update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
model-index:
|
| 8 |
+
- name: albert-offensive-lm-tapt-finetuned
|
| 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 |
+
# albert-offensive-lm-tapt-finetuned
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [k4black/albert-offensive-lm-tapt](https://huggingface.co/k4black/albert-offensive-lm-tapt) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4680
|
| 20 |
+
- F1: 0.7765
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 12
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 52 |
+
| 0.6585 | 0.1 | 100 | 0.6663 | 0.3932 |
|
| 53 |
+
| 0.6308 | 0.2 | 200 | 0.5807 | 0.5746 |
|
| 54 |
+
| 0.5161 | 0.29 | 300 | 0.5005 | 0.7366 |
|
| 55 |
+
| 0.4986 | 0.39 | 400 | 0.4984 | 0.7434 |
|
| 56 |
+
| 0.484 | 0.49 | 500 | 0.4956 | 0.7098 |
|
| 57 |
+
| 0.5035 | 0.59 | 600 | 0.4876 | 0.7334 |
|
| 58 |
+
| 0.4767 | 0.69 | 700 | 0.4824 | 0.7314 |
|
| 59 |
+
| 0.482 | 0.78 | 800 | 0.4937 | 0.7194 |
|
| 60 |
+
| 0.4524 | 0.88 | 900 | 0.4759 | 0.7606 |
|
| 61 |
+
| 0.4541 | 0.98 | 1000 | 0.4786 | 0.7613 |
|
| 62 |
+
| 0.4404 | 1.08 | 1100 | 0.4597 | 0.7663 |
|
| 63 |
+
| 0.4383 | 1.18 | 1200 | 0.4531 | 0.7762 |
|
| 64 |
+
| 0.4414 | 1.27 | 1300 | 0.4436 | 0.7764 |
|
| 65 |
+
| 0.4336 | 1.37 | 1400 | 0.4477 | 0.7625 |
|
| 66 |
+
| 0.4353 | 1.47 | 1500 | 0.4466 | 0.7490 |
|
| 67 |
+
| 0.4356 | 1.57 | 1600 | 0.4429 | 0.7743 |
|
| 68 |
+
| 0.3938 | 1.67 | 1700 | 0.4450 | 0.7727 |
|
| 69 |
+
| 0.4066 | 1.76 | 1800 | 0.4437 | 0.7776 |
|
| 70 |
+
| 0.3867 | 1.86 | 1900 | 0.4717 | 0.7618 |
|
| 71 |
+
| 0.4123 | 1.96 | 2000 | 0.4511 | 0.7689 |
|
| 72 |
+
| 0.3671 | 2.06 | 2100 | 0.4680 | 0.7765 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.23.1
|
| 78 |
+
- Pytorch 1.13.0+cu117
|
| 79 |
+
- Datasets 2.6.1
|
| 80 |
+
- Tokenizers 0.13.1
|