End of training
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +438 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.4218194468408568,
|
| 4 |
+
"train_runtime": 526.8698,
|
| 5 |
+
"train_samples_per_second": 71.061,
|
| 6 |
+
"train_steps_per_second": 1.11
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.4218194468408568,
|
| 4 |
+
"train_runtime": 526.8698,
|
| 5 |
+
"train_samples_per_second": 71.061,
|
| 6 |
+
"train_steps_per_second": 1.11
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,438 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18068847060203552,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-crack-detector\\checkpoint-585",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 585,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 8.47457627118644e-06,
|
| 14 |
+
"loss": 1.3866,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1.694915254237288e-05,
|
| 20 |
+
"loss": 1.3138,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 2.5423728813559322e-05,
|
| 26 |
+
"loss": 1.2036,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 3.389830508474576e-05,
|
| 32 |
+
"loss": 1.012,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.26,
|
| 37 |
+
"learning_rate": 4.2372881355932206e-05,
|
| 38 |
+
"loss": 0.8611,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.31,
|
| 43 |
+
"learning_rate": 4.990494296577947e-05,
|
| 44 |
+
"loss": 0.7258,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.36,
|
| 49 |
+
"learning_rate": 4.8954372623574146e-05,
|
| 50 |
+
"loss": 0.6027,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.41,
|
| 55 |
+
"learning_rate": 4.800380228136883e-05,
|
| 56 |
+
"loss": 0.5971,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.46,
|
| 61 |
+
"learning_rate": 4.70532319391635e-05,
|
| 62 |
+
"loss": 0.5713,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.51,
|
| 67 |
+
"learning_rate": 4.610266159695818e-05,
|
| 68 |
+
"loss": 0.481,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.56,
|
| 73 |
+
"learning_rate": 4.5152091254752856e-05,
|
| 74 |
+
"loss": 0.5275,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.62,
|
| 79 |
+
"learning_rate": 4.4201520912547525e-05,
|
| 80 |
+
"loss": 0.4933,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.67,
|
| 85 |
+
"learning_rate": 4.325095057034221e-05,
|
| 86 |
+
"loss": 0.4915,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.72,
|
| 91 |
+
"learning_rate": 4.2300380228136884e-05,
|
| 92 |
+
"loss": 0.5065,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.77,
|
| 97 |
+
"learning_rate": 4.134980988593156e-05,
|
| 98 |
+
"loss": 0.4511,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.82,
|
| 103 |
+
"learning_rate": 4.0399239543726235e-05,
|
| 104 |
+
"loss": 0.366,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.87,
|
| 109 |
+
"learning_rate": 3.944866920152092e-05,
|
| 110 |
+
"loss": 0.4178,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.92,
|
| 115 |
+
"learning_rate": 3.849809885931559e-05,
|
| 116 |
+
"loss": 0.4868,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.97,
|
| 121 |
+
"learning_rate": 3.754752851711027e-05,
|
| 122 |
+
"loss": 0.3863,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"eval_accuracy": {
|
| 128 |
+
"accuracy": 0.885576923076923
|
| 129 |
+
},
|
| 130 |
+
"eval_f1": {
|
| 131 |
+
"f1": 0.8829318618369404
|
| 132 |
+
},
|
| 133 |
+
"eval_loss": 0.33488142490386963,
|
| 134 |
+
"eval_precision": {
|
| 135 |
+
"precision": 0.8830357915066687
|
| 136 |
+
},
|
| 137 |
+
"eval_recall": {
|
| 138 |
+
"recall": 0.8864842943431257
|
| 139 |
+
},
|
| 140 |
+
"eval_runtime": 19.1649,
|
| 141 |
+
"eval_samples_per_second": 162.798,
|
| 142 |
+
"eval_steps_per_second": 10.175,
|
| 143 |
+
"step": 195
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.03,
|
| 147 |
+
"learning_rate": 3.6596958174904945e-05,
|
| 148 |
+
"loss": 0.4016,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.08,
|
| 153 |
+
"learning_rate": 3.564638783269962e-05,
|
| 154 |
+
"loss": 0.4089,
|
| 155 |
+
"step": 210
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.13,
|
| 159 |
+
"learning_rate": 3.46958174904943e-05,
|
| 160 |
+
"loss": 0.3912,
|
| 161 |
+
"step": 220
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.18,
|
| 165 |
+
"learning_rate": 3.374524714828898e-05,
|
| 166 |
+
"loss": 0.352,
|
| 167 |
+
"step": 230
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.23,
|
| 171 |
+
"learning_rate": 3.2794676806083655e-05,
|
| 172 |
+
"loss": 0.3791,
|
| 173 |
+
"step": 240
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.28,
|
| 177 |
+
"learning_rate": 3.1844106463878324e-05,
|
| 178 |
+
"loss": 0.3799,
|
| 179 |
+
"step": 250
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.33,
|
| 183 |
+
"learning_rate": 3.0893536121673007e-05,
|
| 184 |
+
"loss": 0.3602,
|
| 185 |
+
"step": 260
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.38,
|
| 189 |
+
"learning_rate": 2.994296577946768e-05,
|
| 190 |
+
"loss": 0.3451,
|
| 191 |
+
"step": 270
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.44,
|
| 195 |
+
"learning_rate": 2.8992395437262358e-05,
|
| 196 |
+
"loss": 0.4013,
|
| 197 |
+
"step": 280
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.49,
|
| 201 |
+
"learning_rate": 2.8041825095057034e-05,
|
| 202 |
+
"loss": 0.3138,
|
| 203 |
+
"step": 290
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.54,
|
| 207 |
+
"learning_rate": 2.7091254752851713e-05,
|
| 208 |
+
"loss": 0.3488,
|
| 209 |
+
"step": 300
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.59,
|
| 213 |
+
"learning_rate": 2.614068441064639e-05,
|
| 214 |
+
"loss": 0.3306,
|
| 215 |
+
"step": 310
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.64,
|
| 219 |
+
"learning_rate": 2.5190114068441068e-05,
|
| 220 |
+
"loss": 0.3477,
|
| 221 |
+
"step": 320
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.69,
|
| 225 |
+
"learning_rate": 2.423954372623574e-05,
|
| 226 |
+
"loss": 0.3075,
|
| 227 |
+
"step": 330
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.74,
|
| 231 |
+
"learning_rate": 2.328897338403042e-05,
|
| 232 |
+
"loss": 0.2544,
|
| 233 |
+
"step": 340
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.79,
|
| 237 |
+
"learning_rate": 2.2338403041825095e-05,
|
| 238 |
+
"loss": 0.2909,
|
| 239 |
+
"step": 350
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.85,
|
| 243 |
+
"learning_rate": 2.138783269961977e-05,
|
| 244 |
+
"loss": 0.2901,
|
| 245 |
+
"step": 360
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.9,
|
| 249 |
+
"learning_rate": 2.043726235741445e-05,
|
| 250 |
+
"loss": 0.3154,
|
| 251 |
+
"step": 370
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.95,
|
| 255 |
+
"learning_rate": 1.9486692015209126e-05,
|
| 256 |
+
"loss": 0.2921,
|
| 257 |
+
"step": 380
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.0,
|
| 261 |
+
"learning_rate": 1.8536121673003802e-05,
|
| 262 |
+
"loss": 0.2685,
|
| 263 |
+
"step": 390
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.0,
|
| 267 |
+
"eval_accuracy": {
|
| 268 |
+
"accuracy": 0.9080128205128205
|
| 269 |
+
},
|
| 270 |
+
"eval_f1": {
|
| 271 |
+
"f1": 0.9106277459775055
|
| 272 |
+
},
|
| 273 |
+
"eval_loss": 0.2715485692024231,
|
| 274 |
+
"eval_precision": {
|
| 275 |
+
"precision": 0.9130231253775549
|
| 276 |
+
},
|
| 277 |
+
"eval_recall": {
|
| 278 |
+
"recall": 0.9148104520472664
|
| 279 |
+
},
|
| 280 |
+
"eval_runtime": 19.694,
|
| 281 |
+
"eval_samples_per_second": 158.424,
|
| 282 |
+
"eval_steps_per_second": 9.901,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.05,
|
| 287 |
+
"learning_rate": 1.758555133079848e-05,
|
| 288 |
+
"loss": 0.3095,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.1,
|
| 293 |
+
"learning_rate": 1.6634980988593157e-05,
|
| 294 |
+
"loss": 0.275,
|
| 295 |
+
"step": 410
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.15,
|
| 299 |
+
"learning_rate": 1.5684410646387833e-05,
|
| 300 |
+
"loss": 0.2995,
|
| 301 |
+
"step": 420
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.21,
|
| 305 |
+
"learning_rate": 1.4733840304182512e-05,
|
| 306 |
+
"loss": 0.2558,
|
| 307 |
+
"step": 430
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.26,
|
| 311 |
+
"learning_rate": 1.3783269961977188e-05,
|
| 312 |
+
"loss": 0.3233,
|
| 313 |
+
"step": 440
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.31,
|
| 317 |
+
"learning_rate": 1.2832699619771862e-05,
|
| 318 |
+
"loss": 0.2716,
|
| 319 |
+
"step": 450
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.36,
|
| 323 |
+
"learning_rate": 1.1882129277566541e-05,
|
| 324 |
+
"loss": 0.2387,
|
| 325 |
+
"step": 460
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.41,
|
| 329 |
+
"learning_rate": 1.0931558935361218e-05,
|
| 330 |
+
"loss": 0.275,
|
| 331 |
+
"step": 470
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.46,
|
| 335 |
+
"learning_rate": 9.980988593155894e-06,
|
| 336 |
+
"loss": 0.2475,
|
| 337 |
+
"step": 480
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.51,
|
| 341 |
+
"learning_rate": 9.03041825095057e-06,
|
| 342 |
+
"loss": 0.2272,
|
| 343 |
+
"step": 490
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.56,
|
| 347 |
+
"learning_rate": 8.079847908745247e-06,
|
| 348 |
+
"loss": 0.2475,
|
| 349 |
+
"step": 500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.62,
|
| 353 |
+
"learning_rate": 7.129277566539924e-06,
|
| 354 |
+
"loss": 0.2681,
|
| 355 |
+
"step": 510
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.67,
|
| 359 |
+
"learning_rate": 6.1787072243346015e-06,
|
| 360 |
+
"loss": 0.2519,
|
| 361 |
+
"step": 520
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.72,
|
| 365 |
+
"learning_rate": 5.228136882129278e-06,
|
| 366 |
+
"loss": 0.244,
|
| 367 |
+
"step": 530
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.77,
|
| 371 |
+
"learning_rate": 4.277566539923955e-06,
|
| 372 |
+
"loss": 0.243,
|
| 373 |
+
"step": 540
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.82,
|
| 377 |
+
"learning_rate": 3.3269961977186314e-06,
|
| 378 |
+
"loss": 0.2361,
|
| 379 |
+
"step": 550
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.87,
|
| 383 |
+
"learning_rate": 2.376425855513308e-06,
|
| 384 |
+
"loss": 0.2095,
|
| 385 |
+
"step": 560
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.92,
|
| 389 |
+
"learning_rate": 1.4258555133079848e-06,
|
| 390 |
+
"loss": 0.2171,
|
| 391 |
+
"step": 570
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.97,
|
| 395 |
+
"learning_rate": 4.752851711026616e-07,
|
| 396 |
+
"loss": 0.2235,
|
| 397 |
+
"step": 580
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 3.0,
|
| 401 |
+
"eval_accuracy": {
|
| 402 |
+
"accuracy": 0.9384615384615385
|
| 403 |
+
},
|
| 404 |
+
"eval_f1": {
|
| 405 |
+
"f1": 0.9382975252490704
|
| 406 |
+
},
|
| 407 |
+
"eval_loss": 0.18068847060203552,
|
| 408 |
+
"eval_precision": {
|
| 409 |
+
"precision": 0.9382005688460371
|
| 410 |
+
},
|
| 411 |
+
"eval_recall": {
|
| 412 |
+
"recall": 0.9395073274524703
|
| 413 |
+
},
|
| 414 |
+
"eval_runtime": 19.9688,
|
| 415 |
+
"eval_samples_per_second": 156.243,
|
| 416 |
+
"eval_steps_per_second": 9.765,
|
| 417 |
+
"step": 585
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.0,
|
| 421 |
+
"step": 585,
|
| 422 |
+
"total_flos": 9.306602345005056e+17,
|
| 423 |
+
"train_loss": 0.4218194468408568,
|
| 424 |
+
"train_runtime": 526.8698,
|
| 425 |
+
"train_samples_per_second": 71.061,
|
| 426 |
+
"train_steps_per_second": 1.11
|
| 427 |
+
}
|
| 428 |
+
],
|
| 429 |
+
"logging_steps": 10,
|
| 430 |
+
"max_steps": 585,
|
| 431 |
+
"num_input_tokens_seen": 0,
|
| 432 |
+
"num_train_epochs": 3,
|
| 433 |
+
"save_steps": 500,
|
| 434 |
+
"total_flos": 9.306602345005056e+17,
|
| 435 |
+
"train_batch_size": 16,
|
| 436 |
+
"trial_name": null,
|
| 437 |
+
"trial_params": null
|
| 438 |
+
}
|