Downloads · 30 days
1
2% of all-time downloads
tsavage68_-_IE_M2_1000steps_1e8rate_SFT-4bits
RichardErkhov/tsavage68_-_IE_M2_1000steps_1e8rate_SFT-4bits
tsavage68_-_IE_M2_1000steps_1e8rate_SFT-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
49
Public
Parameters
7.4B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U87B · 95%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
IE_M2_1000steps_1e8rate_SFT - bnb 4bits
- Model creator: https://huggingface.co/tsavage68/
- Original model: https://huggingface.co/tsavage68/IE_M2_1000steps_1e8rate_SFT/
Original model description:
library_name: transformers license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.2 tags:
- trl
- sft
- generated_from_trainer model-index:
- name: IE_M2_1000steps_1e8rate_SFT results: []
<!-- 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_1e8rate_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: 1.9087
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-08
- 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 |
|---|---|---|---|
| 1.8842 | 0.4 | 50 | 1.9129 |
| 1.9556 | 0.8 | 100 | 1.9129 |
| 2.0184 | 1.2 | 150 | 1.9122 |
| 1.9342 | 1.6 | 200 | 1.9112 |
| 1.9748 | 2.0 | 250 | 1.9101 |
| 2.0075 | 2.4 | 300 | 1.9096 |
| 2.0233 | 2.8 | 350 | 1.9092 |
| 1.9096 | 3.2 | 400 | 1.9090 |
| 2.0202 | 3.6 | 450 | 1.9091 |
| 1.9009 | 4.0 | 500 | 1.9094 |
| 2.0555 | 4.4 | 550 | 1.9096 |
| 1.9723 | 4.8 | 600 | 1.9090 |
| 1.9996 | 5.2 | 650 | 1.9088 |
| 1.9609 | 5.6 | 700 | 1.9091 |
| 1.8893 | 6.0 | 750 | 1.9090 |
| 2.0061 | 6.4 | 800 | 1.9088 |
| 1.9079 | 6.8 | 850 | 1.9087 |
| 1.9566 | 7.2 | 900 | 1.9087 |
| 1.9496 | 7.6 | 950 | 1.9087 |
| 1.9817 | 8.0 | 1000 | 1.9087 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1
- Type
- mistral
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025