End of training

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
-metrics:
-- wer
-base_model: facebook/wav2vec2-xls-r-300m
+datasets:
+- xtreme_s
 model-index:
 - name: wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
   results: []
@@ -15,10 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 6.9691
-- Wer: 1.1680
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the xtreme_s dataset.
 
 ## Model description
 
@@ -37,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -45,21 +42,17 @@ 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: 300
-- num_epochs: 600
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.4925        | 300.0 | 300  | 6.2580          | 1.0725 |
-| 0.0626        | 600.0 | 600  | 6.9691          | 1.1680 |
 
 
 ### Framework versions
 
 - Transformers 4.37.1
-- Pytorch 2.1.0+cu121
+- Pytorch 2.1.2+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.1

config.json

@@ -78,7 +78,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 30,
+  "pad_token_id": 62,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -104,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.37.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 33,
+  "vocab_size": 65,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d57cd133f4f23063d568fc2e3d893d211e9f164527128a2b933e08461b7b51
-size 1261942780
+oid sha256:60fd368398d469bcee760020fc80995d9f95ffb04e121c2e25c4c17d9632ddf8
+size 1262073980

preprocessor_config.json

@@ -4,6 +4,6 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Jan25_09-29-39_78d99ad982a5/events.out.tfevents.1706174981.78d99ad982a5.339.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65cd25a7ecd7d82af1c70c5c3669ad7db10d11bd1e762a537651cba1294a2bd
+size 6303

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebc7b77aa0373ca415c790e73f42164d7c104d92ce907b99fc2d09bebe80958
+oid sha256:3db2820d104018abf1e4975ba8fee41d6ee0e183e4e501b8ae2d139629675b76
 size 4792