Downloads · 30 days
8
16% of all-time downloads
Transaminitis_M2_1000rate_1e7_SFT
tsavage68/Transaminitis_M2_1000rate_1e7_SFT
Transaminitis_M2_1000rate_1e7_SFT is a text generation model from tsavage68. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
51
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- May 14, 2024
- Updated
- May 14, 2024
- SHA
- 3aaa9a1c
Try a prompt
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. -->
Transaminitis_M2_1000rate_1e7_SFT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2870
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: 1e-07
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2942 | 0.2 | 25 | 2.2327 |
| 2.0387 | 0.4 | 50 | 1.9312 |
| 1.6442 | 0.6 | 75 | 1.3586 |
| 0.7444 | 0.8 | 100 | 0.5869 |
| 0.4516 | 1.0 | 125 | 0.4222 |
| 0.4019 | 1.2 | 150 | 0.4021 |
| 0.3886 | 1.4 | 175 | 0.3923 |
| 0.3781 | 1.6 | 200 | 0.3711 |
| 0.3635 | 1.8 | 225 | 0.3654 |
| 0.3486 | 2.0 | 250 | 0.3536 |
| 0.3422 | 2.2 | 275 | 0.3393 |
| 0.3271 | 2.4 | 300 | 0.3278 |
| 0.3188 | 2.6 | 325 | 0.3180 |
| 0.3046 | 2.8 | 350 | 0.3057 |
| 0.2926 | 3.0 | 375 | 0.2969 |
| 0.2875 | 3.2 | 400 | 0.2926 |
| 0.2827 | 3.4 | 425 | 0.2919 |
| 0.2894 | 3.6 | 450 | 0.2908 |
| 0.2885 | 3.8 | 475 | 0.2890 |
| 0.2809 | 4.0 | 500 | 0.2896 |
| 0.2764 | 4.2 | 525 | 0.2891 |
| 0.2866 | 4.4 | 550 | 0.2884 |
| 0.2811 | 4.6 | 575 | 0.2880 |
| 0.285 | 4.8 | 600 | 0.2874 |
| 0.2791 | 5.0 | 625 | 0.2870 |
| 0.2793 | 5.2 | 650 | 0.2872 |
| 0.2762 | 5.4 | 675 | 0.2872 |
| 0.2783 | 5.6 | 700 | 0.2875 |
| 0.2821 | 5.8 | 725 | 0.2869 |
| 0.2812 | 6.0 | 750 | 0.2869 |
| 0.2795 | 6.2 | 775 | 0.2868 |
| 0.2823 | 6.4 | 800 | 0.2868 |
| 0.2788 | 6.6 | 825 | 0.2868 |
| 0.2764 | 6.8 | 850 | 0.2870 |
| 0.2817 | 7.0 | 875 | 0.2869 |
| 0.2788 | 7.2 | 900 | 0.2870 |
| 0.28 | 7.4 | 925 | 0.2870 |
| 0.2862 | 7.6 | 950 | 0.2870 |
| 0.2775 | 7.8 | 975 | 0.2870 |
| 0.2799 | 8.0 | 1000 | 0.2870 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- May 14, 2024
- Updated
- May 14, 2024