Training in progress, step 24000
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:e3ed776697e203f3303f55782e2720a0dcffb0a9c4a0e57a946b7b58974f7fdc
|
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 sha256:237b520a58c6857b1020c0e1a55976f112afefa8ec8485ed4f0e0865bb1b4c47
|
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 sha256:42a4649a04683c2d2819ed2479cf93fc5447eaebfbeee0d728ba56fa1860ce6c
|
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:dae8c5e47c41da4d471e6a1fee2c7e800a0991ff1d277f5535c1e7aff0060852
|
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:c753683e6c64c492da11e6e2c5a1b4722dd770f8496021c95111ac5251fc1a08
|
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,
|
@@ -899,11 +899,30 @@
|
|
899 |
"eval_samples_per_second": 76.554,
|
900 |
"eval_steps_per_second": 2.411,
|
901 |
"step": 23500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
902 |
}
|
903 |
],
|
904 |
"max_steps": 62500,
|
905 |
"num_train_epochs": 20,
|
906 |
-
"total_flos":
|
907 |
"trial_name": null,
|
908 |
"trial_params": null
|
909 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6601866483688354,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-24000",
|
4 |
+
"epoch": 7.68,
|
5 |
+
"global_step": 24000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
899 |
"eval_samples_per_second": 76.554,
|
900 |
"eval_steps_per_second": 2.411,
|
901 |
"step": 23500
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 7.68,
|
905 |
+
"learning_rate": 0.0003242778947368421,
|
906 |
+
"loss": 0.4334,
|
907 |
+
"step": 24000
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 7.68,
|
911 |
+
"eval_bleu": 0.06857766001536686,
|
912 |
+
"eval_exact_match": 0.105,
|
913 |
+
"eval_loss": 0.6601866483688354,
|
914 |
+
"eval_rouge1": 0.5140953364016511,
|
915 |
+
"eval_rouge2": 0.35736194915396335,
|
916 |
+
"eval_rougeL": 0.5012302345945796,
|
917 |
+
"eval_runtime": 26.229,
|
918 |
+
"eval_samples_per_second": 76.252,
|
919 |
+
"eval_steps_per_second": 2.402,
|
920 |
+
"step": 24000
|
921 |
}
|
922 |
],
|
923 |
"max_steps": 62500,
|
924 |
"num_train_epochs": 20,
|
925 |
+
"total_flos": 1.0034338438053888e+17,
|
926 |
"trial_name": null,
|
927 |
"trial_params": null
|
928 |
}
|
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 sha256:237b520a58c6857b1020c0e1a55976f112afefa8ec8485ed4f0e0865bb1b4c47
|
3 |
size 242031355
|