Training in progress, step 5000

config.json

@@ -8,29 +8,23 @@
   ],
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
-    220,
-    50256
+    1541
   ],
-  "bos_token_id": 50257,
+  "bos_token_id": 1546,
   "classifier_proj_size": 256,
   "d_model": 768,
   "decoder_attention_heads": 12,
   "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "decoder_start_token_id": 50257,
+  "decoder_start_token_id": 1546,
   "dropout": 0.0,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
-  "eos_token_id": 50256,
-  "forced_decoder_ids": [
-    [
-      1,
-      50362
-    ]
-  ],
+  "eos_token_id": 1541,
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -39,110 +33,26 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": 448,
+  "max_length": 512,
   "max_source_positions": 1500,
-  "max_target_positions": 448,
+  "max_target_positions": 512,
   "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 12,
   "num_mel_bins": 80,
-  "pad_token_id": 50256,
+  "pad_token_id": 1541,
   "scale_embedding": false,
   "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    357,
-    366,
-    438,
-    532,
-    685,
-    705,
-    796,
-    930,
-    1058,
-    1220,
-    1267,
-    1279,
-    1303,
-    1343,
-    1377,
-    1391,
-    1635,
-    1782,
-    1875,
-    2162,
-    2361,
-    2488,
-    3467,
-    4008,
-    4211,
-    4600,
-    4808,
-    5299,
-    5855,
-    6329,
-    7203,
-    9609,
-    9959,
-    10563,
-    10786,
-    11420,
-    11709,
-    11907,
-    13163,
-    13697,
-    13700,
-    14808,
-    15306,
-    16410,
-    16791,
-    17992,
-    19203,
-    19510,
-    20724,
-    22305,
-    22935,
-    27007,
-    30109,
-    30420,
-    33409,
-    34949,
-    40283,
-    40493,
-    40549,
-    47282,
-    49146,
-    50257,
-    50357,
-    50358,
-    50359,
-    50360,
-    50361
+    1546,
+    1548,
+    1547,
+    1544,
+    1545,
+    1542
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51864
+  "vocab_size": 1549
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b76a193d39659f946f662f382749c4194d6a381254920bade93f28997b7e89
-size 966992008
+oid sha256:2d9a87bb0f09b681ca1446cfaa48550f6dbe3f199713c54736e4a8cc364c1036
+size 817182816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a37eaafbf60fec9f78060f0e8a52b0d5fdc4856683fc7cd8d4eade1b027dc09
-size 5240
+oid sha256:8ce83fe46fdd2f27622c268af045ebf91760763f77aa934b399fe0067407b292
+size 7480