End of training

README.md

@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 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_13_0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5797
-- eval_wer: 0.7171
-- eval_runtime: 38.1008
-- eval_samples_per_second: 21.286
-- eval_steps_per_second: 2.677
-- epoch: 3.94
-- step: 2000
+- eval_loss: 1.5610
+- eval_wer: 0.9291
+- eval_runtime: 39.0397
+- eval_samples_per_second: 20.774
+- eval_steps_per_second: 2.613
+- epoch: 26.01
+- step: 13200
 
 ## Model description
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 30
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc52abe5d454384876d3c32ea804db728f581b9990d9d89b3bd4934b1ab7877c
+oid sha256:e80f2f06c0a4c01bfcb11cca8cecd704352978cec51dff7849f71018bf4cfca9
 size 1262135533