100 lines
4.3 KiB
Markdown
100 lines
4.3 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: argilla/zephyr-7b-spin-iter2-v0
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: zephyr-7b-spin-iter3-v0
|
||
|
|
results: []
|
||
|
|
datasets:
|
||
|
|
- argilla/10k_prompts_SPIN_iter3_zephyr_top
|
||
|
|
- argilla/10k_prompts_SPIN_iter2_zephyr_top
|
||
|
|
- DIBT/10k_prompts_ranked
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- 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-spin-iter3-v0
|
||
|
|
|
||
|
|
> A model matching the results of SPIN with very little data (30x less), carefully curated by the amazing [Data Is Better Together community](https://huggingface.co/DIBT)
|
||
|
|
|
||
|
|
<div>
|
||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/aEzpD6gvn0xOrN2rNzpZI.webp">
|
||
|
|
</div>
|
||
|
|
|
||
|
|
|
||
|
|
<p align="center">
|
||
|
|
<a href="https://github.com/argilla-io/distilabel">
|
||
|
|
<img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
|
||
|
|
</a>
|
||
|
|
</p>
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [argilla/zephyr-7b-spin-iter2-v0](https://huggingface.co/argilla/zephyr-7b-spin-iter2-v0) on the
|
||
|
|
[argilla/10k_prompts_SPIN_iter3_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter3_zephyr_top) and the
|
||
|
|
[argilla/10k_prompts_SPIN_iter2_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter2_zephyr_top) dataset.
|
||
|
|
|
||
|
|
Check [this repo](https://github.com/argilla-io/distilabel-spin-dibt) for full reproducible code using the original SPIN implementation and distilabel.
|
||
|
|
|
||
|
|
If you want to contribute to high quality datasets like this, contribute to the [DIBT prompt collective initiative](https://huggingface.co/spaces/DIBT/prompt-collective-dashboard).
|
||
|
|
|
||
|
|
|
||
|
|
## MT-Bench results
|
||
|
|
|
||
|
|
| Model | 1st Turn Score | 2nd Turn Score | Average Score | SPIN paper Score |
|
||
|
|
|-------------------------|----------------|----------------|---------------|------------------|
|
||
|
|
| zephyr-7b-sft-full | 6.6625 | 6.0250 | 6.34375 | 5.94 |
|
||
|
|
| zephyr-7b-spin-iter0-v0 | 6.64375 | 6.1750 | 6.409375 | 6.46 |
|
||
|
|
| zephyr-7b-spin-iter1-v0 | 6.90625 | 6.3000 | 6.603125 | 6.65 |
|
||
|
|
| zephyr-7b-spin-iter2-v0 | **7.1375** | 6.3125 | 6.725000 | 6.78 |
|
||
|
|
| zephyr-7b-spin-iter3-v0 | 7.09375 | **6.4500** | **6.771875** | - |
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## 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: 8
|
||
|
|
- eval_batch_size: 8
|
||
|
|
- seed: 42
|
||
|
|
- distributed_type: multi-GPU
|
||
|
|
- num_devices: 4
|
||
|
|
- gradient_accumulation_steps: 2
|
||
|
|
- total_train_batch_size: 64
|
||
|
|
- total_eval_batch_size: 32
|
||
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||
|
|
- lr_scheduler_type: linear
|
||
|
|
- lr_scheduler_warmup_ratio: 0.1
|
||
|
|
- num_epochs: 2.0
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|
||
|
|
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
|
||
|
|
| 0.2928 | 0.49 | 25 | 0.3951 | -2.6212 | -20.3268 | 0.9062 | 17.7056 | -700.5638 | -278.0876 | -2.8098 | -2.8090 |
|
||
|
|
| 0.1487 | 0.97 | 50 | 0.1319 | -2.9077 | -29.1459 | 0.9375 | 26.2382 | -702.3276 | -278.1449 | -2.8218 | -2.8066 |
|
||
|
|
| 0.006 | 1.46 | 75 | 0.1269 | -2.6037 | -29.1519 | 0.9583 | 26.5482 | -702.3289 | -278.0841 | -2.8175 | -2.8037 |
|
||
|
|
| 0.0086 | 1.94 | 100 | 0.1099 | -2.9181 | -29.6970 | 0.9271 | 26.7789 | -702.4378 | -278.1470 | -2.8177 | -2.8051 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.37.0
|
||
|
|
- Pytorch 2.1.2+cu121
|
||
|
|
- Datasets 2.14.6
|
||
|
|
- Tokenizers 0.15.2
|