benchang1110
/

TaiVisionLM-base-v1

Image-Text-to-Text

text-generation

Model card Files Files and versions Community

benchang1110 commited on Sep 3

Commit

d4a6e28

•

1 Parent(s): 88773ae

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -134,7 +134,7 @@ The following training hyperparameters are used in feature alignment and task sp
 | Data size    | Global Batch Size | Learning Rate | Epochs | Max Length | Weight Decay |
 |--------------|-------------------|---------------|--------|------------|--------------|
-| 1B        | 16               | 5e-5          | 1      | 2048       | 1e-5            |
 We use full-parameter finetuning for the projector and apply LoRA to the language model.

 | Data size    | Global Batch Size | Learning Rate | Epochs | Max Length | Weight Decay |
 |--------------|-------------------|---------------|--------|------------|--------------|
+| 1M        | 16               | 5e-5          | 1      | 2048       | 1e-5            |
 We use full-parameter finetuning for the projector and apply LoRA to the language model.