devvanshhh
commited on
Commit
•
af70865
1
Parent(s):
58464c6
Training in progress, step 250, 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 sha256:23a62c3ecf405604ec6e4190e33eedcae4e5beed3f2b75a0dcbc10ba952015f2
|
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:b96a653c1f51f9d7927aa6b54386f2db7b260970e9db531962de0c3bb2866c73
|
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:bf9a5143902fd783b933803fa7e6d9cf255ce3326e41106856aac651095847ca
|
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 sha256:692a0f797f897038f7496e0009df6122cc0ee0f101912e14a0abe5894212c830
|
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:b21eaf8e9910bb63a5bf8ce0c1d15ef6baac6e044f52a2683a4eb92c193f5b57
|
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,
|
@@ -61,13 +61,19 @@
|
|
61 |
"learning_rate": 0.0002,
|
62 |
"loss": 1.1259,
|
63 |
"step": 225
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 25,
|
67 |
"max_steps": 728,
|
68 |
"num_train_epochs": 1,
|
69 |
"save_steps": 25,
|
70 |
-
"total_flos":
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3434065934065934,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
61 |
"learning_rate": 0.0002,
|
62 |
"loss": 1.1259,
|
63 |
"step": 225
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.34,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 0.8211,
|
69 |
+
"step": 250
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 25,
|
73 |
"max_steps": 728,
|
74 |
"num_train_epochs": 1,
|
75 |
"save_steps": 25,
|
76 |
+
"total_flos": 2417765901336576.0,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|