Commit
•
903beb7
1
Parent(s):
f9db674
End of training
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +461 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 14.082046567855343,
|
| 4 |
+
"train_runtime": 2464.2419,
|
| 5 |
+
"train_samples_per_second": 9.983,
|
| 6 |
+
"train_steps_per_second": 1.258
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 14.082046567855343,
|
| 4 |
+
"train_runtime": 2464.2419,
|
| 5 |
+
"train_samples_per_second": 9.983,
|
| 6 |
+
"train_steps_per_second": 1.258
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 3100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 38.730377197265625,
|
| 13 |
+
"eval_runtime": 2.8841,
|
| 14 |
+
"eval_samples_per_second": 41.955,
|
| 15 |
+
"eval_steps_per_second": 5.548,
|
| 16 |
+
"step": 62
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"eval_loss": 37.18061828613281,
|
| 21 |
+
"eval_runtime": 2.9537,
|
| 22 |
+
"eval_samples_per_second": 40.966,
|
| 23 |
+
"eval_steps_per_second": 5.417,
|
| 24 |
+
"step": 124
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 3.0,
|
| 28 |
+
"eval_loss": 33.34883499145508,
|
| 29 |
+
"eval_runtime": 3.0329,
|
| 30 |
+
"eval_samples_per_second": 39.895,
|
| 31 |
+
"eval_steps_per_second": 5.275,
|
| 32 |
+
"step": 186
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 4.0,
|
| 36 |
+
"eval_loss": 28.77151870727539,
|
| 37 |
+
"eval_runtime": 3.038,
|
| 38 |
+
"eval_samples_per_second": 39.829,
|
| 39 |
+
"eval_steps_per_second": 5.267,
|
| 40 |
+
"step": 248
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.0,
|
| 44 |
+
"eval_loss": 24.89649200439453,
|
| 45 |
+
"eval_runtime": 3.1068,
|
| 46 |
+
"eval_samples_per_second": 38.947,
|
| 47 |
+
"eval_steps_per_second": 5.15,
|
| 48 |
+
"step": 310
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 6.0,
|
| 52 |
+
"eval_loss": 21.40663719177246,
|
| 53 |
+
"eval_runtime": 3.1605,
|
| 54 |
+
"eval_samples_per_second": 38.285,
|
| 55 |
+
"eval_steps_per_second": 5.062,
|
| 56 |
+
"step": 372
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 7.0,
|
| 60 |
+
"eval_loss": 19.166534423828125,
|
| 61 |
+
"eval_runtime": 3.191,
|
| 62 |
+
"eval_samples_per_second": 37.919,
|
| 63 |
+
"eval_steps_per_second": 5.014,
|
| 64 |
+
"step": 434
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 8.0,
|
| 68 |
+
"eval_loss": 17.308666229248047,
|
| 69 |
+
"eval_runtime": 3.1957,
|
| 70 |
+
"eval_samples_per_second": 37.863,
|
| 71 |
+
"eval_steps_per_second": 5.007,
|
| 72 |
+
"step": 496
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.06,
|
| 76 |
+
"learning_rate": 1.6774193548387096e-07,
|
| 77 |
+
"loss": 29.5022,
|
| 78 |
+
"step": 500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 9.0,
|
| 82 |
+
"eval_loss": 15.532267570495605,
|
| 83 |
+
"eval_runtime": 3.0171,
|
| 84 |
+
"eval_samples_per_second": 40.104,
|
| 85 |
+
"eval_steps_per_second": 5.303,
|
| 86 |
+
"step": 558
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.0,
|
| 90 |
+
"eval_loss": 14.449665069580078,
|
| 91 |
+
"eval_runtime": 3.0595,
|
| 92 |
+
"eval_samples_per_second": 39.549,
|
| 93 |
+
"eval_steps_per_second": 5.23,
|
| 94 |
+
"step": 620
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 11.0,
|
| 98 |
+
"eval_loss": 14.162155151367188,
|
| 99 |
+
"eval_runtime": 3.1079,
|
| 100 |
+
"eval_samples_per_second": 38.933,
|
| 101 |
+
"eval_steps_per_second": 5.148,
|
| 102 |
+
"step": 682
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 12.0,
|
| 106 |
+
"eval_loss": 13.751199722290039,
|
| 107 |
+
"eval_runtime": 3.1538,
|
| 108 |
+
"eval_samples_per_second": 38.366,
|
| 109 |
+
"eval_steps_per_second": 5.073,
|
| 110 |
+
"step": 744
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 13.0,
|
| 114 |
+
"eval_loss": 13.394129753112793,
|
| 115 |
+
"eval_runtime": 3.1936,
|
| 116 |
+
"eval_samples_per_second": 37.888,
|
| 117 |
+
"eval_steps_per_second": 5.01,
|
| 118 |
+
"step": 806
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 14.0,
|
| 122 |
+
"eval_loss": 13.021451950073242,
|
| 123 |
+
"eval_runtime": 3.2109,
|
| 124 |
+
"eval_samples_per_second": 37.684,
|
| 125 |
+
"eval_steps_per_second": 4.983,
|
| 126 |
+
"step": 868
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 15.0,
|
| 130 |
+
"eval_loss": 12.83625602722168,
|
| 131 |
+
"eval_runtime": 3.2002,
|
| 132 |
+
"eval_samples_per_second": 37.81,
|
| 133 |
+
"eval_steps_per_second": 5.0,
|
| 134 |
+
"step": 930
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 16.0,
|
| 138 |
+
"eval_loss": 12.659578323364258,
|
| 139 |
+
"eval_runtime": 3.1987,
|
| 140 |
+
"eval_samples_per_second": 37.828,
|
| 141 |
+
"eval_steps_per_second": 5.002,
|
| 142 |
+
"step": 992
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 16.13,
|
| 146 |
+
"learning_rate": 1.3548387096774192e-07,
|
| 147 |
+
"loss": 13.2409,
|
| 148 |
+
"step": 1000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 17.0,
|
| 152 |
+
"eval_loss": 12.591437339782715,
|
| 153 |
+
"eval_runtime": 3.1748,
|
| 154 |
+
"eval_samples_per_second": 38.113,
|
| 155 |
+
"eval_steps_per_second": 5.04,
|
| 156 |
+
"step": 1054
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 18.0,
|
| 160 |
+
"eval_loss": 12.289512634277344,
|
| 161 |
+
"eval_runtime": 3.1814,
|
| 162 |
+
"eval_samples_per_second": 38.033,
|
| 163 |
+
"eval_steps_per_second": 5.029,
|
| 164 |
+
"step": 1116
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 19.0,
|
| 168 |
+
"eval_loss": 12.269988059997559,
|
| 169 |
+
"eval_runtime": 3.2171,
|
| 170 |
+
"eval_samples_per_second": 37.611,
|
| 171 |
+
"eval_steps_per_second": 4.973,
|
| 172 |
+
"step": 1178
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 20.0,
|
| 176 |
+
"eval_loss": 12.142666816711426,
|
| 177 |
+
"eval_runtime": 3.202,
|
| 178 |
+
"eval_samples_per_second": 37.789,
|
| 179 |
+
"eval_steps_per_second": 4.997,
|
| 180 |
+
"step": 1240
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 21.0,
|
| 184 |
+
"eval_loss": 12.13444995880127,
|
| 185 |
+
"eval_runtime": 3.1974,
|
| 186 |
+
"eval_samples_per_second": 37.843,
|
| 187 |
+
"eval_steps_per_second": 5.004,
|
| 188 |
+
"step": 1302
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 22.0,
|
| 192 |
+
"eval_loss": 12.062304496765137,
|
| 193 |
+
"eval_runtime": 3.1989,
|
| 194 |
+
"eval_samples_per_second": 37.825,
|
| 195 |
+
"eval_steps_per_second": 5.002,
|
| 196 |
+
"step": 1364
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 23.0,
|
| 200 |
+
"eval_loss": 12.063033103942871,
|
| 201 |
+
"eval_runtime": 3.2187,
|
| 202 |
+
"eval_samples_per_second": 37.593,
|
| 203 |
+
"eval_steps_per_second": 4.971,
|
| 204 |
+
"step": 1426
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 24.0,
|
| 208 |
+
"eval_loss": 12.098295211791992,
|
| 209 |
+
"eval_runtime": 3.1987,
|
| 210 |
+
"eval_samples_per_second": 37.827,
|
| 211 |
+
"eval_steps_per_second": 5.002,
|
| 212 |
+
"step": 1488
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 24.19,
|
| 216 |
+
"learning_rate": 1.032258064516129e-07,
|
| 217 |
+
"loss": 11.0242,
|
| 218 |
+
"step": 1500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 25.0,
|
| 222 |
+
"eval_loss": 11.790215492248535,
|
| 223 |
+
"eval_runtime": 3.1841,
|
| 224 |
+
"eval_samples_per_second": 38.002,
|
| 225 |
+
"eval_steps_per_second": 5.025,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 26.0,
|
| 230 |
+
"eval_loss": 11.862567901611328,
|
| 231 |
+
"eval_runtime": 3.1927,
|
| 232 |
+
"eval_samples_per_second": 37.899,
|
| 233 |
+
"eval_steps_per_second": 5.011,
|
| 234 |
+
"step": 1612
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 27.0,
|
| 238 |
+
"eval_loss": 11.915380477905273,
|
| 239 |
+
"eval_runtime": 3.2213,
|
| 240 |
+
"eval_samples_per_second": 37.562,
|
| 241 |
+
"eval_steps_per_second": 4.967,
|
| 242 |
+
"step": 1674
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 28.0,
|
| 246 |
+
"eval_loss": 11.648334503173828,
|
| 247 |
+
"eval_runtime": 3.1958,
|
| 248 |
+
"eval_samples_per_second": 37.862,
|
| 249 |
+
"eval_steps_per_second": 5.007,
|
| 250 |
+
"step": 1736
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 29.0,
|
| 254 |
+
"eval_loss": 11.861973762512207,
|
| 255 |
+
"eval_runtime": 3.1992,
|
| 256 |
+
"eval_samples_per_second": 37.822,
|
| 257 |
+
"eval_steps_per_second": 5.001,
|
| 258 |
+
"step": 1798
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 30.0,
|
| 262 |
+
"eval_loss": 11.598742485046387,
|
| 263 |
+
"eval_runtime": 3.2,
|
| 264 |
+
"eval_samples_per_second": 37.812,
|
| 265 |
+
"eval_steps_per_second": 5.0,
|
| 266 |
+
"step": 1860
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 31.0,
|
| 270 |
+
"eval_loss": 11.763324737548828,
|
| 271 |
+
"eval_runtime": 3.1997,
|
| 272 |
+
"eval_samples_per_second": 37.817,
|
| 273 |
+
"eval_steps_per_second": 5.001,
|
| 274 |
+
"step": 1922
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 32.0,
|
| 278 |
+
"eval_loss": 11.699971199035645,
|
| 279 |
+
"eval_runtime": 3.1883,
|
| 280 |
+
"eval_samples_per_second": 37.951,
|
| 281 |
+
"eval_steps_per_second": 5.018,
|
| 282 |
+
"step": 1984
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 32.26,
|
| 286 |
+
"learning_rate": 7.096774193548388e-08,
|
| 287 |
+
"loss": 10.5931,
|
| 288 |
+
"step": 2000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 33.0,
|
| 292 |
+
"eval_loss": 11.6630859375,
|
| 293 |
+
"eval_runtime": 3.1817,
|
| 294 |
+
"eval_samples_per_second": 38.03,
|
| 295 |
+
"eval_steps_per_second": 5.029,
|
| 296 |
+
"step": 2046
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 34.0,
|
| 300 |
+
"eval_loss": 11.431499481201172,
|
| 301 |
+
"eval_runtime": 3.1876,
|
| 302 |
+
"eval_samples_per_second": 37.96,
|
| 303 |
+
"eval_steps_per_second": 5.019,
|
| 304 |
+
"step": 2108
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 35.0,
|
| 308 |
+
"eval_loss": 11.56187915802002,
|
| 309 |
+
"eval_runtime": 3.1936,
|
| 310 |
+
"eval_samples_per_second": 37.889,
|
| 311 |
+
"eval_steps_per_second": 5.01,
|
| 312 |
+
"step": 2170
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 36.0,
|
| 316 |
+
"eval_loss": 11.59299087524414,
|
| 317 |
+
"eval_runtime": 3.1844,
|
| 318 |
+
"eval_samples_per_second": 37.998,
|
| 319 |
+
"eval_steps_per_second": 5.025,
|
| 320 |
+
"step": 2232
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 37.0,
|
| 324 |
+
"eval_loss": 11.55374526977539,
|
| 325 |
+
"eval_runtime": 3.2023,
|
| 326 |
+
"eval_samples_per_second": 37.785,
|
| 327 |
+
"eval_steps_per_second": 4.996,
|
| 328 |
+
"step": 2294
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 38.0,
|
| 332 |
+
"eval_loss": 11.67027473449707,
|
| 333 |
+
"eval_runtime": 3.1993,
|
| 334 |
+
"eval_samples_per_second": 37.821,
|
| 335 |
+
"eval_steps_per_second": 5.001,
|
| 336 |
+
"step": 2356
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 39.0,
|
| 340 |
+
"eval_loss": 11.548821449279785,
|
| 341 |
+
"eval_runtime": 3.1859,
|
| 342 |
+
"eval_samples_per_second": 37.98,
|
| 343 |
+
"eval_steps_per_second": 5.022,
|
| 344 |
+
"step": 2418
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 40.0,
|
| 348 |
+
"eval_loss": 11.443954467773438,
|
| 349 |
+
"eval_runtime": 3.1913,
|
| 350 |
+
"eval_samples_per_second": 37.916,
|
| 351 |
+
"eval_steps_per_second": 5.014,
|
| 352 |
+
"step": 2480
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 40.32,
|
| 356 |
+
"learning_rate": 3.8709677419354835e-08,
|
| 357 |
+
"loss": 10.4503,
|
| 358 |
+
"step": 2500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 41.0,
|
| 362 |
+
"eval_loss": 11.321048736572266,
|
| 363 |
+
"eval_runtime": 3.1707,
|
| 364 |
+
"eval_samples_per_second": 38.162,
|
| 365 |
+
"eval_steps_per_second": 5.046,
|
| 366 |
+
"step": 2542
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 42.0,
|
| 370 |
+
"eval_loss": 11.437300682067871,
|
| 371 |
+
"eval_runtime": 3.1784,
|
| 372 |
+
"eval_samples_per_second": 38.07,
|
| 373 |
+
"eval_steps_per_second": 5.034,
|
| 374 |
+
"step": 2604
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 43.0,
|
| 378 |
+
"eval_loss": 11.486796379089355,
|
| 379 |
+
"eval_runtime": 3.187,
|
| 380 |
+
"eval_samples_per_second": 37.967,
|
| 381 |
+
"eval_steps_per_second": 5.02,
|
| 382 |
+
"step": 2666
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 44.0,
|
| 386 |
+
"eval_loss": 11.38952350616455,
|
| 387 |
+
"eval_runtime": 3.1899,
|
| 388 |
+
"eval_samples_per_second": 37.932,
|
| 389 |
+
"eval_steps_per_second": 5.016,
|
| 390 |
+
"step": 2728
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 45.0,
|
| 394 |
+
"eval_loss": 11.409669876098633,
|
| 395 |
+
"eval_runtime": 3.1917,
|
| 396 |
+
"eval_samples_per_second": 37.911,
|
| 397 |
+
"eval_steps_per_second": 5.013,
|
| 398 |
+
"step": 2790
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 46.0,
|
| 402 |
+
"eval_loss": 11.556734085083008,
|
| 403 |
+
"eval_runtime": 3.1934,
|
| 404 |
+
"eval_samples_per_second": 37.891,
|
| 405 |
+
"eval_steps_per_second": 5.01,
|
| 406 |
+
"step": 2852
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 47.0,
|
| 410 |
+
"eval_loss": 11.35185718536377,
|
| 411 |
+
"eval_runtime": 3.1869,
|
| 412 |
+
"eval_samples_per_second": 37.968,
|
| 413 |
+
"eval_steps_per_second": 5.021,
|
| 414 |
+
"step": 2914
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 48.0,
|
| 418 |
+
"eval_loss": 11.326269149780273,
|
| 419 |
+
"eval_runtime": 3.1877,
|
| 420 |
+
"eval_samples_per_second": 37.959,
|
| 421 |
+
"eval_steps_per_second": 5.019,
|
| 422 |
+
"step": 2976
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 48.39,
|
| 426 |
+
"learning_rate": 6.451612903225806e-09,
|
| 427 |
+
"loss": 10.4239,
|
| 428 |
+
"step": 3000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 49.0,
|
| 432 |
+
"eval_loss": 11.404916763305664,
|
| 433 |
+
"eval_runtime": 3.3462,
|
| 434 |
+
"eval_samples_per_second": 36.16,
|
| 435 |
+
"eval_steps_per_second": 4.782,
|
| 436 |
+
"step": 3038
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 50.0,
|
| 440 |
+
"eval_loss": 11.230060577392578,
|
| 441 |
+
"eval_runtime": 3.1439,
|
| 442 |
+
"eval_samples_per_second": 38.487,
|
| 443 |
+
"eval_steps_per_second": 5.089,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 50.0,
|
| 448 |
+
"step": 3100,
|
| 449 |
+
"total_flos": 1623561609830400.0,
|
| 450 |
+
"train_loss": 14.082046567855343,
|
| 451 |
+
"train_runtime": 2464.2419,
|
| 452 |
+
"train_samples_per_second": 9.983,
|
| 453 |
+
"train_steps_per_second": 1.258
|
| 454 |
+
}
|
| 455 |
+
],
|
| 456 |
+
"max_steps": 3100,
|
| 457 |
+
"num_train_epochs": 50,
|
| 458 |
+
"total_flos": 1623561609830400.0,
|
| 459 |
+
"trial_name": null,
|
| 460 |
+
"trial_params": null
|
| 461 |
+
}
|