Training in progress, step 1000

config.json

@@ -49,7 +49,7 @@
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",
   "feat_proj_dropout": 0.0,
-  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_num_heads": 0,
   "guided_attention_loss_scale": 10.0,
   "guided_attention_loss_sigma": 0.4,
   "hidden_act": "gelu",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81fac92cf15ded8c728a670a13ed2e4946d52eb80a9bc9d346b4822ab29a7f5
+oid sha256:bccecb6753492371ef2fc714c7b68c89daa94b6a3a9f03cbc6e4e6a4df96a028
 size 577789320

runs/Mar16_08-36-05_f90245d0e013/events.out.tfevents.1773650166.f90245d0e013

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da35cee585c4204c6c3ca3be77bf06ca9bc4d5e2153030961cf5270d5bc34ef
+size 14598

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae419bc3264ed66f7a186a656b1a064f96715cee921e9c14d1a402093e78f94
+oid sha256:bbae673cbba8935985a2c275330350d22b2e550ca83c328666ef833cffbf49c0
 size 5048