Downloads · 30 days
8
28% of all-time downloads
llama_ice_domar
thorirhrafn/llama_ice_domar
llama_ice_domar is a machine learning model from thorirhrafn. 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Apr 8, 2024
- Updated
- Apr 9, 2024
- SHA
- 71ad28c9
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. -->
llama_ice_domar
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6789
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 | Validation Loss |
|---|---|---|---|
| 0.6953 | 0.5 | 250 | 0.7694 |
| 0.6506 | 0.99 | 500 | 0.7179 |
| 0.574 | 1.49 | 750 | 0.6986 |
| 0.6497 | 1.99 | 1000 | 0.6768 |
| 0.4312 | 2.48 | 1250 | 0.6751 |
| 0.4771 | 2.98 | 1500 | 0.6650 |
| 0.5283 | 3.48 | 1750 | 0.6730 |
| 0.5224 | 3.97 | 2000 | 0.6737 |
| 0.534 | 4.47 | 2250 | 0.6786 |
| 0.4762 | 4.97 | 2500 | 0.6789 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2
- Library
- peft
- Created
- Apr 8, 2024
- Updated
- Apr 9, 2024