Update run config

run_gpt.sh

@@ -4,7 +4,7 @@ export HF_PROJECT="gpt2-medium-dutch"
 
 # Variables for training the tokenizer and creating the config
 export VOCAB_SIZE="50257"
-export DATASET="yhavinga/mc4_nl_cleaned" # Name of the dataset in the Huggingface Hub
+export DATASET="/home/yeb/data/mc4_nl_cleaned/mc4_nl_cleaned.py" # Name of the dataset in the Huggingface Hub
 export DATASET_CONFIG="full" # Config of the dataset in the Huggingface Hub
 export DATASET_SPLIT="train" # Split to use for training tokenizer and model
 export TEXT_FIELD="text" # Field containing the text to be used for training
@@ -26,7 +26,9 @@ python run_clm_flax.py \
     --learning_rate="0.0024" --warmup_steps="5000" \
     --adam_beta1="0.9" --adam_beta2="0.98" --weight_decay="0.01" \
     --overwrite_output_dir \
-    --num_train_epochs="4" \
+    --num_train_epochs="2" \
+    --dataloader_num_workers="64" \
+    --preprocessing_num_workers="64" \
     --logging_steps="500" \
     --save_steps="40000" \
     --eval_steps="2500" \