Downloads · 30 days
7
14% of all-time downloads
Summary_M2_1000steps_1e6rate_SFT2
tsavage68/Summary_M2_1000steps_1e6rate_SFT2
Summary_M2_1000steps_1e6rate_SFT2 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
50
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
- Jun 13, 2024
- Updated
- Jun 13, 2024
- SHA
- 55fa032e
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. -->
Summary_M2_1000steps_1e6rate_SFT2
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: 0.4895
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-06
- 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 |
|---|---|---|---|
| 0.6188 | 0.2 | 50 | 0.5875 |
| 0.6174 | 0.4 | 100 | 0.5594 |
| 0.5762 | 0.6 | 150 | 0.5458 |
| 0.5371 | 0.8 | 200 | 0.5280 |
| 0.5041 | 1.0 | 250 | 0.5119 |
| 0.4382 | 1.2 | 300 | 0.5024 |
| 0.4769 | 1.4 | 350 | 0.4876 |
| 0.4204 | 1.6 | 400 | 0.4760 |
| 0.3383 | 1.8 | 450 | 0.4682 |
| 0.4251 | 2.0 | 500 | 0.4581 |
| 0.2913 | 2.2 | 550 | 0.4751 |
| 0.2794 | 2.4 | 600 | 0.4784 |
| 0.2921 | 2.6 | 650 | 0.4747 |
| 0.2387 | 2.8 | 700 | 0.4740 |
| 0.2811 | 3.0 | 750 | 0.4710 |
| 0.1751 | 3.2 | 800 | 0.4873 |
| 0.234 | 3.4 | 850 | 0.4892 |
| 0.2363 | 3.6 | 900 | 0.4896 |
| 0.2245 | 3.8 | 950 | 0.4895 |
| 0.228 | 4.0 | 1000 | 0.4895 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jun 13, 2024
- Updated
- Jun 13, 2024