End of training

README.md

@@ -1,29 +1,24 @@
 ---
-base_model: cxfajar197/urdu-ocr
+library_name: transformers
 language:
 - ur
-library_name: transformers
+base_model: cxfajar197/urdu-ocr
 tags:
 - generated_from_trainer
 model-index:
-- name: trocr
+- name: trocr for Urdu
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# trocr
+# trocr for Urdu
 
 This model is a fine-tuned version of [cxfajar197/urdu-ocr](https://huggingface.co/cxfajar197/urdu-ocr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.8610
-- eval_cer: 0.2585
-- eval_runtime: 30.7583
-- eval_samples_per_second: 3.251
-- eval_steps_per_second: 0.228
-- epoch: 1.9127
-- step: 6000
+- Loss: 1.8947
+- Cer: 0.2676
 
 ## Model description
 
@@ -48,9 +43,18 @@ 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: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Cer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.762         | 0.3188 | 1000 | 2.0288          | 0.2936 |
+| 0.6622        | 0.6376 | 2000 | 2.0111          | 0.2791 |
+| 0.5878        | 0.9563 | 3000 | 1.8947          | 0.2676 |
+
+
 ### Framework versions
 
 - Transformers 4.45.1