End of training

README.md

@@ -4,8 +4,6 @@ license: apache-2.0
 base_model: openai/whisper-base
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: whisper-base-zh
   results: []
@@ -18,8 +16,13 @@ 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: 0.4316
-- Wer: 85.1032
+- eval_loss: 0.3523
+- eval_wer: 77.0525
+- eval_runtime: 533.856
+- eval_samples_per_second: 3.606
+- eval_steps_per_second: 0.451
+- epoch: 4.7718
+- step: 2300
 
 ## Model description
 
@@ -38,64 +41,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-06
 - 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
+- lr_scheduler_warmup_steps: 100
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.5085        | 0.2070 | 100  | 0.4641          | 89.6326 |
-| 0.4047        | 0.4141 | 200  | 0.4315          | 88.2235 |
-| 0.4156        | 0.6211 | 300  | 0.4055          | 86.8646 |
-| 0.3826        | 0.8282 | 400  | 0.3907          | 87.2169 |
-| 0.3087        | 1.0352 | 500  | 0.3806          | 86.9149 |
-| 0.2709        | 1.2422 | 600  | 0.3775          | 87.0659 |
-| 0.2707        | 1.4493 | 700  | 0.3681          | 85.7071 |
-| 0.273         | 1.6563 | 800  | 0.3633          | 85.5561 |
-| 0.2638        | 1.8634 | 900  | 0.3592          | 85.4051 |
-| 0.1698        | 2.0704 | 1000 | 0.3613          | 85.6568 |
-| 0.1849        | 2.2774 | 1100 | 0.3628          | 85.7574 |
-| 0.1819        | 2.4845 | 1200 | 0.3645          | 85.4555 |
-| 0.1712        | 2.6915 | 1300 | 0.3611          | 84.8515 |
-| 0.1768        | 2.8986 | 1400 | 0.3573          | 84.3986 |
-| 0.1265        | 3.1056 | 1500 | 0.3640          | 85.2038 |
-| 0.1275        | 3.3126 | 1600 | 0.3661          | 85.4051 |
-| 0.1277        | 3.5197 | 1700 | 0.3698          | 84.3986 |
-| 0.1195        | 3.7267 | 1800 | 0.3684          | 85.3045 |
-| 0.1176        | 3.9337 | 1900 | 0.3668          | 84.9522 |
-| 0.0843        | 4.1408 | 2000 | 0.3764          | 84.9522 |
-| 0.077         | 4.3478 | 2100 | 0.3801          | 84.8012 |
-| 0.0853        | 4.5549 | 2200 | 0.3804          | 85.4051 |
-| 0.0826        | 4.7619 | 2300 | 0.3827          | 84.8515 |
-| 0.0759        | 4.9689 | 2400 | 0.3803          | 84.9522 |
-| 0.0519        | 5.1760 | 2500 | 0.3959          | 84.9522 |
-| 0.0578        | 5.3830 | 2600 | 0.3946          | 85.0528 |
-| 0.0594        | 5.5901 | 2700 | 0.3956          | 85.0528 |
-| 0.0598        | 5.7971 | 2800 | 0.3971          | 85.1535 |
-| 0.0519        | 6.0041 | 2900 | 0.3980          | 84.7509 |
-| 0.0421        | 6.2112 | 3000 | 0.4103          | 85.5058 |
-| 0.0379        | 6.4182 | 3100 | 0.4124          | 84.9019 |
-| 0.0363        | 6.6253 | 3200 | 0.4131          | 84.9019 |
-| 0.0377        | 6.8323 | 3300 | 0.4149          | 85.2038 |
-| 0.0286        | 7.0393 | 3400 | 0.4205          | 84.8515 |
-| 0.0263        | 7.2464 | 3500 | 0.4257          | 84.6502 |
-| 0.0309        | 7.4534 | 3600 | 0.4276          | 85.3548 |
-| 0.0295        | 7.6605 | 3700 | 0.4282          | 85.3045 |
-| 0.0266        | 7.8675 | 3800 | 0.4291          | 85.2038 |
-| 0.0241        | 8.0745 | 3900 | 0.4308          | 85.1535 |
-| 0.025         | 8.2816 | 4000 | 0.4316          | 85.1032 |
-
-
 ### 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 sha256:3e8a239321bd82d63104ac851bd9c451c442dec668a3179e9656f6da43b9e7e0
+oid sha256:1580bed24f3d2b9ce788254e3db0f83017356ca8188b018e5f4b3699436816dd
 size 290403936

runs/Nov16_20-57-52_1e51c95c58f0/events.out.tfevents.1731790675.1e51c95c58f0.2060.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e0dc118e91b9bf8ef454fd299938172e1593500f84c97887aca2fc5d7ffdd7
-size 29116
+oid sha256:aa6a0d0f4587fd7db38e6b127310086832f6d4eaf62e9d3df988be257279651e
+size 32602