End of training

README.md

@@ -1,18 +1,18 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
 datasets:
 - xtreme_s
 metrics:
 - wer
-base_model: facebook/wav2vec2-large-xlsr-53
 model-index:
 - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod2
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: xtreme_s
       type: xtreme_s
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: fleurs.id_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
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8568
+- Loss: 1.9422
 - Wer: 1.0
 
 ## Model description
@@ -60,7 +60,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 200
+- lr_scheduler_warmup_steps: 600
 - num_epochs: 60
 - mixed_precision_training: Native AMP
 
@@ -68,13 +68,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 5.1129        | 7.69  | 100  | 2.8923          | 1.0 |
-| 2.9331        | 15.38 | 200  | 2.8727          | 1.0 |
-| 2.9461        | 23.08 | 300  | 2.8772          | 1.0 |
-| 2.8889        | 30.77 | 400  | 2.8769          | 1.0 |
-| 2.8836        | 38.46 | 500  | 2.8693          | 1.0 |
-| 2.8748        | 46.15 | 600  | 2.8611          | 1.0 |
-| 2.8633        | 53.85 | 700  | 2.8568          | 1.0 |
+| 4.1308        | 9.23  | 300  | 2.8692          | 1.0 |
+| 2.8893        | 18.46 | 600  | 2.8467          | 1.0 |
+| 2.8682        | 27.69 | 900  | 2.8660          | 1.0 |
+| 2.84          | 36.92 | 1200 | 2.7426          | 1.0 |
+| 2.5025        | 46.15 | 1500 | 2.1426          | 1.0 |
+| 2.1729        | 55.38 | 1800 | 1.9422          | 1.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58505ca86256ded9d75cdeb33598295443a1d921627eb68882617dc518d02835
+oid sha256:5dcec334e4758af604dd169ae0d397589e9eef69fe5e269c8a2eecffc163e8ee
 size 1262073980

runs/Jan29_07-36-48_2971c7500582/events.out.tfevents.1706513856.2971c7500582.8809.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8b257ddb4efadcb730343d44bea66e7c84fc9d8cd6f782205efa0db194bce0
-size 8519
+oid sha256:f7e2408b4dd35c316de9df4063f6930e769f1a7daeb2382d5d887614c908d1ef
+size 9348