End of training

README.md

@@ -20,7 +20,12 @@ 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 VoxPopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4567
+- eval_loss: 0.4728
+- eval_runtime: 4.3194
+- eval_samples_per_second: 191.232
+- eval_steps_per_second: 24.078
+- epoch: 1273.5
+- step: 149000
 
 ## Model description
 
@@ -46,19 +51,9 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 150000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5279        | 8.55  | 1000 | 0.4791          |
-| 0.4992        | 17.09 | 2000 | 0.4619          |
-| 0.4883        | 25.64 | 3000 | 0.4586          |
-| 0.4804        | 34.19 | 4000 | 0.4567          |
-
-
 ### Framework versions
 
 - Transformers 4.38.0.dev0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfcd63e59c9a44d2ba2cd40635956b1fe0c7c63d1e2ce6be0fac11665f8c961
+oid sha256:94b5bd2380f03b6439d5a2a61017a0a4d31d126f7b1c5b2790fb0b17cbf54ab5
 size 577789320

runs/Feb09_15-35-25_dgxa100/events.out.tfevents.1707489328.dgxa100

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3f506e91a28c77d238a7d87023e33cdfd7abf8d6e5e7b991cc16fb0c70c594
-size 998395
+oid sha256:058634b1d147bca8df4433606eeff1ea84a133f7766448c8438adcad1d28f3aa
+size 1002351