Training in progress, step 2930, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +220 -6
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735396724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:381fb1d1767bb179d87997063212ed840def37282037cba0a8bd39831ddeb1b8
|
| 3 |
size 735396724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470915147
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6339bbd4c22e595726ce9ea99c27606bec7f67333f9de63c3094a7a082443ac6
|
| 3 |
size 1470915147
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2d6ef7649fd8c8eb9892e7aa216ffeaa0e96cbea91bb923d0bb5e1009eb9f02
|
| 3 |
size 16325
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc0d24c1c5a395ef52114729ca4240df868d7895350f6bd732231ddc3c8279cf
|
| 3 |
size 16325
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57e565d88be6db72e5544fc1fccbbff464c99d832aae52d322848fe9137f2595
|
| 3 |
size 16325
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71e288e0d3e5dd88f3a0e0083fe76f4c8130ea391900858aae67a004d1c5200b
|
| 3 |
size 16325
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1472fc43334d289d5e02c7273e7440d57f120e4b08f8c77342be3bf751a7db1
|
| 3 |
size 16325
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91323545cf1a6b49e3abd48036e93053c245271556febc9bbe9b59178d1233bd
|
| 3 |
size 16325
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b86dce7fc7c357d6d378197c161c7c81d8be93d643b7006ec55e1edea74f6ec
|
| 3 |
size 16325
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:383638b19900ad65d670c04a80be072f927a9aec96b7e2c38852134803ca2a7b
|
| 3 |
size 16325
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a545be8beafc545baba600ea650e0c7f6ef81fbbfbc9cb608754d90bb0ceacf
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "model/checkpoint-
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1465,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -222,6 +222,220 @@
|
|
| 222 |
"eval_samples_per_second": 1510.933,
|
| 223 |
"eval_steps_per_second": 23.608,
|
| 224 |
"step": 1465
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 225 |
}
|
| 226 |
],
|
| 227 |
"logging_steps": 50,
|
|
@@ -241,7 +455,7 @@
|
|
| 241 |
"attributes": {}
|
| 242 |
}
|
| 243 |
},
|
| 244 |
-
"total_flos":
|
| 245 |
"train_batch_size": 256,
|
| 246 |
"trial_name": null,
|
| 247 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 2930,
|
| 3 |
+
"best_metric": 0.7423178801283339,
|
| 4 |
+
"best_model_checkpoint": "model/checkpoint-2930",
|
| 5 |
+
"epoch": 0.5,
|
| 6 |
"eval_steps": 1465,
|
| 7 |
+
"global_step": 2930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 222 |
"eval_samples_per_second": 1510.933,
|
| 223 |
"eval_steps_per_second": 23.608,
|
| 224 |
"step": 1465
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.25597269624573377,
|
| 228 |
+
"grad_norm": 0.21379445493221283,
|
| 229 |
+
"learning_rate": 2.180439671952838e-05,
|
| 230 |
+
"loss": 0.1029,
|
| 231 |
+
"step": 1500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2645051194539249,
|
| 235 |
+
"grad_norm": 0.24124079942703247,
|
| 236 |
+
"learning_rate": 2.157019105016262e-05,
|
| 237 |
+
"loss": 0.1021,
|
| 238 |
+
"step": 1550
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.27303754266211605,
|
| 242 |
+
"grad_norm": 0.2577572464942932,
|
| 243 |
+
"learning_rate": 2.1329058775980853e-05,
|
| 244 |
+
"loss": 0.1009,
|
| 245 |
+
"step": 1600
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.2815699658703072,
|
| 249 |
+
"grad_norm": 0.25605666637420654,
|
| 250 |
+
"learning_rate": 2.1081184041722966e-05,
|
| 251 |
+
"loss": 0.0994,
|
| 252 |
+
"step": 1650
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.2901023890784983,
|
| 256 |
+
"grad_norm": 0.20153528451919556,
|
| 257 |
+
"learning_rate": 2.0826756141122535e-05,
|
| 258 |
+
"loss": 0.101,
|
| 259 |
+
"step": 1700
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.2986348122866894,
|
| 263 |
+
"grad_norm": 0.24819990992546082,
|
| 264 |
+
"learning_rate": 2.0565969372349447e-05,
|
| 265 |
+
"loss": 0.1005,
|
| 266 |
+
"step": 1750
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.30716723549488056,
|
| 270 |
+
"grad_norm": 0.282105416059494,
|
| 271 |
+
"learning_rate": 2.0299022889630834e-05,
|
| 272 |
+
"loss": 0.0989,
|
| 273 |
+
"step": 1800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.31569965870307165,
|
| 277 |
+
"grad_norm": 0.24825932085514069,
|
| 278 |
+
"learning_rate": 2.0026120551163576e-05,
|
| 279 |
+
"loss": 0.1015,
|
| 280 |
+
"step": 1850
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3242320819112628,
|
| 284 |
+
"grad_norm": 0.19880250096321106,
|
| 285 |
+
"learning_rate": 1.9747470763434527e-05,
|
| 286 |
+
"loss": 0.0981,
|
| 287 |
+
"step": 1900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.33276450511945393,
|
| 291 |
+
"grad_norm": 0.25610214471817017,
|
| 292 |
+
"learning_rate": 1.9463286322067397e-05,
|
| 293 |
+
"loss": 0.0993,
|
| 294 |
+
"step": 1950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.3412969283276451,
|
| 298 |
+
"grad_norm": 0.28560763597488403,
|
| 299 |
+
"learning_rate": 1.9173784249317774e-05,
|
| 300 |
+
"loss": 0.097,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.34982935153583616,
|
| 305 |
+
"grad_norm": 0.36660489439964294,
|
| 306 |
+
"learning_rate": 1.8879185628340366e-05,
|
| 307 |
+
"loss": 0.0965,
|
| 308 |
+
"step": 2050
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3583617747440273,
|
| 312 |
+
"grad_norm": 0.26472488045692444,
|
| 313 |
+
"learning_rate": 1.8579715434355174e-05,
|
| 314 |
+
"loss": 0.0988,
|
| 315 |
+
"step": 2100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.36689419795221845,
|
| 319 |
+
"grad_norm": 0.25718653202056885,
|
| 320 |
+
"learning_rate": 1.8275602362841312e-05,
|
| 321 |
+
"loss": 0.0989,
|
| 322 |
+
"step": 2150
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.37542662116040953,
|
| 326 |
+
"grad_norm": 0.2548709213733673,
|
| 327 |
+
"learning_rate": 1.7967078654889858e-05,
|
| 328 |
+
"loss": 0.0974,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.3839590443686007,
|
| 333 |
+
"grad_norm": 0.235497385263443,
|
| 334 |
+
"learning_rate": 1.7654379919849003e-05,
|
| 335 |
+
"loss": 0.0943,
|
| 336 |
+
"step": 2250
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.3924914675767918,
|
| 340 |
+
"grad_norm": 0.31954771280288696,
|
| 341 |
+
"learning_rate": 1.7337744955397012e-05,
|
| 342 |
+
"loss": 0.0965,
|
| 343 |
+
"step": 2300
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.40102389078498296,
|
| 347 |
+
"grad_norm": 0.2830738425254822,
|
| 348 |
+
"learning_rate": 1.7017415565180293e-05,
|
| 349 |
+
"loss": 0.0964,
|
| 350 |
+
"step": 2350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.40955631399317405,
|
| 354 |
+
"grad_norm": 0.23557038605213165,
|
| 355 |
+
"learning_rate": 1.669363637415601e-05,
|
| 356 |
+
"loss": 0.096,
|
| 357 |
+
"step": 2400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.4180887372013652,
|
| 361 |
+
"grad_norm": 0.3127359449863434,
|
| 362 |
+
"learning_rate": 1.636665464178004e-05,
|
| 363 |
+
"loss": 0.0951,
|
| 364 |
+
"step": 2450
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.42662116040955633,
|
| 368 |
+
"grad_norm": 0.2751990556716919,
|
| 369 |
+
"learning_rate": 1.603672007318316e-05,
|
| 370 |
+
"loss": 0.0962,
|
| 371 |
+
"step": 2500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.4351535836177474,
|
| 375 |
+
"grad_norm": 0.23224587738513947,
|
| 376 |
+
"learning_rate": 1.5704084628479443e-05,
|
| 377 |
+
"loss": 0.0975,
|
| 378 |
+
"step": 2550
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.44368600682593856,
|
| 382 |
+
"grad_norm": 0.2621734142303467,
|
| 383 |
+
"learning_rate": 1.536900233035271e-05,
|
| 384 |
+
"loss": 0.0947,
|
| 385 |
+
"step": 2600
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.4522184300341297,
|
| 389 |
+
"grad_norm": 0.2019677609205246,
|
| 390 |
+
"learning_rate": 1.5031729070067773e-05,
|
| 391 |
+
"loss": 0.0967,
|
| 392 |
+
"step": 2650
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.46075085324232085,
|
| 396 |
+
"grad_norm": 0.2038186639547348,
|
| 397 |
+
"learning_rate": 1.4692522412054772e-05,
|
| 398 |
+
"loss": 0.095,
|
| 399 |
+
"step": 2700
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.46928327645051193,
|
| 403 |
+
"grad_norm": 0.25815144181251526,
|
| 404 |
+
"learning_rate": 1.4351641397215703e-05,
|
| 405 |
+
"loss": 0.0935,
|
| 406 |
+
"step": 2750
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.4778156996587031,
|
| 410 |
+
"grad_norm": 0.2345559149980545,
|
| 411 |
+
"learning_rate": 1.4009346345103494e-05,
|
| 412 |
+
"loss": 0.0947,
|
| 413 |
+
"step": 2800
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.4863481228668942,
|
| 417 |
+
"grad_norm": 0.20084676146507263,
|
| 418 |
+
"learning_rate": 1.366589865512454e-05,
|
| 419 |
+
"loss": 0.0946,
|
| 420 |
+
"step": 2850
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.4948805460750853,
|
| 424 |
+
"grad_norm": 0.29759591817855835,
|
| 425 |
+
"learning_rate": 1.3321560606916652e-05,
|
| 426 |
+
"loss": 0.0951,
|
| 427 |
+
"step": 2900
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.5,
|
| 431 |
+
"eval_entity_f1": 0.7423178801283339,
|
| 432 |
+
"eval_entity_precision": 0.6650263167961575,
|
| 433 |
+
"eval_entity_recall": 0.8804226585921899,
|
| 434 |
+
"eval_loss": 0.08911468833684921,
|
| 435 |
+
"eval_runtime": 790.8047,
|
| 436 |
+
"eval_samples_per_second": 1517.442,
|
| 437 |
+
"eval_steps_per_second": 23.71,
|
| 438 |
+
"step": 2930
|
| 439 |
}
|
| 440 |
],
|
| 441 |
"logging_steps": 50,
|
|
|
|
| 455 |
"attributes": {}
|
| 456 |
}
|
| 457 |
},
|
| 458 |
+
"total_flos": 3.706880778043392e+17,
|
| 459 |
"train_batch_size": 256,
|
| 460 |
"trial_name": null,
|
| 461 |
"trial_params": null
|