gvij
/

open-llama-7b-code-alpaca-instruct

alpaca-instruct

Model card Files Files and versions

gvij commited on Jul 4, 2023

Commit

9914182

·

1 Parent(s): 47c5bd6

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -16,7 +16,9 @@ tags:
 We finetuned Open Llama 7B on Code-Alpaca-Instruct Dataset (ewof/code-alpaca-instruct-unfiltered) for 3 epochs using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
-It ran for 75 minutes and costed us `$3` for the entire finetuning run!
 Loss metrics:
 ![training loss](training-loss.png "Training loss")

 We finetuned Open Llama 7B on Code-Alpaca-Instruct Dataset (ewof/code-alpaca-instruct-unfiltered) for 3 epochs using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
+This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.
+The finetuning session got completed in 75 minutes and costed us only `$3` for the entire finetuning run!
 Loss metrics:
 ![training loss](training-loss.png "Training loss")