Downloads · 30 days
0
llama2_instruct_generation
oshada-kasun/llama2_instruct_generation
llama2_instruct_generation is a machine learning model from oshada-kasun. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Nov 21, 2023
Repo size
67.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors67.1 MB · 97%
At a glance
- Access
- Public
- Created
- Nov 21, 2023
- Updated
- Nov 21, 2023
- SHA
- 193279ee
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. -->
llama2_instruct_generation
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6802
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: 2
- 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 |
|---|---|---|---|
| 1.9189 | 0.0 | 20 | 1.8213 |
| 1.8963 | 0.0 | 40 | 1.7935 |
| 1.9081 | 0.0 | 60 | 1.7748 |
| 1.8358 | 0.0 | 80 | 1.7638 |
| 1.8482 | 0.0 | 100 | 1.7539 |
| 1.8578 | 0.0 | 120 | 1.7420 |
| 1.79 | 0.0 | 140 | 1.7188 |
| 1.7997 | 0.01 | 160 | 1.7084 |
| 1.9396 | 0.01 | 180 | 1.7035 |
| 1.8644 | 0.01 | 200 | 1.6968 |
| 1.7963 | 0.01 | 220 | 1.6955 |
| 1.876 | 0.01 | 240 | 1.6945 |
| 1.9236 | 0.01 | 260 | 1.6951 |
| 1.8942 | 0.01 | 280 | 1.6911 |
| 1.6897 | 0.01 | 300 | 1.6890 |
| 1.8062 | 0.01 | 320 | 1.6892 |
| 1.709 | 0.01 | 340 | 1.6854 |
| 1.8508 | 0.01 | 360 | 1.6857 |
| 1.7915 | 0.01 | 380 | 1.6853 |
| 1.7261 | 0.01 | 400 | 1.6838 |
| 1.7328 | 0.01 | 420 | 1.6835 |
| 1.8827 | 0.02 | 440 | 1.6856 |
| 1.811 | 0.02 | 460 | 1.6798 |
| 1.8487 | 0.02 | 480 | 1.6815 |
| 1.8155 | 0.02 | 500 | 1.6802 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Created
- Nov 21, 2023
- Updated
- Nov 21, 2023