Downloads · 30 days
2
8% of all-time downloads
bobai_pt_sft_15000tok_test_2_merged_lr9
IOAIQian/bobai_pt_sft_15000tok_test_2_merged_lr9
bobai_pt_sft_15000tok_test_2_merged_lr9 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
25
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 10, 2024
- Updated
- Aug 10, 2024
- SHA
- 54b71fdf
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_lr9
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4936
- F1: 0.8762
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 |
|---|---|---|---|---|
| 1.4624 | 1.0 | 12 | 1.4135 | 0.4254 |
| 1.2222 | 2.0 | 24 | 1.1007 | 0.4591 |
| 1.0322 | 3.0 | 36 | 0.8439 | 0.6246 |
| 0.7293 | 4.0 | 48 | 0.6618 | 0.7468 |
| 0.6532 | 5.0 | 60 | 0.5634 | 0.8003 |
| 0.5541 | 6.0 | 72 | 0.4884 | 0.8251 |
| 0.5418 | 7.0 | 84 | 0.4676 | 0.8280 |
| 0.3712 | 8.0 | 96 | 0.4104 | 0.8562 |
| 0.3216 | 9.0 | 108 | 0.4172 | 0.8504 |
| 0.2532 | 10.0 | 120 | 0.3928 | 0.8515 |
| 0.2873 | 11.0 | 132 | 0.3865 | 0.8527 |
| 0.298 | 12.0 | 144 | 0.4006 | 0.8575 |
| 0.1543 | 13.0 | 156 | 0.3808 | 0.8759 |
| 0.2007 | 14.0 | 168 | 0.3850 | 0.8665 |
| 0.192 | 15.0 | 180 | 0.3844 | 0.8724 |
| 0.1697 | 16.0 | 192 | 0.3884 | 0.8729 |
| 0.1872 | 17.0 | 204 | 0.3917 | 0.8717 |
| 0.1222 | 18.0 | 216 | 0.3966 | 0.8775 |
| 0.0855 | 19.0 | 228 | 0.4049 | 0.8760 |
| 0.0421 | 20.0 | 240 | 0.4192 | 0.8812 |
| 0.0447 | 21.0 | 252 | 0.4203 | 0.8767 |
| 0.0551 | 22.0 | 264 | 0.4238 | 0.8871 |
| 0.0549 | 23.0 | 276 | 0.4319 | 0.8769 |
| 0.0524 | 24.0 | 288 | 0.4284 | 0.8767 |
| 0.0863 | 25.0 | 300 | 0.4395 | 0.8767 |
| 0.0671 | 26.0 | 312 | 0.4399 | 0.8824 |
| 0.0523 | 27.0 | 324 | 0.4435 | 0.8767 |
| 0.0506 | 28.0 | 336 | 0.4702 | 0.8762 |
| 0.0414 | 29.0 | 348 | 0.4653 | 0.8762 |
| 0.021 | 30.0 | 360 | 0.4627 | 0.8771 |
| 0.0247 | 31.0 | 372 | 0.4751 | 0.8819 |
| 0.0203 | 32.0 | 384 | 0.4774 | 0.8767 |
| 0.0135 | 33.0 | 396 | 0.4739 | 0.8819 |
| 0.0225 | 34.0 | 408 | 0.4665 | 0.8824 |
| 0.0264 | 35.0 | 420 | 0.4752 | 0.8724 |
| 0.0176 | 36.0 | 432 | 0.4826 | 0.8719 |
| 0.0092 | 37.0 | 444 | 0.4850 | 0.8767 |
| 0.0271 | 38.0 | 456 | 0.4805 | 0.8724 |
| 0.0473 | 39.0 | 468 | 0.4816 | 0.8776 |
| 0.0502 | 40.0 | 480 | 0.4873 | 0.8767 |
| 0.0427 | 41.0 | 492 | 0.4888 | 0.8762 |
| 0.0217 | 42.0 | 504 | 0.4901 | 0.8762 |
| 0.022 | 43.0 | 516 | 0.4911 | 0.8819 |
| 0.0222 | 44.0 | 528 | 0.4927 | 0.8762 |
| 0.0235 | 45.0 | 540 | 0.4944 | 0.8762 |
| 0.0168 | 46.0 | 552 | 0.4939 | 0.8762 |
| 0.0131 | 47.0 | 564 | 0.4936 | 0.8762 |
| 0.0123 | 48.0 | 576 | 0.4935 | 0.8762 |
| 0.0145 | 49.0 | 588 | 0.4936 | 0.8762 |
| 0.0156 | 50.0 | 600 | 0.4936 | 0.8762 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Type
- bert
- Created
- Aug 10, 2024
- Updated
- Aug 10, 2024