metadata
base_model: Qwen/Qwen-14B
tags:
- generated_from_trainer
model-index:
- name: OpenAssistant_oasst_top1_2023-08-25
results: []
OpenAssistant_oasst_top1_2023-08-25
This model is a fine-tuned version of Qwen/Qwen-14B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6501
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.01
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.163 | 0.02 | 16 | 1.9459 |
| 1.9498 | 0.04 | 32 | 1.8467 |
| 1.9578 | 0.06 | 48 | 1.7864 |
| 1.8398 | 0.08 | 64 | 1.7530 |
| 1.7696 | 0.1 | 80 | 1.7076 |
| 1.7744 | 0.12 | 96 | 1.7275 |
| 1.8108 | 0.14 | 112 | 1.6887 |
| 1.7707 | 0.17 | 128 | 1.6942 |
| 1.787 | 0.19 | 144 | 1.6894 |
| 1.7029 | 0.21 | 160 | 1.6760 |
| 1.6732 | 0.23 | 176 | 1.6838 |
| 1.6313 | 0.25 | 192 | 1.6754 |
| 1.7071 | 0.27 | 208 | 1.6752 |
| 1.6781 | 0.29 | 224 | 1.6741 |
| 1.7782 | 0.31 | 240 | 1.6698 |
| 1.6836 | 0.33 | 256 | 1.6592 |
| 1.7229 | 0.35 | 272 | 1.6633 |
| 1.7196 | 0.37 | 288 | 1.6638 |
| 1.6892 | 0.39 | 304 | 1.6627 |
| 1.6844 | 0.41 | 320 | 1.6557 |
| 1.8027 | 0.43 | 336 | 1.6540 |
| 1.692 | 0.45 | 352 | 1.6577 |
| 1.7088 | 0.47 | 368 | 1.6611 |
| 1.7987 | 0.5 | 384 | 1.6557 |
| 1.709 | 0.52 | 400 | 1.6600 |
| 1.701 | 0.54 | 416 | 1.6588 |
| 1.6784 | 0.56 | 432 | 1.6594 |
| 1.6997 | 0.58 | 448 | 1.6484 |
| 1.7811 | 0.6 | 464 | 1.6583 |
| 1.7628 | 0.62 | 480 | 1.6461 |
| 1.6254 | 0.64 | 496 | 1.6527 |
| 1.6684 | 0.66 | 512 | 1.6520 |
| 1.6837 | 0.68 | 528 | 1.6570 |
| 1.7209 | 0.7 | 544 | 1.6543 |
| 1.677 | 0.72 | 560 | 1.6562 |
| 1.6819 | 0.74 | 576 | 1.6517 |
| 1.7072 | 0.76 | 592 | 1.6551 |
| 1.6446 | 0.78 | 608 | 1.6562 |
| 1.6908 | 0.8 | 624 | 1.6528 |
| 1.7209 | 0.83 | 640 | 1.6518 |
| 1.6818 | 0.85 | 656 | 1.6517 |
| 1.7007 | 0.87 | 672 | 1.6525 |
| 1.8077 | 0.89 | 688 | 1.6522 |
| 1.6856 | 0.91 | 704 | 1.6516 |
| 1.7247 | 0.93 | 720 | 1.6509 |
| 1.6645 | 0.95 | 736 | 1.6500 |
| 1.6841 | 0.97 | 752 | 1.6499 |
| 1.7244 | 0.99 | 768 | 1.6501 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.1.0
- Datasets 2.14.7
- Tokenizers 0.13.3