Training in progress, step 9000
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 +24 -5
- 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 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:429fd37cdb396d76c57490657bd8ebadf55f4ea6cb6e66b3574a96f35d3649bf
|
3 |
size 484083951
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f857f98fe64b6086e69043a218b1c2433c141aa779b501ca1842e2748bf32a59
|
3 |
size 242031355
|
last-checkpoint/rng_state.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 sha256:881b7625f2648bf0c780e5216ec619f8c3a5f4e4005d05775e3089ef7547f63e
|
3 |
size 14503
|
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:ef9c2bb71c7baedce7e58469f18790c85f10ed792300427c1f310e11d5f9a911
|
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:bb148db24882eab85c67615568d79a6803fcc4a42336148abf06e0fbcbc9cd81
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -329,11 +329,30 @@
|
|
329 |
"eval_samples_per_second": 54.965,
|
330 |
"eval_steps_per_second": 1.731,
|
331 |
"step": 8500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
332 |
}
|
333 |
],
|
334 |
"max_steps": 62500,
|
335 |
"num_train_epochs": 20,
|
336 |
-
"total_flos": 3.
|
337 |
"trial_name": null,
|
338 |
"trial_params": null
|
339 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7340560555458069,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-9000",
|
4 |
+
"epoch": 2.88,
|
5 |
+
"global_step": 9000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
329 |
"eval_samples_per_second": 54.965,
|
330 |
"eval_steps_per_second": 1.731,
|
331 |
"step": 8500
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.88,
|
335 |
+
"learning_rate": 0.00045055157894736844,
|
336 |
+
"loss": 0.6224,
|
337 |
+
"step": 9000
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 2.88,
|
341 |
+
"eval_bleu": 0.06439506753752011,
|
342 |
+
"eval_exact_match": 0.102,
|
343 |
+
"eval_loss": 0.7340560555458069,
|
344 |
+
"eval_rouge1": 0.5052438839482049,
|
345 |
+
"eval_rouge2": 0.34484226789208994,
|
346 |
+
"eval_rougeL": 0.4921510782769857,
|
347 |
+
"eval_runtime": 37.3894,
|
348 |
+
"eval_samples_per_second": 53.491,
|
349 |
+
"eval_steps_per_second": 1.685,
|
350 |
+
"step": 9000
|
351 |
}
|
352 |
],
|
353 |
"max_steps": 62500,
|
354 |
"num_train_epochs": 20,
|
355 |
+
"total_flos": 3.765923690840064e+16,
|
356 |
"trial_name": null,
|
357 |
"trial_params": null
|
358 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f857f98fe64b6086e69043a218b1c2433c141aa779b501ca1842e2748bf32a59
|
3 |
size 242031355
|