End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.98,
|
| 3 |
+
"eval_accuracy": 0.9955262036642523,
|
| 4 |
+
"eval_loss": 0.014164051972329617,
|
| 5 |
+
"eval_runtime": 156.8919,
|
| 6 |
+
"eval_samples_per_second": 29.919,
|
| 7 |
+
"eval_steps_per_second": 0.937,
|
| 8 |
+
"total_flos": 1.8120726851476193e+18,
|
| 9 |
+
"train_loss": 0.08313048457105955,
|
| 10 |
+
"train_runtime": 2165.5413,
|
| 11 |
+
"train_samples_per_second": 10.838,
|
| 12 |
+
"train_steps_per_second": 0.083
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.98,
|
| 3 |
+
"eval_accuracy": 0.9955262036642523,
|
| 4 |
+
"eval_loss": 0.014164051972329617,
|
| 5 |
+
"eval_runtime": 156.8919,
|
| 6 |
+
"eval_samples_per_second": 29.919,
|
| 7 |
+
"eval_steps_per_second": 0.937
|
| 8 |
+
}
|
runs/Feb05_22-19-46_910d9832454d/events.out.tfevents.1675638014.910d9832454d.294.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b30ced96c1df97960ebc12a839d96e3877edef6a408b8b5d0c6e1ebfe9aafae
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.98,
|
| 3 |
+
"total_flos": 1.8120726851476193e+18,
|
| 4 |
+
"train_loss": 0.08313048457105955,
|
| 5 |
+
"train_runtime": 2165.5413,
|
| 6 |
+
"train_samples_per_second": 10.838,
|
| 7 |
+
"train_steps_per_second": 0.083
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9957392415850022,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-finetuned-chest/checkpoint-180",
|
| 4 |
+
"epoch": 4.979591836734694,
|
| 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": 0.14,
|
| 12 |
+
"learning_rate": 1.388888888888889e-05,
|
| 13 |
+
"loss": 0.6592,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 2.777777777777778e-05,
|
| 19 |
+
"loss": 0.4472,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.41,
|
| 24 |
+
"learning_rate": 4.166666666666667e-05,
|
| 25 |
+
"loss": 0.2618,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.54,
|
| 30 |
+
"learning_rate": 4.938271604938271e-05,
|
| 31 |
+
"loss": 0.1677,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.68,
|
| 36 |
+
"learning_rate": 4.783950617283951e-05,
|
| 37 |
+
"loss": 0.1731,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.82,
|
| 42 |
+
"learning_rate": 4.62962962962963e-05,
|
| 43 |
+
"loss": 0.0952,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.95,
|
| 48 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 49 |
+
"loss": 0.1288,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.98,
|
| 54 |
+
"eval_accuracy": 0.9527055815935237,
|
| 55 |
+
"eval_loss": 0.10909163951873779,
|
| 56 |
+
"eval_runtime": 152.5532,
|
| 57 |
+
"eval_samples_per_second": 30.77,
|
| 58 |
+
"eval_steps_per_second": 0.964,
|
| 59 |
+
"step": 36
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.11,
|
| 63 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 64 |
+
"loss": 0.1009,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.24,
|
| 69 |
+
"learning_rate": 4.166666666666667e-05,
|
| 70 |
+
"loss": 0.0668,
|
| 71 |
+
"step": 45
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.38,
|
| 75 |
+
"learning_rate": 4.012345679012346e-05,
|
| 76 |
+
"loss": 0.0414,
|
| 77 |
+
"step": 50
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.52,
|
| 81 |
+
"learning_rate": 3.8580246913580246e-05,
|
| 82 |
+
"loss": 0.0553,
|
| 83 |
+
"step": 55
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.65,
|
| 87 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 88 |
+
"loss": 0.074,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.79,
|
| 93 |
+
"learning_rate": 3.5493827160493834e-05,
|
| 94 |
+
"loss": 0.0478,
|
| 95 |
+
"step": 65
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.93,
|
| 99 |
+
"learning_rate": 3.395061728395062e-05,
|
| 100 |
+
"loss": 0.0458,
|
| 101 |
+
"step": 70
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.98,
|
| 105 |
+
"eval_accuracy": 0.9865786109927567,
|
| 106 |
+
"eval_loss": 0.040942613035440445,
|
| 107 |
+
"eval_runtime": 153.8543,
|
| 108 |
+
"eval_samples_per_second": 30.509,
|
| 109 |
+
"eval_steps_per_second": 0.955,
|
| 110 |
+
"step": 72
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.08,
|
| 114 |
+
"learning_rate": 3.240740740740741e-05,
|
| 115 |
+
"loss": 0.0601,
|
| 116 |
+
"step": 75
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.22,
|
| 120 |
+
"learning_rate": 3.08641975308642e-05,
|
| 121 |
+
"loss": 0.0508,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.35,
|
| 126 |
+
"learning_rate": 2.9320987654320992e-05,
|
| 127 |
+
"loss": 0.0335,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.49,
|
| 132 |
+
"learning_rate": 2.777777777777778e-05,
|
| 133 |
+
"loss": 0.0443,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.63,
|
| 138 |
+
"learning_rate": 2.623456790123457e-05,
|
| 139 |
+
"loss": 0.0218,
|
| 140 |
+
"step": 95
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.76,
|
| 144 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 145 |
+
"loss": 0.0327,
|
| 146 |
+
"step": 100
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.9,
|
| 150 |
+
"learning_rate": 2.314814814814815e-05,
|
| 151 |
+
"loss": 0.0488,
|
| 152 |
+
"step": 105
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.98,
|
| 156 |
+
"eval_accuracy": 0.9906263314870047,
|
| 157 |
+
"eval_loss": 0.023438777774572372,
|
| 158 |
+
"eval_runtime": 155.1826,
|
| 159 |
+
"eval_samples_per_second": 30.248,
|
| 160 |
+
"eval_steps_per_second": 0.947,
|
| 161 |
+
"step": 108
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.05,
|
| 165 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 166 |
+
"loss": 0.0409,
|
| 167 |
+
"step": 110
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.19,
|
| 171 |
+
"learning_rate": 2.006172839506173e-05,
|
| 172 |
+
"loss": 0.0248,
|
| 173 |
+
"step": 115
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.33,
|
| 177 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 178 |
+
"loss": 0.0259,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.46,
|
| 183 |
+
"learning_rate": 1.697530864197531e-05,
|
| 184 |
+
"loss": 0.0165,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.6,
|
| 189 |
+
"learning_rate": 1.54320987654321e-05,
|
| 190 |
+
"loss": 0.0324,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.73,
|
| 195 |
+
"learning_rate": 1.388888888888889e-05,
|
| 196 |
+
"loss": 0.0314,
|
| 197 |
+
"step": 135
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.87,
|
| 201 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 202 |
+
"loss": 0.0287,
|
| 203 |
+
"step": 140
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.98,
|
| 207 |
+
"eval_accuracy": 0.994034938219003,
|
| 208 |
+
"eval_loss": 0.018356822431087494,
|
| 209 |
+
"eval_runtime": 154.3825,
|
| 210 |
+
"eval_samples_per_second": 30.405,
|
| 211 |
+
"eval_steps_per_second": 0.952,
|
| 212 |
+
"step": 144
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.03,
|
| 216 |
+
"learning_rate": 1.0802469135802469e-05,
|
| 217 |
+
"loss": 0.0336,
|
| 218 |
+
"step": 145
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.16,
|
| 222 |
+
"learning_rate": 9.259259259259259e-06,
|
| 223 |
+
"loss": 0.0191,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.3,
|
| 228 |
+
"learning_rate": 7.71604938271605e-06,
|
| 229 |
+
"loss": 0.0161,
|
| 230 |
+
"step": 155
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.44,
|
| 234 |
+
"learning_rate": 6.172839506172839e-06,
|
| 235 |
+
"loss": 0.0096,
|
| 236 |
+
"step": 160
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.57,
|
| 240 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 241 |
+
"loss": 0.0119,
|
| 242 |
+
"step": 165
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.71,
|
| 246 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 247 |
+
"loss": 0.0184,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.84,
|
| 252 |
+
"learning_rate": 1.5432098765432098e-06,
|
| 253 |
+
"loss": 0.0091,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.98,
|
| 258 |
+
"learning_rate": 0.0,
|
| 259 |
+
"loss": 0.0174,
|
| 260 |
+
"step": 180
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.98,
|
| 264 |
+
"eval_accuracy": 0.9957392415850022,
|
| 265 |
+
"eval_loss": 0.013076434843242168,
|
| 266 |
+
"eval_runtime": 153.7061,
|
| 267 |
+
"eval_samples_per_second": 30.539,
|
| 268 |
+
"eval_steps_per_second": 0.956,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.98,
|
| 273 |
+
"step": 180,
|
| 274 |
+
"total_flos": 1.8120726851476193e+18,
|
| 275 |
+
"train_loss": 0.08313048457105955,
|
| 276 |
+
"train_runtime": 2165.5413,
|
| 277 |
+
"train_samples_per_second": 10.838,
|
| 278 |
+
"train_steps_per_second": 0.083
|
| 279 |
+
}
|
| 280 |
+
],
|
| 281 |
+
"max_steps": 180,
|
| 282 |
+
"num_train_epochs": 5,
|
| 283 |
+
"total_flos": 1.8120726851476193e+18,
|
| 284 |
+
"trial_name": null,
|
| 285 |
+
"trial_params": null
|
| 286 |
+
}
|