Model save

README.md

@@ -12,7 +12,9 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/ADL_HW2_RT_GPT2/runs/u6lcqmvu)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/ADL_HW2_RT_GPT2/runs/ov47z0tg)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/ADL_HW2_RT_GPT2/runs/ov47z0tg)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/ADL_HW2_RT_GPT2/runs/ov47z0tg)
 # ADL_HW2_GPT2
 
 This model is a fine-tuned version of [ckiplab/gpt2-tiny-chinese](https://huggingface.co/ckiplab/gpt2-tiny-chinese) on an unknown dataset.
@@ -35,12 +37,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 8
 
 ### Framework versions