End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 9.558848432789091e-06,
|
| 5 |
+
"eval_runtime": 31.5186,
|
| 6 |
+
"eval_samples_per_second": 57.109,
|
| 7 |
+
"eval_steps_per_second": 1.808,
|
| 8 |
+
"total_flos": 1.2014751945240576e+18,
|
| 9 |
+
"train_loss": 0.17176837376540616,
|
| 10 |
+
"train_runtime": 8690.1401,
|
| 11 |
+
"train_samples_per_second": 5.591,
|
| 12 |
+
"train_steps_per_second": 0.043
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 9.558848432789091e-06,
|
| 5 |
+
"eval_runtime": 31.5186,
|
| 6 |
+
"eval_samples_per_second": 57.109,
|
| 7 |
+
"eval_steps_per_second": 1.808
|
| 8 |
+
}
|
runs/Apr15_05-14-38_d3d1cd9553d4/events.out.tfevents.1713167236.d3d1cd9553d4.1260.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6aa408b18c54161e5ccf1664e711de1daa7e90613019f5560d95ac637b10b0e
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"total_flos": 1.2014751945240576e+18,
|
| 4 |
+
"train_loss": 0.17176837376540616,
|
| 5 |
+
"train_runtime": 8690.1401,
|
| 6 |
+
"train_samples_per_second": 5.591,
|
| 7 |
+
"train_steps_per_second": 0.043
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-378",
|
| 4 |
+
"epoch": 2.9822485207100593,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 378,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 12.153364181518555,
|
| 14 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 15 |
+
"loss": 2.1615,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16,
|
| 20 |
+
"grad_norm": 16.816362380981445,
|
| 21 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 22 |
+
"loss": 1.8847,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24,
|
| 27 |
+
"grad_norm": 18.271907806396484,
|
| 28 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 29 |
+
"loss": 1.2194,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32,
|
| 34 |
+
"grad_norm": 5.709053039550781,
|
| 35 |
+
"learning_rate": 4.970588235294118e-05,
|
| 36 |
+
"loss": 0.5036,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.39,
|
| 41 |
+
"grad_norm": 5.6657609939575195,
|
| 42 |
+
"learning_rate": 4.823529411764706e-05,
|
| 43 |
+
"loss": 0.1547,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"grad_norm": 4.165065288543701,
|
| 49 |
+
"learning_rate": 4.6764705882352944e-05,
|
| 50 |
+
"loss": 0.0731,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.55,
|
| 55 |
+
"grad_norm": 8.897403717041016,
|
| 56 |
+
"learning_rate": 4.5294117647058826e-05,
|
| 57 |
+
"loss": 0.0448,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.63,
|
| 62 |
+
"grad_norm": 2.7607221603393555,
|
| 63 |
+
"learning_rate": 4.382352941176471e-05,
|
| 64 |
+
"loss": 0.0227,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.71,
|
| 69 |
+
"grad_norm": 2.4922943115234375,
|
| 70 |
+
"learning_rate": 4.235294117647059e-05,
|
| 71 |
+
"loss": 0.0216,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.79,
|
| 76 |
+
"grad_norm": 1.6621469259262085,
|
| 77 |
+
"learning_rate": 4.0882352941176474e-05,
|
| 78 |
+
"loss": 0.0332,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.87,
|
| 83 |
+
"grad_norm": 6.23069953918457,
|
| 84 |
+
"learning_rate": 3.9411764705882356e-05,
|
| 85 |
+
"loss": 0.0277,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.95,
|
| 90 |
+
"grad_norm": 2.660862684249878,
|
| 91 |
+
"learning_rate": 3.794117647058824e-05,
|
| 92 |
+
"loss": 0.0194,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.99,
|
| 97 |
+
"eval_accuracy": 0.9994444444444445,
|
| 98 |
+
"eval_loss": 0.002504603238776326,
|
| 99 |
+
"eval_runtime": 853.0633,
|
| 100 |
+
"eval_samples_per_second": 2.11,
|
| 101 |
+
"eval_steps_per_second": 0.067,
|
| 102 |
+
"step": 126
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.03,
|
| 106 |
+
"grad_norm": 3.3311333656311035,
|
| 107 |
+
"learning_rate": 3.6470588235294114e-05,
|
| 108 |
+
"loss": 0.0191,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.1,
|
| 113 |
+
"grad_norm": 1.546949028968811,
|
| 114 |
+
"learning_rate": 3.5e-05,
|
| 115 |
+
"loss": 0.0193,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.18,
|
| 120 |
+
"grad_norm": 2.039259910583496,
|
| 121 |
+
"learning_rate": 3.352941176470588e-05,
|
| 122 |
+
"loss": 0.0213,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.26,
|
| 127 |
+
"grad_norm": 2.8678247928619385,
|
| 128 |
+
"learning_rate": 3.205882352941177e-05,
|
| 129 |
+
"loss": 0.017,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.34,
|
| 134 |
+
"grad_norm": 1.6331835985183716,
|
| 135 |
+
"learning_rate": 3.058823529411765e-05,
|
| 136 |
+
"loss": 0.0221,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.42,
|
| 141 |
+
"grad_norm": 0.7777595520019531,
|
| 142 |
+
"learning_rate": 2.9117647058823534e-05,
|
| 143 |
+
"loss": 0.0206,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.5,
|
| 148 |
+
"grad_norm": 2.2770392894744873,
|
| 149 |
+
"learning_rate": 2.7647058823529416e-05,
|
| 150 |
+
"loss": 0.0203,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.58,
|
| 155 |
+
"grad_norm": 1.0933735370635986,
|
| 156 |
+
"learning_rate": 2.6176470588235295e-05,
|
| 157 |
+
"loss": 0.0233,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.66,
|
| 162 |
+
"grad_norm": 0.9536008238792419,
|
| 163 |
+
"learning_rate": 2.4705882352941178e-05,
|
| 164 |
+
"loss": 0.0139,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.74,
|
| 169 |
+
"grad_norm": 0.19179974496364594,
|
| 170 |
+
"learning_rate": 2.323529411764706e-05,
|
| 171 |
+
"loss": 0.007,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.81,
|
| 176 |
+
"grad_norm": 0.12005764245986938,
|
| 177 |
+
"learning_rate": 2.1764705882352943e-05,
|
| 178 |
+
"loss": 0.0105,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.89,
|
| 183 |
+
"grad_norm": 2.346966028213501,
|
| 184 |
+
"learning_rate": 2.0294117647058825e-05,
|
| 185 |
+
"loss": 0.0144,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.97,
|
| 190 |
+
"grad_norm": 1.2424992322921753,
|
| 191 |
+
"learning_rate": 1.8823529411764708e-05,
|
| 192 |
+
"loss": 0.0137,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.0,
|
| 197 |
+
"eval_accuracy": 0.9994444444444445,
|
| 198 |
+
"eval_loss": 0.0009298253571614623,
|
| 199 |
+
"eval_runtime": 31.8455,
|
| 200 |
+
"eval_samples_per_second": 56.523,
|
| 201 |
+
"eval_steps_per_second": 1.79,
|
| 202 |
+
"step": 253
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.05,
|
| 206 |
+
"grad_norm": 1.2912344932556152,
|
| 207 |
+
"learning_rate": 1.735294117647059e-05,
|
| 208 |
+
"loss": 0.0119,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.13,
|
| 213 |
+
"grad_norm": 0.5564313530921936,
|
| 214 |
+
"learning_rate": 1.588235294117647e-05,
|
| 215 |
+
"loss": 0.006,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.21,
|
| 220 |
+
"grad_norm": 0.05754239112138748,
|
| 221 |
+
"learning_rate": 1.4411764705882352e-05,
|
| 222 |
+
"loss": 0.0068,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.29,
|
| 227 |
+
"grad_norm": 0.031185824424028397,
|
| 228 |
+
"learning_rate": 1.2941176470588238e-05,
|
| 229 |
+
"loss": 0.0063,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.37,
|
| 234 |
+
"grad_norm": 0.09058652073144913,
|
| 235 |
+
"learning_rate": 1.1470588235294118e-05,
|
| 236 |
+
"loss": 0.0119,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.45,
|
| 241 |
+
"grad_norm": 0.13693469762802124,
|
| 242 |
+
"learning_rate": 1e-05,
|
| 243 |
+
"loss": 0.0055,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.52,
|
| 248 |
+
"grad_norm": 2.508786201477051,
|
| 249 |
+
"learning_rate": 8.529411764705883e-06,
|
| 250 |
+
"loss": 0.01,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.6,
|
| 255 |
+
"grad_norm": 0.2263449877500534,
|
| 256 |
+
"learning_rate": 7.058823529411765e-06,
|
| 257 |
+
"loss": 0.0059,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.68,
|
| 262 |
+
"grad_norm": 0.004928161855787039,
|
| 263 |
+
"learning_rate": 5.588235294117647e-06,
|
| 264 |
+
"loss": 0.0064,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.76,
|
| 269 |
+
"grad_norm": 3.029522180557251,
|
| 270 |
+
"learning_rate": 4.11764705882353e-06,
|
| 271 |
+
"loss": 0.011,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.84,
|
| 276 |
+
"grad_norm": 0.02349434234201908,
|
| 277 |
+
"learning_rate": 2.647058823529412e-06,
|
| 278 |
+
"loss": 0.0114,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.92,
|
| 283 |
+
"grad_norm": 1.1028828620910645,
|
| 284 |
+
"learning_rate": 1.1764705882352942e-06,
|
| 285 |
+
"loss": 0.0075,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.98,
|
| 290 |
+
"eval_accuracy": 1.0,
|
| 291 |
+
"eval_loss": 9.558848432789091e-06,
|
| 292 |
+
"eval_runtime": 31.5287,
|
| 293 |
+
"eval_samples_per_second": 57.091,
|
| 294 |
+
"eval_steps_per_second": 1.808,
|
| 295 |
+
"step": 378
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.98,
|
| 299 |
+
"step": 378,
|
| 300 |
+
"total_flos": 1.2014751945240576e+18,
|
| 301 |
+
"train_loss": 0.17176837376540616,
|
| 302 |
+
"train_runtime": 8690.1401,
|
| 303 |
+
"train_samples_per_second": 5.591,
|
| 304 |
+
"train_steps_per_second": 0.043
|
| 305 |
+
}
|
| 306 |
+
],
|
| 307 |
+
"logging_steps": 10,
|
| 308 |
+
"max_steps": 378,
|
| 309 |
+
"num_input_tokens_seen": 0,
|
| 310 |
+
"num_train_epochs": 3,
|
| 311 |
+
"save_steps": 500,
|
| 312 |
+
"total_flos": 1.2014751945240576e+18,
|
| 313 |
+
"train_batch_size": 32,
|
| 314 |
+
"trial_name": null,
|
| 315 |
+
"trial_params": null
|
| 316 |
+
}
|