update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: ossp-v0_3
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# ossp-v0_3
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [leadawon/ossp-v0_2](https://huggingface.co/leadawon/ossp-v0_2) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.3451
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 24
|
| 37 |
+
- eval_batch_size: 24
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 42 |
+
- num_epochs: 4
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
| 49 |
+
| 0.3999 | 0.2 | 10000 | 0.4079 |
|
| 50 |
+
| 0.4441 | 0.39 | 20000 | 0.4555 |
|
| 51 |
+
| 0.4361 | 0.59 | 30000 | 0.4378 |
|
| 52 |
+
| 0.4302 | 0.79 | 40000 | 0.4255 |
|
| 53 |
+
| 0.4392 | 0.98 | 50000 | 0.4076 |
|
| 54 |
+
| 0.3714 | 1.18 | 60000 | 0.4006 |
|
| 55 |
+
| 0.3694 | 1.38 | 70000 | 0.3908 |
|
| 56 |
+
| 0.3591 | 1.57 | 80000 | 0.3810 |
|
| 57 |
+
| 0.3594 | 1.77 | 90000 | 0.3762 |
|
| 58 |
+
| 0.3567 | 1.97 | 100000 | 0.3667 |
|
| 59 |
+
| 0.3041 | 2.16 | 110000 | 0.3663 |
|
| 60 |
+
| 0.299 | 2.36 | 120000 | 0.3603 |
|
| 61 |
+
| 0.2972 | 2.56 | 130000 | 0.3569 |
|
| 62 |
+
| 0.2892 | 2.75 | 140000 | 0.3519 |
|
| 63 |
+
| 0.2844 | 2.95 | 150000 | 0.3463 |
|
| 64 |
+
| 0.2372 | 3.15 | 160000 | 0.3522 |
|
| 65 |
+
| 0.2367 | 3.34 | 170000 | 0.3508 |
|
| 66 |
+
| 0.2295 | 3.54 | 180000 | 0.3489 |
|
| 67 |
+
| 0.2281 | 3.74 | 190000 | 0.3468 |
|
| 68 |
+
| 0.2233 | 3.93 | 200000 | 0.3451 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.28.1
|
| 74 |
+
- Pytorch 2.0.0+cu118
|
| 75 |
+
- Tokenizers 0.13.3
|