metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrachat_200k
base_model: BEE-spoke-data/smol_llama-220M-openhermes
model-index:
- name: zephyr-220m-sft-full
results: []
zephyr-220m-sft-full
This model is a fine-tuned version of BEE-spoke-data/smol_llama-220M-openhermes on the Ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.6579
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6447 | 1.0 | 1624 | 1.6579 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 29.33 |
| AI2 Reasoning Challenge (25-Shot) | 25.26 |
| HellaSwag (10-Shot) | 29.03 |
| MMLU (5-Shot) | 26.45 |
| TruthfulQA (0-shot) | 43.23 |
| Winogrande (5-shot) | 51.62 |
| GSM8k (5-shot) | 0.38 |