Training in progress, step 23500
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 sha256:8800d503cd7013e50eb6437ac58e4395be4120220ebca2ff3a9099d76cdb602d
|
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 sha256:6eeca3914bdb6872db2ebcd7098e11c5c44535bb1b81f80a794d8d487c7b1f3c
|
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 sha256:3b0a6d9e8345833900efdb88c8cb5dada6cc9500baac569a6ba4feb4433481a9
|
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 sha256:670a061e604d5241731dbf4da4113098b7822c3b3f5ffa5c546addfb9119edc0
|
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:a6da8a6864e27b651e8d7f8483b881d98a4f688a6005cf6d0d5f6f6828bd9be9
|
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,
|
@@ -880,11 +880,30 @@
|
|
880 |
"eval_samples_per_second": 76.74,
|
881 |
"eval_steps_per_second": 2.417,
|
882 |
"step": 23000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
883 |
}
|
884 |
],
|
885 |
"max_steps": 62500,
|
886 |
"num_train_epochs": 20,
|
887 |
-
"total_flos": 9.
|
888 |
"trial_name": null,
|
889 |
"trial_params": null
|
890 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6632941961288452,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-23500",
|
4 |
+
"epoch": 7.52,
|
5 |
+
"global_step": 23500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
880 |
"eval_samples_per_second": 76.74,
|
881 |
"eval_steps_per_second": 2.417,
|
882 |
"step": 23000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 7.52,
|
886 |
+
"learning_rate": 0.0003284884210526316,
|
887 |
+
"loss": 0.433,
|
888 |
+
"step": 23500
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 7.52,
|
892 |
+
"eval_bleu": 0.06809047383108359,
|
893 |
+
"eval_exact_match": 0.1035,
|
894 |
+
"eval_loss": 0.6632941961288452,
|
895 |
+
"eval_rouge1": 0.511074186368692,
|
896 |
+
"eval_rouge2": 0.35738572766675536,
|
897 |
+
"eval_rougeL": 0.4988662331382937,
|
898 |
+
"eval_runtime": 26.1254,
|
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": 9.824838634124083e+16,
|
907 |
"trial_name": null,
|
908 |
"trial_params": null
|
909 |
}
|
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 sha256:6eeca3914bdb6872db2ebcd7098e11c5c44535bb1b81f80a794d8d487c7b1f3c
|
3 |
size 242031355
|