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:ff052676913de0926615cb1f2b71af95e015945f2a54a0470098476fd22fb5f9
|
| 3 |
+
size 13934748
|
last-checkpoint/optimizer_0/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95417982dd0c51b14604eaa0aff61973b18e62e3a2b70afb785a559085acf026
|
| 3 |
+
size 13999412
|
last-checkpoint/optimizer_0/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:521840236f819147dd8863a7e29e2b411b5a26067409ee98e9abf463f06eb9e6
|
| 3 |
+
size 13990904
|
last-checkpoint/optimizer_0/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:646c8474af8f5ba95be0aca0fa2dfa998e25f6eaa8703f836fa6d1fa8d4e4cbf
|
| 3 |
+
size 13990904
|
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 sha256:920847f1cff8fc1527a736b7c4b551adfb32f773a942bef70a4b46cd67738e14
|
| 3 |
+
size 6966784
|
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 sha256:64bd405e5019796ba13caf7d1f804b8b8d337ad50283bb455ff335b979782437
|
| 3 |
+
size 6966784
|
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 sha256:1a2a96245294c4e0e2161bf1bd1203d983c92d8534ba9d65758e0c41cdb08c4d
|
| 3 |
+
size 6966784
|
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 sha256:2ab3ce924bf5586c0cd87abb18d5d2a7a88a5c6553011aeb4d9923bb81ce2d78
|
| 3 |
+
size 6966784
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9a1f1e453a43f83aa53b56d67647ccab7a6102d29ca677d252db57c6d84112
|
| 3 |
+
size 15088
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f37b096e91cd08927cf4ae4abd0d391ce5ada891c3fc1b2de21881502f3589eb
|
| 3 |
+
size 15088
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e41f09d05169607eee8dce8b84f8f78818000c06c0c89cf2ba601fd24a650bd
|
| 3 |
+
size 15088
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418fcb9eed9f4b34f4356e235c9f424e1c20f8f4d59e678e6ebeeb8a33e83523
|
| 3 |
+
size 15088
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afecba1fad91cfcc309b7789abc8c48e2a84100fb8c489eb3925241bd70b9c9d
|
| 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": 0.12886597938144329,
|
| 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": 0.9369414101290964,
|
| 14 |
+
"eval_f1": 0.18064516129032257,
|
| 15 |
+
"eval_loss": 0.32557418942451477,
|
| 16 |
+
"eval_precision": 0.14285714285714285,
|
| 17 |
+
"eval_recall": 0.24561403508771928,
|
| 18 |
+
"eval_runtime": 85.4903,
|
| 19 |
+
"eval_samples_per_second": 5.322,
|
| 20 |
+
"eval_steps_per_second": 0.175,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.001288659793814433,
|
| 25 |
+
"grad_norm": 4.25856876373291,
|
| 26 |
+
"learning_rate": 2.564102564102564e-07,
|
| 27 |
+
"loss": 0.5948,
|
| 28 |
+
"step": 1
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.002577319587628866,
|
| 32 |
+
"grad_norm": 3.965942144393921,
|
| 33 |
+
"learning_rate": 5.128205128205128e-07,
|
| 34 |
+
"loss": 0.5193,
|
| 35 |
+
"step": 2
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.003865979381443299,
|
| 39 |
+
"grad_norm": 4.168001174926758,
|
| 40 |
+
"learning_rate": 7.692307692307694e-07,
|
| 41 |
+
"loss": 0.5634,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.005154639175257732,
|
| 46 |
+
"grad_norm": 3.510260820388794,
|
| 47 |
+
"learning_rate": 1.0256410256410257e-06,
|
| 48 |
+
"loss": 0.5141,
|
| 49 |
+
"step": 4
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.006443298969072165,
|
| 53 |
+
"grad_norm": 3.4605071544647217,
|
| 54 |
+
"learning_rate": 1.282051282051282e-06,
|
| 55 |
+
"loss": 0.4554,
|
| 56 |
+
"step": 5
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.007731958762886598,
|
| 60 |
+
"grad_norm": 3.9275991916656494,
|
| 61 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 62 |
+
"loss": 0.5348,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.00902061855670103,
|
| 67 |
+
"grad_norm": 3.4560351371765137,
|
| 68 |
+
"learning_rate": 1.794871794871795e-06,
|
| 69 |
+
"loss": 0.4784,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.010309278350515464,
|
| 74 |
+
"grad_norm": 3.93674373626709,
|
| 75 |
+
"learning_rate": 2.0512820512820513e-06,
|
| 76 |
+
"loss": 0.5567,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.011597938144329897,
|
| 81 |
+
"grad_norm": 3.893137216567993,
|
| 82 |
+
"learning_rate": 2.307692307692308e-06,
|
| 83 |
+
"loss": 0.5175,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.01288659793814433,
|
| 88 |
+
"grad_norm": 3.8920130729675293,
|
| 89 |
+
"learning_rate": 2.564102564102564e-06,
|
| 90 |
+
"loss": 0.5187,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.014175257731958763,
|
| 95 |
+
"grad_norm": 4.420604228973389,
|
| 96 |
+
"learning_rate": 2.8205128205128207e-06,
|
| 97 |
+
"loss": 0.5764,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.015463917525773196,
|
| 102 |
+
"grad_norm": 3.916328191757202,
|
| 103 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 104 |
+
"loss": 0.5103,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.01675257731958763,
|
| 109 |
+
"grad_norm": 3.8103713989257812,
|
| 110 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 111 |
+
"loss": 0.5271,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.01804123711340206,
|
| 116 |
+
"grad_norm": 3.2343883514404297,
|
| 117 |
+
"learning_rate": 3.58974358974359e-06,
|
| 118 |
+
"loss": 0.4981,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.019329896907216496,
|
| 123 |
+
"grad_norm": 3.556180953979492,
|
| 124 |
+
"learning_rate": 3.846153846153847e-06,
|
| 125 |
+
"loss": 0.472,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.020618556701030927,
|
| 130 |
+
"grad_norm": 3.4665050506591797,
|
| 131 |
+
"learning_rate": 4.102564102564103e-06,
|
| 132 |
+
"loss": 0.463,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.02190721649484536,
|
| 137 |
+
"grad_norm": 3.6362946033477783,
|
| 138 |
+
"learning_rate": 4.358974358974359e-06,
|
| 139 |
+
"loss": 0.5137,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.023195876288659795,
|
| 144 |
+
"grad_norm": 3.6967854499816895,
|
| 145 |
+
"learning_rate": 4.615384615384616e-06,
|
| 146 |
+
"loss": 0.5288,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.024484536082474227,
|
| 151 |
+
"grad_norm": 3.482665538787842,
|
| 152 |
+
"learning_rate": 4.871794871794872e-06,
|
| 153 |
+
"loss": 0.4946,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.02577319587628866,
|
| 158 |
+
"grad_norm": 3.539522647857666,
|
| 159 |
+
"learning_rate": 5.128205128205128e-06,
|
| 160 |
+
"loss": 0.4529,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.02577319587628866,
|
| 165 |
+
"eval_accuracy": 0.9483614697120158,
|
| 166 |
+
"eval_f1": 0.16129032258064516,
|
| 167 |
+
"eval_loss": 0.28827786445617676,
|
| 168 |
+
"eval_precision": 0.14925373134328357,
|
| 169 |
+
"eval_recall": 0.17543859649122806,
|
| 170 |
+
"eval_runtime": 85.2267,
|
| 171 |
+
"eval_samples_per_second": 5.339,
|
| 172 |
+
"eval_steps_per_second": 0.176,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.027061855670103094,
|
| 177 |
+
"grad_norm": 3.701735496520996,
|
| 178 |
+
"learning_rate": 5.384615384615385e-06,
|
| 179 |
+
"loss": 0.457,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.028350515463917526,
|
| 184 |
+
"grad_norm": 3.351079225540161,
|
| 185 |
+
"learning_rate": 5.641025641025641e-06,
|
| 186 |
+
"loss": 0.4086,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.029639175257731958,
|
| 191 |
+
"grad_norm": 3.3507163524627686,
|
| 192 |
+
"learning_rate": 5.897435897435898e-06,
|
| 193 |
+
"loss": 0.3953,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.030927835051546393,
|
| 198 |
+
"grad_norm": 4.022622108459473,
|
| 199 |
+
"learning_rate": 6.153846153846155e-06,
|
| 200 |
+
"loss": 0.4388,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.03221649484536082,
|
| 205 |
+
"grad_norm": 3.652367353439331,
|
| 206 |
+
"learning_rate": 6.410256410256412e-06,
|
| 207 |
+
"loss": 0.415,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.03350515463917526,
|
| 212 |
+
"grad_norm": 3.2059590816497803,
|
| 213 |
+
"learning_rate": 6.666666666666667e-06,
|
| 214 |
+
"loss": 0.3946,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.03479381443298969,
|
| 219 |
+
"grad_norm": 3.6049065589904785,
|
| 220 |
+
"learning_rate": 6.923076923076923e-06,
|
| 221 |
+
"loss": 0.3836,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.03608247422680412,
|
| 226 |
+
"grad_norm": 3.0256381034851074,
|
| 227 |
+
"learning_rate": 7.17948717948718e-06,
|
| 228 |
+
"loss": 0.3502,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.037371134020618556,
|
| 233 |
+
"grad_norm": 2.608344793319702,
|
| 234 |
+
"learning_rate": 7.435897435897437e-06,
|
| 235 |
+
"loss": 0.322,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.03865979381443299,
|
| 240 |
+
"grad_norm": 2.5998220443725586,
|
| 241 |
+
"learning_rate": 7.692307692307694e-06,
|
| 242 |
+
"loss": 0.3078,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.03994845360824742,
|
| 247 |
+
"grad_norm": 3.184544801712036,
|
| 248 |
+
"learning_rate": 7.948717948717949e-06,
|
| 249 |
+
"loss": 0.3189,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.041237113402061855,
|
| 254 |
+
"grad_norm": 2.9103171825408936,
|
| 255 |
+
"learning_rate": 8.205128205128205e-06,
|
| 256 |
+
"loss": 0.3387,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.04252577319587629,
|
| 261 |
+
"grad_norm": 2.9772467613220215,
|
| 262 |
+
"learning_rate": 8.461538461538462e-06,
|
| 263 |
+
"loss": 0.3093,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.04381443298969072,
|
| 268 |
+
"grad_norm": 2.77077054977417,
|
| 269 |
+
"learning_rate": 8.717948717948719e-06,
|
| 270 |
+
"loss": 0.2961,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.045103092783505154,
|
| 275 |
+
"grad_norm": 2.3303472995758057,
|
| 276 |
+
"learning_rate": 8.974358974358976e-06,
|
| 277 |
+
"loss": 0.2714,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.04639175257731959,
|
| 282 |
+
"grad_norm": 2.529663324356079,
|
| 283 |
+
"learning_rate": 9.230769230769232e-06,
|
| 284 |
+
"loss": 0.2592,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.04768041237113402,
|
| 289 |
+
"grad_norm": 2.3244917392730713,
|
| 290 |
+
"learning_rate": 9.487179487179487e-06,
|
| 291 |
+
"loss": 0.2439,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.04896907216494845,
|
| 296 |
+
"grad_norm": 2.4089925289154053,
|
| 297 |
+
"learning_rate": 9.743589743589744e-06,
|
| 298 |
+
"loss": 0.237,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.05025773195876289,
|
| 303 |
+
"grad_norm": 1.9498683214187622,
|
| 304 |
+
"learning_rate": 1e-05,
|
| 305 |
+
"loss": 0.202,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.05154639175257732,
|
| 310 |
+
"grad_norm": 1.967588186264038,
|
| 311 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 312 |
+
"loss": 0.2483,
|
| 313 |
+
"step": 40
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.05154639175257732,
|
| 317 |
+
"eval_accuracy": 0.9672293942403177,
|
| 318 |
+
"eval_f1": 0.08333333333333333,
|
| 319 |
+
"eval_loss": 0.14610709249973297,
|
| 320 |
+
"eval_precision": 0.2,
|
| 321 |
+
"eval_recall": 0.05263157894736842,
|
| 322 |
+
"eval_runtime": 84.9582,
|
| 323 |
+
"eval_samples_per_second": 5.356,
|
| 324 |
+
"eval_steps_per_second": 0.177,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.05283505154639175,
|
| 329 |
+
"grad_norm": 1.6313542127609253,
|
| 330 |
+
"learning_rate": 1.0512820512820514e-05,
|
| 331 |
+
"loss": 0.2022,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.05412371134020619,
|
| 336 |
+
"grad_norm": 1.4857121706008911,
|
| 337 |
+
"learning_rate": 1.076923076923077e-05,
|
| 338 |
+
"loss": 0.1911,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.055412371134020616,
|
| 343 |
+
"grad_norm": 1.229911208152771,
|
| 344 |
+
"learning_rate": 1.1025641025641028e-05,
|
| 345 |
+
"loss": 0.2323,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.05670103092783505,
|
| 350 |
+
"grad_norm": 1.344585657119751,
|
| 351 |
+
"learning_rate": 1.1282051282051283e-05,
|
| 352 |
+
"loss": 0.1473,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.05798969072164949,
|
| 357 |
+
"grad_norm": 0.909356951713562,
|
| 358 |
+
"learning_rate": 1.1538461538461538e-05,
|
| 359 |
+
"loss": 0.1828,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.059278350515463915,
|
| 364 |
+
"grad_norm": 0.9276474118232727,
|
| 365 |
+
"learning_rate": 1.1794871794871796e-05,
|
| 366 |
+
"loss": 0.1573,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.06056701030927835,
|
| 371 |
+
"grad_norm": 0.984527051448822,
|
| 372 |
+
"learning_rate": 1.2051282051282051e-05,
|
| 373 |
+
"loss": 0.2004,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.061855670103092786,
|
| 378 |
+
"grad_norm": 0.7970030307769775,
|
| 379 |
+
"learning_rate": 1.230769230769231e-05,
|
| 380 |
+
"loss": 0.1276,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.06314432989690721,
|
| 385 |
+
"grad_norm": 1.0922330617904663,
|
| 386 |
+
"learning_rate": 1.2564102564102565e-05,
|
| 387 |
+
"loss": 0.168,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.06443298969072164,
|
| 392 |
+
"grad_norm": 1.187216877937317,
|
| 393 |
+
"learning_rate": 1.2820512820512823e-05,
|
| 394 |
+
"loss": 0.2007,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.06572164948453608,
|
| 399 |
+
"grad_norm": 1.1624428033828735,
|
| 400 |
+
"learning_rate": 1.3076923076923078e-05,
|
| 401 |
+
"loss": 0.1665,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06701030927835051,
|
| 406 |
+
"grad_norm": 1.346639633178711,
|
| 407 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 408 |
+
"loss": 0.2013,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.06829896907216494,
|
| 413 |
+
"grad_norm": 0.9596057534217834,
|
| 414 |
+
"learning_rate": 1.3589743589743592e-05,
|
| 415 |
+
"loss": 0.1412,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06958762886597938,
|
| 420 |
+
"grad_norm": 1.3882497549057007,
|
| 421 |
+
"learning_rate": 1.3846153846153847e-05,
|
| 422 |
+
"loss": 0.191,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.07087628865979381,
|
| 427 |
+
"grad_norm": 0.7435745000839233,
|
| 428 |
+
"learning_rate": 1.4102564102564105e-05,
|
| 429 |
+
"loss": 0.1115,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07216494845360824,
|
| 434 |
+
"grad_norm": 0.8442493081092834,
|
| 435 |
+
"learning_rate": 1.435897435897436e-05,
|
| 436 |
+
"loss": 0.1239,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07345360824742268,
|
| 441 |
+
"grad_norm": 1.1027814149856567,
|
| 442 |
+
"learning_rate": 1.4615384615384615e-05,
|
| 443 |
+
"loss": 0.1605,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07474226804123711,
|
| 448 |
+
"grad_norm": 0.9518107771873474,
|
| 449 |
+
"learning_rate": 1.4871794871794874e-05,
|
| 450 |
+
"loss": 0.1253,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.07603092783505154,
|
| 455 |
+
"grad_norm": 0.8097633719444275,
|
| 456 |
+
"learning_rate": 1.5128205128205129e-05,
|
| 457 |
+
"loss": 0.1258,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07731958762886598,
|
| 462 |
+
"grad_norm": 0.9735177159309387,
|
| 463 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 464 |
+
"loss": 0.1622,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.07731958762886598,
|
| 469 |
+
"eval_accuracy": 0.9687189672293942,
|
| 470 |
+
"eval_f1": 0.18181818181818182,
|
| 471 |
+
"eval_loss": 0.10798302292823792,
|
| 472 |
+
"eval_precision": 0.35,
|
| 473 |
+
"eval_recall": 0.12280701754385964,
|
| 474 |
+
"eval_runtime": 84.7661,
|
| 475 |
+
"eval_samples_per_second": 5.368,
|
| 476 |
+
"eval_steps_per_second": 0.177,
|
| 477 |
+
"step": 60
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.07860824742268041,
|
| 481 |
+
"grad_norm": 0.9637501835823059,
|
| 482 |
+
"learning_rate": 1.5641025641025644e-05,
|
| 483 |
+
"loss": 0.1333,
|
| 484 |
+
"step": 61
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.07989690721649484,
|
| 488 |
+
"grad_norm": 0.6378239393234253,
|
| 489 |
+
"learning_rate": 1.5897435897435897e-05,
|
| 490 |
+
"loss": 0.076,
|
| 491 |
+
"step": 62
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.08118556701030928,
|
| 495 |
+
"grad_norm": 0.7773278951644897,
|
| 496 |
+
"learning_rate": 1.6153846153846154e-05,
|
| 497 |
+
"loss": 0.0937,
|
| 498 |
+
"step": 63
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.08247422680412371,
|
| 502 |
+
"grad_norm": 0.5744358897209167,
|
| 503 |
+
"learning_rate": 1.641025641025641e-05,
|
| 504 |
+
"loss": 0.089,
|
| 505 |
+
"step": 64
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.08376288659793814,
|
| 509 |
+
"grad_norm": 0.6605228781700134,
|
| 510 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 511 |
+
"loss": 0.058,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.08505154639175258,
|
| 516 |
+
"grad_norm": 0.68232661485672,
|
| 517 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 518 |
+
"loss": 0.1027,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.08634020618556701,
|
| 523 |
+
"grad_norm": 0.7368768453598022,
|
| 524 |
+
"learning_rate": 1.717948717948718e-05,
|
| 525 |
+
"loss": 0.1222,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.08762886597938144,
|
| 530 |
+
"grad_norm": 1.2759743928909302,
|
| 531 |
+
"learning_rate": 1.7435897435897438e-05,
|
| 532 |
+
"loss": 0.1637,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.08891752577319588,
|
| 537 |
+
"grad_norm": 1.383555293083191,
|
| 538 |
+
"learning_rate": 1.7692307692307694e-05,
|
| 539 |
+
"loss": 0.1774,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.09020618556701031,
|
| 544 |
+
"grad_norm": 1.048829436302185,
|
| 545 |
+
"learning_rate": 1.794871794871795e-05,
|
| 546 |
+
"loss": 0.0908,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.09149484536082474,
|
| 551 |
+
"grad_norm": 1.0387591123580933,
|
| 552 |
+
"learning_rate": 1.8205128205128208e-05,
|
| 553 |
+
"loss": 0.1263,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.09278350515463918,
|
| 558 |
+
"grad_norm": 0.9198775291442871,
|
| 559 |
+
"learning_rate": 1.8461538461538465e-05,
|
| 560 |
+
"loss": 0.1042,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.09407216494845361,
|
| 565 |
+
"grad_norm": 0.8574474453926086,
|
| 566 |
+
"learning_rate": 1.8717948717948718e-05,
|
| 567 |
+
"loss": 0.0845,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.09536082474226804,
|
| 572 |
+
"grad_norm": 0.9596143364906311,
|
| 573 |
+
"learning_rate": 1.8974358974358975e-05,
|
| 574 |
+
"loss": 0.1468,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.09664948453608248,
|
| 579 |
+
"grad_norm": 0.9079321026802063,
|
| 580 |
+
"learning_rate": 1.923076923076923e-05,
|
| 581 |
+
"loss": 0.0647,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.0979381443298969,
|
| 586 |
+
"grad_norm": 1.2310247421264648,
|
| 587 |
+
"learning_rate": 1.9487179487179488e-05,
|
| 588 |
+
"loss": 0.1315,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.09922680412371133,
|
| 593 |
+
"grad_norm": 0.9216123223304749,
|
| 594 |
+
"learning_rate": 1.9743589743589745e-05,
|
| 595 |
+
"loss": 0.0794,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.10051546391752578,
|
| 600 |
+
"grad_norm": 0.8806676864624023,
|
| 601 |
+
"learning_rate": 2e-05,
|
| 602 |
+
"loss": 0.0733,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.1018041237113402,
|
| 607 |
+
"grad_norm": 1.0531110763549805,
|
| 608 |
+
"learning_rate": 1.999989871195906e-05,
|
| 609 |
+
"loss": 0.045,
|
| 610 |
+
"step": 79
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.10309278350515463,
|
| 614 |
+
"grad_norm": 1.5389978885650635,
|
| 615 |
+
"learning_rate": 1.9999594849888083e-05,
|
| 616 |
+
"loss": 0.1243,
|
| 617 |
+
"step": 80
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.10309278350515463,
|
| 621 |
+
"eval_accuracy": 0.9697120158887785,
|
| 622 |
+
"eval_f1": 0.3838383838383838,
|
| 623 |
+
"eval_loss": 0.08788777142763138,
|
| 624 |
+
"eval_precision": 0.4523809523809524,
|
| 625 |
+
"eval_recall": 0.3333333333333333,
|
| 626 |
+
"eval_runtime": 84.9491,
|
| 627 |
+
"eval_samples_per_second": 5.356,
|
| 628 |
+
"eval_steps_per_second": 0.177,
|
| 629 |
+
"step": 80
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.10438144329896908,
|
| 633 |
+
"grad_norm": 1.1171326637268066,
|
| 634 |
+
"learning_rate": 1.9999088419942598e-05,
|
| 635 |
+
"loss": 0.081,
|
| 636 |
+
"step": 81
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.1056701030927835,
|
| 640 |
+
"grad_norm": 1.4132601022720337,
|
| 641 |
+
"learning_rate": 1.999837943238166e-05,
|
| 642 |
+
"loss": 0.0699,
|
| 643 |
+
"step": 82
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.10695876288659793,
|
| 647 |
+
"grad_norm": 2.1418771743774414,
|
| 648 |
+
"learning_rate": 1.999746790156766e-05,
|
| 649 |
+
"loss": 0.1157,
|
| 650 |
+
"step": 83
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.10824742268041238,
|
| 654 |
+
"grad_norm": 2.2251861095428467,
|
| 655 |
+
"learning_rate": 1.9996353845966033e-05,
|
| 656 |
+
"loss": 0.1371,
|
| 657 |
+
"step": 84
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.1095360824742268,
|
| 661 |
+
"grad_norm": 1.8240890502929688,
|
| 662 |
+
"learning_rate": 1.999503728814488e-05,
|
| 663 |
+
"loss": 0.0972,
|
| 664 |
+
"step": 85
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.11082474226804123,
|
| 668 |
+
"grad_norm": 2.1466102600097656,
|
| 669 |
+
"learning_rate": 1.9993518254774517e-05,
|
| 670 |
+
"loss": 0.0827,
|
| 671 |
+
"step": 86
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.11211340206185567,
|
| 675 |
+
"grad_norm": 1.60856032371521,
|
| 676 |
+
"learning_rate": 1.999179677662692e-05,
|
| 677 |
+
"loss": 0.0902,
|
| 678 |
+
"step": 87
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.1134020618556701,
|
| 682 |
+
"grad_norm": 1.7380954027175903,
|
| 683 |
+
"learning_rate": 1.998987288857513e-05,
|
| 684 |
+
"loss": 0.1057,
|
| 685 |
+
"step": 88
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.11469072164948453,
|
| 689 |
+
"grad_norm": 0.9695951342582703,
|
| 690 |
+
"learning_rate": 1.9987746629592506e-05,
|
| 691 |
+
"loss": 0.0485,
|
| 692 |
+
"step": 89
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.11597938144329897,
|
| 696 |
+
"grad_norm": 2.6375732421875,
|
| 697 |
+
"learning_rate": 1.9985418042751975e-05,
|
| 698 |
+
"loss": 0.0962,
|
| 699 |
+
"step": 90
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.1172680412371134,
|
| 703 |
+
"grad_norm": 1.3601967096328735,
|
| 704 |
+
"learning_rate": 1.9982887175225136e-05,
|
| 705 |
+
"loss": 0.0402,
|
| 706 |
+
"step": 91
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.11855670103092783,
|
| 710 |
+
"grad_norm": 1.6553303003311157,
|
| 711 |
+
"learning_rate": 1.998015407828131e-05,
|
| 712 |
+
"loss": 0.0576,
|
| 713 |
+
"step": 92
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.11984536082474227,
|
| 717 |
+
"grad_norm": 1.6685421466827393,
|
| 718 |
+
"learning_rate": 1.9977218807286507e-05,
|
| 719 |
+
"loss": 0.0666,
|
| 720 |
+
"step": 93
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.1211340206185567,
|
| 724 |
+
"grad_norm": 3.0571939945220947,
|
| 725 |
+
"learning_rate": 1.9974081421702296e-05,
|
| 726 |
+
"loss": 0.0754,
|
| 727 |
+
"step": 94
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.12242268041237113,
|
| 731 |
+
"grad_norm": 1.3410394191741943,
|
| 732 |
+
"learning_rate": 1.99707419850846e-05,
|
| 733 |
+
"loss": 0.0545,
|
| 734 |
+
"step": 95
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.12371134020618557,
|
| 738 |
+
"grad_norm": 1.2060542106628418,
|
| 739 |
+
"learning_rate": 1.9967200565082426e-05,
|
| 740 |
+
"loss": 0.0423,
|
| 741 |
+
"step": 96
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.125,
|
| 745 |
+
"grad_norm": 2.734278678894043,
|
| 746 |
+
"learning_rate": 1.9963457233436468e-05,
|
| 747 |
+
"loss": 0.0951,
|
| 748 |
+
"step": 97
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.12628865979381443,
|
| 752 |
+
"grad_norm": 1.210222601890564,
|
| 753 |
+
"learning_rate": 1.9959512065977673e-05,
|
| 754 |
+
"loss": 0.0476,
|
| 755 |
+
"step": 98
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.12757731958762886,
|
| 759 |
+
"grad_norm": 2.3914737701416016,
|
| 760 |
+
"learning_rate": 1.9955365142625694e-05,
|
| 761 |
+
"loss": 0.0498,
|
| 762 |
+
"step": 99
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.12886597938144329,
|
| 766 |
+
"grad_norm": 2.5380992889404297,
|
| 767 |
+
"learning_rate": 1.9951016547387286e-05,
|
| 768 |
+
"loss": 0.0678,
|
| 769 |
+
"step": 100
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.12886597938144329,
|
| 773 |
+
"eval_accuracy": 0.9692154915590864,
|
| 774 |
+
"eval_f1": 0.5753424657534246,
|
| 775 |
+
"eval_loss": 0.06998522579669952,
|
| 776 |
+
"eval_precision": 0.47191011235955055,
|
| 777 |
+
"eval_recall": 0.7368421052631579,
|
| 778 |
+
"eval_runtime": 84.7785,
|
| 779 |
+
"eval_samples_per_second": 5.367,
|
| 780 |
+
"eval_steps_per_second": 0.177,
|
| 781 |
+
"step": 100
|
| 782 |
+
}
|
| 783 |
+
],
|
| 784 |
+
"logging_steps": 1,
|
| 785 |
+
"max_steps": 776,
|
| 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": 3.347688371467059e+16,
|
| 802 |
+
"train_batch_size": 8,
|
| 803 |
+
"trial_name": null,
|
| 804 |
+
"trial_params": null
|
| 805 |
+
}
|