Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "openai/whisper-medium",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -10,17 +10,17 @@
   "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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 24,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 24,
   "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
@@ -49,7 +49,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "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 sha256:513dc692465a7e65d2288bcb1bdb7aff132221e86d5e1651835f0a61dcc58270
-size 966995080
+oid sha256:c3e986152e107b238f2b6a26dd99d13fad194b8b42b3adbd11d40ce52f0db3ce
+size 3055544304

runs/Nov22_19-56-17_vaani-gpu-ins-1/events.out.tfevents.1732305380.vaani-gpu-ins-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328f826e149204d7bbd9e908755293c1410f22604b6b92b6c66a4f3e8be1138c
+size 15537

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfa0da0a6daa517c0a1b3392e8871f6685416aec8495121d4bc9e1e18f36af3
+oid sha256:5e3d01d6ebb3dfdc1a6ffd7e77e61e1fcfad0c0fb5e136450321b668519b00ad
 size 5432