genejalston
commited on
Commit
•
81d78b2
1
Parent(s):
0b37129
Training in progress, step 4500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb6a3997803eebdd2cab8b05d3e11fc7b1b5e72b059d14b88afbc5e9d2e960a2
|
3 |
size 1625426996
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250759951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0659d84d42f67f7d0614c9db8ed7e1b90dc5467ce646c45a244117e0d8b281e6
|
3 |
size 3250759951
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10d14f7de59f48f4ade3e9464aacd8c0fa09164a39807a7c587e8743b637b06e
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6032f9ebe8c8c14bc64b0775131b92bc24d785e7deee32c5a13741aeca0eff6f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -55,13 +55,19 @@
|
|
55 |
"learning_rate": 1.941958993083083e-05,
|
56 |
"loss": 0.0909,
|
57 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
61 |
"max_steps": 137499,
|
62 |
"num_train_epochs": 3,
|
63 |
"save_steps": 500,
|
64 |
-
"total_flos":
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09818253223659809,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"learning_rate": 1.941958993083083e-05,
|
56 |
"loss": 0.0909,
|
57 |
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.1,
|
61 |
+
"learning_rate": 1.934685683945625e-05,
|
62 |
+
"loss": 0.1167,
|
63 |
+
"step": 4500
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 500,
|
67 |
"max_steps": 137499,
|
68 |
"num_train_epochs": 3,
|
69 |
"save_steps": 500,
|
70 |
+
"total_flos": 7618727116800000.0,
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|