End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: microsoft/speecht5_tts
+tags:
+- generated_from_trainer
+model-index:
+- name: zlm_b32_le5_s12000
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zlm_b32_le5_s12000
+
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3561
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- training_steps: 12050
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.4311        | 0.2094 | 500   | 0.3863          |
+| 0.4432        | 0.4188 | 1000  | 0.3867          |
+| 0.4185        | 0.6281 | 1500  | 0.3835          |
+| 0.4257        | 0.8375 | 2000  | 0.3799          |
+| 0.4112        | 1.0469 | 2500  | 0.3801          |
+| 0.4178        | 1.2563 | 3000  | 0.3758          |
+| 0.4069        | 1.4657 | 3500  | 0.3738          |
+| 0.4015        | 1.6750 | 4000  | 0.3724          |
+| 0.4155        | 1.8844 | 4500  | 0.3700          |
+| 0.4126        | 2.0938 | 5000  | 0.3674          |
+| 0.4084        | 2.3032 | 5500  | 0.3662          |
+| 0.396         | 2.5126 | 6000  | 0.3621          |
+| 0.4084        | 2.7219 | 6500  | 0.3648          |
+| 0.3949        | 2.9313 | 7000  | 0.3608          |
+| 0.4045        | 3.1407 | 7500  | 0.3619          |
+| 0.4078        | 3.3501 | 8000  | 0.3607          |
+| 0.3926        | 3.5595 | 8500  | 0.3583          |
+| 0.4007        | 3.7688 | 9000  | 0.3579          |
+| 0.3899        | 3.9782 | 9500  | 0.3589          |
+| 0.3902        | 4.1876 | 10000 | 0.3566          |
+| 0.4023        | 4.3970 | 10500 | 0.3594          |
+| 0.3971        | 4.6064 | 11000 | 0.3552          |
+| 0.3956        | 4.8157 | 11500 | 0.3562          |
+| 0.3974        | 5.0251 | 12000 | 0.3561          |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca926d7c3960557026bab3ac966ec219f413fb37a78592cfd22eab4b2bbc78ca
+oid sha256:4986febb703a2545e82aa6231a48dee257352b827a6f9f32839997a65f406aa0
 size 577789320

runs/Apr28_16-29-57_04d99b6f0733/events.out.tfevents.1714321798.04d99b6f0733.4857.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bf6962c8b4daa80afb8a7de239b9828dad872f28093f4b08d91c2b26d07399
-size 63624
+oid sha256:fdc7cfec7607e7ced5db9a062e6d642fda90996b5f94e2ae1a436c56b0e7cb28
+size 64189