Femboyuwu2000
commited on
Commit
•
f46db50
1
Parent(s):
d809bf5
Training in progress, step 40, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa87f9a0408e652f2cd82092e72ff2e96f13f4b26866f97fa213ccfcfd1875e7
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a6d4ad1bdf689ff7848bdd376ed71b9e3153c1275c8fa0f523199c4f6114e48
|
3 |
size 2423738
|
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:d6246f1d35aa1eab9fcd17e8db6c68cde8174cff2dbe036ec556636e6a487b85
|
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:ee69713eca90a4b42f85a38f48c7f4908b9b4f001537f2b81f42ae0dfd8f1388
|
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":
|
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,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 3.3333333333333333e-06,
|
15 |
"loss": 3.6397,
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
@@ -21,7 +28,7 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 1,
|
23 |
"save_steps": 20,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 1,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.1130100472399276e-05,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 3.3333333333333333e-06,
|
15 |
"loss": 3.6397,
|
16 |
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 2.218903064727783,
|
21 |
+
"learning_rate": 6.666666666666667e-06,
|
22 |
+
"loss": 3.6917,
|
23 |
+
"step": 40
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
"save_steps": 20,
|
31 |
+
"total_flos": 279152537333760.0,
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|