Commit
•
7749757
1
Parent(s):
0689031
Model save
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +232 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.138628448046035e+18,
|
| 4 |
+
"train_loss": 1.7424827136245429,
|
| 5 |
+
"train_runtime": 2056.1169,
|
| 6 |
+
"train_samples_per_second": 19.041,
|
| 7 |
+
"train_steps_per_second": 0.149
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.138628448046035e+18,
|
| 4 |
+
"train_loss": 1.7424827136245429,
|
| 5 |
+
"train_runtime": 2056.1169,
|
| 6 |
+
"train_samples_per_second": 19.041,
|
| 7 |
+
"train_steps_per_second": 0.149
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9944827586206897,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch32-224-in21k-finetuned-eurosat/checkpoint-306",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 306,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 2.258064516129032e-05,
|
| 13 |
+
"loss": 3.3592,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 3.870967741935484e-05,
|
| 19 |
+
"loss": 3.3092,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.29,
|
| 24 |
+
"learning_rate": 4.945454545454546e-05,
|
| 25 |
+
"loss": 3.2009,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.39,
|
| 30 |
+
"learning_rate": 4.763636363636364e-05,
|
| 31 |
+
"loss": 3.0279,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.49,
|
| 36 |
+
"learning_rate": 4.581818181818182e-05,
|
| 37 |
+
"loss": 2.796,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.59,
|
| 42 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 43 |
+
"loss": 2.5733,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.69,
|
| 48 |
+
"learning_rate": 4.218181818181818e-05,
|
| 49 |
+
"loss": 2.382,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.78,
|
| 54 |
+
"learning_rate": 4.0363636363636367e-05,
|
| 55 |
+
"loss": 2.1719,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.88,
|
| 60 |
+
"learning_rate": 3.8545454545454544e-05,
|
| 61 |
+
"loss": 2.0397,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.98,
|
| 66 |
+
"learning_rate": 3.672727272727273e-05,
|
| 67 |
+
"loss": 1.8903,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.9517241379310345,
|
| 73 |
+
"eval_loss": 1.5728360414505005,
|
| 74 |
+
"eval_runtime": 172.9242,
|
| 75 |
+
"eval_samples_per_second": 8.385,
|
| 76 |
+
"eval_steps_per_second": 0.266,
|
| 77 |
+
"step": 102
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.08,
|
| 81 |
+
"learning_rate": 3.490909090909091e-05,
|
| 82 |
+
"loss": 1.7733,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.18,
|
| 87 |
+
"learning_rate": 3.3090909090909095e-05,
|
| 88 |
+
"loss": 1.6463,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.27,
|
| 93 |
+
"learning_rate": 3.127272727272728e-05,
|
| 94 |
+
"loss": 1.6179,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.37,
|
| 99 |
+
"learning_rate": 2.9454545454545456e-05,
|
| 100 |
+
"loss": 1.5367,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.47,
|
| 105 |
+
"learning_rate": 2.7636363636363636e-05,
|
| 106 |
+
"loss": 1.47,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.57,
|
| 111 |
+
"learning_rate": 2.581818181818182e-05,
|
| 112 |
+
"loss": 1.4046,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.67,
|
| 117 |
+
"learning_rate": 2.4e-05,
|
| 118 |
+
"loss": 1.3476,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.76,
|
| 123 |
+
"learning_rate": 2.2181818181818184e-05,
|
| 124 |
+
"loss": 1.3275,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.86,
|
| 129 |
+
"learning_rate": 2.0363636363636365e-05,
|
| 130 |
+
"loss": 1.2839,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.96,
|
| 135 |
+
"learning_rate": 1.8545454545454545e-05,
|
| 136 |
+
"loss": 1.2226,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.0,
|
| 141 |
+
"eval_accuracy": 0.9917241379310345,
|
| 142 |
+
"eval_loss": 0.9373832941055298,
|
| 143 |
+
"eval_runtime": 9.4058,
|
| 144 |
+
"eval_samples_per_second": 154.161,
|
| 145 |
+
"eval_steps_per_second": 4.891,
|
| 146 |
+
"step": 204
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.06,
|
| 150 |
+
"learning_rate": 1.672727272727273e-05,
|
| 151 |
+
"loss": 1.1917,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.16,
|
| 156 |
+
"learning_rate": 1.4909090909090908e-05,
|
| 157 |
+
"loss": 1.1838,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.25,
|
| 162 |
+
"learning_rate": 1.3090909090909093e-05,
|
| 163 |
+
"loss": 1.1872,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.35,
|
| 168 |
+
"learning_rate": 1.1272727272727274e-05,
|
| 169 |
+
"loss": 1.1204,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.45,
|
| 174 |
+
"learning_rate": 9.454545454545454e-06,
|
| 175 |
+
"loss": 1.1191,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.55,
|
| 180 |
+
"learning_rate": 7.636363636363638e-06,
|
| 181 |
+
"loss": 1.1262,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.65,
|
| 186 |
+
"learning_rate": 5.8181818181818185e-06,
|
| 187 |
+
"loss": 1.0852,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.75,
|
| 192 |
+
"learning_rate": 4.000000000000001e-06,
|
| 193 |
+
"loss": 1.0953,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.84,
|
| 198 |
+
"learning_rate": 2.181818181818182e-06,
|
| 199 |
+
"loss": 1.0887,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.94,
|
| 204 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 205 |
+
"loss": 1.1069,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.0,
|
| 210 |
+
"eval_accuracy": 0.9944827586206897,
|
| 211 |
+
"eval_loss": 0.8114762902259827,
|
| 212 |
+
"eval_runtime": 9.5561,
|
| 213 |
+
"eval_samples_per_second": 151.736,
|
| 214 |
+
"eval_steps_per_second": 4.814,
|
| 215 |
+
"step": 306
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.0,
|
| 219 |
+
"step": 306,
|
| 220 |
+
"total_flos": 3.138628448046035e+18,
|
| 221 |
+
"train_loss": 1.7424827136245429,
|
| 222 |
+
"train_runtime": 2056.1169,
|
| 223 |
+
"train_samples_per_second": 19.041,
|
| 224 |
+
"train_steps_per_second": 0.149
|
| 225 |
+
}
|
| 226 |
+
],
|
| 227 |
+
"max_steps": 306,
|
| 228 |
+
"num_train_epochs": 3,
|
| 229 |
+
"total_flos": 3.138628448046035e+18,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|