End of training

README.md

@@ -14,6 +14,7 @@ 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/kkchaulagain/OCR/runs/ilqogjx6)
 # llava-1.5-7b-hf-ft-mix-vsft
 
 This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset.
@@ -36,14 +37,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1.4e-05
-- train_batch_size: 15
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 30
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a3a5282de67e3a9a0ee5db968b6999ba084b7550b598889a3a48287b605a3b
+oid sha256:9df8031d6b61c5fe81237582ab8b90b8ef760a75c279c3a8f476b98efd03b00c
 size 1290994752