update model card README.md

README.md

@@ -12,14 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # indic-gpt
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an indian language (https://ai4bharat.iitm.ac.in/corpora) dataset. Sample Dataset is available here -https://huggingface.co/datasets/aashay96/indic-gpt/
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 8.1648
-- eval_runtime: 203.8512
-- eval_samples_per_second: 227.941
-- eval_steps_per_second: 7.128
-- epoch: 0.0
-- step: 3
+- Loss: 1.9482
 
 ## Model description
 
@@ -39,17 +34,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- total_train_batch_size: 1024
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.3653        | 0.3   | 500  | 2.2985          |
+| 2.2079        | 0.61  | 1000 | 2.0401          |
+| 2.0396        | 0.91  | 1500 | 1.9482          |
+
+
 ### Framework versions
 
 - Transformers 4.25.1