prepared dataset caching, other misc fixes (#665)

* prepared dataset caching, other misc fixes * also don't load from disk cache unless explicit
2023-10-02 21:07:24 -04:00
parent f4868d733c
commit e50a64e85e
32 changed files with 35 additions and 34 deletions
--- a/examples/openllama-3b/config.yml
+++ b/examples/openllama-3b/config.yml
@@ -9,7 +9,7 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path: last_run_prepared
+dataset_prepared_path:
 val_set_size: 0.02
 adapter:
 lora_model_dir:
--- a/examples/openllama-3b/lora.yml
+++ b/examples/openllama-3b/lora.yml
@@ -9,7 +9,7 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path: last_run_prepared
+dataset_prepared_path:
 val_set_size: 0.02
 adapter: lora
 lora_model_dir:
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -9,7 +9,7 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path: last_run_prepared
+dataset_prepared_path:
 val_set_size: 0.01
 adapter: qlora
 lora_model_dir: