devvanshhh
commited on
Commit
•
cc99153
1
Parent(s):
cf15de6
Training in progress, step 125, 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:d1d710940550297bb534c572597e5fc93fbe0e08df77a6a90e4c37b704d87eb1
|
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:f2bc34da270dd08f6aacd9d137555586d0c113704199454e5881295af53016f7
|
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:c450c82b23431e459aa8d00087a28bfa92d7ffb1c880150b0c347e94aa9867f9
|
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 sha256:44940d4930266a8280980e39b352a0c3c27ca4bb840c1344b77d047e121dae08
|
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 sha256:08ebaf136abbd24057d9dfb7d673e9595bc900b8054cd6608e4b9b14f1e3487e
|
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,
|
@@ -31,13 +31,19 @@
|
|
31 |
"learning_rate": 0.0002,
|
32 |
"loss": 0.9931,
|
33 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 25,
|
37 |
"max_steps": 728,
|
38 |
"num_train_epochs": 1,
|
39 |
"save_steps": 25,
|
40 |
-
"total_flos":
|
41 |
"trial_name": null,
|
42 |
"trial_params": null
|
43 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1717032967032967,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 125,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
31 |
"learning_rate": 0.0002,
|
32 |
"loss": 0.9931,
|
33 |
"step": 100
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.17,
|
37 |
+
"learning_rate": 0.0002,
|
38 |
+
"loss": 1.2852,
|
39 |
+
"step": 125
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 25,
|
43 |
"max_steps": 728,
|
44 |
"num_train_epochs": 1,
|
45 |
"save_steps": 25,
|
46 |
+
"total_flos": 1282007144595456.0,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
49 |
}
|