End of training

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
@@ -15,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3686
-- eval_runtime: 7.6727
-- eval_samples_per_second: 21.374
-- eval_steps_per_second: 1.434
-- epoch: 69.5652
-- step: 3200
+- Loss: 0.3886
 
 ## Model description
 
@@ -39,18 +35,37 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 2
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 400
-- training_steps: 4000
+- lr_scheduler_warmup_steps: 200
+- training_steps: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.5085        | 4.3360  | 200  | 0.4609          |
+| 0.4697        | 8.6721  | 400  | 0.4265          |
+| 0.4509        | 13.0081 | 600  | 0.4111          |
+| 0.4289        | 17.3442 | 800  | 0.4057          |
+| 0.4208        | 21.6802 | 1000 | 0.4049          |
+| 0.4136        | 26.0163 | 1200 | 0.3990          |
+| 0.4072        | 30.3523 | 1400 | 0.3980          |
+| 0.4011        | 34.6883 | 1600 | 0.3920          |
+| 0.3971        | 39.0244 | 1800 | 0.3905          |
+| 0.3898        | 43.3604 | 2000 | 0.3886          |
+
 
 ### Framework versions
 
-- Transformers 4.40.0
-- Pytorch 2.4.1+cu124
+- Transformers 4.46.3
+- Pytorch 2.10.0+cu128
 - Datasets 2.19.0
-- Tokenizers 0.19.1
+- Tokenizers 0.20.3

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.46.3"
 }