stefania-radu
commited on
Commit
•
1625a53
1
Parent(s):
63bd7a2
Training in progress, step 60000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893440890
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a05b029ed1927bee45376b9ec825ac1e6ad7ff6cc8cad870573ced24bc0e8a7a
|
3 |
size 893440890
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c27e63159040ffd991f11430bcaa8ba43680821f717186a7bc3c221a468601c
|
3 |
size 454197066
|
last-checkpoint/rng_state.pth
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 sha256:76f1055b9fbc745e8095815e2f9b0f2460e6416163d65d839c2d6bec7dc4f817
|
3 |
+
size 14308
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c55f5050853d52e8377712864d5685c98b2bc91dad2debd9776569f4616235b0
|
3 |
size 1064
|
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,
|
@@ -376,11 +376,85 @@
|
|
376 |
"eval_samples_per_second": 101.039,
|
377 |
"eval_steps_per_second": 12.63,
|
378 |
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
379 |
}
|
380 |
],
|
381 |
"max_steps": 1000000,
|
382 |
"num_train_epochs": 9223372036854775807,
|
383 |
-
"total_flos":
|
384 |
"trial_name": null,
|
385 |
"trial_params": null
|
386 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06,
|
5 |
+
"global_step": 60000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
376 |
"eval_samples_per_second": 101.039,
|
377 |
"eval_steps_per_second": 12.63,
|
378 |
"step": 50000
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.05,
|
382 |
+
"learning_rate": 1.874997607785047e-05,
|
383 |
+
"loss": 0.497,
|
384 |
+
"step": 51000
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.05,
|
388 |
+
"learning_rate": 1.874990431166348e-05,
|
389 |
+
"loss": 0.498,
|
390 |
+
"step": 52000
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.05,
|
394 |
+
"learning_rate": 1.8749784702223863e-05,
|
395 |
+
"loss": 0.4921,
|
396 |
+
"step": 53000
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.05,
|
400 |
+
"learning_rate": 1.8749617250839647e-05,
|
401 |
+
"loss": 0.4876,
|
402 |
+
"step": 54000
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.06,
|
406 |
+
"learning_rate": 1.8749401959342052e-05,
|
407 |
+
"loss": 0.483,
|
408 |
+
"step": 55000
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.06,
|
412 |
+
"eval_runtime": 3145.913,
|
413 |
+
"eval_samples_per_second": 107.966,
|
414 |
+
"eval_steps_per_second": 13.496,
|
415 |
+
"step": 55000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.06,
|
419 |
+
"learning_rate": 1.874913883008547e-05,
|
420 |
+
"loss": 0.4809,
|
421 |
+
"step": 56000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.06,
|
425 |
+
"learning_rate": 1.8748827865947437e-05,
|
426 |
+
"loss": 0.4788,
|
427 |
+
"step": 57000
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.06,
|
431 |
+
"learning_rate": 1.8748469070328614e-05,
|
432 |
+
"loss": 0.4767,
|
433 |
+
"step": 58000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.06,
|
437 |
+
"learning_rate": 1.8748062447152732e-05,
|
438 |
+
"loss": 0.475,
|
439 |
+
"step": 59000
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.06,
|
443 |
+
"learning_rate": 1.874760800086655e-05,
|
444 |
+
"loss": 0.4696,
|
445 |
+
"step": 60000
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.06,
|
449 |
+
"eval_runtime": 3128.1932,
|
450 |
+
"eval_samples_per_second": 108.578,
|
451 |
+
"eval_steps_per_second": 13.572,
|
452 |
+
"step": 60000
|
453 |
}
|
454 |
],
|
455 |
"max_steps": 1000000,
|
456 |
"num_train_epochs": 9223372036854775807,
|
457 |
+
"total_flos": 5.3127661039386624e+20,
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|
460 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c27e63159040ffd991f11430bcaa8ba43680821f717186a7bc3c221a468601c
|
3 |
size 454197066
|