End of training

README.md

@@ -5,24 +5,9 @@ tags:
 - generated_from_trainer
 datasets:
 - common_voice_11_0
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-xls-r-300m-cv_vi
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: common_voice_11_0
-      type: common_voice_11_0
-      config: vi
-      split: test
-      args: vi
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.6293736974882088
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,9 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-xls-r-300m-cv_vi
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_11_0 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4553
-- Wer: 0.6294
 
 ## Model description
 
@@ -56,23 +38,18 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
+- lr_scheduler_warmup_steps: 7000
 - num_epochs: 30
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 8.9094        | 4.61  | 400  | 3.4930          | 1.0    |
-| 1.8862        | 9.22  | 800  | 1.4226          | 0.7562 |
-| 0.3298        | 13.83 | 1200 | 1.2513          | 0.6858 |
-| 0.1738        | 18.44 | 1600 | 1.4055          | 0.6732 |
-| 0.1134        | 23.05 | 2000 | 1.4623          | 0.6557 |
-| 0.0755        | 27.67 | 2400 | 1.4553          | 0.6294 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7a117f1e2fec87f4a4e65519f4e24fa43c6414a43792662c0f2409b298fd09
+oid sha256:b19cdc0be3b3ba797f894dd9d903b03ae32fc2af0065a2ba14092cf27fedc5b4
 size 1262303661

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea8bda4b0f91f8da23c2895d24f0a84467f385953ba25a0260d7cf666bacf44
+oid sha256:76898e22431e422ed2f50ee7ce06ad1c4c75439b195644757e13d6048031db8d
 size 4027