Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,75 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: ds9_all
|
| 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 |
+
# ds9_all
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.4600
|
| 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: 1.372e-07
|
| 37 |
+
- train_batch_size: 1
|
| 38 |
+
- eval_batch_size: 1
|
| 39 |
+
- seed: 1523398255
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_steps: 10
|
| 43 |
+
- num_epochs: 30
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 1.1261 | 13.0 | 8619 | 3.4600 |
|
| 51 |
+
| 1.141 | 14.0 | 9282 | 3.4634 |
|
| 52 |
+
| 1.1278 | 15.0 | 9945 | 3.4665 |
|
| 53 |
+
| 1.1183 | 16.0 | 10608 | 3.4697 |
|
| 54 |
+
| 1.1048 | 17.0 | 11271 | 3.4714 |
|
| 55 |
+
| 1.1061 | 18.0 | 11934 | 3.4752 |
|
| 56 |
+
| 1.1471 | 19.0 | 12597 | 3.4773 |
|
| 57 |
+
| 1.1402 | 20.0 | 13260 | 3.4798 |
|
| 58 |
+
| 1.0847 | 21.0 | 13923 | 3.4811 |
|
| 59 |
+
| 1.1462 | 22.0 | 14586 | 3.4841 |
|
| 60 |
+
| 1.1107 | 23.0 | 15249 | 3.4852 |
|
| 61 |
+
| 1.1192 | 24.0 | 15912 | 3.4873 |
|
| 62 |
+
| 1.0868 | 25.0 | 16575 | 3.4879 |
|
| 63 |
+
| 1.1313 | 26.0 | 17238 | 3.4898 |
|
| 64 |
+
| 1.1033 | 27.0 | 17901 | 3.4915 |
|
| 65 |
+
| 1.1578 | 28.0 | 18564 | 3.4939 |
|
| 66 |
+
| 1.0987 | 29.0 | 19227 | 3.4947 |
|
| 67 |
+
| 1.0779 | 30.0 | 19890 | 3.4972 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.13.0.dev0
|
| 73 |
+
- Pytorch 1.10.0+cu113
|
| 74 |
+
- Datasets 1.15.1
|
| 75 |
+
- Tokenizers 0.10.3
|