End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
-base_model: openai/whisper-small
 datasets:
 - common_voice_13_0
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: Compare-XLS-R-to-Whisper-demo-google-colab-Ezra_William_Prod
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: common_voice_13_0
       type: common_voice_13_0
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: id
     metrics:
-    - type: wer
+    - name: Wer
+      type: wer
       value: 1.0
-      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -52,21 +52,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 1e-06
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 12
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 0.0           | 1.0   | 556  | nan             | 1.0 |
-| 0.0           | 2.0   | 1112 | nan             | 1.0 |
-| 0.0           | 3.0   | 1668 | nan             | 1.0 |
+| 0.0           | 1.0   | 278  | nan             | 1.0 |
+| 0.0           | 2.0   | 556  | nan             | 1.0 |
+| 0.0           | 3.0   | 834  | nan             | 1.0 |
+| 0.0           | 4.0   | 1112 | nan             | 1.0 |
+| 0.0           | 5.0   | 1390 | nan             | 1.0 |
+| 0.0           | 6.0   | 1668 | nan             | 1.0 |
+| 0.0           | 7.0   | 1946 | nan             | 1.0 |
+| 0.0           | 8.0   | 2224 | nan             | 1.0 |
+| 0.0           | 9.0   | 2502 | nan             | 1.0 |
+| 0.0           | 10.0  | 2780 | nan             | 1.0 |
+| 0.0           | 11.0  | 3058 | nan             | 1.0 |
+| 0.0           | 12.0  | 3336 | nan             | 1.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b861f304a019cee25a7c5c476363e882a06b147ede4e8f6fcc3d04ca25c2626
+oid sha256:6cea041471b0fc12d8dcf9d10463c8c96ced9386ec76c66680a8e8b8ca325f82
 size 377651116

runs/Jun12_21-28-00_e0e2c397659e/events.out.tfevents.1718227800.e0e2c397659e.1337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c843b8f899242a6bb348dc524e7c2141fbf4f5d4904432e90a4cf9a8e41bf8a
+size 19043

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b75eb265a375c8dfd2b6008d63c4ed50f03f4df26efaa9bc0180524dfe329c
+oid sha256:9ef748a5f73c9b7b50ddd469d272a0066e94150654d0905404ea34679df9ea68
 size 5176