m-biriuchinskii
/

Llama-3.2-post-ocr-synthetic-data-2

Inference Endpoints

Model card Files Files and versions Community

m-biriuchinskii commited on about 1 month ago

Commit

6928468

•

1 Parent(s): 663ba60

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ wandb:   train_steps_per_second 0.198
 training_arguments = SFTConfig(
     output_dir=new_model,
     run_name="fine_tune_ocr_correction",
-    per_device_train_batch_size=2,
     per_device_eval_batch_size=3,
     gradient_accumulation_steps=4,
     optim="paged_adamw_32bit",

 training_arguments = SFTConfig(
     output_dir=new_model,
     run_name="fine_tune_ocr_correction",
+    per_device_train_batch_size=4,
     per_device_eval_batch_size=3,
     gradient_accumulation_steps=4,
     optim="paged_adamw_32bit",