Commit
•
d585867
1
Parent(s):
b0030ec
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- generator
|
| 7 |
+
model-index:
|
| 8 |
+
- name: scideberta-cs-tdm-pretrained-finetuned-ner-finetuned-ner
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# scideberta-cs-tdm-pretrained-finetuned-ner-finetuned-ner
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the generator dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7548
|
| 20 |
+
- Overall Precision: 0.5582
|
| 21 |
+
- Overall Recall: 0.7048
|
| 22 |
+
- Overall F1: 0.6230
|
| 23 |
+
- Overall Accuracy: 0.9578
|
| 24 |
+
- Datasetname F1: 0.6225
|
| 25 |
+
- Hyperparametername F1: 0.5707
|
| 26 |
+
- Hyperparametervalue F1: 0.6796
|
| 27 |
+
- Methodname F1: 0.6812
|
| 28 |
+
- Metricname F1: 0.5039
|
| 29 |
+
- Metricvalue F1: 0.7097
|
| 30 |
+
- Taskname F1: 0.5776
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 2e-05
|
| 50 |
+
- train_batch_size: 8
|
| 51 |
+
- eval_batch_size: 8
|
| 52 |
+
- seed: 42
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- num_epochs: 100
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Datasetname F1 | Hyperparametername F1 | Hyperparametervalue F1 | Methodname F1 | Metricname F1 | Metricvalue F1 | Taskname F1 |
|
| 60 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:---------------------:|:----------------------:|:-------------:|:-------------:|:--------------:|:-----------:|
|
| 61 |
+
| No log | 1.0 | 132 | 0.6819 | 0.2314 | 0.3769 | 0.2867 | 0.9125 | 0.1270 | 0.2305 | 0.2479 | 0.4072 | 0.3119 | 0.0635 | 0.2366 |
|
| 62 |
+
| No log | 2.0 | 264 | 0.4337 | 0.3977 | 0.5687 | 0.4681 | 0.9429 | 0.4516 | 0.3704 | 0.5419 | 0.5900 | 0.2446 | 0.4340 | 0.4609 |
|
| 63 |
+
| No log | 3.0 | 396 | 0.3968 | 0.3617 | 0.6367 | 0.4613 | 0.9335 | 0.4828 | 0.3586 | 0.5649 | 0.5331 | 0.3190 | 0.4800 | 0.4585 |
|
| 64 |
+
| 0.5603 | 4.0 | 528 | 0.3730 | 0.3605 | 0.6327 | 0.4593 | 0.9363 | 0.4750 | 0.3789 | 0.6066 | 0.5376 | 0.3229 | 0.4571 | 0.4375 |
|
| 65 |
+
| 0.5603 | 5.0 | 660 | 0.4132 | 0.4650 | 0.6871 | 0.5546 | 0.9482 | 0.4943 | 0.4965 | 0.6577 | 0.6465 | 0.4387 | 0.5306 | 0.5039 |
|
| 66 |
+
| 0.5603 | 6.0 | 792 | 0.4071 | 0.4482 | 0.6884 | 0.5429 | 0.9468 | 0.5541 | 0.4341 | 0.5991 | 0.6037 | 0.4865 | 0.64 | 0.5688 |
|
| 67 |
+
| 0.5603 | 7.0 | 924 | 0.4077 | 0.4830 | 0.6952 | 0.5700 | 0.9508 | 0.5063 | 0.4953 | 0.7032 | 0.6397 | 0.4286 | 0.6263 | 0.5469 |
|
| 68 |
+
| 0.1161 | 8.0 | 1056 | 0.5215 | 0.5426 | 0.6925 | 0.6085 | 0.9577 | 0.6423 | 0.5190 | 0.7115 | 0.6711 | 0.5175 | 0.6286 | 0.5797 |
|
| 69 |
+
| 0.1161 | 9.0 | 1188 | 0.5192 | 0.4859 | 0.7020 | 0.5743 | 0.9518 | 0.5578 | 0.5195 | 0.5992 | 0.6571 | 0.4744 | 0.5532 | 0.5611 |
|
| 70 |
+
| 0.1161 | 10.0 | 1320 | 0.5301 | 0.5478 | 0.7020 | 0.6154 | 0.9563 | 0.5732 | 0.5782 | 0.7619 | 0.6462 | 0.4675 | 0.7253 | 0.5727 |
|
| 71 |
+
| 0.1161 | 11.0 | 1452 | 0.4965 | 0.5139 | 0.7048 | 0.5944 | 0.9531 | 0.5857 | 0.5290 | 0.7189 | 0.6639 | 0.4235 | 0.6476 | 0.5532 |
|
| 72 |
+
| 0.049 | 12.0 | 1584 | 0.6207 | 0.5713 | 0.6925 | 0.6261 | 0.9582 | 0.64 | 0.5377 | 0.7594 | 0.7207 | 0.5070 | 0.6136 | 0.5530 |
|
| 73 |
+
| 0.049 | 13.0 | 1716 | 0.6056 | 0.5360 | 0.7088 | 0.6104 | 0.9570 | 0.5921 | 0.5035 | 0.7000 | 0.7115 | 0.4648 | 0.6939 | 0.5854 |
|
| 74 |
+
| 0.049 | 14.0 | 1848 | 0.6540 | 0.5804 | 0.6925 | 0.6315 | 0.9599 | 0.6466 | 0.5344 | 0.7324 | 0.6874 | 0.5401 | 0.7083 | 0.5980 |
|
| 75 |
+
| 0.049 | 15.0 | 1980 | 0.5911 | 0.5068 | 0.7048 | 0.5896 | 0.9528 | 0.5399 | 0.5176 | 0.7150 | 0.6397 | 0.4625 | 0.6800 | 0.5865 |
|
| 76 |
+
| 0.0225 | 16.0 | 2112 | 0.5788 | 0.5186 | 0.7007 | 0.5961 | 0.9531 | 0.5874 | 0.5011 | 0.7177 | 0.6796 | 0.4810 | 0.6744 | 0.5517 |
|
| 77 |
+
| 0.0225 | 17.0 | 2244 | 0.6097 | 0.5399 | 0.6912 | 0.6062 | 0.9547 | 0.5811 | 0.5744 | 0.6900 | 0.6439 | 0.5033 | 0.7253 | 0.5470 |
|
| 78 |
+
| 0.0225 | 18.0 | 2376 | 0.7006 | 0.5714 | 0.6748 | 0.6188 | 0.9590 | 0.6471 | 0.5645 | 0.6465 | 0.6710 | 0.5426 | 0.6809 | 0.5755 |
|
| 79 |
+
| 0.0149 | 19.0 | 2508 | 0.6051 | 0.5400 | 0.7252 | 0.6190 | 0.9554 | 0.6443 | 0.5514 | 0.6547 | 0.6777 | 0.5132 | 0.6947 | 0.6 |
|
| 80 |
+
| 0.0149 | 20.0 | 2640 | 0.7220 | 0.5995 | 0.6884 | 0.6409 | 0.9605 | 0.6429 | 0.5570 | 0.6806 | 0.7339 | 0.5865 | 0.7416 | 0.5540 |
|
| 81 |
+
| 0.0149 | 21.0 | 2772 | 0.6912 | 0.5977 | 0.7034 | 0.6462 | 0.9599 | 0.6377 | 0.5387 | 0.7343 | 0.7281 | 0.5846 | 0.7273 | 0.5899 |
|
| 82 |
+
| 0.0149 | 22.0 | 2904 | 0.6952 | 0.5802 | 0.6939 | 0.6320 | 0.9574 | 0.5867 | 0.5445 | 0.7358 | 0.6951 | 0.5736 | 0.7473 | 0.5830 |
|
| 83 |
+
| 0.0097 | 23.0 | 3036 | 0.7600 | 0.6241 | 0.6912 | 0.6559 | 0.9618 | 0.6119 | 0.5895 | 0.7629 | 0.7356 | 0.5512 | 0.6897 | 0.5837 |
|
| 84 |
+
| 0.0097 | 24.0 | 3168 | 0.7184 | 0.5924 | 0.6980 | 0.6408 | 0.9598 | 0.6486 | 0.5640 | 0.7179 | 0.7146 | 0.5630 | 0.7174 | 0.5714 |
|
| 85 |
+
| 0.0097 | 25.0 | 3300 | 0.7120 | 0.5485 | 0.7007 | 0.6153 | 0.9566 | 0.6579 | 0.5441 | 0.6667 | 0.6993 | 0.4774 | 0.6522 | 0.5766 |
|
| 86 |
+
| 0.0097 | 26.0 | 3432 | 0.7914 | 0.6009 | 0.7088 | 0.6504 | 0.9583 | 0.6443 | 0.6070 | 0.7293 | 0.7082 | 0.5645 | 0.6737 | 0.5872 |
|
| 87 |
+
| 0.0065 | 27.0 | 3564 | 0.7986 | 0.5800 | 0.6952 | 0.6324 | 0.9589 | 0.6309 | 0.5521 | 0.7150 | 0.7281 | 0.4844 | 0.7097 | 0.5714 |
|
| 88 |
+
| 0.0065 | 28.0 | 3696 | 0.7767 | 0.6087 | 0.7007 | 0.6515 | 0.9599 | 0.6364 | 0.5824 | 0.7526 | 0.7169 | 0.5238 | 0.7097 | 0.6038 |
|
| 89 |
+
| 0.0065 | 29.0 | 3828 | 0.7435 | 0.6077 | 0.6912 | 0.6467 | 0.9612 | 0.6479 | 0.5674 | 0.7396 | 0.7088 | 0.5255 | 0.7333 | 0.6066 |
|
| 90 |
+
| 0.0065 | 30.0 | 3960 | 0.8305 | 0.6230 | 0.6857 | 0.6528 | 0.9613 | 0.6483 | 0.5650 | 0.7817 | 0.7341 | 0.4715 | 0.7174 | 0.5962 |
|
| 91 |
+
| 0.0051 | 31.0 | 4092 | 0.7180 | 0.5776 | 0.7088 | 0.6365 | 0.9583 | 0.6194 | 0.5825 | 0.7393 | 0.6874 | 0.4923 | 0.7021 | 0.5962 |
|
| 92 |
+
| 0.0051 | 32.0 | 4224 | 0.7526 | 0.5708 | 0.6857 | 0.6230 | 0.9585 | 0.64 | 0.5276 | 0.7246 | 0.7083 | 0.4627 | 0.6813 | 0.5922 |
|
| 93 |
+
| 0.0051 | 33.0 | 4356 | 0.7548 | 0.5582 | 0.7048 | 0.6230 | 0.9578 | 0.6225 | 0.5707 | 0.6796 | 0.6812 | 0.5039 | 0.7097 | 0.5776 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.23.1
|
| 99 |
+
- Pytorch 1.12.1+cu102
|
| 100 |
+
- Datasets 2.6.1
|
| 101 |
+
- Tokenizers 0.13.1
|