Downloads · 30 days
3
1% of all-time downloads
llama-3.1-8B-Instruct-v1.6-only-completion-only_playpen_SFT-e3_DABL01
clembench-playpen/llama-3.1-8B-Instruct-v1.6-only-completion-only_playpen_SFT-e3_DABL01
llama-3.1-8B-Instruct-v1.6-only-completion-only_playpen_SFT-e3_DABL01 is a machine learning model from clembench-playpen. 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 llama3.1.
should probably proofread and complete it, then remove this comment. --
All-time downloads
539
Public
Repo size
688 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors671 MB · 97%
At a glance
- Library
- peft
- License
- llama3.1
- Access
- Public
- Created
- Mar 24, 2025
- Updated
- Mar 24, 2025
- SHA
- 52817095
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-3.1-8B-Instruct-v1.6-only-completion-only_playpen_SFT-e3_DABL01
This model is a fine-tuned version of unsloth/meta-llama-3.1-8b-instruct-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5069
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: 7331
- optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 5
- training_steps: 0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4497 | 0.1011 | 100 | 0.7268 |
| 0.7161 | 0.2022 | 200 | 0.6571 |
| 0.726 | 0.3033 | 300 | 0.6521 |
| 0.7743 | 0.4044 | 400 | 0.6219 |
| 0.663 | 0.5056 | 500 | 0.6099 |
| 0.5058 | 0.6067 | 600 | 0.6166 |
| 0.7012 | 0.7078 | 700 | 0.6172 |
| 0.6851 | 0.8089 | 800 | 0.5514 |
| 0.7853 | 0.9100 | 900 | 0.5332 |
| 0.4253 | 1.0111 | 1000 | 0.5790 |
| 0.3812 | 1.1122 | 1100 | 0.5368 |
| 0.23 | 1.2133 | 1200 | 0.5738 |
| 0.2816 | 1.3145 | 1300 | 0.5386 |
| 0.3602 | 1.4156 | 1400 | 0.5400 |
| 0.2753 | 1.5167 | 1500 | 0.5450 |
| 0.3007 | 1.6178 | 1600 | 0.5106 |
| 0.3579 | 1.7189 | 1700 | 0.5234 |
| 0.2141 | 1.8200 | 1800 | 0.4857 |
| 0.2473 | 1.9211 | 1900 | 0.4888 |
| 0.1723 | 2.0222 | 2000 | 0.5195 |
| 0.177 | 2.1234 | 2100 | 0.5540 |
| 0.1055 | 2.2245 | 2200 | 0.5313 |
| 0.1021 | 2.3256 | 2300 | 0.5066 |
| 0.1115 | 2.4267 | 2400 | 0.5173 |
| 0.1115 | 2.5278 | 2500 | 0.5050 |
| 0.1133 | 2.6289 | 2600 | 0.5131 |
| 0.1102 | 2.7300 | 2700 | 0.5315 |
| 0.1709 | 2.8311 | 2800 | 0.5200 |
| 0.1484 | 2.9323 | 2900 | 0.5069 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.21.0
- Library
- peft
- License
- llama3.1
- Created
- Mar 24, 2025
- Updated
- Mar 24, 2025