Commit
•
eff6d59
1
Parent(s):
3216a1b
Training in progress, epoch 0
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.46,
|
| 3 |
+
"total_flos": 2.967245304616526e+18,
|
| 4 |
+
"train_loss": 1.0191877312130397,
|
| 5 |
+
"train_runtime": 1137.2862,
|
| 6 |
+
"train_samples_per_second": 20.698,
|
| 7 |
+
"train_steps_per_second": 0.158
|
| 8 |
+
}
|
runs/Jul04_18-06-52_2df985b450cf/events.out.tfevents.1688495350.2df985b450cf.3039.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b6fa5f88f522c99459ea3309f3d264385c88e6b6f2efce2bee1827071aa5740
|
| 3 |
+
size 4941
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.46,
|
| 3 |
+
"total_flos": 2.967245304616526e+18,
|
| 4 |
+
"train_loss": 1.0191877312130397,
|
| 5 |
+
"train_runtime": 1137.2862,
|
| 6 |
+
"train_samples_per_second": 20.698,
|
| 7 |
+
"train_steps_per_second": 0.158
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7220338983050848,
|
| 3 |
+
"best_model_checkpoint": "swinv2-large-patch4-window12-192-22k-finetuned-eurosat-50/checkpoint-157",
|
| 4 |
+
"epoch": 19.45945945945946,
|
| 5 |
+
"global_step": 180,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.97,
|
| 12 |
+
"eval_accuracy": 0.3728813559322034,
|
| 13 |
+
"eval_loss": 1.6984361410140991,
|
| 14 |
+
"eval_runtime": 5.7347,
|
| 15 |
+
"eval_samples_per_second": 51.441,
|
| 16 |
+
"eval_steps_per_second": 1.744,
|
| 17 |
+
"step": 9
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.95,
|
| 21 |
+
"eval_accuracy": 0.488135593220339,
|
| 22 |
+
"eval_loss": 1.5150169134140015,
|
| 23 |
+
"eval_runtime": 5.5319,
|
| 24 |
+
"eval_samples_per_second": 53.327,
|
| 25 |
+
"eval_steps_per_second": 1.808,
|
| 26 |
+
"step": 18
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.16,
|
| 30 |
+
"learning_rate": 4.46927374301676e-06,
|
| 31 |
+
"loss": 1.6944,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.92,
|
| 36 |
+
"eval_accuracy": 0.5389830508474577,
|
| 37 |
+
"eval_loss": 1.3304221630096436,
|
| 38 |
+
"eval_runtime": 5.5883,
|
| 39 |
+
"eval_samples_per_second": 52.789,
|
| 40 |
+
"eval_steps_per_second": 1.789,
|
| 41 |
+
"step": 27
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 4.0,
|
| 45 |
+
"eval_accuracy": 0.6,
|
| 46 |
+
"eval_loss": 1.1760876178741455,
|
| 47 |
+
"eval_runtime": 5.4945,
|
| 48 |
+
"eval_samples_per_second": 53.69,
|
| 49 |
+
"eval_steps_per_second": 1.82,
|
| 50 |
+
"step": 37
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.32,
|
| 54 |
+
"learning_rate": 3.910614525139665e-06,
|
| 55 |
+
"loss": 1.3633,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.97,
|
| 60 |
+
"eval_accuracy": 0.6372881355932203,
|
| 61 |
+
"eval_loss": 1.0587867498397827,
|
| 62 |
+
"eval_runtime": 5.5671,
|
| 63 |
+
"eval_samples_per_second": 52.99,
|
| 64 |
+
"eval_steps_per_second": 1.796,
|
| 65 |
+
"step": 46
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.95,
|
| 69 |
+
"eval_accuracy": 0.6474576271186441,
|
| 70 |
+
"eval_loss": 0.9951748847961426,
|
| 71 |
+
"eval_runtime": 5.5905,
|
| 72 |
+
"eval_samples_per_second": 52.768,
|
| 73 |
+
"eval_steps_per_second": 1.789,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.49,
|
| 78 |
+
"learning_rate": 3.35195530726257e-06,
|
| 79 |
+
"loss": 1.1208,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.92,
|
| 84 |
+
"eval_accuracy": 0.6610169491525424,
|
| 85 |
+
"eval_loss": 0.9326281547546387,
|
| 86 |
+
"eval_runtime": 5.5768,
|
| 87 |
+
"eval_samples_per_second": 52.898,
|
| 88 |
+
"eval_steps_per_second": 1.793,
|
| 89 |
+
"step": 64
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 8.0,
|
| 93 |
+
"eval_accuracy": 0.6711864406779661,
|
| 94 |
+
"eval_loss": 0.8784985542297363,
|
| 95 |
+
"eval_runtime": 5.506,
|
| 96 |
+
"eval_samples_per_second": 53.578,
|
| 97 |
+
"eval_steps_per_second": 1.816,
|
| 98 |
+
"step": 74
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.65,
|
| 102 |
+
"learning_rate": 2.793296089385475e-06,
|
| 103 |
+
"loss": 0.9891,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.97,
|
| 108 |
+
"eval_accuracy": 0.6745762711864407,
|
| 109 |
+
"eval_loss": 0.8478348851203918,
|
| 110 |
+
"eval_runtime": 5.4498,
|
| 111 |
+
"eval_samples_per_second": 54.13,
|
| 112 |
+
"eval_steps_per_second": 1.835,
|
| 113 |
+
"step": 83
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 9.95,
|
| 117 |
+
"eval_accuracy": 0.6847457627118644,
|
| 118 |
+
"eval_loss": 0.8144229054450989,
|
| 119 |
+
"eval_runtime": 5.4795,
|
| 120 |
+
"eval_samples_per_second": 53.837,
|
| 121 |
+
"eval_steps_per_second": 1.825,
|
| 122 |
+
"step": 92
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.81,
|
| 126 |
+
"learning_rate": 2.23463687150838e-06,
|
| 127 |
+
"loss": 0.9011,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.92,
|
| 132 |
+
"eval_accuracy": 0.7016949152542373,
|
| 133 |
+
"eval_loss": 0.7773841023445129,
|
| 134 |
+
"eval_runtime": 5.5651,
|
| 135 |
+
"eval_samples_per_second": 53.009,
|
| 136 |
+
"eval_steps_per_second": 1.797,
|
| 137 |
+
"step": 101
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 12.0,
|
| 141 |
+
"eval_accuracy": 0.6983050847457627,
|
| 142 |
+
"eval_loss": 0.7567483186721802,
|
| 143 |
+
"eval_runtime": 5.5809,
|
| 144 |
+
"eval_samples_per_second": 52.859,
|
| 145 |
+
"eval_steps_per_second": 1.792,
|
| 146 |
+
"step": 111
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 12.97,
|
| 150 |
+
"learning_rate": 1.675977653631285e-06,
|
| 151 |
+
"loss": 0.8143,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.97,
|
| 156 |
+
"eval_accuracy": 0.6949152542372882,
|
| 157 |
+
"eval_loss": 0.7525233626365662,
|
| 158 |
+
"eval_runtime": 5.5142,
|
| 159 |
+
"eval_samples_per_second": 53.498,
|
| 160 |
+
"eval_steps_per_second": 1.813,
|
| 161 |
+
"step": 120
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 13.95,
|
| 165 |
+
"eval_accuracy": 0.7050847457627119,
|
| 166 |
+
"eval_loss": 0.7308651804924011,
|
| 167 |
+
"eval_runtime": 5.4401,
|
| 168 |
+
"eval_samples_per_second": 54.227,
|
| 169 |
+
"eval_steps_per_second": 1.838,
|
| 170 |
+
"step": 129
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.92,
|
| 174 |
+
"eval_accuracy": 0.711864406779661,
|
| 175 |
+
"eval_loss": 0.7140872478485107,
|
| 176 |
+
"eval_runtime": 5.575,
|
| 177 |
+
"eval_samples_per_second": 52.915,
|
| 178 |
+
"eval_steps_per_second": 1.794,
|
| 179 |
+
"step": 138
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 15.14,
|
| 183 |
+
"learning_rate": 1.11731843575419e-06,
|
| 184 |
+
"loss": 0.7926,
|
| 185 |
+
"step": 140
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 16.0,
|
| 189 |
+
"eval_accuracy": 0.7186440677966102,
|
| 190 |
+
"eval_loss": 0.7095121741294861,
|
| 191 |
+
"eval_runtime": 5.5218,
|
| 192 |
+
"eval_samples_per_second": 53.424,
|
| 193 |
+
"eval_steps_per_second": 1.811,
|
| 194 |
+
"step": 148
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 16.97,
|
| 198 |
+
"eval_accuracy": 0.7220338983050848,
|
| 199 |
+
"eval_loss": 0.7057121396064758,
|
| 200 |
+
"eval_runtime": 5.5266,
|
| 201 |
+
"eval_samples_per_second": 53.378,
|
| 202 |
+
"eval_steps_per_second": 1.809,
|
| 203 |
+
"step": 157
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 17.3,
|
| 207 |
+
"learning_rate": 5.58659217877095e-07,
|
| 208 |
+
"loss": 0.7439,
|
| 209 |
+
"step": 160
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 17.95,
|
| 213 |
+
"eval_accuracy": 0.7220338983050848,
|
| 214 |
+
"eval_loss": 0.6987767219543457,
|
| 215 |
+
"eval_runtime": 5.5133,
|
| 216 |
+
"eval_samples_per_second": 53.507,
|
| 217 |
+
"eval_steps_per_second": 1.814,
|
| 218 |
+
"step": 166
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 18.92,
|
| 222 |
+
"eval_accuracy": 0.7220338983050848,
|
| 223 |
+
"eval_loss": 0.6967313885688782,
|
| 224 |
+
"eval_runtime": 5.4926,
|
| 225 |
+
"eval_samples_per_second": 53.709,
|
| 226 |
+
"eval_steps_per_second": 1.821,
|
| 227 |
+
"step": 175
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 19.46,
|
| 231 |
+
"learning_rate": 0.0,
|
| 232 |
+
"loss": 0.7533,
|
| 233 |
+
"step": 180
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 19.46,
|
| 237 |
+
"eval_accuracy": 0.7220338983050848,
|
| 238 |
+
"eval_loss": 0.6966923475265503,
|
| 239 |
+
"eval_runtime": 5.5104,
|
| 240 |
+
"eval_samples_per_second": 53.535,
|
| 241 |
+
"eval_steps_per_second": 1.815,
|
| 242 |
+
"step": 180
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 19.46,
|
| 246 |
+
"step": 180,
|
| 247 |
+
"total_flos": 2.967245304616526e+18,
|
| 248 |
+
"train_loss": 1.0191877312130397,
|
| 249 |
+
"train_runtime": 1137.2862,
|
| 250 |
+
"train_samples_per_second": 20.698,
|
| 251 |
+
"train_steps_per_second": 0.158
|
| 252 |
+
}
|
| 253 |
+
],
|
| 254 |
+
"max_steps": 180,
|
| 255 |
+
"num_train_epochs": 20,
|
| 256 |
+
"total_flos": 2.967245304616526e+18,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|