DuongTrongChi
commited on
Commit
•
28a9548
1
Parent(s):
772c94d
Training in progress, step 226, 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 60010048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c36ed35a85bed4aa0161b43af9120c5e887955ab694498fa4b3d80dbca01e19
|
3 |
size 60010048
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31301554
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36bc18af20bdac3c6cf3467c5bfc67062c1b759a70082c934eb7460fa38cf39f
|
3 |
size 31301554
|
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 sha256:83a8753c40496b1b8f2c1a74d48d5798ac40492d8d426173e910ee96607d424f
|
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,
|
@@ -1582,6 +1582,13 @@
|
|
1582 |
"learning_rate": 3.1496062992125985e-06,
|
1583 |
"loss": 1.1703,
|
1584 |
"step": 225
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1585 |
}
|
1586 |
],
|
1587 |
"logging_steps": 1,
|
@@ -1601,7 +1608,7 @@
|
|
1601 |
"attributes": {}
|
1602 |
}
|
1603 |
},
|
1604 |
-
"total_flos": 4.
|
1605 |
"train_batch_size": 2,
|
1606 |
"trial_name": null,
|
1607 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9920779176240612,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 226,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1582 |
"learning_rate": 3.1496062992125985e-06,
|
1583 |
"loss": 1.1703,
|
1584 |
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.9920779176240612,
|
1588 |
+
"grad_norm": 0.10907357186079025,
|
1589 |
+
"learning_rate": 1.5748031496062992e-06,
|
1590 |
+
"loss": 1.1232,
|
1591 |
+
"step": 226
|
1592 |
}
|
1593 |
],
|
1594 |
"logging_steps": 1,
|
|
|
1608 |
"attributes": {}
|
1609 |
}
|
1610 |
},
|
1611 |
+
"total_flos": 4.342231954207949e+17,
|
1612 |
"train_batch_size": 2,
|
1613 |
"trial_name": null,
|
1614 |
"trial_params": null
|