End of training
Browse files- all_results.json +40 -4
- pytorch_model.bin +1 -1
- runs/Mar10_12-04-59_96c678b480cf/events.out.tfevents.1678452496.96c678b480cf.1488.4 +2 -2
- runs/Mar10_12-04-59_96c678b480cf/events.out.tfevents.1678453656.96c678b480cf.1488.6 +3 -0
- test_results.json +11 -0
- train_more_results.json +11 -0
- train_results.json +4 -4
- trainer_state.json +238 -130
- valid_results.json +11 -0
all_results.json
CHANGED
|
@@ -1,8 +1,44 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"total_flos": 2118227382190080.0,
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_f1": 1.0,
|
| 5 |
+
"eval_loss": 0.01563212461769581,
|
| 6 |
+
"eval_precision": 1.0,
|
| 7 |
+
"eval_recall": 1.0,
|
| 8 |
+
"eval_runtime": 4.7878,
|
| 9 |
+
"eval_samples_per_second": 139.103,
|
| 10 |
+
"eval_steps_per_second": 4.386,
|
| 11 |
+
"test_accuracy": 1.0,
|
| 12 |
+
"test_f1": 1.0,
|
| 13 |
+
"test_loss": 0.015602031722664833,
|
| 14 |
+
"test_precision": 1.0,
|
| 15 |
+
"test_recall": 1.0,
|
| 16 |
+
"test_runtime": 3.7938,
|
| 17 |
+
"test_samples_per_second": 175.812,
|
| 18 |
+
"test_steps_per_second": 5.535,
|
| 19 |
+
"testaccuracy": 1.0,
|
| 20 |
+
"testf1": 1.0,
|
| 21 |
+
"testloss": 0.015602031722664833,
|
| 22 |
+
"testprecision": 1.0,
|
| 23 |
+
"testrecall": 1.0,
|
| 24 |
+
"testruntime": 3.8386,
|
| 25 |
+
"testsamples_per_second": 173.763,
|
| 26 |
+
"teststeps_per_second": 5.471,
|
| 27 |
"total_flos": 2118227382190080.0,
|
| 28 |
+
"train_accuracy": 0.9981231231231231,
|
| 29 |
+
"train_f1": 0.9981237024802164,
|
| 30 |
+
"train_loss": 0.02615901082754135,
|
| 31 |
+
"train_precision": 0.9981332041882663,
|
| 32 |
+
"train_recall": 0.9981231231231231,
|
| 33 |
+
"train_runtime": 33.3791,
|
| 34 |
+
"train_samples_per_second": 159.621,
|
| 35 |
+
"train_steps_per_second": 5.003,
|
| 36 |
+
"valid_accuracy": 1.0,
|
| 37 |
+
"valid_f1": 1.0,
|
| 38 |
+
"valid_loss": 0.01563212461769581,
|
| 39 |
+
"valid_precision": 1.0,
|
| 40 |
+
"valid_recall": 1.0,
|
| 41 |
+
"valid_runtime": 4.1534,
|
| 42 |
+
"valid_samples_per_second": 160.349,
|
| 43 |
+
"valid_steps_per_second": 5.056
|
| 44 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267926253
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08deb6849fe67d26281d2b1bf52aa27b8e8ce8ec312683bc555bf4a2085139d1
|
| 3 |
size 267926253
|
runs/Mar10_12-04-59_96c678b480cf/events.out.tfevents.1678452496.96c678b480cf.1488.4
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:bdf3ce9529f776c11ccd571ba6031c022c4ee710078bffa150095682e3bd76a7
|
| 3 |
+
size 14516
|
runs/Mar10_12-04-59_96c678b480cf/events.out.tfevents.1678453656.96c678b480cf.1488.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ee7068b830d374b680fd3796e24d3ca4cd9c05b94270ede480852a62fb73d2
|
| 3 |
+
size 4288
|
test_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 1.0,
|
| 4 |
+
"test_f1": 1.0,
|
| 5 |
+
"test_loss": 0.015602031722664833,
|
| 6 |
+
"test_precision": 1.0,
|
| 7 |
+
"test_recall": 1.0,
|
| 8 |
+
"test_runtime": 3.7938,
|
| 9 |
+
"test_samples_per_second": 175.812,
|
| 10 |
+
"test_steps_per_second": 5.535
|
| 11 |
+
}
|
train_more_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_accuracy": 0.9981231231231231,
|
| 4 |
+
"train_f1": 0.9981237024802164,
|
| 5 |
+
"train_loss": 0.02615901082754135,
|
| 6 |
+
"train_precision": 0.9981332041882663,
|
| 7 |
+
"train_recall": 0.9981231231231231,
|
| 8 |
+
"train_runtime": 33.3791,
|
| 9 |
+
"train_samples_per_second": 159.621,
|
| 10 |
+
"train_steps_per_second": 5.003
|
| 11 |
+
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"total_flos": 2118227382190080.0,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"total_flos": 2118227382190080.0,
|
| 4 |
+
"train_loss": 0.08387424607952673,
|
| 5 |
+
"train_runtime": 368.9515,
|
| 6 |
+
"train_samples_per_second": 43.323,
|
| 7 |
+
"train_steps_per_second": 1.358
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0
|
| 3 |
-
"best_model_checkpoint": "distilbert-base-uncased_finetuned_text_2_disease/checkpoint-
|
| 4 |
"epoch": 3.0,
|
| 5 |
"global_step": 501,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,348 +9,456 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.06,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.12,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.18,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.24,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.3,
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.36,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.42,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.48,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.54,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.6,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.66,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.72,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.78,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.84,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.9,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.96,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 1.0,
|
| 108 |
-
"eval_accuracy": 0.
|
| 109 |
-
"eval_f1": 0.
|
| 110 |
-
"eval_loss": 0.
|
| 111 |
-
"eval_precision": 0.
|
| 112 |
-
"eval_recall": 0.
|
| 113 |
-
"eval_runtime": 3.
|
| 114 |
-
"eval_samples_per_second":
|
| 115 |
-
"eval_steps_per_second": 5.
|
| 116 |
"step": 167
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.02,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 170
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 1.08,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 180
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.14,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 190
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 1.2,
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 200
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 1.26,
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 210
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 1.32,
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 220
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 1.38,
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 230
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.44,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 240
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 1.5,
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 250
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 1.56,
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 260
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 1.62,
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 270
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.68,
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 280
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 1.74,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 290
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 1.8,
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 300
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.86,
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 310
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 1.92,
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 320
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 1.98,
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 330
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.0,
|
| 222 |
-
"eval_accuracy": 0
|
| 223 |
-
"eval_f1": 0
|
| 224 |
-
"eval_loss": 0.
|
| 225 |
-
"eval_precision": 0
|
| 226 |
-
"eval_recall": 0
|
| 227 |
-
"eval_runtime":
|
| 228 |
-
"eval_samples_per_second":
|
| 229 |
-
"eval_steps_per_second": 5.
|
| 230 |
"step": 334
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.04,
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 340
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.1,
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 350
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 2.16,
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 360
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 2.22,
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 370
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 2.28,
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 380
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 2.34,
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 390
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 2.4,
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 2.46,
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 410
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 2.51,
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 420
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 2.57,
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 430
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 2.63,
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 440
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 2.69,
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 450
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 2.75,
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 460
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 2.81,
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 470
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 2.87,
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 480
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 2.93,
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 490
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 2.99,
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 500
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 3.0,
|
| 336 |
-
"eval_accuracy": 0
|
| 337 |
-
"eval_f1": 0
|
| 338 |
-
"eval_loss": 0.
|
| 339 |
-
"eval_precision": 0
|
| 340 |
-
"eval_recall": 0
|
| 341 |
-
"eval_runtime":
|
| 342 |
-
"eval_samples_per_second":
|
| 343 |
-
"eval_steps_per_second": 5.
|
| 344 |
"step": 501
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 3.0,
|
| 348 |
"step": 501,
|
| 349 |
"total_flos": 2118227382190080.0,
|
| 350 |
-
"train_loss": 0.
|
| 351 |
-
"train_runtime":
|
| 352 |
-
"train_samples_per_second":
|
| 353 |
-
"train_steps_per_second": 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
}
|
| 355 |
],
|
| 356 |
"max_steps": 501,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "distilbert-base-uncased_finetuned_text_2_disease/checkpoint-334",
|
| 4 |
"epoch": 3.0,
|
| 5 |
"global_step": 501,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.9600798403193614e-05,
|
| 13 |
+
"loss": 0.3519,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 1.920159680638723e-05,
|
| 19 |
+
"loss": 0.3228,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 1.8802395209580838e-05,
|
| 25 |
+
"loss": 0.3043,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 1.8403193612774454e-05,
|
| 31 |
+
"loss": 0.232,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 1.8003992015968066e-05,
|
| 37 |
+
"loss": 0.2346,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 1.7604790419161678e-05,
|
| 43 |
+
"loss": 0.2027,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.42,
|
| 48 |
+
"learning_rate": 1.720558882235529e-05,
|
| 49 |
+
"loss": 0.1758,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.48,
|
| 54 |
+
"learning_rate": 1.6806387225548902e-05,
|
| 55 |
+
"loss": 0.1465,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.54,
|
| 60 |
+
"learning_rate": 1.6407185628742518e-05,
|
| 61 |
+
"loss": 0.1593,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.6,
|
| 66 |
+
"learning_rate": 1.600798403193613e-05,
|
| 67 |
+
"loss": 0.1201,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.66,
|
| 72 |
+
"learning_rate": 1.5608782435129742e-05,
|
| 73 |
+
"loss": 0.1107,
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.72,
|
| 78 |
+
"learning_rate": 1.5209580838323354e-05,
|
| 79 |
+
"loss": 0.1138,
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.78,
|
| 84 |
+
"learning_rate": 1.4810379241516968e-05,
|
| 85 |
+
"loss": 0.0947,
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.84,
|
| 90 |
+
"learning_rate": 1.4411177644710582e-05,
|
| 91 |
+
"loss": 0.0911,
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.9,
|
| 96 |
+
"learning_rate": 1.4011976047904192e-05,
|
| 97 |
+
"loss": 0.0613,
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.96,
|
| 102 |
+
"learning_rate": 1.3612774451097806e-05,
|
| 103 |
+
"loss": 0.0585,
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 1.0,
|
| 108 |
+
"eval_accuracy": 0.9984984984984985,
|
| 109 |
+
"eval_f1": 0.9984973421631103,
|
| 110 |
+
"eval_loss": 0.03541606292128563,
|
| 111 |
+
"eval_precision": 0.9985541096652208,
|
| 112 |
+
"eval_recall": 0.9984984984984985,
|
| 113 |
+
"eval_runtime": 3.7271,
|
| 114 |
+
"eval_samples_per_second": 178.69,
|
| 115 |
+
"eval_steps_per_second": 5.634,
|
| 116 |
"step": 167
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.02,
|
| 120 |
+
"learning_rate": 1.3213572854291418e-05,
|
| 121 |
+
"loss": 0.0779,
|
| 122 |
"step": 170
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 1.08,
|
| 126 |
+
"learning_rate": 1.2814371257485032e-05,
|
| 127 |
+
"loss": 0.0501,
|
| 128 |
"step": 180
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.14,
|
| 132 |
+
"learning_rate": 1.2415169660678643e-05,
|
| 133 |
+
"loss": 0.0756,
|
| 134 |
"step": 190
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 1.2,
|
| 138 |
+
"learning_rate": 1.2015968063872256e-05,
|
| 139 |
+
"loss": 0.0417,
|
| 140 |
"step": 200
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 1.26,
|
| 144 |
+
"learning_rate": 1.161676646706587e-05,
|
| 145 |
+
"loss": 0.0505,
|
| 146 |
"step": 210
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 1.32,
|
| 150 |
+
"learning_rate": 1.1217564870259482e-05,
|
| 151 |
+
"loss": 0.0609,
|
| 152 |
"step": 220
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 1.38,
|
| 156 |
+
"learning_rate": 1.0818363273453095e-05,
|
| 157 |
+
"loss": 0.0764,
|
| 158 |
"step": 230
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.44,
|
| 162 |
+
"learning_rate": 1.0419161676646707e-05,
|
| 163 |
+
"loss": 0.0677,
|
| 164 |
"step": 240
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 1.5,
|
| 168 |
+
"learning_rate": 1.001996007984032e-05,
|
| 169 |
+
"loss": 0.0617,
|
| 170 |
"step": 250
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 1.56,
|
| 174 |
+
"learning_rate": 9.620758483033933e-06,
|
| 175 |
+
"loss": 0.0365,
|
| 176 |
"step": 260
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 1.62,
|
| 180 |
+
"learning_rate": 9.221556886227547e-06,
|
| 181 |
+
"loss": 0.0315,
|
| 182 |
"step": 270
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.68,
|
| 186 |
+
"learning_rate": 8.822355289421159e-06,
|
| 187 |
+
"loss": 0.0297,
|
| 188 |
"step": 280
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 1.74,
|
| 192 |
+
"learning_rate": 8.42315369261477e-06,
|
| 193 |
+
"loss": 0.0505,
|
| 194 |
"step": 290
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 1.8,
|
| 198 |
+
"learning_rate": 8.023952095808385e-06,
|
| 199 |
+
"loss": 0.0275,
|
| 200 |
"step": 300
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.86,
|
| 204 |
+
"learning_rate": 7.624750499001997e-06,
|
| 205 |
+
"loss": 0.0366,
|
| 206 |
"step": 310
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 1.92,
|
| 210 |
+
"learning_rate": 7.225548902195609e-06,
|
| 211 |
+
"loss": 0.0269,
|
| 212 |
"step": 320
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 1.98,
|
| 216 |
+
"learning_rate": 6.826347305389223e-06,
|
| 217 |
+
"loss": 0.0457,
|
| 218 |
"step": 330
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.0,
|
| 222 |
+
"eval_accuracy": 1.0,
|
| 223 |
+
"eval_f1": 1.0,
|
| 224 |
+
"eval_loss": 0.01563212461769581,
|
| 225 |
+
"eval_precision": 1.0,
|
| 226 |
+
"eval_recall": 1.0,
|
| 227 |
+
"eval_runtime": 4.0223,
|
| 228 |
+
"eval_samples_per_second": 165.575,
|
| 229 |
+
"eval_steps_per_second": 5.221,
|
| 230 |
"step": 334
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.04,
|
| 234 |
+
"learning_rate": 6.427145708582835e-06,
|
| 235 |
+
"loss": 0.0284,
|
| 236 |
"step": 340
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.1,
|
| 240 |
+
"learning_rate": 6.027944111776448e-06,
|
| 241 |
+
"loss": 0.0241,
|
| 242 |
"step": 350
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 2.16,
|
| 246 |
+
"learning_rate": 5.62874251497006e-06,
|
| 247 |
+
"loss": 0.0424,
|
| 248 |
"step": 360
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 2.22,
|
| 252 |
+
"learning_rate": 5.229540918163674e-06,
|
| 253 |
+
"loss": 0.0444,
|
| 254 |
"step": 370
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 2.28,
|
| 258 |
+
"learning_rate": 4.830339321357286e-06,
|
| 259 |
+
"loss": 0.0222,
|
| 260 |
"step": 380
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 2.34,
|
| 264 |
+
"learning_rate": 4.431137724550898e-06,
|
| 265 |
+
"loss": 0.0248,
|
| 266 |
"step": 390
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 2.4,
|
| 270 |
+
"learning_rate": 4.031936127744511e-06,
|
| 271 |
+
"loss": 0.0344,
|
| 272 |
"step": 400
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 2.46,
|
| 276 |
+
"learning_rate": 3.6327345309381242e-06,
|
| 277 |
+
"loss": 0.0214,
|
| 278 |
"step": 410
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 2.51,
|
| 282 |
+
"learning_rate": 3.2335329341317368e-06,
|
| 283 |
+
"loss": 0.0216,
|
| 284 |
"step": 420
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 2.57,
|
| 288 |
+
"learning_rate": 2.8343313373253494e-06,
|
| 289 |
+
"loss": 0.0512,
|
| 290 |
"step": 430
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 2.63,
|
| 294 |
+
"learning_rate": 2.4351297405189623e-06,
|
| 295 |
+
"loss": 0.0437,
|
| 296 |
"step": 440
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 2.69,
|
| 300 |
+
"learning_rate": 2.035928143712575e-06,
|
| 301 |
+
"loss": 0.0439,
|
| 302 |
"step": 450
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 2.75,
|
| 306 |
+
"learning_rate": 1.6367265469061877e-06,
|
| 307 |
+
"loss": 0.0212,
|
| 308 |
"step": 460
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 2.81,
|
| 312 |
+
"learning_rate": 1.2375249500998005e-06,
|
| 313 |
+
"loss": 0.0203,
|
| 314 |
"step": 470
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 2.87,
|
| 318 |
+
"learning_rate": 8.383233532934132e-07,
|
| 319 |
+
"loss": 0.0483,
|
| 320 |
"step": 480
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 2.93,
|
| 324 |
+
"learning_rate": 4.39121756487026e-07,
|
| 325 |
+
"loss": 0.0594,
|
| 326 |
"step": 490
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 2.99,
|
| 330 |
+
"learning_rate": 3.992015968063872e-08,
|
| 331 |
+
"loss": 0.0207,
|
| 332 |
"step": 500
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 3.0,
|
| 336 |
+
"eval_accuracy": 1.0,
|
| 337 |
+
"eval_f1": 1.0,
|
| 338 |
+
"eval_loss": 0.012468785047531128,
|
| 339 |
+
"eval_precision": 1.0,
|
| 340 |
+
"eval_recall": 1.0,
|
| 341 |
+
"eval_runtime": 4.1959,
|
| 342 |
+
"eval_samples_per_second": 158.726,
|
| 343 |
+
"eval_steps_per_second": 5.005,
|
| 344 |
"step": 501
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 3.0,
|
| 348 |
"step": 501,
|
| 349 |
"total_flos": 2118227382190080.0,
|
| 350 |
+
"train_loss": 0.08387424607952673,
|
| 351 |
+
"train_runtime": 368.9515,
|
| 352 |
+
"train_samples_per_second": 43.323,
|
| 353 |
+
"train_steps_per_second": 1.358
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.0,
|
| 357 |
+
"eval_accuracy": 0.9981231231231231,
|
| 358 |
+
"eval_f1": 0.9981237024802164,
|
| 359 |
+
"eval_loss": 0.02615901082754135,
|
| 360 |
+
"eval_precision": 0.9981332041882663,
|
| 361 |
+
"eval_recall": 0.9981231231231231,
|
| 362 |
+
"eval_runtime": 31.1804,
|
| 363 |
+
"eval_samples_per_second": 170.877,
|
| 364 |
+
"eval_steps_per_second": 5.356,
|
| 365 |
+
"step": 501
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.0,
|
| 369 |
+
"eval_accuracy": 0.9981231231231231,
|
| 370 |
+
"eval_f1": 0.9981237024802164,
|
| 371 |
+
"eval_loss": 0.02615901082754135,
|
| 372 |
+
"eval_precision": 0.9981332041882663,
|
| 373 |
+
"eval_recall": 0.9981231231231231,
|
| 374 |
+
"eval_runtime": 31.2125,
|
| 375 |
+
"eval_samples_per_second": 170.701,
|
| 376 |
+
"eval_steps_per_second": 5.35,
|
| 377 |
+
"step": 501
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.0,
|
| 381 |
+
"eval_accuracy": 0.9981231231231231,
|
| 382 |
+
"eval_f1": 0.9981237024802164,
|
| 383 |
+
"eval_loss": 0.02615901082754135,
|
| 384 |
+
"eval_precision": 0.9981332041882663,
|
| 385 |
+
"eval_recall": 0.9981231231231231,
|
| 386 |
+
"eval_runtime": 33.039,
|
| 387 |
+
"eval_samples_per_second": 161.264,
|
| 388 |
+
"eval_steps_per_second": 5.055,
|
| 389 |
+
"step": 501
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"eval_accuracy": 0.9981231231231231,
|
| 394 |
+
"eval_f1": 0.9981237024802164,
|
| 395 |
+
"eval_loss": 0.02615901082754135,
|
| 396 |
+
"eval_precision": 0.9981332041882663,
|
| 397 |
+
"eval_recall": 0.9981231231231231,
|
| 398 |
+
"eval_runtime": 33.3791,
|
| 399 |
+
"eval_samples_per_second": 159.621,
|
| 400 |
+
"eval_steps_per_second": 5.003,
|
| 401 |
+
"step": 501
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.0,
|
| 405 |
+
"eval_accuracy": 1.0,
|
| 406 |
+
"eval_f1": 1.0,
|
| 407 |
+
"eval_loss": 0.01563212461769581,
|
| 408 |
+
"eval_precision": 1.0,
|
| 409 |
+
"eval_recall": 1.0,
|
| 410 |
+
"eval_runtime": 4.7878,
|
| 411 |
+
"eval_samples_per_second": 139.103,
|
| 412 |
+
"eval_steps_per_second": 4.386,
|
| 413 |
+
"step": 501
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.0,
|
| 417 |
+
"eval_accuracy": 1.0,
|
| 418 |
+
"eval_f1": 1.0,
|
| 419 |
+
"eval_loss": 0.015602031722664833,
|
| 420 |
+
"eval_precision": 1.0,
|
| 421 |
+
"eval_recall": 1.0,
|
| 422 |
+
"eval_runtime": 3.8386,
|
| 423 |
+
"eval_samples_per_second": 173.763,
|
| 424 |
+
"eval_steps_per_second": 5.471,
|
| 425 |
+
"step": 501
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"eval_accuracy": 1.0,
|
| 430 |
+
"eval_f1": 1.0,
|
| 431 |
+
"eval_loss": 0.015602031722664833,
|
| 432 |
+
"eval_precision": 1.0,
|
| 433 |
+
"eval_recall": 1.0,
|
| 434 |
+
"eval_runtime": 4.2166,
|
| 435 |
+
"eval_samples_per_second": 158.186,
|
| 436 |
+
"eval_steps_per_second": 4.98,
|
| 437 |
+
"step": 501
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.0,
|
| 441 |
+
"eval_accuracy": 1.0,
|
| 442 |
+
"eval_f1": 1.0,
|
| 443 |
+
"eval_loss": 0.01563212461769581,
|
| 444 |
+
"eval_precision": 1.0,
|
| 445 |
+
"eval_recall": 1.0,
|
| 446 |
+
"eval_runtime": 4.1534,
|
| 447 |
+
"eval_samples_per_second": 160.349,
|
| 448 |
+
"eval_steps_per_second": 5.056,
|
| 449 |
+
"step": 501
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.0,
|
| 453 |
+
"eval_accuracy": 1.0,
|
| 454 |
+
"eval_f1": 1.0,
|
| 455 |
+
"eval_loss": 0.015602031722664833,
|
| 456 |
+
"eval_precision": 1.0,
|
| 457 |
+
"eval_recall": 1.0,
|
| 458 |
+
"eval_runtime": 3.7938,
|
| 459 |
+
"eval_samples_per_second": 175.812,
|
| 460 |
+
"eval_steps_per_second": 5.535,
|
| 461 |
+
"step": 501
|
| 462 |
}
|
| 463 |
],
|
| 464 |
"max_steps": 501,
|
valid_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"valid_accuracy": 1.0,
|
| 4 |
+
"valid_f1": 1.0,
|
| 5 |
+
"valid_loss": 0.01563212461769581,
|
| 6 |
+
"valid_precision": 1.0,
|
| 7 |
+
"valid_recall": 1.0,
|
| 8 |
+
"valid_runtime": 4.1534,
|
| 9 |
+
"valid_samples_per_second": 160.349,
|
| 10 |
+
"valid_steps_per_second": 5.056
|
| 11 |
+
}
|