Training in progress, step 6000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +74 -3
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- runs/May31_16-24-16_71176b7c2bb4/1685551038.3793378/events.out.tfevents.1685551038.71176b7c2bb4.5217.1 +3 -0
- runs/May31_16-24-16_71176b7c2bb4/events.out.tfevents.1685551038.71176b7c2bb4.5217.0 +3 -0
- training_args.bin +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2023671531
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4144fbcdc5d4f3fafbf6afc510ff856f789e4829a4858bcd16d4d390e9e5f2d
|
3 |
size 2023671531
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014236857
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e042bccb9e210670a39bb71562238d3440188919639fe843a2f55fef029e0ed
|
3 |
size 1014236857
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7436c395c71fe4a126e1e8460c76c5d99ba4173ae247ae8f8b8372d61aabdb5
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace18575c64fb9061a4bdb4187294f04e31e9a65a2e4da680ca78aeef9f963e2
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -328,11 +328,82 @@
|
|
328 |
"learning_rate": 3.603039785426911e-05,
|
329 |
"loss": 2.1803,
|
330 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
331 |
}
|
332 |
],
|
333 |
"max_steps": 11448,
|
334 |
"num_train_epochs": 8,
|
335 |
-
"total_flos":
|
336 |
"trial_name": null,
|
337 |
"trial_params": null
|
338 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.1928721174004195,
|
5 |
+
"global_step": 6000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
328 |
"learning_rate": 3.603039785426911e-05,
|
329 |
"loss": 2.1803,
|
330 |
"step": 5000
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 3.56,
|
334 |
+
"learning_rate": 3.5471613768439874e-05,
|
335 |
+
"loss": 2.1553,
|
336 |
+
"step": 5100
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 3.63,
|
340 |
+
"learning_rate": 3.491282968261064e-05,
|
341 |
+
"loss": 2.0567,
|
342 |
+
"step": 5200
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 3.7,
|
346 |
+
"learning_rate": 3.4354045596781406e-05,
|
347 |
+
"loss": 2.0147,
|
348 |
+
"step": 5300
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 3.77,
|
352 |
+
"learning_rate": 3.379526151095217e-05,
|
353 |
+
"loss": 1.9817,
|
354 |
+
"step": 5400
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 3.84,
|
358 |
+
"learning_rate": 3.323647742512294e-05,
|
359 |
+
"loss": 1.8843,
|
360 |
+
"step": 5500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 3.91,
|
364 |
+
"learning_rate": 3.26776933392937e-05,
|
365 |
+
"loss": 1.8849,
|
366 |
+
"step": 5600
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 3.98,
|
370 |
+
"learning_rate": 3.2118909253464465e-05,
|
371 |
+
"loss": 1.8232,
|
372 |
+
"step": 5700
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 4.05,
|
376 |
+
"learning_rate": 3.156012516763523e-05,
|
377 |
+
"loss": 1.6714,
|
378 |
+
"step": 5800
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 4.12,
|
382 |
+
"learning_rate": 3.100134108180599e-05,
|
383 |
+
"loss": 1.6047,
|
384 |
+
"step": 5900
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 4.19,
|
388 |
+
"learning_rate": 3.0442556995976757e-05,
|
389 |
+
"loss": 1.5893,
|
390 |
+
"step": 6000
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 4.19,
|
394 |
+
"eval_bleu": 57.7509,
|
395 |
+
"eval_em": 0.0033,
|
396 |
+
"eval_gen_len": 44.132,
|
397 |
+
"eval_loss": 1.7326730489730835,
|
398 |
+
"eval_runtime": 426.2734,
|
399 |
+
"eval_samples_per_second": 2.827,
|
400 |
+
"eval_steps_per_second": 0.354,
|
401 |
+
"step": 6000
|
402 |
}
|
403 |
],
|
404 |
"max_steps": 11448,
|
405 |
"num_train_epochs": 8,
|
406 |
+
"total_flos": 3958825611574680.0,
|
407 |
"trial_name": null,
|
408 |
"trial_params": null
|
409 |
}
|
last-checkpoint/training_args.bin
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 sha256:1e8aedd63b2a88667896dddc2d8d2d2c614cf71faf40847285ec9385424c5189
|
3 |
+
size 4219
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014236857
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e042bccb9e210670a39bb71562238d3440188919639fe843a2f55fef029e0ed
|
3 |
size 1014236857
|
runs/May31_16-24-16_71176b7c2bb4/1685551038.3793378/events.out.tfevents.1685551038.71176b7c2bb4.5217.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0556b0d2a94c5f20fa40561abf5d34a572ab34aabe4d40a5ad7e74ccc37c54f5
|
3 |
+
size 6342
|
runs/May31_16-24-16_71176b7c2bb4/events.out.tfevents.1685551038.71176b7c2bb4.5217.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfb70b57b2babcef0706723afa3bd21e04e88364a0d1cc6d98d2b82193854754
|
3 |
+
size 10573
|
training_args.bin
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 sha256:1e8aedd63b2a88667896dddc2d8d2d2c614cf71faf40847285ec9385424c5189
|
3 |
+
size 4219
|