Downloads · 30 days
7
19% of all-time downloads
llama2_instruct_generation
rouven-spiess/llama2_instruct_generation
llama2_instruct_generation is a machine learning model from rouven-spiess. 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
37
Public
Repo size
134 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors134 MB · 99%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jan 23, 2024
- Updated
- Jan 23, 2024
- SHA
- fb0574ce
Base models
Datasets
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. -->
llama2_instruct_generation
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6750
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8413 | 0.0 | 20 | 1.8102 |
| 1.9042 | 0.01 | 40 | 1.7811 |
| 1.8402 | 0.01 | 60 | 1.7657 |
| 1.8856 | 0.01 | 80 | 1.7511 |
| 1.9212 | 0.01 | 100 | 1.7390 |
| 1.807 | 0.02 | 120 | 1.7090 |
| 1.8321 | 0.02 | 140 | 1.7029 |
| 1.871 | 0.02 | 160 | 1.6979 |
| 1.848 | 0.02 | 180 | 1.6947 |
| 1.8378 | 0.03 | 200 | 1.6908 |
| 1.746 | 0.03 | 220 | 1.6893 |
| 1.7568 | 0.03 | 240 | 1.6874 |
| 1.8227 | 0.04 | 260 | 1.6860 |
| 1.8134 | 0.04 | 280 | 1.6835 |
| 1.8026 | 0.04 | 300 | 1.6819 |
| 1.8267 | 0.04 | 320 | 1.6831 |
| 1.7998 | 0.05 | 340 | 1.6816 |
| 1.8747 | 0.05 | 360 | 1.6793 |
| 1.8478 | 0.05 | 380 | 1.6785 |
| 1.8627 | 0.05 | 400 | 1.6776 |
| 1.7956 | 0.06 | 420 | 1.6783 |
| 1.7184 | 0.06 | 440 | 1.6764 |
| 1.7038 | 0.06 | 460 | 1.6753 |
| 1.9049 | 0.07 | 480 | 1.6764 |
| 1.8113 | 0.07 | 500 | 1.6750 |
Framework versions
- PEFT 0.7.1
- Transformers 4.37.0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Library
- peft
- Created
- Jan 23, 2024
- Updated
- Jan 23, 2024