Commit
•
7342fe6
1
Parent(s):
7df96e5
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 2.0537798263831064e-05,
|
| 5 |
+
"eval_runtime": 74.0243,
|
| 6 |
+
"eval_samples_per_second": 135.509,
|
| 7 |
+
"eval_steps_per_second": 4.242,
|
| 8 |
+
"total_flos": 8.139769344619315e+17,
|
| 9 |
+
"train_loss": 0.788053667698151,
|
| 10 |
+
"train_runtime": 1008.4422,
|
| 11 |
+
"train_samples_per_second": 44.76,
|
| 12 |
+
"train_steps_per_second": 0.348
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 2.0537798263831064e-05,
|
| 5 |
+
"eval_runtime": 74.0243,
|
| 6 |
+
"eval_samples_per_second": 135.509,
|
| 7 |
+
"eval_steps_per_second": 4.242
|
| 8 |
+
}
|
runs/Feb08_05-52-21_8c2f8b0cb065/events.out.tfevents.1675836730.8c2f8b0cb065.115.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d00a4aac7b13ec13f6e2d26f718a42ffdaf3c76ba2025ba7f822621873981f07
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 8.139769344619315e+17,
|
| 4 |
+
"train_loss": 0.788053667698151,
|
| 5 |
+
"train_runtime": 1008.4422,
|
| 6 |
+
"train_samples_per_second": 44.76,
|
| 7 |
+
"train_steps_per_second": 0.348
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "cvt-13-finetuned-waste/checkpoint-117",
|
| 4 |
+
"epoch": 2.9936305732484074,
|
| 5 |
+
"global_step": 351,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.388888888888889e-05,
|
| 13 |
+
"loss": 7.9487,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 2.777777777777778e-05,
|
| 19 |
+
"loss": 6.9548,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.25,
|
| 24 |
+
"learning_rate": 4.166666666666667e-05,
|
| 25 |
+
"loss": 4.6619,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 4.936507936507937e-05,
|
| 31 |
+
"loss": 2.2104,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.42,
|
| 36 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 37 |
+
"loss": 0.9647,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.51,
|
| 42 |
+
"learning_rate": 4.6190476190476194e-05,
|
| 43 |
+
"loss": 0.4498,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"learning_rate": 4.460317460317461e-05,
|
| 49 |
+
"loss": 0.1823,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.68,
|
| 54 |
+
"learning_rate": 4.301587301587302e-05,
|
| 55 |
+
"loss": 0.1543,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.76,
|
| 60 |
+
"learning_rate": 4.1428571428571437e-05,
|
| 61 |
+
"loss": 0.1095,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.85,
|
| 66 |
+
"learning_rate": 3.984126984126984e-05,
|
| 67 |
+
"loss": 0.1266,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.93,
|
| 72 |
+
"learning_rate": 3.8253968253968256e-05,
|
| 73 |
+
"loss": 0.1715,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.99,
|
| 78 |
+
"eval_accuracy": 1.0,
|
| 79 |
+
"eval_loss": 2.0537798263831064e-05,
|
| 80 |
+
"eval_runtime": 73.8748,
|
| 81 |
+
"eval_samples_per_second": 135.784,
|
| 82 |
+
"eval_steps_per_second": 4.25,
|
| 83 |
+
"step": 117
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.03,
|
| 87 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 88 |
+
"loss": 0.171,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.11,
|
| 93 |
+
"learning_rate": 3.5079365079365075e-05,
|
| 94 |
+
"loss": 0.1278,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.2,
|
| 99 |
+
"learning_rate": 3.349206349206349e-05,
|
| 100 |
+
"loss": 0.1283,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.28,
|
| 105 |
+
"learning_rate": 3.19047619047619e-05,
|
| 106 |
+
"loss": 0.1861,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.37,
|
| 111 |
+
"learning_rate": 3.0317460317460318e-05,
|
| 112 |
+
"loss": 0.1497,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.45,
|
| 117 |
+
"learning_rate": 2.8730158730158728e-05,
|
| 118 |
+
"loss": 0.1633,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.54,
|
| 123 |
+
"learning_rate": 2.714285714285714e-05,
|
| 124 |
+
"loss": 0.1733,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.62,
|
| 129 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 130 |
+
"loss": 0.1624,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.7,
|
| 135 |
+
"learning_rate": 2.396825396825397e-05,
|
| 136 |
+
"loss": 0.1725,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.79,
|
| 141 |
+
"learning_rate": 2.2380952380952384e-05,
|
| 142 |
+
"loss": 0.172,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.87,
|
| 147 |
+
"learning_rate": 2.0793650793650797e-05,
|
| 148 |
+
"loss": 0.1514,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.96,
|
| 153 |
+
"learning_rate": 1.920634920634921e-05,
|
| 154 |
+
"loss": 0.1194,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.99,
|
| 159 |
+
"eval_accuracy": 1.0,
|
| 160 |
+
"eval_loss": 1.5838317267480306e-05,
|
| 161 |
+
"eval_runtime": 73.1043,
|
| 162 |
+
"eval_samples_per_second": 137.215,
|
| 163 |
+
"eval_steps_per_second": 4.295,
|
| 164 |
+
"step": 234
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.05,
|
| 168 |
+
"learning_rate": 1.761904761904762e-05,
|
| 169 |
+
"loss": 0.1772,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.14,
|
| 174 |
+
"learning_rate": 1.6031746031746033e-05,
|
| 175 |
+
"loss": 0.1811,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.22,
|
| 180 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 181 |
+
"loss": 0.1552,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.31,
|
| 186 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 187 |
+
"loss": 0.1242,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.39,
|
| 192 |
+
"learning_rate": 1.126984126984127e-05,
|
| 193 |
+
"loss": 0.124,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.48,
|
| 198 |
+
"learning_rate": 9.682539682539683e-06,
|
| 199 |
+
"loss": 0.1551,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.56,
|
| 204 |
+
"learning_rate": 8.095238095238097e-06,
|
| 205 |
+
"loss": 0.1902,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.65,
|
| 210 |
+
"learning_rate": 6.507936507936509e-06,
|
| 211 |
+
"loss": 0.1134,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.73,
|
| 216 |
+
"learning_rate": 4.920634920634921e-06,
|
| 217 |
+
"loss": 0.1701,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.82,
|
| 222 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 223 |
+
"loss": 0.134,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.9,
|
| 228 |
+
"learning_rate": 1.7460317460317462e-06,
|
| 229 |
+
"loss": 0.1645,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.99,
|
| 234 |
+
"learning_rate": 1.5873015873015874e-07,
|
| 235 |
+
"loss": 0.1496,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.99,
|
| 240 |
+
"eval_accuracy": 1.0,
|
| 241 |
+
"eval_loss": 1.7963629943551496e-05,
|
| 242 |
+
"eval_runtime": 72.7324,
|
| 243 |
+
"eval_samples_per_second": 137.917,
|
| 244 |
+
"eval_steps_per_second": 4.317,
|
| 245 |
+
"step": 351
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.99,
|
| 249 |
+
"step": 351,
|
| 250 |
+
"total_flos": 8.139769344619315e+17,
|
| 251 |
+
"train_loss": 0.788053667698151,
|
| 252 |
+
"train_runtime": 1008.4422,
|
| 253 |
+
"train_samples_per_second": 44.76,
|
| 254 |
+
"train_steps_per_second": 0.348
|
| 255 |
+
}
|
| 256 |
+
],
|
| 257 |
+
"max_steps": 351,
|
| 258 |
+
"num_train_epochs": 3,
|
| 259 |
+
"total_flos": 8.139769344619315e+17,
|
| 260 |
+
"trial_name": null,
|
| 261 |
+
"trial_params": null
|
| 262 |
+
}
|