Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2-VL-2B-Instruct
+base_model: Qwen/Qwen2-VL-7B-Instruct
 library_name: peft
 license: apache-2.0
 tags:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2-2b-instruct-amazon-description
 
-This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

runs/Sep30_13-29-45_ip-172-31-27-157/events.out.tfevents.1727702988.ip-172-31-27-157.3077.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc968b6afcd9693ccf68569bab1eb88a496f50f82851dd1717abef4287eeb684
-size 11494
+oid sha256:a4ffae97faae188e7033c352566bdedd3a4590821690765bc7c4c116ec9c6878
+size 11842