End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8768
+- Loss: 2.9977
 - Wer: 1.0
 
 ## Model description
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 2000
+- training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 2.9017        | 200.0 | 1000 | 2.9104          | 1.0 |
-| 2.7237        | 400.0 | 2000 | 2.8768          | 1.0 |
+| 3.1676        | 100.0 | 500  | 3.1581          | 1.0 |
+| 2.8849        | 200.0 | 1000 | 2.9977          | 1.0 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49ea321f22db993f0d775303120c281758e532f5a8771082f801c227a4ff115
+oid sha256:250d5eadf21f816ad9065003ee6659e5a6bacd015190f18aa4fe448520dd9334
 size 377658785

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8217faa69141aade9877f6fe0c337acf7ee0c53a95c5d08d25313524e41801d9
+oid sha256:0d60ca21714bcb7c6d3e20a4f9dcfd24698e47b0d90504334f2917ab32b78619
 size 4027