End of training

README.md

@@ -1,15 +1,13 @@
 ---
 license: mit
-base_model: Edmon02/speecht5_finetuned_hy
+base_model: Edmon02/speecht5_finetuned_voxpopuli_hy
 tags:
 - generated_from_trainer
+datasets:
+- common_voice_17_0
 model-index:
 - name: speecht5_finetuned_voxpopuli_hy
   results: []
-datasets:
-- mozilla-foundation/common_voice_17_0
-language:
-- hy
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_hy
 
-This model is a fine-tuned version of [Edmon02/speecht5_finetuned_hy](https://huggingface.co/Edmon02/speecht5_finetuned_hy) on the None dataset.
+This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_hy](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_hy) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6214
+- Loss: 0.5088
 
 ## Model description
 
@@ -38,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
@@ -46,27 +44,27 @@ 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: 1000
+- lr_scheduler_warmup_steps: 250
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 0.7717        | 4.4199  | 500  | 0.7195          |
-| 0.7361        | 8.8398  | 1000 | 0.6810          |
-| 0.7088        | 13.2597 | 1500 | 0.6597          |
-| 0.6942        | 17.6796 | 2000 | 0.6465          |
-| 0.6835        | 22.0994 | 2500 | 0.6367          |
-| 0.6753        | 26.5193 | 3000 | 0.6309          |
-| 0.6734        | 30.9392 | 3500 | 0.6245          |
-| 0.6747        | 35.3591 | 4000 | 0.6214          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5974        | 1.2114 | 500  | 0.5489          |
+| 0.57          | 2.4228 | 1000 | 0.5261          |
+| 0.5684        | 3.6342 | 1500 | 0.5201          |
+| 0.5516        | 4.8455 | 2000 | 0.5144          |
+| 0.5521        | 6.0569 | 2500 | 0.5134          |
+| 0.5436        | 7.2683 | 3000 | 0.5116          |
+| 0.5434        | 8.4797 | 3500 | 0.5105          |
+| 0.5449        | 9.6911 | 4000 | 0.5088          |
 
 
 ### Framework versions
 
-- Transformers 4.43.3
-- Pytorch 2.4.0+cu121
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.42.4"
 }