Downloads · 30 days
9
18% of all-time downloads
Summary_M2_1000steps_1e5rate_SFT
tsavage68/Summary_M2_1000steps_1e5rate_SFT
Summary_M2_1000steps_1e5rate_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
29 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
- 4fe253e6
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_1e5rate_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: 0.6850
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-05
- 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 |
|---|---|---|---|
| 0.6385 | 0.2 | 50 | 0.6765 |
| 0.72 | 0.4 | 100 | 0.6479 |
| 0.6779 | 0.6 | 150 | 0.6345 |
| 0.5987 | 0.8 | 200 | 0.5944 |
| 0.5399 | 1.0 | 250 | 0.5650 |
| 0.415 | 1.2 | 300 | 0.5565 |
| 0.4069 | 1.4 | 350 | 0.5603 |
| 0.3703 | 1.6 | 400 | 0.5337 |
| 0.297 | 1.8 | 450 | 0.5317 |
| 0.3897 | 2.0 | 500 | 0.5171 |
| 0.1212 | 2.2 | 550 | 0.5834 |
| 0.1173 | 2.4 | 600 | 0.5994 |
| 0.1106 | 2.6 | 650 | 0.6056 |
| 0.0869 | 2.8 | 700 | 0.5971 |
| 0.1012 | 3.0 | 750 | 0.6044 |
| 0.0132 | 3.2 | 800 | 0.6711 |
| 0.0187 | 3.4 | 850 | 0.6858 |
| 0.0203 | 3.6 | 900 | 0.6849 |
| 0.0156 | 3.8 | 950 | 0.6850 |
| 0.0193 | 4.0 | 1000 | 0.6850 |
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