Training in progress, step 100

config.json

@@ -9,17 +9,17 @@
   "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
@@ -48,7 +48,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f261a8f001f3d39b634c8e32d13edb6b2e784e9378a4c82c6bbbf40a9691ace
-size 966995080
+oid sha256:38a5e644c2520e3a852f059fc325ad634a48a3e77a33a61a835746e643589e89
+size 290403936

runs/Jul11_05-49-17_ffccf608ed55/events.out.tfevents.1752212978.ffccf608ed55.927.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca0f9495e3089034567d356bdd6471c31f98a591bdc4db4bfae0564ed6c7ae1
+size 7914

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044729f044bc05dbdf42392b6917ac74adce821fc02ae7d7661055bf5fead158
-size 5560
+oid sha256:f2607fc38b97eae81ae993601e27e3a067175cb2a6b1ad44435203fcff3f7fbb
+size 5496