Downloads · 30 days
4
5% of all-time downloads
Llama3_8B_final_MT
rishavranaut/Llama3_8B_final_MT
Llama3_8B_final_MT is a machine learning model from rishavranaut. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.
should probably proofread and complete it, then remove this comment. --
All-time downloads
87
Public
Repo size
546 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors54.6 MB · 86%
At a glance
- Library
- peft
- License
- llama3
- Access
- Public
- Created
- Oct 22, 2024
- Updated
- Oct 23, 2024
- SHA
- 8c8d05c0
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Llama3_8B_final_MT
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6495
- Accuracy: 0.7983
- Precision: 0.8076
- Recall: 0.7833
- F1 score: 0.7953
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Accuracy | F1 score | Precision | Recall | Validation Loss |
|---|---|---|---|---|---|---|---|
| 0.6898 | 0.5 | 200 | 0.745 | 0.7339 | 0.7673 | 0.7033 | 0.6158 |
| 0.5331 | 1.0 | 400 | 0.7817 | 0.7698 | 0.8141 | 0.73 | 0.5279 |
| 0.3824 | 1.5 | 600 | 0.7667 | 0.7846 | 0.7286 | 0.85 | 0.5694 |
| 0.3539 | 2.0 | 800 | 0.4800 | 0.805 | 0.8427 | 0.75 | 0.7937 |
| 0.2684 | 2.5 | 1000 | 0.5545 | 0.795 | 0.7864 | 0.81 | 0.7980 |
| 0.247 | 3.0 | 1200 | 0.5031 | 0.8233 | 0.8540 | 0.78 | 0.8153 |
| 0.164 | 3.5 | 1400 | 0.5347 | 0.8183 | 0.8687 | 0.75 | 0.8050 |
| 0.1628 | 4.0 | 1600 | 0.5893 | 0.8 | 0.7903 | 0.8167 | 0.8033 |
| 0.0864 | 4.5 | 1800 | 0.6370 | 0.81 | 0.8142 | 0.8033 | 0.8087 |
| 0.0802 | 5.0 | 2000 | 0.6495 | 0.7983 | 0.8076 | 0.7833 | 0.7953 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- peft
- License
- llama3
- Created
- Oct 22, 2024
- Updated
- Oct 23, 2024