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 484059375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732fd15e9736cf903b8e7b8b085c6bf99773fb62b5f6b2fbc74812d3fae962ef
|
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:df59b9fb61c0eb3c62fcbc559333a3456275b63d76700ece15ed3c20b894f444
|
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 sha256:3b937419a60409445d0cf756c823e6db64f8f1ccee3c469dbff728db700c3c50
|
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 sha256:04a32cf34139cef7ccf85eccba14bca543513afa71c5dd5ebd0ce9975003a757
|
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 sha256:0961446f2081a256b3eadd0a429499494e97c5494c01dafefe3f6dfaaf7b3898
|
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,
|
@@ -44,11 +44,30 @@
|
|
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":
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
54 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8664323687553406,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/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": 91.204,
|
45 |
"eval_steps_per_second": 2.873,
|
46 |
"step": 1000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.48,
|
50 |
+
"learning_rate": 9.558541266794626e-05,
|
51 |
+
"loss": 0.8139,
|
52 |
+
"step": 1500
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.48,
|
56 |
+
"eval_bleu": 0.11428222214709638,
|
57 |
+
"eval_exact_match": 0.148,
|
58 |
+
"eval_loss": 0.8664323687553406,
|
59 |
+
"eval_rouge1": 0.5501019947483123,
|
60 |
+
"eval_rouge2": 0.37606920276228095,
|
61 |
+
"eval_rougeL": 0.5316473251371836,
|
62 |
+
"eval_runtime": 21.9364,
|
63 |
+
"eval_samples_per_second": 91.173,
|
64 |
+
"eval_steps_per_second": 2.872,
|
65 |
+
"step": 1500
|
66 |
}
|
67 |
],
|
68 |
"max_steps": 31250,
|
69 |
"num_train_epochs": 10,
|
70 |
+
"total_flos": 5419990829236224.0,
|
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 242019067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df59b9fb61c0eb3c62fcbc559333a3456275b63d76700ece15ed3c20b894f444
|
3 |
size 242019067
|