metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: Deci/DeciLM-7B
model-index:
- name: DeciLM7B-FineTuning-checkpoints
results: []
DeciLM7B-FineTuning-checkpoints
This model is a fine-tuned version of Deci/DeciLM-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6058
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: reduce_lr_on_plateau
- lr_scheduler_warmup_steps: 150
- training_steps: 738
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2254 | 3.23 | 100 | 2.1523 |
| 0.4367 | 6.45 | 200 | 2.2709 |
| 0.3763 | 9.68 | 300 | 2.4208 |
| 0.3719 | 12.9 | 400 | 2.4735 |
| 0.355 | 16.13 | 500 | 2.7165 |
| 0.3513 | 19.35 | 600 | 2.7926 |
| 0.3738 | 22.58 | 700 | 2.6058 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0