metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: zephyr_instruct_generation
results: []
zephyr_instruct_generation
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6969
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 250
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9323 | 0.4 | 10 | 2.3454 |
| 1.8157 | 0.8 | 20 | 1.2996 |
| 1.0619 | 1.2 | 30 | 0.9573 |
| 0.9194 | 1.6 | 40 | 0.8412 |
| 0.8632 | 2.0 | 50 | 0.7692 |
| 0.7134 | 2.4 | 60 | 0.7218 |
| 0.713 | 2.8 | 70 | 0.6712 |
| 0.5945 | 3.2 | 80 | 0.6554 |
| 0.5862 | 3.6 | 90 | 0.6273 |
| 0.5921 | 4.0 | 100 | 0.5959 |
| 0.4869 | 4.4 | 110 | 0.6252 |
| 0.4996 | 4.8 | 120 | 0.5930 |
| 0.4916 | 5.2 | 130 | 0.6227 |
| 0.4385 | 5.6 | 140 | 0.6186 |
| 0.4755 | 6.0 | 150 | 0.6063 |
| 0.4194 | 6.4 | 160 | 0.6827 |
| 0.4211 | 6.8 | 170 | 0.6189 |
| 0.3944 | 7.2 | 180 | 0.6656 |
| 0.3687 | 7.6 | 190 | 0.6673 |
| 0.3811 | 8.0 | 200 | 0.6728 |
| 0.3537 | 8.4 | 210 | 0.7390 |
| 0.3427 | 8.8 | 220 | 0.6733 |
| 0.3373 | 9.2 | 230 | 0.7724 |
| 0.3415 | 9.6 | 240 | 0.6975 |
| 0.3325 | 10.0 | 250 | 0.6969 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0