safouaneelg commited on
Commit
3444b13
·
verified ·
1 Parent(s): 589c12a

update model card

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -31,7 +31,9 @@ Check out the model info here: [Swiss-AI/LLM](https://huggingface.co/collections
31
  # Finetuned on AQUA-RAT
32
 
33
  This repo contains the fine-tuned version of Apertus on [AQuA-RAT dataset](https://huggingface.co/datasets/deepmind/aqua_rat).
 
34
  The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with the following parameters:
 
35
  - per_device_train_batch_size: 8
36
  - gradient_accumulation_steps: 4 (effective batch size: 32)
37
  - warmup_steps: 10
@@ -46,7 +48,7 @@ The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with th
46
  - eval_strategy: steps
47
  - eval_steps: 150
48
  - packing: True
49
- -
50
  ## How to use
51
 
52
  You can run this fine-tuned version using the below instructions:
 
31
  # Finetuned on AQUA-RAT
32
 
33
  This repo contains the fine-tuned version of Apertus on [AQuA-RAT dataset](https://huggingface.co/datasets/deepmind/aqua_rat).
34
+
35
  The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with the following parameters:
36
+
37
  - per_device_train_batch_size: 8
38
  - gradient_accumulation_steps: 4 (effective batch size: 32)
39
  - warmup_steps: 10
 
48
  - eval_strategy: steps
49
  - eval_steps: 150
50
  - packing: True
51
+
52
  ## How to use
53
 
54
  You can run this fine-tuned version using the below instructions: