metadata
base_model: HuggingFaceH4/zephyr-7b-beta
library_name: peft
license: mit
tags:
- generated_from_trainer
model-index:
- name: peft-dialogue-summary-training-1725686937
results: []
peft-dialogue-summary-training-1725686937
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: 0.9554
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.605 | 0.0078 | 25 | 1.0042 |
| 0.5464 | 0.0155 | 50 | 1.1322 |
| 1.2482 | 0.0233 | 75 | 0.9708 |
| 0.5344 | 0.0311 | 100 | 0.9554 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1