Downloads · 30 days
9
18% of all-time downloads
mistralit2_1000_STEPS_5e8_SFT_SFT
tsavage68/mistralit2_1000_STEPS_5e8_SFT_SFT
mistralit2_1000_STEPS_5e8_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
49
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
- Mar 8, 2024
- Updated
- Mar 8, 2024
- SHA
- 03f3239f
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. -->
mistralit2_1000_STEPS_5e8_SFT_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: 0.3690
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: 5e-08
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|
| 1.4484 | 0.1 | 50 | 1.4370 |
| 1.3055 | 0.2 | 100 | 1.2880 |
| 1.1102 | 0.29 | 150 | 1.0868 |
| 0.9133 | 0.39 | 200 | 0.8993 |
| 0.7102 | 0.49 | 250 | 0.6891 |
| 0.5453 | 0.59 | 300 | 0.5207 |
| 0.4238 | 0.68 | 350 | 0.4248 |
| 0.4008 | 0.78 | 400 | 0.3916 |
| 0.3768 | 0.88 | 450 | 0.3790 |
| 0.3766 | 0.98 | 500 | 0.3744 |
| 0.3672 | 1.07 | 550 | 0.3718 |
| 0.3752 | 1.17 | 600 | 0.3702 |
| 0.3828 | 1.27 | 650 | 0.3694 |
| 0.3502 | 1.37 | 700 | 0.3691 |
| 0.3676 | 1.46 | 750 | 0.3690 |
| 0.3717 | 1.56 | 800 | 0.3690 |
| 0.3695 | 1.66 | 850 | 0.3690 |
| 0.3727 | 1.76 | 900 | 0.3690 |
| 0.3854 | 1.86 | 950 | 0.3690 |
| 0.3768 | 1.95 | 1000 | 0.3690 |
Framework versions
- Transformers 4.38.2
- 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
- Mar 8, 2024
- Updated
- Mar 8, 2024