End of training

README.md

@@ -1,7 +1,10 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2_batangueno
   results: []
@@ -14,8 +17,8 @@ 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: 0.5103
-- Wer: 0.3127
+- Loss: 0.5957
+- Wer: 0.3902
 
 ## Model description
 
@@ -42,19 +45,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 30
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.5525        | 10.64 | 500  | 1.9745          | 1.0    |
-| 0.5882        | 21.28 | 1000 | 0.5103          | 0.3127 |
+| 3.665         | 10.64 | 500  | 2.2443          | 1.0    |
+| 0.6541        | 21.28 | 1000 | 0.5957          | 0.3902 |
 
 
 ### Framework versions
 
-- Transformers 4.17.0
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 1.18.3
 - Tokenizers 0.14.1

config.json

@@ -1,6 +1,7 @@
 {
   "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -110,7 +111,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.34.0",
   "use_weighted_layer_sum": false,
   "vocab_size": 32,
   "xvector_output_dim": 512

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1fb5e69d5a4a53015b43e12dcfa169b648f67201f145b1bbaf1da218e23d13
-size 377673441
+oid sha256:905698b4212676e5dfed35f08faebb0b9879fcda0e7b4651139a750df444f6f5
+size 377658785

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6378570125b9175cd3a99265e11046f70cf5544d97780ec50d6ab5fba3397b62
-size 3067
+oid sha256:d65fe8a0dc33835ece082264d2a8ae74efb531789b574f42fd9cee8fa5802b7c
+size 4091