chore: update following PR

examples/mistral/config.yml

@@ -2,6 +2,7 @@ base_model: mistralai/Mistral-7B-v0.1
 base_model_config: mistralai/Mistral-7B-v0.1
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
 
 load_in_8bit: false
 load_in_4bit: false
@@ -14,18 +15,10 @@ dataset_prepared_path: last_run_prepared
 val_set_size: 0.01
 output_dir: ./out
 
-sequence_len: 4096
+sequence_len: 8192
 sample_packing:
 pad_to_sequence_len:
 
-adapter:
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
 wandb_project:
 wandb_entity:
 wandb_watch:
@@ -51,7 +44,7 @@ resume_from_checkpoint:
 local_rank:
 logging_steps: 1
 xformers_attention:
-flash_attention:
+flash_attention: true
 
 warmup_steps: 10
 eval_steps: 20