Dmitriy007
commited on
Commit
•
ce2ae74
1
Parent(s):
40f38bd
Training in progress, step 5000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f12f0e3cc3a75131d80ef954591903d87848e78f8aac91efd11f0ed4721108
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb07cc67e0c3019a668ca16793a4037e6f6c3114d85ec18d1b2d2dbdd61ea22c
|
3 |
size 1524261149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65768316a99ca15259a80613401c71fe0281d535c47ea22858cfb5f907594f12
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:355906bcd8f0f8b5bf00f616ffb8e1745f24244d737cc4abfa86b78127641f87
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -86,11 +86,31 @@
|
|
86 |
"eval_samples_per_second": 15.516,
|
87 |
"eval_steps_per_second": 5.174,
|
88 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 19990,
|
92 |
"num_train_epochs": 5,
|
93 |
-
"total_flos":
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2506253126563283,
|
5 |
+
"global_step": 5000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
86 |
"eval_samples_per_second": 15.516,
|
87 |
"eval_steps_per_second": 5.174,
|
88 |
"step": 4000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.13,
|
92 |
+
"learning_rate": 1.5497748874437218e-05,
|
93 |
+
"loss": 2.5641,
|
94 |
+
"step": 4500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.25,
|
98 |
+
"learning_rate": 1.4997498749374688e-05,
|
99 |
+
"loss": 2.5279,
|
100 |
+
"step": 5000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.25,
|
104 |
+
"eval_loss": 3.182180881500244,
|
105 |
+
"eval_runtime": 136.5938,
|
106 |
+
"eval_samples_per_second": 15.499,
|
107 |
+
"eval_steps_per_second": 5.169,
|
108 |
+
"step": 5000
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 19990,
|
112 |
"num_train_epochs": 5,
|
113 |
+
"total_flos": 7074087321600000.0,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb07cc67e0c3019a668ca16793a4037e6f6c3114d85ec18d1b2d2dbdd61ea22c
|
3 |
size 1524261149
|
runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4749a00c3b1c97331a917c2704ddbc65d76054575332b78ce1e1a699a82bb6
|
3 |
+
size 5953
|