Upload folder using huggingface_hub
Browse files- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +842 -2
- vocab.model +2 -2
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 853681210
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e89ad651d32e985eb54278a73052c0a859f2fdcb293f4ee18fe1f6b24745a05
|
3 |
size 853681210
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:489158a799545f87c162b73e1abbfe1d0335b37508a47e870496f7918f8deec2
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:990bf38066c8fa8004c28e3d0c1817b366ea6e1a5e89cf1f2a6ea3b8ad356075
|
3 |
size 1000
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 9.
|
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,
|
@@ -20167,6 +20167,846 @@
|
|
20167 |
"learning_rate": 0.00020952468145148259,
|
20168 |
"loss": 0.0,
|
20169 |
"step": 1680000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20170 |
}
|
20171 |
],
|
20172 |
"logging_steps": 500,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.424512348803894,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1750000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
20167 |
"learning_rate": 0.00020952468145148259,
|
20168 |
"loss": 0.0,
|
20169 |
"step": 1680000
|
20170 |
+
},
|
20171 |
+
{
|
20172 |
+
"epoch": 9.05,
|
20173 |
+
"learning_rate": 0.00020949775427334314,
|
20174 |
+
"loss": 0.0,
|
20175 |
+
"step": 1680500
|
20176 |
+
},
|
20177 |
+
{
|
20178 |
+
"epoch": 9.05,
|
20179 |
+
"learning_rate": 0.00020947082709520373,
|
20180 |
+
"loss": 0.0,
|
20181 |
+
"step": 1681000
|
20182 |
+
},
|
20183 |
+
{
|
20184 |
+
"epoch": 9.06,
|
20185 |
+
"learning_rate": 0.00020944389991706428,
|
20186 |
+
"loss": 0.0,
|
20187 |
+
"step": 1681500
|
20188 |
+
},
|
20189 |
+
{
|
20190 |
+
"epoch": 9.06,
|
20191 |
+
"learning_rate": 0.00020941697273892484,
|
20192 |
+
"loss": 0.0,
|
20193 |
+
"step": 1682000
|
20194 |
+
},
|
20195 |
+
{
|
20196 |
+
"epoch": 9.06,
|
20197 |
+
"learning_rate": 0.00020939004556078537,
|
20198 |
+
"loss": 0.0,
|
20199 |
+
"step": 1682500
|
20200 |
+
},
|
20201 |
+
{
|
20202 |
+
"epoch": 9.06,
|
20203 |
+
"learning_rate": 0.00020936311838264595,
|
20204 |
+
"loss": 0.0,
|
20205 |
+
"step": 1683000
|
20206 |
+
},
|
20207 |
+
{
|
20208 |
+
"epoch": 9.07,
|
20209 |
+
"learning_rate": 0.0002093361912045065,
|
20210 |
+
"loss": 0.0,
|
20211 |
+
"step": 1683500
|
20212 |
+
},
|
20213 |
+
{
|
20214 |
+
"epoch": 9.07,
|
20215 |
+
"learning_rate": 0.00020930926402636707,
|
20216 |
+
"loss": 0.0,
|
20217 |
+
"step": 1684000
|
20218 |
+
},
|
20219 |
+
{
|
20220 |
+
"epoch": 9.07,
|
20221 |
+
"learning_rate": 0.00020928233684822765,
|
20222 |
+
"loss": 0.0,
|
20223 |
+
"step": 1684500
|
20224 |
+
},
|
20225 |
+
{
|
20226 |
+
"epoch": 9.07,
|
20227 |
+
"learning_rate": 0.0002092554096700882,
|
20228 |
+
"loss": 0.0,
|
20229 |
+
"step": 1685000
|
20230 |
+
},
|
20231 |
+
{
|
20232 |
+
"epoch": 9.08,
|
20233 |
+
"learning_rate": 0.00020922848249194876,
|
20234 |
+
"loss": 0.0,
|
20235 |
+
"step": 1685500
|
20236 |
+
},
|
20237 |
+
{
|
20238 |
+
"epoch": 9.08,
|
20239 |
+
"learning_rate": 0.0002092015553138093,
|
20240 |
+
"loss": 0.0,
|
20241 |
+
"step": 1686000
|
20242 |
+
},
|
20243 |
+
{
|
20244 |
+
"epoch": 9.08,
|
20245 |
+
"learning_rate": 0.00020917462813566987,
|
20246 |
+
"loss": 0.0,
|
20247 |
+
"step": 1686500
|
20248 |
+
},
|
20249 |
+
{
|
20250 |
+
"epoch": 9.09,
|
20251 |
+
"learning_rate": 0.00020914770095753043,
|
20252 |
+
"loss": 0.0,
|
20253 |
+
"step": 1687000
|
20254 |
+
},
|
20255 |
+
{
|
20256 |
+
"epoch": 9.09,
|
20257 |
+
"learning_rate": 0.000209120773779391,
|
20258 |
+
"loss": 0.0,
|
20259 |
+
"step": 1687500
|
20260 |
+
},
|
20261 |
+
{
|
20262 |
+
"epoch": 9.09,
|
20263 |
+
"learning_rate": 0.00020909384660125154,
|
20264 |
+
"loss": 0.0,
|
20265 |
+
"step": 1688000
|
20266 |
+
},
|
20267 |
+
{
|
20268 |
+
"epoch": 9.09,
|
20269 |
+
"learning_rate": 0.00020906691942311213,
|
20270 |
+
"loss": 0.0,
|
20271 |
+
"step": 1688500
|
20272 |
+
},
|
20273 |
+
{
|
20274 |
+
"epoch": 9.1,
|
20275 |
+
"learning_rate": 0.00020903999224497268,
|
20276 |
+
"loss": 0.0,
|
20277 |
+
"step": 1689000
|
20278 |
+
},
|
20279 |
+
{
|
20280 |
+
"epoch": 9.1,
|
20281 |
+
"learning_rate": 0.00020901306506683324,
|
20282 |
+
"loss": 0.0,
|
20283 |
+
"step": 1689500
|
20284 |
+
},
|
20285 |
+
{
|
20286 |
+
"epoch": 9.1,
|
20287 |
+
"learning_rate": 0.00020898613788869377,
|
20288 |
+
"loss": 0.0,
|
20289 |
+
"step": 1690000
|
20290 |
+
},
|
20291 |
+
{
|
20292 |
+
"epoch": 9.1,
|
20293 |
+
"learning_rate": 0.00020895921071055435,
|
20294 |
+
"loss": 0.0,
|
20295 |
+
"step": 1690500
|
20296 |
+
},
|
20297 |
+
{
|
20298 |
+
"epoch": 9.11,
|
20299 |
+
"learning_rate": 0.0002089322835324149,
|
20300 |
+
"loss": 0.0,
|
20301 |
+
"step": 1691000
|
20302 |
+
},
|
20303 |
+
{
|
20304 |
+
"epoch": 9.11,
|
20305 |
+
"learning_rate": 0.00020890535635427547,
|
20306 |
+
"loss": 0.0,
|
20307 |
+
"step": 1691500
|
20308 |
+
},
|
20309 |
+
{
|
20310 |
+
"epoch": 9.11,
|
20311 |
+
"learning_rate": 0.00020887842917613605,
|
20312 |
+
"loss": 0.0,
|
20313 |
+
"step": 1692000
|
20314 |
+
},
|
20315 |
+
{
|
20316 |
+
"epoch": 9.11,
|
20317 |
+
"learning_rate": 0.0002088515019979966,
|
20318 |
+
"loss": 0.0,
|
20319 |
+
"step": 1692500
|
20320 |
+
},
|
20321 |
+
{
|
20322 |
+
"epoch": 9.12,
|
20323 |
+
"learning_rate": 0.00020882457481985716,
|
20324 |
+
"loss": 0.0,
|
20325 |
+
"step": 1693000
|
20326 |
+
},
|
20327 |
+
{
|
20328 |
+
"epoch": 9.12,
|
20329 |
+
"learning_rate": 0.00020879764764171775,
|
20330 |
+
"loss": 0.0,
|
20331 |
+
"step": 1693500
|
20332 |
+
},
|
20333 |
+
{
|
20334 |
+
"epoch": 9.12,
|
20335 |
+
"learning_rate": 0.00020877072046357828,
|
20336 |
+
"loss": 0.0,
|
20337 |
+
"step": 1694000
|
20338 |
+
},
|
20339 |
+
{
|
20340 |
+
"epoch": 9.13,
|
20341 |
+
"learning_rate": 0.00020874379328543883,
|
20342 |
+
"loss": 0.0,
|
20343 |
+
"step": 1694500
|
20344 |
+
},
|
20345 |
+
{
|
20346 |
+
"epoch": 9.13,
|
20347 |
+
"learning_rate": 0.0002087168661072994,
|
20348 |
+
"loss": 0.0,
|
20349 |
+
"step": 1695000
|
20350 |
+
},
|
20351 |
+
{
|
20352 |
+
"epoch": 9.13,
|
20353 |
+
"learning_rate": 0.00020868993892915997,
|
20354 |
+
"loss": 0.0,
|
20355 |
+
"step": 1695500
|
20356 |
+
},
|
20357 |
+
{
|
20358 |
+
"epoch": 9.13,
|
20359 |
+
"learning_rate": 0.00020866301175102053,
|
20360 |
+
"loss": 0.0,
|
20361 |
+
"step": 1696000
|
20362 |
+
},
|
20363 |
+
{
|
20364 |
+
"epoch": 9.14,
|
20365 |
+
"learning_rate": 0.0002086360845728811,
|
20366 |
+
"loss": 0.0,
|
20367 |
+
"step": 1696500
|
20368 |
+
},
|
20369 |
+
{
|
20370 |
+
"epoch": 9.14,
|
20371 |
+
"learning_rate": 0.00020860915739474164,
|
20372 |
+
"loss": 0.0,
|
20373 |
+
"step": 1697000
|
20374 |
+
},
|
20375 |
+
{
|
20376 |
+
"epoch": 9.14,
|
20377 |
+
"learning_rate": 0.00020858223021660217,
|
20378 |
+
"loss": 0.0,
|
20379 |
+
"step": 1697500
|
20380 |
+
},
|
20381 |
+
{
|
20382 |
+
"epoch": 9.14,
|
20383 |
+
"learning_rate": 0.00020855530303846276,
|
20384 |
+
"loss": 0.0,
|
20385 |
+
"step": 1698000
|
20386 |
+
},
|
20387 |
+
{
|
20388 |
+
"epoch": 9.15,
|
20389 |
+
"learning_rate": 0.0002085283758603233,
|
20390 |
+
"loss": 0.0,
|
20391 |
+
"step": 1698500
|
20392 |
+
},
|
20393 |
+
{
|
20394 |
+
"epoch": 9.15,
|
20395 |
+
"learning_rate": 0.00020850144868218387,
|
20396 |
+
"loss": 0.0,
|
20397 |
+
"step": 1699000
|
20398 |
+
},
|
20399 |
+
{
|
20400 |
+
"epoch": 9.15,
|
20401 |
+
"learning_rate": 0.00020847452150404445,
|
20402 |
+
"loss": 0.0,
|
20403 |
+
"step": 1699500
|
20404 |
+
},
|
20405 |
+
{
|
20406 |
+
"epoch": 9.16,
|
20407 |
+
"learning_rate": 0.000208447594325905,
|
20408 |
+
"loss": 0.0,
|
20409 |
+
"step": 1700000
|
20410 |
+
},
|
20411 |
+
{
|
20412 |
+
"epoch": 9.16,
|
20413 |
+
"learning_rate": 0.00020842066714776557,
|
20414 |
+
"loss": 0.0,
|
20415 |
+
"step": 1700500
|
20416 |
+
},
|
20417 |
+
{
|
20418 |
+
"epoch": 9.16,
|
20419 |
+
"learning_rate": 0.00020839373996962615,
|
20420 |
+
"loss": 0.0,
|
20421 |
+
"step": 1701000
|
20422 |
+
},
|
20423 |
+
{
|
20424 |
+
"epoch": 9.16,
|
20425 |
+
"learning_rate": 0.00020836681279148668,
|
20426 |
+
"loss": 0.0,
|
20427 |
+
"step": 1701500
|
20428 |
+
},
|
20429 |
+
{
|
20430 |
+
"epoch": 9.17,
|
20431 |
+
"learning_rate": 0.00020833988561334724,
|
20432 |
+
"loss": 0.0,
|
20433 |
+
"step": 1702000
|
20434 |
+
},
|
20435 |
+
{
|
20436 |
+
"epoch": 9.17,
|
20437 |
+
"learning_rate": 0.0002083129584352078,
|
20438 |
+
"loss": 0.0,
|
20439 |
+
"step": 1702500
|
20440 |
+
},
|
20441 |
+
{
|
20442 |
+
"epoch": 9.17,
|
20443 |
+
"learning_rate": 0.00020828603125706838,
|
20444 |
+
"loss": 0.0,
|
20445 |
+
"step": 1703000
|
20446 |
+
},
|
20447 |
+
{
|
20448 |
+
"epoch": 9.17,
|
20449 |
+
"learning_rate": 0.00020825910407892893,
|
20450 |
+
"loss": 0.0,
|
20451 |
+
"step": 1703500
|
20452 |
+
},
|
20453 |
+
{
|
20454 |
+
"epoch": 9.18,
|
20455 |
+
"learning_rate": 0.0002082321769007895,
|
20456 |
+
"loss": 0.0,
|
20457 |
+
"step": 1704000
|
20458 |
+
},
|
20459 |
+
{
|
20460 |
+
"epoch": 9.18,
|
20461 |
+
"learning_rate": 0.00020820524972265005,
|
20462 |
+
"loss": 0.0,
|
20463 |
+
"step": 1704500
|
20464 |
+
},
|
20465 |
+
{
|
20466 |
+
"epoch": 9.18,
|
20467 |
+
"learning_rate": 0.00020817832254451063,
|
20468 |
+
"loss": 0.0,
|
20469 |
+
"step": 1705000
|
20470 |
+
},
|
20471 |
+
{
|
20472 |
+
"epoch": 9.18,
|
20473 |
+
"learning_rate": 0.00020815139536637116,
|
20474 |
+
"loss": 0.0,
|
20475 |
+
"step": 1705500
|
20476 |
+
},
|
20477 |
+
{
|
20478 |
+
"epoch": 9.19,
|
20479 |
+
"learning_rate": 0.00020812446818823172,
|
20480 |
+
"loss": 0.0,
|
20481 |
+
"step": 1706000
|
20482 |
+
},
|
20483 |
+
{
|
20484 |
+
"epoch": 9.19,
|
20485 |
+
"learning_rate": 0.00020809754101009227,
|
20486 |
+
"loss": 0.0,
|
20487 |
+
"step": 1706500
|
20488 |
+
},
|
20489 |
+
{
|
20490 |
+
"epoch": 9.19,
|
20491 |
+
"learning_rate": 0.00020807061383195286,
|
20492 |
+
"loss": 0.0,
|
20493 |
+
"step": 1707000
|
20494 |
+
},
|
20495 |
+
{
|
20496 |
+
"epoch": 9.2,
|
20497 |
+
"learning_rate": 0.0002080436866538134,
|
20498 |
+
"loss": 0.0,
|
20499 |
+
"step": 1707500
|
20500 |
+
},
|
20501 |
+
{
|
20502 |
+
"epoch": 9.2,
|
20503 |
+
"learning_rate": 0.00020801675947567397,
|
20504 |
+
"loss": 0.0,
|
20505 |
+
"step": 1708000
|
20506 |
+
},
|
20507 |
+
{
|
20508 |
+
"epoch": 9.2,
|
20509 |
+
"learning_rate": 0.00020798983229753455,
|
20510 |
+
"loss": 0.0,
|
20511 |
+
"step": 1708500
|
20512 |
+
},
|
20513 |
+
{
|
20514 |
+
"epoch": 9.2,
|
20515 |
+
"learning_rate": 0.00020796290511939508,
|
20516 |
+
"loss": 0.0,
|
20517 |
+
"step": 1709000
|
20518 |
+
},
|
20519 |
+
{
|
20520 |
+
"epoch": 9.21,
|
20521 |
+
"learning_rate": 0.00020793597794125564,
|
20522 |
+
"loss": 0.0,
|
20523 |
+
"step": 1709500
|
20524 |
+
},
|
20525 |
+
{
|
20526 |
+
"epoch": 9.21,
|
20527 |
+
"learning_rate": 0.0002079090507631162,
|
20528 |
+
"loss": 0.0,
|
20529 |
+
"step": 1710000
|
20530 |
+
},
|
20531 |
+
{
|
20532 |
+
"epoch": 9.21,
|
20533 |
+
"learning_rate": 0.00020788212358497678,
|
20534 |
+
"loss": 0.0,
|
20535 |
+
"step": 1710500
|
20536 |
+
},
|
20537 |
+
{
|
20538 |
+
"epoch": 9.21,
|
20539 |
+
"learning_rate": 0.00020785519640683734,
|
20540 |
+
"loss": 0.0,
|
20541 |
+
"step": 1711000
|
20542 |
+
},
|
20543 |
+
{
|
20544 |
+
"epoch": 9.22,
|
20545 |
+
"learning_rate": 0.0002078282692286979,
|
20546 |
+
"loss": 0.0,
|
20547 |
+
"step": 1711500
|
20548 |
+
},
|
20549 |
+
{
|
20550 |
+
"epoch": 9.22,
|
20551 |
+
"learning_rate": 0.00020780134205055845,
|
20552 |
+
"loss": 0.0,
|
20553 |
+
"step": 1712000
|
20554 |
+
},
|
20555 |
+
{
|
20556 |
+
"epoch": 9.22,
|
20557 |
+
"learning_rate": 0.00020777441487241903,
|
20558 |
+
"loss": 0.0,
|
20559 |
+
"step": 1712500
|
20560 |
+
},
|
20561 |
+
{
|
20562 |
+
"epoch": 9.23,
|
20563 |
+
"learning_rate": 0.00020774748769427956,
|
20564 |
+
"loss": 0.0,
|
20565 |
+
"step": 1713000
|
20566 |
+
},
|
20567 |
+
{
|
20568 |
+
"epoch": 9.23,
|
20569 |
+
"learning_rate": 0.00020772056051614012,
|
20570 |
+
"loss": 0.0,
|
20571 |
+
"step": 1713500
|
20572 |
+
},
|
20573 |
+
{
|
20574 |
+
"epoch": 9.23,
|
20575 |
+
"learning_rate": 0.00020769363333800067,
|
20576 |
+
"loss": 0.0,
|
20577 |
+
"step": 1714000
|
20578 |
+
},
|
20579 |
+
{
|
20580 |
+
"epoch": 9.23,
|
20581 |
+
"learning_rate": 0.00020766670615986126,
|
20582 |
+
"loss": 0.0,
|
20583 |
+
"step": 1714500
|
20584 |
+
},
|
20585 |
+
{
|
20586 |
+
"epoch": 9.24,
|
20587 |
+
"learning_rate": 0.00020763977898172181,
|
20588 |
+
"loss": 0.0,
|
20589 |
+
"step": 1715000
|
20590 |
+
},
|
20591 |
+
{
|
20592 |
+
"epoch": 9.24,
|
20593 |
+
"learning_rate": 0.00020761285180358237,
|
20594 |
+
"loss": 0.0,
|
20595 |
+
"step": 1715500
|
20596 |
+
},
|
20597 |
+
{
|
20598 |
+
"epoch": 9.24,
|
20599 |
+
"learning_rate": 0.00020758592462544295,
|
20600 |
+
"loss": 0.0,
|
20601 |
+
"step": 1716000
|
20602 |
+
},
|
20603 |
+
{
|
20604 |
+
"epoch": 9.24,
|
20605 |
+
"learning_rate": 0.0002075589974473035,
|
20606 |
+
"loss": 0.0,
|
20607 |
+
"step": 1716500
|
20608 |
+
},
|
20609 |
+
{
|
20610 |
+
"epoch": 9.25,
|
20611 |
+
"learning_rate": 0.00020753207026916404,
|
20612 |
+
"loss": 0.0,
|
20613 |
+
"step": 1717000
|
20614 |
+
},
|
20615 |
+
{
|
20616 |
+
"epoch": 9.25,
|
20617 |
+
"learning_rate": 0.0002075051430910246,
|
20618 |
+
"loss": 0.0,
|
20619 |
+
"step": 1717500
|
20620 |
+
},
|
20621 |
+
{
|
20622 |
+
"epoch": 9.25,
|
20623 |
+
"learning_rate": 0.00020747821591288518,
|
20624 |
+
"loss": 0.0,
|
20625 |
+
"step": 1718000
|
20626 |
+
},
|
20627 |
+
{
|
20628 |
+
"epoch": 9.25,
|
20629 |
+
"learning_rate": 0.00020745128873474574,
|
20630 |
+
"loss": 0.0,
|
20631 |
+
"step": 1718500
|
20632 |
+
},
|
20633 |
+
{
|
20634 |
+
"epoch": 9.26,
|
20635 |
+
"learning_rate": 0.0002074243615566063,
|
20636 |
+
"loss": 0.0,
|
20637 |
+
"step": 1719000
|
20638 |
+
},
|
20639 |
+
{
|
20640 |
+
"epoch": 9.26,
|
20641 |
+
"learning_rate": 0.00020739743437846688,
|
20642 |
+
"loss": 0.0,
|
20643 |
+
"step": 1719500
|
20644 |
+
},
|
20645 |
+
{
|
20646 |
+
"epoch": 9.26,
|
20647 |
+
"learning_rate": 0.00020737050720032743,
|
20648 |
+
"loss": 0.0,
|
20649 |
+
"step": 1720000
|
20650 |
+
},
|
20651 |
+
{
|
20652 |
+
"epoch": 9.27,
|
20653 |
+
"learning_rate": 0.00020734358002218796,
|
20654 |
+
"loss": 0.0,
|
20655 |
+
"step": 1720500
|
20656 |
+
},
|
20657 |
+
{
|
20658 |
+
"epoch": 9.27,
|
20659 |
+
"learning_rate": 0.00020731665284404852,
|
20660 |
+
"loss": 0.0,
|
20661 |
+
"step": 1721000
|
20662 |
+
},
|
20663 |
+
{
|
20664 |
+
"epoch": 9.27,
|
20665 |
+
"learning_rate": 0.00020728972566590908,
|
20666 |
+
"loss": 0.0,
|
20667 |
+
"step": 1721500
|
20668 |
+
},
|
20669 |
+
{
|
20670 |
+
"epoch": 9.27,
|
20671 |
+
"learning_rate": 0.00020726279848776966,
|
20672 |
+
"loss": 0.0,
|
20673 |
+
"step": 1722000
|
20674 |
+
},
|
20675 |
+
{
|
20676 |
+
"epoch": 9.28,
|
20677 |
+
"learning_rate": 0.00020723587130963022,
|
20678 |
+
"loss": 0.0,
|
20679 |
+
"step": 1722500
|
20680 |
+
},
|
20681 |
+
{
|
20682 |
+
"epoch": 9.28,
|
20683 |
+
"learning_rate": 0.00020720894413149077,
|
20684 |
+
"loss": 0.0,
|
20685 |
+
"step": 1723000
|
20686 |
+
},
|
20687 |
+
{
|
20688 |
+
"epoch": 9.28,
|
20689 |
+
"learning_rate": 0.00020718201695335136,
|
20690 |
+
"loss": 0.0,
|
20691 |
+
"step": 1723500
|
20692 |
+
},
|
20693 |
+
{
|
20694 |
+
"epoch": 9.28,
|
20695 |
+
"learning_rate": 0.00020715508977521191,
|
20696 |
+
"loss": 0.0,
|
20697 |
+
"step": 1724000
|
20698 |
+
},
|
20699 |
+
{
|
20700 |
+
"epoch": 9.29,
|
20701 |
+
"learning_rate": 0.00020712816259707244,
|
20702 |
+
"loss": 0.0,
|
20703 |
+
"step": 1724500
|
20704 |
+
},
|
20705 |
+
{
|
20706 |
+
"epoch": 9.29,
|
20707 |
+
"learning_rate": 0.000207101235418933,
|
20708 |
+
"loss": 0.0,
|
20709 |
+
"step": 1725000
|
20710 |
+
},
|
20711 |
+
{
|
20712 |
+
"epoch": 9.29,
|
20713 |
+
"learning_rate": 0.00020707430824079358,
|
20714 |
+
"loss": 0.0,
|
20715 |
+
"step": 1725500
|
20716 |
+
},
|
20717 |
+
{
|
20718 |
+
"epoch": 9.3,
|
20719 |
+
"learning_rate": 0.00020704738106265414,
|
20720 |
+
"loss": 0.0,
|
20721 |
+
"step": 1726000
|
20722 |
+
},
|
20723 |
+
{
|
20724 |
+
"epoch": 9.3,
|
20725 |
+
"learning_rate": 0.0002070204538845147,
|
20726 |
+
"loss": 0.0,
|
20727 |
+
"step": 1726500
|
20728 |
+
},
|
20729 |
+
{
|
20730 |
+
"epoch": 9.3,
|
20731 |
+
"learning_rate": 0.00020699352670637528,
|
20732 |
+
"loss": 0.0,
|
20733 |
+
"step": 1727000
|
20734 |
+
},
|
20735 |
+
{
|
20736 |
+
"epoch": 9.3,
|
20737 |
+
"learning_rate": 0.00020696659952823584,
|
20738 |
+
"loss": 0.0,
|
20739 |
+
"step": 1727500
|
20740 |
+
},
|
20741 |
+
{
|
20742 |
+
"epoch": 9.31,
|
20743 |
+
"learning_rate": 0.0002069396723500964,
|
20744 |
+
"loss": 0.0,
|
20745 |
+
"step": 1728000
|
20746 |
+
},
|
20747 |
+
{
|
20748 |
+
"epoch": 9.31,
|
20749 |
+
"learning_rate": 0.00020691274517195692,
|
20750 |
+
"loss": 0.0,
|
20751 |
+
"step": 1728500
|
20752 |
+
},
|
20753 |
+
{
|
20754 |
+
"epoch": 9.31,
|
20755 |
+
"learning_rate": 0.0002068858179938175,
|
20756 |
+
"loss": 0.0,
|
20757 |
+
"step": 1729000
|
20758 |
+
},
|
20759 |
+
{
|
20760 |
+
"epoch": 9.31,
|
20761 |
+
"learning_rate": 0.00020685889081567806,
|
20762 |
+
"loss": 0.0,
|
20763 |
+
"step": 1729500
|
20764 |
+
},
|
20765 |
+
{
|
20766 |
+
"epoch": 9.32,
|
20767 |
+
"learning_rate": 0.00020683196363753862,
|
20768 |
+
"loss": 0.0,
|
20769 |
+
"step": 1730000
|
20770 |
+
},
|
20771 |
+
{
|
20772 |
+
"epoch": 9.32,
|
20773 |
+
"learning_rate": 0.00020680503645939918,
|
20774 |
+
"loss": 0.0,
|
20775 |
+
"step": 1730500
|
20776 |
+
},
|
20777 |
+
{
|
20778 |
+
"epoch": 9.32,
|
20779 |
+
"learning_rate": 0.00020677810928125976,
|
20780 |
+
"loss": 0.0,
|
20781 |
+
"step": 1731000
|
20782 |
+
},
|
20783 |
+
{
|
20784 |
+
"epoch": 9.32,
|
20785 |
+
"learning_rate": 0.00020675118210312032,
|
20786 |
+
"loss": 0.0,
|
20787 |
+
"step": 1731500
|
20788 |
+
},
|
20789 |
+
{
|
20790 |
+
"epoch": 9.33,
|
20791 |
+
"learning_rate": 0.00020672425492498085,
|
20792 |
+
"loss": 0.0,
|
20793 |
+
"step": 1732000
|
20794 |
+
},
|
20795 |
+
{
|
20796 |
+
"epoch": 9.33,
|
20797 |
+
"learning_rate": 0.0002066973277468414,
|
20798 |
+
"loss": 0.0,
|
20799 |
+
"step": 1732500
|
20800 |
+
},
|
20801 |
+
{
|
20802 |
+
"epoch": 9.33,
|
20803 |
+
"learning_rate": 0.00020667040056870199,
|
20804 |
+
"loss": 0.0,
|
20805 |
+
"step": 1733000
|
20806 |
+
},
|
20807 |
+
{
|
20808 |
+
"epoch": 9.34,
|
20809 |
+
"learning_rate": 0.00020664347339056254,
|
20810 |
+
"loss": 0.0,
|
20811 |
+
"step": 1733500
|
20812 |
+
},
|
20813 |
+
{
|
20814 |
+
"epoch": 9.34,
|
20815 |
+
"learning_rate": 0.0002066165462124231,
|
20816 |
+
"loss": 0.0,
|
20817 |
+
"step": 1734000
|
20818 |
+
},
|
20819 |
+
{
|
20820 |
+
"epoch": 9.34,
|
20821 |
+
"learning_rate": 0.00020658961903428368,
|
20822 |
+
"loss": 0.0,
|
20823 |
+
"step": 1734500
|
20824 |
+
},
|
20825 |
+
{
|
20826 |
+
"epoch": 9.34,
|
20827 |
+
"learning_rate": 0.00020656269185614424,
|
20828 |
+
"loss": 0.0,
|
20829 |
+
"step": 1735000
|
20830 |
+
},
|
20831 |
+
{
|
20832 |
+
"epoch": 9.35,
|
20833 |
+
"learning_rate": 0.0002065357646780048,
|
20834 |
+
"loss": 0.0,
|
20835 |
+
"step": 1735500
|
20836 |
+
},
|
20837 |
+
{
|
20838 |
+
"epoch": 9.35,
|
20839 |
+
"learning_rate": 0.00020650883749986532,
|
20840 |
+
"loss": 0.0,
|
20841 |
+
"step": 1736000
|
20842 |
+
},
|
20843 |
+
{
|
20844 |
+
"epoch": 9.35,
|
20845 |
+
"learning_rate": 0.0002064819103217259,
|
20846 |
+
"loss": 0.0,
|
20847 |
+
"step": 1736500
|
20848 |
+
},
|
20849 |
+
{
|
20850 |
+
"epoch": 9.35,
|
20851 |
+
"learning_rate": 0.00020645498314358647,
|
20852 |
+
"loss": 0.0,
|
20853 |
+
"step": 1737000
|
20854 |
+
},
|
20855 |
+
{
|
20856 |
+
"epoch": 9.36,
|
20857 |
+
"learning_rate": 0.00020642805596544702,
|
20858 |
+
"loss": 0.0,
|
20859 |
+
"step": 1737500
|
20860 |
+
},
|
20861 |
+
{
|
20862 |
+
"epoch": 9.36,
|
20863 |
+
"learning_rate": 0.00020640112878730758,
|
20864 |
+
"loss": 0.0,
|
20865 |
+
"step": 1738000
|
20866 |
+
},
|
20867 |
+
{
|
20868 |
+
"epoch": 9.36,
|
20869 |
+
"learning_rate": 0.00020637420160916816,
|
20870 |
+
"loss": 0.0,
|
20871 |
+
"step": 1738500
|
20872 |
+
},
|
20873 |
+
{
|
20874 |
+
"epoch": 9.37,
|
20875 |
+
"learning_rate": 0.00020634727443102872,
|
20876 |
+
"loss": 0.0,
|
20877 |
+
"step": 1739000
|
20878 |
+
},
|
20879 |
+
{
|
20880 |
+
"epoch": 9.37,
|
20881 |
+
"learning_rate": 0.00020632034725288927,
|
20882 |
+
"loss": 0.0,
|
20883 |
+
"step": 1739500
|
20884 |
+
},
|
20885 |
+
{
|
20886 |
+
"epoch": 9.37,
|
20887 |
+
"learning_rate": 0.0002062934200747498,
|
20888 |
+
"loss": 0.0,
|
20889 |
+
"step": 1740000
|
20890 |
+
},
|
20891 |
+
{
|
20892 |
+
"epoch": 9.37,
|
20893 |
+
"learning_rate": 0.0002062664928966104,
|
20894 |
+
"loss": 0.0,
|
20895 |
+
"step": 1740500
|
20896 |
+
},
|
20897 |
+
{
|
20898 |
+
"epoch": 9.38,
|
20899 |
+
"learning_rate": 0.00020623956571847094,
|
20900 |
+
"loss": 0.0,
|
20901 |
+
"step": 1741000
|
20902 |
+
},
|
20903 |
+
{
|
20904 |
+
"epoch": 9.38,
|
20905 |
+
"learning_rate": 0.0002062126385403315,
|
20906 |
+
"loss": 0.0,
|
20907 |
+
"step": 1741500
|
20908 |
+
},
|
20909 |
+
{
|
20910 |
+
"epoch": 9.38,
|
20911 |
+
"learning_rate": 0.00020618571136219208,
|
20912 |
+
"loss": 0.0,
|
20913 |
+
"step": 1742000
|
20914 |
+
},
|
20915 |
+
{
|
20916 |
+
"epoch": 9.38,
|
20917 |
+
"learning_rate": 0.00020615878418405264,
|
20918 |
+
"loss": 0.0,
|
20919 |
+
"step": 1742500
|
20920 |
+
},
|
20921 |
+
{
|
20922 |
+
"epoch": 9.39,
|
20923 |
+
"learning_rate": 0.0002061318570059132,
|
20924 |
+
"loss": 0.0,
|
20925 |
+
"step": 1743000
|
20926 |
+
},
|
20927 |
+
{
|
20928 |
+
"epoch": 9.39,
|
20929 |
+
"learning_rate": 0.00020610492982777373,
|
20930 |
+
"loss": 0.0,
|
20931 |
+
"step": 1743500
|
20932 |
+
},
|
20933 |
+
{
|
20934 |
+
"epoch": 9.39,
|
20935 |
+
"learning_rate": 0.0002060780026496343,
|
20936 |
+
"loss": 0.0,
|
20937 |
+
"step": 1744000
|
20938 |
+
},
|
20939 |
+
{
|
20940 |
+
"epoch": 9.39,
|
20941 |
+
"learning_rate": 0.00020605107547149487,
|
20942 |
+
"loss": 0.0,
|
20943 |
+
"step": 1744500
|
20944 |
+
},
|
20945 |
+
{
|
20946 |
+
"epoch": 9.4,
|
20947 |
+
"learning_rate": 0.00020602414829335542,
|
20948 |
+
"loss": 0.0,
|
20949 |
+
"step": 1745000
|
20950 |
+
},
|
20951 |
+
{
|
20952 |
+
"epoch": 9.4,
|
20953 |
+
"learning_rate": 0.00020599722111521598,
|
20954 |
+
"loss": 0.0,
|
20955 |
+
"step": 1745500
|
20956 |
+
},
|
20957 |
+
{
|
20958 |
+
"epoch": 9.4,
|
20959 |
+
"learning_rate": 0.00020597029393707656,
|
20960 |
+
"loss": 0.0,
|
20961 |
+
"step": 1746000
|
20962 |
+
},
|
20963 |
+
{
|
20964 |
+
"epoch": 9.41,
|
20965 |
+
"learning_rate": 0.00020594336675893712,
|
20966 |
+
"loss": 0.0,
|
20967 |
+
"step": 1746500
|
20968 |
+
},
|
20969 |
+
{
|
20970 |
+
"epoch": 9.41,
|
20971 |
+
"learning_rate": 0.00020591643958079768,
|
20972 |
+
"loss": 0.0,
|
20973 |
+
"step": 1747000
|
20974 |
+
},
|
20975 |
+
{
|
20976 |
+
"epoch": 9.41,
|
20977 |
+
"learning_rate": 0.0002058895124026582,
|
20978 |
+
"loss": 0.0,
|
20979 |
+
"step": 1747500
|
20980 |
+
},
|
20981 |
+
{
|
20982 |
+
"epoch": 9.41,
|
20983 |
+
"learning_rate": 0.0002058625852245188,
|
20984 |
+
"loss": 0.0,
|
20985 |
+
"step": 1748000
|
20986 |
+
},
|
20987 |
+
{
|
20988 |
+
"epoch": 9.42,
|
20989 |
+
"learning_rate": 0.00020583565804637935,
|
20990 |
+
"loss": 0.0,
|
20991 |
+
"step": 1748500
|
20992 |
+
},
|
20993 |
+
{
|
20994 |
+
"epoch": 9.42,
|
20995 |
+
"learning_rate": 0.0002058087308682399,
|
20996 |
+
"loss": 0.0,
|
20997 |
+
"step": 1749000
|
20998 |
+
},
|
20999 |
+
{
|
21000 |
+
"epoch": 9.42,
|
21001 |
+
"learning_rate": 0.0002057818036901005,
|
21002 |
+
"loss": 0.0,
|
21003 |
+
"step": 1749500
|
21004 |
+
},
|
21005 |
+
{
|
21006 |
+
"epoch": 9.42,
|
21007 |
+
"learning_rate": 0.00020575487651196104,
|
21008 |
+
"loss": 0.0,
|
21009 |
+
"step": 1750000
|
21010 |
}
|
21011 |
],
|
21012 |
"logging_steps": 500,
|
vocab.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:913db505dc9a9500992c7fc62f6038e04d17748445d9a72fe81b92b6eb78b0c8
|
3 |
+
size 1536750
|