Training in progress, step 2000

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20240327_190513-7p2x8a0l/run-7p2x8a0l.wandb filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b28427eca5db81abd6c0b41b5a828e9deac65e6e8d7d071ed00be3850a7dda
+oid sha256:7739bdf3b7d2d335f50c1a3089d6342e1704066cd74b22de2569d20355529615
 size 3025686376

runs/Mar27_19-04-58_hf-dgx-01/events.out.tfevents.1711562712.hf-dgx-01.1894903.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d2088d006f005c7eb61e37b06f361c2c53843da4442f53136b5f5981f55f50
-size 14123
+oid sha256:fce9b7059b879eed8123406b6db0293671926595e1881a5858f5cf2e1b04ee7e
+size 22881

wandb/run-20240327_190513-7p2x8a0l/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.1059, "train/grad_norm": 1.7170511484146118, "train/learning_rate": 8.78888888888889e-05, "train/epoch": 4.73, "train/global_step": 1050, "_timestamp": 1711565906.6150107, "_runtime": 3192.9672026634216, "_step": 42, "eval/loss": 0.30151915550231934, "eval/wer": 0.3249633006258209, "eval/runtime": 1360.3971, "eval/samples_per_second": 2.296, "eval/steps_per_second": 0.072}
+{"train/loss": 0.0124, "train/grad_norm": 0.7414669990539551, "train/learning_rate": 6.622222222222224e-05, "train/epoch": 9.12, "train/global_step": 2025, "_timestamp": 1711568907.3259914, "_runtime": 6193.678183317184, "_step": 82, "eval/loss": 0.3495735228061676, "eval/wer": 0.30066445182724255, "eval/runtime": 1282.4445, "eval/samples_per_second": 2.435, "eval/steps_per_second": 0.076}