Model save

README.md

@@ -5,14 +5,14 @@ base_model: Qwen/Qwen2-VL-7B-Instruct
 tags:
 - generated_from_trainer
 model-index:
-- name: qwen2-vl-video-eval_st_55296_regression
+- name: qwen2-vl-video-eval_st_bad5k_55296_regression
   results: []
 ---
 
 <!-- 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. -->
 
-# qwen2-vl-video-eval_st_55296_regression
+# qwen2-vl-video-eval_st_bad5k_55296_regression
 
 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.
 
@@ -38,10 +38,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 8
+- num_devices: 7
+- gradient_accumulation_steps: 9
+- total_train_batch_size: 63
+- total_eval_batch_size: 7
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03