Labagaite commited on
Commit
71771d3
1 Parent(s): 1ecffe7

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -21,12 +21,12 @@ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
21
  # Training Logs
22
 
23
  ## Summary metrics
24
- ### Best ROUGE-1 score : **0.15938795027095953**
25
- ### Best ROUGE-2 score : **0.15885167464114833**
26
- ### Best ROUGE-L score : **0.15938795027095953**
27
 
28
  ## Wandb logs
29
- You can view the training logs [<img src="https://raw.githubusercontent.com/wandb/wandb/main/docs/README_images/logo-light.svg" width="200"/>](https://wandb.ai/william-derue/LLM-summarizer_trainer/runs/e3co46y5).
30
 
31
  ## Training details
32
 
@@ -43,7 +43,7 @@ You can view the training logs [<img src="https://raw.githubusercontent.com/wand
43
  # Project details
44
  [<img src="https://avatars.githubusercontent.com/u/116890814?v=4" width="100"/>](https://github.com/WillIsback/Report_Maker)
45
  Fine-tuned on French audio podcast transcription data for summarization task. As a result, the model is able to summarize French audio podcast transcription data.
46
- The model will be used for a AI application: [Report Maker](https://github.com/WillIsback/Report_Maker) wich is a powerful tool designed to automate the process of transcribing and summarizing meetings.
47
  It leverages state-of-the-art machine learning models to provide detailed and accurate reports.
48
 
49
  This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
21
  # Training Logs
22
 
23
  ## Summary metrics
24
+ ### Best ROUGE-1 score : **0.9842446709916588**
25
+ ### Best ROUGE-2 score : **0.9842154131847726**
26
+ ### Best ROUGE-L score : **0.9842446709916588**
27
 
28
  ## Wandb logs
29
+ You can view the training logs [<img src="https://raw.githubusercontent.com/wandb/wandb/main/docs/README_images/logo-light.svg" width="200"/>](https://wandb.ai/william-derue/LLM-summarizer_trainer/runs/s9xqw6o8).
30
 
31
  ## Training details
32
 
 
43
  # Project details
44
  [<img src="https://avatars.githubusercontent.com/u/116890814?v=4" width="100"/>](https://github.com/WillIsback/Report_Maker)
45
  Fine-tuned on French audio podcast transcription data for summarization task. As a result, the model is able to summarize French audio podcast transcription data.
46
+ The model will be used for an AI application: [Report Maker](https://github.com/WillIsback/Report_Maker) wich is a powerful tool designed to automate the process of transcribing and summarizing meetings.
47
  It leverages state-of-the-art machine learning models to provide detailed and accurate reports.
48
 
49
  This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.