Training in progress, step 7500
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6d25670b1aa73045b7ab3a2dd08d8118f890e0c21f8f70686cd281e18a7c33c
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f567f9927df26a278dc8b85ed5c69740b7e4a34d6c651d3992144b6a8a169314
|
3 |
size 551185105
|
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 sha256:1960a2c19b4cb34d1447fb092da3e0b31be09a51629469514d8eeec187a5ee17
|
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:de4fbae35cf2b04d80b79eee0e1bc810cefcf0c3ac70c8f2e605869f303eac55
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -90,11 +90,17 @@
|
|
90 |
"learning_rate": 4.204545454545455e-05,
|
91 |
"loss": 0.0338,
|
92 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 44000,
|
96 |
"num_train_epochs": 1,
|
97 |
-
"total_flos":
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10173905965978458,
|
5 |
+
"global_step": 7500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
90 |
"learning_rate": 4.204545454545455e-05,
|
91 |
"loss": 0.0338,
|
92 |
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.1,
|
96 |
+
"learning_rate": 4.1477272727272734e-05,
|
97 |
+
"loss": 0.0358,
|
98 |
+
"step": 7500
|
99 |
}
|
100 |
],
|
101 |
"max_steps": 44000,
|
102 |
"num_train_epochs": 1,
|
103 |
+
"total_flos": 7838302577098752.0,
|
104 |
"trial_name": null,
|
105 |
"trial_params": null
|
106 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f567f9927df26a278dc8b85ed5c69740b7e4a34d6c651d3992144b6a8a169314
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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:a66b486f2dd5265de917680674a30319bbd66d7db849855f3f9a88d06f4ac3cf
|
3 |
+
size 48001
|