End of training

README.md

@@ -18,8 +18,8 @@ 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.4972
-- Wer Score: 39.8
+- Loss: 6.1918
+- Wer Score: 39.6
 
 ## Model description
 
@@ -38,28 +38,39 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_restarts
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 85
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 8.3012        | 2.5   | 10   | 8.0024          | 140.2     |
-| 7.8744        | 5.0   | 20   | 7.5821          | 140.4     |
-| 7.4706        | 7.5   | 30   | 7.2110          | 140.4     |
-| 7.1213        | 10.0  | 40   | 6.9042          | 100.4     |
-| 6.85          | 12.5  | 50   | 6.6843          | 47.8      |
-| 6.6704        | 15.0  | 60   | 6.5571          | 40.6      |
-| 6.5787        | 17.5  | 70   | 6.5053          | 40.0      |
-| 6.5497        | 20.0  | 80   | 6.4972          | 39.8      |
+| 8.3548        | 5.0   | 10   | 8.2504          | 134.8     |
+| 8.3219        | 10.0  | 20   | 8.1985          | 138.2     |
+| 8.2518        | 15.0  | 30   | 8.1159          | 139.6     |
+| 8.1592        | 20.0  | 40   | 8.0218          | 140.0     |
+| 8.0551        | 25.0  | 50   | 7.9160          | 140.2     |
+| 7.9388        | 30.0  | 60   | 7.7972          | 140.4     |
+| 7.807         | 35.0  | 70   | 7.6597          | 140.4     |
+| 7.6548        | 40.0  | 80   | 7.4993          | 139.8     |
+| 7.4774        | 45.0  | 90   | 7.3130          | 140.4     |
+| 7.2745        | 50.0  | 100  | 7.0992          | 140.4     |
+| 7.0447        | 55.0  | 110  | 6.8640          | 139.8     |
+| 6.8103        | 60.0  | 120  | 6.6401          | 95.8      |
+| 6.6006        | 65.0  | 130  | 6.4553          | 103.6     |
+| 6.4349        | 70.0  | 140  | 6.3183          | 39.6      |
+| 6.3224        | 75.0  | 150  | 6.2360          | 39.6      |
+| 6.2614        | 80.0  | 160  | 6.1996          | 39.6      |
+| 6.2396        | 85.0  | 170  | 6.1918          | 39.6      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548ef0a4823179db81543536b1baf32c9750066a25a0a201f5e4585dd9aea70b
+oid sha256:81f917d1a0423a42de363c1be695226075df360c302ec5549cd743d7cf4205ec
 size 706516040

runs/Oct20_19-23-19_bfc8df5d81ba/events.out.tfevents.1729452206.bfc8df5d81ba.209.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb532ad3e47c308029b817a7b3daf5fb8880eb7efe80123ab5bfa9cef24b4df
-size 13639
+oid sha256:fde07929b973e643ebf31fba2693328eab2bdf8393f7b0e0f9f6cc7b1a0e7892
+size 14528