Training in progress, step 2560, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4725595416
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a79993ca3bb2e40d715e49b6365049f27102e49dd8b3a9ce020c6ea5a9f9fe9
|
| 3 |
size 4725595416
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9179193343
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bf2691edb5f20acb6de9eb1f6120c2449bed48ca00eecc968c5be167084b7bb
|
| 3 |
size 9179193343
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c349c1691bbeda5a6b16abd459bd4b17c698c1ae8b87b93b48229ee14acd38e
|
| 3 |
size 14503
|
last-checkpoint/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 sha256:28472ecbb49d175fddb5467d2d36c375ce76e352a7c4d1642d73ecb32735946a
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 512,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -11,502 +11,102 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.02,
|
| 13 |
"learning_rate": 9.962169351263485e-05,
|
| 14 |
-
"loss":
|
| 15 |
"step": 256
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.04,
|
| 19 |
"learning_rate": 9.92433870252697e-05,
|
| 20 |
-
"loss":
|
| 21 |
"step": 512
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.04,
|
| 25 |
-
"eval_loss":
|
| 26 |
-
"eval_runtime":
|
| 27 |
-
"eval_samples_per_second":
|
| 28 |
-
"eval_steps_per_second":
|
| 29 |
"step": 512
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.06,
|
| 33 |
"learning_rate": 9.886508053790455e-05,
|
| 34 |
-
"loss":
|
| 35 |
"step": 768
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 0.08,
|
| 39 |
"learning_rate": 9.848677405053938e-05,
|
| 40 |
-
"loss":
|
| 41 |
"step": 1024
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 0.08,
|
| 45 |
-
"eval_loss":
|
| 46 |
-
"eval_runtime":
|
| 47 |
-
"eval_samples_per_second":
|
| 48 |
-
"eval_steps_per_second":
|
| 49 |
"step": 1024
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 0.09,
|
| 53 |
"learning_rate": 9.810846756317423e-05,
|
| 54 |
-
"loss":
|
| 55 |
"step": 1280
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"epoch": 0.11,
|
| 59 |
"learning_rate": 9.773016107580908e-05,
|
| 60 |
-
"loss":
|
| 61 |
"step": 1536
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 0.11,
|
| 65 |
-
"eval_loss":
|
| 66 |
-
"eval_runtime":
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second":
|
| 69 |
"step": 1536
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.13,
|
| 73 |
"learning_rate": 9.735185458844393e-05,
|
| 74 |
-
"loss":
|
| 75 |
"step": 1792
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.15,
|
| 79 |
"learning_rate": 9.697354810107877e-05,
|
| 80 |
-
"loss":
|
| 81 |
"step": 2048
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.15,
|
| 85 |
-
"eval_loss":
|
| 86 |
-
"eval_runtime":
|
| 87 |
-
"eval_samples_per_second":
|
| 88 |
-
"eval_steps_per_second":
|
| 89 |
"step": 2048
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 0.17,
|
| 93 |
"learning_rate": 9.659524161371362e-05,
|
| 94 |
-
"loss":
|
| 95 |
"step": 2304
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.19,
|
| 99 |
"learning_rate": 9.621693512634847e-05,
|
| 100 |
-
"loss":
|
| 101 |
"step": 2560
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.19,
|
| 105 |
-
"eval_loss":
|
| 106 |
-
"eval_runtime":
|
| 107 |
-
"eval_samples_per_second":
|
| 108 |
-
"eval_steps_per_second":
|
| 109 |
"step": 2560
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 0.21,
|
| 113 |
-
"learning_rate": 9.58386286389833e-05,
|
| 114 |
-
"loss": 20474.4043,
|
| 115 |
-
"step": 2816
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.23,
|
| 119 |
-
"learning_rate": 9.546032215161815e-05,
|
| 120 |
-
"loss": 18948.6875,
|
| 121 |
-
"step": 3072
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.23,
|
| 125 |
-
"eval_loss": 16196.150390625,
|
| 126 |
-
"eval_runtime": 62.7371,
|
| 127 |
-
"eval_samples_per_second": 54.163,
|
| 128 |
-
"eval_steps_per_second": 54.163,
|
| 129 |
-
"step": 3072
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.25,
|
| 133 |
-
"learning_rate": 9.5082015664253e-05,
|
| 134 |
-
"loss": 17958.9785,
|
| 135 |
-
"step": 3328
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.26,
|
| 139 |
-
"learning_rate": 9.470370917688785e-05,
|
| 140 |
-
"loss": 17018.3223,
|
| 141 |
-
"step": 3584
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.26,
|
| 145 |
-
"eval_loss": 15006.568359375,
|
| 146 |
-
"eval_runtime": 59.6957,
|
| 147 |
-
"eval_samples_per_second": 56.922,
|
| 148 |
-
"eval_steps_per_second": 56.922,
|
| 149 |
-
"step": 3584
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.28,
|
| 153 |
-
"learning_rate": 9.43254026895227e-05,
|
| 154 |
-
"loss": 16859.2793,
|
| 155 |
-
"step": 3840
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 0.3,
|
| 159 |
-
"learning_rate": 9.394709620215754e-05,
|
| 160 |
-
"loss": 16723.5449,
|
| 161 |
-
"step": 4096
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 0.3,
|
| 165 |
-
"eval_loss": 14789.91796875,
|
| 166 |
-
"eval_runtime": 59.5641,
|
| 167 |
-
"eval_samples_per_second": 57.048,
|
| 168 |
-
"eval_steps_per_second": 57.048,
|
| 169 |
-
"step": 4096
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 0.32,
|
| 173 |
-
"learning_rate": 9.356878971479238e-05,
|
| 174 |
-
"loss": 16488.6934,
|
| 175 |
-
"step": 4352
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"epoch": 0.34,
|
| 179 |
-
"learning_rate": 9.319048322742722e-05,
|
| 180 |
-
"loss": 16159.4502,
|
| 181 |
-
"step": 4608
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 0.34,
|
| 185 |
-
"eval_loss": 14223.150390625,
|
| 186 |
-
"eval_runtime": 60.4382,
|
| 187 |
-
"eval_samples_per_second": 56.223,
|
| 188 |
-
"eval_steps_per_second": 56.223,
|
| 189 |
-
"step": 4608
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.36,
|
| 193 |
-
"learning_rate": 9.281217674006207e-05,
|
| 194 |
-
"loss": 16155.2217,
|
| 195 |
-
"step": 4864
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.38,
|
| 199 |
-
"learning_rate": 9.243387025269692e-05,
|
| 200 |
-
"loss": 16132.4766,
|
| 201 |
-
"step": 5120
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.38,
|
| 205 |
-
"eval_loss": 14493.603515625,
|
| 206 |
-
"eval_runtime": 61.3546,
|
| 207 |
-
"eval_samples_per_second": 55.383,
|
| 208 |
-
"eval_steps_per_second": 55.383,
|
| 209 |
-
"step": 5120
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 0.4,
|
| 213 |
-
"learning_rate": 9.205556376533177e-05,
|
| 214 |
-
"loss": 16020.0381,
|
| 215 |
-
"step": 5376
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 0.42,
|
| 219 |
-
"learning_rate": 9.167725727796661e-05,
|
| 220 |
-
"loss": 15904.9912,
|
| 221 |
-
"step": 5632
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.42,
|
| 225 |
-
"eval_loss": 14683.6728515625,
|
| 226 |
-
"eval_runtime": 62.3009,
|
| 227 |
-
"eval_samples_per_second": 54.542,
|
| 228 |
-
"eval_steps_per_second": 54.542,
|
| 229 |
-
"step": 5632
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 0.44,
|
| 233 |
-
"learning_rate": 9.129895079060146e-05,
|
| 234 |
-
"loss": 15820.0801,
|
| 235 |
-
"step": 5888
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.45,
|
| 239 |
-
"learning_rate": 9.09206443032363e-05,
|
| 240 |
-
"loss": 15531.0293,
|
| 241 |
-
"step": 6144
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.45,
|
| 245 |
-
"eval_loss": 14102.1162109375,
|
| 246 |
-
"eval_runtime": 59.6921,
|
| 247 |
-
"eval_samples_per_second": 56.925,
|
| 248 |
-
"eval_steps_per_second": 56.925,
|
| 249 |
-
"step": 6144
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.47,
|
| 253 |
-
"learning_rate": 9.054233781587114e-05,
|
| 254 |
-
"loss": 15656.3779,
|
| 255 |
-
"step": 6400
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.49,
|
| 259 |
-
"learning_rate": 9.016403132850599e-05,
|
| 260 |
-
"loss": 15575.4033,
|
| 261 |
-
"step": 6656
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.49,
|
| 265 |
-
"eval_loss": 13737.095703125,
|
| 266 |
-
"eval_runtime": 49.6762,
|
| 267 |
-
"eval_samples_per_second": 68.403,
|
| 268 |
-
"eval_steps_per_second": 68.403,
|
| 269 |
-
"step": 6656
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.51,
|
| 273 |
-
"learning_rate": 8.978572484114084e-05,
|
| 274 |
-
"loss": 15500.876,
|
| 275 |
-
"step": 6912
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 0.53,
|
| 279 |
-
"learning_rate": 8.940741835377569e-05,
|
| 280 |
-
"loss": 15452.5596,
|
| 281 |
-
"step": 7168
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 0.53,
|
| 285 |
-
"eval_loss": 14052.9873046875,
|
| 286 |
-
"eval_runtime": 49.0398,
|
| 287 |
-
"eval_samples_per_second": 69.291,
|
| 288 |
-
"eval_steps_per_second": 69.291,
|
| 289 |
-
"step": 7168
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 0.55,
|
| 293 |
-
"learning_rate": 8.902911186641053e-05,
|
| 294 |
-
"loss": 15443.3691,
|
| 295 |
-
"step": 7424
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 0.57,
|
| 299 |
-
"learning_rate": 8.865080537904538e-05,
|
| 300 |
-
"loss": 15420.5,
|
| 301 |
-
"step": 7680
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 0.57,
|
| 305 |
-
"eval_loss": 13470.451171875,
|
| 306 |
-
"eval_runtime": 48.9981,
|
| 307 |
-
"eval_samples_per_second": 69.35,
|
| 308 |
-
"eval_steps_per_second": 69.35,
|
| 309 |
-
"step": 7680
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.59,
|
| 313 |
-
"learning_rate": 8.827249889168022e-05,
|
| 314 |
-
"loss": 15402.9678,
|
| 315 |
-
"step": 7936
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.61,
|
| 319 |
-
"learning_rate": 8.789419240431506e-05,
|
| 320 |
-
"loss": 15077.2871,
|
| 321 |
-
"step": 8192
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.61,
|
| 325 |
-
"eval_loss": 13587.75,
|
| 326 |
-
"eval_runtime": 50.6149,
|
| 327 |
-
"eval_samples_per_second": 67.134,
|
| 328 |
-
"eval_steps_per_second": 67.134,
|
| 329 |
-
"step": 8192
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 0.62,
|
| 333 |
-
"learning_rate": 8.751588591694991e-05,
|
| 334 |
-
"loss": 14985.3994,
|
| 335 |
-
"step": 8448
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 0.64,
|
| 339 |
-
"learning_rate": 8.713757942958476e-05,
|
| 340 |
-
"loss": 15089.6094,
|
| 341 |
-
"step": 8704
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 0.64,
|
| 345 |
-
"eval_loss": 13345.4736328125,
|
| 346 |
-
"eval_runtime": 49.1305,
|
| 347 |
-
"eval_samples_per_second": 69.163,
|
| 348 |
-
"eval_steps_per_second": 69.163,
|
| 349 |
-
"step": 8704
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 0.66,
|
| 353 |
-
"learning_rate": 8.67592729422196e-05,
|
| 354 |
-
"loss": 15185.1504,
|
| 355 |
-
"step": 8960
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 0.68,
|
| 359 |
-
"learning_rate": 8.638096645485444e-05,
|
| 360 |
-
"loss": 15208.8115,
|
| 361 |
-
"step": 9216
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.68,
|
| 365 |
-
"eval_loss": 13608.46875,
|
| 366 |
-
"eval_runtime": 49.1786,
|
| 367 |
-
"eval_samples_per_second": 69.095,
|
| 368 |
-
"eval_steps_per_second": 69.095,
|
| 369 |
-
"step": 9216
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.7,
|
| 373 |
-
"learning_rate": 8.600265996748929e-05,
|
| 374 |
-
"loss": 15028.958,
|
| 375 |
-
"step": 9472
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.72,
|
| 379 |
-
"learning_rate": 8.562435348012414e-05,
|
| 380 |
-
"loss": 14966.6143,
|
| 381 |
-
"step": 9728
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.72,
|
| 385 |
-
"eval_loss": 12910.7265625,
|
| 386 |
-
"eval_runtime": 57.0213,
|
| 387 |
-
"eval_samples_per_second": 59.592,
|
| 388 |
-
"eval_steps_per_second": 59.592,
|
| 389 |
-
"step": 9728
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.74,
|
| 393 |
-
"learning_rate": 8.524604699275897e-05,
|
| 394 |
-
"loss": 14777.6895,
|
| 395 |
-
"step": 9984
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.76,
|
| 399 |
-
"learning_rate": 8.486774050539382e-05,
|
| 400 |
-
"loss": 14924.749,
|
| 401 |
-
"step": 10240
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.76,
|
| 405 |
-
"eval_loss": 13132.9765625,
|
| 406 |
-
"eval_runtime": 49.0092,
|
| 407 |
-
"eval_samples_per_second": 69.334,
|
| 408 |
-
"eval_steps_per_second": 69.334,
|
| 409 |
-
"step": 10240
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 0.78,
|
| 413 |
-
"learning_rate": 8.448943401802867e-05,
|
| 414 |
-
"loss": 14694.0498,
|
| 415 |
-
"step": 10496
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 0.79,
|
| 419 |
-
"learning_rate": 8.411112753066351e-05,
|
| 420 |
-
"loss": 14639.1904,
|
| 421 |
-
"step": 10752
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 0.79,
|
| 425 |
-
"eval_loss": 13389.201171875,
|
| 426 |
-
"eval_runtime": 53.5263,
|
| 427 |
-
"eval_samples_per_second": 63.483,
|
| 428 |
-
"eval_steps_per_second": 63.483,
|
| 429 |
-
"step": 10752
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.81,
|
| 433 |
-
"learning_rate": 8.373282104329836e-05,
|
| 434 |
-
"loss": 14814.9424,
|
| 435 |
-
"step": 11008
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.83,
|
| 439 |
-
"learning_rate": 8.335451455593321e-05,
|
| 440 |
-
"loss": 14682.3984,
|
| 441 |
-
"step": 11264
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.83,
|
| 445 |
-
"eval_loss": 13232.8876953125,
|
| 446 |
-
"eval_runtime": 48.9422,
|
| 447 |
-
"eval_samples_per_second": 69.429,
|
| 448 |
-
"eval_steps_per_second": 69.429,
|
| 449 |
-
"step": 11264
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 0.85,
|
| 453 |
-
"learning_rate": 8.297620806856804e-05,
|
| 454 |
-
"loss": 14631.1221,
|
| 455 |
-
"step": 11520
|
| 456 |
-
},
|
| 457 |
-
{
|
| 458 |
-
"epoch": 0.87,
|
| 459 |
-
"learning_rate": 8.259790158120289e-05,
|
| 460 |
-
"loss": 14661.7021,
|
| 461 |
-
"step": 11776
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 0.87,
|
| 465 |
-
"eval_loss": 13184.365234375,
|
| 466 |
-
"eval_runtime": 49.4282,
|
| 467 |
-
"eval_samples_per_second": 68.746,
|
| 468 |
-
"eval_steps_per_second": 68.746,
|
| 469 |
-
"step": 11776
|
| 470 |
-
},
|
| 471 |
-
{
|
| 472 |
-
"epoch": 0.89,
|
| 473 |
-
"learning_rate": 8.221959509383774e-05,
|
| 474 |
-
"loss": 14565.9648,
|
| 475 |
-
"step": 12032
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 0.91,
|
| 479 |
-
"learning_rate": 8.184128860647259e-05,
|
| 480 |
-
"loss": 14608.0898,
|
| 481 |
-
"step": 12288
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.91,
|
| 485 |
-
"eval_loss": 13070.6923828125,
|
| 486 |
-
"eval_runtime": 49.197,
|
| 487 |
-
"eval_samples_per_second": 69.069,
|
| 488 |
-
"eval_steps_per_second": 69.069,
|
| 489 |
-
"step": 12288
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.93,
|
| 493 |
-
"learning_rate": 8.146298211910744e-05,
|
| 494 |
-
"loss": 14447.6699,
|
| 495 |
-
"step": 12544
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.95,
|
| 499 |
-
"learning_rate": 8.108467563174228e-05,
|
| 500 |
-
"loss": 14423.6045,
|
| 501 |
-
"step": 12800
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.95,
|
| 505 |
-
"eval_loss": 12849.525390625,
|
| 506 |
-
"eval_runtime": 48.9783,
|
| 507 |
-
"eval_samples_per_second": 69.378,
|
| 508 |
-
"eval_steps_per_second": 69.378,
|
| 509 |
-
"step": 12800
|
| 510 |
}
|
| 511 |
],
|
| 512 |
"logging_steps": 256,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 19020.044921875,
|
| 3 |
+
"best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-2560",
|
| 4 |
+
"epoch": 0.18914450899082907,
|
| 5 |
"eval_steps": 512,
|
| 6 |
+
"global_step": 2560,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.02,
|
| 13 |
"learning_rate": 9.962169351263485e-05,
|
| 14 |
+
"loss": 122076.6875,
|
| 15 |
"step": 256
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.04,
|
| 19 |
"learning_rate": 9.92433870252697e-05,
|
| 20 |
+
"loss": 75620.8047,
|
| 21 |
"step": 512
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.04,
|
| 25 |
+
"eval_loss": 67218.640625,
|
| 26 |
+
"eval_runtime": 49.08,
|
| 27 |
+
"eval_samples_per_second": 69.234,
|
| 28 |
+
"eval_steps_per_second": 69.234,
|
| 29 |
"step": 512
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.06,
|
| 33 |
"learning_rate": 9.886508053790455e-05,
|
| 34 |
+
"loss": 71143.4766,
|
| 35 |
"step": 768
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 0.08,
|
| 39 |
"learning_rate": 9.848677405053938e-05,
|
| 40 |
+
"loss": 65495.2617,
|
| 41 |
"step": 1024
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 0.08,
|
| 45 |
+
"eval_loss": 55127.15234375,
|
| 46 |
+
"eval_runtime": 57.5577,
|
| 47 |
+
"eval_samples_per_second": 59.036,
|
| 48 |
+
"eval_steps_per_second": 59.036,
|
| 49 |
"step": 1024
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 0.09,
|
| 53 |
"learning_rate": 9.810846756317423e-05,
|
| 54 |
+
"loss": 57857.6445,
|
| 55 |
"step": 1280
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"epoch": 0.11,
|
| 59 |
"learning_rate": 9.773016107580908e-05,
|
| 60 |
+
"loss": 49931.2188,
|
| 61 |
"step": 1536
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 0.11,
|
| 65 |
+
"eval_loss": 44795.0859375,
|
| 66 |
+
"eval_runtime": 62.2532,
|
| 67 |
+
"eval_samples_per_second": 54.584,
|
| 68 |
+
"eval_steps_per_second": 54.584,
|
| 69 |
"step": 1536
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.13,
|
| 73 |
"learning_rate": 9.735185458844393e-05,
|
| 74 |
+
"loss": 42072.0,
|
| 75 |
"step": 1792
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.15,
|
| 79 |
"learning_rate": 9.697354810107877e-05,
|
| 80 |
+
"loss": 35028.5938,
|
| 81 |
"step": 2048
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.15,
|
| 85 |
+
"eval_loss": 29700.298828125,
|
| 86 |
+
"eval_runtime": 72.4329,
|
| 87 |
+
"eval_samples_per_second": 46.912,
|
| 88 |
+
"eval_steps_per_second": 46.912,
|
| 89 |
"step": 2048
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 0.17,
|
| 93 |
"learning_rate": 9.659524161371362e-05,
|
| 94 |
+
"loss": 27458.9082,
|
| 95 |
"step": 2304
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.19,
|
| 99 |
"learning_rate": 9.621693512634847e-05,
|
| 100 |
+
"loss": 21147.1016,
|
| 101 |
"step": 2560
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.19,
|
| 105 |
+
"eval_loss": 19020.044921875,
|
| 106 |
+
"eval_runtime": 49.0881,
|
| 107 |
+
"eval_samples_per_second": 69.222,
|
| 108 |
+
"eval_steps_per_second": 69.222,
|
| 109 |
"step": 2560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
}
|
| 111 |
],
|
| 112 |
"logging_steps": 256,
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4271
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb40828a1d4ffeac31865af000ab0d03e5851c44943c5a9b31dbbf1ac5027a97
|
| 3 |
size 4271
|