Commit
·
5d3abcb
1
Parent(s):
9908fcf
Upload 8 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +112 -672
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995641861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010cc660b5d560447c7fb8b57393b8f97dba3cba806dcec5ee0218894aebf79d
|
| 3 |
size 995641861
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497807197
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8292a97db24ad842f8357890c37607ffdb8c0abbf25b087a8cc581fd45f68c4
|
| 3 |
size 497807197
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fbc44877a85dc9e31508ab5cdcb4b09e15e4ccd881628820393d3ed5e0b4726
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:272d9d323ca9bc4225a532f1ca51900b269e2ae9a9366402febf725ced99fda9
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,743 +1,183 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate": 9.
|
| 14 |
-
"loss": 3.
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 9.
|
| 20 |
-
"loss":
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.13,
|
| 25 |
-
"learning_rate": 9.836629781301735e-06,
|
| 26 |
-
"loss": 2.4309,
|
| 27 |
-
"step": 1500
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.17,
|
| 31 |
-
"learning_rate": 9.782173041735646e-06,
|
| 32 |
-
"loss": 2.1416,
|
| 33 |
-
"step": 2000
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.22,
|
| 37 |
-
"learning_rate": 9.727716302169558e-06,
|
| 38 |
-
"loss": 2.0346,
|
| 39 |
-
"step": 2500
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.26,
|
| 43 |
-
"learning_rate": 9.673259562603468e-06,
|
| 44 |
-
"loss": 1.9859,
|
| 45 |
-
"step": 3000
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.3,
|
| 49 |
-
"learning_rate": 9.61880282303738e-06,
|
| 50 |
-
"loss": 1.9512,
|
| 51 |
-
"step": 3500
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.35,
|
| 55 |
-
"learning_rate": 9.56434608347129e-06,
|
| 56 |
-
"loss": 1.9171,
|
| 57 |
-
"step": 4000
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.39,
|
| 61 |
-
"learning_rate": 9.509889343905202e-06,
|
| 62 |
-
"loss": 1.8989,
|
| 63 |
-
"step": 4500
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.44,
|
| 67 |
-
"learning_rate": 9.455432604339114e-06,
|
| 68 |
-
"loss": 1.868,
|
| 69 |
-
"step": 5000
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.48,
|
| 73 |
-
"learning_rate": 9.400975864773026e-06,
|
| 74 |
-
"loss": 1.8423,
|
| 75 |
-
"step": 5500
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.52,
|
| 79 |
-
"learning_rate": 9.346519125206936e-06,
|
| 80 |
-
"loss": 1.8311,
|
| 81 |
-
"step": 6000
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.57,
|
| 85 |
-
"learning_rate": 9.292062385640848e-06,
|
| 86 |
-
"loss": 1.8139,
|
| 87 |
-
"step": 6500
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.61,
|
| 91 |
-
"learning_rate": 9.237605646074758e-06,
|
| 92 |
-
"loss": 1.809,
|
| 93 |
-
"step": 7000
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.65,
|
| 97 |
-
"learning_rate": 9.18314890650867e-06,
|
| 98 |
-
"loss": 1.7932,
|
| 99 |
-
"step": 7500
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.7,
|
| 103 |
-
"learning_rate": 9.128692166942582e-06,
|
| 104 |
-
"loss": 1.7807,
|
| 105 |
-
"step": 8000
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.74,
|
| 109 |
-
"learning_rate": 9.074235427376494e-06,
|
| 110 |
-
"loss": 1.7729,
|
| 111 |
-
"step": 8500
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.78,
|
| 115 |
-
"learning_rate": 9.019778687810404e-06,
|
| 116 |
-
"loss": 1.7695,
|
| 117 |
-
"step": 9000
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 0.83,
|
| 121 |
-
"learning_rate": 8.965321948244316e-06,
|
| 122 |
-
"loss": 1.7464,
|
| 123 |
-
"step": 9500
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.87,
|
| 127 |
-
"learning_rate": 8.910865208678226e-06,
|
| 128 |
-
"loss": 1.7436,
|
| 129 |
-
"step": 10000
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.91,
|
| 133 |
-
"learning_rate": 8.856408469112138e-06,
|
| 134 |
-
"loss": 1.736,
|
| 135 |
-
"step": 10500
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.96,
|
| 139 |
-
"learning_rate": 8.80195172954605e-06,
|
| 140 |
-
"loss": 1.729,
|
| 141 |
-
"step": 11000
|
| 142 |
-
},
|
| 143 |
{
|
| 144 |
"epoch": 1.0,
|
| 145 |
-
"eval_loss":
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second":
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 1.
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"loss":
|
| 155 |
-
"step":
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 1.05,
|
| 159 |
-
"learning_rate": 8.693038250413871e-06,
|
| 160 |
-
"loss": 1.708,
|
| 161 |
-
"step": 12000
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 1.09,
|
| 165 |
-
"learning_rate": 8.638581510847783e-06,
|
| 166 |
-
"loss": 1.6948,
|
| 167 |
-
"step": 12500
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 1.13,
|
| 171 |
-
"learning_rate": 8.584124771281695e-06,
|
| 172 |
-
"loss": 1.698,
|
| 173 |
-
"step": 13000
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 1.18,
|
| 177 |
-
"learning_rate": 8.529668031715605e-06,
|
| 178 |
-
"loss": 1.692,
|
| 179 |
-
"step": 13500
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 1.22,
|
| 183 |
-
"learning_rate": 8.475211292149517e-06,
|
| 184 |
-
"loss": 1.684,
|
| 185 |
-
"step": 14000
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 1.26,
|
| 189 |
-
"learning_rate": 8.420754552583429e-06,
|
| 190 |
-
"loss": 1.6879,
|
| 191 |
-
"step": 14500
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.31,
|
| 195 |
-
"learning_rate": 8.36629781301734e-06,
|
| 196 |
-
"loss": 1.6804,
|
| 197 |
-
"step": 15000
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 1.35,
|
| 201 |
-
"learning_rate": 8.311841073451251e-06,
|
| 202 |
-
"loss": 1.6713,
|
| 203 |
-
"step": 15500
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 1.39,
|
| 207 |
-
"learning_rate": 8.257384333885163e-06,
|
| 208 |
-
"loss": 1.6703,
|
| 209 |
-
"step": 16000
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 1.44,
|
| 213 |
-
"learning_rate": 8.202927594319073e-06,
|
| 214 |
-
"loss": 1.6646,
|
| 215 |
-
"step": 16500
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 1.48,
|
| 219 |
-
"learning_rate": 8.148470854752985e-06,
|
| 220 |
-
"loss": 1.651,
|
| 221 |
-
"step": 17000
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 1.52,
|
| 225 |
-
"learning_rate": 8.094014115186897e-06,
|
| 226 |
-
"loss": 1.6488,
|
| 227 |
-
"step": 17500
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.57,
|
| 231 |
-
"learning_rate": 8.039557375620808e-06,
|
| 232 |
-
"loss": 1.6452,
|
| 233 |
-
"step": 18000
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.61,
|
| 237 |
-
"learning_rate": 7.985100636054719e-06,
|
| 238 |
-
"loss": 1.6386,
|
| 239 |
-
"step": 18500
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 1.66,
|
| 243 |
-
"learning_rate": 7.93064389648863e-06,
|
| 244 |
-
"loss": 1.6349,
|
| 245 |
-
"step": 19000
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 1.7,
|
| 249 |
-
"learning_rate": 7.87618715692254e-06,
|
| 250 |
-
"loss": 1.6345,
|
| 251 |
-
"step": 19500
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 1.74,
|
| 255 |
-
"learning_rate": 7.821730417356452e-06,
|
| 256 |
-
"loss": 1.6294,
|
| 257 |
-
"step": 20000
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 1.79,
|
| 261 |
-
"learning_rate": 7.767273677790364e-06,
|
| 262 |
-
"loss": 1.631,
|
| 263 |
-
"step": 20500
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 1.83,
|
| 267 |
-
"learning_rate": 7.712816938224276e-06,
|
| 268 |
-
"loss": 1.6261,
|
| 269 |
-
"step": 21000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.87,
|
| 273 |
-
"learning_rate": 7.658360198658186e-06,
|
| 274 |
-
"loss": 1.6281,
|
| 275 |
-
"step": 21500
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.92,
|
| 279 |
-
"learning_rate": 7.603903459092098e-06,
|
| 280 |
-
"loss": 1.611,
|
| 281 |
-
"step": 22000
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 1.96,
|
| 285 |
-
"learning_rate": 7.549446719526009e-06,
|
| 286 |
-
"loss": 1.6155,
|
| 287 |
-
"step": 22500
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"epoch":
|
| 291 |
-
"
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"eval_steps_per_second": 4.957,
|
| 295 |
-
"step": 22954
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 2.0,
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
|
| 303 |
-
|
| 304 |
-
"epoch": 2.05,
|
| 305 |
-
"learning_rate": 7.440533240393831e-06,
|
| 306 |
-
"loss": 1.607,
|
| 307 |
-
"step": 23500
|
| 308 |
-
},
|
| 309 |
-
{
|
| 310 |
-
"epoch": 2.09,
|
| 311 |
-
"learning_rate": 7.386076500827744e-06,
|
| 312 |
-
"loss": 1.5977,
|
| 313 |
-
"step": 24000
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 2.13,
|
| 317 |
-
"learning_rate": 7.331619761261655e-06,
|
| 318 |
-
"loss": 1.5922,
|
| 319 |
-
"step": 24500
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 2.18,
|
| 323 |
-
"learning_rate": 7.277163021695566e-06,
|
| 324 |
-
"loss": 1.5956,
|
| 325 |
-
"step": 25000
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch": 2.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss":
|
| 331 |
-
"step":
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 2.27,
|
| 335 |
-
"learning_rate": 7.168249542563388e-06,
|
| 336 |
-
"loss": 1.5826,
|
| 337 |
-
"step": 26000
|
| 338 |
-
},
|
| 339 |
-
{
|
| 340 |
-
"epoch": 2.31,
|
| 341 |
-
"learning_rate": 7.1137928029972995e-06,
|
| 342 |
-
"loss": 1.5846,
|
| 343 |
-
"step": 26500
|
| 344 |
-
},
|
| 345 |
-
{
|
| 346 |
-
"epoch": 2.35,
|
| 347 |
-
"learning_rate": 7.059336063431211e-06,
|
| 348 |
-
"loss": 1.5899,
|
| 349 |
-
"step": 27000
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 2.4,
|
| 353 |
-
"learning_rate": 7.004879323865122e-06,
|
| 354 |
-
"loss": 1.5828,
|
| 355 |
-
"step": 27500
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 2.44,
|
| 359 |
-
"learning_rate": 6.950422584299033e-06,
|
| 360 |
-
"loss": 1.5762,
|
| 361 |
-
"step": 28000
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 2.48,
|
| 365 |
-
"learning_rate": 6.895965844732945e-06,
|
| 366 |
-
"loss": 1.5739,
|
| 367 |
-
"step": 28500
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 2.53,
|
| 371 |
-
"learning_rate": 6.841509105166856e-06,
|
| 372 |
-
"loss": 1.574,
|
| 373 |
-
"step": 29000
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 2.57,
|
| 377 |
-
"learning_rate": 6.787052365600767e-06,
|
| 378 |
-
"loss": 1.5759,
|
| 379 |
-
"step": 29500
|
| 380 |
-
},
|
| 381 |
-
{
|
| 382 |
-
"epoch": 2.61,
|
| 383 |
-
"learning_rate": 6.732595626034678e-06,
|
| 384 |
-
"loss": 1.5737,
|
| 385 |
-
"step": 30000
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 2.66,
|
| 389 |
-
"learning_rate": 6.67813888646859e-06,
|
| 390 |
-
"loss": 1.5637,
|
| 391 |
-
"step": 30500
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"epoch": 2.7,
|
| 395 |
-
"learning_rate": 6.623682146902502e-06,
|
| 396 |
-
"loss": 1.5635,
|
| 397 |
-
"step": 31000
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 2.74,
|
| 401 |
-
"learning_rate": 6.569225407336413e-06,
|
| 402 |
-
"loss": 1.5641,
|
| 403 |
-
"step": 31500
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 2.79,
|
| 407 |
-
"learning_rate": 6.514768667770324e-06,
|
| 408 |
-
"loss": 1.553,
|
| 409 |
-
"step": 32000
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 2.83,
|
| 413 |
-
"learning_rate": 6.460311928204235e-06,
|
| 414 |
-
"loss": 1.5699,
|
| 415 |
-
"step": 32500
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 2.88,
|
| 419 |
-
"learning_rate": 6.405855188638146e-06,
|
| 420 |
-
"loss": 1.5695,
|
| 421 |
-
"step": 33000
|
| 422 |
},
|
| 423 |
{
|
| 424 |
-
"epoch": 2.
|
| 425 |
-
"learning_rate":
|
| 426 |
-
"loss":
|
| 427 |
-
"step":
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 2.96,
|
| 431 |
-
"learning_rate":
|
| 432 |
-
"loss":
|
| 433 |
-
"step":
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 3.0,
|
| 437 |
-
"eval_loss":
|
| 438 |
-
"eval_runtime":
|
| 439 |
-
"eval_samples_per_second":
|
| 440 |
-
"eval_steps_per_second": 5.
|
| 441 |
-
"step":
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 3.01,
|
| 445 |
-
"learning_rate": 6.24248496993988e-06,
|
| 446 |
-
"loss": 1.5506,
|
| 447 |
-
"step": 34500
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 3.05,
|
| 451 |
-
"learning_rate": 6.188028230373791e-06,
|
| 452 |
-
"loss": 1.559,
|
| 453 |
-
"step": 35000
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 3.09,
|
| 457 |
-
"learning_rate": 6.133571490807702e-06,
|
| 458 |
-
"loss": 1.5388,
|
| 459 |
-
"step": 35500
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 3.14,
|
| 463 |
-
"learning_rate": 6.079114751241613e-06,
|
| 464 |
-
"loss": 1.5467,
|
| 465 |
-
"step": 36000
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 3.18,
|
| 469 |
-
"learning_rate": 6.024658011675526e-06,
|
| 470 |
-
"loss": 1.5391,
|
| 471 |
-
"step": 36500
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 3.22,
|
| 475 |
-
"learning_rate": 5.970201272109437e-06,
|
| 476 |
-
"loss": 1.5364,
|
| 477 |
-
"step": 37000
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 3.27,
|
| 481 |
-
"learning_rate": 5.915744532543348e-06,
|
| 482 |
-
"loss": 1.5376,
|
| 483 |
-
"step": 37500
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 3.31,
|
| 487 |
-
"learning_rate": 5.861287792977259e-06,
|
| 488 |
-
"loss": 1.5397,
|
| 489 |
-
"step": 38000
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 3.35,
|
| 493 |
-
"learning_rate": 5.806831053411171e-06,
|
| 494 |
-
"loss": 1.5336,
|
| 495 |
-
"step": 38500
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 3.4,
|
| 499 |
-
"learning_rate": 5.752374313845082e-06,
|
| 500 |
-
"loss": 1.5378,
|
| 501 |
-
"step": 39000
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 3.44,
|
| 505 |
-
"learning_rate": 5.697917574278993e-06,
|
| 506 |
-
"loss": 1.5318,
|
| 507 |
-
"step": 39500
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 3.49,
|
| 511 |
-
"learning_rate": 5.643460834712905e-06,
|
| 512 |
-
"loss": 1.5252,
|
| 513 |
-
"step": 40000
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 3.53,
|
| 517 |
-
"learning_rate": 5.589004095146816e-06,
|
| 518 |
-
"loss": 1.5333,
|
| 519 |
-
"step": 40500
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 3.57,
|
| 523 |
-
"learning_rate": 5.5345473555807275e-06,
|
| 524 |
-
"loss": 1.5299,
|
| 525 |
-
"step": 41000
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 3.62,
|
| 529 |
-
"learning_rate": 5.4800906160146385e-06,
|
| 530 |
-
"loss": 1.5215,
|
| 531 |
-
"step": 41500
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 3.66,
|
| 535 |
-
"learning_rate": 5.4256338764485495e-06,
|
| 536 |
-
"loss": 1.52,
|
| 537 |
-
"step": 42000
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 3.7,
|
| 541 |
-
"learning_rate": 5.3711771368824605e-06,
|
| 542 |
-
"loss": 1.5258,
|
| 543 |
-
"step": 42500
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 3.75,
|
| 547 |
-
"learning_rate": 5.316720397316373e-06,
|
| 548 |
-
"loss": 1.5256,
|
| 549 |
-
"step": 43000
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 3.79,
|
| 553 |
-
"learning_rate": 5.262263657750284e-06,
|
| 554 |
-
"loss": 1.5205,
|
| 555 |
-
"step": 43500
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 3.83,
|
| 559 |
-
"learning_rate": 5.207806918184195e-06,
|
| 560 |
-
"loss": 1.5236,
|
| 561 |
-
"step": 44000
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch": 3.
|
| 565 |
-
"learning_rate":
|
| 566 |
-
"loss":
|
| 567 |
-
"step":
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 3.92,
|
| 571 |
-
"learning_rate": 5.098893439052017e-06,
|
| 572 |
-
"loss": 1.5175,
|
| 573 |
-
"step": 45000
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"epoch": 3.
|
| 577 |
-
"learning_rate":
|
| 578 |
-
"loss":
|
| 579 |
-
"step":
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 4.0,
|
| 583 |
-
"eval_loss":
|
| 584 |
-
"eval_runtime":
|
| 585 |
-
"eval_samples_per_second":
|
| 586 |
-
"eval_steps_per_second": 5.
|
| 587 |
-
"step":
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 4.01,
|
| 591 |
-
"learning_rate": 4.98997995991984e-06,
|
| 592 |
-
"loss": 1.5202,
|
| 593 |
-
"step": 46000
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 4.05,
|
| 597 |
-
"learning_rate": 4.935523220353751e-06,
|
| 598 |
-
"loss": 1.5136,
|
| 599 |
-
"step": 46500
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 4.1,
|
| 603 |
-
"learning_rate": 4.881066480787663e-06,
|
| 604 |
-
"loss": 1.5119,
|
| 605 |
-
"step": 47000
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 4.14,
|
| 609 |
-
"learning_rate": 4.826609741221574e-06,
|
| 610 |
-
"loss": 1.5052,
|
| 611 |
-
"step": 47500
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 4.18,
|
| 615 |
-
"learning_rate": 4.772153001655485e-06,
|
| 616 |
-
"loss": 1.5088,
|
| 617 |
-
"step": 48000
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 4.23,
|
| 621 |
-
"learning_rate":
|
| 622 |
-
"loss":
|
| 623 |
-
"step":
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 4.27,
|
| 627 |
-
"learning_rate": 4.663239522523308e-06,
|
| 628 |
-
"loss": 1.5099,
|
| 629 |
-
"step": 49000
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 4.31,
|
| 633 |
-
"learning_rate": 4.608782782957219e-06,
|
| 634 |
-
"loss": 1.5098,
|
| 635 |
-
"step": 49500
|
| 636 |
-
},
|
| 637 |
-
{
|
| 638 |
-
"epoch": 4.36,
|
| 639 |
-
"learning_rate": 4.5543260433911305e-06,
|
| 640 |
-
"loss": 1.5044,
|
| 641 |
-
"step": 50000
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 4.4,
|
| 645 |
-
"learning_rate": 4.4998693038250415e-06,
|
| 646 |
-
"loss": 1.5049,
|
| 647 |
-
"step": 50500
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 4.44,
|
| 651 |
-
"learning_rate": 4.445412564258953e-06,
|
| 652 |
-
"loss": 1.4958,
|
| 653 |
-
"step": 51000
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 4.49,
|
| 657 |
-
"learning_rate": 4.390955824692864e-06,
|
| 658 |
-
"loss": 1.5073,
|
| 659 |
-
"step": 51500
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 4.53,
|
| 663 |
-
"learning_rate": 4.336499085126776e-06,
|
| 664 |
-
"loss": 1.5015,
|
| 665 |
-
"step": 52000
|
| 666 |
},
|
| 667 |
{
|
| 668 |
-
"epoch": 4.
|
| 669 |
-
"learning_rate":
|
| 670 |
-
"loss":
|
| 671 |
-
"step":
|
| 672 |
},
|
| 673 |
{
|
| 674 |
-
"epoch":
|
| 675 |
-
"
|
| 676 |
-
"
|
| 677 |
-
"
|
|
|
|
|
|
|
| 678 |
},
|
| 679 |
{
|
| 680 |
-
"epoch":
|
| 681 |
-
"learning_rate":
|
| 682 |
-
"loss":
|
| 683 |
-
"step":
|
| 684 |
},
|
| 685 |
{
|
| 686 |
-
"epoch":
|
| 687 |
-
"learning_rate":
|
| 688 |
-
"loss":
|
| 689 |
-
"step":
|
| 690 |
},
|
| 691 |
{
|
| 692 |
-
"epoch":
|
| 693 |
-
"learning_rate":
|
| 694 |
-
"loss":
|
| 695 |
-
"step":
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch":
|
| 699 |
-
"
|
| 700 |
-
"
|
| 701 |
-
"
|
|
|
|
|
|
|
| 702 |
},
|
| 703 |
{
|
| 704 |
-
"epoch":
|
| 705 |
-
"learning_rate":
|
| 706 |
-
"loss":
|
| 707 |
-
"step":
|
| 708 |
},
|
| 709 |
{
|
| 710 |
-
"epoch":
|
| 711 |
-
"learning_rate":
|
| 712 |
-
"loss":
|
| 713 |
-
"step":
|
| 714 |
},
|
| 715 |
{
|
| 716 |
-
"epoch":
|
| 717 |
-
"
|
| 718 |
-
"
|
| 719 |
-
"
|
|
|
|
|
|
|
| 720 |
},
|
| 721 |
{
|
| 722 |
-
"epoch":
|
| 723 |
-
"learning_rate":
|
| 724 |
-
"loss":
|
| 725 |
-
"step":
|
| 726 |
},
|
| 727 |
{
|
| 728 |
-
"epoch":
|
| 729 |
-
"
|
| 730 |
-
"
|
| 731 |
-
"
|
| 732 |
-
"eval_steps_per_second": 5.21,
|
| 733 |
-
"step": 57385
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 500,
|
| 737 |
-
"max_steps":
|
| 738 |
-
"num_train_epochs":
|
| 739 |
-
"save_steps":
|
| 740 |
-
"total_flos":
|
| 741 |
"trial_name": null,
|
| 742 |
"trial_params": null
|
| 743 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9456,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.42,
|
| 13 |
+
"learning_rate": 9.894247038917091e-06,
|
| 14 |
+
"loss": 3.5932,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.85,
|
| 19 |
+
"learning_rate": 9.78849407783418e-06,
|
| 20 |
+
"loss": 3.336,
|
| 21 |
"step": 1000
|
| 22 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
{
|
| 24 |
"epoch": 1.0,
|
| 25 |
+
"eval_loss": 3.2544538974761963,
|
| 26 |
+
"eval_runtime": 6.101,
|
| 27 |
+
"eval_samples_per_second": 41.961,
|
| 28 |
+
"eval_steps_per_second": 5.245,
|
| 29 |
+
"step": 1182
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 1.27,
|
| 33 |
+
"learning_rate": 9.68274111675127e-06,
|
| 34 |
+
"loss": 3.2562,
|
| 35 |
+
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
},
|
| 37 |
{
|
| 38 |
+
"epoch": 1.69,
|
| 39 |
+
"learning_rate": 9.57698815566836e-06,
|
| 40 |
+
"loss": 3.1967,
|
| 41 |
+
"step": 2000
|
|
|
|
|
|
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 2.0,
|
| 45 |
+
"eval_loss": 3.1576380729675293,
|
| 46 |
+
"eval_runtime": 6.0951,
|
| 47 |
+
"eval_samples_per_second": 42.001,
|
| 48 |
+
"eval_steps_per_second": 5.25,
|
| 49 |
+
"step": 2364
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
+
"epoch": 2.12,
|
| 53 |
+
"learning_rate": 9.47123519458545e-06,
|
| 54 |
+
"loss": 3.1613,
|
| 55 |
+
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
},
|
| 57 |
{
|
| 58 |
+
"epoch": 2.54,
|
| 59 |
+
"learning_rate": 9.36548223350254e-06,
|
| 60 |
+
"loss": 3.1268,
|
| 61 |
+
"step": 3000
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 2.96,
|
| 65 |
+
"learning_rate": 9.25972927241963e-06,
|
| 66 |
+
"loss": 3.1148,
|
| 67 |
+
"step": 3500
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"epoch": 3.0,
|
| 71 |
+
"eval_loss": 3.1073131561279297,
|
| 72 |
+
"eval_runtime": 6.0936,
|
| 73 |
+
"eval_samples_per_second": 42.011,
|
| 74 |
+
"eval_steps_per_second": 5.251,
|
| 75 |
+
"step": 3546
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 3.38,
|
| 79 |
+
"learning_rate": 9.15397631133672e-06,
|
| 80 |
+
"loss": 3.0804,
|
| 81 |
+
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 3.81,
|
| 85 |
+
"learning_rate": 9.048223350253808e-06,
|
| 86 |
+
"loss": 3.0814,
|
| 87 |
+
"step": 4500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 4.0,
|
| 91 |
+
"eval_loss": 3.074193000793457,
|
| 92 |
+
"eval_runtime": 6.0939,
|
| 93 |
+
"eval_samples_per_second": 42.009,
|
| 94 |
+
"eval_steps_per_second": 5.251,
|
| 95 |
+
"step": 4728
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 4.23,
|
| 99 |
+
"learning_rate": 8.942470389170898e-06,
|
| 100 |
+
"loss": 3.054,
|
| 101 |
+
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 4.65,
|
| 105 |
+
"learning_rate": 8.836717428087988e-06,
|
| 106 |
+
"loss": 3.0355,
|
| 107 |
+
"step": 5500
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 5.0,
|
| 111 |
+
"eval_loss": 3.04995059967041,
|
| 112 |
+
"eval_runtime": 6.09,
|
| 113 |
+
"eval_samples_per_second": 42.036,
|
| 114 |
+
"eval_steps_per_second": 5.254,
|
| 115 |
+
"step": 5910
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 5.08,
|
| 119 |
+
"learning_rate": 8.730964467005076e-06,
|
| 120 |
+
"loss": 3.0365,
|
| 121 |
+
"step": 6000
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 5.5,
|
| 125 |
+
"learning_rate": 8.625211505922166e-06,
|
| 126 |
+
"loss": 3.0104,
|
| 127 |
+
"step": 6500
|
| 128 |
},
|
| 129 |
{
|
| 130 |
+
"epoch": 5.92,
|
| 131 |
+
"learning_rate": 8.519458544839256e-06,
|
| 132 |
+
"loss": 3.0126,
|
| 133 |
+
"step": 7000
|
| 134 |
},
|
| 135 |
{
|
| 136 |
+
"epoch": 6.0,
|
| 137 |
+
"eval_loss": 3.0317230224609375,
|
| 138 |
+
"eval_runtime": 6.0899,
|
| 139 |
+
"eval_samples_per_second": 42.037,
|
| 140 |
+
"eval_steps_per_second": 5.255,
|
| 141 |
+
"step": 7092
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 6.35,
|
| 145 |
+
"learning_rate": 8.413705583756346e-06,
|
| 146 |
+
"loss": 2.9923,
|
| 147 |
+
"step": 7500
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 6.77,
|
| 151 |
+
"learning_rate": 8.307952622673435e-06,
|
| 152 |
+
"loss": 2.9902,
|
| 153 |
+
"step": 8000
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 7.0,
|
| 157 |
+
"eval_loss": 3.0167293548583984,
|
| 158 |
+
"eval_runtime": 6.0906,
|
| 159 |
+
"eval_samples_per_second": 42.032,
|
| 160 |
+
"eval_steps_per_second": 5.254,
|
| 161 |
+
"step": 8274
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 7.19,
|
| 165 |
+
"learning_rate": 8.202199661590525e-06,
|
| 166 |
+
"loss": 2.9783,
|
| 167 |
+
"step": 8500
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 7.61,
|
| 171 |
+
"learning_rate": 8.096446700507615e-06,
|
| 172 |
+
"loss": 2.9722,
|
| 173 |
+
"step": 9000
|
|
|
|
|
|
|
| 174 |
}
|
| 175 |
],
|
| 176 |
"logging_steps": 500,
|
| 177 |
+
"max_steps": 47280,
|
| 178 |
+
"num_train_epochs": 40,
|
| 179 |
+
"save_steps": 9456,
|
| 180 |
+
"total_flos": 1.4819961470976e+16,
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|
| 183 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae185e461383878779e83ce5ef9c772ed06a4c034c0c8dd422cbd6909ed7f255
|
| 3 |
size 4027
|