Downloads · 30 days
8
31% of all-time downloads
scottsuk0306_-_zephyr-7b-stem-train-8bits
RichardErkhov/scottsuk0306_-_zephyr-7b-stem-train-8bits
scottsuk0306_-_zephyr-7b-stem-train-8bits 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
26
Public
Parameters
7.2B
7.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
Parameter types
How the weights are stored.
I87B · 96%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
zephyr-7b-stem-train - bnb 8bits
- Model creator: https://huggingface.co/scottsuk0306/
- Original model: https://huggingface.co/scottsuk0306/zephyr-7b-stem-train/
Original model description:
library_name: transformers license: apache-2.0 base_model: alignment-handbook/zephyr-7b-sft-full tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer datasets:
- scottsuk0306/DepthQA model-index:
- name: zephyr-7b-stem-train 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. -->
zephyr-7b-stem-train
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the scottsuk0306/DepthQA dataset. It achieves the following results on the evaluation set:
- Loss: 0.4842
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1139 | 1.0 | 1 | 1.1133 |
| 1.1139 | 2.0 | 2 | 1.2947 |
| 1.1139 | 3.0 | 3 | 1.0840 |
| 1.1139 | 4.0 | 4 | 0.8533 |
| 1.0874 | 5.0 | 5 | 0.7534 |
| 1.0874 | 6.0 | 6 | 0.6295 |
| 1.0874 | 7.0 | 7 | 0.5679 |
| 1.0874 | 8.0 | 8 | 0.5225 |
| 1.0874 | 9.0 | 9 | 0.4936 |
| 0.5928 | 10.0 | 10 | 0.4842 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Type
- mistral
- Created
- Mar 15, 2025
- Updated
- Mar 15, 2025