MohamedAhmedAE
commited on
Commit
•
a0d4891
1
Parent(s):
d19ffb5
Training in progress, step 11600, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b74082b50533e4333b88e29acd5ec8eecf39804ba0295840da3c866df5050cc
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4f867fe76c879c3168a89d511c76e1fa1b26ec6a18b25ec83cf06f006a135e0
|
3 |
size 84581014
|
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 sha256:68341ef163cc0109a8713173add8dbcfd98bf67468e1a64939a8b03523666bf9
|
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:c6fa196d6a1215f8cb5411f481e0c89a67b0e9876e4efe3f1ada6c1ba44ba0a3
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -406,6 +406,13 @@
|
|
406 |
"learning_rate": 1.9999858428217852e-05,
|
407 |
"loss": 1.6124,
|
408 |
"step": 11400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
409 |
}
|
410 |
],
|
411 |
"logging_steps": 200,
|
@@ -413,7 +420,7 @@
|
|
413 |
"num_input_tokens_seen": 0,
|
414 |
"num_train_epochs": 5,
|
415 |
"save_steps": 200,
|
416 |
-
"total_flos": 1.
|
417 |
"train_batch_size": 1,
|
418 |
"trial_name": null,
|
419 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008626491509226999,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 11600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
406 |
"learning_rate": 1.9999858428217852e-05,
|
407 |
"loss": 1.6124,
|
408 |
"step": 11400
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.01,
|
412 |
+
"grad_norm": 3.860379219055176,
|
413 |
+
"learning_rate": 1.9999853411898932e-05,
|
414 |
+
"loss": 1.5097,
|
415 |
+
"step": 11600
|
416 |
}
|
417 |
],
|
418 |
"logging_steps": 200,
|
|
|
420 |
"num_input_tokens_seen": 0,
|
421 |
"num_train_epochs": 5,
|
422 |
"save_steps": 200,
|
423 |
+
"total_flos": 1.5179994612574618e+17,
|
424 |
"train_batch_size": 1,
|
425 |
"trial_name": null,
|
426 |
"trial_params": null
|