Training in progress, step 300

config.json

@@ -1,11 +1,11 @@
 {
-  "activation_dropout": 0.0,
+  "activation_dropout": 0.02,
   "activation_function": "gelu",
   "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.02,
   "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -15,7 +15,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.02,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cfe0617a3ab92a33a7ffd631d79bfcaedc62c3fa824c01b4067a2a824a299d
+oid sha256:237afda75d6b1087851b1e64950fadce591b97a5edcebc9e07ec1b59afd5ebe3
 size 966995080

runs/Nov14_17-05-08_38570736c0ee/events.out.tfevents.1763139915.38570736c0ee.38.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a439a926a787e8eaeee0352d0f7518fd3f348117aafbfd66c6eae54a2ff528ea
+size 13685

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986431e87c6193c1f7bde88a5413f115bb999aab30d020f0d37a94267a9ad5fc
+oid sha256:1f1891e7ba684b2e6b26af7a11094ded1a49fd0b099be1b2f0a55f5524b2a38c
 size 5432