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: 0.0159
-- Wer Score: 0.0853
+- Loss: 0.8754
+- Wer Score: 0.1947
 
 ## Model description
 
@@ -41,18 +41,16 @@ 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: 5
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | 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    |
+| 7.5362        | 0.9091 | 50   | 5.0569          | 12.4513   |
+| 3.5403        | 1.8182 | 100  | 2.0086          | 12.2035   |
+| 1.4121        | 2.7273 | 150  | 0.8754          | 0.1947    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11485090fe4e34e1caa5b5708a75534ced114552e98d89da20135636e40a5a6
+oid sha256:3738f2e10517931631b62197ad2be7433b8f3b633593d76b0ed4110c7d85bb44
 size 706516040

runs/Jun25_17-13-30_2c089c048155/events.out.tfevents.1719335611.2c089c048155.4491.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5810d454de1dd86f4f631d31eb174053e98c392374990b8eb9a9aaf9e23bbc95
-size 5561
+oid sha256:77f336939f9aa4fd5f251b3690dd710a670b1881ac08b421be12c291e30f6581
+size 6975