Commit
•
e2d31cb
1
Parent(s):
79b47b3
huggingartists
Browse files- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +116 -370
- training_args.bin +1 -1
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 1.
|
|
|
|
| 1 |
+
{"eval_loss": 1.5699154138565063, "eval_runtime": 1.6396, "eval_samples_per_second": 40.864, "eval_steps_per_second": 5.489, "epoch": 19.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6c6d9455a9248044f8aa6d328cfc1cacfec66afa20d954f5b23c85da87bb276
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0547fe049e205f9d46a99245e89e28e83958fd72a8d9fa5b43bf74f1ac59c7d0
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3b234073b5cdc8b007569ead18a8e3db6e74c4f98109b5edb6969fffac2bc99
|
| 3 |
size 510396521
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48674dcd750e9b55c532cef24aef9f7d2e9eb9e19cbfa1a48641e0750f3f3e85
|
| 3 |
size 14567
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:425621844a56a29950ce1fbf1c301ca1c67a62f1420b3598db0e6910a94a3c8c
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,592 +1,338 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/headie-one/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.11,
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss":
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.21,
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.32,
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss":
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.43,
|
| 30 |
-
"learning_rate": 8.
|
| 31 |
-
"loss":
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.53,
|
| 36 |
-
"learning_rate": 6.
|
| 37 |
-
"loss":
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.64,
|
| 42 |
-
"learning_rate": 3.
|
| 43 |
-
"loss":
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.74,
|
| 48 |
-
"learning_rate": 2.
|
| 49 |
-
"loss":
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.85,
|
| 54 |
-
"learning_rate": 7.
|
| 55 |
-
"loss":
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.96,
|
| 60 |
"learning_rate": 6.1208431258209e-07,
|
| 61 |
-
"loss":
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.0,
|
| 66 |
-
"eval_loss":
|
| 67 |
-
"eval_runtime": 1.
|
| 68 |
-
"eval_samples_per_second":
|
| 69 |
-
"eval_steps_per_second":
|
| 70 |
"step": 47
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 1.06,
|
| 74 |
-
"learning_rate": 1.
|
| 75 |
-
"loss":
|
| 76 |
"step": 50
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 1.17,
|
| 80 |
-
"learning_rate": 9.
|
| 81 |
-
"loss":
|
| 82 |
"step": 55
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 1.28,
|
| 86 |
-
"learning_rate": 2.
|
| 87 |
-
"loss":
|
| 88 |
"step": 60
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.38,
|
| 92 |
-
"learning_rate": 4.
|
| 93 |
-
"loss":
|
| 94 |
"step": 65
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 1.49,
|
| 98 |
-
"learning_rate": 6.
|
| 99 |
-
"loss":
|
| 100 |
"step": 70
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 1.6,
|
| 104 |
-
"learning_rate": 8.
|
| 105 |
-
"loss":
|
| 106 |
"step": 75
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 1.7,
|
| 110 |
-
"learning_rate": 0.
|
| 111 |
-
"loss":
|
| 112 |
"step": 80
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.81,
|
| 116 |
-
"learning_rate": 0.
|
| 117 |
-
"loss":
|
| 118 |
"step": 85
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 1.91,
|
| 122 |
"learning_rate": 0.00013476258540873022,
|
| 123 |
-
"loss":
|
| 124 |
"step": 90
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 2.0,
|
| 128 |
-
"eval_loss":
|
| 129 |
-
"eval_runtime": 1.
|
| 130 |
-
"eval_samples_per_second":
|
| 131 |
-
"eval_steps_per_second":
|
| 132 |
"step": 94
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.02,
|
| 136 |
"learning_rate": 0.00013704680787354832,
|
| 137 |
-
"loss":
|
| 138 |
"step": 95
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 2.13,
|
| 142 |
"learning_rate": 0.00013175658222600302,
|
| 143 |
-
"loss":
|
| 144 |
"step": 100
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 2.23,
|
| 148 |
-
"learning_rate": 0.
|
| 149 |
-
"loss":
|
| 150 |
"step": 105
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 2.34,
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss":
|
| 156 |
"step": 110
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 2.45,
|
| 160 |
-
"learning_rate": 8.
|
| 161 |
-
"loss":
|
| 162 |
"step": 115
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 2.55,
|
| 166 |
-
"learning_rate": 5.
|
| 167 |
-
"loss":
|
| 168 |
"step": 120
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 2.66,
|
| 172 |
-
"learning_rate": 3.
|
| 173 |
-
"loss":
|
| 174 |
"step": 125
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.77,
|
| 178 |
-
"learning_rate": 1.
|
| 179 |
-
"loss":
|
| 180 |
"step": 130
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.87,
|
| 184 |
-
"learning_rate": 5.
|
| 185 |
-
"loss":
|
| 186 |
"step": 135
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 2.98,
|
| 190 |
-
"learning_rate": 1.
|
| 191 |
-
"loss":
|
| 192 |
"step": 140
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 3.0,
|
| 196 |
-
"eval_loss":
|
| 197 |
-
"eval_runtime": 1.
|
| 198 |
-
"eval_samples_per_second":
|
| 199 |
-
"eval_steps_per_second": 5.
|
| 200 |
"step": 141
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.09,
|
| 204 |
-
"learning_rate": 2.
|
| 205 |
-
"loss":
|
| 206 |
"step": 145
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 3.19,
|
| 210 |
-
"learning_rate": 1.
|
| 211 |
-
"loss":
|
| 212 |
"step": 150
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 3.3,
|
| 216 |
-
"learning_rate": 2.
|
| 217 |
-
"loss":
|
| 218 |
"step": 155
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 3.4,
|
| 222 |
-
"learning_rate": 4.
|
| 223 |
-
"loss":
|
| 224 |
"step": 160
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 3.51,
|
| 228 |
-
"learning_rate": 7.
|
| 229 |
-
"loss":
|
| 230 |
"step": 165
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 3.62,
|
| 234 |
-
"learning_rate": 9.
|
| 235 |
-
"loss":
|
| 236 |
"step": 170
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 3.72,
|
| 240 |
-
"learning_rate": 0.
|
| 241 |
-
"loss":
|
| 242 |
"step": 175
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 3.83,
|
| 246 |
-
"learning_rate": 0.
|
| 247 |
-
"loss":
|
| 248 |
"step": 180
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 3.94,
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss":
|
| 254 |
"step": 185
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 4.0,
|
| 258 |
-
"eval_loss":
|
| 259 |
-
"eval_runtime": 1.
|
| 260 |
-
"eval_samples_per_second":
|
| 261 |
-
"eval_steps_per_second": 5.
|
| 262 |
"step": 188
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 4.04,
|
| 266 |
-
"learning_rate": 0.
|
| 267 |
-
"loss":
|
| 268 |
"step": 190
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 4.15,
|
| 272 |
-
"learning_rate": 0.
|
| 273 |
-
"loss":
|
| 274 |
"step": 195
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 4.26,
|
| 278 |
-
"learning_rate": 0.
|
| 279 |
-
"loss":
|
| 280 |
"step": 200
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 4.36,
|
| 284 |
-
"learning_rate": 9.
|
| 285 |
-
"loss":
|
| 286 |
"step": 205
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 4.47,
|
| 290 |
-
"learning_rate": 7.
|
| 291 |
-
"loss":
|
| 292 |
"step": 210
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 4.57,
|
| 296 |
-
"learning_rate": 5.
|
| 297 |
-
"loss":
|
| 298 |
"step": 215
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 4.68,
|
| 302 |
-
"learning_rate": 3.
|
| 303 |
-
"loss":
|
| 304 |
"step": 220
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.79,
|
| 308 |
-
"learning_rate": 1.
|
| 309 |
-
"loss":
|
| 310 |
"step": 225
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 4.89,
|
| 314 |
-
"learning_rate": 3.
|
| 315 |
-
"loss":
|
| 316 |
"step": 230
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 5.0,
|
| 320 |
"learning_rate": 0.0,
|
| 321 |
-
"loss":
|
| 322 |
"step": 235
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 5.0,
|
| 326 |
-
"eval_loss": 1.
|
| 327 |
-
"eval_runtime": 1.
|
| 328 |
-
"eval_samples_per_second":
|
| 329 |
-
"eval_steps_per_second": 5.
|
| 330 |
"step": 235
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 5.11,
|
| 334 |
-
"learning_rate": 3.7957003156967485e-06,
|
| 335 |
-
"loss": 1.6773,
|
| 336 |
-
"step": 240
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 5.21,
|
| 340 |
-
"learning_rate": 1.4762762169883802e-05,
|
| 341 |
-
"loss": 1.9066,
|
| 342 |
-
"step": 245
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 5.32,
|
| 346 |
-
"learning_rate": 3.168755057299255e-05,
|
| 347 |
-
"loss": 1.7702,
|
| 348 |
-
"step": 250
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 5.43,
|
| 352 |
-
"learning_rate": 5.269713769164743e-05,
|
| 353 |
-
"loss": 1.7718,
|
| 354 |
-
"step": 255
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 5.53,
|
| 358 |
-
"learning_rate": 7.546656444541325e-05,
|
| 359 |
-
"loss": 1.6923,
|
| 360 |
-
"step": 260
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 5.64,
|
| 364 |
-
"learning_rate": 9.747612470258363e-05,
|
| 365 |
-
"loss": 1.8134,
|
| 366 |
-
"step": 265
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 5.74,
|
| 370 |
-
"learning_rate": 0.0001162902005384805,
|
| 371 |
-
"loss": 1.6943,
|
| 372 |
-
"step": 270
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 5.85,
|
| 376 |
-
"learning_rate": 0.00012982679213998787,
|
| 377 |
-
"loss": 1.7474,
|
| 378 |
-
"step": 275
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 5.96,
|
| 382 |
-
"learning_rate": 0.00013658791568741792,
|
| 383 |
-
"loss": 1.664,
|
| 384 |
-
"step": 280
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 6.0,
|
| 388 |
-
"eval_loss": 1.8830074071884155,
|
| 389 |
-
"eval_runtime": 1.6028,
|
| 390 |
-
"eval_samples_per_second": 41.801,
|
| 391 |
-
"eval_steps_per_second": 5.615,
|
| 392 |
-
"step": 282
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 6.06,
|
| 396 |
-
"learning_rate": 0.00013582537296550986,
|
| 397 |
-
"loss": 1.7593,
|
| 398 |
-
"step": 285
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 6.17,
|
| 402 |
-
"learning_rate": 0.00012762354833724559,
|
| 403 |
-
"loss": 1.68,
|
| 404 |
-
"step": 290
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 6.28,
|
| 408 |
-
"learning_rate": 0.0001128900706169339,
|
| 409 |
-
"loss": 1.5629,
|
| 410 |
-
"step": 295
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 6.38,
|
| 414 |
-
"learning_rate": 9.325537321665346e-05,
|
| 415 |
-
"loss": 1.5448,
|
| 416 |
-
"step": 300
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 6.49,
|
| 420 |
-
"learning_rate": 7.089226742272658e-05,
|
| 421 |
-
"loss": 1.5643,
|
| 422 |
-
"step": 305
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 6.6,
|
| 426 |
-
"learning_rate": 4.827549515124539e-05,
|
| 427 |
-
"loss": 1.5585,
|
| 428 |
-
"step": 310
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 6.7,
|
| 432 |
-
"learning_rate": 2.7907869511566348e-05,
|
| 433 |
-
"loss": 1.724,
|
| 434 |
-
"step": 315
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 6.81,
|
| 438 |
-
"learning_rate": 1.2043308960555334e-05,
|
| 439 |
-
"loss": 1.3896,
|
| 440 |
-
"step": 320
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 6.91,
|
| 444 |
-
"learning_rate": 2.437414591269752e-06,
|
| 445 |
-
"loss": 1.4656,
|
| 446 |
-
"step": 325
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 7.0,
|
| 450 |
-
"eval_loss": 1.7848814725875854,
|
| 451 |
-
"eval_runtime": 1.6359,
|
| 452 |
-
"eval_samples_per_second": 40.956,
|
| 453 |
-
"eval_steps_per_second": 5.502,
|
| 454 |
-
"step": 329
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"epoch": 7.02,
|
| 458 |
-
"learning_rate": 1.5319212645167772e-07,
|
| 459 |
-
"loss": 1.4519,
|
| 460 |
-
"step": 330
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 7.13,
|
| 464 |
-
"learning_rate": 5.443417773996994e-06,
|
| 465 |
-
"loss": 1.5894,
|
| 466 |
-
"step": 335
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 7.23,
|
| 470 |
-
"learning_rate": 1.772266555255011e-05,
|
| 471 |
-
"loss": 1.377,
|
| 472 |
-
"step": 340
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 7.34,
|
| 476 |
-
"learning_rate": 3.563209159419346e-05,
|
| 477 |
-
"loss": 1.4357,
|
| 478 |
-
"step": 345
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 7.45,
|
| 482 |
-
"learning_rate": 5.718980627559723e-05,
|
| 483 |
-
"loss": 1.5269,
|
| 484 |
-
"step": 350
|
| 485 |
-
},
|
| 486 |
-
{
|
| 487 |
-
"epoch": 7.55,
|
| 488 |
-
"learning_rate": 8.001019372440265e-05,
|
| 489 |
-
"loss": 1.4501,
|
| 490 |
-
"step": 355
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 7.66,
|
| 494 |
-
"learning_rate": 0.00010156790840580641,
|
| 495 |
-
"loss": 1.2612,
|
| 496 |
-
"step": 360
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 7.77,
|
| 500 |
-
"learning_rate": 0.0001194773344474498,
|
| 501 |
-
"loss": 1.3453,
|
| 502 |
-
"step": 365
|
| 503 |
-
},
|
| 504 |
-
{
|
| 505 |
-
"epoch": 7.87,
|
| 506 |
-
"learning_rate": 0.00013175658222600294,
|
| 507 |
-
"loss": 1.4728,
|
| 508 |
-
"step": 370
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 7.98,
|
| 512 |
-
"learning_rate": 0.00013704680787354832,
|
| 513 |
-
"loss": 1.4687,
|
| 514 |
-
"step": 375
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 8.0,
|
| 518 |
-
"eval_loss": 1.76621675491333,
|
| 519 |
-
"eval_runtime": 1.6517,
|
| 520 |
-
"eval_samples_per_second": 40.565,
|
| 521 |
-
"eval_steps_per_second": 5.449,
|
| 522 |
-
"step": 376
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 8.09,
|
| 526 |
-
"learning_rate": 0.00013476258540873022,
|
| 527 |
-
"loss": 1.4856,
|
| 528 |
-
"step": 380
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 8.19,
|
| 532 |
-
"learning_rate": 0.00012515669103944473,
|
| 533 |
-
"loss": 1.2361,
|
| 534 |
-
"step": 385
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 8.3,
|
| 538 |
-
"learning_rate": 0.00010929213048843395,
|
| 539 |
-
"loss": 1.1886,
|
| 540 |
-
"step": 390
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 8.4,
|
| 544 |
-
"learning_rate": 8.892450484875472e-05,
|
| 545 |
-
"loss": 1.3658,
|
| 546 |
-
"step": 395
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"epoch": 8.51,
|
| 550 |
-
"learning_rate": 6.630773257727356e-05,
|
| 551 |
-
"loss": 1.3489,
|
| 552 |
-
"step": 400
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 8.62,
|
| 556 |
-
"learning_rate": 4.394462678334666e-05,
|
| 557 |
-
"loss": 1.2336,
|
| 558 |
-
"step": 405
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 8.72,
|
| 562 |
-
"learning_rate": 2.4309929383066207e-05,
|
| 563 |
-
"loss": 1.2826,
|
| 564 |
-
"step": 410
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 8.83,
|
| 568 |
-
"learning_rate": 9.576451662754362e-06,
|
| 569 |
-
"loss": 1.381,
|
| 570 |
-
"step": 415
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 8.94,
|
| 574 |
-
"learning_rate": 1.3746270344902175e-06,
|
| 575 |
-
"loss": 1.2151,
|
| 576 |
-
"step": 420
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 9.0,
|
| 580 |
-
"eval_loss": 1.6784825325012207,
|
| 581 |
-
"eval_runtime": 1.678,
|
| 582 |
-
"eval_samples_per_second": 39.927,
|
| 583 |
-
"eval_steps_per_second": 5.363,
|
| 584 |
-
"step": 423
|
| 585 |
}
|
| 586 |
],
|
| 587 |
-
"max_steps":
|
| 588 |
-
"num_train_epochs":
|
| 589 |
-
"total_flos":
|
| 590 |
"trial_name": null,
|
| 591 |
"trial_params": null
|
| 592 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.5699154138565063,
|
| 3 |
+
"best_model_checkpoint": "output/headie-one/checkpoint-235",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 235,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 0.00013340429968430325,
|
| 13 |
+
"loss": 1.271,
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 0.00012243723783011623,
|
| 19 |
+
"loss": 1.1922,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 0.00010551244942700729,
|
| 25 |
+
"loss": 1.0699,
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 8.450286230835261e-05,
|
| 31 |
+
"loss": 1.0247,
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 6.17334355545868e-05,
|
| 37 |
+
"loss": 0.9594,
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.64,
|
| 42 |
+
"learning_rate": 3.9723875297416415e-05,
|
| 43 |
+
"loss": 0.9693,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.74,
|
| 48 |
+
"learning_rate": 2.090979946151953e-05,
|
| 49 |
+
"loss": 1.106,
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.85,
|
| 54 |
+
"learning_rate": 7.373207860012262e-06,
|
| 55 |
+
"loss": 1.0108,
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.96,
|
| 60 |
"learning_rate": 6.1208431258209e-07,
|
| 61 |
+
"loss": 1.0614,
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.0,
|
| 66 |
+
"eval_loss": 1.6016333103179932,
|
| 67 |
+
"eval_runtime": 1.5387,
|
| 68 |
+
"eval_samples_per_second": 43.543,
|
| 69 |
+
"eval_steps_per_second": 5.849,
|
| 70 |
"step": 47
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 1.06,
|
| 74 |
+
"learning_rate": 1.3746270344901794e-06,
|
| 75 |
+
"loss": 1.1841,
|
| 76 |
"step": 50
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 1.17,
|
| 80 |
+
"learning_rate": 9.5764516627544e-06,
|
| 81 |
+
"loss": 1.0057,
|
| 82 |
"step": 55
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 1.28,
|
| 86 |
+
"learning_rate": 2.4309929383065895e-05,
|
| 87 |
+
"loss": 0.8867,
|
| 88 |
"step": 60
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.38,
|
| 92 |
+
"learning_rate": 4.394462678334651e-05,
|
| 93 |
+
"loss": 1.0264,
|
| 94 |
"step": 65
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 1.49,
|
| 98 |
+
"learning_rate": 6.630773257727362e-05,
|
| 99 |
+
"loss": 0.9567,
|
| 100 |
"step": 70
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 1.6,
|
| 104 |
+
"learning_rate": 8.892450484875433e-05,
|
| 105 |
+
"loss": 0.8565,
|
| 106 |
"step": 75
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 1.7,
|
| 110 |
+
"learning_rate": 0.00010929213048843382,
|
| 111 |
+
"loss": 1.0029,
|
| 112 |
"step": 80
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.81,
|
| 116 |
+
"learning_rate": 0.00012515669103944463,
|
| 117 |
+
"loss": 1.0274,
|
| 118 |
"step": 85
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 1.91,
|
| 122 |
"learning_rate": 0.00013476258540873022,
|
| 123 |
+
"loss": 0.9839,
|
| 124 |
"step": 90
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 2.0,
|
| 128 |
+
"eval_loss": 1.6458494663238525,
|
| 129 |
+
"eval_runtime": 1.5583,
|
| 130 |
+
"eval_samples_per_second": 42.996,
|
| 131 |
+
"eval_steps_per_second": 5.776,
|
| 132 |
"step": 94
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.02,
|
| 136 |
"learning_rate": 0.00013704680787354832,
|
| 137 |
+
"loss": 0.9767,
|
| 138 |
"step": 95
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 2.13,
|
| 142 |
"learning_rate": 0.00013175658222600302,
|
| 143 |
+
"loss": 1.1312,
|
| 144 |
"step": 100
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 2.23,
|
| 148 |
+
"learning_rate": 0.00011947733444745008,
|
| 149 |
+
"loss": 0.7833,
|
| 150 |
"step": 105
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 2.34,
|
| 154 |
+
"learning_rate": 0.00010156790840580658,
|
| 155 |
+
"loss": 0.8376,
|
| 156 |
"step": 110
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 2.45,
|
| 160 |
+
"learning_rate": 8.001019372440257e-05,
|
| 161 |
+
"loss": 0.9393,
|
| 162 |
"step": 115
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 2.55,
|
| 166 |
+
"learning_rate": 5.71898062755974e-05,
|
| 167 |
+
"loss": 0.8203,
|
| 168 |
"step": 120
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 2.66,
|
| 172 |
+
"learning_rate": 3.5632091594193825e-05,
|
| 173 |
+
"loss": 0.9363,
|
| 174 |
"step": 125
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.77,
|
| 178 |
+
"learning_rate": 1.7722665552550217e-05,
|
| 179 |
+
"loss": 0.9023,
|
| 180 |
"step": 130
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.87,
|
| 184 |
+
"learning_rate": 5.443417773996963e-06,
|
| 185 |
+
"loss": 0.7999,
|
| 186 |
"step": 135
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 2.98,
|
| 190 |
+
"learning_rate": 1.5319212645170819e-07,
|
| 191 |
+
"loss": 0.8643,
|
| 192 |
"step": 140
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 3.0,
|
| 196 |
+
"eval_loss": 1.5993356704711914,
|
| 197 |
+
"eval_runtime": 1.5942,
|
| 198 |
+
"eval_samples_per_second": 42.027,
|
| 199 |
+
"eval_steps_per_second": 5.645,
|
| 200 |
"step": 141
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.09,
|
| 204 |
+
"learning_rate": 2.4374145912697747e-06,
|
| 205 |
+
"loss": 0.6501,
|
| 206 |
"step": 145
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 3.19,
|
| 210 |
+
"learning_rate": 1.204330896055538e-05,
|
| 211 |
+
"loss": 0.7052,
|
| 212 |
"step": 150
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 3.3,
|
| 216 |
+
"learning_rate": 2.7907869511566212e-05,
|
| 217 |
+
"loss": 0.9473,
|
| 218 |
"step": 155
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 3.4,
|
| 222 |
+
"learning_rate": 4.8275495151245236e-05,
|
| 223 |
+
"loss": 0.7318,
|
| 224 |
"step": 160
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 3.51,
|
| 228 |
+
"learning_rate": 7.08922674227264e-05,
|
| 229 |
+
"loss": 0.7595,
|
| 230 |
"step": 165
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 3.62,
|
| 234 |
+
"learning_rate": 9.325537321665307e-05,
|
| 235 |
+
"loss": 0.8141,
|
| 236 |
"step": 170
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 3.72,
|
| 240 |
+
"learning_rate": 0.00011289007061693377,
|
| 241 |
+
"loss": 0.7721,
|
| 242 |
"step": 175
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 3.83,
|
| 246 |
+
"learning_rate": 0.0001276235483372456,
|
| 247 |
+
"loss": 0.8703,
|
| 248 |
"step": 180
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 3.94,
|
| 252 |
+
"learning_rate": 0.00013582537296550983,
|
| 253 |
+
"loss": 0.8111,
|
| 254 |
"step": 185
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 4.0,
|
| 258 |
+
"eval_loss": 1.582382082939148,
|
| 259 |
+
"eval_runtime": 1.6284,
|
| 260 |
+
"eval_samples_per_second": 41.144,
|
| 261 |
+
"eval_steps_per_second": 5.527,
|
| 262 |
"step": 188
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 4.04,
|
| 266 |
+
"learning_rate": 0.00013658791568741795,
|
| 267 |
+
"loss": 0.8595,
|
| 268 |
"step": 190
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 4.15,
|
| 272 |
+
"learning_rate": 0.00012982679213998795,
|
| 273 |
+
"loss": 0.6313,
|
| 274 |
"step": 195
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 4.26,
|
| 278 |
+
"learning_rate": 0.00011629020053848043,
|
| 279 |
+
"loss": 0.8127,
|
| 280 |
"step": 200
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 4.36,
|
| 284 |
+
"learning_rate": 9.747612470258399e-05,
|
| 285 |
+
"loss": 0.8002,
|
| 286 |
"step": 205
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 4.47,
|
| 290 |
+
"learning_rate": 7.546656444541318e-05,
|
| 291 |
+
"loss": 0.7541,
|
| 292 |
"step": 210
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 4.57,
|
| 296 |
+
"learning_rate": 5.269713769164736e-05,
|
| 297 |
+
"loss": 0.7412,
|
| 298 |
"step": 215
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 4.68,
|
| 302 |
+
"learning_rate": 3.1687550572992684e-05,
|
| 303 |
+
"loss": 0.6833,
|
| 304 |
"step": 220
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.79,
|
| 308 |
+
"learning_rate": 1.4762762169884062e-05,
|
| 309 |
+
"loss": 0.7674,
|
| 310 |
"step": 225
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 4.89,
|
| 314 |
+
"learning_rate": 3.795700315696802e-06,
|
| 315 |
+
"loss": 0.6441,
|
| 316 |
"step": 230
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 5.0,
|
| 320 |
"learning_rate": 0.0,
|
| 321 |
+
"loss": 0.761,
|
| 322 |
"step": 235
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 5.0,
|
| 326 |
+
"eval_loss": 1.5699154138565063,
|
| 327 |
+
"eval_runtime": 1.6286,
|
| 328 |
+
"eval_samples_per_second": 41.139,
|
| 329 |
+
"eval_steps_per_second": 5.526,
|
| 330 |
"step": 235
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 331 |
}
|
| 332 |
],
|
| 333 |
+
"max_steps": 893,
|
| 334 |
+
"num_train_epochs": 19,
|
| 335 |
+
"total_flos": 244308049920000.0,
|
| 336 |
"trial_name": null,
|
| 337 |
"trial_params": null
|
| 338 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3311
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:069f57f162316ae065f1862c62495b43d5890dbecac1d9475fdbff65ca730f07
|
| 3 |
size 3311
|