Training in progress, step 10500
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 sha256:1a404583ef80bf3b8c4a510d27f887ac8e29f3411663bf49b4ab7232ce9a412a
|
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 sha256:8cf45d731900f7f9e07949ef1dfe708b522e158b7cfbb371287593175d5efcd1
|
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:a00f35a9c679472118eaa7dabfb186e79026b1432f53b64dfdf5c3e63bbd9480
|
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 sha256:1c3bf52f39b4d9c5882704c54922db0ba799f5f2afb01fd986c87b5fde9ed4b4
|
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:bfb31fa41ab4193878df5129dfbe7781af2d43ca089016d1833b7ff3a9dc1ee5
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -386,11 +386,30 @@
|
|
386 |
"eval_samples_per_second": 57.0,
|
387 |
"eval_steps_per_second": 1.795,
|
388 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
389 |
}
|
390 |
],
|
391 |
"max_steps": 62500,
|
392 |
"num_train_epochs": 20,
|
393 |
-
"total_flos": 4.
|
394 |
"trial_name": null,
|
395 |
"trial_params": null
|
396 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.715421736240387,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-10500",
|
4 |
+
"epoch": 3.36,
|
5 |
+
"global_step": 10500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
386 |
"eval_samples_per_second": 57.0,
|
387 |
"eval_steps_per_second": 1.795,
|
388 |
"step": 10000
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 3.36,
|
392 |
+
"learning_rate": 0.00043792,
|
393 |
+
"loss": 0.5708,
|
394 |
+
"step": 10500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 3.36,
|
398 |
+
"eval_bleu": 0.06631228557498069,
|
399 |
+
"eval_exact_match": 0.0995,
|
400 |
+
"eval_loss": 0.715421736240387,
|
401 |
+
"eval_rouge1": 0.5068028046779569,
|
402 |
+
"eval_rouge2": 0.34473925417295426,
|
403 |
+
"eval_rougeL": 0.49254925133943384,
|
404 |
+
"eval_runtime": 35.4516,
|
405 |
+
"eval_samples_per_second": 56.415,
|
406 |
+
"eval_steps_per_second": 1.777,
|
407 |
+
"step": 10500
|
408 |
}
|
409 |
],
|
410 |
"max_steps": 62500,
|
411 |
"num_train_epochs": 20,
|
412 |
+
"total_flos": 4.393192338122342e+16,
|
413 |
"trial_name": null,
|
414 |
"trial_params": null
|
415 |
}
|
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 sha256:8cf45d731900f7f9e07949ef1dfe708b522e158b7cfbb371287593175d5efcd1
|
3 |
size 242031355
|