Downloads · 30 days
0
llama2_instruct_generation
shreyasmenon/llama2_instruct_generation
llama2_instruct_generation is a machine learning model from shreyasmenon. 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 19, 2023
Repo size
134 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors134 MB · 99%
At a glance
- Access
- Public
- Created
- Nov 19, 2023
- Updated
- Nov 19, 2023
- SHA
- 0586ff35
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: 1.6696
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 |
|---|---|---|---|
| 1.9496 | 0.0 | 10 | 1.8436 |
| 1.9477 | 0.0 | 20 | 1.8131 |
| 1.9025 | 0.0 | 30 | 1.7940 |
| 1.7997 | 0.0 | 40 | 1.7798 |
| 1.858 | 0.0 | 50 | 1.7719 |
| 1.8767 | 0.0 | 60 | 1.7646 |
| 1.8571 | 0.0 | 70 | 1.7585 |
| 1.8494 | 0.01 | 80 | 1.7535 |
| 1.9404 | 0.01 | 90 | 1.7476 |
| 1.852 | 0.01 | 100 | 1.7396 |
| 1.8713 | 0.01 | 110 | 1.7218 |
| 1.8863 | 0.01 | 120 | 1.7153 |
| 1.9036 | 0.01 | 130 | 1.7068 |
| 1.8432 | 0.01 | 140 | 1.7040 |
| 1.8168 | 0.01 | 150 | 1.7000 |
| 1.8272 | 0.01 | 160 | 1.6978 |
| 1.807 | 0.01 | 170 | 1.6952 |
| 1.8131 | 0.01 | 180 | 1.6938 |
| 1.8317 | 0.01 | 190 | 1.6904 |
| 1.79 | 0.01 | 200 | 1.6901 |
| 1.6645 | 0.01 | 210 | 1.6885 |
| 1.8626 | 0.02 | 220 | 1.6901 |
| 1.8129 | 0.02 | 230 | 1.6864 |
| 1.8821 | 0.02 | 240 | 1.6862 |
| 1.8552 | 0.02 | 250 | 1.6843 |
| 1.8641 | 0.02 | 260 | 1.6840 |
| 1.7304 | 0.02 | 270 | 1.6834 |
| 1.7279 | 0.02 | 280 | 1.6825 |
| 1.8039 | 0.02 | 290 | 1.6829 |
| 1.7132 | 0.02 | 300 | 1.6815 |
| 1.8142 | 0.02 | 310 | 1.6807 |
| 1.7918 | 0.02 | 320 | 1.6799 |
| 1.8154 | 0.02 | 330 | 1.6781 |
| 1.6644 | 0.02 | 340 | 1.6789 |
| 1.7383 | 0.02 | 350 | 1.6779 |
| 1.8327 | 0.03 | 360 | 1.6767 |
| 1.7003 | 0.03 | 370 | 1.6769 |
| 1.7698 | 0.03 | 380 | 1.6758 |
| 1.7725 | 0.03 | 390 | 1.6753 |
| 1.6452 | 0.03 | 400 | 1.6754 |
| 1.7474 | 0.03 | 410 | 1.6760 |
| 1.7243 | 0.03 | 420 | 1.6760 |
| 1.7344 | 0.03 | 430 | 1.6755 |
| 1.6396 | 0.03 | 440 | 1.6744 |
| 1.7835 | 0.03 | 450 | 1.6739 |
| 1.7635 | 0.03 | 460 | 1.6735 |
| 1.7007 | 0.03 | 470 | 1.6727 |
| 1.801 | 0.03 | 480 | 1.6722 |
| 1.7607 | 0.03 | 490 | 1.6710 |
| 1.7926 | 0.04 | 500 | 1.6696 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Created
- Nov 19, 2023
- Updated
- Nov 19, 2023