Femboyuwu2000
commited on
Commit
•
4dcea30
1
Parent(s):
9829872
Training in progress, step 18540, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1a89e01452a1f4a07786e13815583895e60d58274777765962f66cefaa61094
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98428bd88fdf622ed27e54ec99ad6aff4a2635b140eb02e69ec3d2b2c59a6ea7
|
3 |
size 7062522
|
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:cac6c71d875067e541674f24a19d324074a4e353704dafdd9d6d6cd6edb82f1a
|
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 sha256:3e0540d1cdcac50331660ae8f79c6485938552612b78b57c5285e9b6f7182b9b
|
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,
|
@@ -6489,6 +6489,13 @@
|
|
6489 |
"learning_rate": 7.145784012061424e-07,
|
6490 |
"loss": 3.5844,
|
6491 |
"step": 18520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6492 |
}
|
6493 |
],
|
6494 |
"logging_steps": 20,
|
@@ -6496,7 +6503,7 @@
|
|
6496 |
"num_input_tokens_seen": 0,
|
6497 |
"num_train_epochs": 1,
|
6498 |
"save_steps": 20,
|
6499 |
-
"total_flos": 4.
|
6500 |
"train_batch_size": 8,
|
6501 |
"trial_name": null,
|
6502 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2623721042129544,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 18540,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
6489 |
"learning_rate": 7.145784012061424e-07,
|
6490 |
"loss": 3.5844,
|
6491 |
"step": 18520
|
6492 |
+
},
|
6493 |
+
{
|
6494 |
+
"epoch": 0.26,
|
6495 |
+
"grad_norm": 22.156579971313477,
|
6496 |
+
"learning_rate": 6.954854106421715e-07,
|
6497 |
+
"loss": 3.5348,
|
6498 |
+
"step": 18540
|
6499 |
}
|
6500 |
],
|
6501 |
"logging_steps": 20,
|
|
|
6503 |
"num_input_tokens_seen": 0,
|
6504 |
"num_train_epochs": 1,
|
6505 |
"save_steps": 20,
|
6506 |
+
"total_flos": 4.028930209962394e+16,
|
6507 |
"train_batch_size": 8,
|
6508 |
"trial_name": null,
|
6509 |
"trial_params": null
|