Training in progress, step 17000
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 484085807
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04a2889cb8b3fdffc9b65c359c756e48a223cc578207b06481018859948edd1
|
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 sha256:4313e998740e78177fb5d3f65d12db4e3e2b067c400f4d4e37d46862161a12d7
|
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 sha256:7a9a940df49662b4ff881c4afbd1f6c7790494ba98b0cd756cda25da77503248
|
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 sha256:9ec6b6bb9e305aea40d06ac76c1046c4f17ef3bea3dd3ce2c67e53cbebb07ead
|
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 sha256:0057183e7dfe7a74e99394d790f72d36c9f2442ef240fb6e405f4b700af338c0
|
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.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -633,11 +633,30 @@
|
|
633 |
"eval_samples_per_second": 77.269,
|
634 |
"eval_steps_per_second": 2.434,
|
635 |
"step": 16500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
636 |
}
|
637 |
],
|
638 |
"max_steps": 62500,
|
639 |
"num_train_epochs": 20,
|
640 |
-
"total_flos":
|
641 |
"trial_name": null,
|
642 |
"trial_params": null
|
643 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6765531301498413,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-17000",
|
4 |
+
"epoch": 5.44,
|
5 |
+
"global_step": 17000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
633 |
"eval_samples_per_second": 77.269,
|
634 |
"eval_steps_per_second": 2.434,
|
635 |
"step": 16500
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 5.44,
|
639 |
+
"learning_rate": 0.00038321684210526315,
|
640 |
+
"loss": 0.4874,
|
641 |
+
"step": 17000
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 5.44,
|
645 |
+
"eval_bleu": 0.0690414017532501,
|
646 |
+
"eval_exact_match": 0.103,
|
647 |
+
"eval_loss": 0.6765531301498413,
|
648 |
+
"eval_rouge1": 0.5144668417632419,
|
649 |
+
"eval_rouge2": 0.35703037655654435,
|
650 |
+
"eval_rougeL": 0.5011385205263255,
|
651 |
+
"eval_runtime": 26.2313,
|
652 |
+
"eval_samples_per_second": 76.245,
|
653 |
+
"eval_steps_per_second": 2.402,
|
654 |
+
"step": 17000
|
655 |
}
|
656 |
],
|
657 |
"max_steps": 62500,
|
658 |
"num_train_epochs": 20,
|
659 |
+
"total_flos": 7.112275954709299e+16,
|
660 |
"trial_name": null,
|
661 |
"trial_params": null
|
662 |
}
|
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 sha256:4313e998740e78177fb5d3f65d12db4e3e2b067c400f4d4e37d46862161a12d7
|
3 |
size 242031355
|