Training in progress, step 100, checkpoint
Browse files- .gitattributes +8 -0
- last-checkpoint/optimizer_0/.metadata +0 -0
- last-checkpoint/optimizer_0/__0_0.distcp +3 -0
- last-checkpoint/optimizer_0/__1_0.distcp +3 -0
- last-checkpoint/optimizer_0/__2_0.distcp +3 -0
- last-checkpoint/optimizer_0/__3_0.distcp +3 -0
- last-checkpoint/pytorch_model_fsdp_0/.metadata +0 -0
- last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp +3 -0
- last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp +3 -0
- last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp +3 -0
- last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +805 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
last-checkpoint/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
last-checkpoint/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
last-checkpoint/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
last-checkpoint/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
last-checkpoint/optimizer_0/.metadata
ADDED
|
Binary file (369 kB). View file
|
|
|
last-checkpoint/optimizer_0/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4f400f9c8252c3907336d7e343409569f9416a7811ccee54ea90cd6e1487760
|
| 3 |
+
size 27566236
|
last-checkpoint/optimizer_0/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a321ddd94525214b01034b7dd5c829c8f5c774110e53a835f44598d6f6718356
|
| 3 |
+
size 27630900
|
last-checkpoint/optimizer_0/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e69a575ce407be18a88352ce2fba384077c65ac9c525b4ba7510629a05d3142
|
| 3 |
+
size 27622392
|
last-checkpoint/optimizer_0/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d462087a031a3e8fbfa21af32693f98dca8bf9ef1a4cb3941a166085c457e65d
|
| 3 |
+
size 27622392
|
last-checkpoint/pytorch_model_fsdp_0/.metadata
ADDED
|
Binary file (135 kB). View file
|
|
|
last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4bbfa20dabe10a871576b86fe5f5a535c6320c9d704ffd31e930374052613e3
|
| 3 |
+
size 13782528
|
last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:257c58c2297733667c9c0c814d11bc07796191cce00534cb5921f30cdfc776f4
|
| 3 |
+
size 13782528
|
last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be68455e2498c25bc93148836614c38b4a427e34fcb5d96afd9877503ec371ef
|
| 3 |
+
size 13782528
|
last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97113445bb35120c9d888adbfc2838d204231a098490792274dbfe48ae2d9c0e
|
| 3 |
+
size 13782528
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e4ead7a9090a756b7fd44dcd84a0128fc3e073a0556a840016ee79c554e0b80
|
| 3 |
+
size 14960
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45746def86d7a8510cabcc16531091de91eaf8f9bdd39d725096005db8ee2a1a
|
| 3 |
+
size 14960
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6f6f333666bf8e00dd613a01077ed8920391e394339b3ae8687718cf5f788c2
|
| 3 |
+
size 14960
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:111993f0c7702ea7b86533de3410a44aff0126390ec01a74930984eb2b182a72
|
| 3 |
+
size 14960
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a104c065133d085f18edd3e5b4057dbd861eb3e31968053f10edac0d68e4236e
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,805 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.28735632183908044,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0,
|
| 13 |
+
"eval_accuracy": 0.7376237623762376,
|
| 14 |
+
"eval_f1": 0.11666666666666667,
|
| 15 |
+
"eval_loss": 0.595770537853241,
|
| 16 |
+
"eval_precision": 0.5,
|
| 17 |
+
"eval_recall": 0.0660377358490566,
|
| 18 |
+
"eval_runtime": 16.1893,
|
| 19 |
+
"eval_samples_per_second": 6.548,
|
| 20 |
+
"eval_steps_per_second": 0.247,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0028735632183908046,
|
| 25 |
+
"grad_norm": 1.7269402742385864,
|
| 26 |
+
"learning_rate": 5.714285714285715e-07,
|
| 27 |
+
"loss": 0.7755,
|
| 28 |
+
"step": 1
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.005747126436781609,
|
| 32 |
+
"grad_norm": 1.7528263330459595,
|
| 33 |
+
"learning_rate": 1.142857142857143e-06,
|
| 34 |
+
"loss": 0.7738,
|
| 35 |
+
"step": 2
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.008620689655172414,
|
| 39 |
+
"grad_norm": 1.903218150138855,
|
| 40 |
+
"learning_rate": 1.7142857142857145e-06,
|
| 41 |
+
"loss": 0.7635,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.011494252873563218,
|
| 46 |
+
"grad_norm": 2.011042833328247,
|
| 47 |
+
"learning_rate": 2.285714285714286e-06,
|
| 48 |
+
"loss": 0.7872,
|
| 49 |
+
"step": 4
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.014367816091954023,
|
| 53 |
+
"grad_norm": 1.8846079111099243,
|
| 54 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 55 |
+
"loss": 0.7811,
|
| 56 |
+
"step": 5
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.017241379310344827,
|
| 60 |
+
"grad_norm": 1.7371026277542114,
|
| 61 |
+
"learning_rate": 3.428571428571429e-06,
|
| 62 |
+
"loss": 0.7517,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.020114942528735632,
|
| 67 |
+
"grad_norm": 1.8430122137069702,
|
| 68 |
+
"learning_rate": 4.000000000000001e-06,
|
| 69 |
+
"loss": 0.7732,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.022988505747126436,
|
| 74 |
+
"grad_norm": 1.683440923690796,
|
| 75 |
+
"learning_rate": 4.571428571428572e-06,
|
| 76 |
+
"loss": 0.738,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.02586206896551724,
|
| 81 |
+
"grad_norm": 1.8083072900772095,
|
| 82 |
+
"learning_rate": 5.142857142857142e-06,
|
| 83 |
+
"loss": 0.739,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.028735632183908046,
|
| 88 |
+
"grad_norm": 1.8509185314178467,
|
| 89 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 90 |
+
"loss": 0.7536,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.031609195402298854,
|
| 95 |
+
"grad_norm": 1.948458194732666,
|
| 96 |
+
"learning_rate": 6.285714285714286e-06,
|
| 97 |
+
"loss": 0.7414,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.034482758620689655,
|
| 102 |
+
"grad_norm": 1.6882693767547607,
|
| 103 |
+
"learning_rate": 6.857142857142858e-06,
|
| 104 |
+
"loss": 0.7356,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.03735632183908046,
|
| 109 |
+
"grad_norm": 1.7302439212799072,
|
| 110 |
+
"learning_rate": 7.428571428571429e-06,
|
| 111 |
+
"loss": 0.727,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.040229885057471264,
|
| 116 |
+
"grad_norm": 1.6159391403198242,
|
| 117 |
+
"learning_rate": 8.000000000000001e-06,
|
| 118 |
+
"loss": 0.7069,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.04310344827586207,
|
| 123 |
+
"grad_norm": 1.63016939163208,
|
| 124 |
+
"learning_rate": 8.571428571428571e-06,
|
| 125 |
+
"loss": 0.6835,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.04597701149425287,
|
| 130 |
+
"grad_norm": 1.506463646888733,
|
| 131 |
+
"learning_rate": 9.142857142857144e-06,
|
| 132 |
+
"loss": 0.7347,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.04885057471264368,
|
| 137 |
+
"grad_norm": 1.412893295288086,
|
| 138 |
+
"learning_rate": 9.714285714285715e-06,
|
| 139 |
+
"loss": 0.702,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.05172413793103448,
|
| 144 |
+
"grad_norm": 1.5896869897842407,
|
| 145 |
+
"learning_rate": 1.0285714285714285e-05,
|
| 146 |
+
"loss": 0.6948,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.05459770114942529,
|
| 151 |
+
"grad_norm": 1.4004888534545898,
|
| 152 |
+
"learning_rate": 1.0857142857142858e-05,
|
| 153 |
+
"loss": 0.6604,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.05747126436781609,
|
| 158 |
+
"grad_norm": 1.3640953302383423,
|
| 159 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 160 |
+
"loss": 0.6819,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.05747126436781609,
|
| 165 |
+
"eval_accuracy": 0.745049504950495,
|
| 166 |
+
"eval_f1": 0.13445378151260504,
|
| 167 |
+
"eval_loss": 0.569399356842041,
|
| 168 |
+
"eval_precision": 0.6153846153846154,
|
| 169 |
+
"eval_recall": 0.07547169811320754,
|
| 170 |
+
"eval_runtime": 17.731,
|
| 171 |
+
"eval_samples_per_second": 5.978,
|
| 172 |
+
"eval_steps_per_second": 0.226,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.0603448275862069,
|
| 177 |
+
"grad_norm": 1.487462043762207,
|
| 178 |
+
"learning_rate": 1.2e-05,
|
| 179 |
+
"loss": 0.6763,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.06321839080459771,
|
| 184 |
+
"grad_norm": 1.291784405708313,
|
| 185 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 186 |
+
"loss": 0.6705,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.06609195402298851,
|
| 191 |
+
"grad_norm": 1.1527869701385498,
|
| 192 |
+
"learning_rate": 1.3142857142857145e-05,
|
| 193 |
+
"loss": 0.6183,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.06896551724137931,
|
| 198 |
+
"grad_norm": 1.1266508102416992,
|
| 199 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 200 |
+
"loss": 0.609,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.07183908045977011,
|
| 205 |
+
"grad_norm": 1.2343026399612427,
|
| 206 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 207 |
+
"loss": 0.619,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.07471264367816093,
|
| 212 |
+
"grad_norm": 1.1558549404144287,
|
| 213 |
+
"learning_rate": 1.4857142857142858e-05,
|
| 214 |
+
"loss": 0.6031,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.07758620689655173,
|
| 219 |
+
"grad_norm": 1.0646226406097412,
|
| 220 |
+
"learning_rate": 1.542857142857143e-05,
|
| 221 |
+
"loss": 0.584,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.08045977011494253,
|
| 226 |
+
"grad_norm": 0.975098729133606,
|
| 227 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 228 |
+
"loss": 0.5594,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.08333333333333333,
|
| 233 |
+
"grad_norm": 1.0657261610031128,
|
| 234 |
+
"learning_rate": 1.6571428571428574e-05,
|
| 235 |
+
"loss": 0.567,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.08620689655172414,
|
| 240 |
+
"grad_norm": 0.872745156288147,
|
| 241 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 242 |
+
"loss": 0.5435,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.08908045977011494,
|
| 247 |
+
"grad_norm": 0.8025686144828796,
|
| 248 |
+
"learning_rate": 1.7714285714285717e-05,
|
| 249 |
+
"loss": 0.537,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.09195402298850575,
|
| 254 |
+
"grad_norm": 0.8637747764587402,
|
| 255 |
+
"learning_rate": 1.8285714285714288e-05,
|
| 256 |
+
"loss": 0.541,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.09482758620689655,
|
| 261 |
+
"grad_norm": 1.0375990867614746,
|
| 262 |
+
"learning_rate": 1.885714285714286e-05,
|
| 263 |
+
"loss": 0.5199,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.09770114942528736,
|
| 268 |
+
"grad_norm": 0.9441830515861511,
|
| 269 |
+
"learning_rate": 1.942857142857143e-05,
|
| 270 |
+
"loss": 0.5388,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.10057471264367816,
|
| 275 |
+
"grad_norm": 0.8663190603256226,
|
| 276 |
+
"learning_rate": 2e-05,
|
| 277 |
+
"loss": 0.5268,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.10344827586206896,
|
| 282 |
+
"grad_norm": 0.9546361565589905,
|
| 283 |
+
"learning_rate": 1.9999496293646753e-05,
|
| 284 |
+
"loss": 0.5381,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.10632183908045977,
|
| 289 |
+
"grad_norm": 0.7847493290901184,
|
| 290 |
+
"learning_rate": 1.999798522533102e-05,
|
| 291 |
+
"loss": 0.5131,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.10919540229885058,
|
| 296 |
+
"grad_norm": 0.8559457659721375,
|
| 297 |
+
"learning_rate": 1.9995466947279753e-05,
|
| 298 |
+
"loss": 0.4771,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.11206896551724138,
|
| 303 |
+
"grad_norm": 0.9539210796356201,
|
| 304 |
+
"learning_rate": 1.9991941713187477e-05,
|
| 305 |
+
"loss": 0.4833,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.11494252873563218,
|
| 310 |
+
"grad_norm": 1.2878869771957397,
|
| 311 |
+
"learning_rate": 1.9987409878190752e-05,
|
| 312 |
+
"loss": 0.4789,
|
| 313 |
+
"step": 40
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.11494252873563218,
|
| 317 |
+
"eval_accuracy": 0.754950495049505,
|
| 318 |
+
"eval_f1": 0.5857740585774058,
|
| 319 |
+
"eval_loss": 0.47763171792030334,
|
| 320 |
+
"eval_precision": 0.5263157894736842,
|
| 321 |
+
"eval_recall": 0.660377358490566,
|
| 322 |
+
"eval_runtime": 17.3231,
|
| 323 |
+
"eval_samples_per_second": 6.119,
|
| 324 |
+
"eval_steps_per_second": 0.231,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.11781609195402298,
|
| 329 |
+
"grad_norm": 1.0973199605941772,
|
| 330 |
+
"learning_rate": 1.99818718988324e-05,
|
| 331 |
+
"loss": 0.4739,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1206896551724138,
|
| 336 |
+
"grad_norm": 0.8685905337333679,
|
| 337 |
+
"learning_rate": 1.9975328333015497e-05,
|
| 338 |
+
"loss": 0.4639,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1235632183908046,
|
| 343 |
+
"grad_norm": 0.7956727147102356,
|
| 344 |
+
"learning_rate": 1.9967779839947172e-05,
|
| 345 |
+
"loss": 0.475,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.12643678160919541,
|
| 350 |
+
"grad_norm": 0.9125760197639465,
|
| 351 |
+
"learning_rate": 1.9959227180072216e-05,
|
| 352 |
+
"loss": 0.4166,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.12931034482758622,
|
| 357 |
+
"grad_norm": 0.8798947930335999,
|
| 358 |
+
"learning_rate": 1.9949671214996448e-05,
|
| 359 |
+
"loss": 0.4689,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.13218390804597702,
|
| 364 |
+
"grad_norm": 0.7233872413635254,
|
| 365 |
+
"learning_rate": 1.993911290739993e-05,
|
| 366 |
+
"loss": 0.4416,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.13505747126436782,
|
| 371 |
+
"grad_norm": 0.7250576615333557,
|
| 372 |
+
"learning_rate": 1.992755332093999e-05,
|
| 373 |
+
"loss": 0.3968,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.13793103448275862,
|
| 378 |
+
"grad_norm": 1.153190016746521,
|
| 379 |
+
"learning_rate": 1.9914993620144055e-05,
|
| 380 |
+
"loss": 0.4316,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.14080459770114942,
|
| 385 |
+
"grad_norm": 0.8170616626739502,
|
| 386 |
+
"learning_rate": 1.990143507029234e-05,
|
| 387 |
+
"loss": 0.4398,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.14367816091954022,
|
| 392 |
+
"grad_norm": 0.8207669854164124,
|
| 393 |
+
"learning_rate": 1.9886879037290385e-05,
|
| 394 |
+
"loss": 0.4042,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.14655172413793102,
|
| 399 |
+
"grad_norm": 0.7794085144996643,
|
| 400 |
+
"learning_rate": 1.9871326987531453e-05,
|
| 401 |
+
"loss": 0.3656,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.14942528735632185,
|
| 406 |
+
"grad_norm": 0.8606981635093689,
|
| 407 |
+
"learning_rate": 1.98547804877488e-05,
|
| 408 |
+
"loss": 0.3982,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.15229885057471265,
|
| 413 |
+
"grad_norm": 0.8829456567764282,
|
| 414 |
+
"learning_rate": 1.983724120485783e-05,
|
| 415 |
+
"loss": 0.4397,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.15517241379310345,
|
| 420 |
+
"grad_norm": 0.6965311765670776,
|
| 421 |
+
"learning_rate": 1.9818710905788195e-05,
|
| 422 |
+
"loss": 0.3995,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.15804597701149425,
|
| 427 |
+
"grad_norm": 1.190281867980957,
|
| 428 |
+
"learning_rate": 1.9799191457305767e-05,
|
| 429 |
+
"loss": 0.412,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.16091954022988506,
|
| 434 |
+
"grad_norm": 1.1659263372421265,
|
| 435 |
+
"learning_rate": 1.977868482582459e-05,
|
| 436 |
+
"loss": 0.3629,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.16379310344827586,
|
| 441 |
+
"grad_norm": 0.9981995820999146,
|
| 442 |
+
"learning_rate": 1.9757193077208776e-05,
|
| 443 |
+
"loss": 0.4309,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.16666666666666666,
|
| 448 |
+
"grad_norm": 0.9343249201774597,
|
| 449 |
+
"learning_rate": 1.9734718376564386e-05,
|
| 450 |
+
"loss": 0.3732,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.16954022988505746,
|
| 455 |
+
"grad_norm": 1.1614587306976318,
|
| 456 |
+
"learning_rate": 1.9711262988021322e-05,
|
| 457 |
+
"loss": 0.4035,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.1724137931034483,
|
| 462 |
+
"grad_norm": 1.0494896173477173,
|
| 463 |
+
"learning_rate": 1.968682927450523e-05,
|
| 464 |
+
"loss": 0.4108,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.1724137931034483,
|
| 469 |
+
"eval_accuracy": 0.8044554455445545,
|
| 470 |
+
"eval_f1": 0.6255924170616114,
|
| 471 |
+
"eval_loss": 0.40430542826652527,
|
| 472 |
+
"eval_precision": 0.6285714285714286,
|
| 473 |
+
"eval_recall": 0.6226415094339622,
|
| 474 |
+
"eval_runtime": 17.0915,
|
| 475 |
+
"eval_samples_per_second": 6.202,
|
| 476 |
+
"eval_steps_per_second": 0.234,
|
| 477 |
+
"step": 60
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.1752873563218391,
|
| 481 |
+
"grad_norm": 0.9192970991134644,
|
| 482 |
+
"learning_rate": 1.9661419697499455e-05,
|
| 483 |
+
"loss": 0.3989,
|
| 484 |
+
"step": 61
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.1781609195402299,
|
| 488 |
+
"grad_norm": 0.999806821346283,
|
| 489 |
+
"learning_rate": 1.9635036816797072e-05,
|
| 490 |
+
"loss": 0.4099,
|
| 491 |
+
"step": 62
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.1810344827586207,
|
| 495 |
+
"grad_norm": 1.073845624923706,
|
| 496 |
+
"learning_rate": 1.960768329024301e-05,
|
| 497 |
+
"loss": 0.3862,
|
| 498 |
+
"step": 63
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.1839080459770115,
|
| 502 |
+
"grad_norm": 1.1665489673614502,
|
| 503 |
+
"learning_rate": 1.957936187346628e-05,
|
| 504 |
+
"loss": 0.3551,
|
| 505 |
+
"step": 64
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.1867816091954023,
|
| 509 |
+
"grad_norm": 1.0729217529296875,
|
| 510 |
+
"learning_rate": 1.955007541960241e-05,
|
| 511 |
+
"loss": 0.4163,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.1896551724137931,
|
| 516 |
+
"grad_norm": 1.194051742553711,
|
| 517 |
+
"learning_rate": 1.9519826879005964e-05,
|
| 518 |
+
"loss": 0.4146,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.1925287356321839,
|
| 523 |
+
"grad_norm": 1.5440024137496948,
|
| 524 |
+
"learning_rate": 1.948861929895336e-05,
|
| 525 |
+
"loss": 0.4091,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.19540229885057472,
|
| 530 |
+
"grad_norm": 1.1414806842803955,
|
| 531 |
+
"learning_rate": 1.945645582333587e-05,
|
| 532 |
+
"loss": 0.3836,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.19827586206896552,
|
| 537 |
+
"grad_norm": 1.4426944255828857,
|
| 538 |
+
"learning_rate": 1.9423339692342885e-05,
|
| 539 |
+
"loss": 0.3825,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.20114942528735633,
|
| 544 |
+
"grad_norm": 1.102241039276123,
|
| 545 |
+
"learning_rate": 1.9389274242135528e-05,
|
| 546 |
+
"loss": 0.355,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.20402298850574713,
|
| 551 |
+
"grad_norm": 1.8680758476257324,
|
| 552 |
+
"learning_rate": 1.9354262904510544e-05,
|
| 553 |
+
"loss": 0.407,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.20689655172413793,
|
| 558 |
+
"grad_norm": 1.2773621082305908,
|
| 559 |
+
"learning_rate": 1.9318309206554567e-05,
|
| 560 |
+
"loss": 0.35,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.20977011494252873,
|
| 565 |
+
"grad_norm": 1.063806414604187,
|
| 566 |
+
"learning_rate": 1.9281416770288806e-05,
|
| 567 |
+
"loss": 0.3602,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.21264367816091953,
|
| 572 |
+
"grad_norm": 1.1581475734710693,
|
| 573 |
+
"learning_rate": 1.924358931230418e-05,
|
| 574 |
+
"loss": 0.345,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.21551724137931033,
|
| 579 |
+
"grad_norm": 1.524601697921753,
|
| 580 |
+
"learning_rate": 1.920483064338687e-05,
|
| 581 |
+
"loss": 0.3571,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.21839080459770116,
|
| 586 |
+
"grad_norm": 1.7578339576721191,
|
| 587 |
+
"learning_rate": 1.9165144668134426e-05,
|
| 588 |
+
"loss": 0.3739,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.22126436781609196,
|
| 593 |
+
"grad_norm": 2.7177462577819824,
|
| 594 |
+
"learning_rate": 1.9124535384562423e-05,
|
| 595 |
+
"loss": 0.3796,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.22413793103448276,
|
| 600 |
+
"grad_norm": 2.676715850830078,
|
| 601 |
+
"learning_rate": 1.9083006883701688e-05,
|
| 602 |
+
"loss": 0.3738,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.22701149425287356,
|
| 607 |
+
"grad_norm": 1.5852210521697998,
|
| 608 |
+
"learning_rate": 1.904056334918617e-05,
|
| 609 |
+
"loss": 0.3082,
|
| 610 |
+
"step": 79
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.22988505747126436,
|
| 614 |
+
"grad_norm": 1.1979814767837524,
|
| 615 |
+
"learning_rate": 1.8997209056831462e-05,
|
| 616 |
+
"loss": 0.3486,
|
| 617 |
+
"step": 80
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.22988505747126436,
|
| 621 |
+
"eval_accuracy": 0.8366336633663366,
|
| 622 |
+
"eval_f1": 0.6826923076923077,
|
| 623 |
+
"eval_loss": 0.37516123056411743,
|
| 624 |
+
"eval_precision": 0.696078431372549,
|
| 625 |
+
"eval_recall": 0.6698113207547169,
|
| 626 |
+
"eval_runtime": 16.3429,
|
| 627 |
+
"eval_samples_per_second": 6.486,
|
| 628 |
+
"eval_steps_per_second": 0.245,
|
| 629 |
+
"step": 80
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.23275862068965517,
|
| 633 |
+
"grad_norm": 1.432535171508789,
|
| 634 |
+
"learning_rate": 1.8952948374204066e-05,
|
| 635 |
+
"loss": 0.4083,
|
| 636 |
+
"step": 81
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.23563218390804597,
|
| 640 |
+
"grad_norm": 1.1334880590438843,
|
| 641 |
+
"learning_rate": 1.8907785760181392e-05,
|
| 642 |
+
"loss": 0.3422,
|
| 643 |
+
"step": 82
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.23850574712643677,
|
| 647 |
+
"grad_norm": 1.8673022985458374,
|
| 648 |
+
"learning_rate": 1.8861725764502557e-05,
|
| 649 |
+
"loss": 0.3871,
|
| 650 |
+
"step": 83
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.2413793103448276,
|
| 654 |
+
"grad_norm": 1.3424856662750244,
|
| 655 |
+
"learning_rate": 1.881477302731006e-05,
|
| 656 |
+
"loss": 0.3595,
|
| 657 |
+
"step": 84
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.2442528735632184,
|
| 661 |
+
"grad_norm": 1.7336989641189575,
|
| 662 |
+
"learning_rate": 1.87669322786823e-05,
|
| 663 |
+
"loss": 0.3578,
|
| 664 |
+
"step": 85
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.2471264367816092,
|
| 668 |
+
"grad_norm": 1.203000545501709,
|
| 669 |
+
"learning_rate": 1.8718208338157082e-05,
|
| 670 |
+
"loss": 0.3601,
|
| 671 |
+
"step": 86
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.25,
|
| 675 |
+
"grad_norm": 1.185094952583313,
|
| 676 |
+
"learning_rate": 1.866860611424609e-05,
|
| 677 |
+
"loss": 0.3307,
|
| 678 |
+
"step": 87
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.25287356321839083,
|
| 682 |
+
"grad_norm": 2.083695888519287,
|
| 683 |
+
"learning_rate": 1.8618130603940386e-05,
|
| 684 |
+
"loss": 0.3123,
|
| 685 |
+
"step": 88
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.2557471264367816,
|
| 689 |
+
"grad_norm": 1.6941533088684082,
|
| 690 |
+
"learning_rate": 1.856678689220701e-05,
|
| 691 |
+
"loss": 0.3294,
|
| 692 |
+
"step": 89
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.25862068965517243,
|
| 696 |
+
"grad_norm": 2.76645565032959,
|
| 697 |
+
"learning_rate": 1.851458015147673e-05,
|
| 698 |
+
"loss": 0.3773,
|
| 699 |
+
"step": 90
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.2614942528735632,
|
| 703 |
+
"grad_norm": 1.9406121969223022,
|
| 704 |
+
"learning_rate": 1.846151564112294e-05,
|
| 705 |
+
"loss": 0.309,
|
| 706 |
+
"step": 91
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.26436781609195403,
|
| 710 |
+
"grad_norm": 1.4476113319396973,
|
| 711 |
+
"learning_rate": 1.840759870693184e-05,
|
| 712 |
+
"loss": 0.3724,
|
| 713 |
+
"step": 92
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.2672413793103448,
|
| 717 |
+
"grad_norm": 1.4683369398117065,
|
| 718 |
+
"learning_rate": 1.8352834780563888e-05,
|
| 719 |
+
"loss": 0.3712,
|
| 720 |
+
"step": 93
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.27011494252873564,
|
| 724 |
+
"grad_norm": 1.5984596014022827,
|
| 725 |
+
"learning_rate": 1.8297229379006614e-05,
|
| 726 |
+
"loss": 0.277,
|
| 727 |
+
"step": 94
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.27298850574712646,
|
| 731 |
+
"grad_norm": 1.4368345737457275,
|
| 732 |
+
"learning_rate": 1.8240788104018824e-05,
|
| 733 |
+
"loss": 0.337,
|
| 734 |
+
"step": 95
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.27586206896551724,
|
| 738 |
+
"grad_norm": 3.34250545501709,
|
| 739 |
+
"learning_rate": 1.8183516641566278e-05,
|
| 740 |
+
"loss": 0.315,
|
| 741 |
+
"step": 96
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.27873563218390807,
|
| 745 |
+
"grad_norm": 1.4906728267669678,
|
| 746 |
+
"learning_rate": 1.8125420761248878e-05,
|
| 747 |
+
"loss": 0.3778,
|
| 748 |
+
"step": 97
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.28160919540229884,
|
| 752 |
+
"grad_norm": 1.4306960105895996,
|
| 753 |
+
"learning_rate": 1.806650631571943e-05,
|
| 754 |
+
"loss": 0.354,
|
| 755 |
+
"step": 98
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.28448275862068967,
|
| 759 |
+
"grad_norm": 1.657739281654358,
|
| 760 |
+
"learning_rate": 1.8006779240094024e-05,
|
| 761 |
+
"loss": 0.2976,
|
| 762 |
+
"step": 99
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.28735632183908044,
|
| 766 |
+
"grad_norm": 1.2605433464050293,
|
| 767 |
+
"learning_rate": 1.7946245551354156e-05,
|
| 768 |
+
"loss": 0.2936,
|
| 769 |
+
"step": 100
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.28735632183908044,
|
| 773 |
+
"eval_accuracy": 0.8465346534653465,
|
| 774 |
+
"eval_f1": 0.7047619047619048,
|
| 775 |
+
"eval_loss": 0.36498525738716125,
|
| 776 |
+
"eval_precision": 0.7115384615384616,
|
| 777 |
+
"eval_recall": 0.6981132075471698,
|
| 778 |
+
"eval_runtime": 16.9232,
|
| 779 |
+
"eval_samples_per_second": 6.264,
|
| 780 |
+
"eval_steps_per_second": 0.236,
|
| 781 |
+
"step": 100
|
| 782 |
+
}
|
| 783 |
+
],
|
| 784 |
+
"logging_steps": 1,
|
| 785 |
+
"max_steps": 348,
|
| 786 |
+
"num_input_tokens_seen": 0,
|
| 787 |
+
"num_train_epochs": 1,
|
| 788 |
+
"save_steps": 100,
|
| 789 |
+
"stateful_callbacks": {
|
| 790 |
+
"TrainerControl": {
|
| 791 |
+
"args": {
|
| 792 |
+
"should_epoch_stop": false,
|
| 793 |
+
"should_evaluate": false,
|
| 794 |
+
"should_log": false,
|
| 795 |
+
"should_save": true,
|
| 796 |
+
"should_training_stop": false
|
| 797 |
+
},
|
| 798 |
+
"attributes": {}
|
| 799 |
+
}
|
| 800 |
+
},
|
| 801 |
+
"total_flos": 3.1445919459180544e+16,
|
| 802 |
+
"train_batch_size": 8,
|
| 803 |
+
"trial_name": null,
|
| 804 |
+
"trial_params": null
|
| 805 |
+
}
|