Update README.md

README.md

@@ -14,5 +14,29 @@ This is a Norwegian T5-base model trained on the Norwegian Colossal Corpus (NCC)
 
  The following setting were used in training:
 ```bash
-./run_t5_mlm_flax_streaming.py \\n    --output_dir="./" \\n    --model_type="t5" \\n    --config_name="./" \\n    --tokenizer_name="./" \\n    --dataset_name="pere/norwegian_colossal_corpus_v2_short100k" \\n    --max_seq_length="512" \\n    --weight_decay="0.01" \\n    --per_device_train_batch_size="32" \\n    --per_device_eval_batch_size="32" \\n    --learning_rate="8e-3" \\n    --warmup_steps="5000" \\n    --overwrite_output_dir \\n    --cache_dir /mnt/disks/flaxdisk/cache/ \\n    --num_train_epochs="5" \\n    --adam_beta1="0.9" \\n    --adam_beta2="0.98" \\n    --logging_steps="500" \\n    --num_train_steps="1000000" \\n    --num_eval_samples="5000" \\n    --save_steps="5000" \\n    --eval_steps="5000" \\n    --preprocessing_num_workers 96 \\n    --adafactor \\n    --push_to_hub
+./run_t5_mlm_flax_streaming.py \
+    --output_dir="./" \
+    --model_type="t5" \
+    --config_name="./" \
+    --tokenizer_name="./" \
+    --dataset_name="pere/norwegian_colossal_corpus_v2_short100k" \
+    --max_seq_length="512" \
+    --weight_decay="0.01" \
+    --per_device_train_batch_size="32" \
+    --per_device_eval_batch_size="32" \
+    --learning_rate="8e-3" \
+    --warmup_steps="0" \
+    --overwrite_output_dir \
+    --cache_dir /mnt/disks/flaxdisk/cache/ \
+    --num_train_epochs="5" \
+    --adam_beta1="0.9" \
+    --adam_beta2="0.98" \
+    --logging_steps="500" \
+    --num_train_steps="1000000" \
+    --num_eval_samples="5000" \
+    --save_steps="5000" \
+    --eval_steps="5000" \
+    --preprocessing_num_workers 96 \
+    --adafactor \
+    --push_to_hub
  ```