End of training

README.md

@@ -1,26 +1,12 @@
 ---
+base_model: f77777/wav2vec2-large-xls-r-300m-firdousahamed-nep-colab
 tags:
 - generated_from_trainer
 datasets:
 - common_voice_13_0
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-xls-r-300m-firdousahamed-nep-colab
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: common_voice_13_0
-      type: common_voice_13_0
-      config: ne-NP
-      split: None
-      args: ne-NP
-    metrics:
-    - name: Wer
-      type: wer
-      value: 1.0
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-large-xls-r-300m-firdousahamed-nep-colab
 
-This model was trained from scratch on the common_voice_13_0 dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
-- Wer: 1.0
+This model is a fine-tuned version of [f77777/wav2vec2-large-xls-r-300m-firdousahamed-nep-colab](https://huggingface.co/f77777/wav2vec2-large-xls-r-300m-firdousahamed-nep-colab) on the common_voice_13_0 dataset.
 
 ## Model description
 
@@ -50,20 +33,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0003
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 30
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| No log        | 1.0   | 14   | nan             | 1.0 |
-| No log        | 2.0   | 28   | nan             | 1.0 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/wav2vec2-large-xls-r-300m-firdousahamed-nep-colab",
+  "_name_or_path": "f77777/wav2vec2-large-xls-r-300m-firdousahamed-nep-colab",
   "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Apr21_03-32-30_7b34f0633fa0/events.out.tfevents.1713670352.7b34f0633fa0.1901.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08aca3578249e9cea46c19402ef63a197ff3dacf9126d6ae84975d37e79182d4
+size 6260

runs/Apr21_03-32-47_7b34f0633fa0/events.out.tfevents.1713670405.7b34f0633fa0.1901.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd2ea42fc5086076f2a03194c28249971edf3b3677db7e8539b840758cdf21f
+size 6605

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa60672fbe801375d7ccb7c6af19b2b7a4e37b295e21bf8df414660835d239e
-size 4984
+oid sha256:64509d908465087a0a00a237542d9b12c748841c2a14565748b0171dd9146203
+size 4920