|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: petals-team/falcon-rw-1b |
|
model-index: |
|
- name: GenAI-task-2-ModelD-DS |
|
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. --> |
|
|
|
# GenAI-task-2-ModelD-DS |
|
|
|
This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8551 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.01 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.538 | 0.0316 | 20 | 1.4898 | |
|
| 2.1944 | 0.0631 | 40 | 1.4676 | |
|
| 2.2479 | 0.0947 | 60 | 1.4396 | |
|
| 1.7654 | 0.1263 | 80 | 1.3892 | |
|
| 2.1763 | 0.1579 | 100 | 1.3834 | |
|
| 1.3644 | 0.1894 | 120 | 1.3282 | |
|
| 1.6781 | 0.2210 | 140 | 1.3058 | |
|
| 1.7429 | 0.2526 | 160 | 1.2880 | |
|
| 1.37 | 0.2841 | 180 | 1.2483 | |
|
| 1.8196 | 0.3157 | 200 | 1.2511 | |
|
| 1.223 | 0.3473 | 220 | 1.2120 | |
|
| 1.5357 | 0.3788 | 240 | 1.2171 | |
|
| 1.6471 | 0.4104 | 260 | 1.1906 | |
|
| 1.271 | 0.4420 | 280 | 1.1818 | |
|
| 1.7222 | 0.4736 | 300 | 1.1788 | |
|
| 1.2022 | 0.5051 | 320 | 1.1170 | |
|
| 1.4455 | 0.5367 | 340 | 1.1633 | |
|
| 1.7014 | 0.5683 | 360 | 1.1011 | |
|
| 1.1309 | 0.5998 | 380 | 1.0815 | |
|
| 1.6978 | 0.6314 | 400 | 1.0966 | |
|
| 1.0796 | 0.6630 | 420 | 1.0325 | |
|
| 1.4504 | 0.6946 | 440 | 1.0429 | |
|
| 1.4698 | 0.7261 | 460 | 1.0216 | |
|
| 1.0858 | 0.7577 | 480 | 1.0031 | |
|
| 1.4275 | 0.7893 | 500 | 1.0115 | |
|
| 0.9607 | 0.8208 | 520 | 0.9771 | |
|
| 1.2579 | 0.8524 | 540 | 0.9792 | |
|
| 1.3363 | 0.8840 | 560 | 0.9608 | |
|
| 1.0551 | 0.9155 | 580 | 0.9471 | |
|
| 1.531 | 0.9471 | 600 | 0.9530 | |
|
| 0.9776 | 0.9787 | 620 | 0.9321 | |
|
| 1.374 | 1.0103 | 640 | 0.9257 | |
|
| 0.9688 | 1.0418 | 660 | 0.9217 | |
|
| 1.464 | 1.0734 | 680 | 0.9278 | |
|
| 1.0608 | 1.1050 | 700 | 0.9040 | |
|
| 1.0711 | 1.1365 | 720 | 0.9017 | |
|
| 1.2806 | 1.1681 | 740 | 0.8954 | |
|
| 0.9129 | 1.1997 | 760 | 0.8877 | |
|
| 1.2161 | 1.2313 | 780 | 0.8907 | |
|
| 1.0221 | 1.2628 | 800 | 0.8794 | |
|
| 1.1306 | 1.2944 | 820 | 0.8782 | |
|
| 1.3235 | 1.3260 | 840 | 0.8768 | |
|
| 0.9663 | 1.3575 | 860 | 0.8711 | |
|
| 1.3124 | 1.3891 | 880 | 0.8716 | |
|
| 1.0169 | 1.4207 | 900 | 0.8663 | |
|
| 1.1686 | 1.4522 | 920 | 0.8658 | |
|
| 1.2976 | 1.4838 | 940 | 0.8656 | |
|
| 0.8896 | 1.5154 | 960 | 0.8620 | |
|
| 1.3252 | 1.5470 | 980 | 0.8623 | |
|
| 1.0821 | 1.5785 | 1000 | 0.8601 | |
|
| 1.1595 | 1.6101 | 1020 | 0.8594 | |
|
| 1.4023 | 1.6417 | 1040 | 0.8591 | |
|
| 0.8901 | 1.6732 | 1060 | 0.8574 | |
|
| 1.2387 | 1.7048 | 1080 | 0.8575 | |
|
| 0.9921 | 1.7364 | 1100 | 0.8564 | |
|
| 1.0593 | 1.7680 | 1120 | 0.8558 | |
|
| 1.3434 | 1.7995 | 1140 | 0.8558 | |
|
| 0.8345 | 1.8311 | 1160 | 0.8554 | |
|
| 1.3537 | 1.8627 | 1180 | 0.8554 | |
|
| 1.0417 | 1.8942 | 1200 | 0.8552 | |
|
| 1.0643 | 1.9258 | 1220 | 0.8551 | |
|
| 1.2218 | 1.9574 | 1240 | 0.8551 | |
|
| 1.1633 | 1.9890 | 1260 | 0.8551 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |