Training in progress, step 7700, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da96841ad3583dbc7b4aeacef2e78609769e91da09980acc267dd83a7b6196c
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb06068295e4587ecd5596da997d72f09c52e05bd415dc282b263a1f40aaf4d
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:755c2ca3296f205d4e70e3d45a52af5ad94d49ccccd688a0a5fc8b1f58a58adb
|
| 3 |
size 15006
|
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:f0d54321d467af33867abb91f4d52667bf97d0dec02b52e579c734cda9d42f77
|
| 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": 15.
|
| 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,
|
|
@@ -659,6 +659,13 @@
|
|
| 659 |
"learning_rate": 4.933333333333334e-05,
|
| 660 |
"loss": 1.2353,
|
| 661 |
"step": 7600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 662 |
}
|
| 663 |
],
|
| 664 |
"logging_steps": 100,
|
|
@@ -678,7 +685,7 @@
|
|
| 678 |
"attributes": {}
|
| 679 |
}
|
| 680 |
},
|
| 681 |
-
"total_flos": 1.
|
| 682 |
"train_batch_size": 8,
|
| 683 |
"trial_name": null,
|
| 684 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.397594125917825,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 659 |
"learning_rate": 4.933333333333334e-05,
|
| 660 |
"loss": 1.2353,
|
| 661 |
"step": 7600
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 15.397594125917825,
|
| 665 |
+
"grad_norm": 0.2148446887731552,
|
| 666 |
+
"learning_rate": 4.866666666666667e-05,
|
| 667 |
+
"loss": 1.2372,
|
| 668 |
+
"step": 7700
|
| 669 |
}
|
| 670 |
],
|
| 671 |
"logging_steps": 100,
|
|
|
|
| 685 |
"attributes": {}
|
| 686 |
}
|
| 687 |
},
|
| 688 |
+
"total_flos": 1.2017635428434706e+19,
|
| 689 |
"train_batch_size": 8,
|
| 690 |
"trial_name": null,
|
| 691 |
"trial_params": null
|