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 sha256:91f268d6f1c02a6bcffe9b69cb02125edf3ed394508b0a72915847d4abf4d38a
|
| 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:b4390c765a10454451e6637f646c7ee3de5916471255934f2b28005336ff62ab
|
| 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:dbf4488f97f48d8eec5fe4fb5c65e0fc203257e006d2da3dac449c5f11befd59
|
| 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 sha256:16f57e6baab85aef9f3987e89ed9bb24ff8783133cdb8b05b1f0c42f465789fd
|
| 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:e56c527a4b46ce93e60755b5246f49c281427d55e2aecbe9bd806b47a31ec3f0
|
| 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 sha256:40c4fc9de677d8f30c357d4f0c52cbec65a101eb8050f52cbae690a0c85c9ae3
|
| 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:ca4a0923d94e13dcc2f3e7c5ec43790d1d0f6dc4dffd5897d4a43bfbefc9684a
|
| 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 sha256:5736f7c3c93a7e68e3969752bf23448739cb265393b70d1a9888a852386f4db1
|
| 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 sha256:88bbe0dc30d7f00590a26acb3b9f980e2398fa208f750dab94c02256be71eee9
|
| 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:b9aeac2ef30f0ea83b5fe26f1910a995da1dcae2b9e5b67b95fc89866c365f45
|
| 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 sha256:67a02ed65f1e8b1d5b53759509278028feb0bbbd832210bb513184a0c3914508
|
| 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 sha256:7621b58e8394fb77a4651720150070950e3a4b44cfe98ababeb6f8601fb569ee
|
| 3 |
+
size 14960
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:219024013de80e1e441f10f45b80072241f3d99e22bf7c142252fbd0909bf2bb
|
| 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": 0.09276437847866419,
|
| 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": 0.738359201773836,
|
| 14 |
+
"eval_f1": 0.23376623376623376,
|
| 15 |
+
"eval_loss": 0.5994226336479187,
|
| 16 |
+
"eval_precision": 0.6545454545454545,
|
| 17 |
+
"eval_recall": 0.1422924901185771,
|
| 18 |
+
"eval_runtime": 47.8594,
|
| 19 |
+
"eval_samples_per_second": 5.767,
|
| 20 |
+
"eval_steps_per_second": 0.188,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0009276437847866419,
|
| 25 |
+
"grad_norm": 2.113847255706787,
|
| 26 |
+
"learning_rate": 1.8518518518518518e-07,
|
| 27 |
+
"loss": 0.6464,
|
| 28 |
+
"step": 1
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.0018552875695732839,
|
| 32 |
+
"grad_norm": 2.337275505065918,
|
| 33 |
+
"learning_rate": 3.7037037037037036e-07,
|
| 34 |
+
"loss": 0.7325,
|
| 35 |
+
"step": 2
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.0027829313543599257,
|
| 39 |
+
"grad_norm": 2.0731401443481445,
|
| 40 |
+
"learning_rate": 5.555555555555555e-07,
|
| 41 |
+
"loss": 0.6441,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0037105751391465678,
|
| 46 |
+
"grad_norm": 2.075726270675659,
|
| 47 |
+
"learning_rate": 7.407407407407407e-07,
|
| 48 |
+
"loss": 0.6722,
|
| 49 |
+
"step": 4
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.00463821892393321,
|
| 53 |
+
"grad_norm": 2.2193410396575928,
|
| 54 |
+
"learning_rate": 9.259259259259259e-07,
|
| 55 |
+
"loss": 0.6676,
|
| 56 |
+
"step": 5
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.0055658627087198514,
|
| 60 |
+
"grad_norm": 2.2222299575805664,
|
| 61 |
+
"learning_rate": 1.111111111111111e-06,
|
| 62 |
+
"loss": 0.5932,
|
| 63 |
+
"step": 6
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.006493506493506494,
|
| 67 |
+
"grad_norm": 2.5532214641571045,
|
| 68 |
+
"learning_rate": 1.2962962962962962e-06,
|
| 69 |
+
"loss": 0.6558,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.0074211502782931356,
|
| 74 |
+
"grad_norm": 1.7259494066238403,
|
| 75 |
+
"learning_rate": 1.4814814814814815e-06,
|
| 76 |
+
"loss": 0.5976,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.008348794063079777,
|
| 81 |
+
"grad_norm": 2.020770788192749,
|
| 82 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 83 |
+
"loss": 0.6576,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.00927643784786642,
|
| 88 |
+
"grad_norm": 2.5885586738586426,
|
| 89 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 90 |
+
"loss": 0.6656,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.01020408163265306,
|
| 95 |
+
"grad_norm": 1.901673674583435,
|
| 96 |
+
"learning_rate": 2.037037037037037e-06,
|
| 97 |
+
"loss": 0.6293,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.011131725417439703,
|
| 102 |
+
"grad_norm": 1.867441177368164,
|
| 103 |
+
"learning_rate": 2.222222222222222e-06,
|
| 104 |
+
"loss": 0.5698,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.012059369202226345,
|
| 109 |
+
"grad_norm": 2.405125141143799,
|
| 110 |
+
"learning_rate": 2.4074074074074075e-06,
|
| 111 |
+
"loss": 0.5984,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.012987012987012988,
|
| 116 |
+
"grad_norm": 2.0719292163848877,
|
| 117 |
+
"learning_rate": 2.5925925925925925e-06,
|
| 118 |
+
"loss": 0.5933,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.013914656771799629,
|
| 123 |
+
"grad_norm": 2.2819459438323975,
|
| 124 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 125 |
+
"loss": 0.6439,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.014842300556586271,
|
| 130 |
+
"grad_norm": 2.3114988803863525,
|
| 131 |
+
"learning_rate": 2.962962962962963e-06,
|
| 132 |
+
"loss": 0.6118,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.015769944341372914,
|
| 137 |
+
"grad_norm": 2.1615548133850098,
|
| 138 |
+
"learning_rate": 3.1481481481481483e-06,
|
| 139 |
+
"loss": 0.5185,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.016697588126159554,
|
| 144 |
+
"grad_norm": 2.3003029823303223,
|
| 145 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 146 |
+
"loss": 0.6267,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.017625231910946195,
|
| 151 |
+
"grad_norm": 2.284081220626831,
|
| 152 |
+
"learning_rate": 3.5185185185185187e-06,
|
| 153 |
+
"loss": 0.6659,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.01855287569573284,
|
| 158 |
+
"grad_norm": 1.8381303548812866,
|
| 159 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 160 |
+
"loss": 0.572,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.01855287569573284,
|
| 165 |
+
"eval_accuracy": 0.7394678492239468,
|
| 166 |
+
"eval_f1": 0.22950819672131148,
|
| 167 |
+
"eval_loss": 0.5945659279823303,
|
| 168 |
+
"eval_precision": 0.6730769230769231,
|
| 169 |
+
"eval_recall": 0.1383399209486166,
|
| 170 |
+
"eval_runtime": 47.6156,
|
| 171 |
+
"eval_samples_per_second": 5.796,
|
| 172 |
+
"eval_steps_per_second": 0.189,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.01948051948051948,
|
| 177 |
+
"grad_norm": 2.036238670349121,
|
| 178 |
+
"learning_rate": 3.88888888888889e-06,
|
| 179 |
+
"loss": 0.6409,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.02040816326530612,
|
| 184 |
+
"grad_norm": 1.9110214710235596,
|
| 185 |
+
"learning_rate": 4.074074074074074e-06,
|
| 186 |
+
"loss": 0.6008,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.021335807050092765,
|
| 191 |
+
"grad_norm": 2.4081571102142334,
|
| 192 |
+
"learning_rate": 4.2592592592592596e-06,
|
| 193 |
+
"loss": 0.632,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.022263450834879406,
|
| 198 |
+
"grad_norm": 1.9782453775405884,
|
| 199 |
+
"learning_rate": 4.444444444444444e-06,
|
| 200 |
+
"loss": 0.6474,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.023191094619666047,
|
| 205 |
+
"grad_norm": 1.7934902906417847,
|
| 206 |
+
"learning_rate": 4.62962962962963e-06,
|
| 207 |
+
"loss": 0.5803,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.02411873840445269,
|
| 212 |
+
"grad_norm": 2.6915359497070312,
|
| 213 |
+
"learning_rate": 4.814814814814815e-06,
|
| 214 |
+
"loss": 0.6505,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.02504638218923933,
|
| 219 |
+
"grad_norm": 1.806140422821045,
|
| 220 |
+
"learning_rate": 5e-06,
|
| 221 |
+
"loss": 0.5283,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.025974025974025976,
|
| 226 |
+
"grad_norm": 1.7927738428115845,
|
| 227 |
+
"learning_rate": 5.185185185185185e-06,
|
| 228 |
+
"loss": 0.5696,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.026901669758812616,
|
| 233 |
+
"grad_norm": 1.7386640310287476,
|
| 234 |
+
"learning_rate": 5.370370370370371e-06,
|
| 235 |
+
"loss": 0.4902,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.027829313543599257,
|
| 240 |
+
"grad_norm": 2.015052318572998,
|
| 241 |
+
"learning_rate": 5.555555555555557e-06,
|
| 242 |
+
"loss": 0.6123,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.0287569573283859,
|
| 247 |
+
"grad_norm": 1.620802402496338,
|
| 248 |
+
"learning_rate": 5.740740740740741e-06,
|
| 249 |
+
"loss": 0.5611,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.029684601113172542,
|
| 254 |
+
"grad_norm": 1.8895862102508545,
|
| 255 |
+
"learning_rate": 5.925925925925926e-06,
|
| 256 |
+
"loss": 0.6024,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.030612244897959183,
|
| 261 |
+
"grad_norm": 2.030715227127075,
|
| 262 |
+
"learning_rate": 6.111111111111112e-06,
|
| 263 |
+
"loss": 0.6245,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.03153988868274583,
|
| 268 |
+
"grad_norm": 2.208017349243164,
|
| 269 |
+
"learning_rate": 6.296296296296297e-06,
|
| 270 |
+
"loss": 0.5331,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.032467532467532464,
|
| 275 |
+
"grad_norm": 2.373842239379883,
|
| 276 |
+
"learning_rate": 6.481481481481482e-06,
|
| 277 |
+
"loss": 0.638,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.03339517625231911,
|
| 282 |
+
"grad_norm": 2.170443296432495,
|
| 283 |
+
"learning_rate": 6.666666666666667e-06,
|
| 284 |
+
"loss": 0.563,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.03432282003710575,
|
| 289 |
+
"grad_norm": 1.4894213676452637,
|
| 290 |
+
"learning_rate": 6.851851851851853e-06,
|
| 291 |
+
"loss": 0.5338,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.03525046382189239,
|
| 296 |
+
"grad_norm": 1.9410276412963867,
|
| 297 |
+
"learning_rate": 7.0370370370370375e-06,
|
| 298 |
+
"loss": 0.5609,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.036178107606679034,
|
| 303 |
+
"grad_norm": 2.315661668777466,
|
| 304 |
+
"learning_rate": 7.222222222222223e-06,
|
| 305 |
+
"loss": 0.4866,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.03710575139146568,
|
| 310 |
+
"grad_norm": 1.8483999967575073,
|
| 311 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 312 |
+
"loss": 0.5829,
|
| 313 |
+
"step": 40
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.03710575139146568,
|
| 317 |
+
"eval_accuracy": 0.7494456762749445,
|
| 318 |
+
"eval_f1": 0.2848101265822785,
|
| 319 |
+
"eval_loss": 0.5677995681762695,
|
| 320 |
+
"eval_precision": 0.7142857142857143,
|
| 321 |
+
"eval_recall": 0.17786561264822134,
|
| 322 |
+
"eval_runtime": 46.6917,
|
| 323 |
+
"eval_samples_per_second": 5.911,
|
| 324 |
+
"eval_steps_per_second": 0.193,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.038033395176252316,
|
| 329 |
+
"grad_norm": 2.0759365558624268,
|
| 330 |
+
"learning_rate": 7.592592592592594e-06,
|
| 331 |
+
"loss": 0.5541,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.03896103896103896,
|
| 336 |
+
"grad_norm": 1.7480107545852661,
|
| 337 |
+
"learning_rate": 7.77777777777778e-06,
|
| 338 |
+
"loss": 0.5236,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.039888682745825604,
|
| 343 |
+
"grad_norm": 1.8141703605651855,
|
| 344 |
+
"learning_rate": 7.962962962962963e-06,
|
| 345 |
+
"loss": 0.519,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.04081632653061224,
|
| 350 |
+
"grad_norm": 1.8323687314987183,
|
| 351 |
+
"learning_rate": 8.148148148148148e-06,
|
| 352 |
+
"loss": 0.5472,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.041743970315398886,
|
| 357 |
+
"grad_norm": 1.6657449007034302,
|
| 358 |
+
"learning_rate": 8.333333333333334e-06,
|
| 359 |
+
"loss": 0.4735,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.04267161410018553,
|
| 364 |
+
"grad_norm": 2.900596857070923,
|
| 365 |
+
"learning_rate": 8.518518518518519e-06,
|
| 366 |
+
"loss": 0.5968,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.04359925788497217,
|
| 371 |
+
"grad_norm": 1.9013563394546509,
|
| 372 |
+
"learning_rate": 8.703703703703705e-06,
|
| 373 |
+
"loss": 0.5436,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.04452690166975881,
|
| 378 |
+
"grad_norm": 1.7270978689193726,
|
| 379 |
+
"learning_rate": 8.888888888888888e-06,
|
| 380 |
+
"loss": 0.4987,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.045454545454545456,
|
| 385 |
+
"grad_norm": 1.4679995775222778,
|
| 386 |
+
"learning_rate": 9.074074074074075e-06,
|
| 387 |
+
"loss": 0.4405,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.04638218923933209,
|
| 392 |
+
"grad_norm": 2.332545042037964,
|
| 393 |
+
"learning_rate": 9.25925925925926e-06,
|
| 394 |
+
"loss": 0.5181,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.04730983302411874,
|
| 399 |
+
"grad_norm": 2.0095181465148926,
|
| 400 |
+
"learning_rate": 9.444444444444445e-06,
|
| 401 |
+
"loss": 0.5561,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.04823747680890538,
|
| 406 |
+
"grad_norm": 2.628974199295044,
|
| 407 |
+
"learning_rate": 9.62962962962963e-06,
|
| 408 |
+
"loss": 0.5791,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.04916512059369202,
|
| 413 |
+
"grad_norm": 1.918746829032898,
|
| 414 |
+
"learning_rate": 9.814814814814815e-06,
|
| 415 |
+
"loss": 0.5171,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.05009276437847866,
|
| 420 |
+
"grad_norm": 1.907528281211853,
|
| 421 |
+
"learning_rate": 1e-05,
|
| 422 |
+
"loss": 0.5104,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.05102040816326531,
|
| 427 |
+
"grad_norm": 1.70274817943573,
|
| 428 |
+
"learning_rate": 1.0185185185185186e-05,
|
| 429 |
+
"loss": 0.5104,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.05194805194805195,
|
| 434 |
+
"grad_norm": 2.177898406982422,
|
| 435 |
+
"learning_rate": 1.037037037037037e-05,
|
| 436 |
+
"loss": 0.4683,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.05287569573283859,
|
| 441 |
+
"grad_norm": 2.1687746047973633,
|
| 442 |
+
"learning_rate": 1.0555555555555557e-05,
|
| 443 |
+
"loss": 0.4888,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.05380333951762523,
|
| 448 |
+
"grad_norm": 3.19343900680542,
|
| 449 |
+
"learning_rate": 1.0740740740740742e-05,
|
| 450 |
+
"loss": 0.5476,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.05473098330241188,
|
| 455 |
+
"grad_norm": 2.7876338958740234,
|
| 456 |
+
"learning_rate": 1.0925925925925926e-05,
|
| 457 |
+
"loss": 0.4876,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.055658627087198514,
|
| 462 |
+
"grad_norm": 2.028104066848755,
|
| 463 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 464 |
+
"loss": 0.4808,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.055658627087198514,
|
| 469 |
+
"eval_accuracy": 0.7694013303769401,
|
| 470 |
+
"eval_f1": 0.45549738219895286,
|
| 471 |
+
"eval_loss": 0.512853741645813,
|
| 472 |
+
"eval_precision": 0.6744186046511628,
|
| 473 |
+
"eval_recall": 0.3438735177865613,
|
| 474 |
+
"eval_runtime": 46.8717,
|
| 475 |
+
"eval_samples_per_second": 5.888,
|
| 476 |
+
"eval_steps_per_second": 0.192,
|
| 477 |
+
"step": 60
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.05658627087198516,
|
| 481 |
+
"grad_norm": 2.1539430618286133,
|
| 482 |
+
"learning_rate": 1.1296296296296297e-05,
|
| 483 |
+
"loss": 0.5098,
|
| 484 |
+
"step": 61
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.0575139146567718,
|
| 488 |
+
"grad_norm": 2.1614112854003906,
|
| 489 |
+
"learning_rate": 1.1481481481481482e-05,
|
| 490 |
+
"loss": 0.4424,
|
| 491 |
+
"step": 62
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.05844155844155844,
|
| 495 |
+
"grad_norm": 2.3000025749206543,
|
| 496 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 497 |
+
"loss": 0.4228,
|
| 498 |
+
"step": 63
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.059369202226345084,
|
| 502 |
+
"grad_norm": 2.695854663848877,
|
| 503 |
+
"learning_rate": 1.1851851851851852e-05,
|
| 504 |
+
"loss": 0.4409,
|
| 505 |
+
"step": 64
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.06029684601113173,
|
| 509 |
+
"grad_norm": 2.0516905784606934,
|
| 510 |
+
"learning_rate": 1.2037037037037039e-05,
|
| 511 |
+
"loss": 0.5061,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.061224489795918366,
|
| 516 |
+
"grad_norm": 2.1683146953582764,
|
| 517 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 518 |
+
"loss": 0.4346,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.06215213358070501,
|
| 523 |
+
"grad_norm": 1.7861865758895874,
|
| 524 |
+
"learning_rate": 1.2407407407407408e-05,
|
| 525 |
+
"loss": 0.4451,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.06307977736549165,
|
| 530 |
+
"grad_norm": 2.505061626434326,
|
| 531 |
+
"learning_rate": 1.2592592592592593e-05,
|
| 532 |
+
"loss": 0.4545,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.0640074211502783,
|
| 537 |
+
"grad_norm": 2.663344621658325,
|
| 538 |
+
"learning_rate": 1.2777777777777777e-05,
|
| 539 |
+
"loss": 0.4741,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.06493506493506493,
|
| 544 |
+
"grad_norm": 2.4229860305786133,
|
| 545 |
+
"learning_rate": 1.2962962962962964e-05,
|
| 546 |
+
"loss": 0.4564,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.06586270871985157,
|
| 551 |
+
"grad_norm": 1.9748098850250244,
|
| 552 |
+
"learning_rate": 1.314814814814815e-05,
|
| 553 |
+
"loss": 0.4832,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.06679035250463822,
|
| 558 |
+
"grad_norm": 2.0413177013397217,
|
| 559 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 560 |
+
"loss": 0.4377,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.06771799628942486,
|
| 565 |
+
"grad_norm": 2.965312957763672,
|
| 566 |
+
"learning_rate": 1.351851851851852e-05,
|
| 567 |
+
"loss": 0.3847,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.0686456400742115,
|
| 572 |
+
"grad_norm": 3.3258345127105713,
|
| 573 |
+
"learning_rate": 1.3703703703703706e-05,
|
| 574 |
+
"loss": 0.441,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.06957328385899815,
|
| 579 |
+
"grad_norm": 4.911780834197998,
|
| 580 |
+
"learning_rate": 1.388888888888889e-05,
|
| 581 |
+
"loss": 0.5277,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.07050092764378478,
|
| 586 |
+
"grad_norm": 3.556264638900757,
|
| 587 |
+
"learning_rate": 1.4074074074074075e-05,
|
| 588 |
+
"loss": 0.5102,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.07142857142857142,
|
| 593 |
+
"grad_norm": 2.313514232635498,
|
| 594 |
+
"learning_rate": 1.4259259259259259e-05,
|
| 595 |
+
"loss": 0.3874,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.07235621521335807,
|
| 600 |
+
"grad_norm": 2.3410682678222656,
|
| 601 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 602 |
+
"loss": 0.3794,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.07328385899814471,
|
| 607 |
+
"grad_norm": 1.974550724029541,
|
| 608 |
+
"learning_rate": 1.4629629629629631e-05,
|
| 609 |
+
"loss": 0.3691,
|
| 610 |
+
"step": 79
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.07421150278293136,
|
| 614 |
+
"grad_norm": 3.7399516105651855,
|
| 615 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 616 |
+
"loss": 0.498,
|
| 617 |
+
"step": 80
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.07421150278293136,
|
| 621 |
+
"eval_accuracy": 0.7804878048780488,
|
| 622 |
+
"eval_f1": 0.5217391304347826,
|
| 623 |
+
"eval_loss": 0.46577775478363037,
|
| 624 |
+
"eval_precision": 0.6708074534161491,
|
| 625 |
+
"eval_recall": 0.4268774703557312,
|
| 626 |
+
"eval_runtime": 47.3211,
|
| 627 |
+
"eval_samples_per_second": 5.832,
|
| 628 |
+
"eval_steps_per_second": 0.19,
|
| 629 |
+
"step": 80
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.075139146567718,
|
| 633 |
+
"grad_norm": 4.030659198760986,
|
| 634 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 635 |
+
"loss": 0.4012,
|
| 636 |
+
"step": 81
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.07606679035250463,
|
| 640 |
+
"grad_norm": 4.128874778747559,
|
| 641 |
+
"learning_rate": 1.5185185185185187e-05,
|
| 642 |
+
"loss": 0.4411,
|
| 643 |
+
"step": 82
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.07699443413729128,
|
| 647 |
+
"grad_norm": 5.405181884765625,
|
| 648 |
+
"learning_rate": 1.537037037037037e-05,
|
| 649 |
+
"loss": 0.3886,
|
| 650 |
+
"step": 83
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.07792207792207792,
|
| 654 |
+
"grad_norm": 2.473198175430298,
|
| 655 |
+
"learning_rate": 1.555555555555556e-05,
|
| 656 |
+
"loss": 0.3348,
|
| 657 |
+
"step": 84
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.07884972170686456,
|
| 661 |
+
"grad_norm": 3.9382104873657227,
|
| 662 |
+
"learning_rate": 1.5740740740740744e-05,
|
| 663 |
+
"loss": 0.3732,
|
| 664 |
+
"step": 85
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.07977736549165121,
|
| 668 |
+
"grad_norm": 2.209444761276245,
|
| 669 |
+
"learning_rate": 1.5925925925925926e-05,
|
| 670 |
+
"loss": 0.3247,
|
| 671 |
+
"step": 86
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.08070500927643785,
|
| 675 |
+
"grad_norm": 4.216385364532471,
|
| 676 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 677 |
+
"loss": 0.4295,
|
| 678 |
+
"step": 87
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.08163265306122448,
|
| 682 |
+
"grad_norm": 4.730212211608887,
|
| 683 |
+
"learning_rate": 1.6296296296296297e-05,
|
| 684 |
+
"loss": 0.3214,
|
| 685 |
+
"step": 88
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.08256029684601113,
|
| 689 |
+
"grad_norm": 2.821192741394043,
|
| 690 |
+
"learning_rate": 1.6481481481481482e-05,
|
| 691 |
+
"loss": 0.3864,
|
| 692 |
+
"step": 89
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.08348794063079777,
|
| 696 |
+
"grad_norm": 2.9178500175476074,
|
| 697 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 698 |
+
"loss": 0.3257,
|
| 699 |
+
"step": 90
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.08441558441558442,
|
| 703 |
+
"grad_norm": 4.074183464050293,
|
| 704 |
+
"learning_rate": 1.6851851851851853e-05,
|
| 705 |
+
"loss": 0.3916,
|
| 706 |
+
"step": 91
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.08534322820037106,
|
| 710 |
+
"grad_norm": 2.721669912338257,
|
| 711 |
+
"learning_rate": 1.7037037037037038e-05,
|
| 712 |
+
"loss": 0.3153,
|
| 713 |
+
"step": 92
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.0862708719851577,
|
| 717 |
+
"grad_norm": 4.657402992248535,
|
| 718 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 719 |
+
"loss": 0.4462,
|
| 720 |
+
"step": 93
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.08719851576994433,
|
| 724 |
+
"grad_norm": 2.9709548950195312,
|
| 725 |
+
"learning_rate": 1.740740740740741e-05,
|
| 726 |
+
"loss": 0.3124,
|
| 727 |
+
"step": 94
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.08812615955473098,
|
| 731 |
+
"grad_norm": 5.8010711669921875,
|
| 732 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 733 |
+
"loss": 0.2713,
|
| 734 |
+
"step": 95
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.08905380333951762,
|
| 738 |
+
"grad_norm": 3.4263553619384766,
|
| 739 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 740 |
+
"loss": 0.3161,
|
| 741 |
+
"step": 96
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.08998144712430427,
|
| 745 |
+
"grad_norm": 3.680510997772217,
|
| 746 |
+
"learning_rate": 1.7962962962962965e-05,
|
| 747 |
+
"loss": 0.3464,
|
| 748 |
+
"step": 97
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.09090909090909091,
|
| 752 |
+
"grad_norm": 5.526573657989502,
|
| 753 |
+
"learning_rate": 1.814814814814815e-05,
|
| 754 |
+
"loss": 0.2899,
|
| 755 |
+
"step": 98
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.09183673469387756,
|
| 759 |
+
"grad_norm": 3.2282707691192627,
|
| 760 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 761 |
+
"loss": 0.2088,
|
| 762 |
+
"step": 99
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.09276437847866419,
|
| 766 |
+
"grad_norm": 3.8928277492523193,
|
| 767 |
+
"learning_rate": 1.851851851851852e-05,
|
| 768 |
+
"loss": 0.2531,
|
| 769 |
+
"step": 100
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.09276437847866419,
|
| 773 |
+
"eval_accuracy": 0.8015521064301552,
|
| 774 |
+
"eval_f1": 0.5665859564164649,
|
| 775 |
+
"eval_loss": 0.4834875166416168,
|
| 776 |
+
"eval_precision": 0.73125,
|
| 777 |
+
"eval_recall": 0.4624505928853755,
|
| 778 |
+
"eval_runtime": 48.1977,
|
| 779 |
+
"eval_samples_per_second": 5.726,
|
| 780 |
+
"eval_steps_per_second": 0.187,
|
| 781 |
+
"step": 100
|
| 782 |
+
}
|
| 783 |
+
],
|
| 784 |
+
"logging_steps": 1,
|
| 785 |
+
"max_steps": 1078,
|
| 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": 3.184988301085901e+16,
|
| 802 |
+
"train_batch_size": 8,
|
| 803 |
+
"trial_name": null,
|
| 804 |
+
"trial_params": null
|
| 805 |
+
}
|