End of training

config.json

@@ -8,22 +8,22 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50256
+    50257
   ],
-  "bos_token_id": 50256,
+  "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 256,
-  "decoder_attention_heads": 4,
-  "decoder_ffn_dim": 1536,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 50257,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 4,
-  "encoder_ffn_dim": 1536,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 50256,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
       1,
@@ -46,13 +46,14 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
+  "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
-  "pad_token_id": 50256,
+  "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",

generation_config.json

@@ -2,11 +2,114 @@
   "_from_model_config": true,
   "begin_suppress_tokens": [
     220,
-    50256
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "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,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50360,
+    50361,
+    50362
   ],
-  "bos_token_id": 50256,
-  "decoder_start_token_id": 50257,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
   "transformers_version": "4.31.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df980d6d878a7ebaad35123d4564c74ac89fed23cc00c6624dd34ae1bdea230
-size 113048417
+oid sha256:a06c370da1ca4431f8a9fa516bdcaa4791f046c4accb1ef547a3751f90d41064
+size 967096009

runs/Sep19_14-49-37_tracy/events.out.tfevents.1695115181.tracy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf381823e45f04cad3babbfde6f9f5ee1e604d62683f3ad71a6dcc62565d258
+size 5225

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93eee562fa4da78c669da012a3adabb4e533fda96fea64c2f040abd03041692
+oid sha256:54dea0a050a1c1a8ee39f772b846bf9b21cc3082a4b898eb9691eaf79900578c
 size 4091