quickstart instructions for starting from runpod (#5)

configs/llama_7B_4bit.yml

@@ -4,7 +4,7 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: true
 datasets:
-  - path: vicgalle/alpaca-gpt4
+  - path: tatsu-lab/alpaca  # original alpaca dataset
     type: alpaca
 dataset_prepared_path: data/last_run_prepared
 val_set_size: 0.04
@@ -29,6 +29,7 @@ output_dir: ./lora-test
 batch_size: 8
 micro_batch_size: 2
 num_epochs: 3
+warmup_steps: 100
 learning_rate: 0.00003
 train_on_inputs: false
 group_by_length: false
@@ -37,5 +38,8 @@ tf32: true
 gradient_checkpointing: false
 early_stopping_patience: 3
 resume_from_checkpoint:
+auto_resume_from_checkpoints: true
 local_rank:
 load_4bit: true
+xformers_attention: true
+flash_attention: