Commit
•
1ef1a50
1
Parent(s):
fbe970e
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.872196261682243,
|
| 4 |
+
"eval_loss": 0.4010835587978363,
|
| 5 |
+
"eval_runtime": 85.9556,
|
| 6 |
+
"eval_samples_per_second": 49.793,
|
| 7 |
+
"eval_steps_per_second": 1.559,
|
| 8 |
+
"total_flos": 3.9721912052731453e+18,
|
| 9 |
+
"train_loss": 0.5681018877148927,
|
| 10 |
+
"train_runtime": 3778.1283,
|
| 11 |
+
"train_samples_per_second": 13.592,
|
| 12 |
+
"train_steps_per_second": 0.106
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.872196261682243,
|
| 4 |
+
"eval_loss": 0.4010835587978363,
|
| 5 |
+
"eval_runtime": 85.9556,
|
| 6 |
+
"eval_samples_per_second": 49.793,
|
| 7 |
+
"eval_steps_per_second": 1.559
|
| 8 |
+
}
|
runs/Sep27_18-58-02_3728c78946fb/events.out.tfevents.1664309418.3728c78946fb.17.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7806937169e32ed145a8acccdc47d1c8ac519b0de8dd062b43c1b4e81b328ae9
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 3.9721912052731453e+18,
|
| 4 |
+
"train_loss": 0.5681018877148927,
|
| 5 |
+
"train_runtime": 3778.1283,
|
| 6 |
+
"train_samples_per_second": 13.592,
|
| 7 |
+
"train_steps_per_second": 0.106
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.872196261682243,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-cassava/checkpoint-399",
|
| 4 |
+
"epoch": 2.994392523364486,
|
| 5 |
+
"global_step": 399,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 1.25e-05,
|
| 13 |
+
"loss": 1.6059,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 2.5e-05,
|
| 19 |
+
"loss": 1.381,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.22,
|
| 24 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 25 |
+
"loss": 1.1472,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.3,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 1.0363,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.37,
|
| 36 |
+
"learning_rate": 4.860724233983287e-05,
|
| 37 |
+
"loss": 0.9067,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.45,
|
| 42 |
+
"learning_rate": 4.721448467966574e-05,
|
| 43 |
+
"loss": 0.7733,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.52,
|
| 48 |
+
"learning_rate": 4.582172701949861e-05,
|
| 49 |
+
"loss": 0.7452,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.6,
|
| 54 |
+
"learning_rate": 4.442896935933148e-05,
|
| 55 |
+
"loss": 0.6585,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.67,
|
| 60 |
+
"learning_rate": 4.303621169916435e-05,
|
| 61 |
+
"loss": 0.6018,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.75,
|
| 66 |
+
"learning_rate": 4.164345403899722e-05,
|
| 67 |
+
"loss": 0.5398,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.82,
|
| 72 |
+
"learning_rate": 4.0250696378830085e-05,
|
| 73 |
+
"loss": 0.5506,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.9,
|
| 78 |
+
"learning_rate": 3.885793871866296e-05,
|
| 79 |
+
"loss": 0.5615,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.97,
|
| 84 |
+
"learning_rate": 3.746518105849583e-05,
|
| 85 |
+
"loss": 0.5242,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.99,
|
| 90 |
+
"eval_accuracy": 0.8502336448598131,
|
| 91 |
+
"eval_loss": 0.4905190169811249,
|
| 92 |
+
"eval_runtime": 89.5244,
|
| 93 |
+
"eval_samples_per_second": 47.808,
|
| 94 |
+
"eval_steps_per_second": 1.497,
|
| 95 |
+
"step": 133
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.05,
|
| 99 |
+
"learning_rate": 3.607242339832869e-05,
|
| 100 |
+
"loss": 0.5078,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.13,
|
| 105 |
+
"learning_rate": 3.4679665738161556e-05,
|
| 106 |
+
"loss": 0.5059,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.2,
|
| 111 |
+
"learning_rate": 3.328690807799443e-05,
|
| 112 |
+
"loss": 0.4914,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.28,
|
| 117 |
+
"learning_rate": 3.18941504178273e-05,
|
| 118 |
+
"loss": 0.4694,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.35,
|
| 123 |
+
"learning_rate": 3.050139275766017e-05,
|
| 124 |
+
"loss": 0.4538,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.43,
|
| 129 |
+
"learning_rate": 2.9108635097493035e-05,
|
| 130 |
+
"loss": 0.4467,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.5,
|
| 135 |
+
"learning_rate": 2.7715877437325903e-05,
|
| 136 |
+
"loss": 0.4958,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.58,
|
| 141 |
+
"learning_rate": 2.6323119777158778e-05,
|
| 142 |
+
"loss": 0.4647,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.65,
|
| 147 |
+
"learning_rate": 2.4930362116991646e-05,
|
| 148 |
+
"loss": 0.413,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.73,
|
| 153 |
+
"learning_rate": 2.3537604456824514e-05,
|
| 154 |
+
"loss": 0.4005,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.8,
|
| 159 |
+
"learning_rate": 2.214484679665738e-05,
|
| 160 |
+
"loss": 0.4374,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.87,
|
| 165 |
+
"learning_rate": 2.0752089136490253e-05,
|
| 166 |
+
"loss": 0.4366,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.95,
|
| 171 |
+
"learning_rate": 1.935933147632312e-05,
|
| 172 |
+
"loss": 0.4405,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.99,
|
| 177 |
+
"eval_accuracy": 0.8696261682242991,
|
| 178 |
+
"eval_loss": 0.41539567708969116,
|
| 179 |
+
"eval_runtime": 92.6526,
|
| 180 |
+
"eval_samples_per_second": 46.194,
|
| 181 |
+
"eval_steps_per_second": 1.446,
|
| 182 |
+
"step": 266
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.03,
|
| 186 |
+
"learning_rate": 1.7966573816155992e-05,
|
| 187 |
+
"loss": 0.4296,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.1,
|
| 192 |
+
"learning_rate": 1.6573816155988857e-05,
|
| 193 |
+
"loss": 0.4433,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.18,
|
| 198 |
+
"learning_rate": 1.518105849582173e-05,
|
| 199 |
+
"loss": 0.4323,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.25,
|
| 204 |
+
"learning_rate": 1.3788300835654596e-05,
|
| 205 |
+
"loss": 0.4169,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.33,
|
| 210 |
+
"learning_rate": 1.2395543175487466e-05,
|
| 211 |
+
"loss": 0.395,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.4,
|
| 216 |
+
"learning_rate": 1.1002785515320335e-05,
|
| 217 |
+
"loss": 0.4045,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.48,
|
| 222 |
+
"learning_rate": 9.610027855153205e-06,
|
| 223 |
+
"loss": 0.3718,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.55,
|
| 228 |
+
"learning_rate": 8.217270194986073e-06,
|
| 229 |
+
"loss": 0.4601,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.63,
|
| 234 |
+
"learning_rate": 6.8245125348189415e-06,
|
| 235 |
+
"loss": 0.3969,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.7,
|
| 240 |
+
"learning_rate": 5.43175487465181e-06,
|
| 241 |
+
"loss": 0.397,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.78,
|
| 246 |
+
"learning_rate": 4.03899721448468e-06,
|
| 247 |
+
"loss": 0.3909,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.85,
|
| 252 |
+
"learning_rate": 2.6462395543175487e-06,
|
| 253 |
+
"loss": 0.4032,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.93,
|
| 258 |
+
"learning_rate": 1.253481894150418e-06,
|
| 259 |
+
"loss": 0.3938,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.99,
|
| 264 |
+
"eval_accuracy": 0.872196261682243,
|
| 265 |
+
"eval_loss": 0.4010835587978363,
|
| 266 |
+
"eval_runtime": 89.5202,
|
| 267 |
+
"eval_samples_per_second": 47.81,
|
| 268 |
+
"eval_steps_per_second": 1.497,
|
| 269 |
+
"step": 399
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.99,
|
| 273 |
+
"step": 399,
|
| 274 |
+
"total_flos": 3.9721912052731453e+18,
|
| 275 |
+
"train_loss": 0.5681018877148927,
|
| 276 |
+
"train_runtime": 3778.1283,
|
| 277 |
+
"train_samples_per_second": 13.592,
|
| 278 |
+
"train_steps_per_second": 0.106
|
| 279 |
+
}
|
| 280 |
+
],
|
| 281 |
+
"max_steps": 399,
|
| 282 |
+
"num_train_epochs": 3,
|
| 283 |
+
"total_flos": 3.9721912052731453e+18,
|
| 284 |
+
"trial_name": null,
|
| 285 |
+
"trial_params": null
|
| 286 |
+
}
|