Training in progress, step 12500
Browse files- last-checkpoint/optimizer.pt +2 -2
- 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 +43 -5
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1469fd8f07e70fce660a4bda8d192ac3ca66d3a3adcd912308371c5b393ca1c8
|
3 |
+
size 484085807
|
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 sha256:3d40cc1bf78ae2fdf97890c22cee215c66be9991f64cd6ae155d73abb89a9476
|
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 sha256:5ec297f64b905ab7abfa9445f11bda740a316a229f1922734f0890e5b6f74cef
|
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 sha256:44c678f5ce85ae0880e5cb719fac1528e583baf5b81c7f17b42193be6e2267a6
|
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:d0d912af195496eae2ada290b21559cf33ed0e7810e2664f30610cf99e61c2f6
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -443,11 +443,49 @@
|
|
443 |
"eval_samples_per_second": 56.492,
|
444 |
"eval_steps_per_second": 1.779,
|
445 |
"step": 11500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
446 |
}
|
447 |
],
|
448 |
"max_steps": 62500,
|
449 |
"num_train_epochs": 20,
|
450 |
-
"total_flos":
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7067587971687317,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-12500",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 12500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
443 |
"eval_samples_per_second": 56.492,
|
444 |
"eval_steps_per_second": 1.779,
|
445 |
"step": 11500
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 3.84,
|
449 |
+
"learning_rate": 0.00042530526315789473,
|
450 |
+
"loss": 0.5593,
|
451 |
+
"step": 12000
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 3.84,
|
455 |
+
"eval_bleu": 0.06743929871449864,
|
456 |
+
"eval_exact_match": 0.104,
|
457 |
+
"eval_loss": 0.7079191207885742,
|
458 |
+
"eval_rouge1": 0.5109229447218538,
|
459 |
+
"eval_rouge2": 0.3498840589135052,
|
460 |
+
"eval_rougeL": 0.49719053454192585,
|
461 |
+
"eval_runtime": 35.9294,
|
462 |
+
"eval_samples_per_second": 55.665,
|
463 |
+
"eval_steps_per_second": 1.753,
|
464 |
+
"step": 12000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 4.0,
|
468 |
+
"learning_rate": 0.00042109473684210524,
|
469 |
+
"loss": 0.5501,
|
470 |
+
"step": 12500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 4.0,
|
474 |
+
"eval_bleu": 0.06587822883992077,
|
475 |
+
"eval_exact_match": 0.0965,
|
476 |
+
"eval_loss": 0.7067587971687317,
|
477 |
+
"eval_rouge1": 0.5063077878070544,
|
478 |
+
"eval_rouge2": 0.34684822407233706,
|
479 |
+
"eval_rougeL": 0.49414991531075403,
|
480 |
+
"eval_runtime": 26.7311,
|
481 |
+
"eval_samples_per_second": 74.819,
|
482 |
+
"eval_steps_per_second": 2.357,
|
483 |
+
"step": 12500
|
484 |
}
|
485 |
],
|
486 |
"max_steps": 62500,
|
487 |
"num_train_epochs": 20,
|
488 |
+
"total_flos": 5.230290684975514e+16,
|
489 |
"trial_name": null,
|
490 |
"trial_params": null
|
491 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3823
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82218b9221f705e316837d205f7c97b4c6919db9b79fa061ca82a4d79c80f35
|
3 |
size 3823
|
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 sha256:3d40cc1bf78ae2fdf97890c22cee215c66be9991f64cd6ae155d73abb89a9476
|
3 |
size 242031355
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3823
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82218b9221f705e316837d205f7c97b4c6919db9b79fa061ca82a4d79c80f35
|
3 |
size 3823
|