End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1212
-- Wer: 3.6561
+- Loss: 0.1142
+- Wer: 3.7226
 
 ## Model description
 
@@ -42,60 +42,33 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 4000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 0.1587        | 0.3676  | 100  | 0.1626          | 7.1105 |
-| 0.1464        | 0.7353  | 200  | 0.1325          | 5.7486 |
-| 0.0699        | 1.1029  | 300  | 0.1217          | 4.3894 |
-| 0.0714        | 1.4706  | 400  | 0.1147          | 4.2034 |
-| 0.0529        | 1.8382  | 500  | 0.1117          | 4.0358 |
-| 0.0315        | 2.2059  | 600  | 0.1087          | 3.8865 |
-| 0.0305        | 2.5735  | 700  | 0.1077          | 3.8787 |
-| 0.0307        | 2.9412  | 800  | 0.1031          | 3.5958 |
-| 0.0137        | 3.3088  | 900  | 0.1075          | 3.5304 |
-| 0.0125        | 3.6765  | 1000 | 0.1065          | 3.4858 |
-| 0.0103        | 4.0441  | 1100 | 0.1069          | 3.5592 |
-| 0.0066        | 4.4118  | 1200 | 0.1093          | 3.5539 |
-| 0.0063        | 4.7794  | 1300 | 0.1072          | 4.0332 |
-| 0.0043        | 5.1471  | 1400 | 0.1095          | 3.5880 |
-| 0.0045        | 5.5147  | 1500 | 0.1109          | 5.1672 |
-| 0.0048        | 5.8824  | 1600 | 0.1114          | 3.5723 |
-| 0.0035        | 6.25    | 1700 | 0.1128          | 3.5775 |
-| 0.0033        | 6.6176  | 1800 | 0.1117          | 4.6591 |
-| 0.0032        | 6.9853  | 1900 | 0.1132          | 3.5435 |
-| 0.0032        | 7.3529  | 2000 | 0.1138          | 3.5801 |
-| 0.0026        | 7.7206  | 2100 | 0.1151          | 3.6246 |
-| 0.0024        | 8.0882  | 2200 | 0.1155          | 3.6639 |
-| 0.0023        | 8.4559  | 2300 | 0.1167          | 3.6613 |
-| 0.0022        | 8.8235  | 2400 | 0.1176          | 3.6299 |
-| 0.0019        | 9.1912  | 2500 | 0.1177          | 3.5592 |
-| 0.0018        | 9.5588  | 2600 | 0.1169          | 3.5827 |
-| 0.0018        | 9.9265  | 2700 | 0.1175          | 3.5985 |
-| 0.0016        | 10.2941 | 2800 | 0.1183          | 3.6142 |
-| 0.0017        | 10.6618 | 2900 | 0.1190          | 3.6246 |
-| 0.0016        | 11.0294 | 3000 | 0.1184          | 3.6954 |
-| 0.0016        | 11.3971 | 3100 | 0.1192          | 3.6194 |
-| 0.0015        | 11.7647 | 3200 | 0.1197          | 3.6508 |
-| 0.0014        | 12.1324 | 3300 | 0.1202          | 3.6142 |
-| 0.0013        | 12.5    | 3400 | 0.1202          | 3.6194 |
-| 0.0014        | 12.8676 | 3500 | 0.1204          | 3.6561 |
-| 0.0013        | 13.2353 | 3600 | 0.1208          | 3.6351 |
-| 0.0014        | 13.6029 | 3700 | 0.1209          | 3.6561 |
-| 0.0013        | 13.9706 | 3800 | 0.1211          | 3.6456 |
-| 0.0014        | 14.3382 | 3900 | 0.1212          | 3.6613 |
-| 0.0013        | 14.7059 | 4000 | 0.1212          | 3.6561 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.0667        | 0.3534 | 100  | 0.1267          | 4.8230 |
+| 0.0693        | 0.7067 | 200  | 0.1188          | 4.1087 |
+| 0.0614        | 1.0601 | 300  | 0.1133          | 3.7907 |
+| 0.0274        | 1.4134 | 400  | 0.1128          | 3.7503 |
+| 0.0365        | 1.7668 | 500  | 0.1113          | 3.8513 |
+| 0.014         | 2.1201 | 600  | 0.1106          | 3.7201 |
+| 0.0165        | 2.4735 | 700  | 0.1116          | 3.7352 |
+| 0.0137        | 2.8269 | 800  | 0.1096          | 3.6999 |
+| 0.007         | 3.1802 | 900  | 0.1114          | 3.6216 |
+| 0.007         | 3.5336 | 1000 | 0.1130          | 3.6317 |
+| 0.0077        | 3.8869 | 1100 | 0.1128          | 3.6645 |
+| 0.0056        | 4.2403 | 1200 | 0.1138          | 3.7302 |
+| 0.005         | 4.5936 | 1300 | 0.1142          | 3.7226 |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.5.0+cu121
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
 - Datasets 3.1.0
-- Tokenizers 0.19.1
+- Tokenizers 0.20.3

generation_config.json

@@ -158,99 +158,10 @@
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
   "return_timestamps": 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": [],
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ee7230035ecb1104f14b7a9de94ac2200734a71f7c234038347ff4edbe8f90
+oid sha256:6ffb3af42b837d1636b54074d6590583c9e44fe5e6aa8ff39ceb078c37cac371
 size 290403936

runs/Nov16_04-24-38_cf84fc18aa82/events.out.tfevents.1731731099.cf84fc18aa82.2855.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb9f8c1168d97baa5c0867e39ad1de554cb8675ba86098b9ec3e1dd21e6492b
-size 19702
+oid sha256:39f704db49d6f6128f6f54cc9aaff9b32cd1581925a78b0c4422b94e371991a5
+size 21218