End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0664
-- Wer: 99.6730
+- Wer: 100.4905
 
 ## Model description
 
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| No log        | 6.9565  | 10   | 2.1992          | 99.5749 |
-| No log        | 13.9130 | 20   | 2.0664          | 99.6730 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer      |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| No log        | 6.9565  | 10   | 2.1992          | 102.3218 |
+| No log        | 13.9130 | 20   | 2.0664          | 100.4905 |
 
 
 ### Framework versions

runs/Sep25_06-20-06_ip-10-0-4-196/events.out.tfevents.1727245292.ip-10-0-4-196

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdea3e3097e0cbf5cfa6727edd56bc496ca3fba378ca00ff1e94ddec7127d491
-size 7104
+oid sha256:77ac658c72bc5ef0798d0260746da2d61c177bff20e80af4d07e53d687f8be6b
+size 7764