Merge pull request #31 from FarukhS52/main

[Docs] : Fix typo
rhymes-ai · Oct 16, 2024 · 719ff4e · 719ff4e
2 parents a0b0690 + 0cefdfc
commit 719ff4e
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/examples/nextqa/README.md b/examples/nextqa/README.md
@@ -24,7 +24,7 @@ CUDA_VISIBLE_DEVICES=0 python aria/train.py --config examples/nextqa/config_lora
 ```
 
 ## Full Params
-Full paramater finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
+Full parameter finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
 ```bash
 accelerate launch --config_file recipes/accelerate_configs/zero3_offload.yaml aria/train.py --config examples/nextqa/config_full.yaml --output_dir [YOUR_OUT_DIR]
 ```

diff --git a/examples/nlvr2/README.md b/examples/nlvr2/README.md
@@ -33,7 +33,7 @@ CUDA_VISIBLE_DEVICES=0 python aria/train.py --config examples/nlvr2/config_lora.
 ```
 
 ## Full Params
-Full paramater finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
+Full parameter finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
 ```bash
 accelerate launch --config_file recipes/accelerate_configs/zero3_offload.yaml aria/train.py --config examples/nlvr2/config_full.yaml --max_image_size 980 --output_dir [YOUR_OUT_DIR]
 ```

diff --git a/examples/refcoco/README.md b/examples/refcoco/README.md
@@ -23,7 +23,7 @@ CUDA_VISIBLE_DEVICES=0 python aria/train.py --config examples/refcoco/config_lor
 ```
 
 ## Full Params
-Full paramater finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
+Full parameter finetuning is feasible with 8 H100 GPUs, using `ZeRO3` and `Offload Parameter`. The command is as following:
 ```bash
 accelerate launch --config_file recipes/accelerate_configs/zero3_offload.yaml aria/train.py --config examples/refcoco/config_full.yaml --output_dir [YOUR_OUT_DIR]
 ```
@@ -79,4 +79,4 @@ These are the loss curves of `LoRA Finetuning` (left) and `Full Params Finetunin
 <div style="display: flex; justify-content: space-between;">
     <img src="../../assets/refcoco_loss_lora.png" alt="Left Image" style="width: 48%;">
     <img src="../../assets/refcoco_loss_full.png" alt="Right Image" style="width: 48%;">
-</div>
+</div>