squad_hotpot config

configs/squad_hotpot_qa.yaml

@@ -1,6 +1,6 @@
 output_dir: "" # just a placeholder
 bf16: true
-model_name_or_path: google/gemma-2-2b-it
+model_name_or_path: google/gemma-3-1b-it
 label_names: ["labels"]
 # eval_on_start: True
 # eval_strategy: "steps"
@@ -28,20 +28,20 @@ weight_decay: 0.01
 
 warmup_steps: 100
 
-dataloader_prefetch_factor: 8
+dataloader_prefetch_factor: 16
 dataloader_num_workers: 8
 
 # LoRA
 lora_r: 8
-lora_dropout: 0.02
+lora_dropout: 0.0
 target_modules:
   - down_proj
 
 # data
 train_ds_names:
-  - pwc
   - hotpot_qa
+  - squad
 
 val_ds_names:
-  - pwc
   - hotpot_qa
+  - squad

pyproject.toml

@@ -30,6 +30,7 @@ dependencies = [
     "plotly",
     "rouge-score",
     "vllm==0.8.5",
+    "huggingface-hub[hf-transfer]>=0.32.0",
 ]
 
 [build-system]