Training in progress, epoch 0
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.6383622592934052e+18,
|
| 4 |
+
"train_loss": 0.04099405483170799,
|
| 5 |
+
"train_runtime": 643.5496,
|
| 6 |
+
"train_samples_per_second": 32.632,
|
| 7 |
+
"train_steps_per_second": 0.508
|
| 8 |
+
}
|
runs/Apr27_00-09-40_5061ebfbac97/1682555224.1685631/events.out.tfevents.1682555224.5061ebfbac97.1106.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:756af95d08dc86b0f4323a5eea73bed639f6ecc4aa8afcb00f6664069ecc664c
|
| 3 |
+
size 5862
|
runs/Apr27_00-09-40_5061ebfbac97/events.out.tfevents.1682555224.5061ebfbac97.1106.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4adcf1fb780d09da91550ceca94c5cffa078c384aed5469c26d1b1b0fc0ed49e
|
| 3 |
+
size 6293
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.6383622592934052e+18,
|
| 4 |
+
"train_loss": 0.04099405483170799,
|
| 5 |
+
"train_runtime": 643.5496,
|
| 6 |
+
"train_samples_per_second": 32.632,
|
| 7 |
+
"train_steps_per_second": 0.508
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9996666666666667,
|
| 3 |
+
"best_model_checkpoint": "swin-kidneys/checkpoint-327",
|
| 4 |
+
"epoch": 2.9863013698630136,
|
| 5 |
+
"global_step": 327,
|
| 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": 1.5151515151515153e-05,
|
| 13 |
+
"loss": 0.6308,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 19 |
+
"loss": 0.4012,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 4.545454545454546e-05,
|
| 25 |
+
"loss": 0.136,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.37,
|
| 30 |
+
"learning_rate": 4.880952380952381e-05,
|
| 31 |
+
"loss": 0.0678,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.46,
|
| 36 |
+
"learning_rate": 4.710884353741497e-05,
|
| 37 |
+
"loss": 0.0276,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.55,
|
| 42 |
+
"learning_rate": 4.5408163265306124e-05,
|
| 43 |
+
"loss": 0.0158,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.64,
|
| 48 |
+
"learning_rate": 4.3707482993197277e-05,
|
| 49 |
+
"loss": 0.0084,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.73,
|
| 54 |
+
"learning_rate": 4.200680272108844e-05,
|
| 55 |
+
"loss": 0.0075,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.82,
|
| 60 |
+
"learning_rate": 4.0306122448979596e-05,
|
| 61 |
+
"loss": 0.0041,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.91,
|
| 66 |
+
"learning_rate": 3.860544217687075e-05,
|
| 67 |
+
"loss": 0.0048,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.998,
|
| 73 |
+
"eval_loss": 0.006910140160471201,
|
| 74 |
+
"eval_runtime": 41.5794,
|
| 75 |
+
"eval_samples_per_second": 72.151,
|
| 76 |
+
"eval_steps_per_second": 4.521,
|
| 77 |
+
"step": 109
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.0,
|
| 81 |
+
"learning_rate": 3.690476190476191e-05,
|
| 82 |
+
"loss": 0.017,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.1,
|
| 87 |
+
"learning_rate": 3.520408163265306e-05,
|
| 88 |
+
"loss": 0.0069,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.19,
|
| 93 |
+
"learning_rate": 3.350340136054422e-05,
|
| 94 |
+
"loss": 0.0013,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.28,
|
| 99 |
+
"learning_rate": 3.180272108843538e-05,
|
| 100 |
+
"loss": 0.0003,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.37,
|
| 105 |
+
"learning_rate": 3.0102040816326533e-05,
|
| 106 |
+
"loss": 0.0022,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.46,
|
| 111 |
+
"learning_rate": 2.8401360544217685e-05,
|
| 112 |
+
"loss": 0.0002,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.55,
|
| 117 |
+
"learning_rate": 2.6700680272108845e-05,
|
| 118 |
+
"loss": 0.0002,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.64,
|
| 123 |
+
"learning_rate": 2.5e-05,
|
| 124 |
+
"loss": 0.0001,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.74,
|
| 129 |
+
"learning_rate": 2.3299319727891157e-05,
|
| 130 |
+
"loss": 0.0001,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.83,
|
| 135 |
+
"learning_rate": 2.1598639455782314e-05,
|
| 136 |
+
"loss": 0.0001,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.92,
|
| 141 |
+
"learning_rate": 1.989795918367347e-05,
|
| 142 |
+
"loss": 0.0002,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.0,
|
| 147 |
+
"eval_accuracy": 0.9993333333333333,
|
| 148 |
+
"eval_loss": 0.0023863492533564568,
|
| 149 |
+
"eval_runtime": 41.4125,
|
| 150 |
+
"eval_samples_per_second": 72.442,
|
| 151 |
+
"eval_steps_per_second": 4.54,
|
| 152 |
+
"step": 219
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.01,
|
| 156 |
+
"learning_rate": 1.8197278911564626e-05,
|
| 157 |
+
"loss": 0.0,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.1,
|
| 162 |
+
"learning_rate": 1.6496598639455782e-05,
|
| 163 |
+
"loss": 0.0005,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.19,
|
| 168 |
+
"learning_rate": 1.479591836734694e-05,
|
| 169 |
+
"loss": 0.0,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.28,
|
| 174 |
+
"learning_rate": 1.3095238095238096e-05,
|
| 175 |
+
"loss": 0.0,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.37,
|
| 180 |
+
"learning_rate": 1.1394557823129252e-05,
|
| 181 |
+
"loss": 0.0003,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.47,
|
| 186 |
+
"learning_rate": 9.693877551020408e-06,
|
| 187 |
+
"loss": 0.0,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.56,
|
| 192 |
+
"learning_rate": 7.993197278911566e-06,
|
| 193 |
+
"loss": 0.0001,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.65,
|
| 198 |
+
"learning_rate": 6.292517006802722e-06,
|
| 199 |
+
"loss": 0.0,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.74,
|
| 204 |
+
"learning_rate": 4.591836734693878e-06,
|
| 205 |
+
"loss": 0.0,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.83,
|
| 210 |
+
"learning_rate": 2.8911564625850344e-06,
|
| 211 |
+
"loss": 0.0068,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.92,
|
| 216 |
+
"learning_rate": 1.1904761904761904e-06,
|
| 217 |
+
"loss": 0.0002,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.99,
|
| 222 |
+
"eval_accuracy": 0.9996666666666667,
|
| 223 |
+
"eval_loss": 0.0007389984093606472,
|
| 224 |
+
"eval_runtime": 41.4403,
|
| 225 |
+
"eval_samples_per_second": 72.393,
|
| 226 |
+
"eval_steps_per_second": 4.537,
|
| 227 |
+
"step": 327
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.99,
|
| 231 |
+
"step": 327,
|
| 232 |
+
"total_flos": 1.6383622592934052e+18,
|
| 233 |
+
"train_loss": 0.04099405483170799,
|
| 234 |
+
"train_runtime": 643.5496,
|
| 235 |
+
"train_samples_per_second": 32.632,
|
| 236 |
+
"train_steps_per_second": 0.508
|
| 237 |
+
}
|
| 238 |
+
],
|
| 239 |
+
"max_steps": 327,
|
| 240 |
+
"num_train_epochs": 3,
|
| 241 |
+
"total_flos": 1.6383622592934052e+18,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|