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 +21 -3
- 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 484079855
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:344ee033be3b5c288bdabcafcb2b91d0b39fa8279671e975979e58743cba338d
|
3 |
size 484079855
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f152f59266c4c01c5fb145455314841dc4ef2c98fe040dbd0ccbe299b4250879
|
3 |
size 242029307
|
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 sha256:74337421f4b5deb1fbf3656c17edbeea4392fd1faacddd4865ca0c1f1ab5aa2b
|
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:cd9ee1147533a922890265ee38da2fa816de2c9f8ffd49b73e1b461db73fb1b7
|
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 sha256:09815559a8e883e3412adb178816408cb1cf30f7f0a73da5458e848a6def0b34
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -60,11 +60,29 @@
|
|
60 |
"eval_samples_per_second": 142.157,
|
61 |
"eval_steps_per_second": 1.485,
|
62 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 72090,
|
66 |
"num_train_epochs": 10,
|
67 |
-
"total_flos":
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
+
"epoch": 1.1097239561659038,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 142.157,
|
61 |
"eval_steps_per_second": 1.485,
|
62 |
"step": 6000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.11,
|
66 |
+
"learning_rate": 9.358983719062569e-05,
|
67 |
+
"loss": 1.1394,
|
68 |
+
"step": 8000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.11,
|
72 |
+
"eval_exact_match": 0.3172705921825197,
|
73 |
+
"eval_loss": 1.6098668575286865,
|
74 |
+
"eval_rouge1": 0.507425024161823,
|
75 |
+
"eval_rouge2": 0.2482872472913446,
|
76 |
+
"eval_rougeL": 0.5069841743495872,
|
77 |
+
"eval_runtime": 166.4039,
|
78 |
+
"eval_samples_per_second": 143.29,
|
79 |
+
"eval_steps_per_second": 1.496,
|
80 |
+
"step": 8000
|
81 |
}
|
82 |
],
|
83 |
"max_steps": 72090,
|
84 |
"num_train_epochs": 10,
|
85 |
+
"total_flos": 1.0393032276836352e+17,
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f152f59266c4c01c5fb145455314841dc4ef2c98fe040dbd0ccbe299b4250879
|
3 |
size 242029307
|