Commit
•
53e4a20
1
Parent(s):
8c690f8
End of training
Browse files
all_results.json
CHANGED
|
@@ -1,8 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8635994587280108,
|
| 4 |
+
"eval_loss": 0.3961198627948761,
|
| 5 |
+
"eval_runtime": 43.5124,
|
| 6 |
+
"eval_samples_per_second": 84.918,
|
| 7 |
+
"eval_steps_per_second": 2.666,
|
| 8 |
+
"total_flos": 3.4309418479871754e+18,
|
| 9 |
+
"train_loss": 0.5908640992814216,
|
| 10 |
+
"train_runtime": 1178.2294,
|
| 11 |
+
"train_samples_per_second": 37.625,
|
| 12 |
+
"train_steps_per_second": 0.293
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8635994587280108,
|
| 4 |
+
"eval_loss": 0.3961198627948761,
|
| 5 |
+
"eval_runtime": 43.5124,
|
| 6 |
+
"eval_samples_per_second": 84.918,
|
| 7 |
+
"eval_steps_per_second": 2.666
|
| 8 |
}
|
runs/Apr03_02-13-41_316614c81af4/events.out.tfevents.1648953793.316614c81af4.97.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09df04c8389dcc5b8524bd8a9ce27cb24e584ed4aeb5abd08a1ccde7c1efb10a
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.4309418479871754e+18,
|
| 4 |
+
"train_loss": 0.5908640992814216,
|
| 5 |
+
"train_runtime": 1178.2294,
|
| 6 |
+
"train_samples_per_second": 37.625,
|
| 7 |
+
"train_steps_per_second": 0.293
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8635994587280108,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-bantai_vitv1/checkpoint-345",
|
| 4 |
+
"epoch": 2.995670995670996,
|
| 5 |
+
"global_step": 345,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 13 |
+
"loss": 1.3904,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 2.857142857142857e-05,
|
| 19 |
+
"loss": 1.3115,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 25 |
+
"loss": 1.1847,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 4.9193548387096775e-05,
|
| 31 |
+
"loss": 0.9772,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.43,
|
| 36 |
+
"learning_rate": 4.7580645161290326e-05,
|
| 37 |
+
"loss": 0.8358,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 4.596774193548387e-05,
|
| 43 |
+
"loss": 0.7316,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.61,
|
| 48 |
+
"learning_rate": 4.435483870967742e-05,
|
| 49 |
+
"loss": 0.6985,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.69,
|
| 54 |
+
"learning_rate": 4.2741935483870973e-05,
|
| 55 |
+
"loss": 0.6644,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.78,
|
| 60 |
+
"learning_rate": 4.112903225806452e-05,
|
| 61 |
+
"loss": 0.6267,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.87,
|
| 66 |
+
"learning_rate": 3.951612903225806e-05,
|
| 67 |
+
"loss": 0.5925,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.95,
|
| 72 |
+
"learning_rate": 3.7903225806451614e-05,
|
| 73 |
+
"loss": 0.5997,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 0.7886332882273343,
|
| 79 |
+
"eval_loss": 0.5401414632797241,
|
| 80 |
+
"eval_runtime": 43.7103,
|
| 81 |
+
"eval_samples_per_second": 84.534,
|
| 82 |
+
"eval_steps_per_second": 2.654,
|
| 83 |
+
"step": 115
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.04,
|
| 87 |
+
"learning_rate": 3.6290322580645165e-05,
|
| 88 |
+
"loss": 0.6008,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.13,
|
| 93 |
+
"learning_rate": 3.467741935483872e-05,
|
| 94 |
+
"loss": 0.5502,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.22,
|
| 99 |
+
"learning_rate": 3.306451612903226e-05,
|
| 100 |
+
"loss": 0.5703,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.3,
|
| 105 |
+
"learning_rate": 3.1451612903225806e-05,
|
| 106 |
+
"loss": 0.5032,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.39,
|
| 111 |
+
"learning_rate": 2.9838709677419357e-05,
|
| 112 |
+
"loss": 0.5292,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.48,
|
| 117 |
+
"learning_rate": 2.822580645161291e-05,
|
| 118 |
+
"loss": 0.4798,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.56,
|
| 123 |
+
"learning_rate": 2.661290322580645e-05,
|
| 124 |
+
"loss": 0.4857,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.65,
|
| 129 |
+
"learning_rate": 2.5e-05,
|
| 130 |
+
"loss": 0.4893,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.74,
|
| 135 |
+
"learning_rate": 2.338709677419355e-05,
|
| 136 |
+
"loss": 0.4587,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.82,
|
| 141 |
+
"learning_rate": 2.1774193548387097e-05,
|
| 142 |
+
"loss": 0.4735,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.91,
|
| 147 |
+
"learning_rate": 2.0161290322580645e-05,
|
| 148 |
+
"loss": 0.486,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 1.8548387096774193e-05,
|
| 154 |
+
"loss": 0.4696,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0,
|
| 159 |
+
"eval_accuracy": 0.8481732070365359,
|
| 160 |
+
"eval_loss": 0.4410068094730377,
|
| 161 |
+
"eval_runtime": 43.5298,
|
| 162 |
+
"eval_samples_per_second": 84.884,
|
| 163 |
+
"eval_steps_per_second": 2.665,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.09,
|
| 168 |
+
"learning_rate": 1.693548387096774e-05,
|
| 169 |
+
"loss": 0.49,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.17,
|
| 174 |
+
"learning_rate": 1.5322580645161292e-05,
|
| 175 |
+
"loss": 0.397,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.26,
|
| 180 |
+
"learning_rate": 1.3709677419354839e-05,
|
| 181 |
+
"loss": 0.4055,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.35,
|
| 186 |
+
"learning_rate": 1.2096774193548388e-05,
|
| 187 |
+
"loss": 0.4111,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.43,
|
| 192 |
+
"learning_rate": 1.0483870967741936e-05,
|
| 193 |
+
"loss": 0.4216,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.52,
|
| 198 |
+
"learning_rate": 8.870967741935484e-06,
|
| 199 |
+
"loss": 0.4084,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.61,
|
| 204 |
+
"learning_rate": 7.258064516129033e-06,
|
| 205 |
+
"loss": 0.3866,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.69,
|
| 210 |
+
"learning_rate": 5.64516129032258e-06,
|
| 211 |
+
"loss": 0.3881,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.78,
|
| 216 |
+
"learning_rate": 4.032258064516129e-06,
|
| 217 |
+
"loss": 0.3809,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.87,
|
| 222 |
+
"learning_rate": 2.4193548387096776e-06,
|
| 223 |
+
"loss": 0.391,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.95,
|
| 228 |
+
"learning_rate": 8.064516129032258e-07,
|
| 229 |
+
"loss": 0.4019,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.0,
|
| 234 |
+
"eval_accuracy": 0.8635994587280108,
|
| 235 |
+
"eval_loss": 0.3961198627948761,
|
| 236 |
+
"eval_runtime": 43.4324,
|
| 237 |
+
"eval_samples_per_second": 85.075,
|
| 238 |
+
"eval_steps_per_second": 2.671,
|
| 239 |
+
"step": 345
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.0,
|
| 243 |
+
"step": 345,
|
| 244 |
+
"total_flos": 3.4309418479871754e+18,
|
| 245 |
+
"train_loss": 0.5908640992814216,
|
| 246 |
+
"train_runtime": 1178.2294,
|
| 247 |
+
"train_samples_per_second": 37.625,
|
| 248 |
+
"train_steps_per_second": 0.293
|
| 249 |
+
}
|
| 250 |
+
],
|
| 251 |
+
"max_steps": 345,
|
| 252 |
+
"num_train_epochs": 3,
|
| 253 |
+
"total_flos": 3.4309418479871754e+18,
|
| 254 |
+
"trial_name": null,
|
| 255 |
+
"trial_params": null
|
| 256 |
+
}
|