🍻 cheers
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9849624060150376,
|
| 4 |
+
"eval_loss": 0.05050145834684372,
|
| 5 |
+
"eval_runtime": 1.4955,
|
| 6 |
+
"eval_samples_per_second": 88.935,
|
| 7 |
+
"eval_steps_per_second": 11.368,
|
| 8 |
+
"total_flos": 6.410194832952852e+17,
|
| 9 |
+
"train_loss": 0.08019667567255405,
|
| 10 |
+
"train_runtime": 186.4742,
|
| 11 |
+
"train_samples_per_second": 44.36,
|
| 12 |
+
"train_steps_per_second": 2.789
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9849624060150376,
|
| 4 |
+
"eval_loss": 0.05050145834684372,
|
| 5 |
+
"eval_runtime": 1.4955,
|
| 6 |
+
"eval_samples_per_second": 88.935,
|
| 7 |
+
"eval_steps_per_second": 11.368
|
| 8 |
+
}
|
runs/Feb12_23-10-17_607fa9b8b674/events.out.tfevents.1644708484.607fa9b8b674.124.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5d9e01b442f6b48a4ce20371742ecf9383ea60723c0772cb9c62f430cd20da2
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"total_flos": 6.410194832952852e+17,
|
| 4 |
+
"train_loss": 0.08019667567255405,
|
| 5 |
+
"train_runtime": 186.4742,
|
| 6 |
+
"train_samples_per_second": 44.36,
|
| 7 |
+
"train_steps_per_second": 2.789
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.05050145834684372,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-500",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 520,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 0.00019615384615384615,
|
| 13 |
+
"loss": 0.9379,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.31,
|
| 18 |
+
"learning_rate": 0.00019230769230769233,
|
| 19 |
+
"loss": 0.4657,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.46,
|
| 24 |
+
"learning_rate": 0.00018846153846153847,
|
| 25 |
+
"loss": 0.1998,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.62,
|
| 30 |
+
"learning_rate": 0.00018461538461538463,
|
| 31 |
+
"loss": 0.3618,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.77,
|
| 36 |
+
"learning_rate": 0.00018076923076923077,
|
| 37 |
+
"loss": 0.2387,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.92,
|
| 42 |
+
"learning_rate": 0.00017692307692307693,
|
| 43 |
+
"loss": 0.1682,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.08,
|
| 48 |
+
"learning_rate": 0.0001730769230769231,
|
| 49 |
+
"loss": 0.2817,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.23,
|
| 54 |
+
"learning_rate": 0.00016923076923076923,
|
| 55 |
+
"loss": 0.1381,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.38,
|
| 60 |
+
"learning_rate": 0.0001653846153846154,
|
| 61 |
+
"loss": 0.1933,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.54,
|
| 66 |
+
"learning_rate": 0.00016153846153846155,
|
| 67 |
+
"loss": 0.1166,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.54,
|
| 72 |
+
"eval_accuracy": 0.9849624060150376,
|
| 73 |
+
"eval_loss": 0.07644423842430115,
|
| 74 |
+
"eval_runtime": 1.439,
|
| 75 |
+
"eval_samples_per_second": 92.425,
|
| 76 |
+
"eval_steps_per_second": 11.814,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.69,
|
| 81 |
+
"learning_rate": 0.0001576923076923077,
|
| 82 |
+
"loss": 0.0955,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.85,
|
| 87 |
+
"learning_rate": 0.00015384615384615385,
|
| 88 |
+
"loss": 0.1201,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.0,
|
| 93 |
+
"learning_rate": 0.00015000000000000001,
|
| 94 |
+
"loss": 0.1216,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.15,
|
| 99 |
+
"learning_rate": 0.00014615384615384615,
|
| 100 |
+
"loss": 0.0981,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.31,
|
| 105 |
+
"learning_rate": 0.0001423076923076923,
|
| 106 |
+
"loss": 0.0418,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.46,
|
| 111 |
+
"learning_rate": 0.00013846153846153847,
|
| 112 |
+
"loss": 0.0546,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.62,
|
| 117 |
+
"learning_rate": 0.00013461538461538464,
|
| 118 |
+
"loss": 0.0333,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.77,
|
| 123 |
+
"learning_rate": 0.00013076923076923077,
|
| 124 |
+
"loss": 0.0193,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.92,
|
| 129 |
+
"learning_rate": 0.00012692307692307693,
|
| 130 |
+
"loss": 0.0325,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.08,
|
| 135 |
+
"learning_rate": 0.0001230769230769231,
|
| 136 |
+
"loss": 0.1607,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.08,
|
| 141 |
+
"eval_accuracy": 0.9398496240601504,
|
| 142 |
+
"eval_loss": 0.21135304868221283,
|
| 143 |
+
"eval_runtime": 1.6144,
|
| 144 |
+
"eval_samples_per_second": 82.384,
|
| 145 |
+
"eval_steps_per_second": 10.53,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.23,
|
| 150 |
+
"learning_rate": 0.00011923076923076923,
|
| 151 |
+
"loss": 0.0295,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.38,
|
| 156 |
+
"learning_rate": 0.00011538461538461538,
|
| 157 |
+
"loss": 0.0193,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.54,
|
| 162 |
+
"learning_rate": 0.00011153846153846154,
|
| 163 |
+
"loss": 0.0271,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.69,
|
| 168 |
+
"learning_rate": 0.0001076923076923077,
|
| 169 |
+
"loss": 0.0098,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.85,
|
| 174 |
+
"learning_rate": 0.00010384615384615386,
|
| 175 |
+
"loss": 0.0104,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.0,
|
| 180 |
+
"learning_rate": 0.0001,
|
| 181 |
+
"loss": 0.0079,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.15,
|
| 186 |
+
"learning_rate": 9.615384615384617e-05,
|
| 187 |
+
"loss": 0.0077,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.31,
|
| 192 |
+
"learning_rate": 9.230769230769232e-05,
|
| 193 |
+
"loss": 0.012,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.46,
|
| 198 |
+
"learning_rate": 8.846153846153847e-05,
|
| 199 |
+
"loss": 0.0109,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.62,
|
| 204 |
+
"learning_rate": 8.461538461538461e-05,
|
| 205 |
+
"loss": 0.0067,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.62,
|
| 210 |
+
"eval_accuracy": 0.9774436090225563,
|
| 211 |
+
"eval_loss": 0.0692465677857399,
|
| 212 |
+
"eval_runtime": 1.4522,
|
| 213 |
+
"eval_samples_per_second": 91.585,
|
| 214 |
+
"eval_steps_per_second": 11.706,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.77,
|
| 219 |
+
"learning_rate": 8.076923076923078e-05,
|
| 220 |
+
"loss": 0.0379,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.92,
|
| 225 |
+
"learning_rate": 7.692307692307693e-05,
|
| 226 |
+
"loss": 0.0116,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 5.08,
|
| 231 |
+
"learning_rate": 7.307692307692307e-05,
|
| 232 |
+
"loss": 0.0072,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.23,
|
| 237 |
+
"learning_rate": 6.923076923076924e-05,
|
| 238 |
+
"loss": 0.0064,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.38,
|
| 243 |
+
"learning_rate": 6.538461538461539e-05,
|
| 244 |
+
"loss": 0.0063,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.54,
|
| 249 |
+
"learning_rate": 6.153846153846155e-05,
|
| 250 |
+
"loss": 0.0055,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.69,
|
| 255 |
+
"learning_rate": 5.769230769230769e-05,
|
| 256 |
+
"loss": 0.0055,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.85,
|
| 261 |
+
"learning_rate": 5.384615384615385e-05,
|
| 262 |
+
"loss": 0.0053,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 6.0,
|
| 267 |
+
"learning_rate": 5e-05,
|
| 268 |
+
"loss": 0.0051,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.15,
|
| 273 |
+
"learning_rate": 4.615384615384616e-05,
|
| 274 |
+
"loss": 0.005,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.15,
|
| 279 |
+
"eval_accuracy": 0.9624060150375939,
|
| 280 |
+
"eval_loss": 0.0944083109498024,
|
| 281 |
+
"eval_runtime": 1.7559,
|
| 282 |
+
"eval_samples_per_second": 75.743,
|
| 283 |
+
"eval_steps_per_second": 9.681,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.31,
|
| 288 |
+
"learning_rate": 4.230769230769231e-05,
|
| 289 |
+
"loss": 0.0049,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.46,
|
| 294 |
+
"learning_rate": 3.846153846153846e-05,
|
| 295 |
+
"loss": 0.0047,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.62,
|
| 300 |
+
"learning_rate": 3.461538461538462e-05,
|
| 301 |
+
"loss": 0.0047,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.77,
|
| 306 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 307 |
+
"loss": 0.0045,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.92,
|
| 312 |
+
"learning_rate": 2.6923076923076923e-05,
|
| 313 |
+
"loss": 0.0045,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.08,
|
| 318 |
+
"learning_rate": 2.307692307692308e-05,
|
| 319 |
+
"loss": 0.0045,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.23,
|
| 324 |
+
"learning_rate": 1.923076923076923e-05,
|
| 325 |
+
"loss": 0.0044,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.38,
|
| 330 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 331 |
+
"loss": 0.0044,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.54,
|
| 336 |
+
"learning_rate": 1.153846153846154e-05,
|
| 337 |
+
"loss": 0.0044,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.69,
|
| 342 |
+
"learning_rate": 7.692307692307694e-06,
|
| 343 |
+
"loss": 0.0043,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 7.69,
|
| 348 |
+
"eval_accuracy": 0.9849624060150376,
|
| 349 |
+
"eval_loss": 0.05050145834684372,
|
| 350 |
+
"eval_runtime": 1.4729,
|
| 351 |
+
"eval_samples_per_second": 90.301,
|
| 352 |
+
"eval_steps_per_second": 11.542,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.85,
|
| 357 |
+
"learning_rate": 3.846153846153847e-06,
|
| 358 |
+
"loss": 0.0043,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"learning_rate": 0.0,
|
| 364 |
+
"loss": 0.0043,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 8.0,
|
| 369 |
+
"step": 520,
|
| 370 |
+
"total_flos": 6.410194832952852e+17,
|
| 371 |
+
"train_loss": 0.08019667567255405,
|
| 372 |
+
"train_runtime": 186.4742,
|
| 373 |
+
"train_samples_per_second": 44.36,
|
| 374 |
+
"train_steps_per_second": 2.789
|
| 375 |
+
}
|
| 376 |
+
],
|
| 377 |
+
"max_steps": 520,
|
| 378 |
+
"num_train_epochs": 8,
|
| 379 |
+
"total_flos": 6.410194832952852e+17,
|
| 380 |
+
"trial_name": null,
|
| 381 |
+
"trial_params": null
|
| 382 |
+
}
|