Model save

README.md

@@ -34,20 +34,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 8
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 300
-- training_steps: 3000
-- mixed_precision_training: Native AMP
+- lr_scheduler_warmup_steps: 150
+- training_steps: 1500
 
 ### Framework versions
 
 - Transformers 4.53.2
 - Pytorch 2.6.0+cu124
-- Datasets 4.0.0
+- Datasets 2.14.4
 - Tokenizers 0.21.2

config.json

@@ -6,7 +6,6 @@
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
   "d_model": 1280,
@@ -21,7 +20,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 32,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -30,7 +28,6 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": null,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,
@@ -39,7 +36,7 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.53.2",
   "use_cache": false,
   "use_weighted_layer_sum": false,

generation_config.json

@@ -218,7 +218,96 @@
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
   "return_timestamps": false,
-  "suppress_tokens": [],
+  "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
+  ],
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3508d59734fe44bab3c9b3f1f413d0d808cdeba5dbf8ce0a6fc76cdd9982e2d
+size 4992706480

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b6b78a5b694bed18907c4ee943758dfae3d579257411381e7786d6300d0a58
+size 1180663192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6038b811fd79b4ce583fbd7f04f9e13dc4b2b623c9c7227cff6927b45c2721
+oid sha256:137d0929f18565db19c616bcb7392ee4c71db13d6459f3f5e43b4d22e421d5b2
 size 5560