Training in progress, step 2000
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:c78775b277a150c378cb6023b4c7ebd644bcb1272f698f386de7116e2bc4c64c
|
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 sha256:338cef626f855cc242565a0a65a36037297f51b115d97b599c1f6fbdf730e422
|
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:aa94201b22acd5018fd38b655dbef6e9f1b2912d0b368aa3980c2a7c1e0e048b
|
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:ea80ccc04bef8b48980e66f640dfdc266a4836d420269ff472cffc44731cade3
|
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 sha256:35f47f50c30a41c44e8be8c01dd6d3241113de176e599b4b3e3d734ad3340af3
|
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,
|
@@ -63,11 +63,30 @@
|
|
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":
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8371005058288574,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/checkpoint-2000",
|
4 |
+
"epoch": 0.64,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
63 |
"eval_samples_per_second": 91.173,
|
64 |
"eval_steps_per_second": 2.872,
|
65 |
"step": 1500
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.64,
|
69 |
+
"learning_rate": 9.854818607471284e-05,
|
70 |
+
"loss": 0.7535,
|
71 |
+
"step": 2000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.64,
|
75 |
+
"eval_bleu": 0.12118583002054595,
|
76 |
+
"eval_exact_match": 0.152,
|
77 |
+
"eval_loss": 0.8371005058288574,
|
78 |
+
"eval_rouge1": 0.5554072128917051,
|
79 |
+
"eval_rouge2": 0.37994480723664975,
|
80 |
+
"eval_rougeL": 0.5360569772635451,
|
81 |
+
"eval_runtime": 21.9828,
|
82 |
+
"eval_samples_per_second": 90.98,
|
83 |
+
"eval_steps_per_second": 2.866,
|
84 |
+
"step": 2000
|
85 |
}
|
86 |
],
|
87 |
"max_steps": 31250,
|
88 |
"num_train_epochs": 10,
|
89 |
+
"total_flos": 7244330642178048.0,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
92 |
}
|
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 sha256:338cef626f855cc242565a0a65a36037297f51b115d97b599c1f6fbdf730e422
|
3 |
size 242019067
|