Training in progress, step 60000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -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 893438545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a827260146648964e1c0473647fdd276801d3a7209c7df3eb87d73e4518f74c
|
3 |
size 893438545
|
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 sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
|
3 |
size 449471589
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad14af5dd7abce3c61cc5e578461c309f69e60de21b0c054a8f3f4c7bba9e4e6
|
3 |
+
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8388ca66f8f9c6c8c8157a81f6bde550f1b25a31aa2aa22e4704b5ef4e971ee
|
3 |
size 14503
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:782279cba623055efc3193875769c57ec4b067421ccba6e615fbf1b5214e724b
|
3 |
+
size 14439
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:749c503bc6cade081df3a923d8ae2be2ccf707f9f3b893640379c785aa6facd4
|
3 |
size 14503
|
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 sha256:90ff94ce099b109f6c343c1450c170171a247badda4343ab1850180869cf03e2
|
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,
|
@@ -376,11 +376,85 @@
|
|
376 |
"eval_samples_per_second": 963.96,
|
377 |
"eval_steps_per_second": 15.423,
|
378 |
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
379 |
}
|
380 |
],
|
381 |
"max_steps": 1000000,
|
382 |
"num_train_epochs": 16,
|
383 |
-
"total_flos":
|
384 |
"trial_name": null,
|
385 |
"trial_params": null
|
386 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9162123780292272,
|
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": 963.96,
|
377 |
"eval_steps_per_second": 15.423,
|
378 |
"step": 50000
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.78,
|
382 |
+
"learning_rate": 0.0001499996172456075,
|
383 |
+
"loss": 0.4824,
|
384 |
+
"step": 51000
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.79,
|
388 |
+
"learning_rate": 0.00014999846898661572,
|
389 |
+
"loss": 0.4778,
|
390 |
+
"step": 52000
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.81,
|
394 |
+
"learning_rate": 0.00014999655523558183,
|
395 |
+
"loss": 0.474,
|
396 |
+
"step": 53000
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.82,
|
400 |
+
"learning_rate": 0.00014999387601343436,
|
401 |
+
"loss": 0.4694,
|
402 |
+
"step": 54000
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.84,
|
406 |
+
"learning_rate": 0.00014999043134947282,
|
407 |
+
"loss": 0.4651,
|
408 |
+
"step": 55000
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.84,
|
412 |
+
"eval_runtime": 1.0465,
|
413 |
+
"eval_samples_per_second": 955.566,
|
414 |
+
"eval_steps_per_second": 15.289,
|
415 |
+
"step": 55000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.86,
|
419 |
+
"learning_rate": 0.00014998622128136748,
|
420 |
+
"loss": 0.4608,
|
421 |
+
"step": 56000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.87,
|
425 |
+
"learning_rate": 0.000149981245855159,
|
426 |
+
"loss": 0.4566,
|
427 |
+
"step": 57000
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.89,
|
431 |
+
"learning_rate": 0.00014997550512525784,
|
432 |
+
"loss": 0.4523,
|
433 |
+
"step": 58000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.9,
|
437 |
+
"learning_rate": 0.0001499689991544437,
|
438 |
+
"loss": 0.4483,
|
439 |
+
"step": 59000
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.92,
|
443 |
+
"learning_rate": 0.00014996172801386482,
|
444 |
+
"loss": 0.4447,
|
445 |
+
"step": 60000
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.92,
|
449 |
+
"eval_runtime": 1.2288,
|
450 |
+
"eval_samples_per_second": 813.826,
|
451 |
+
"eval_steps_per_second": 13.021,
|
452 |
+
"step": 60000
|
453 |
}
|
454 |
],
|
455 |
"max_steps": 1000000,
|
456 |
"num_train_epochs": 16,
|
457 |
+
"total_flos": 4.2060156618208287e+21,
|
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 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
|
3 |
size 449471589
|