Downloads · 30 days
1
5% of all-time downloads
bobai_pt_sft_15000tok_test_2_merged_lr5
IOAIQian/bobai_pt_sft_15000tok_test_2_merged_lr5
bobai_pt_sft_15000tok_test_2_merged_lr5 is a machine learning model from IOAIQian. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
21
Public
Parameters
179M
715 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors715 MB · 99%
At a glance
- Model type
- bert
- Access
- Public
- Created
- Aug 5, 2024
- Updated
- Aug 5, 2024
- SHA
- 1c08f37d
Model card
From the Hugging Face model README
<!-- 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. -->
bobai_pt_sft_15000tok_test_2_merged_lr5
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5850
- F1: 0.8901
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: 128
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.4134 | 1.0 | 12 | 1.3248 | 0.4767 |
| 1.0646 | 2.0 | 24 | 0.9354 | 0.6678 |
| 0.9275 | 3.0 | 36 | 0.6764 | 0.7504 |
| 0.5852 | 4.0 | 48 | 0.5299 | 0.8117 |
| 0.519 | 5.0 | 60 | 0.4400 | 0.8485 |
| 0.4808 | 6.0 | 72 | 0.4030 | 0.8597 |
| 0.4164 | 7.0 | 84 | 0.3790 | 0.8724 |
| 0.2572 | 8.0 | 96 | 0.3684 | 0.8844 |
| 0.2457 | 9.0 | 108 | 0.3806 | 0.8838 |
| 0.1958 | 10.0 | 120 | 0.3833 | 0.8898 |
| 0.172 | 11.0 | 132 | 0.3912 | 0.8890 |
| 0.1599 | 12.0 | 144 | 0.4046 | 0.8898 |
| 0.1185 | 13.0 | 156 | 0.4092 | 0.8894 |
| 0.0659 | 14.0 | 168 | 0.4185 | 0.8894 |
| 0.0662 | 15.0 | 180 | 0.4303 | 0.8848 |
| 0.0965 | 16.0 | 192 | 0.4439 | 0.8737 |
| 0.0794 | 17.0 | 204 | 0.4609 | 0.8681 |
| 0.0592 | 18.0 | 216 | 0.5050 | 0.8682 |
| 0.0595 | 19.0 | 228 | 0.4705 | 0.8797 |
| 0.0197 | 20.0 | 240 | 0.4713 | 0.8801 |
| 0.0558 | 21.0 | 252 | 0.4882 | 0.8783 |
| 0.0683 | 22.0 | 264 | 0.5046 | 0.8800 |
| 0.0274 | 23.0 | 276 | 0.5142 | 0.8796 |
| 0.015 | 24.0 | 288 | 0.5253 | 0.8675 |
| 0.0155 | 25.0 | 300 | 0.5153 | 0.8796 |
| 0.0142 | 26.0 | 312 | 0.5216 | 0.8792 |
| 0.0128 | 27.0 | 324 | 0.5351 | 0.8854 |
| 0.0108 | 28.0 | 336 | 0.5430 | 0.8797 |
| 0.0094 | 29.0 | 348 | 0.5658 | 0.8762 |
| 0.0109 | 30.0 | 360 | 0.5503 | 0.8897 |
| 0.0082 | 31.0 | 372 | 0.5770 | 0.8712 |
| 0.0119 | 32.0 | 384 | 0.5733 | 0.8709 |
| 0.0129 | 33.0 | 396 | 0.5697 | 0.8806 |
| 0.0061 | 34.0 | 408 | 0.5700 | 0.8764 |
| 0.0075 | 35.0 | 420 | 0.5697 | 0.8901 |
| 0.0063 | 36.0 | 432 | 0.5731 | 0.8791 |
| 0.0068 | 37.0 | 444 | 0.5729 | 0.8901 |
| 0.0057 | 38.0 | 456 | 0.5781 | 0.8843 |
| 0.0071 | 39.0 | 468 | 0.5778 | 0.8901 |
| 0.0108 | 40.0 | 480 | 0.5825 | 0.8758 |
| 0.0131 | 41.0 | 492 | 0.5827 | 0.8858 |
| 0.0065 | 42.0 | 504 | 0.5833 | 0.8901 |
| 0.0073 | 43.0 | 516 | 0.5850 | 0.8855 |
| 0.0057 | 44.0 | 528 | 0.5859 | 0.8843 |
| 0.0056 | 45.0 | 540 | 0.5861 | 0.8843 |
| 0.0059 | 46.0 | 552 | 0.5857 | 0.8901 |
| 0.0055 | 47.0 | 564 | 0.5853 | 0.8901 |
| 0.0055 | 48.0 | 576 | 0.5851 | 0.8901 |
| 0.0129 | 49.0 | 588 | 0.5851 | 0.8901 |
| 0.0093 | 50.0 | 600 | 0.5850 | 0.8901 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Type
- bert
- Created
- Aug 5, 2024
- Updated
- Aug 5, 2024