update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gpt2-kl_01_07-hs_cn
|
| 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_07-hs_cn
|
| 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: 0.5492
|
| 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 |
+
| 73.6057 | 0.02 | 10 | 69.5688 |
|
| 50 |
+
| 46.1297 | 0.04 | 20 | 32.9398 |
|
| 51 |
+
| 13.6236 | 0.06 | 30 | 10.6408 |
|
| 52 |
+
| 6.8926 | 0.08 | 40 | 4.2341 |
|
| 53 |
+
| 3.624 | 0.1 | 50 | 2.0277 |
|
| 54 |
+
| 1.4923 | 0.12 | 60 | 1.0828 |
|
| 55 |
+
| 1.1113 | 0.14 | 70 | 0.8631 |
|
| 56 |
+
| 1.0637 | 0.16 | 80 | 0.8401 |
|
| 57 |
+
| 0.8052 | 0.18 | 90 | 0.7114 |
|
| 58 |
+
| 0.8037 | 0.2 | 100 | 0.6471 |
|
| 59 |
+
| 0.6838 | 0.22 | 110 | 0.5986 |
|
| 60 |
+
| 0.6964 | 0.24 | 120 | 0.5857 |
|
| 61 |
+
| 0.7026 | 0.26 | 130 | 0.5939 |
|
| 62 |
+
| 0.7504 | 0.28 | 140 | 0.5821 |
|
| 63 |
+
| 0.6942 | 0.3 | 150 | 0.5732 |
|
| 64 |
+
| 0.6843 | 0.32 | 160 | 0.5735 |
|
| 65 |
+
| 0.5917 | 0.34 | 170 | 0.5641 |
|
| 66 |
+
| 0.7147 | 0.36 | 180 | 0.5679 |
|
| 67 |
+
| 0.7191 | 0.38 | 190 | 0.5727 |
|
| 68 |
+
| 0.6479 | 0.4 | 200 | 0.5622 |
|
| 69 |
+
| 0.7827 | 0.42 | 210 | 0.5531 |
|
| 70 |
+
| 0.7211 | 0.44 | 220 | 0.5480 |
|
| 71 |
+
| 0.6038 | 0.46 | 230 | 0.5514 |
|
| 72 |
+
| 0.6323 | 0.48 | 240 | 0.5456 |
|
| 73 |
+
| 0.6168 | 0.5 | 250 | 0.5470 |
|
| 74 |
+
| 0.6322 | 0.52 | 260 | 0.5515 |
|
| 75 |
+
| 0.6365 | 0.54 | 270 | 0.5492 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.29.0.dev0
|
| 81 |
+
- Pytorch 1.12.0a0+bd13bc6
|
| 82 |
+
- Datasets 2.12.0
|
| 83 |
+
- Tokenizers 0.13.3
|