Training in progress, step 4000
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 484059375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5a0bb96ccf6cd7fbed7100c837bae72dcca5d955bbd1a353ef95a291eab6087
|
3 |
size 484059375
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242019067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c7425dc9a83d2f571fe7a67f44350b2789d9d8f1fbf0fe7788479ec09cd8213
|
3 |
size 242019067
|
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 sha256:3157b79eb8ff70b16f69ce8c1632076ed5241d343158cd32d0680ceece7215f5
|
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 sha256:28fe7356ac41326de74498362e867b46c2afaac5b870542146ebe7498b6d42a8
|
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:e16c8230a03e10d415501889aee265e809acdb939d6b899c3741c14494c27590
|
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/Salesforce-codet5-small-CodeXGLUE-CONCODE-selected/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -25,11 +25,30 @@
|
|
25 |
"eval_samples_per_second": 8.583,
|
26 |
"eval_steps_per_second": 0.27,
|
27 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
],
|
30 |
"max_steps": 62500,
|
31 |
"num_train_epochs": 20,
|
32 |
-
"total_flos":
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8113107681274414,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-selected/checkpoint-4000",
|
4 |
+
"epoch": 1.28,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
25 |
"eval_samples_per_second": 8.583,
|
26 |
"eval_steps_per_second": 0.27,
|
27 |
"step": 2000
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.28,
|
31 |
+
"learning_rate": 9.853642105263158e-05,
|
32 |
+
"loss": 0.7186,
|
33 |
+
"step": 4000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.28,
|
37 |
+
"eval_bleu": 0.2686100325072973,
|
38 |
+
"eval_exact_match": 0.1755,
|
39 |
+
"eval_loss": 0.8113107681274414,
|
40 |
+
"eval_rouge1": 0.5759137545878418,
|
41 |
+
"eval_rouge2": 0.3934978008929957,
|
42 |
+
"eval_rougeL": 0.5514257399531202,
|
43 |
+
"eval_runtime": 222.3222,
|
44 |
+
"eval_samples_per_second": 8.996,
|
45 |
+
"eval_steps_per_second": 0.283,
|
46 |
+
"step": 4000
|
47 |
}
|
48 |
],
|
49 |
"max_steps": 62500,
|
50 |
"num_train_epochs": 20,
|
51 |
+
"total_flos": 1.4464215171465216e+16,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
54 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242019067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c7425dc9a83d2f571fe7a67f44350b2789d9d8f1fbf0fe7788479ec09cd8213
|
3 |
size 242019067
|