Model save

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: swinv2-ocr-finetuned-panjabi
+  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. -->
+
+# swinv2-ocr-finetuned-panjabi
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5755
+- Cer: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Cer    |
+|:-------------:|:-----:|:------:|:---------------:|:------:|
+| 3.1527        | 1.0   | 5883   | 3.4368          | 1.0    |
+| 3.271         | 2.0   | 11766  | 3.2032          | 1.0001 |
+| 2.9587        | 3.0   | 17649  | 3.0627          | 1.0    |
+| 2.4732        | 4.0   | 23532  | 3.0279          | 1.0108 |
+| 2.1076        | 5.0   | 29415  | 2.5229          | 0.9997 |
+| 1.8924        | 6.0   | 35298  | 2.4476          | 1.0    |
+| 1.7687        | 7.0   | 41181  | 2.4754          | 1.0    |
+| 1.5841        | 8.0   | 47064  | 2.5346          | 1.0    |
+| 1.6036        | 9.0   | 52947  | 2.4699          | 1.0    |
+| 1.3961        | 10.0  | 58830  | 2.4823          | 1.0    |
+| 1.2846        | 11.0  | 64713  | 2.5168          | 1.0    |
+| 1.0196        | 12.0  | 70596  | 2.4514          | 1.0    |
+| 1.1475        | 13.0  | 76479  | 2.5678          | 1.0    |
+| 1.0415        | 14.0  | 82362  | 2.6223          | 1.0    |
+| 1.0472        | 15.0  | 88245  | 2.6513          | 1.0    |
+| 0.7244        | 16.0  | 94128  | 2.4963          | 1.0    |
+| 0.6422        | 17.0  | 100011 | 2.5385          | 1.0    |
+| 0.7878        | 18.0  | 105894 | 2.6305          | 1.0    |
+| 0.6919        | 19.0  | 111777 | 2.5720          | 1.0    |
+| 0.5415        | 20.0  | 117660 | 2.5755          | 1.0    |
+
+
+### Framework versions
+
+- Transformers 4.46.0
+- Pytorch 2.5.1+cu118
+- Datasets 2.20.0
+- Tokenizers 0.20.1

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_length": 512,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.0"
+}