Commit
•
c33e3e8
1
Parent(s):
4363216
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.9768518518518519,
|
| 4 |
+
"eval_loss": 0.09591178596019745,
|
| 5 |
+
"eval_runtime": 35.0128,
|
| 6 |
+
"eval_samples_per_second": 154.229,
|
| 7 |
+
"eval_steps_per_second": 4.827,
|
| 8 |
+
"total_flos": 1.0833412255308841e+18,
|
| 9 |
+
"train_loss": 0.5169055745715186,
|
| 10 |
+
"train_runtime": 771.9486,
|
| 11 |
+
"train_samples_per_second": 55.962,
|
| 12 |
+
"train_steps_per_second": 0.435
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.9768518518518519,
|
| 4 |
+
"eval_loss": 0.09591178596019745,
|
| 5 |
+
"eval_runtime": 35.0128,
|
| 6 |
+
"eval_samples_per_second": 154.229,
|
| 7 |
+
"eval_steps_per_second": 4.827
|
| 8 |
+
}
|
runs/Dec10_11-42-38_b3b6c3daa0f1/events.out.tfevents.1670673588.b3b6c3daa0f1.74.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0523dcd7dd2defe0687594d6045ae0081c0f31d3524132c0ee504decc5af2fb
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.0833412255308841e+18,
|
| 4 |
+
"train_loss": 0.5169055745715186,
|
| 5 |
+
"train_runtime": 771.9486,
|
| 6 |
+
"train_samples_per_second": 55.962,
|
| 7 |
+
"train_steps_per_second": 0.435
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9768518518518519,
|
| 3 |
+
"best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat/checkpoint-336",
|
| 4 |
+
"epoch": 1.9955555555555555,
|
| 5 |
+
"global_step": 336,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 13 |
+
"loss": 2.3032,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 19 |
+
"loss": 2.2221,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 4.411764705882353e-05,
|
| 25 |
+
"loss": 2.0497,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 4.900662251655629e-05,
|
| 31 |
+
"loss": 1.7565,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 4.735099337748345e-05,
|
| 37 |
+
"loss": 1.4608,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 4.56953642384106e-05,
|
| 43 |
+
"loss": 1.1119,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41,
|
| 48 |
+
"learning_rate": 4.403973509933775e-05,
|
| 49 |
+
"loss": 0.8738,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.47,
|
| 54 |
+
"learning_rate": 4.23841059602649e-05,
|
| 55 |
+
"loss": 0.686,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.53,
|
| 60 |
+
"learning_rate": 4.0728476821192055e-05,
|
| 61 |
+
"loss": 0.5653,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.59,
|
| 66 |
+
"learning_rate": 3.907284768211921e-05,
|
| 67 |
+
"loss": 0.4671,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.65,
|
| 72 |
+
"learning_rate": 3.741721854304636e-05,
|
| 73 |
+
"loss": 0.3921,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.71,
|
| 78 |
+
"learning_rate": 3.576158940397351e-05,
|
| 79 |
+
"loss": 0.3261,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.77,
|
| 84 |
+
"learning_rate": 3.410596026490066e-05,
|
| 85 |
+
"loss": 0.2757,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.83,
|
| 90 |
+
"learning_rate": 3.2450331125827816e-05,
|
| 91 |
+
"loss": 0.262,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.89,
|
| 96 |
+
"learning_rate": 3.079470198675497e-05,
|
| 97 |
+
"loss": 0.2301,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.95,
|
| 102 |
+
"learning_rate": 2.913907284768212e-05,
|
| 103 |
+
"loss": 0.206,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0,
|
| 108 |
+
"eval_accuracy": 0.9612962962962963,
|
| 109 |
+
"eval_loss": 0.17533423006534576,
|
| 110 |
+
"eval_runtime": 35.5662,
|
| 111 |
+
"eval_samples_per_second": 151.829,
|
| 112 |
+
"eval_steps_per_second": 4.752,
|
| 113 |
+
"step": 168
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.01,
|
| 117 |
+
"learning_rate": 2.7483443708609274e-05,
|
| 118 |
+
"loss": 0.1966,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.07,
|
| 123 |
+
"learning_rate": 2.5827814569536424e-05,
|
| 124 |
+
"loss": 0.1539,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.13,
|
| 129 |
+
"learning_rate": 2.4172185430463578e-05,
|
| 130 |
+
"loss": 0.1506,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.19,
|
| 135 |
+
"learning_rate": 2.2516556291390732e-05,
|
| 136 |
+
"loss": 0.1292,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.25,
|
| 141 |
+
"learning_rate": 2.0860927152317882e-05,
|
| 142 |
+
"loss": 0.1197,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.31,
|
| 147 |
+
"learning_rate": 1.9205298013245036e-05,
|
| 148 |
+
"loss": 0.1274,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.37,
|
| 153 |
+
"learning_rate": 1.7549668874172186e-05,
|
| 154 |
+
"loss": 0.1167,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.43,
|
| 159 |
+
"learning_rate": 1.589403973509934e-05,
|
| 160 |
+
"loss": 0.1136,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.49,
|
| 165 |
+
"learning_rate": 1.4238410596026492e-05,
|
| 166 |
+
"loss": 0.1105,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.55,
|
| 171 |
+
"learning_rate": 1.2582781456953644e-05,
|
| 172 |
+
"loss": 0.1294,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.6,
|
| 177 |
+
"learning_rate": 1.0927152317880796e-05,
|
| 178 |
+
"loss": 0.1268,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.66,
|
| 183 |
+
"learning_rate": 9.271523178807948e-06,
|
| 184 |
+
"loss": 0.1165,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.72,
|
| 189 |
+
"learning_rate": 7.6158940397350995e-06,
|
| 190 |
+
"loss": 0.1092,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.78,
|
| 195 |
+
"learning_rate": 5.9602649006622515e-06,
|
| 196 |
+
"loss": 0.1002,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.84,
|
| 201 |
+
"learning_rate": 4.304635761589404e-06,
|
| 202 |
+
"loss": 0.1134,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.9,
|
| 207 |
+
"learning_rate": 2.6490066225165563e-06,
|
| 208 |
+
"loss": 0.1148,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.96,
|
| 213 |
+
"learning_rate": 9.933774834437087e-07,
|
| 214 |
+
"loss": 0.0904,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.0,
|
| 219 |
+
"eval_accuracy": 0.9768518518518519,
|
| 220 |
+
"eval_loss": 0.09591178596019745,
|
| 221 |
+
"eval_runtime": 34.4727,
|
| 222 |
+
"eval_samples_per_second": 156.646,
|
| 223 |
+
"eval_steps_per_second": 4.902,
|
| 224 |
+
"step": 336
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.0,
|
| 228 |
+
"step": 336,
|
| 229 |
+
"total_flos": 1.0833412255308841e+18,
|
| 230 |
+
"train_loss": 0.5169055745715186,
|
| 231 |
+
"train_runtime": 771.9486,
|
| 232 |
+
"train_samples_per_second": 55.962,
|
| 233 |
+
"train_steps_per_second": 0.435
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"max_steps": 336,
|
| 237 |
+
"num_train_epochs": 2,
|
| 238 |
+
"total_flos": 1.0833412255308841e+18,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": null
|
| 241 |
+
}
|