End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2366
-- Accuracy: 0.9429
+- Loss: nan
+- Accuracy: 0.7297
 
 ## Model description
 
@@ -44,18 +44,19 @@ 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: 50
-- training_steps: 500
+- training_steps: 6000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.6175        | 0.0053 | 100  | 0.5800          | 0.7297   |
-| 0.5478        | 0.0105 | 200  | 0.5069          | 0.7297   |
-| 0.3762        | 0.0158 | 300  | 0.3544          | 0.7713   |
-| 0.2103        | 0.0211 | 400  | 0.2486          | 0.9394   |
-| 0.2034        | 0.0263 | 500  | 0.2366          | 0.9429   |
+| 0.0625        | 0.0527 | 1000 | 0.0503          | 0.9897   |
+| 0.0757        | 0.1053 | 2000 | 0.0616          | 0.9897   |
+| 0.0231        | 0.1580 | 3000 | 0.0574          | 0.9913   |
+| 0.0439        | 0.2107 | 4000 | nan             | 0.7342   |
+| 0.0           | 0.2633 | 5000 | nan             | 0.7297   |
+| 0.0           | 0.3160 | 6000 | nan             | 0.7297   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c872dbcb73cdab2b4ea3ce07ca274064fa6abd5231a0b7229bc4f597a24e8c9
+oid sha256:06168968dba7da942ae0ec49bb2053fd6591cb3d5d60df4044cb337674e2850f
 size 1262858456