Upload train_gpt2.slurm

This is the training resource allocation. Limited to one A100 with 26 GPU hours.

train_gpt2.slurm

@@ -0,0 +1,14 @@
+#!/bin/bash
+#SBATCH --job-name=gpt2_train
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1  
+#SBATCH --cpus-per-task=32
+#SBATCH --time=26:00:00              #Request 24 hours
+#SBATCH --mem=128GB                  #Request 128GB per node
+#SBATCH --partition=gpu              #Request the GPU partition/queue
+#SBATCH --gres=gpu:a100:1            #Request one A100 GPU to use
+
+#SBATCH --output=gpt2_train.%j.log            #Redirect stdout/err to file
+
+# Run the training script
+python train.py --config configs/config.yaml