Training in progress, epoch 40

log.txt

@@ -296,3 +296,11 @@
 {'loss': 0.0199, 'grad_norm': 9.916908264160156, 'learning_rate': 1.1498074903745188e-05, 'epoch': 38.5}
 {'loss': 0.023, 'grad_norm': 0.0108343455940485, 'learning_rate': 1.1323066153307665e-05, 'epoch': 38.68}
 {'loss': 0.0198, 'grad_norm': 14.326728820800781, 'learning_rate': 1.1148057402870144e-05, 'epoch': 38.85}
+[3 3 1 ... 3 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 7.759762287139893, 'eval_accuracy': 0.41310064546975855, 'eval_runtime': 5.034, 'eval_samples_per_second': 830.946, 'eval_steps_per_second': 13.111, 'epoch': 39.0}
+{'loss': 0.0193, 'grad_norm': 16.8110294342041, 'learning_rate': 1.0973048652432621e-05, 'epoch': 39.03}
+{'loss': 0.0161, 'grad_norm': 16.760862350463867, 'learning_rate': 1.0798039901995102e-05, 'epoch': 39.2}
+{'loss': 0.018, 'grad_norm': 0.7209157943725586, 'learning_rate': 1.0623031151557579e-05, 'epoch': 39.38}
+{'loss': 0.0208, 'grad_norm': 13.089346885681152, 'learning_rate': 1.0448022401120058e-05, 'epoch': 39.55}
+{'loss': 0.0191, 'grad_norm': 9.088654518127441, 'learning_rate': 1.0273013650682535e-05, 'epoch': 39.73}
+{'loss': 0.0185, 'grad_norm': 0.02565234899520874, 'learning_rate': 1.0098004900245014e-05, 'epoch': 39.9}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4737570a7863c922f1e5164a2984c5e055408ee03a46792d113af860ff8079
+oid sha256:837370d8452ea6183c7858364eaf8d6dffe0af58b8c5c9d845e70dbdb9123dfb
 size 267829484

runs/Mar13_17-26-31_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710375994.cehsc-app-001.ad.unlv.edu.3270813.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923a16493dd8cd41dc2209cda6259d18cbdcd1ccb0b4a7a3f7d92e6ea70a0b3d
-size 65078
+oid sha256:e8bf9e62c17fc2bdf7976372a84e842e66065bf102a9534eb495663d738fa807
+size 66697