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 sha256:84cc6088d1a36caf682b4ba964cd893752db7233c9ac2731e0bdecbcdf7b5227
|
| 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 sha256:032757e766de4d9f4bbb31e72c0fc2f5016ed662bacbf4cdcb7e3308b6a0cac9
|
| 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 sha256:70dfcfbc62023412081edce90fbfc6bb052f6d340a3c3b07f004f301584ee0c7
|
| 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 sha256:7d14f395311907bcfada3de9ddd795697a83c436721b6e3a2577a7a74cef92c4
|
| 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 sha256:2500194f21bc76538b2c1b940c338d34558bbab87fb9822b585aa3e1dd3bf6d3
|
| 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 sha256:7d67ce69eb50c202ffe38a37d23ce8fbaad42cc3bb0f50546f25c3f334b359f2
|
| 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 sha256:4f618b60099ee98077cb33d7ef25639a63a2d4d3d44e14c170bbcf863d1d7915
|
| 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 sha256:01392e604b9718dfb75b6aca4d767028a8d9e9db814f90dfae1a541d68f3bd92
|
| 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 sha256:5e3af1412bccc3eadfac8740ec9f3a4420a7c5f09e3fe3834916f8d1d62e32cc
|
| 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 sha256:507c5ba79941654ef19efd04ea7687a98a5da5e324999e5c56ab7ef5a7874501
|
| 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:cbcca81eaf3e1fcd1ffc0e0811d0c9e7d0347da9661b13e7fa139d8134abcfcb
|
| 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 sha256:91b21db9b4b2ed193b6628ce22e61310c77f199ef08663c67ba353159845902c
|
| 3 |
+
size 14960
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cef0f333423fa3aff21a166b2bb6d2a55f2f3a173fc6ee99710701765969b439
|
| 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": 0.04740459824602986,
|
| 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": 0.9098228663446055,
|
| 14 |
+
"eval_f1": 0.3,
|
| 15 |
+
"eval_loss": 0.39109358191490173,
|
| 16 |
+
"eval_precision": 0.2222222222222222,
|
| 17 |
+
"eval_recall": 0.46153846153846156,
|
| 18 |
+
"eval_runtime": 50.0411,
|
| 19 |
+
"eval_samples_per_second": 5.416,
|
| 20 |
+
"eval_steps_per_second": 0.18,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.00047404598246029864,
|
| 25 |
+
"grad_norm": 2.736264228820801,
|
| 26 |
+
"learning_rate": 9.478672985781992e-08,
|
| 27 |
+
"loss": 0.6485,
|
| 28 |
+
"step": 1
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.0009480919649205973,
|
| 32 |
+
"grad_norm": 2.5090606212615967,
|
| 33 |
+
"learning_rate": 1.8957345971563984e-07,
|
| 34 |
+
"loss": 0.6663,
|
| 35 |
+
"step": 2
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.001422137947380896,
|
| 39 |
+
"grad_norm": 2.8418514728546143,
|
| 40 |
+
"learning_rate": 2.843601895734597e-07,
|
| 41 |
+
"loss": 0.6669,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0018961839298411946,
|
| 46 |
+
"grad_norm": 3.081920862197876,
|
| 47 |
+
"learning_rate": 3.791469194312797e-07,
|
| 48 |
+
"loss": 0.7195,
|
| 49 |
+
"step": 4
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.002370229912301493,
|
| 53 |
+
"grad_norm": 2.9263253211975098,
|
| 54 |
+
"learning_rate": 4.7393364928909956e-07,
|
| 55 |
+
"loss": 0.699,
|
| 56 |
+
"step": 5
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.002844275894761792,
|
| 60 |
+
"grad_norm": 2.3481531143188477,
|
| 61 |
+
"learning_rate": 5.687203791469194e-07,
|
| 62 |
+
"loss": 0.6352,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.0033183218772220905,
|
| 67 |
+
"grad_norm": 2.840491533279419,
|
| 68 |
+
"learning_rate": 6.635071090047394e-07,
|
| 69 |
+
"loss": 0.6859,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.003792367859682389,
|
| 74 |
+
"grad_norm": 2.8396637439727783,
|
| 75 |
+
"learning_rate": 7.582938388625594e-07,
|
| 76 |
+
"loss": 0.6912,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.004266413842142688,
|
| 81 |
+
"grad_norm": 3.1124157905578613,
|
| 82 |
+
"learning_rate": 8.530805687203792e-07,
|
| 83 |
+
"loss": 0.6481,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.004740459824602986,
|
| 88 |
+
"grad_norm": 2.768177032470703,
|
| 89 |
+
"learning_rate": 9.478672985781991e-07,
|
| 90 |
+
"loss": 0.6911,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0052145058070632855,
|
| 95 |
+
"grad_norm": 2.4753313064575195,
|
| 96 |
+
"learning_rate": 1.042654028436019e-06,
|
| 97 |
+
"loss": 0.5654,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.005688551789523584,
|
| 102 |
+
"grad_norm": 3.73299241065979,
|
| 103 |
+
"learning_rate": 1.1374407582938388e-06,
|
| 104 |
+
"loss": 0.7249,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.006162597771983883,
|
| 109 |
+
"grad_norm": 2.8647408485412598,
|
| 110 |
+
"learning_rate": 1.2322274881516587e-06,
|
| 111 |
+
"loss": 0.571,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.006636643754444181,
|
| 116 |
+
"grad_norm": 1.9949300289154053,
|
| 117 |
+
"learning_rate": 1.3270142180094788e-06,
|
| 118 |
+
"loss": 0.5458,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.00711068973690448,
|
| 123 |
+
"grad_norm": 2.8095905780792236,
|
| 124 |
+
"learning_rate": 1.4218009478672987e-06,
|
| 125 |
+
"loss": 0.6974,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.007584735719364778,
|
| 130 |
+
"grad_norm": 2.3465747833251953,
|
| 131 |
+
"learning_rate": 1.5165876777251187e-06,
|
| 132 |
+
"loss": 0.5798,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.008058781701825076,
|
| 137 |
+
"grad_norm": 2.2376415729522705,
|
| 138 |
+
"learning_rate": 1.6113744075829384e-06,
|
| 139 |
+
"loss": 0.6219,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.008532827684285376,
|
| 144 |
+
"grad_norm": 2.2321646213531494,
|
| 145 |
+
"learning_rate": 1.7061611374407585e-06,
|
| 146 |
+
"loss": 0.6327,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.009006873666745675,
|
| 151 |
+
"grad_norm": 2.9532177448272705,
|
| 152 |
+
"learning_rate": 1.8009478672985784e-06,
|
| 153 |
+
"loss": 0.7287,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.009480919649205973,
|
| 158 |
+
"grad_norm": 2.7521305084228516,
|
| 159 |
+
"learning_rate": 1.8957345971563982e-06,
|
| 160 |
+
"loss": 0.7904,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.009480919649205973,
|
| 165 |
+
"eval_accuracy": 0.9162640901771336,
|
| 166 |
+
"eval_f1": 0.3157894736842105,
|
| 167 |
+
"eval_loss": 0.3854508101940155,
|
| 168 |
+
"eval_precision": 0.24,
|
| 169 |
+
"eval_recall": 0.46153846153846156,
|
| 170 |
+
"eval_runtime": 50.1605,
|
| 171 |
+
"eval_samples_per_second": 5.403,
|
| 172 |
+
"eval_steps_per_second": 0.179,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.009954965631666271,
|
| 177 |
+
"grad_norm": 2.5812387466430664,
|
| 178 |
+
"learning_rate": 1.990521327014218e-06,
|
| 179 |
+
"loss": 0.6582,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.010429011614126571,
|
| 184 |
+
"grad_norm": 2.5878043174743652,
|
| 185 |
+
"learning_rate": 2.085308056872038e-06,
|
| 186 |
+
"loss": 0.5975,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.01090305759658687,
|
| 191 |
+
"grad_norm": 2.4602837562561035,
|
| 192 |
+
"learning_rate": 2.180094786729858e-06,
|
| 193 |
+
"loss": 0.6356,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.011377103579047167,
|
| 198 |
+
"grad_norm": 2.857377290725708,
|
| 199 |
+
"learning_rate": 2.2748815165876777e-06,
|
| 200 |
+
"loss": 0.6933,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.011851149561507466,
|
| 205 |
+
"grad_norm": 2.478761911392212,
|
| 206 |
+
"learning_rate": 2.369668246445498e-06,
|
| 207 |
+
"loss": 0.6806,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.012325195543967766,
|
| 212 |
+
"grad_norm": 2.6150331497192383,
|
| 213 |
+
"learning_rate": 2.4644549763033174e-06,
|
| 214 |
+
"loss": 0.6727,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.012799241526428064,
|
| 219 |
+
"grad_norm": 2.4646215438842773,
|
| 220 |
+
"learning_rate": 2.5592417061611373e-06,
|
| 221 |
+
"loss": 0.7231,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.013273287508888362,
|
| 226 |
+
"grad_norm": 2.3204421997070312,
|
| 227 |
+
"learning_rate": 2.6540284360189576e-06,
|
| 228 |
+
"loss": 0.715,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.01374733349134866,
|
| 233 |
+
"grad_norm": 2.1901276111602783,
|
| 234 |
+
"learning_rate": 2.7488151658767775e-06,
|
| 235 |
+
"loss": 0.6207,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.01422137947380896,
|
| 240 |
+
"grad_norm": 2.659156322479248,
|
| 241 |
+
"learning_rate": 2.8436018957345973e-06,
|
| 242 |
+
"loss": 0.6465,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.014695425456269258,
|
| 247 |
+
"grad_norm": 3.0104305744171143,
|
| 248 |
+
"learning_rate": 2.938388625592417e-06,
|
| 249 |
+
"loss": 0.6848,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.015169471438729557,
|
| 254 |
+
"grad_norm": 3.2612526416778564,
|
| 255 |
+
"learning_rate": 3.0331753554502375e-06,
|
| 256 |
+
"loss": 0.6094,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.015643517421189856,
|
| 261 |
+
"grad_norm": 2.8630073070526123,
|
| 262 |
+
"learning_rate": 3.1279620853080574e-06,
|
| 263 |
+
"loss": 0.6679,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.016117563403650153,
|
| 268 |
+
"grad_norm": 3.1366546154022217,
|
| 269 |
+
"learning_rate": 3.222748815165877e-06,
|
| 270 |
+
"loss": 0.6961,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.016591609386110453,
|
| 275 |
+
"grad_norm": 2.5289793014526367,
|
| 276 |
+
"learning_rate": 3.3175355450236967e-06,
|
| 277 |
+
"loss": 0.6363,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.017065655368570753,
|
| 282 |
+
"grad_norm": 1.996009111404419,
|
| 283 |
+
"learning_rate": 3.412322274881517e-06,
|
| 284 |
+
"loss": 0.6137,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.01753970135103105,
|
| 289 |
+
"grad_norm": 2.309265613555908,
|
| 290 |
+
"learning_rate": 3.507109004739337e-06,
|
| 291 |
+
"loss": 0.5873,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.01801374733349135,
|
| 296 |
+
"grad_norm": 2.2232859134674072,
|
| 297 |
+
"learning_rate": 3.6018957345971567e-06,
|
| 298 |
+
"loss": 0.6081,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.018487793315951646,
|
| 303 |
+
"grad_norm": 2.608635902404785,
|
| 304 |
+
"learning_rate": 3.6966824644549766e-06,
|
| 305 |
+
"loss": 0.5946,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.018961839298411946,
|
| 310 |
+
"grad_norm": 2.9958667755126953,
|
| 311 |
+
"learning_rate": 3.7914691943127964e-06,
|
| 312 |
+
"loss": 0.6496,
|
| 313 |
+
"step": 40
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.018961839298411946,
|
| 317 |
+
"eval_accuracy": 0.9299516908212561,
|
| 318 |
+
"eval_f1": 0.304,
|
| 319 |
+
"eval_loss": 0.357759952545166,
|
| 320 |
+
"eval_precision": 0.2602739726027397,
|
| 321 |
+
"eval_recall": 0.36538461538461536,
|
| 322 |
+
"eval_runtime": 50.7819,
|
| 323 |
+
"eval_samples_per_second": 5.337,
|
| 324 |
+
"eval_steps_per_second": 0.177,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.019435885280872246,
|
| 329 |
+
"grad_norm": 2.9960222244262695,
|
| 330 |
+
"learning_rate": 3.886255924170616e-06,
|
| 331 |
+
"loss": 0.7012,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.019909931263332542,
|
| 336 |
+
"grad_norm": 2.469219923019409,
|
| 337 |
+
"learning_rate": 3.981042654028436e-06,
|
| 338 |
+
"loss": 0.5172,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.020383977245792842,
|
| 343 |
+
"grad_norm": 2.2367403507232666,
|
| 344 |
+
"learning_rate": 4.075829383886256e-06,
|
| 345 |
+
"loss": 0.6086,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.020858023228253142,
|
| 350 |
+
"grad_norm": 2.455852746963501,
|
| 351 |
+
"learning_rate": 4.170616113744076e-06,
|
| 352 |
+
"loss": 0.6616,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.02133206921071344,
|
| 357 |
+
"grad_norm": 2.6048426628112793,
|
| 358 |
+
"learning_rate": 4.265402843601897e-06,
|
| 359 |
+
"loss": 0.6319,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.02180611519317374,
|
| 364 |
+
"grad_norm": 2.633476495742798,
|
| 365 |
+
"learning_rate": 4.360189573459716e-06,
|
| 366 |
+
"loss": 0.5807,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.022280161175634035,
|
| 371 |
+
"grad_norm": 2.525595188140869,
|
| 372 |
+
"learning_rate": 4.4549763033175355e-06,
|
| 373 |
+
"loss": 0.566,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.022754207158094335,
|
| 378 |
+
"grad_norm": 2.116396427154541,
|
| 379 |
+
"learning_rate": 4.549763033175355e-06,
|
| 380 |
+
"loss": 0.5222,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.023228253140554635,
|
| 385 |
+
"grad_norm": 2.2869620323181152,
|
| 386 |
+
"learning_rate": 4.644549763033176e-06,
|
| 387 |
+
"loss": 0.6677,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.02370229912301493,
|
| 392 |
+
"grad_norm": 3.656646966934204,
|
| 393 |
+
"learning_rate": 4.739336492890996e-06,
|
| 394 |
+
"loss": 0.6329,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.02417634510547523,
|
| 399 |
+
"grad_norm": 2.4779574871063232,
|
| 400 |
+
"learning_rate": 4.834123222748816e-06,
|
| 401 |
+
"loss": 0.6179,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.02465039108793553,
|
| 406 |
+
"grad_norm": 2.9239354133605957,
|
| 407 |
+
"learning_rate": 4.928909952606635e-06,
|
| 408 |
+
"loss": 0.5679,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.025124437070395828,
|
| 413 |
+
"grad_norm": 2.596090793609619,
|
| 414 |
+
"learning_rate": 5.023696682464455e-06,
|
| 415 |
+
"loss": 0.5907,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.025598483052856127,
|
| 420 |
+
"grad_norm": 2.4275245666503906,
|
| 421 |
+
"learning_rate": 5.118483412322275e-06,
|
| 422 |
+
"loss": 0.5432,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.026072529035316427,
|
| 427 |
+
"grad_norm": 3.1805362701416016,
|
| 428 |
+
"learning_rate": 5.213270142180096e-06,
|
| 429 |
+
"loss": 0.6221,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.026546575017776724,
|
| 434 |
+
"grad_norm": 2.3142030239105225,
|
| 435 |
+
"learning_rate": 5.308056872037915e-06,
|
| 436 |
+
"loss": 0.6459,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.027020621000237024,
|
| 441 |
+
"grad_norm": 2.3154592514038086,
|
| 442 |
+
"learning_rate": 5.402843601895735e-06,
|
| 443 |
+
"loss": 0.5481,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.02749466698269732,
|
| 448 |
+
"grad_norm": 2.70127272605896,
|
| 449 |
+
"learning_rate": 5.497630331753555e-06,
|
| 450 |
+
"loss": 0.5592,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.02796871296515762,
|
| 455 |
+
"grad_norm": 2.5554442405700684,
|
| 456 |
+
"learning_rate": 5.592417061611375e-06,
|
| 457 |
+
"loss": 0.587,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.02844275894761792,
|
| 462 |
+
"grad_norm": 2.4974448680877686,
|
| 463 |
+
"learning_rate": 5.687203791469195e-06,
|
| 464 |
+
"loss": 0.5209,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.02844275894761792,
|
| 469 |
+
"eval_accuracy": 0.9468599033816425,
|
| 470 |
+
"eval_f1": 0.23255813953488372,
|
| 471 |
+
"eval_loss": 0.30114662647247314,
|
| 472 |
+
"eval_precision": 0.29411764705882354,
|
| 473 |
+
"eval_recall": 0.19230769230769232,
|
| 474 |
+
"eval_runtime": 50.6864,
|
| 475 |
+
"eval_samples_per_second": 5.347,
|
| 476 |
+
"eval_steps_per_second": 0.178,
|
| 477 |
+
"step": 60
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.028916804930078217,
|
| 481 |
+
"grad_norm": 2.1992790699005127,
|
| 482 |
+
"learning_rate": 5.7819905213270145e-06,
|
| 483 |
+
"loss": 0.6134,
|
| 484 |
+
"step": 61
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.029390850912538517,
|
| 488 |
+
"grad_norm": 2.135422468185425,
|
| 489 |
+
"learning_rate": 5.876777251184834e-06,
|
| 490 |
+
"loss": 0.5917,
|
| 491 |
+
"step": 62
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.029864896894998817,
|
| 495 |
+
"grad_norm": 1.9710865020751953,
|
| 496 |
+
"learning_rate": 5.971563981042654e-06,
|
| 497 |
+
"loss": 0.5341,
|
| 498 |
+
"step": 63
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.030338942877459113,
|
| 502 |
+
"grad_norm": 2.6831486225128174,
|
| 503 |
+
"learning_rate": 6.066350710900475e-06,
|
| 504 |
+
"loss": 0.5878,
|
| 505 |
+
"step": 64
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.030812988859919413,
|
| 509 |
+
"grad_norm": 2.277893543243408,
|
| 510 |
+
"learning_rate": 6.161137440758295e-06,
|
| 511 |
+
"loss": 0.5407,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.03128703484237971,
|
| 516 |
+
"grad_norm": 2.153470993041992,
|
| 517 |
+
"learning_rate": 6.255924170616115e-06,
|
| 518 |
+
"loss": 0.5109,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.03176108082484001,
|
| 523 |
+
"grad_norm": 2.458293914794922,
|
| 524 |
+
"learning_rate": 6.350710900473935e-06,
|
| 525 |
+
"loss": 0.5687,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.032235126807300306,
|
| 530 |
+
"grad_norm": 1.6730012893676758,
|
| 531 |
+
"learning_rate": 6.445497630331754e-06,
|
| 532 |
+
"loss": 0.511,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.032709172789760606,
|
| 537 |
+
"grad_norm": 2.294477939605713,
|
| 538 |
+
"learning_rate": 6.5402843601895735e-06,
|
| 539 |
+
"loss": 0.5163,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.033183218772220906,
|
| 544 |
+
"grad_norm": 1.931765079498291,
|
| 545 |
+
"learning_rate": 6.635071090047393e-06,
|
| 546 |
+
"loss": 0.5463,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.033657264754681206,
|
| 551 |
+
"grad_norm": 1.9582473039627075,
|
| 552 |
+
"learning_rate": 6.729857819905213e-06,
|
| 553 |
+
"loss": 0.5404,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.034131310737141506,
|
| 558 |
+
"grad_norm": 2.352447986602783,
|
| 559 |
+
"learning_rate": 6.824644549763034e-06,
|
| 560 |
+
"loss": 0.5004,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.0346053567196018,
|
| 565 |
+
"grad_norm": 2.5306575298309326,
|
| 566 |
+
"learning_rate": 6.919431279620854e-06,
|
| 567 |
+
"loss": 0.491,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.0350794027020621,
|
| 572 |
+
"grad_norm": 1.954287052154541,
|
| 573 |
+
"learning_rate": 7.014218009478674e-06,
|
| 574 |
+
"loss": 0.5096,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.0355534486845224,
|
| 579 |
+
"grad_norm": 1.7585203647613525,
|
| 580 |
+
"learning_rate": 7.1090047393364935e-06,
|
| 581 |
+
"loss": 0.4437,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.0360274946669827,
|
| 586 |
+
"grad_norm": 1.9448845386505127,
|
| 587 |
+
"learning_rate": 7.203791469194313e-06,
|
| 588 |
+
"loss": 0.4902,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.036501540649443,
|
| 593 |
+
"grad_norm": 2.1417629718780518,
|
| 594 |
+
"learning_rate": 7.298578199052133e-06,
|
| 595 |
+
"loss": 0.5599,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.03697558663190329,
|
| 600 |
+
"grad_norm": 1.9677048921585083,
|
| 601 |
+
"learning_rate": 7.393364928909953e-06,
|
| 602 |
+
"loss": 0.5196,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.03744963261436359,
|
| 607 |
+
"grad_norm": 4.773871421813965,
|
| 608 |
+
"learning_rate": 7.488151658767773e-06,
|
| 609 |
+
"loss": 0.7193,
|
| 610 |
+
"step": 79
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.03792367859682389,
|
| 614 |
+
"grad_norm": 1.7716329097747803,
|
| 615 |
+
"learning_rate": 7.582938388625593e-06,
|
| 616 |
+
"loss": 0.482,
|
| 617 |
+
"step": 80
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.03792367859682389,
|
| 621 |
+
"eval_accuracy": 0.9524959742351047,
|
| 622 |
+
"eval_f1": 0.21333333333333335,
|
| 623 |
+
"eval_loss": 0.2597336769104004,
|
| 624 |
+
"eval_precision": 0.34782608695652173,
|
| 625 |
+
"eval_recall": 0.15384615384615385,
|
| 626 |
+
"eval_runtime": 50.3051,
|
| 627 |
+
"eval_samples_per_second": 5.387,
|
| 628 |
+
"eval_steps_per_second": 0.179,
|
| 629 |
+
"step": 80
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.03839772457928419,
|
| 633 |
+
"grad_norm": 1.7248247861862183,
|
| 634 |
+
"learning_rate": 7.677725118483414e-06,
|
| 635 |
+
"loss": 0.4988,
|
| 636 |
+
"step": 81
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.03887177056174449,
|
| 640 |
+
"grad_norm": 2.6806564331054688,
|
| 641 |
+
"learning_rate": 7.772511848341233e-06,
|
| 642 |
+
"loss": 0.6173,
|
| 643 |
+
"step": 82
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.03934581654420479,
|
| 647 |
+
"grad_norm": 3.3090500831604004,
|
| 648 |
+
"learning_rate": 7.867298578199053e-06,
|
| 649 |
+
"loss": 0.6747,
|
| 650 |
+
"step": 83
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.039819862526665084,
|
| 654 |
+
"grad_norm": 1.7768396139144897,
|
| 655 |
+
"learning_rate": 7.962085308056872e-06,
|
| 656 |
+
"loss": 0.4246,
|
| 657 |
+
"step": 84
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.040293908509125384,
|
| 661 |
+
"grad_norm": 2.553398847579956,
|
| 662 |
+
"learning_rate": 8.056872037914693e-06,
|
| 663 |
+
"loss": 0.5885,
|
| 664 |
+
"step": 85
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.040767954491585684,
|
| 668 |
+
"grad_norm": 2.223745107650757,
|
| 669 |
+
"learning_rate": 8.151658767772512e-06,
|
| 670 |
+
"loss": 0.631,
|
| 671 |
+
"step": 86
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.041242000474045984,
|
| 675 |
+
"grad_norm": 2.303098440170288,
|
| 676 |
+
"learning_rate": 8.246445497630333e-06,
|
| 677 |
+
"loss": 0.4689,
|
| 678 |
+
"step": 87
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.041716046456506284,
|
| 682 |
+
"grad_norm": 1.8970552682876587,
|
| 683 |
+
"learning_rate": 8.341232227488152e-06,
|
| 684 |
+
"loss": 0.523,
|
| 685 |
+
"step": 88
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.04219009243896658,
|
| 689 |
+
"grad_norm": 2.505955934524536,
|
| 690 |
+
"learning_rate": 8.436018957345973e-06,
|
| 691 |
+
"loss": 0.4935,
|
| 692 |
+
"step": 89
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.04266413842142688,
|
| 696 |
+
"grad_norm": 1.875301718711853,
|
| 697 |
+
"learning_rate": 8.530805687203793e-06,
|
| 698 |
+
"loss": 0.4522,
|
| 699 |
+
"step": 90
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.04313818440388718,
|
| 703 |
+
"grad_norm": 1.900534749031067,
|
| 704 |
+
"learning_rate": 8.625592417061612e-06,
|
| 705 |
+
"loss": 0.4667,
|
| 706 |
+
"step": 91
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.04361223038634748,
|
| 710 |
+
"grad_norm": 3.142495632171631,
|
| 711 |
+
"learning_rate": 8.720379146919431e-06,
|
| 712 |
+
"loss": 0.7367,
|
| 713 |
+
"step": 92
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.04408627636880778,
|
| 717 |
+
"grad_norm": 2.096675395965576,
|
| 718 |
+
"learning_rate": 8.815165876777252e-06,
|
| 719 |
+
"loss": 0.5286,
|
| 720 |
+
"step": 93
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.04456032235126807,
|
| 724 |
+
"grad_norm": 2.4111526012420654,
|
| 725 |
+
"learning_rate": 8.909952606635071e-06,
|
| 726 |
+
"loss": 0.4165,
|
| 727 |
+
"step": 94
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.04503436833372837,
|
| 731 |
+
"grad_norm": 2.4553468227386475,
|
| 732 |
+
"learning_rate": 9.004739336492892e-06,
|
| 733 |
+
"loss": 0.5336,
|
| 734 |
+
"step": 95
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.04550841431618867,
|
| 738 |
+
"grad_norm": 2.3772170543670654,
|
| 739 |
+
"learning_rate": 9.09952606635071e-06,
|
| 740 |
+
"loss": 0.455,
|
| 741 |
+
"step": 96
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.04598246029864897,
|
| 745 |
+
"grad_norm": 2.652953863143921,
|
| 746 |
+
"learning_rate": 9.194312796208532e-06,
|
| 747 |
+
"loss": 0.5995,
|
| 748 |
+
"step": 97
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.04645650628110927,
|
| 752 |
+
"grad_norm": 1.7384384870529175,
|
| 753 |
+
"learning_rate": 9.289099526066352e-06,
|
| 754 |
+
"loss": 0.4296,
|
| 755 |
+
"step": 98
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.04693055226356957,
|
| 759 |
+
"grad_norm": 2.1251447200775146,
|
| 760 |
+
"learning_rate": 9.383886255924171e-06,
|
| 761 |
+
"loss": 0.5505,
|
| 762 |
+
"step": 99
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.04740459824602986,
|
| 766 |
+
"grad_norm": 1.7407325506210327,
|
| 767 |
+
"learning_rate": 9.478672985781992e-06,
|
| 768 |
+
"loss": 0.4165,
|
| 769 |
+
"step": 100
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.04740459824602986,
|
| 773 |
+
"eval_accuracy": 0.9549114331723028,
|
| 774 |
+
"eval_f1": 0.40425531914893614,
|
| 775 |
+
"eval_loss": 0.2602430284023285,
|
| 776 |
+
"eval_precision": 0.4523809523809524,
|
| 777 |
+
"eval_recall": 0.36538461538461536,
|
| 778 |
+
"eval_runtime": 50.5287,
|
| 779 |
+
"eval_samples_per_second": 5.363,
|
| 780 |
+
"eval_steps_per_second": 0.178,
|
| 781 |
+
"step": 100
|
| 782 |
+
}
|
| 783 |
+
],
|
| 784 |
+
"logging_steps": 1,
|
| 785 |
+
"max_steps": 2109,
|
| 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": 2.677803521880883e+16,
|
| 802 |
+
"train_batch_size": 8,
|
| 803 |
+
"trial_name": null,
|
| 804 |
+
"trial_params": null
|
| 805 |
+
}
|