Training in progress, step 21500
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 sha256:3d026ce2c28cb8dd486d769dc4cd0adb31c66a1e59ba524721ac3d27b118c7bb
|
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:c860b31a1313cc4fa5b34ab5a795e2313ccb97c1c5501722896e7934176b9108
|
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:f491a731659f5c4d65010aeb2b452b98e4db5c7bc965bbdea6c273bb689dc2b3
|
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:d3afd1ea69570e14c844a66118a1c192109cf6c9891a12c6ec31646e0d11ed68
|
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 sha256:213368c8ae9175cdaa32b0aa2af166014c8f1fce26f0dfa9306d5d9ecfa693b4
|
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": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -804,11 +804,30 @@
|
|
804 |
"eval_samples_per_second": 76.54,
|
805 |
"eval_steps_per_second": 2.411,
|
806 |
"step": 21000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
807 |
}
|
808 |
],
|
809 |
"max_steps": 62500,
|
810 |
"num_train_epochs": 20,
|
811 |
-
"total_flos": 8.
|
812 |
"trial_name": null,
|
813 |
"trial_params": null
|
814 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6690553426742554,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-21500",
|
4 |
+
"epoch": 6.88,
|
5 |
+
"global_step": 21500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
804 |
"eval_samples_per_second": 76.54,
|
805 |
"eval_steps_per_second": 2.411,
|
806 |
"step": 21000
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 6.88,
|
810 |
+
"learning_rate": 0.0003453221052631579,
|
811 |
+
"loss": 0.4588,
|
812 |
+
"step": 21500
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 6.88,
|
816 |
+
"eval_bleu": 0.06913111094634318,
|
817 |
+
"eval_exact_match": 0.102,
|
818 |
+
"eval_loss": 0.6690553426742554,
|
819 |
+
"eval_rouge1": 0.5125284973649041,
|
820 |
+
"eval_rouge2": 0.35722843628208867,
|
821 |
+
"eval_rougeL": 0.5004858865893127,
|
822 |
+
"eval_runtime": 27.2998,
|
823 |
+
"eval_samples_per_second": 73.26,
|
824 |
+
"eval_steps_per_second": 2.308,
|
825 |
+
"step": 21500
|
826 |
}
|
827 |
],
|
828 |
"max_steps": 62500,
|
829 |
"num_train_epochs": 20,
|
830 |
+
"total_flos": 8.989717969344922e+16,
|
831 |
"trial_name": null,
|
832 |
"trial_params": null
|
833 |
}
|
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:c860b31a1313cc4fa5b34ab5a795e2313ccb97c1c5501722896e7934176b9108
|
3 |
size 242031355
|