Training in progress, step 500

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": 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": [
     [
@@ -48,12 +48,12 @@
   "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,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.51.2",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b28d0c0f72951cde17a3b1bc0c549d520e936f8e01d5046ac71bfdb77b3a6ab
-size 966995080
+oid sha256:b996b6fe77fb58f7d76dc5d422947a8892a488cea00ef353edeba4629e7b4a65
+size 3055544304

runs/Apr11_10-43-35_ip-172-31-38-156/events.out.tfevents.1744368222.ip-172-31-38-156.5365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06adb0a127055b97300f4cab8811aebd4e85478a660b57473283f843e538f08f
+size 11667

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f32ba44490b458dcbe49562a5245e615cd7a3561e3d2072ad349c1039389c74
+oid sha256:f3397f1f471e85eabab9146117dce579d634c27f93b109a00423b68777e3ff8b
 size 5496