Commit
•
85d7167
1
Parent(s):
5d3abcb
Upload 12 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +359 -3
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:b1958c3dbb04813e9cfb37dc3270d881bdb32b10faf80bc576183dadd1d67b1f
|
| 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:d55afad0c1ff1e9d5816f48bc770e1719f184367f8577205df45a7ada8f25d79
|
| 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:e34348f4fc7163b2cbb271bcc37ef245469192a3f7f73ffc101fcb3e6ff34188
|
| 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 sha256:7b4432ea76e605f5a2ab91b958cd7cebdc5efaf3ebb4c8fe1d3da0e35f885a53
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 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,
|
|
@@ -171,13 +171,369 @@
|
|
| 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":
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|
| 183 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 28368,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 171 |
"learning_rate": 8.096446700507615e-06,
|
| 172 |
"loss": 2.9722,
|
| 173 |
"step": 9000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 8.0,
|
| 177 |
+
"eval_loss": 3.004361391067505,
|
| 178 |
+
"eval_runtime": 6.0481,
|
| 179 |
+
"eval_samples_per_second": 42.327,
|
| 180 |
+
"eval_steps_per_second": 5.291,
|
| 181 |
+
"step": 9456
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 8.04,
|
| 185 |
+
"learning_rate": 7.990693739424705e-06,
|
| 186 |
+
"loss": 2.9628,
|
| 187 |
+
"step": 9500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 8.46,
|
| 191 |
+
"learning_rate": 7.884940778341795e-06,
|
| 192 |
+
"loss": 2.9593,
|
| 193 |
+
"step": 10000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.88,
|
| 197 |
+
"learning_rate": 7.779187817258885e-06,
|
| 198 |
+
"loss": 2.9485,
|
| 199 |
+
"step": 10500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 9.0,
|
| 203 |
+
"eval_loss": 2.9940547943115234,
|
| 204 |
+
"eval_runtime": 6.1451,
|
| 205 |
+
"eval_samples_per_second": 41.659,
|
| 206 |
+
"eval_steps_per_second": 5.207,
|
| 207 |
+
"step": 10638
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.31,
|
| 211 |
+
"learning_rate": 7.673434856175973e-06,
|
| 212 |
+
"loss": 2.9405,
|
| 213 |
+
"step": 11000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.73,
|
| 217 |
+
"learning_rate": 7.567681895093063e-06,
|
| 218 |
+
"loss": 2.943,
|
| 219 |
+
"step": 11500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 10.0,
|
| 223 |
+
"eval_loss": 2.9857802391052246,
|
| 224 |
+
"eval_runtime": 6.2619,
|
| 225 |
+
"eval_samples_per_second": 40.882,
|
| 226 |
+
"eval_steps_per_second": 5.11,
|
| 227 |
+
"step": 11820
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.15,
|
| 231 |
+
"learning_rate": 7.461928934010153e-06,
|
| 232 |
+
"loss": 2.9243,
|
| 233 |
+
"step": 12000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 10.58,
|
| 237 |
+
"learning_rate": 7.356175972927243e-06,
|
| 238 |
+
"loss": 2.9228,
|
| 239 |
+
"step": 12500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 11.0,
|
| 243 |
+
"learning_rate": 7.2504230118443316e-06,
|
| 244 |
+
"loss": 2.9216,
|
| 245 |
+
"step": 13000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 11.0,
|
| 249 |
+
"eval_loss": 2.9776651859283447,
|
| 250 |
+
"eval_runtime": 6.2854,
|
| 251 |
+
"eval_samples_per_second": 40.73,
|
| 252 |
+
"eval_steps_per_second": 5.091,
|
| 253 |
+
"step": 13002
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 11.42,
|
| 257 |
+
"learning_rate": 7.144670050761422e-06,
|
| 258 |
+
"loss": 2.9118,
|
| 259 |
+
"step": 13500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 11.84,
|
| 263 |
+
"learning_rate": 7.038917089678512e-06,
|
| 264 |
+
"loss": 2.911,
|
| 265 |
+
"step": 14000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 12.0,
|
| 269 |
+
"eval_loss": 2.9713006019592285,
|
| 270 |
+
"eval_runtime": 6.1107,
|
| 271 |
+
"eval_samples_per_second": 41.894,
|
| 272 |
+
"eval_steps_per_second": 5.237,
|
| 273 |
+
"step": 14184
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.27,
|
| 277 |
+
"learning_rate": 6.933164128595601e-06,
|
| 278 |
+
"loss": 2.9038,
|
| 279 |
+
"step": 14500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.69,
|
| 283 |
+
"learning_rate": 6.827411167512691e-06,
|
| 284 |
+
"loss": 2.8924,
|
| 285 |
+
"step": 15000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 13.0,
|
| 289 |
+
"eval_loss": 2.9653375148773193,
|
| 290 |
+
"eval_runtime": 6.1162,
|
| 291 |
+
"eval_samples_per_second": 41.856,
|
| 292 |
+
"eval_steps_per_second": 5.232,
|
| 293 |
+
"step": 15366
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 13.11,
|
| 297 |
+
"learning_rate": 6.721658206429781e-06,
|
| 298 |
+
"loss": 2.9025,
|
| 299 |
+
"step": 15500
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 13.54,
|
| 303 |
+
"learning_rate": 6.61590524534687e-06,
|
| 304 |
+
"loss": 2.8886,
|
| 305 |
+
"step": 16000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 13.96,
|
| 309 |
+
"learning_rate": 6.51015228426396e-06,
|
| 310 |
+
"loss": 2.8882,
|
| 311 |
+
"step": 16500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.0,
|
| 315 |
+
"eval_loss": 2.960761547088623,
|
| 316 |
+
"eval_runtime": 6.1211,
|
| 317 |
+
"eval_samples_per_second": 41.822,
|
| 318 |
+
"eval_steps_per_second": 5.228,
|
| 319 |
+
"step": 16548
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 14.38,
|
| 323 |
+
"learning_rate": 6.40439932318105e-06,
|
| 324 |
+
"loss": 2.8777,
|
| 325 |
+
"step": 17000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 14.81,
|
| 329 |
+
"learning_rate": 6.298646362098139e-06,
|
| 330 |
+
"loss": 2.8826,
|
| 331 |
+
"step": 17500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 15.0,
|
| 335 |
+
"eval_loss": 2.9559221267700195,
|
| 336 |
+
"eval_runtime": 6.0998,
|
| 337 |
+
"eval_samples_per_second": 41.969,
|
| 338 |
+
"eval_steps_per_second": 5.246,
|
| 339 |
+
"step": 17730
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.23,
|
| 343 |
+
"learning_rate": 6.1928934010152285e-06,
|
| 344 |
+
"loss": 2.8796,
|
| 345 |
+
"step": 18000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 15.65,
|
| 349 |
+
"learning_rate": 6.0871404399323185e-06,
|
| 350 |
+
"loss": 2.8697,
|
| 351 |
+
"step": 18500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 16.0,
|
| 355 |
+
"eval_loss": 2.952040672302246,
|
| 356 |
+
"eval_runtime": 6.2485,
|
| 357 |
+
"eval_samples_per_second": 40.97,
|
| 358 |
+
"eval_steps_per_second": 5.121,
|
| 359 |
+
"step": 18912
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 16.07,
|
| 363 |
+
"learning_rate": 5.981387478849409e-06,
|
| 364 |
+
"loss": 2.8645,
|
| 365 |
+
"step": 19000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 16.5,
|
| 369 |
+
"learning_rate": 5.875634517766498e-06,
|
| 370 |
+
"loss": 2.8678,
|
| 371 |
+
"step": 19500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 16.92,
|
| 375 |
+
"learning_rate": 5.769881556683588e-06,
|
| 376 |
+
"loss": 2.8616,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 17.0,
|
| 381 |
+
"eval_loss": 2.948793888092041,
|
| 382 |
+
"eval_runtime": 6.2711,
|
| 383 |
+
"eval_samples_per_second": 40.822,
|
| 384 |
+
"eval_steps_per_second": 5.103,
|
| 385 |
+
"step": 20094
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 17.34,
|
| 389 |
+
"learning_rate": 5.664128595600678e-06,
|
| 390 |
+
"loss": 2.8548,
|
| 391 |
+
"step": 20500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 17.77,
|
| 395 |
+
"learning_rate": 5.558375634517766e-06,
|
| 396 |
+
"loss": 2.8529,
|
| 397 |
+
"step": 21000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 18.0,
|
| 401 |
+
"eval_loss": 2.945361614227295,
|
| 402 |
+
"eval_runtime": 6.3517,
|
| 403 |
+
"eval_samples_per_second": 40.304,
|
| 404 |
+
"eval_steps_per_second": 5.038,
|
| 405 |
+
"step": 21276
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.19,
|
| 409 |
+
"learning_rate": 5.452622673434856e-06,
|
| 410 |
+
"loss": 2.8557,
|
| 411 |
+
"step": 21500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.61,
|
| 415 |
+
"learning_rate": 5.346869712351946e-06,
|
| 416 |
+
"loss": 2.8448,
|
| 417 |
+
"step": 22000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 19.0,
|
| 421 |
+
"eval_loss": 2.9428470134735107,
|
| 422 |
+
"eval_runtime": 6.2219,
|
| 423 |
+
"eval_samples_per_second": 41.145,
|
| 424 |
+
"eval_steps_per_second": 5.143,
|
| 425 |
+
"step": 22458
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 19.04,
|
| 429 |
+
"learning_rate": 5.241116751269036e-06,
|
| 430 |
+
"loss": 2.8458,
|
| 431 |
+
"step": 22500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 19.46,
|
| 435 |
+
"learning_rate": 5.1353637901861255e-06,
|
| 436 |
+
"loss": 2.8462,
|
| 437 |
+
"step": 23000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 19.88,
|
| 441 |
+
"learning_rate": 5.0296108291032155e-06,
|
| 442 |
+
"loss": 2.84,
|
| 443 |
+
"step": 23500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 20.0,
|
| 447 |
+
"eval_loss": 2.940398693084717,
|
| 448 |
+
"eval_runtime": 6.2496,
|
| 449 |
+
"eval_samples_per_second": 40.962,
|
| 450 |
+
"eval_steps_per_second": 5.12,
|
| 451 |
+
"step": 23640
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 20.3,
|
| 455 |
+
"learning_rate": 4.923857868020305e-06,
|
| 456 |
+
"loss": 2.8349,
|
| 457 |
+
"step": 24000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 20.73,
|
| 461 |
+
"learning_rate": 4.818104906937395e-06,
|
| 462 |
+
"loss": 2.8285,
|
| 463 |
+
"step": 24500
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 21.0,
|
| 467 |
+
"eval_loss": 2.938441276550293,
|
| 468 |
+
"eval_runtime": 6.1601,
|
| 469 |
+
"eval_samples_per_second": 41.558,
|
| 470 |
+
"eval_steps_per_second": 5.195,
|
| 471 |
+
"step": 24822
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.15,
|
| 475 |
+
"learning_rate": 4.712351945854484e-06,
|
| 476 |
+
"loss": 2.8345,
|
| 477 |
+
"step": 25000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 21.57,
|
| 481 |
+
"learning_rate": 4.606598984771574e-06,
|
| 482 |
+
"loss": 2.8302,
|
| 483 |
+
"step": 25500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 22.0,
|
| 487 |
+
"learning_rate": 4.500846023688664e-06,
|
| 488 |
+
"loss": 2.8266,
|
| 489 |
+
"step": 26000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 22.0,
|
| 493 |
+
"eval_loss": 2.9362807273864746,
|
| 494 |
+
"eval_runtime": 6.0955,
|
| 495 |
+
"eval_samples_per_second": 41.998,
|
| 496 |
+
"eval_steps_per_second": 5.25,
|
| 497 |
+
"step": 26004
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 22.42,
|
| 501 |
+
"learning_rate": 4.395093062605753e-06,
|
| 502 |
+
"loss": 2.819,
|
| 503 |
+
"step": 26500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 22.84,
|
| 507 |
+
"learning_rate": 4.289340101522843e-06,
|
| 508 |
+
"loss": 2.8232,
|
| 509 |
+
"step": 27000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 23.0,
|
| 513 |
+
"eval_loss": 2.934544324874878,
|
| 514 |
+
"eval_runtime": 6.1597,
|
| 515 |
+
"eval_samples_per_second": 41.561,
|
| 516 |
+
"eval_steps_per_second": 5.195,
|
| 517 |
+
"step": 27186
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 23.27,
|
| 521 |
+
"learning_rate": 4.183587140439932e-06,
|
| 522 |
+
"loss": 2.8213,
|
| 523 |
+
"step": 27500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 23.69,
|
| 527 |
+
"learning_rate": 4.0778341793570224e-06,
|
| 528 |
+
"loss": 2.8136,
|
| 529 |
+
"step": 28000
|
| 530 |
}
|
| 531 |
],
|
| 532 |
"logging_steps": 500,
|
| 533 |
"max_steps": 47280,
|
| 534 |
"num_train_epochs": 40,
|
| 535 |
"save_steps": 9456,
|
| 536 |
+
"total_flos": 4.4459884412928e+16,
|
| 537 |
"trial_name": null,
|
| 538 |
"trial_params": null
|
| 539 |
}
|