Training in progress, step 500

config.json

@@ -6,7 +6,7 @@
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
-  "attention_dropout": 0.2,
+  "attention_dropout": 0.3,
   "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -16,7 +16,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
   "decoder_start_token_id": 50258,
-  "dropout": 0.2,
+  "dropout": 0.3,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
@@ -42,7 +42,7 @@
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
-  "use_attention_mask": false,
+  "use_attention_mask": true,
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632595c4fe5d4d66d3404c7e43b299bd2e3802cc1a20a38ff63f75d3cacfc92e
+oid sha256:ea3c045d81b5030b6c885a4dc096526c299024ba0b2456244bd129c70ad7b9fa
 size 290403936

runs/Nov19_03-42-11_53be0e62afda/events.out.tfevents.1731987732.53be0e62afda.1551.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1cb69569b8d9b32846b2f5d6d427d7798ee4f67952b5ff89ea277fa454d70d
-size 15169
+oid sha256:7ac3301c36549ede310ff0289d043a3ed059c002ece5691f6139155e2941eb8e
+size 15380

runs/Nov19_04-56-18_53be0e62afda/events.out.tfevents.1731992183.53be0e62afda.1551.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb7fa1eea58d904ae34e39d1fba132d873403608b498df63baffcd1b8ec1562
+size 8638

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65c355ebf95a633300e4d7c8a823555f86153d79cd151941562098b8e6dec28
+oid sha256:08977ae79f1b63180425538f26eb8fa6b607bd238e969e5e86a83a348ffd531d
 size 5432