Training in progress, step 300

config.json

@@ -1,11 +1,11 @@
 {
-  "activation_dropout": 0.1,
+  "activation_dropout": 0.08,
   "activation_function": "gelu",
   "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.08,
   "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": 0.1,
+  "dropout": 0.08,
   "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 sha256:265ba72f16e51b07e813e31de477e77e271ea89953b727e7a548fe986f447a15
+oid sha256:aa1e78b406d4c765c2ef1469a5ade75296445ee9386702655d52b1dadd9651df
 size 966995080

runs/Oct13_15-34-32_2204c93af372/events.out.tfevents.1760369681.2204c93af372.36.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9542f512fd965af2d40caca9a161dd658c378e59526606c01d3922d9c3e782ea
-size 35495
+oid sha256:315ee30afd6be68d25cd2d36789dfbe29af7bb08447584294216ab4ddd69aba1
+size 37394

runs/Oct13_19-44-12_2204c93af372/events.out.tfevents.1760384677.2204c93af372.36.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e80fb347b5dec5a0bf6e0ad4c370e444be3f4699a2c2dee474e83352698065f
+size 14049

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbaf57e49825326ffc8059f7644b61b5796e1be4ab8eda9ead679d8f2d79e8f6
+oid sha256:6559cf77f43bec1ed3ea64c06d4407789b2a6b9267f0030d4fa580b59615f875
 size 5432