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 sha256:622bc81f8f68315981230410a5af9295ce13d9d2442cda4d2e0c1394ab643b63
|
| 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 sha256:4466298f59f74f2396af30cc6846b03c5e2c475c68f597a2280900b5ef9f6822
|
| 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:bb65453e41ba57df1e49499b4515f11a2109e747a8b475018fb820ed8547d1eb
|
| 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 sha256:4bf652736c23d5ec500d53e4354bd3773109f926f1b4b0d4d59aa2ea69aef069
|
| 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 sha256:376356308c6e8d10bb682cfb1a0b4946d89136884ead7b05403c587b67da24d4
|
| 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 sha256:0094cac6a81cd2cfbebec1f49ccdb27974dfa74431cee11fdad66a765c1d98d2
|
| 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 sha256:040531dc57ed33e37cbfe9dcd7e1112c382584100f1bc640594960230566b736
|
| 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 sha256:3ab6e917dda4050ac4d807b0d9a1f67dc38eb806edecf6d4ff9f2b2d5e86f777
|
| 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:d599ef6d880da0407794d2d1e47f232e539d56e142a25747095b9788a64b4a0d
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed7e2cf1c59b7e3fc4655862d319e154ce50df93b4a979d06081d1b6dff38468
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc1fa1da948f84f37dc872f4ee1aeeca7ef28ae0f1d1cc77d8a981b0bf8135cd
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86ac5d5301adaa867d76938d6c3a2f107900c1dc4d17da3726a78980838f397d
|
| 3 |
+
size 15024
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d661a2f97e83bfd63aa735702d498a3c1b7836c17a4de8072ad7a10523a2471c
|
| 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": 0.12552301255230125,
|
| 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": 0.7339955849889624,
|
| 14 |
+
"eval_f1": 0.2445141065830721,
|
| 15 |
+
"eval_loss": 0.5994934439659119,
|
| 16 |
+
"eval_precision": 0.6,
|
| 17 |
+
"eval_recall": 0.15354330708661418,
|
| 18 |
+
"eval_runtime": 52.2305,
|
| 19 |
+
"eval_samples_per_second": 5.303,
|
| 20 |
+
"eval_steps_per_second": 0.172,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0012552301255230125,
|
| 25 |
+
"grad_norm": 1.9609311819076538,
|
| 26 |
+
"learning_rate": 2.5000000000000004e-07,
|
| 27 |
+
"loss": 0.6978,
|
| 28 |
+
"step": 1
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.002510460251046025,
|
| 32 |
+
"grad_norm": 1.9798370599746704,
|
| 33 |
+
"learning_rate": 5.000000000000001e-07,
|
| 34 |
+
"loss": 0.6725,
|
| 35 |
+
"step": 2
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.0037656903765690376,
|
| 39 |
+
"grad_norm": 2.634610652923584,
|
| 40 |
+
"learning_rate": 7.5e-07,
|
| 41 |
+
"loss": 0.7798,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.00502092050209205,
|
| 46 |
+
"grad_norm": 1.9435328245162964,
|
| 47 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 48 |
+
"loss": 0.6777,
|
| 49 |
+
"step": 4
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.006276150627615063,
|
| 53 |
+
"grad_norm": 2.0514488220214844,
|
| 54 |
+
"learning_rate": 1.25e-06,
|
| 55 |
+
"loss": 0.7849,
|
| 56 |
+
"step": 5
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.007531380753138075,
|
| 60 |
+
"grad_norm": 3.1893956661224365,
|
| 61 |
+
"learning_rate": 1.5e-06,
|
| 62 |
+
"loss": 0.7281,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.008786610878661089,
|
| 67 |
+
"grad_norm": 2.2875595092773438,
|
| 68 |
+
"learning_rate": 1.75e-06,
|
| 69 |
+
"loss": 0.7267,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.0100418410041841,
|
| 74 |
+
"grad_norm": 1.7282941341400146,
|
| 75 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 76 |
+
"loss": 0.642,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.011297071129707114,
|
| 81 |
+
"grad_norm": 1.9356372356414795,
|
| 82 |
+
"learning_rate": 2.25e-06,
|
| 83 |
+
"loss": 0.6923,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.012552301255230125,
|
| 88 |
+
"grad_norm": 2.0085136890411377,
|
| 89 |
+
"learning_rate": 2.5e-06,
|
| 90 |
+
"loss": 0.6507,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.013807531380753139,
|
| 95 |
+
"grad_norm": 2.1001739501953125,
|
| 96 |
+
"learning_rate": 2.7500000000000004e-06,
|
| 97 |
+
"loss": 0.6162,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.01506276150627615,
|
| 102 |
+
"grad_norm": 2.053370714187622,
|
| 103 |
+
"learning_rate": 3e-06,
|
| 104 |
+
"loss": 0.674,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.016317991631799162,
|
| 109 |
+
"grad_norm": 2.3665823936462402,
|
| 110 |
+
"learning_rate": 3.2500000000000002e-06,
|
| 111 |
+
"loss": 0.6931,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.017573221757322177,
|
| 116 |
+
"grad_norm": 1.99113929271698,
|
| 117 |
+
"learning_rate": 3.5e-06,
|
| 118 |
+
"loss": 0.7218,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.01882845188284519,
|
| 123 |
+
"grad_norm": 1.8170547485351562,
|
| 124 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 125 |
+
"loss": 0.6488,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.0200836820083682,
|
| 130 |
+
"grad_norm": 1.8335210084915161,
|
| 131 |
+
"learning_rate": 4.000000000000001e-06,
|
| 132 |
+
"loss": 0.6467,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.021338912133891212,
|
| 137 |
+
"grad_norm": 1.6069227457046509,
|
| 138 |
+
"learning_rate": 4.25e-06,
|
| 139 |
+
"loss": 0.6395,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.022594142259414227,
|
| 144 |
+
"grad_norm": 1.7745310068130493,
|
| 145 |
+
"learning_rate": 4.5e-06,
|
| 146 |
+
"loss": 0.6905,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.02384937238493724,
|
| 151 |
+
"grad_norm": 2.1716341972351074,
|
| 152 |
+
"learning_rate": 4.75e-06,
|
| 153 |
+
"loss": 0.653,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.02510460251046025,
|
| 158 |
+
"grad_norm": 1.9034003019332886,
|
| 159 |
+
"learning_rate": 5e-06,
|
| 160 |
+
"loss": 0.7266,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.02510460251046025,
|
| 165 |
+
"eval_accuracy": 0.7384105960264901,
|
| 166 |
+
"eval_f1": 0.26625386996904027,
|
| 167 |
+
"eval_loss": 0.5908851027488708,
|
| 168 |
+
"eval_precision": 0.6231884057971014,
|
| 169 |
+
"eval_recall": 0.16929133858267717,
|
| 170 |
+
"eval_runtime": 52.6006,
|
| 171 |
+
"eval_samples_per_second": 5.266,
|
| 172 |
+
"eval_steps_per_second": 0.171,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.026359832635983262,
|
| 177 |
+
"grad_norm": 1.7850794792175293,
|
| 178 |
+
"learning_rate": 5.2500000000000006e-06,
|
| 179 |
+
"loss": 0.65,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.027615062761506277,
|
| 184 |
+
"grad_norm": 1.765768051147461,
|
| 185 |
+
"learning_rate": 5.500000000000001e-06,
|
| 186 |
+
"loss": 0.6715,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.02887029288702929,
|
| 191 |
+
"grad_norm": 1.8612842559814453,
|
| 192 |
+
"learning_rate": 5.75e-06,
|
| 193 |
+
"loss": 0.6614,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.0301255230125523,
|
| 198 |
+
"grad_norm": 1.8554290533065796,
|
| 199 |
+
"learning_rate": 6e-06,
|
| 200 |
+
"loss": 0.641,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.03138075313807531,
|
| 205 |
+
"grad_norm": 1.8867026567459106,
|
| 206 |
+
"learning_rate": 6.25e-06,
|
| 207 |
+
"loss": 0.6224,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.032635983263598324,
|
| 212 |
+
"grad_norm": 1.8916778564453125,
|
| 213 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 214 |
+
"loss": 0.6471,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.033891213389121336,
|
| 219 |
+
"grad_norm": 1.7810847759246826,
|
| 220 |
+
"learning_rate": 6.750000000000001e-06,
|
| 221 |
+
"loss": 0.6197,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.035146443514644354,
|
| 226 |
+
"grad_norm": 1.6231898069381714,
|
| 227 |
+
"learning_rate": 7e-06,
|
| 228 |
+
"loss": 0.6362,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.036401673640167366,
|
| 233 |
+
"grad_norm": 1.7416272163391113,
|
| 234 |
+
"learning_rate": 7.25e-06,
|
| 235 |
+
"loss": 0.6425,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.03765690376569038,
|
| 240 |
+
"grad_norm": 1.6757186651229858,
|
| 241 |
+
"learning_rate": 7.500000000000001e-06,
|
| 242 |
+
"loss": 0.5854,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.03891213389121339,
|
| 247 |
+
"grad_norm": 1.9119001626968384,
|
| 248 |
+
"learning_rate": 7.75e-06,
|
| 249 |
+
"loss": 0.5457,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.0401673640167364,
|
| 254 |
+
"grad_norm": 1.576582908630371,
|
| 255 |
+
"learning_rate": 8.000000000000001e-06,
|
| 256 |
+
"loss": 0.5516,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.04142259414225941,
|
| 261 |
+
"grad_norm": 1.5435791015625,
|
| 262 |
+
"learning_rate": 8.25e-06,
|
| 263 |
+
"loss": 0.5458,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.042677824267782424,
|
| 268 |
+
"grad_norm": 1.8229247331619263,
|
| 269 |
+
"learning_rate": 8.5e-06,
|
| 270 |
+
"loss": 0.6167,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.043933054393305436,
|
| 275 |
+
"grad_norm": 2.217472791671753,
|
| 276 |
+
"learning_rate": 8.750000000000001e-06,
|
| 277 |
+
"loss": 0.6588,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.045188284518828455,
|
| 282 |
+
"grad_norm": 1.8096412420272827,
|
| 283 |
+
"learning_rate": 9e-06,
|
| 284 |
+
"loss": 0.6595,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.046443514644351466,
|
| 289 |
+
"grad_norm": 1.8887217044830322,
|
| 290 |
+
"learning_rate": 9.250000000000001e-06,
|
| 291 |
+
"loss": 0.6004,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.04769874476987448,
|
| 296 |
+
"grad_norm": 1.55510413646698,
|
| 297 |
+
"learning_rate": 9.5e-06,
|
| 298 |
+
"loss": 0.5685,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.04895397489539749,
|
| 303 |
+
"grad_norm": 1.6017107963562012,
|
| 304 |
+
"learning_rate": 9.75e-06,
|
| 305 |
+
"loss": 0.497,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.0502092050209205,
|
| 310 |
+
"grad_norm": 2.4420340061187744,
|
| 311 |
+
"learning_rate": 1e-05,
|
| 312 |
+
"loss": 0.674,
|
| 313 |
+
"step": 40
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.0502092050209205,
|
| 317 |
+
"eval_accuracy": 0.7516556291390728,
|
| 318 |
+
"eval_f1": 0.3553008595988539,
|
| 319 |
+
"eval_loss": 0.5497225522994995,
|
| 320 |
+
"eval_precision": 0.6526315789473685,
|
| 321 |
+
"eval_recall": 0.2440944881889764,
|
| 322 |
+
"eval_runtime": 53.1059,
|
| 323 |
+
"eval_samples_per_second": 5.216,
|
| 324 |
+
"eval_steps_per_second": 0.169,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.05146443514644351,
|
| 329 |
+
"grad_norm": 1.6397217512130737,
|
| 330 |
+
"learning_rate": 1.025e-05,
|
| 331 |
+
"loss": 0.5409,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.052719665271966525,
|
| 336 |
+
"grad_norm": 1.616377353668213,
|
| 337 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 338 |
+
"loss": 0.5902,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.05397489539748954,
|
| 343 |
+
"grad_norm": 1.5098403692245483,
|
| 344 |
+
"learning_rate": 1.075e-05,
|
| 345 |
+
"loss": 0.5468,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.055230125523012555,
|
| 350 |
+
"grad_norm": 2.074469566345215,
|
| 351 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 352 |
+
"loss": 0.5969,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.056485355648535567,
|
| 357 |
+
"grad_norm": 1.646159291267395,
|
| 358 |
+
"learning_rate": 1.125e-05,
|
| 359 |
+
"loss": 0.5629,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.05774058577405858,
|
| 364 |
+
"grad_norm": 1.7806731462478638,
|
| 365 |
+
"learning_rate": 1.15e-05,
|
| 366 |
+
"loss": 0.565,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.05899581589958159,
|
| 371 |
+
"grad_norm": 1.5080231428146362,
|
| 372 |
+
"learning_rate": 1.1750000000000001e-05,
|
| 373 |
+
"loss": 0.5349,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.0602510460251046,
|
| 378 |
+
"grad_norm": 1.4364521503448486,
|
| 379 |
+
"learning_rate": 1.2e-05,
|
| 380 |
+
"loss": 0.5335,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.06150627615062761,
|
| 385 |
+
"grad_norm": 1.3679174184799194,
|
| 386 |
+
"learning_rate": 1.2250000000000001e-05,
|
| 387 |
+
"loss": 0.5727,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.06276150627615062,
|
| 392 |
+
"grad_norm": 2.1571309566497803,
|
| 393 |
+
"learning_rate": 1.25e-05,
|
| 394 |
+
"loss": 0.473,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.06401673640167364,
|
| 399 |
+
"grad_norm": 1.4333269596099854,
|
| 400 |
+
"learning_rate": 1.275e-05,
|
| 401 |
+
"loss": 0.5388,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06527196652719665,
|
| 406 |
+
"grad_norm": 1.5196632146835327,
|
| 407 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 408 |
+
"loss": 0.5264,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.06652719665271967,
|
| 413 |
+
"grad_norm": 1.491036057472229,
|
| 414 |
+
"learning_rate": 1.325e-05,
|
| 415 |
+
"loss": 0.4879,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06778242677824267,
|
| 420 |
+
"grad_norm": 2.134739875793457,
|
| 421 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 422 |
+
"loss": 0.563,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.06903765690376569,
|
| 427 |
+
"grad_norm": 1.4758329391479492,
|
| 428 |
+
"learning_rate": 1.375e-05,
|
| 429 |
+
"loss": 0.4958,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07029288702928871,
|
| 434 |
+
"grad_norm": 1.4116944074630737,
|
| 435 |
+
"learning_rate": 1.4e-05,
|
| 436 |
+
"loss": 0.5011,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07154811715481171,
|
| 441 |
+
"grad_norm": 2.1076178550720215,
|
| 442 |
+
"learning_rate": 1.425e-05,
|
| 443 |
+
"loss": 0.5847,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07280334728033473,
|
| 448 |
+
"grad_norm": 1.6353111267089844,
|
| 449 |
+
"learning_rate": 1.45e-05,
|
| 450 |
+
"loss": 0.573,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.07405857740585774,
|
| 455 |
+
"grad_norm": 1.8148682117462158,
|
| 456 |
+
"learning_rate": 1.4750000000000003e-05,
|
| 457 |
+
"loss": 0.4973,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07531380753138076,
|
| 462 |
+
"grad_norm": 1.46212637424469,
|
| 463 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 464 |
+
"loss": 0.5187,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.07531380753138076,
|
| 469 |
+
"eval_accuracy": 0.7759381898454746,
|
| 470 |
+
"eval_f1": 0.5333333333333333,
|
| 471 |
+
"eval_loss": 0.4896416962146759,
|
| 472 |
+
"eval_precision": 0.6408839779005525,
|
| 473 |
+
"eval_recall": 0.4566929133858268,
|
| 474 |
+
"eval_runtime": 52.5243,
|
| 475 |
+
"eval_samples_per_second": 5.274,
|
| 476 |
+
"eval_steps_per_second": 0.171,
|
| 477 |
+
"step": 60
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.07656903765690376,
|
| 481 |
+
"grad_norm": 1.7205400466918945,
|
| 482 |
+
"learning_rate": 1.525e-05,
|
| 483 |
+
"loss": 0.4742,
|
| 484 |
+
"step": 61
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.07782426778242678,
|
| 488 |
+
"grad_norm": 1.6081304550170898,
|
| 489 |
+
"learning_rate": 1.55e-05,
|
| 490 |
+
"loss": 0.4835,
|
| 491 |
+
"step": 62
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.0790794979079498,
|
| 495 |
+
"grad_norm": 1.903638482093811,
|
| 496 |
+
"learning_rate": 1.575e-05,
|
| 497 |
+
"loss": 0.525,
|
| 498 |
+
"step": 63
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.0803347280334728,
|
| 502 |
+
"grad_norm": 1.9859038591384888,
|
| 503 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 504 |
+
"loss": 0.5183,
|
| 505 |
+
"step": 64
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.08158995815899582,
|
| 509 |
+
"grad_norm": 1.567049264907837,
|
| 510 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 511 |
+
"loss": 0.4662,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.08284518828451883,
|
| 516 |
+
"grad_norm": 1.9365341663360596,
|
| 517 |
+
"learning_rate": 1.65e-05,
|
| 518 |
+
"loss": 0.5389,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.08410041841004184,
|
| 523 |
+
"grad_norm": 2.623508930206299,
|
| 524 |
+
"learning_rate": 1.675e-05,
|
| 525 |
+
"loss": 0.4868,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.08535564853556485,
|
| 530 |
+
"grad_norm": 2.0028135776519775,
|
| 531 |
+
"learning_rate": 1.7e-05,
|
| 532 |
+
"loss": 0.5124,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.08661087866108787,
|
| 537 |
+
"grad_norm": 1.8613665103912354,
|
| 538 |
+
"learning_rate": 1.7250000000000003e-05,
|
| 539 |
+
"loss": 0.4848,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.08786610878661087,
|
| 544 |
+
"grad_norm": 2.0450963973999023,
|
| 545 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 546 |
+
"loss": 0.4746,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.08912133891213389,
|
| 551 |
+
"grad_norm": 2.370429515838623,
|
| 552 |
+
"learning_rate": 1.775e-05,
|
| 553 |
+
"loss": 0.4939,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.09037656903765691,
|
| 558 |
+
"grad_norm": 2.433497905731201,
|
| 559 |
+
"learning_rate": 1.8e-05,
|
| 560 |
+
"loss": 0.3848,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.09163179916317991,
|
| 565 |
+
"grad_norm": 2.043933868408203,
|
| 566 |
+
"learning_rate": 1.825e-05,
|
| 567 |
+
"loss": 0.4812,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.09288702928870293,
|
| 572 |
+
"grad_norm": 3.1938834190368652,
|
| 573 |
+
"learning_rate": 1.8500000000000002e-05,
|
| 574 |
+
"loss": 0.4042,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.09414225941422594,
|
| 579 |
+
"grad_norm": 2.2702953815460205,
|
| 580 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 581 |
+
"loss": 0.4561,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.09539748953974896,
|
| 586 |
+
"grad_norm": 2.0371036529541016,
|
| 587 |
+
"learning_rate": 1.9e-05,
|
| 588 |
+
"loss": 0.4152,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.09665271966527196,
|
| 593 |
+
"grad_norm": 2.1548779010772705,
|
| 594 |
+
"learning_rate": 1.925e-05,
|
| 595 |
+
"loss": 0.4596,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.09790794979079498,
|
| 600 |
+
"grad_norm": 2.221036195755005,
|
| 601 |
+
"learning_rate": 1.95e-05,
|
| 602 |
+
"loss": 0.3985,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.099163179916318,
|
| 607 |
+
"grad_norm": 2.6363329887390137,
|
| 608 |
+
"learning_rate": 1.9750000000000002e-05,
|
| 609 |
+
"loss": 0.4098,
|
| 610 |
+
"step": 79
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.100418410041841,
|
| 614 |
+
"grad_norm": 3.167816162109375,
|
| 615 |
+
"learning_rate": 2e-05,
|
| 616 |
+
"loss": 0.4811,
|
| 617 |
+
"step": 80
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.100418410041841,
|
| 621 |
+
"eval_accuracy": 0.7958057395143487,
|
| 622 |
+
"eval_f1": 0.5605700712589073,
|
| 623 |
+
"eval_loss": 0.4410252869129181,
|
| 624 |
+
"eval_precision": 0.7065868263473054,
|
| 625 |
+
"eval_recall": 0.4645669291338583,
|
| 626 |
+
"eval_runtime": 52.3433,
|
| 627 |
+
"eval_samples_per_second": 5.292,
|
| 628 |
+
"eval_steps_per_second": 0.172,
|
| 629 |
+
"step": 80
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.10167364016736402,
|
| 633 |
+
"grad_norm": 2.885763168334961,
|
| 634 |
+
"learning_rate": 1.9999903740631467e-05,
|
| 635 |
+
"loss": 0.4426,
|
| 636 |
+
"step": 81
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.10292887029288703,
|
| 640 |
+
"grad_norm": 3.0578081607818604,
|
| 641 |
+
"learning_rate": 1.9999614964379037e-05,
|
| 642 |
+
"loss": 0.3756,
|
| 643 |
+
"step": 82
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.10418410041841004,
|
| 647 |
+
"grad_norm": 2.6213362216949463,
|
| 648 |
+
"learning_rate": 1.9999133676802198e-05,
|
| 649 |
+
"loss": 0.3389,
|
| 650 |
+
"step": 83
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.10543933054393305,
|
| 654 |
+
"grad_norm": 2.924165964126587,
|
| 655 |
+
"learning_rate": 1.9998459887166635e-05,
|
| 656 |
+
"loss": 0.4445,
|
| 657 |
+
"step": 84
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.10669456066945607,
|
| 661 |
+
"grad_norm": 3.2457644939422607,
|
| 662 |
+
"learning_rate": 1.999759360844406e-05,
|
| 663 |
+
"loss": 0.3953,
|
| 664 |
+
"step": 85
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.10794979079497909,
|
| 668 |
+
"grad_norm": 3.2740261554718018,
|
| 669 |
+
"learning_rate": 1.9996534857311967e-05,
|
| 670 |
+
"loss": 0.3838,
|
| 671 |
+
"step": 86
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.10920502092050209,
|
| 675 |
+
"grad_norm": 2.938350200653076,
|
| 676 |
+
"learning_rate": 1.999528365415329e-05,
|
| 677 |
+
"loss": 0.3549,
|
| 678 |
+
"step": 87
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.11046025104602511,
|
| 682 |
+
"grad_norm": 3.5133864879608154,
|
| 683 |
+
"learning_rate": 1.9993840023056045e-05,
|
| 684 |
+
"loss": 0.3628,
|
| 685 |
+
"step": 88
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.11171548117154811,
|
| 689 |
+
"grad_norm": 4.392985820770264,
|
| 690 |
+
"learning_rate": 1.9992203991812823e-05,
|
| 691 |
+
"loss": 0.3628,
|
| 692 |
+
"step": 89
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.11297071129707113,
|
| 696 |
+
"grad_norm": 4.105576515197754,
|
| 697 |
+
"learning_rate": 1.9990375591920304e-05,
|
| 698 |
+
"loss": 0.3535,
|
| 699 |
+
"step": 90
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.11422594142259414,
|
| 703 |
+
"grad_norm": 3.1926333904266357,
|
| 704 |
+
"learning_rate": 1.9988354858578603e-05,
|
| 705 |
+
"loss": 0.3401,
|
| 706 |
+
"step": 91
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.11548117154811716,
|
| 710 |
+
"grad_norm": 3.768364191055298,
|
| 711 |
+
"learning_rate": 1.9986141830690626e-05,
|
| 712 |
+
"loss": 0.3704,
|
| 713 |
+
"step": 92
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.11673640167364016,
|
| 717 |
+
"grad_norm": 7.29379940032959,
|
| 718 |
+
"learning_rate": 1.9983736550861306e-05,
|
| 719 |
+
"loss": 0.4349,
|
| 720 |
+
"step": 93
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.11799163179916318,
|
| 724 |
+
"grad_norm": 2.7373130321502686,
|
| 725 |
+
"learning_rate": 1.9981139065396786e-05,
|
| 726 |
+
"loss": 0.3264,
|
| 727 |
+
"step": 94
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.1192468619246862,
|
| 731 |
+
"grad_norm": 6.39415979385376,
|
| 732 |
+
"learning_rate": 1.9978349424303532e-05,
|
| 733 |
+
"loss": 0.3619,
|
| 734 |
+
"step": 95
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.1205020920502092,
|
| 738 |
+
"grad_norm": 3.354396343231201,
|
| 739 |
+
"learning_rate": 1.9975367681287358e-05,
|
| 740 |
+
"loss": 0.338,
|
| 741 |
+
"step": 96
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.12175732217573222,
|
| 745 |
+
"grad_norm": 4.022518634796143,
|
| 746 |
+
"learning_rate": 1.99721938937524e-05,
|
| 747 |
+
"loss": 0.3851,
|
| 748 |
+
"step": 97
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.12301255230125523,
|
| 752 |
+
"grad_norm": 3.3857271671295166,
|
| 753 |
+
"learning_rate": 1.9968828122800022e-05,
|
| 754 |
+
"loss": 0.352,
|
| 755 |
+
"step": 98
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.12426778242677824,
|
| 759 |
+
"grad_norm": 3.325467824935913,
|
| 760 |
+
"learning_rate": 1.9965270433227623e-05,
|
| 761 |
+
"loss": 0.3588,
|
| 762 |
+
"step": 99
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.12552301255230125,
|
| 766 |
+
"grad_norm": 3.3111820220947266,
|
| 767 |
+
"learning_rate": 1.9961520893527385e-05,
|
| 768 |
+
"loss": 0.2811,
|
| 769 |
+
"step": 100
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.12552301255230125,
|
| 773 |
+
"eval_accuracy": 0.8101545253863135,
|
| 774 |
+
"eval_f1": 0.5825242718446602,
|
| 775 |
+
"eval_loss": 0.4248526096343994,
|
| 776 |
+
"eval_precision": 0.759493670886076,
|
| 777 |
+
"eval_recall": 0.47244094488188976,
|
| 778 |
+
"eval_runtime": 53.343,
|
| 779 |
+
"eval_samples_per_second": 5.193,
|
| 780 |
+
"eval_steps_per_second": 0.169,
|
| 781 |
+
"step": 100
|
| 782 |
+
}
|
| 783 |
+
],
|
| 784 |
+
"logging_steps": 1,
|
| 785 |
+
"max_steps": 796,
|
| 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": 3.634801281282867e+16,
|
| 802 |
+
"train_batch_size": 6,
|
| 803 |
+
"trial_name": null,
|
| 804 |
+
"trial_params": null
|
| 805 |
+
}
|