Training in progress, step 22500
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 sha256:5b7e7c078a39a689939c037d72235890bf6584bb928d9e785916172b4e820915
|
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 sha256:9b361896c6802b68ef5c776b2fe5bb5136a17df509fd1b4edd8e0dd8ca078872
|
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:fe6804e8b27ef59599074328bde187701e649cea127bf1422ab7db7c638f4ffe
|
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 sha256:9556b71e3b9b23ca382a0e542ff1e829397dee87fcc10ddaf64025aba131f238
|
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:c86fc1e8e7ea6191ee0b61ef0d2d0c43d8b17b6e883db57fd0037b8796a41551
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -842,11 +842,30 @@
|
|
842 |
"eval_samples_per_second": 71.099,
|
843 |
"eval_steps_per_second": 2.24,
|
844 |
"step": 22000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
845 |
}
|
846 |
],
|
847 |
"max_steps": 62500,
|
848 |
"num_train_epochs": 20,
|
849 |
-
"total_flos": 9.
|
850 |
"trial_name": null,
|
851 |
"trial_params": null
|
852 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.665252685546875,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-22500",
|
4 |
+
"epoch": 7.2,
|
5 |
+
"global_step": 22500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
842 |
"eval_samples_per_second": 71.099,
|
843 |
"eval_steps_per_second": 2.24,
|
844 |
"step": 22000
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 7.2,
|
848 |
+
"learning_rate": 0.00033690105263157896,
|
849 |
+
"loss": 0.4311,
|
850 |
+
"step": 22500
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 7.2,
|
854 |
+
"eval_bleu": 0.06724531081942378,
|
855 |
+
"eval_exact_match": 0.1035,
|
856 |
+
"eval_loss": 0.665252685546875,
|
857 |
+
"eval_rouge1": 0.510047207004009,
|
858 |
+
"eval_rouge2": 0.3579587667006371,
|
859 |
+
"eval_rougeL": 0.4979863063664335,
|
860 |
+
"eval_runtime": 26.0203,
|
861 |
+
"eval_samples_per_second": 76.863,
|
862 |
+
"eval_steps_per_second": 2.421,
|
863 |
+
"step": 22500
|
864 |
}
|
865 |
],
|
866 |
"max_steps": 62500,
|
867 |
"num_train_epochs": 20,
|
868 |
+
"total_flos": 9.40622390451241e+16,
|
869 |
"trial_name": null,
|
870 |
"trial_params": null
|
871 |
}
|
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 sha256:9b361896c6802b68ef5c776b2fe5bb5136a17df509fd1b4edd8e0dd8ca078872
|
3 |
size 242031355
|