From 3fddd2f01b0e63663bf39ac848f0d8ed9779958f Mon Sep 17 00:00:00 2001 From: Tilman Kerl Date: Wed, 20 Dec 2023 08:19:19 +0100 Subject: [PATCH] Update HACKING.md --- HACKING.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/HACKING.md b/HACKING.md index 8294d60..048dab7 100644 --- a/HACKING.md +++ b/HACKING.md @@ -90,7 +90,7 @@ The first training run was more of a proof-of-concept and test-run to see if the Please see the table below for a comparison of the two models. | Model | Dataset | Epochs | Batch Size | Training Time | GPU | Training Loss | -| --- | --- | --- | --- | --- | --- | --- | --- | +| --- | --- | --- | --- | --- | --- | --- | | llama-13b | ICD-11 | 3 | 2 | 18062 | NVIDIA A10G - 24GB | 0.0611 | | llama-7b | dialogue-full | 2 | 3 | 18062 | NVIDIA A10G - 24GB | 1.8428 |