|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: tiiuae/falcon-rw-1b |
|
|
model-index: |
|
|
- name: qlora-out |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
# qlora-out |
|
|
|
|
|
This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.2365 |
|
|
|
|
|
## 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: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 2 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 10 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.3201 | 0.0 | 5 | 1.9676 | |
|
|
| 2.2557 | 0.0 | 10 | 1.7400 | |
|
|
| 1.571 | 0.0 | 15 | 1.6036 | |
|
|
| 1.3875 | 0.01 | 20 | 1.5074 | |
|
|
| 1.5436 | 0.01 | 25 | 1.4680 | |
|
|
| 1.4257 | 0.01 | 30 | 1.4222 | |
|
|
| 1.097 | 0.01 | 35 | 1.4049 | |
|
|
| 1.4748 | 0.01 | 40 | 1.3831 | |
|
|
| 1.1752 | 0.01 | 45 | 1.3784 | |
|
|
| 1.3857 | 0.01 | 50 | 1.3780 | |
|
|
| 1.5965 | 0.01 | 55 | 1.3631 | |
|
|
| 1.071 | 0.02 | 60 | 1.3275 | |
|
|
| 1.197 | 0.02 | 65 | 1.3171 | |
|
|
| 1.8883 | 0.02 | 70 | 1.3108 | |
|
|
| 1.0119 | 0.02 | 75 | 1.3053 | |
|
|
| 1.399 | 0.02 | 80 | 1.3035 | |
|
|
| 1.5369 | 0.02 | 85 | 1.3028 | |
|
|
| 1.5707 | 0.02 | 90 | 1.2982 | |
|
|
| 1.0073 | 0.03 | 95 | 1.3020 | |
|
|
| 1.1018 | 0.03 | 100 | 1.2908 | |
|
|
| 1.2036 | 0.03 | 105 | 1.2742 | |
|
|
| 1.2444 | 0.03 | 110 | 1.2967 | |
|
|
| 0.6345 | 0.03 | 115 | 1.2656 | |
|
|
| 1.0579 | 0.03 | 120 | 1.2641 | |
|
|
| 1.2388 | 0.03 | 125 | 1.2543 | |
|
|
| 1.0607 | 0.04 | 130 | 1.2552 | |
|
|
| 1.0723 | 0.04 | 135 | 1.2611 | |
|
|
| 1.3775 | 0.04 | 140 | 1.2582 | |
|
|
| 1.1543 | 0.04 | 145 | 1.2527 | |
|
|
| 1.1324 | 0.04 | 150 | 1.2365 | |
|
|
| 0.7309 | 0.04 | 155 | 1.2445 | |
|
|
| 1.3585 | 0.04 | 160 | 1.2491 | |
|
|
| 1.0855 | 0.04 | 165 | 1.2365 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.1.dev0 |
|
|
- Transformers 4.36.0.dev0 |
|
|
- Pytorch 2.0.1+cu117 |
|
|
- Datasets 2.15.0 |
|
|
- Tokenizers 0.15.0 |
