Merge pull request #13 from rhymes-ai/full_params_training_examples

update the experiment results of nextqa and refcoco
rhymes-ai · Oct 4, 2024 · 1b2d41b · 1b2d41b
2 parents 5041017 + dbfe96e
commit 1b2d41b
Show file tree

Hide file tree

Showing 4 changed files with 2 additions and 2 deletions.
diff --git a/assets/nextqa_loss_full.png b/assets/nextqa_loss_full.png
diff --git a/assets/refcoco_loss_full.png b/assets/refcoco_loss_full.png
diff --git a/examples/nextqa/README.md b/examples/nextqa/README.md
@@ -49,7 +49,7 @@ CUDA_VISIBLE_DEVICES=0 python examples/nextqa/evaluation.py \
 The `Accuracy`:
 | Aria                           | LoRA SFT               | Full Params SFT  |
 |:-------------------------------------:|:-------------------------:|:-------:|
-|78.14 | 80.80 | 81.42 |
+|78.14 | 80.80 | 80.08 |
 
 ## Loss Curve
 These are the loss curves of `LoRA SFT` and `Full Params SFT`:

diff --git a/examples/refcoco/README.md b/examples/refcoco/README.md
@@ -70,7 +70,7 @@ CUDA_VISIBLE_DEVICES=0 python examples/refcoco/evaluation.py \
 The `Precision@1`:
 | Aria                           | LoRA SFT               | Full Params SFT  |
 |:-------------------------------------:|:-------------------------:|:-------:|
-|2.27 | 88.68 | 88.85 |
+|2.27 | 88.68 | 88.69 |
 
 # Loss Curve
 These are the loss curves of `LoRA Finetuning` (left) and `Full Params Finetuning` (right):