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 +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 484059375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc6e0c116722c7a682a8b0afaec07e02a2da3e591e6dcf1220f3831b82c5f97
|
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 sha256:8c77c798d9e31609fea26b21195d171ffeeb9f678b44971464e4f0e629b33f92
|
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 sha256:78a6e9072f3d44af85578942995a84e246dc4332ccb4f4db91024858f4e2ce08
|
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:d4347e029ad4f9668b68ba6074637e2375409db773513e24d41828ac35c9648b
|
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 sha256:4ab8fe23652b92861f17aafa33b8f75c2e0a340d47c51871a24705a3471cd03c
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.528552770614624,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -24,11 +24,29 @@
|
|
24 |
"eval_samples_per_second": 145.883,
|
25 |
"eval_steps_per_second": 1.523,
|
26 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
28 |
],
|
29 |
"max_steps": 36045,
|
30 |
"num_train_epochs": 5,
|
31 |
-
"total_flos":
|
32 |
"trial_name": null,
|
33 |
"trial_params": null
|
34 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.528552770614624,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
|
4 |
+
"epoch": 0.5548619780829519,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
24 |
"eval_samples_per_second": 145.883,
|
25 |
"eval_steps_per_second": 1.523,
|
26 |
"step": 2000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.55,
|
30 |
+
"learning_rate": 9.359558437007184e-05,
|
31 |
+
"loss": 1.3098,
|
32 |
+
"step": 4000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.55,
|
36 |
+
"eval_exact_match": 0.29667840966280823,
|
37 |
+
"eval_loss": 1.5582195520401,
|
38 |
+
"eval_rouge1": 0.499918373090859,
|
39 |
+
"eval_rouge2": 0.22982882883486827,
|
40 |
+
"eval_rougeL": 0.49974542584946463,
|
41 |
+
"eval_runtime": 169.5108,
|
42 |
+
"eval_samples_per_second": 140.664,
|
43 |
+
"eval_steps_per_second": 1.469,
|
44 |
+
"step": 4000
|
45 |
}
|
46 |
],
|
47 |
"max_steps": 36045,
|
48 |
"num_train_epochs": 5,
|
49 |
+
"total_flos": 5.1971251765248e+16,
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
52 |
}
|
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 sha256:8c77c798d9e31609fea26b21195d171ffeeb9f678b44971464e4f0e629b33f92
|
3 |
size 242019067
|