Training in progress, step 1800000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +383 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 893439185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84eeca699785d889add4fce9e83fcf219cc03b8c3e8612092092ba4f022e339b
|
| 3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a47c42cd40edaf177247b0f81cc113941e45da543bcd8075122f86f8a439a53
|
| 3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c22e615daa20a7523bf096df9dcc68366ed60a8151bafc863df6c6b53275a84a
|
| 3 |
size 21643
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c4c724e259a52a66e7ae3019ca30f1baaafdcfcaf6dbe949cbda0206af52d55
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a24dd415d95b2d83e758fabab0d2c6d80262a248eda13bb423bd8c9ef9f0d1d
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -13306,11 +13306,391 @@
|
|
| 13306 |
"eval_samples_per_second": 80.645,
|
| 13307 |
"eval_steps_per_second": 0.63,
|
| 13308 |
"step": 1750000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13309 |
}
|
| 13310 |
],
|
| 13311 |
"max_steps": 2000000,
|
| 13312 |
"num_train_epochs": 9223372036854775807,
|
| 13313 |
-
"total_flos": 1.
|
| 13314 |
"trial_name": null,
|
| 13315 |
"trial_params": null
|
| 13316 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.15,
|
| 5 |
+
"global_step": 1800000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 13306 |
"eval_samples_per_second": 80.645,
|
| 13307 |
"eval_steps_per_second": 0.63,
|
| 13308 |
"step": 1750000
|
| 13309 |
+
},
|
| 13310 |
+
{
|
| 13311 |
+
"epoch": 0.13,
|
| 13312 |
+
"learning_rate": 1.6540859441048118e-05,
|
| 13313 |
+
"loss": 0.4394,
|
| 13314 |
+
"step": 1751000
|
| 13315 |
+
},
|
| 13316 |
+
{
|
| 13317 |
+
"epoch": 0.13,
|
| 13318 |
+
"learning_rate": 1.6489389468730806e-05,
|
| 13319 |
+
"loss": 0.439,
|
| 13320 |
+
"step": 1752000
|
| 13321 |
+
},
|
| 13322 |
+
{
|
| 13323 |
+
"epoch": 0.13,
|
| 13324 |
+
"learning_rate": 1.6438215320582125e-05,
|
| 13325 |
+
"loss": 0.4382,
|
| 13326 |
+
"step": 1753000
|
| 13327 |
+
},
|
| 13328 |
+
{
|
| 13329 |
+
"epoch": 0.13,
|
| 13330 |
+
"learning_rate": 1.638713204573334e-05,
|
| 13331 |
+
"loss": 0.4381,
|
| 13332 |
+
"step": 1754000
|
| 13333 |
+
},
|
| 13334 |
+
{
|
| 13335 |
+
"epoch": 0.13,
|
| 13336 |
+
"learning_rate": 1.6336293339368757e-05,
|
| 13337 |
+
"loss": 0.4392,
|
| 13338 |
+
"step": 1755000
|
| 13339 |
+
},
|
| 13340 |
+
{
|
| 13341 |
+
"epoch": 0.13,
|
| 13342 |
+
"eval_loss": 0.420003205537796,
|
| 13343 |
+
"eval_runtime": 78.6855,
|
| 13344 |
+
"eval_samples_per_second": 81.336,
|
| 13345 |
+
"eval_steps_per_second": 0.635,
|
| 13346 |
+
"step": 1755000
|
| 13347 |
+
},
|
| 13348 |
+
{
|
| 13349 |
+
"epoch": 0.13,
|
| 13350 |
+
"learning_rate": 1.628559757718579e-05,
|
| 13351 |
+
"loss": 0.439,
|
| 13352 |
+
"step": 1756000
|
| 13353 |
+
},
|
| 13354 |
+
{
|
| 13355 |
+
"epoch": 0.13,
|
| 13356 |
+
"learning_rate": 1.6235095900122255e-05,
|
| 13357 |
+
"loss": 0.4383,
|
| 13358 |
+
"step": 1757000
|
| 13359 |
+
},
|
| 13360 |
+
{
|
| 13361 |
+
"epoch": 0.13,
|
| 13362 |
+
"learning_rate": 1.61848386723797e-05,
|
| 13363 |
+
"loss": 0.4386,
|
| 13364 |
+
"step": 1758000
|
| 13365 |
+
},
|
| 13366 |
+
{
|
| 13367 |
+
"epoch": 0.13,
|
| 13368 |
+
"learning_rate": 1.6134725432005385e-05,
|
| 13369 |
+
"loss": 0.4395,
|
| 13370 |
+
"step": 1759000
|
| 13371 |
+
},
|
| 13372 |
+
{
|
| 13373 |
+
"epoch": 0.13,
|
| 13374 |
+
"learning_rate": 1.6084856557803128e-05,
|
| 13375 |
+
"loss": 0.438,
|
| 13376 |
+
"step": 1760000
|
| 13377 |
+
},
|
| 13378 |
+
{
|
| 13379 |
+
"epoch": 0.13,
|
| 13380 |
+
"eval_loss": 0.4174318015575409,
|
| 13381 |
+
"eval_runtime": 76.8661,
|
| 13382 |
+
"eval_samples_per_second": 83.262,
|
| 13383 |
+
"eval_steps_per_second": 0.65,
|
| 13384 |
+
"step": 1760000
|
| 13385 |
+
},
|
| 13386 |
+
{
|
| 13387 |
+
"epoch": 0.13,
|
| 13388 |
+
"learning_rate": 1.6035132364121584e-05,
|
| 13389 |
+
"loss": 0.4388,
|
| 13390 |
+
"step": 1761000
|
| 13391 |
+
},
|
| 13392 |
+
{
|
| 13393 |
+
"epoch": 0.13,
|
| 13394 |
+
"learning_rate": 1.5985603018519935e-05,
|
| 13395 |
+
"loss": 0.4378,
|
| 13396 |
+
"step": 1762000
|
| 13397 |
+
},
|
| 13398 |
+
{
|
| 13399 |
+
"epoch": 0.13,
|
| 13400 |
+
"learning_rate": 1.5936317908767756e-05,
|
| 13401 |
+
"loss": 0.4368,
|
| 13402 |
+
"step": 1763000
|
| 13403 |
+
},
|
| 13404 |
+
{
|
| 13405 |
+
"epoch": 0.13,
|
| 13406 |
+
"learning_rate": 1.5887178516132736e-05,
|
| 13407 |
+
"loss": 0.4412,
|
| 13408 |
+
"step": 1764000
|
| 13409 |
+
},
|
| 13410 |
+
{
|
| 13411 |
+
"epoch": 0.13,
|
| 13412 |
+
"learning_rate": 1.5838283268763148e-05,
|
| 13413 |
+
"loss": 0.4383,
|
| 13414 |
+
"step": 1765000
|
| 13415 |
+
},
|
| 13416 |
+
{
|
| 13417 |
+
"epoch": 0.13,
|
| 13418 |
+
"eval_loss": 0.41864004731178284,
|
| 13419 |
+
"eval_runtime": 86.8232,
|
| 13420 |
+
"eval_samples_per_second": 73.713,
|
| 13421 |
+
"eval_steps_per_second": 0.576,
|
| 13422 |
+
"step": 1765000
|
| 13423 |
+
},
|
| 13424 |
+
{
|
| 13425 |
+
"epoch": 0.13,
|
| 13426 |
+
"learning_rate": 1.5789583078410045e-05,
|
| 13427 |
+
"loss": 0.4389,
|
| 13428 |
+
"step": 1766000
|
| 13429 |
+
},
|
| 13430 |
+
{
|
| 13431 |
+
"epoch": 0.13,
|
| 13432 |
+
"learning_rate": 1.574102963743466e-05,
|
| 13433 |
+
"loss": 0.439,
|
| 13434 |
+
"step": 1767000
|
| 13435 |
+
},
|
| 13436 |
+
{
|
| 13437 |
+
"epoch": 0.13,
|
| 13438 |
+
"learning_rate": 1.5692671940427092e-05,
|
| 13439 |
+
"loss": 0.4385,
|
| 13440 |
+
"step": 1768000
|
| 13441 |
+
},
|
| 13442 |
+
{
|
| 13443 |
+
"epoch": 0.13,
|
| 13444 |
+
"learning_rate": 1.5644510134693248e-05,
|
| 13445 |
+
"loss": 0.4384,
|
| 13446 |
+
"step": 1769000
|
| 13447 |
+
},
|
| 13448 |
+
{
|
| 13449 |
+
"epoch": 0.14,
|
| 13450 |
+
"learning_rate": 1.559654436694238e-05,
|
| 13451 |
+
"loss": 0.4392,
|
| 13452 |
+
"step": 1770000
|
| 13453 |
+
},
|
| 13454 |
+
{
|
| 13455 |
+
"epoch": 0.14,
|
| 13456 |
+
"eval_loss": 0.4172964096069336,
|
| 13457 |
+
"eval_runtime": 79.9939,
|
| 13458 |
+
"eval_samples_per_second": 80.006,
|
| 13459 |
+
"eval_steps_per_second": 0.625,
|
| 13460 |
+
"step": 1770000
|
| 13461 |
+
},
|
| 13462 |
+
{
|
| 13463 |
+
"epoch": 0.14,
|
| 13464 |
+
"learning_rate": 1.5548822454827717e-05,
|
| 13465 |
+
"loss": 0.4393,
|
| 13466 |
+
"step": 1771000
|
| 13467 |
+
},
|
| 13468 |
+
{
|
| 13469 |
+
"epoch": 0.14,
|
| 13470 |
+
"learning_rate": 1.5501249004379188e-05,
|
| 13471 |
+
"loss": 0.4392,
|
| 13472 |
+
"step": 1772000
|
| 13473 |
+
},
|
| 13474 |
+
{
|
| 13475 |
+
"epoch": 0.14,
|
| 13476 |
+
"learning_rate": 1.54539193071009e-05,
|
| 13477 |
+
"loss": 0.4386,
|
| 13478 |
+
"step": 1773000
|
| 13479 |
+
},
|
| 13480 |
+
{
|
| 13481 |
+
"epoch": 0.14,
|
| 13482 |
+
"learning_rate": 1.5406738753042658e-05,
|
| 13483 |
+
"loss": 0.4393,
|
| 13484 |
+
"step": 1774000
|
| 13485 |
+
},
|
| 13486 |
+
{
|
| 13487 |
+
"epoch": 0.14,
|
| 13488 |
+
"learning_rate": 1.5359754961260252e-05,
|
| 13489 |
+
"loss": 0.4387,
|
| 13490 |
+
"step": 1775000
|
| 13491 |
+
},
|
| 13492 |
+
{
|
| 13493 |
+
"epoch": 0.14,
|
| 13494 |
+
"eval_loss": 0.4169865548610687,
|
| 13495 |
+
"eval_runtime": 77.7982,
|
| 13496 |
+
"eval_samples_per_second": 82.264,
|
| 13497 |
+
"eval_steps_per_second": 0.643,
|
| 13498 |
+
"step": 1775000
|
| 13499 |
+
},
|
| 13500 |
+
{
|
| 13501 |
+
"epoch": 0.14,
|
| 13502 |
+
"learning_rate": 1.5312968074874446e-05,
|
| 13503 |
+
"loss": 0.4381,
|
| 13504 |
+
"step": 1776000
|
| 13505 |
+
},
|
| 13506 |
+
{
|
| 13507 |
+
"epoch": 0.14,
|
| 13508 |
+
"learning_rate": 1.5266424727771944e-05,
|
| 13509 |
+
"loss": 0.4396,
|
| 13510 |
+
"step": 1777000
|
| 13511 |
+
},
|
| 13512 |
+
{
|
| 13513 |
+
"epoch": 0.14,
|
| 13514 |
+
"learning_rate": 1.522003188188146e-05,
|
| 13515 |
+
"loss": 0.4395,
|
| 13516 |
+
"step": 1778000
|
| 13517 |
+
},
|
| 13518 |
+
{
|
| 13519 |
+
"epoch": 0.14,
|
| 13520 |
+
"learning_rate": 1.517383636700831e-05,
|
| 13521 |
+
"loss": 0.4382,
|
| 13522 |
+
"step": 1779000
|
| 13523 |
+
},
|
| 13524 |
+
{
|
| 13525 |
+
"epoch": 0.14,
|
| 13526 |
+
"learning_rate": 1.5127838323872036e-05,
|
| 13527 |
+
"loss": 0.4364,
|
| 13528 |
+
"step": 1780000
|
| 13529 |
+
},
|
| 13530 |
+
{
|
| 13531 |
+
"epoch": 0.14,
|
| 13532 |
+
"eval_loss": 0.41849958896636963,
|
| 13533 |
+
"eval_runtime": 76.5418,
|
| 13534 |
+
"eval_samples_per_second": 83.614,
|
| 13535 |
+
"eval_steps_per_second": 0.653,
|
| 13536 |
+
"step": 1780000
|
| 13537 |
+
},
|
| 13538 |
+
{
|
| 13539 |
+
"epoch": 0.14,
|
| 13540 |
+
"learning_rate": 1.5082037892590664e-05,
|
| 13541 |
+
"loss": 0.439,
|
| 13542 |
+
"step": 1781000
|
| 13543 |
+
},
|
| 13544 |
+
{
|
| 13545 |
+
"epoch": 0.14,
|
| 13546 |
+
"learning_rate": 1.5036480716537045e-05,
|
| 13547 |
+
"loss": 0.4393,
|
| 13548 |
+
"step": 1782000
|
| 13549 |
+
},
|
| 13550 |
+
{
|
| 13551 |
+
"epoch": 0.14,
|
| 13552 |
+
"learning_rate": 1.4991121035047137e-05,
|
| 13553 |
+
"loss": 0.4383,
|
| 13554 |
+
"step": 1783000
|
| 13555 |
+
},
|
| 13556 |
+
{
|
| 13557 |
+
"epoch": 0.14,
|
| 13558 |
+
"learning_rate": 1.4945913877821996e-05,
|
| 13559 |
+
"loss": 0.4383,
|
| 13560 |
+
"step": 1784000
|
| 13561 |
+
},
|
| 13562 |
+
{
|
| 13563 |
+
"epoch": 0.14,
|
| 13564 |
+
"learning_rate": 1.4900904886625165e-05,
|
| 13565 |
+
"loss": 0.4377,
|
| 13566 |
+
"step": 1785000
|
| 13567 |
+
},
|
| 13568 |
+
{
|
| 13569 |
+
"epoch": 0.14,
|
| 13570 |
+
"eval_loss": 0.4204372465610504,
|
| 13571 |
+
"eval_runtime": 76.9476,
|
| 13572 |
+
"eval_samples_per_second": 83.173,
|
| 13573 |
+
"eval_steps_per_second": 0.65,
|
| 13574 |
+
"step": 1785000
|
| 13575 |
+
},
|
| 13576 |
+
{
|
| 13577 |
+
"epoch": 0.14,
|
| 13578 |
+
"learning_rate": 1.4856138910151988e-05,
|
| 13579 |
+
"loss": 0.4388,
|
| 13580 |
+
"step": 1786000
|
| 13581 |
+
},
|
| 13582 |
+
{
|
| 13583 |
+
"epoch": 0.14,
|
| 13584 |
+
"learning_rate": 1.4811526463215664e-05,
|
| 13585 |
+
"loss": 0.4371,
|
| 13586 |
+
"step": 1787000
|
| 13587 |
+
},
|
| 13588 |
+
{
|
| 13589 |
+
"epoch": 0.14,
|
| 13590 |
+
"learning_rate": 1.476715690631307e-05,
|
| 13591 |
+
"loss": 0.438,
|
| 13592 |
+
"step": 1788000
|
| 13593 |
+
},
|
| 13594 |
+
{
|
| 13595 |
+
"epoch": 0.14,
|
| 13596 |
+
"learning_rate": 1.4722941546682392e-05,
|
| 13597 |
+
"loss": 0.4381,
|
| 13598 |
+
"step": 1789000
|
| 13599 |
+
},
|
| 13600 |
+
{
|
| 13601 |
+
"epoch": 0.14,
|
| 13602 |
+
"learning_rate": 1.4678968949438921e-05,
|
| 13603 |
+
"loss": 0.4363,
|
| 13604 |
+
"step": 1790000
|
| 13605 |
+
},
|
| 13606 |
+
{
|
| 13607 |
+
"epoch": 0.14,
|
| 13608 |
+
"eval_loss": 0.4183988869190216,
|
| 13609 |
+
"eval_runtime": 76.9826,
|
| 13610 |
+
"eval_samples_per_second": 83.136,
|
| 13611 |
+
"eval_steps_per_second": 0.649,
|
| 13612 |
+
"step": 1790000
|
| 13613 |
+
},
|
| 13614 |
+
{
|
| 13615 |
+
"epoch": 0.15,
|
| 13616 |
+
"learning_rate": 1.4635151215325466e-05,
|
| 13617 |
+
"loss": 0.4366,
|
| 13618 |
+
"step": 1791000
|
| 13619 |
+
},
|
| 13620 |
+
{
|
| 13621 |
+
"epoch": 0.15,
|
| 13622 |
+
"learning_rate": 1.4591576112997706e-05,
|
| 13623 |
+
"loss": 0.4391,
|
| 13624 |
+
"step": 1792000
|
| 13625 |
+
},
|
| 13626 |
+
{
|
| 13627 |
+
"epoch": 0.15,
|
| 13628 |
+
"learning_rate": 1.4548156537772989e-05,
|
| 13629 |
+
"loss": 0.4391,
|
| 13630 |
+
"step": 1793000
|
| 13631 |
+
},
|
| 13632 |
+
{
|
| 13633 |
+
"epoch": 0.15,
|
| 13634 |
+
"learning_rate": 1.4504936340214418e-05,
|
| 13635 |
+
"loss": 0.4385,
|
| 13636 |
+
"step": 1794000
|
| 13637 |
+
},
|
| 13638 |
+
{
|
| 13639 |
+
"epoch": 0.15,
|
| 13640 |
+
"learning_rate": 1.4461958572967858e-05,
|
| 13641 |
+
"loss": 0.4378,
|
| 13642 |
+
"step": 1795000
|
| 13643 |
+
},
|
| 13644 |
+
{
|
| 13645 |
+
"epoch": 0.15,
|
| 13646 |
+
"eval_loss": 0.4223540425300598,
|
| 13647 |
+
"eval_runtime": 77.2417,
|
| 13648 |
+
"eval_samples_per_second": 82.857,
|
| 13649 |
+
"eval_steps_per_second": 0.647,
|
| 13650 |
+
"step": 1795000
|
| 13651 |
+
},
|
| 13652 |
+
{
|
| 13653 |
+
"epoch": 0.15,
|
| 13654 |
+
"learning_rate": 1.4419137325396865e-05,
|
| 13655 |
+
"loss": 0.4389,
|
| 13656 |
+
"step": 1796000
|
| 13657 |
+
},
|
| 13658 |
+
{
|
| 13659 |
+
"epoch": 0.15,
|
| 13660 |
+
"learning_rate": 1.437651584850691e-05,
|
| 13661 |
+
"loss": 0.4386,
|
| 13662 |
+
"step": 1797000
|
| 13663 |
+
},
|
| 13664 |
+
{
|
| 13665 |
+
"epoch": 0.15,
|
| 13666 |
+
"learning_rate": 1.4334094272130413e-05,
|
| 13667 |
+
"loss": 0.4367,
|
| 13668 |
+
"step": 1798000
|
| 13669 |
+
},
|
| 13670 |
+
{
|
| 13671 |
+
"epoch": 0.15,
|
| 13672 |
+
"learning_rate": 1.4291872725490842e-05,
|
| 13673 |
+
"loss": 0.4384,
|
| 13674 |
+
"step": 1799000
|
| 13675 |
+
},
|
| 13676 |
+
{
|
| 13677 |
+
"epoch": 0.15,
|
| 13678 |
+
"learning_rate": 1.4249893258568889e-05,
|
| 13679 |
+
"loss": 0.4384,
|
| 13680 |
+
"step": 1800000
|
| 13681 |
+
},
|
| 13682 |
+
{
|
| 13683 |
+
"epoch": 0.15,
|
| 13684 |
+
"eval_loss": 0.4171189069747925,
|
| 13685 |
+
"eval_runtime": 76.9772,
|
| 13686 |
+
"eval_samples_per_second": 83.142,
|
| 13687 |
+
"eval_steps_per_second": 0.65,
|
| 13688 |
+
"step": 1800000
|
| 13689 |
}
|
| 13690 |
],
|
| 13691 |
"max_steps": 2000000,
|
| 13692 |
"num_train_epochs": 9223372036854775807,
|
| 13693 |
+
"total_flos": 1.5772558930477056e+22,
|
| 13694 |
"trial_name": null,
|
| 13695 |
"trial_params": null
|
| 13696 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a47c42cd40edaf177247b0f81cc113941e45da543bcd8075122f86f8a439a53
|
| 3 |
size 449471589
|