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": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 4,
   "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": 4,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.52.2",
   "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 sha256:8be9c3f01993bfc158b3d8a63fca56bd814c5d4a539b6ad877d4f463a8ce4522
-size 966995080
+oid sha256:cfac290c02e092e59c28aa385dcfa9f348acaa0bdfb7e2ebd87715813c29427e
+size 151061672

runs/Jun01_07-16-11_d2cadc8cf957/events.out.tfevents.1748762185.d2cadc8cf957.201.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9028d6329f215857be14488838c9674bbd2fed7c58089685a9c0a7cc9c875e71
+size 11598

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c682c521ef8e7883dd2b717b3c32361ae2e69d6c66d4371ea62ac72e94200a
-size 5496
+oid sha256:8211af096364a91dcaa9291bab9132ed83a206b4e1c673fabb87fbeacb55cfdf
+size 5432