Downloads · 30 days
9
4% of all-time downloads
IE_M2_1000steps_1e7rate_SFT
tsavage68/IE_M2_1000steps_1e7rate_SFT
IE_M2_1000steps_1e7rate_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
205
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
- Sep 22, 2024
- Updated
- Sep 22, 2024
- SHA
- 66fab591
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. -->
IE_M2_1000steps_1e7rate_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: 1.2801
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 |
|---|---|---|---|
| 1.8404 | 0.4 | 50 | 1.8454 |
| 1.6261 | 0.8 | 100 | 1.5552 |
| 1.4351 | 1.2 | 150 | 1.3280 |
| 1.3429 | 1.6 | 200 | 1.3033 |
| 1.3587 | 2.0 | 250 | 1.2943 |
| 1.3562 | 2.4 | 300 | 1.2894 |
| 1.3709 | 2.8 | 350 | 1.2861 |
| 1.2679 | 3.2 | 400 | 1.2843 |
| 1.3609 | 3.6 | 450 | 1.2828 |
| 1.2742 | 4.0 | 500 | 1.2819 |
| 1.3383 | 4.4 | 550 | 1.2812 |
| 1.296 | 4.8 | 600 | 1.2806 |
| 1.3159 | 5.2 | 650 | 1.2804 |
| 1.3007 | 5.6 | 700 | 1.2802 |
| 1.2311 | 6.0 | 750 | 1.2802 |
| 1.2871 | 6.4 | 800 | 1.2802 |
| 1.2652 | 6.8 | 850 | 1.2801 |
| 1.2764 | 7.2 | 900 | 1.2801 |
| 1.2565 | 7.6 | 950 | 1.2801 |
| 1.3073 | 8.0 | 1000 | 1.2801 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Sep 22, 2024
- Updated
- Sep 22, 2024