End of training

README.md

@@ -16,8 +16,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4131
-- Wer Score: 24.1207
+- Loss: 0.0573
+- Wer Score: 0.6707
 
 ## Model description
 
@@ -37,25 +37,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Score |
 |:-------------:|:------:|:----:|:---------------:|:---------:|
-| 6.6954        | 0.9474 | 9    | 6.1194          | 24.2241   |
-| 5.8759        | 1.8947 | 18   | 5.4065          | 24.1552   |
-| 5.2401        | 2.8421 | 27   | 4.8795          | 24.1379   |
-| 4.7997        | 3.7895 | 36   | 4.5462          | 24.1034   |
-| 4.5467        | 4.7368 | 45   | 4.4131          | 24.1207   |
+| 7.4065        | 2.1277 | 50   | 4.7483          | 20.4625   |
+| 2.9029        | 4.2553 | 100  | 1.1386          | 12.1695   |
+| 0.5188        | 6.3830 | 150  | 0.1472          | 0.7676    |
+| 0.0871        | 8.5106 | 200  | 0.0573          | 0.6707    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23dda9102c7814f77d42aeefd08d5ef21e044202cab67a72c3be8987a0e19b01
+oid sha256:32339843a69f87e810c653e3e556dddbfd50349a9fa918af77f51019522d79a9
 size 706516040

runs/Oct01_07-37-45_cbf5861e1559/events.out.tfevents.1727768270.cbf5861e1559.6782.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6cc5b05d4d429b986eb2d20aad051d6b4c6a1ab4d1677debe21b39ea7b827d
-size 7247
+oid sha256:205f916e9ca532e9015426cf02bc72f8a11bfe858c56adbbab89acb38fcbfa69
+size 7601