End of training

README.md

@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_hy](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_hy) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4599
-- eval_runtime: 13.0209
-- eval_samples_per_second: 37.094
-- eval_steps_per_second: 9.293
-- epoch: 14.7194
-- step: 2000
+- Loss: 0.4146
 
 ## Model description
 
@@ -51,6 +46,20 @@ The following hyperparameters were used during training:
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch    | Step | Validation Loss |
+|:-------------:|:--------:|:----:|:---------------:|
+| 0.4505        | 16.1290  | 500  | 0.4243          |
+| 0.4401        | 32.2581  | 1000 | 0.4246          |
+| 0.4346        | 48.3871  | 1500 | 0.4201          |
+| 0.4272        | 64.5161  | 2000 | 0.4183          |
+| 0.4293        | 80.6452  | 2500 | 0.4160          |
+| 0.4215        | 96.7742  | 3000 | 0.4149          |
+| 0.4159        | 112.9032 | 3500 | 0.4142          |
+| 0.4152        | 129.0323 | 4000 | 0.4146          |
+
+
 ### Framework versions
 
 - Transformers 4.43.3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e2f4f73f87b0c23e43f0945f3ed86914ddd22b06a6055401a4a2f54ff82b8a
+oid sha256:1efa1998a04e1af0a82b05a098a1cd9d3042ce62d52d01a2e056e78d65584e52
 size 577887624