devvanshhh
commited on
Commit
•
5c73f3f
1
Parent(s):
f68836e
Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 369214349
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebde0a2c239cc87e2ba747dbb26451f45eb1cb9fc0ac81ea9bd63a003c5abf89
|
3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 369142184
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96c7d53f211c562ca99aa5bf9ccdde10e31d881e4bb0672cef5320b43f99a1f6
|
3 |
size 369142184
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 738393541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e74aa30c7fca8cabc378cafbe8ecec2ce92a6cbfcea20850f0be21bb05c54e3
|
3 |
size 738393541
|
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 sha256:92343fa897a7f2b7ee300d2792808f910a8eb1bf1ba73666e73c8d9e0f06ea39
|
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:d217edb059555be97837810de03dc22d79976c8832aac609d084f6016b5003c4
|
3 |
size 627
|
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,
|
@@ -13,13 +13,19 @@
|
|
13 |
"learning_rate": 0.0002,
|
14 |
"loss": 1.9673,
|
15 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"logging_steps": 25,
|
19 |
"max_steps": 728,
|
20 |
"num_train_epochs": 1,
|
21 |
"save_steps": 25,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06868131868131869,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
13 |
"learning_rate": 0.0002,
|
14 |
"loss": 1.9673,
|
15 |
"step": 25
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.07,
|
19 |
+
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.524,
|
21 |
+
"step": 50
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 25,
|
25 |
"max_steps": 728,
|
26 |
"num_train_epochs": 1,
|
27 |
"save_steps": 25,
|
28 |
+
"total_flos": 507374726184960.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|