Training in progress, step 1500
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 sha256:94b1bc6940be30a1574a752ec9589ebc1c7725d74853b8ca289bb1903af8b1ed
|
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:a6164e35df3dd7dc166ba6b62f0378f2f17510d002e553ae78edf51d779fd091
|
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 sha256:9ff352162e8fc4965abd4f0ffb1552cfb1c4ca24a6e8479930f09dff77a91606
|
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 sha256:32520252762c272ab2bf1105ae2a9a712ece49950681f93d86d2dc5bc1d7fdf9
|
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 sha256:58a421609b894b29550434ab6df6484f10b348abdb45cd0469dc206a94140924
|
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,
|
@@ -44,11 +44,30 @@
|
|
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":
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
54 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1938430070877075,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-1500",
|
4 |
+
"epoch": 0.48,
|
5 |
+
"global_step": 1500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
44 |
"eval_samples_per_second": 57.841,
|
45 |
"eval_steps_per_second": 1.822,
|
46 |
"step": 1000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.48,
|
50 |
+
"learning_rate": 0.00023952,
|
51 |
+
"loss": 1.3575,
|
52 |
+
"step": 1500
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.48,
|
56 |
+
"eval_bleu": 0.04388514972808356,
|
57 |
+
"eval_exact_match": 0.053,
|
58 |
+
"eval_loss": 1.1938430070877075,
|
59 |
+
"eval_rouge1": 0.4102062635539608,
|
60 |
+
"eval_rouge2": 0.21783150768420984,
|
61 |
+
"eval_rougeL": 0.3907330178570455,
|
62 |
+
"eval_runtime": 34.9414,
|
63 |
+
"eval_samples_per_second": 57.239,
|
64 |
+
"eval_steps_per_second": 1.803,
|
65 |
+
"step": 1500
|
66 |
}
|
67 |
],
|
68 |
"max_steps": 62500,
|
69 |
"num_train_epochs": 20,
|
70 |
+
"total_flos": 6282414164803584.0,
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
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:a6164e35df3dd7dc166ba6b62f0378f2f17510d002e553ae78edf51d779fd091
|
3 |
size 242031355
|