Model save
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/May28_14-54-44_project/events.out.tfevents.1685285711.project.172733.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +269 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.87,
|
| 3 |
+
"total_flos": 5.909979961466413e+18,
|
| 4 |
+
"train_loss": 0.2693378947283092,
|
| 5 |
+
"train_runtime": 19015.6271,
|
| 6 |
+
"train_samples_per_second": 4.016,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347601681
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d88672e77fc9e6d06620f44a3e2742ce47430d93a70a47aee2cc239ddc0d79e
|
| 3 |
size 347601681
|
runs/May28_14-54-44_project/events.out.tfevents.1685285711.project.172733.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13f52610d02da9f149938f46308ce76673847516dd203eecf65d9a9bf97023c4
|
| 3 |
+
size 13251
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.87,
|
| 3 |
+
"total_flos": 5.909979961466413e+18,
|
| 4 |
+
"train_loss": 0.2693378947283092,
|
| 5 |
+
"train_runtime": 19015.6271,
|
| 6 |
+
"train_samples_per_second": 4.016,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8605655930871956,
|
| 3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_11/checkpoint-96",
|
| 4 |
+
"epoch": 9.87012987012987,
|
| 5 |
+
"global_step": 190,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.52,
|
| 12 |
+
"learning_rate": 0.0005263157894736842,
|
| 13 |
+
"loss": 1.2738,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"eval_accuracy": 0.3605655930871956,
|
| 19 |
+
"eval_f1_score": 0.2878120760544522,
|
| 20 |
+
"eval_loss": 3.6805028915405273,
|
| 21 |
+
"eval_precision": 0.6974014336917563,
|
| 22 |
+
"eval_runtime": 145.8752,
|
| 23 |
+
"eval_samples_per_second": 17.453,
|
| 24 |
+
"eval_sensitivity": 0.35686207037891016,
|
| 25 |
+
"eval_specificity": 0.8381290831748818,
|
| 26 |
+
"eval_steps_per_second": 0.178,
|
| 27 |
+
"step": 19
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.04,
|
| 31 |
+
"learning_rate": 0.0009941520467836257,
|
| 32 |
+
"loss": 0.9199,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.56,
|
| 37 |
+
"learning_rate": 0.000935672514619883,
|
| 38 |
+
"loss": 0.8184,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.97,
|
| 43 |
+
"eval_accuracy": 0.5196386488609583,
|
| 44 |
+
"eval_f1_score": 0.48419321422424316,
|
| 45 |
+
"eval_loss": 2.2141478061676025,
|
| 46 |
+
"eval_precision": 0.8084805071896239,
|
| 47 |
+
"eval_runtime": 143.7897,
|
| 48 |
+
"eval_samples_per_second": 17.706,
|
| 49 |
+
"eval_sensitivity": 0.5310745609579017,
|
| 50 |
+
"eval_specificity": 0.8793499818649668,
|
| 51 |
+
"eval_steps_per_second": 0.181,
|
| 52 |
+
"step": 38
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.08,
|
| 56 |
+
"learning_rate": 0.0008771929824561404,
|
| 57 |
+
"loss": 0.3378,
|
| 58 |
+
"step": 40
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.6,
|
| 62 |
+
"learning_rate": 0.0008187134502923977,
|
| 63 |
+
"loss": 0.3966,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.96,
|
| 68 |
+
"eval_accuracy": 0.8008641005498822,
|
| 69 |
+
"eval_f1_score": 0.7976254105368799,
|
| 70 |
+
"eval_loss": 0.6808411478996277,
|
| 71 |
+
"eval_precision": 0.8463324408375659,
|
| 72 |
+
"eval_runtime": 145.0768,
|
| 73 |
+
"eval_samples_per_second": 17.549,
|
| 74 |
+
"eval_sensitivity": 0.8028516850378219,
|
| 75 |
+
"eval_specificity": 0.9490601966554548,
|
| 76 |
+
"eval_steps_per_second": 0.179,
|
| 77 |
+
"step": 57
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.12,
|
| 81 |
+
"learning_rate": 0.0007602339181286549,
|
| 82 |
+
"loss": 0.2088,
|
| 83 |
+
"step": 60
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.64,
|
| 87 |
+
"learning_rate": 0.0007017543859649122,
|
| 88 |
+
"loss": 0.2336,
|
| 89 |
+
"step": 70
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.0,
|
| 93 |
+
"eval_accuracy": 0.7945797329143754,
|
| 94 |
+
"eval_f1_score": 0.8010782370930126,
|
| 95 |
+
"eval_loss": 0.5913988947868347,
|
| 96 |
+
"eval_precision": 0.8170231877099705,
|
| 97 |
+
"eval_runtime": 143.2938,
|
| 98 |
+
"eval_samples_per_second": 17.768,
|
| 99 |
+
"eval_sensitivity": 0.7978279035240907,
|
| 100 |
+
"eval_specificity": 0.9460506294613161,
|
| 101 |
+
"eval_steps_per_second": 0.181,
|
| 102 |
+
"step": 77
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.16,
|
| 106 |
+
"learning_rate": 0.0006432748538011695,
|
| 107 |
+
"loss": 0.1887,
|
| 108 |
+
"step": 80
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.68,
|
| 112 |
+
"learning_rate": 0.0005847953216374269,
|
| 113 |
+
"loss": 0.1196,
|
| 114 |
+
"step": 90
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.99,
|
| 118 |
+
"eval_accuracy": 0.8605655930871956,
|
| 119 |
+
"eval_f1_score": 0.860571684525386,
|
| 120 |
+
"eval_loss": 0.4851493239402771,
|
| 121 |
+
"eval_precision": 0.8779184919829779,
|
| 122 |
+
"eval_runtime": 148.4094,
|
| 123 |
+
"eval_samples_per_second": 17.155,
|
| 124 |
+
"eval_sensitivity": 0.8644996698700784,
|
| 125 |
+
"eval_specificity": 0.964375163934619,
|
| 126 |
+
"eval_steps_per_second": 0.175,
|
| 127 |
+
"step": 96
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 5.19,
|
| 131 |
+
"learning_rate": 0.0005263157894736842,
|
| 132 |
+
"loss": 0.1029,
|
| 133 |
+
"step": 100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.71,
|
| 137 |
+
"learning_rate": 0.0004678362573099415,
|
| 138 |
+
"loss": 0.1003,
|
| 139 |
+
"step": 110
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.97,
|
| 143 |
+
"eval_accuracy": 0.8413197172034564,
|
| 144 |
+
"eval_f1_score": 0.847505946157961,
|
| 145 |
+
"eval_loss": 0.5353347659111023,
|
| 146 |
+
"eval_precision": 0.8716205753374235,
|
| 147 |
+
"eval_runtime": 144.5966,
|
| 148 |
+
"eval_samples_per_second": 17.608,
|
| 149 |
+
"eval_sensitivity": 0.8442495649729828,
|
| 150 |
+
"eval_specificity": 0.9593485741891146,
|
| 151 |
+
"eval_steps_per_second": 0.18,
|
| 152 |
+
"step": 115
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.23,
|
| 156 |
+
"learning_rate": 0.00040935672514619883,
|
| 157 |
+
"loss": 0.0756,
|
| 158 |
+
"step": 120
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.75,
|
| 162 |
+
"learning_rate": 0.0003508771929824561,
|
| 163 |
+
"loss": 0.0876,
|
| 164 |
+
"step": 130
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.96,
|
| 168 |
+
"eval_accuracy": 0.8032207384131972,
|
| 169 |
+
"eval_f1_score": 0.815103775194211,
|
| 170 |
+
"eval_loss": 0.6691173315048218,
|
| 171 |
+
"eval_precision": 0.8765709834552656,
|
| 172 |
+
"eval_runtime": 145.6989,
|
| 173 |
+
"eval_samples_per_second": 17.474,
|
| 174 |
+
"eval_sensitivity": 0.8050530606233461,
|
| 175 |
+
"eval_specificity": 0.9503200126073728,
|
| 176 |
+
"eval_steps_per_second": 0.178,
|
| 177 |
+
"step": 134
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.27,
|
| 181 |
+
"learning_rate": 0.00029239766081871346,
|
| 182 |
+
"loss": 0.0454,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.79,
|
| 187 |
+
"learning_rate": 0.00023391812865497074,
|
| 188 |
+
"loss": 0.0569,
|
| 189 |
+
"step": 150
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.0,
|
| 193 |
+
"eval_accuracy": 0.8570306362922231,
|
| 194 |
+
"eval_f1_score": 0.8610031913382027,
|
| 195 |
+
"eval_loss": 0.4530697762966156,
|
| 196 |
+
"eval_precision": 0.8775565915946316,
|
| 197 |
+
"eval_runtime": 144.0104,
|
| 198 |
+
"eval_samples_per_second": 17.679,
|
| 199 |
+
"eval_sensitivity": 0.8613897087049174,
|
| 200 |
+
"eval_specificity": 0.963431312241978,
|
| 201 |
+
"eval_steps_per_second": 0.181,
|
| 202 |
+
"step": 154
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 8.31,
|
| 206 |
+
"learning_rate": 0.00017543859649122806,
|
| 207 |
+
"loss": 0.0524,
|
| 208 |
+
"step": 160
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 8.83,
|
| 212 |
+
"learning_rate": 0.00011695906432748537,
|
| 213 |
+
"loss": 0.0329,
|
| 214 |
+
"step": 170
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 8.99,
|
| 218 |
+
"eval_accuracy": 0.7977219167321288,
|
| 219 |
+
"eval_f1_score": 0.8081175377109597,
|
| 220 |
+
"eval_loss": 0.8580703735351562,
|
| 221 |
+
"eval_precision": 0.8692144353715325,
|
| 222 |
+
"eval_runtime": 144.2222,
|
| 223 |
+
"eval_samples_per_second": 17.653,
|
| 224 |
+
"eval_sensitivity": 0.8022743869652864,
|
| 225 |
+
"eval_specificity": 0.9488235279456919,
|
| 226 |
+
"eval_steps_per_second": 0.18,
|
| 227 |
+
"step": 173
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 9.35,
|
| 231 |
+
"learning_rate": 5.8479532163742686e-05,
|
| 232 |
+
"loss": 0.0401,
|
| 233 |
+
"step": 180
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 9.87,
|
| 237 |
+
"learning_rate": 0.0,
|
| 238 |
+
"loss": 0.0262,
|
| 239 |
+
"step": 190
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 9.87,
|
| 243 |
+
"eval_accuracy": 0.8566378633150039,
|
| 244 |
+
"eval_f1_score": 0.862624548745769,
|
| 245 |
+
"eval_loss": 0.5326746702194214,
|
| 246 |
+
"eval_precision": 0.8916086530475995,
|
| 247 |
+
"eval_runtime": 142.1789,
|
| 248 |
+
"eval_samples_per_second": 17.907,
|
| 249 |
+
"eval_sensitivity": 0.8581894341524791,
|
| 250 |
+
"eval_specificity": 0.9636117700670255,
|
| 251 |
+
"eval_steps_per_second": 0.183,
|
| 252 |
+
"step": 190
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 9.87,
|
| 256 |
+
"step": 190,
|
| 257 |
+
"total_flos": 5.909979961466413e+18,
|
| 258 |
+
"train_loss": 0.2693378947283092,
|
| 259 |
+
"train_runtime": 19015.6271,
|
| 260 |
+
"train_samples_per_second": 4.016,
|
| 261 |
+
"train_steps_per_second": 0.01
|
| 262 |
+
}
|
| 263 |
+
],
|
| 264 |
+
"max_steps": 190,
|
| 265 |
+
"num_train_epochs": 10,
|
| 266 |
+
"total_flos": 5.909979961466413e+18,
|
| 267 |
+
"trial_name": null,
|
| 268 |
+
"trial_params": null
|
| 269 |
+
}
|