Training in progress, step 8000
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 sha256:9ecd2121c62b78fefadaeabf329af30965c1d5254ad8a247a2f5e1c089314099
|
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:f011fe99c630646ec9bff8b3f6cd382f67008dc8ff7658561572678aac30eb7e
|
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:f2142769294a8c158a319ee7619050123d4d200b9168f6287bd440d1df8e4983
|
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 sha256:3782c5183f4b3926da31cb7a03a04d622797e9ed4a0007066495827d4864b745
|
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 sha256:789abdc0646d0e04a81d17afdf777ec7127cfb77488d5350e897ba1735bdfab3
|
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-selected/checkpoint-
|
4 |
-
"epoch":
|
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": 7.699,
|
64 |
"eval_steps_per_second": 0.243,
|
65 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"max_steps": 62500,
|
69 |
"num_train_epochs": 20,
|
70 |
-
"total_flos": 2.
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7699160575866699,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-selected/checkpoint-8000",
|
4 |
+
"epoch": 2.56,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
63 |
"eval_samples_per_second": 7.699,
|
64 |
"eval_steps_per_second": 0.243,
|
65 |
"step": 6000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.56,
|
69 |
+
"learning_rate": 9.179957894736842e-05,
|
70 |
+
"loss": 0.562,
|
71 |
+
"step": 8000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.56,
|
75 |
+
"eval_bleu": 0.2967822969771582,
|
76 |
+
"eval_exact_match": 0.179,
|
77 |
+
"eval_loss": 0.7699160575866699,
|
78 |
+
"eval_rouge1": 0.5769004117490721,
|
79 |
+
"eval_rouge2": 0.400017695314681,
|
80 |
+
"eval_rougeL": 0.5526377939756941,
|
81 |
+
"eval_runtime": 274.6962,
|
82 |
+
"eval_samples_per_second": 7.281,
|
83 |
+
"eval_steps_per_second": 0.229,
|
84 |
+
"step": 8000
|
85 |
}
|
86 |
],
|
87 |
"max_steps": 62500,
|
88 |
"num_train_epochs": 20,
|
89 |
+
"total_flos": 2.891269685850931e+16,
|
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:f011fe99c630646ec9bff8b3f6cd382f67008dc8ff7658561572678aac30eb7e
|
3 |
size 242019067
|