Training in progress, step 9500, 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 4523108832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbea7d5f54f57679a90cba71f46bbf6c332fd420c33b306d96c81472be41f84e
|
| 3 |
size 4523108832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2912179275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13cf77e7b99c3db96808de10020f37d02f6882906b8f4b37afd6411b00c8233a
|
| 3 |
size 2912179275
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94b1a91810562429d557b8e7351faf37318bcc85fdd6894e29a36576f9f1604
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f5a942dc6ef7ac130d236db01f3a3420bd6734f1ffdb87a8973ecf688f97a4e
|
| 3 |
size 1383
|
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 sha256:63648154d3e77a1db2914de15171f8c04129f962d7c01a66dad259f7f1d60451
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -6308,6 +6308,356 @@
|
|
| 6308 |
"learning_rate": 2.004e-05,
|
| 6309 |
"loss": 0.01628260165452957,
|
| 6310 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6311 |
}
|
| 6312 |
],
|
| 6313 |
"logging_steps": 10,
|
|
@@ -6327,7 +6677,7 @@
|
|
| 6327 |
"attributes": {}
|
| 6328 |
}
|
| 6329 |
},
|
| 6330 |
-
"total_flos":
|
| 6331 |
"train_batch_size": 1,
|
| 6332 |
"trial_name": null,
|
| 6333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0192,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6308 |
"learning_rate": 2.004e-05,
|
| 6309 |
"loss": 0.01628260165452957,
|
| 6310 |
"step": 9000
|
| 6311 |
+
},
|
| 6312 |
+
{
|
| 6313 |
+
"epoch": 9.0014,
|
| 6314 |
+
"grad_norm": 0.08494532853364944,
|
| 6315 |
+
"learning_rate": 1.984e-05,
|
| 6316 |
+
"loss": 0.014085091650485992,
|
| 6317 |
+
"step": 9010
|
| 6318 |
+
},
|
| 6319 |
+
{
|
| 6320 |
+
"epoch": 9.0024,
|
| 6321 |
+
"grad_norm": 0.06271655112504959,
|
| 6322 |
+
"learning_rate": 1.9640000000000002e-05,
|
| 6323 |
+
"loss": 0.014741827547550202,
|
| 6324 |
+
"step": 9020
|
| 6325 |
+
},
|
| 6326 |
+
{
|
| 6327 |
+
"epoch": 9.0034,
|
| 6328 |
+
"grad_norm": 0.05553199723362923,
|
| 6329 |
+
"learning_rate": 1.944e-05,
|
| 6330 |
+
"loss": 0.015085065364837646,
|
| 6331 |
+
"step": 9030
|
| 6332 |
+
},
|
| 6333 |
+
{
|
| 6334 |
+
"epoch": 9.0044,
|
| 6335 |
+
"grad_norm": 0.07189421355724335,
|
| 6336 |
+
"learning_rate": 1.924e-05,
|
| 6337 |
+
"loss": 0.015170367062091827,
|
| 6338 |
+
"step": 9040
|
| 6339 |
+
},
|
| 6340 |
+
{
|
| 6341 |
+
"epoch": 9.0054,
|
| 6342 |
+
"grad_norm": 0.07952412962913513,
|
| 6343 |
+
"learning_rate": 1.904e-05,
|
| 6344 |
+
"loss": 0.015609446167945861,
|
| 6345 |
+
"step": 9050
|
| 6346 |
+
},
|
| 6347 |
+
{
|
| 6348 |
+
"epoch": 9.0064,
|
| 6349 |
+
"grad_norm": 0.07108260691165924,
|
| 6350 |
+
"learning_rate": 1.8840000000000003e-05,
|
| 6351 |
+
"loss": 0.016404539346694946,
|
| 6352 |
+
"step": 9060
|
| 6353 |
+
},
|
| 6354 |
+
{
|
| 6355 |
+
"epoch": 9.0074,
|
| 6356 |
+
"grad_norm": 0.06802374124526978,
|
| 6357 |
+
"learning_rate": 1.864e-05,
|
| 6358 |
+
"loss": 0.015850432217121124,
|
| 6359 |
+
"step": 9070
|
| 6360 |
+
},
|
| 6361 |
+
{
|
| 6362 |
+
"epoch": 9.0084,
|
| 6363 |
+
"grad_norm": 0.050249889492988586,
|
| 6364 |
+
"learning_rate": 1.8440000000000003e-05,
|
| 6365 |
+
"loss": 0.015042982995510101,
|
| 6366 |
+
"step": 9080
|
| 6367 |
+
},
|
| 6368 |
+
{
|
| 6369 |
+
"epoch": 9.0094,
|
| 6370 |
+
"grad_norm": 0.06494880467653275,
|
| 6371 |
+
"learning_rate": 1.824e-05,
|
| 6372 |
+
"loss": 0.015259303152561188,
|
| 6373 |
+
"step": 9090
|
| 6374 |
+
},
|
| 6375 |
+
{
|
| 6376 |
+
"epoch": 9.0104,
|
| 6377 |
+
"grad_norm": 0.06114324554800987,
|
| 6378 |
+
"learning_rate": 1.804e-05,
|
| 6379 |
+
"loss": 0.015477609634399415,
|
| 6380 |
+
"step": 9100
|
| 6381 |
+
},
|
| 6382 |
+
{
|
| 6383 |
+
"epoch": 9.0114,
|
| 6384 |
+
"grad_norm": 0.06710667163133621,
|
| 6385 |
+
"learning_rate": 1.7840000000000002e-05,
|
| 6386 |
+
"loss": 0.015735583007335664,
|
| 6387 |
+
"step": 9110
|
| 6388 |
+
},
|
| 6389 |
+
{
|
| 6390 |
+
"epoch": 9.0124,
|
| 6391 |
+
"grad_norm": 0.058985739946365356,
|
| 6392 |
+
"learning_rate": 1.764e-05,
|
| 6393 |
+
"loss": 0.01523323804140091,
|
| 6394 |
+
"step": 9120
|
| 6395 |
+
},
|
| 6396 |
+
{
|
| 6397 |
+
"epoch": 9.0134,
|
| 6398 |
+
"grad_norm": 0.06335913389921188,
|
| 6399 |
+
"learning_rate": 1.7440000000000002e-05,
|
| 6400 |
+
"loss": 0.014204534888267516,
|
| 6401 |
+
"step": 9130
|
| 6402 |
+
},
|
| 6403 |
+
{
|
| 6404 |
+
"epoch": 9.0144,
|
| 6405 |
+
"grad_norm": 0.0716351643204689,
|
| 6406 |
+
"learning_rate": 1.724e-05,
|
| 6407 |
+
"loss": 0.014392800629138947,
|
| 6408 |
+
"step": 9140
|
| 6409 |
+
},
|
| 6410 |
+
{
|
| 6411 |
+
"epoch": 9.0154,
|
| 6412 |
+
"grad_norm": 0.08384208381175995,
|
| 6413 |
+
"learning_rate": 1.704e-05,
|
| 6414 |
+
"loss": 0.016598230600357054,
|
| 6415 |
+
"step": 9150
|
| 6416 |
+
},
|
| 6417 |
+
{
|
| 6418 |
+
"epoch": 9.0164,
|
| 6419 |
+
"grad_norm": 0.085759237408638,
|
| 6420 |
+
"learning_rate": 1.684e-05,
|
| 6421 |
+
"loss": 0.014103879034519196,
|
| 6422 |
+
"step": 9160
|
| 6423 |
+
},
|
| 6424 |
+
{
|
| 6425 |
+
"epoch": 9.0174,
|
| 6426 |
+
"grad_norm": 0.12926150858402252,
|
| 6427 |
+
"learning_rate": 1.664e-05,
|
| 6428 |
+
"loss": 0.015359596908092498,
|
| 6429 |
+
"step": 9170
|
| 6430 |
+
},
|
| 6431 |
+
{
|
| 6432 |
+
"epoch": 9.0184,
|
| 6433 |
+
"grad_norm": 0.07225863635540009,
|
| 6434 |
+
"learning_rate": 1.644e-05,
|
| 6435 |
+
"loss": 0.014975431561470031,
|
| 6436 |
+
"step": 9180
|
| 6437 |
+
},
|
| 6438 |
+
{
|
| 6439 |
+
"epoch": 9.0194,
|
| 6440 |
+
"grad_norm": 0.07080310583114624,
|
| 6441 |
+
"learning_rate": 1.624e-05,
|
| 6442 |
+
"loss": 0.015512678027153014,
|
| 6443 |
+
"step": 9190
|
| 6444 |
+
},
|
| 6445 |
+
{
|
| 6446 |
+
"epoch": 9.0204,
|
| 6447 |
+
"grad_norm": 0.06747028976678848,
|
| 6448 |
+
"learning_rate": 1.604e-05,
|
| 6449 |
+
"loss": 0.01568002849817276,
|
| 6450 |
+
"step": 9200
|
| 6451 |
+
},
|
| 6452 |
+
{
|
| 6453 |
+
"epoch": 9.0214,
|
| 6454 |
+
"grad_norm": 0.05957520753145218,
|
| 6455 |
+
"learning_rate": 1.584e-05,
|
| 6456 |
+
"loss": 0.015441593527793885,
|
| 6457 |
+
"step": 9210
|
| 6458 |
+
},
|
| 6459 |
+
{
|
| 6460 |
+
"epoch": 9.0224,
|
| 6461 |
+
"grad_norm": 0.06704767793416977,
|
| 6462 |
+
"learning_rate": 1.5640000000000003e-05,
|
| 6463 |
+
"loss": 0.014649063348770142,
|
| 6464 |
+
"step": 9220
|
| 6465 |
+
},
|
| 6466 |
+
{
|
| 6467 |
+
"epoch": 9.0234,
|
| 6468 |
+
"grad_norm": 0.06555522978305817,
|
| 6469 |
+
"learning_rate": 1.544e-05,
|
| 6470 |
+
"loss": 0.01482708305120468,
|
| 6471 |
+
"step": 9230
|
| 6472 |
+
},
|
| 6473 |
+
{
|
| 6474 |
+
"epoch": 9.0244,
|
| 6475 |
+
"grad_norm": 0.07707587629556656,
|
| 6476 |
+
"learning_rate": 1.5240000000000001e-05,
|
| 6477 |
+
"loss": 0.014254559576511384,
|
| 6478 |
+
"step": 9240
|
| 6479 |
+
},
|
| 6480 |
+
{
|
| 6481 |
+
"epoch": 9.0254,
|
| 6482 |
+
"grad_norm": 0.07337791472673416,
|
| 6483 |
+
"learning_rate": 1.5040000000000002e-05,
|
| 6484 |
+
"loss": 0.015043064951896667,
|
| 6485 |
+
"step": 9250
|
| 6486 |
+
},
|
| 6487 |
+
{
|
| 6488 |
+
"epoch": 9.0264,
|
| 6489 |
+
"grad_norm": 0.08570864051580429,
|
| 6490 |
+
"learning_rate": 1.4840000000000002e-05,
|
| 6491 |
+
"loss": 0.01574891060590744,
|
| 6492 |
+
"step": 9260
|
| 6493 |
+
},
|
| 6494 |
+
{
|
| 6495 |
+
"epoch": 9.0274,
|
| 6496 |
+
"grad_norm": 0.07305701076984406,
|
| 6497 |
+
"learning_rate": 1.464e-05,
|
| 6498 |
+
"loss": 0.015572662651538848,
|
| 6499 |
+
"step": 9270
|
| 6500 |
+
},
|
| 6501 |
+
{
|
| 6502 |
+
"epoch": 9.0284,
|
| 6503 |
+
"grad_norm": 0.059258975088596344,
|
| 6504 |
+
"learning_rate": 1.444e-05,
|
| 6505 |
+
"loss": 0.01588566303253174,
|
| 6506 |
+
"step": 9280
|
| 6507 |
+
},
|
| 6508 |
+
{
|
| 6509 |
+
"epoch": 9.0294,
|
| 6510 |
+
"grad_norm": 0.08041700720787048,
|
| 6511 |
+
"learning_rate": 1.4240000000000001e-05,
|
| 6512 |
+
"loss": 0.016104544699192046,
|
| 6513 |
+
"step": 9290
|
| 6514 |
+
},
|
| 6515 |
+
{
|
| 6516 |
+
"epoch": 9.0304,
|
| 6517 |
+
"grad_norm": 0.12365186959505081,
|
| 6518 |
+
"learning_rate": 1.4040000000000001e-05,
|
| 6519 |
+
"loss": 0.01534939706325531,
|
| 6520 |
+
"step": 9300
|
| 6521 |
+
},
|
| 6522 |
+
{
|
| 6523 |
+
"epoch": 10.0002,
|
| 6524 |
+
"grad_norm": 0.057674337178468704,
|
| 6525 |
+
"learning_rate": 1.384e-05,
|
| 6526 |
+
"loss": 0.015914039313793184,
|
| 6527 |
+
"step": 9310
|
| 6528 |
+
},
|
| 6529 |
+
{
|
| 6530 |
+
"epoch": 10.0012,
|
| 6531 |
+
"grad_norm": 0.06685669720172882,
|
| 6532 |
+
"learning_rate": 1.364e-05,
|
| 6533 |
+
"loss": 0.014044062793254852,
|
| 6534 |
+
"step": 9320
|
| 6535 |
+
},
|
| 6536 |
+
{
|
| 6537 |
+
"epoch": 10.0022,
|
| 6538 |
+
"grad_norm": 0.07209975272417068,
|
| 6539 |
+
"learning_rate": 1.344e-05,
|
| 6540 |
+
"loss": 0.014324517548084259,
|
| 6541 |
+
"step": 9330
|
| 6542 |
+
},
|
| 6543 |
+
{
|
| 6544 |
+
"epoch": 10.0032,
|
| 6545 |
+
"grad_norm": 0.07383687049150467,
|
| 6546 |
+
"learning_rate": 1.324e-05,
|
| 6547 |
+
"loss": 0.014187808334827422,
|
| 6548 |
+
"step": 9340
|
| 6549 |
+
},
|
| 6550 |
+
{
|
| 6551 |
+
"epoch": 10.0042,
|
| 6552 |
+
"grad_norm": 0.05301659554243088,
|
| 6553 |
+
"learning_rate": 1.3039999999999999e-05,
|
| 6554 |
+
"loss": 0.014343148469924927,
|
| 6555 |
+
"step": 9350
|
| 6556 |
+
},
|
| 6557 |
+
{
|
| 6558 |
+
"epoch": 10.0052,
|
| 6559 |
+
"grad_norm": 0.07555723190307617,
|
| 6560 |
+
"learning_rate": 1.2839999999999999e-05,
|
| 6561 |
+
"loss": 0.014555636048316955,
|
| 6562 |
+
"step": 9360
|
| 6563 |
+
},
|
| 6564 |
+
{
|
| 6565 |
+
"epoch": 10.0062,
|
| 6566 |
+
"grad_norm": 0.07009563595056534,
|
| 6567 |
+
"learning_rate": 1.2640000000000003e-05,
|
| 6568 |
+
"loss": 0.015680891275405884,
|
| 6569 |
+
"step": 9370
|
| 6570 |
+
},
|
| 6571 |
+
{
|
| 6572 |
+
"epoch": 10.0072,
|
| 6573 |
+
"grad_norm": 0.07948929071426392,
|
| 6574 |
+
"learning_rate": 1.244e-05,
|
| 6575 |
+
"loss": 0.015406323969364167,
|
| 6576 |
+
"step": 9380
|
| 6577 |
+
},
|
| 6578 |
+
{
|
| 6579 |
+
"epoch": 10.0082,
|
| 6580 |
+
"grad_norm": 0.07286491245031357,
|
| 6581 |
+
"learning_rate": 1.224e-05,
|
| 6582 |
+
"loss": 0.014841750264167786,
|
| 6583 |
+
"step": 9390
|
| 6584 |
+
},
|
| 6585 |
+
{
|
| 6586 |
+
"epoch": 10.0092,
|
| 6587 |
+
"grad_norm": 0.0699690729379654,
|
| 6588 |
+
"learning_rate": 1.204e-05,
|
| 6589 |
+
"loss": 0.01526234596967697,
|
| 6590 |
+
"step": 9400
|
| 6591 |
+
},
|
| 6592 |
+
{
|
| 6593 |
+
"epoch": 10.0102,
|
| 6594 |
+
"grad_norm": 0.06607243418693542,
|
| 6595 |
+
"learning_rate": 1.1840000000000002e-05,
|
| 6596 |
+
"loss": 0.014856207370758056,
|
| 6597 |
+
"step": 9410
|
| 6598 |
+
},
|
| 6599 |
+
{
|
| 6600 |
+
"epoch": 10.0112,
|
| 6601 |
+
"grad_norm": 0.06737522780895233,
|
| 6602 |
+
"learning_rate": 1.164e-05,
|
| 6603 |
+
"loss": 0.014999723434448243,
|
| 6604 |
+
"step": 9420
|
| 6605 |
+
},
|
| 6606 |
+
{
|
| 6607 |
+
"epoch": 10.0122,
|
| 6608 |
+
"grad_norm": 0.06653918325901031,
|
| 6609 |
+
"learning_rate": 1.144e-05,
|
| 6610 |
+
"loss": 0.015131491422653198,
|
| 6611 |
+
"step": 9430
|
| 6612 |
+
},
|
| 6613 |
+
{
|
| 6614 |
+
"epoch": 10.0132,
|
| 6615 |
+
"grad_norm": 0.06990286707878113,
|
| 6616 |
+
"learning_rate": 1.124e-05,
|
| 6617 |
+
"loss": 0.014309829473495484,
|
| 6618 |
+
"step": 9440
|
| 6619 |
+
},
|
| 6620 |
+
{
|
| 6621 |
+
"epoch": 10.0142,
|
| 6622 |
+
"grad_norm": 0.07211795449256897,
|
| 6623 |
+
"learning_rate": 1.1040000000000001e-05,
|
| 6624 |
+
"loss": 0.01395113468170166,
|
| 6625 |
+
"step": 9450
|
| 6626 |
+
},
|
| 6627 |
+
{
|
| 6628 |
+
"epoch": 10.0152,
|
| 6629 |
+
"grad_norm": 0.09780146181583405,
|
| 6630 |
+
"learning_rate": 1.084e-05,
|
| 6631 |
+
"loss": 0.016415250301361085,
|
| 6632 |
+
"step": 9460
|
| 6633 |
+
},
|
| 6634 |
+
{
|
| 6635 |
+
"epoch": 10.0162,
|
| 6636 |
+
"grad_norm": 0.05811549723148346,
|
| 6637 |
+
"learning_rate": 1.064e-05,
|
| 6638 |
+
"loss": 0.01397673338651657,
|
| 6639 |
+
"step": 9470
|
| 6640 |
+
},
|
| 6641 |
+
{
|
| 6642 |
+
"epoch": 10.0172,
|
| 6643 |
+
"grad_norm": 0.06327290832996368,
|
| 6644 |
+
"learning_rate": 1.0440000000000002e-05,
|
| 6645 |
+
"loss": 0.014413160085678101,
|
| 6646 |
+
"step": 9480
|
| 6647 |
+
},
|
| 6648 |
+
{
|
| 6649 |
+
"epoch": 10.0182,
|
| 6650 |
+
"grad_norm": 0.05637902393937111,
|
| 6651 |
+
"learning_rate": 1.024e-05,
|
| 6652 |
+
"loss": 0.014348730444908142,
|
| 6653 |
+
"step": 9490
|
| 6654 |
+
},
|
| 6655 |
+
{
|
| 6656 |
+
"epoch": 10.0192,
|
| 6657 |
+
"grad_norm": 0.06641823798418045,
|
| 6658 |
+
"learning_rate": 1.004e-05,
|
| 6659 |
+
"loss": 0.014750830829143524,
|
| 6660 |
+
"step": 9500
|
| 6661 |
}
|
| 6662 |
],
|
| 6663 |
"logging_steps": 10,
|
|
|
|
| 6677 |
"attributes": {}
|
| 6678 |
}
|
| 6679 |
},
|
| 6680 |
+
"total_flos": 8.041649731122708e+17,
|
| 6681 |
"train_batch_size": 1,
|
| 6682 |
"trial_name": null,
|
| 6683 |
"trial_params": null
|