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 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e139b9e0f4909b3797b7ba6962ced8429af4fd19327c677ff84780f8fd06b98
|
3 |
size 484083951
|
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 sha256:13e3a338ddc5b7cddde26979b2bd8fd537186a223a74db92750ad39d56cc532b
|
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:edd2f119893dc0e1e9a7411866ffd48762a345d86f826cec7b78021f83658442
|
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:fc578179f5f11115d21af0380a1ecec0f43688f71c8a75d747da2af2c1663c5b
|
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 sha256:8c9e4efd618efaa7f1b85a426ab7e5036c26551ce37e43df2d28a19a0db8ab19
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/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": 55.178,
|
26 |
"eval_steps_per_second": 1.738,
|
27 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 1.4567848443984985,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/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": 55.178,
|
26 |
"eval_steps_per_second": 1.738,
|
27 |
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.32,
|
31 |
+
"learning_rate": 0.00015968,
|
32 |
+
"loss": 1.7625,
|
33 |
+
"step": 1000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.32,
|
37 |
+
"eval_bleu": 0.038749091873206375,
|
38 |
+
"eval_exact_match": 0.0145,
|
39 |
+
"eval_loss": 1.4567848443984985,
|
40 |
+
"eval_rouge1": 0.35498006740689036,
|
41 |
+
"eval_rouge2": 0.13946738339077275,
|
42 |
+
"eval_rougeL": 0.3327171698914647,
|
43 |
+
"eval_runtime": 34.5773,
|
44 |
+
"eval_samples_per_second": 57.841,
|
45 |
+
"eval_steps_per_second": 1.822,
|
46 |
+
"step": 1000
|
47 |
}
|
48 |
],
|
49 |
"max_steps": 62500,
|
50 |
"num_train_epochs": 20,
|
51 |
+
"total_flos": 4191281825710080.0,
|
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 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13e3a338ddc5b7cddde26979b2bd8fd537186a223a74db92750ad39d56cc532b
|
3 |
size 242031355
|