Training in progress, step 10000
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 +21 -3
- 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 484079855
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c44c63931f546bab96f25a9653aeda56150ae69a868a9f7120f8db83057847b4
|
3 |
size 484079855
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98d388236a5ac12f54122881523fd9eec57271529a378b4420d1123f37d63475
|
3 |
size 242029307
|
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:c4596ea7cd7ae6c0252c56421bf56b3436d93483f3453718b8e382fbf4e1f49a
|
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:c81a90d32031ababf8fa58b225710323ce6490a2e7e8fd36a3bd77d76226ba7c
|
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:dc509778b77a1e045e9dce33bbd0636b63e51df466535494e9c97735dd4d2d8a
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -78,11 +78,29 @@
|
|
78 |
"eval_samples_per_second": 143.29,
|
79 |
"eval_steps_per_second": 1.496,
|
80 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
}
|
82 |
],
|
83 |
"max_steps": 72090,
|
84 |
"num_train_epochs": 10,
|
85 |
-
"total_flos": 1.
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
+
"epoch": 1.3871549452073797,
|
5 |
+
"global_step": 10000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
78 |
"eval_samples_per_second": 143.29,
|
79 |
"eval_steps_per_second": 1.496,
|
80 |
"step": 8000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.39,
|
84 |
+
"learning_rate": 9.066948966927065e-05,
|
85 |
+
"loss": 1.0699,
|
86 |
+
"step": 10000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.39,
|
90 |
+
"eval_exact_match": 0.32087736956886426,
|
91 |
+
"eval_loss": 1.5405367612838745,
|
92 |
+
"eval_rouge1": 0.5257435158783685,
|
93 |
+
"eval_rouge2": 0.2513617731408373,
|
94 |
+
"eval_rougeL": 0.5253820138123132,
|
95 |
+
"eval_runtime": 166.5276,
|
96 |
+
"eval_samples_per_second": 143.183,
|
97 |
+
"eval_steps_per_second": 1.495,
|
98 |
+
"step": 10000
|
99 |
}
|
100 |
],
|
101 |
"max_steps": 72090,
|
102 |
"num_train_epochs": 10,
|
103 |
+
"total_flos": 1.2991594865098752e+17,
|
104 |
"trial_name": null,
|
105 |
"trial_params": null
|
106 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98d388236a5ac12f54122881523fd9eec57271529a378b4420d1123f37d63475
|
3 |
size 242029307
|