Training in progress, step 1000
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 sha256:151e08bd1babc90d723a982bcf88d1c88925283922c6259c8d89c044373fd8b9
|
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 sha256:3b825473e64798104695604c2cd2efd5aa5239a70d8f9d3501eb9fe138254b9e
|
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:de400c1e0c66057008d54f040bec42a96bdf19b525f3991c6cb1cbae48d31f1c
|
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 sha256:0f5cf4936c2dd29d99f5b051334cc5e9be4c9312eeab742ac81b2f62ebca8103
|
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 sha256:0f92b46a43f4ad35f3c7a06cacd3ba8dff212dcae6ffb713cbd9cfdeed7569e1
|
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-w_special_tokens/checkpoint-
|
4 |
-
"epoch": 0.
|
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": 84.482,
|
26 |
"eval_steps_per_second": 2.661,
|
27 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
],
|
30 |
"max_steps": 31250,
|
31 |
"num_train_epochs": 10,
|
32 |
-
"total_flos":
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8933660984039307,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/checkpoint-1000",
|
4 |
+
"epoch": 0.32,
|
5 |
+
"global_step": 1000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
25 |
"eval_samples_per_second": 84.482,
|
26 |
"eval_steps_per_second": 2.661,
|
27 |
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.32,
|
31 |
+
"learning_rate": 6.35956493921945e-05,
|
32 |
+
"loss": 0.8968,
|
33 |
+
"step": 1000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.32,
|
37 |
+
"eval_bleu": 0.11661343796568427,
|
38 |
+
"eval_exact_match": 0.148,
|
39 |
+
"eval_loss": 0.8933660984039307,
|
40 |
+
"eval_rouge1": 0.5490713398258988,
|
41 |
+
"eval_rouge2": 0.3737481223472951,
|
42 |
+
"eval_rougeL": 0.5313359382235461,
|
43 |
+
"eval_runtime": 21.9288,
|
44 |
+
"eval_samples_per_second": 91.204,
|
45 |
+
"eval_steps_per_second": 2.873,
|
46 |
+
"step": 1000
|
47 |
}
|
48 |
],
|
49 |
"max_steps": 31250,
|
50 |
"num_train_epochs": 10,
|
51 |
+
"total_flos": 3609058313502720.0,
|
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 sha256:3b825473e64798104695604c2cd2efd5aa5239a70d8f9d3501eb9fe138254b9e
|
3 |
size 242019067
|