Model save

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0153
-- Wer Score: 10.3101
+- Loss: 0.0159
+- Wer Score: 0.0853
 
 ## Model description
 
@@ -41,29 +41,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer Score |
-|:-------------:|:-------:|:----:|:---------------:|:---------:|
-| 7.3651        | 0.9091  | 50   | 4.4704          | 3.7287    |
-| 2.2873        | 1.8182  | 100  | 0.3801          | 0.2171    |
-| 0.1229        | 2.7273  | 150  | 0.0296          | 10.8450   |
-| 0.0263        | 3.6364  | 200  | 0.0190          | 0.1705    |
-| 0.0161        | 4.5455  | 250  | 0.0135          | 0.1085    |
-| 0.0124        | 5.4545  | 300  | 0.0168          | 0.1085    |
-| 0.0126        | 6.3636  | 350  | 0.0109          | 0.0775    |
-| 0.0105        | 7.2727  | 400  | 0.0119          | 0.1163    |
-| 0.01          | 8.1818  | 450  | 0.0142          | 0.1085    |
-| 0.0093        | 9.0909  | 500  | 0.0113          | 10.1628   |
-| 0.0091        | 10.0    | 550  | 0.0143          | 0.1163    |
-| 0.0082        | 10.9091 | 600  | 0.0146          | 0.1163    |
-| 0.0079        | 11.8182 | 650  | 0.0141          | 10.3256   |
-| 0.0074        | 12.7273 | 700  | 0.0144          | 10.2636   |
-| 0.0072        | 13.6364 | 750  | 0.0152          | 10.3411   |
-| 0.0068        | 14.5455 | 800  | 0.0153          | 10.3101   |
+| Training Loss | Epoch  | Step | Validation Loss | Wer Score |
+|:-------------:|:------:|:----:|:---------------:|:---------:|
+| 7.4394        | 0.9091 | 50   | 4.7350          | 9.1395    |
+| 2.8448        | 1.8182 | 100  | 0.9714          | 4.1550    |
+| 0.3926        | 2.7273 | 150  | 0.0756          | 0.1395    |
+| 0.0504        | 3.6364 | 200  | 0.0248          | 0.1473    |
+| 0.0212        | 4.5455 | 250  | 0.0159          | 0.0853    |
 
 
 ### Framework versions

runs/Jun24_20-42-21_8e3b1ee642f7/events.out.tfevents.1719261748.8e3b1ee642f7.3835.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae8df12b7e6475d4e640e8cb003dccaa3206d9548f6e7f7391639fcc08110f5
-size 7691
+oid sha256:dd1b17bc92d9361063a7542e10cad949dcee0ad690545cf2124074d4d141aac6
+size 8045