metadata
license: apache-2.0
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: norallm/normistral-7b-warm
datasets:
- hugodk-sch/aftonposten_title_sft
model-index:
- name: ap-normistral-7b-sft-qlora
results: []
ap-normistral-7b-sft-qlora
This model is a fine-tuned version of norallm/normistral-7b-warm on the hugodk-sch/aftonposten_title_sft dataset. It achieves the following results on the evaluation set:
- Loss: 1.6055
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.063 | 1.0 | 264 | 2.1618 |
| 1.2293 | 2.0 | 528 | 1.9121 |
| 0.6985 | 3.0 | 792 | 1.6916 |
| 0.4922 | 4.0 | 1056 | 1.6054 |
| 0.3396 | 5.0 | 1320 | 1.6055 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1