": 3.130434782608696e-05,
"loss": 0.0248,
"step": 632
},
{
"epoch": 3.45,
"learning_rate": 3.108695652173913e-05,
"loss": 0.0213,
"step": 634
},
{
"epoch": 3.46,
"learning_rate": 3.086956521739131e-05,
"loss": 0.0189,
"step": 636
},
{
"epoch": 3.47,
"learning_rate": 3.065217391304348e-05,
"loss": 0.0221,
"step": 638
},
{
"epoch": 3.48,
"learning_rate": 3.0434782608695656e-05,
"loss": 0.0223,
"step": 640
},
{
"epoch": 3.49,
"learning_rate": 3.0217391304347827e-05,
"loss": 0.0242,
"step": 642
},
{
"epoch": 3.5,
"learning_rate": 3e-05,
"loss": 0.0228,
"step": 644
},
{
"epoch": 3.51,
"learning_rate": 2.9782608695652175e-05,
"loss": 0.0217,
"step": 646
},
{
"epoch": 3.52,
"learning_rate": 2.9565217391304352e-05,
"loss": 0.021,
"step": 648
},
{
"epoch": 3.53,
"learning_rate": 2.9347826086956526e-05,
"loss": 0.0247,
"step": 650
},
{
"epoch": 3.53,
"eval_f1": 0.9423872456441195,
"eval_loss": 0.018970053642988205,
"eval_precision": 0.9418783673711327,
"eval_recall": 0.9429066848995525,
"eval_runtime": 14.0441,
"eval_samples_per_second": 132.155,
"eval_steps_per_second": 0.57,
"step": 650
},
{
"epoch": 3.54,
"learning_rate": 2.9130434782608696e-05,
"loss": 0.0254,
"step": 652
},
{
"epoch": 3.55,
"learning_rate": 2.891304347826087e-05,
"loss": 0.0215,
"step": 654
},
{
"epoch": 3.57,
"learning_rate": 2.8695652173913044e-05,
"loss": 0.0264,
"step": 656
},
{
"epoch": 3.58,
"learning_rate": 2.847826086956522e-05,
"loss": 0.0239,
"step": 658
},
{
"epoch": 3.59,
"learning_rate": 2.826086956521739e-05,
"loss": 0.018,
"step": 660
},
{
"epoch": 3.6,
"learning_rate": 2.8043478260869566e-05,
"loss": 0.0156,
"step": 662
},
{
"epoch": 3.61,
"learning_rate": 2.782608695652174e-05,
"loss": 0.0206,
"step": 664
},
{
"epoch": 3.62,
"learning_rate": 2.7608695652173917e-05,
"loss": 0.0208,
"step": 666
},
{
"epoch": 3.63,
"learning_rate": 2.7391304347826085e-05,
"loss": 0.0192,
"step": 668
},
{
"epoch": 3.64,
"learning_rate": 2.7173913043478262e-05,
"loss": 0.023,
"step": 670
},
{
"epoch": 3.65,
"learning_rate": 2.6956521739130436e-05,
"loss": 0.0203,
"step": 672
},
{
"epoch": 3.66,
"learning_rate": 2.673913043478261e-05,
"loss": 0.0217,
"step": 674
},
{
"epoch": 3.67,
"learning_rate": 2.6521739130434787e-05,
"loss": 0.0216,
"step": 676
},
{
"epoch": 3.68,
"learning_rate": 2.6304347826086954e-05,
"loss": 0.0182,
"step": 678
},
{
"epoch": 3.7,
"learning_rate": 2.608695652173913e-05,
"loss": 0.0231,
"step": 680
},
{
"epoch": 3.71,
"learning_rate": 2.5869565217391305e-05,
"loss": 0.0189,
"step": 682
},
{
"epoch": 3.72,
"learning_rate": 2.5652173913043483e-05,
"loss": 0.0215,
"step": 684
},
{
"epoch": 3.73,
"learning_rate": 2.543478260869565e-05,
"loss": 0.0257,
"step": 686
},
{
"epoch": 3.74,
"learning_rate": 2.5217391304347827e-05,
"loss": 0.0145,
"step": 688
},
{
"epoch": 3.75,
"learning_rate": 2.5e-05,
"loss": 0.0186,
"step": 690
},
{
"epoch": 3.76,
"learning_rate": 2.4782608695652175e-05,
"loss": 0.0174,
"step": 692
},
{
"epoch": 3.77,
"learning_rate": 2.456521739130435e-05,
"loss": 0.023,
"step": 694
},
{
"epoch": 3.78,
"learning_rate": 2.4347826086956523e-05,
"loss": 0.021,
"step": 696
},
{
"epoch": 3.79,
"learning_rate": 2.4130434782608697e-05,
"loss": 0.0202,
"step": 698
},
{
"epoch": 3.8,
"learning_rate": 2.391304347826087e-05,
"loss": 0.0184,
"step": 700
},
{
"epoch": 3.8,
"eval_f1": 0.9427964190902829,
"eval_loss": 0.01869898848235607,
"eval_precision": 0.9387495218777859,
"eval_recall": 0.9468884458628936,
"eval_runtime": 13.5723,
"eval_samples_per_second": 136.749,
"eval_steps_per_second": 0.589,
"step": 700
},
{
"epoch": 3.82,
"learning_rate": 2.3695652173913045e-05,
"loss": 0.02,
"step": 702
},
{
"epoch": 3.83,
"learning_rate": 2.347826086956522e-05,
"loss": 0.0202,
"step": 704
},
{
"epoch": 3.84,
"learning_rate": 2.3260869565217393e-05,
"loss": 0.0207,
"step": 706
},
{
"epoch": 3.85,
"learning_rate": 2.3043478260869567e-05,
"loss": 0.0244,
"step": 708
},
{
"epoch": 3.86,
"learning_rate": 2.282608695652174e-05,
"loss": 0.0203,
"step": 710
},
{
"epoch": 3.87,
"learning_rate": 2.2608695652173914e-05,
"loss": 0.0195,
"step": 712
},
{
"epoch": 3.88,
"learning_rate": 2.239130434782609e-05,
"loss": 0.0164,
"step": 714
},
{
"epoch": 3.89,
"learning_rate": 2.2173913043478262e-05,
"loss": 0.0236,
"step": 716
},
{
"epoch": 3.9,
"learning_rate": 2.1956521739130436e-05,
"loss": 0.0209,
"step": 718
},
{
"epoch": 3.91,
"learning_rate": 2.173913043478261e-05,
"loss": 0.0218,
"step": 720
},
{
"epoch": 3.92,
"learning_rate": 2.1521739130434784e-05,
"loss": 0.0259,
"step": 722
},
{
"epoch": 3.93,
"learning_rate": 2.1304347826086958e-05,
"loss": 0.0207,
"step": 724
},
{
"epoch": 3.95,
"learning_rate": 2.1086956521739132e-05,
"loss": 0.0188,
"step": 726
},
{
"epoch": 3.96,
"learning_rate": 2.0869565217391303e-05,
"loss": 0.0231,
"step": 728
},
{
"epoch": 3.97,
"learning_rate": 2.065217391304348e-05,
"loss": 0.0222,
"step": 730
},
{
"epoch": 3.98,
"learning_rate": 2.0434782608695654e-05,
"loss": 0.0191,
"step": 732
},
{
"epoch": 3.99,
"learning_rate": 2.0217391304347828e-05,
"loss": 0.0221,
"step": 734
},
{
"epoch": 4.0,
"learning_rate": 2e-05,
"loss": 0.0211,
"step": 736
},
{
"epoch": 4.01,
"learning_rate": 1.9782608695652176e-05,
"loss": 0.02,
"step": 738
},
{
"epoch": 4.02,
"learning_rate": 1.956521739130435e-05,
"loss": 0.0197,
"step": 740
},
{
"epoch": 4.03,
"learning_rate": 1.9347826086956523e-05,
"loss": 0.0208,
"step": 742
},
{
"epoch": 4.04,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.0181,
"step": 744
},
{
"epoch": 4.05,
"learning_rate": 1.8913043478260868e-05,
"loss": 0.0223,
"step": 746
},
{
"epoch": 4.07,
"learning_rate": 1.8695652173913045e-05,
"loss": 0.0212,
"step": 748
},
{
"epoch": 4.08,
"learning_rate": 1.8478260869565216e-05,
"loss": 0.0183,
"step": 750
},
{
"epoch": 4.08,
"eval_f1": 0.9462391459396587,
"eval_loss": 0.017822517082095146,
"eval_precision": 0.9451528154384874,
"eval_recall": 0.9473379995200449,
"eval_runtime": 13.4572,
"eval_samples_per_second": 137.919,
"eval_steps_per_second": 0.594,
"step": 750
},
{
"epoch": 4.09,
"learning_rate": 1.8260869565217393e-05,
"loss": 0.0193,
"step": 752
},
{
"epoch": 4.1,
"learning_rate": 1.8043478260869567e-05,
"loss": 0.0159,
"step": 754
},
{
"epoch": 4.11,
"learning_rate": 1.782608695652174e-05,
"loss": 0.0212,
"step": 756
},
{
"epoch": 4.12,
"learning_rate": 1.7608695652173915e-05,
"loss": 0.0192,
"step": 758
},
{
"epoch": 4.13,
"learning_rate": 1.739130434782609e-05,
"loss": 0.0223,
"step": 760
},
{
"epoch": 4.14,
"learning_rate": 1.7173913043478263e-05,
"loss": 0.0166,
"step": 762
},
{
"epoch": 4.15,
"learning_rate": 1.6956521739130433e-05,
"loss": 0.0188,
"step": 764
},
{
"epoch": 4.16,
"learning_rate": 1.673913043478261e-05,
"loss": 0.0182,
"step": 766
},
{
"epoch": 4.17,
"learning_rate": 1.652173913043478e-05,
"loss": 0.0193,
"step": 768
},
{
"epoch": 4.18,
"learning_rate": 1.630434782608696e-05,
"loss": 0.0177,
"step": 770
},
{
"epoch": 4.2,
"learning_rate": 1.608695652173913e-05,
"loss": 0.0176,
"step": 772
},
{
"epoch": 4.21,
"learning_rate": 1.5869565217391306e-05,
"loss": 0.0202,
"step": 774
},
{
"epoch": 4.22,
"learning_rate": 1.565217391304348e-05,
"loss": 0.0199,
"step": 776
},
{
"epoch": 4.23,
"learning_rate": 1.5434782608695654e-05,
"loss": 0.0204,
"step": 778
},
{
"epoch": 4.24,
"learning_rate": 1.5217391304347828e-05,
"loss": 0.0199,
"step": 780
},
{
"epoch": 4.25,
"learning_rate": 1.5e-05,
"loss": 0.0205,
"step": 782
},
{
"epoch": 4.26,
"learning_rate": 1.4782608695652176e-05,
"loss": 0.0215,
"step": 784
},
{
"epoch": 4.27,
"learning_rate": 1.4565217391304348e-05,
"loss": 0.0179,
"step": 786
},
{
"epoch": 4.28,
"learning_rate": 1.4347826086956522e-05,
"loss": 0.0181,
"step": 788
},
{
"epoch": 4.29,
"learning_rate": 1.4130434782608694e-05,
"loss": 0.0217,
"step": 790
},
{
"epoch": 4.3,
"learning_rate": 1.391304347826087e-05,
"loss": 0.0212,
"step": 792
},
{
"epoch": 4.32,
"learning_rate": 1.3695652173913042e-05,
"loss": 0.0208,
"step": 794
},
{
"epoch": 4.33,
"learning_rate": 1.3478260869565218e-05,
"loss": 0.0157,
"step": 796
},
{
"epoch": 4.34,
"learning_rate": 1.3260869565217394e-05,
"loss": 0.0161,
"step": 798
},
{
"epoch": 4.35,
"learning_rate": 1.3043478260869566e-05,
"loss": 0.0175,
"step": 800
},
{
"epoch": 4.35,
"eval_f1": 0.9480086057353725,
"eval_loss": 0.017221176996827126,
"eval_precision": 0.9474055538789009,
"eval_recall": 0.9486224385404776,
"eval_runtime": 13.6694,
"eval_samples_per_second": 135.777,
"eval_steps_per_second": 0.585,
"step": 800
}
],
"max_steps": 920,
"num_train_epochs": 5,
"total_flos": 4.01525989965824e+16,
"trial_name": null,
"trial_params": null
}