metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: teknium/OpenHermes-2.5-Mistral-7B
model-index:
- name: paper_imp_new_format_1
results: []
paper_imp_new_format_1
This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6991
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8356 | 0.33 | 9 | 1.8214 |
| 1.8011 | 0.67 | 18 | 1.7745 |
| 1.724 | 1.0 | 27 | 1.6848 |
| 1.6316 | 1.33 | 36 | 1.5849 |
| 1.5605 | 1.67 | 45 | 1.4827 |
| 1.4149 | 2.0 | 54 | 1.3548 |
| 1.2969 | 2.33 | 63 | 1.1693 |
| 0.9925 | 2.67 | 72 | 0.9323 |
| 0.8631 | 3.0 | 81 | 0.8125 |
| 0.7053 | 3.33 | 90 | 0.7490 |
| 0.6931 | 3.67 | 99 | 0.7222 |
| 0.6993 | 4.0 | 108 | 0.6991 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0