yhavinga
/

gpt2-medium-dutch

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

yhavinga commited on Dec 21, 2021

Commit

233fa8e

•

1 Parent(s): 617829a

Update run script parameters

Files changed (1) hide show

run_gpt.sh +1 -1

run_gpt.sh CHANGED Viewed

@@ -23,7 +23,7 @@ python run_clm_flax.py \
     --block_size="512" \
     --per_device_train_batch_size="16" \
     --per_device_eval_batch_size="16" \
-    --learning_rate="8e-4" --warmup_steps="5000" \
     --adam_beta1="0.9" --adam_beta2="0.98" --weight_decay="0.01" \
     --overwrite_output_dir \
     --num_train_epochs="4" \

     --block_size="512" \
     --per_device_train_batch_size="16" \
     --per_device_eval_batch_size="16" \
+    --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" \