Model save

README.md

@@ -32,15 +32,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 15
 - mixed_precision_training: Native AMP
 

config.json

@@ -25,20 +25,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 32,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -56,96 +43,7 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "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,
-    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,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
+  "suppress_tokens": [],
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_cache": true,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b86d7b6af24ad53ae2a73df2ec6fb7c6addfc1b3203f87e581d6fbbc52813f
+oid sha256:69b450ed68277c1450c62bf75a3b3432761f706127d048008a015171c7b7af57
 size 4992706480

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7f64d220924aa05d952ac9ce6b56a0f6da8752819a6091fd5353e6531ec806
+oid sha256:50495652d41d82584900ebc8b8ce0cc7b7e5648f1bdf63e5a68dedaba3cd8ab4
 size 1180663192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c8a7be8e33f4c3ff4dce0708fdfe9c1a83aafdb4e9c3e9db2cca7490d71529
+oid sha256:80236a5400903c1272642bdd66f887a6ca42ea66786033202c9ca6fb67377ffe
 size 5048