Downloads · 30 days
3
6% of all-time downloads
v1_750_STEPS_1e5_SFT_SFT
tsavage68/v1_750_STEPS_1e5_SFT_SFT
v1_750_STEPS_1e5_SFT_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
53
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
- Apr 6, 2024
- Updated
- Apr 6, 2024
- SHA
- 29b44cad
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. -->
v1_750_STEPS_1e5_SFT_SFT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3202
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: 750
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4004 | 0.05 | 50 | 0.4035 |
| 0.3957 | 0.1 | 100 | 0.4218 |
| 0.4288 | 0.15 | 150 | 0.4015 |
| 0.4599 | 0.2 | 200 | 0.3914 |
| 0.3886 | 0.24 | 250 | 0.3879 |
| 0.3968 | 0.29 | 300 | 0.3768 |
| 0.3678 | 0.34 | 350 | 0.3688 |
| 0.3559 | 0.39 | 400 | 0.3574 |
| 0.3606 | 0.44 | 450 | 0.3467 |
| 0.3473 | 0.49 | 500 | 0.3384 |
| 0.3278 | 0.54 | 550 | 0.3308 |
| 0.3294 | 0.59 | 600 | 0.3248 |
| 0.314 | 0.64 | 650 | 0.3214 |
| 0.3049 | 0.68 | 700 | 0.3202 |
| 0.3119 | 0.73 | 750 | 0.3202 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Apr 6, 2024
- Updated
- Apr 6, 2024