update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gpt2-kl_01_04-hs_cn-loto_lgbt
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# gpt2-kl_01_04-hs_cn-loto_lgbt
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5297
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 21
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 43 |
+
- num_epochs: 3.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 72.2334 | 0.03 | 10 | 64.5474 |
|
| 50 |
+
| 30.2905 | 0.06 | 20 | 17.8612 |
|
| 51 |
+
| 8.886 | 0.08 | 30 | 6.3404 |
|
| 52 |
+
| 3.4861 | 0.11 | 40 | 2.6744 |
|
| 53 |
+
| 1.6441 | 0.14 | 50 | 1.1987 |
|
| 54 |
+
| 0.9746 | 0.17 | 60 | 0.8715 |
|
| 55 |
+
| 1.0152 | 0.2 | 70 | 0.7307 |
|
| 56 |
+
| 0.7374 | 0.23 | 80 | 0.6868 |
|
| 57 |
+
| 0.6436 | 0.25 | 90 | 0.6203 |
|
| 58 |
+
| 0.7525 | 0.28 | 100 | 0.6001 |
|
| 59 |
+
| 0.6146 | 0.31 | 110 | 0.5946 |
|
| 60 |
+
| 0.5676 | 0.34 | 120 | 0.5914 |
|
| 61 |
+
| 0.563 | 0.37 | 130 | 0.5716 |
|
| 62 |
+
| 0.6439 | 0.4 | 140 | 0.5743 |
|
| 63 |
+
| 0.5706 | 0.42 | 150 | 0.5702 |
|
| 64 |
+
| 0.689 | 0.45 | 160 | 0.5696 |
|
| 65 |
+
| 0.5986 | 0.48 | 170 | 0.5557 |
|
| 66 |
+
| 0.6159 | 0.51 | 180 | 0.5606 |
|
| 67 |
+
| 0.5925 | 0.54 | 190 | 0.5498 |
|
| 68 |
+
| 0.6124 | 0.57 | 200 | 0.5496 |
|
| 69 |
+
| 0.559 | 0.59 | 210 | 0.5501 |
|
| 70 |
+
| 0.6202 | 0.62 | 220 | 0.5544 |
|
| 71 |
+
| 0.6504 | 0.65 | 230 | 0.5486 |
|
| 72 |
+
| 0.697 | 0.68 | 240 | 0.5528 |
|
| 73 |
+
| 0.5171 | 0.71 | 250 | 0.5522 |
|
| 74 |
+
| 0.6247 | 0.74 | 260 | 0.5390 |
|
| 75 |
+
| 0.5882 | 0.76 | 270 | 0.5350 |
|
| 76 |
+
| 0.5941 | 0.79 | 280 | 0.5339 |
|
| 77 |
+
| 0.5673 | 0.82 | 290 | 0.5321 |
|
| 78 |
+
| 0.6336 | 0.85 | 300 | 0.5307 |
|
| 79 |
+
| 0.5581 | 0.88 | 310 | 0.5264 |
|
| 80 |
+
| 0.5499 | 0.91 | 320 | 0.5251 |
|
| 81 |
+
| 0.5626 | 0.93 | 330 | 0.5227 |
|
| 82 |
+
| 0.5443 | 0.96 | 340 | 0.5205 |
|
| 83 |
+
| 0.6252 | 0.99 | 350 | 0.5215 |
|
| 84 |
+
| 0.5427 | 1.02 | 360 | 0.5241 |
|
| 85 |
+
| 0.5231 | 1.05 | 370 | 0.5297 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.28.0
|
| 91 |
+
- Pytorch 1.11.0+cu113
|
| 92 |
+
- Datasets 2.11.0
|
| 93 |
+
- Tokenizers 0.13.3
|