Femboyuwu2000
commited on
Commit
•
56a21e9
1
Parent(s):
11ac3f0
Training in progress, step 18560, 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:f3ead06ca64c097b468e4848a48dfe313e10e066882daadec4733b392f7d027f
|
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 sha256:7406298021aee6db4278f2ee9543df6b8e99529b9e938b2035da9248006c804c
|
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 sha256:47f34dc38cec7b95d2822f7dac5953198d47e6fd7a3a22a93769d88071de8848
|
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:b581f3feb3bd9bc8f3fdf9e12a5bd849da1459f5b42fe0464a7236b0311e0814
|
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,
|
@@ -6496,6 +6496,13 @@
|
|
6496 |
"learning_rate": 6.954854106421715e-07,
|
6497 |
"loss": 3.5348,
|
6498 |
"step": 18540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6499 |
}
|
6500 |
],
|
6501 |
"logging_steps": 20,
|
@@ -6503,7 +6510,7 @@
|
|
6503 |
"num_input_tokens_seen": 0,
|
6504 |
"num_train_epochs": 1,
|
6505 |
"save_steps": 20,
|
6506 |
-
"total_flos": 4.
|
6507 |
"train_batch_size": 8,
|
6508 |
"trial_name": null,
|
6509 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2626551377665822,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 18560,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
6496 |
"learning_rate": 6.954854106421715e-07,
|
6497 |
"loss": 3.5348,
|
6498 |
"step": 18540
|
6499 |
+
},
|
6500 |
+
{
|
6501 |
+
"epoch": 0.26,
|
6502 |
+
"grad_norm": 28.641721725463867,
|
6503 |
+
"learning_rate": 6.766473629355452e-07,
|
6504 |
+
"loss": 3.5451,
|
6505 |
+
"step": 18560
|
6506 |
}
|
6507 |
],
|
6508 |
"logging_steps": 20,
|
|
|
6510 |
"num_input_tokens_seen": 0,
|
6511 |
"num_train_epochs": 1,
|
6512 |
"save_steps": 20,
|
6513 |
+
"total_flos": 4.033483670627942e+16,
|
6514 |
"train_batch_size": 8,
|
6515 |
"trial_name": null,
|
6516 |
"trial_params": null
|