Commit
•
ade0a56
1
Parent(s):
57dbdbd
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 |
+
model-index:
|
| 6 |
+
- name: taylor-swift-model-paragraphs
|
| 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 |
+
# taylor-swift-model-paragraphs
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.3564
|
| 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: 2e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 25
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 3.9316 | 1.0 | 59 | 3.8227 |
|
| 49 |
+
| 3.824 | 2.0 | 118 | 3.7301 |
|
| 50 |
+
| 3.5808 | 3.0 | 177 | 3.6658 |
|
| 51 |
+
| 3.625 | 4.0 | 236 | 3.6205 |
|
| 52 |
+
| 3.643 | 5.0 | 295 | 3.5862 |
|
| 53 |
+
| 3.5443 | 6.0 | 354 | 3.5545 |
|
| 54 |
+
| 3.4535 | 7.0 | 413 | 3.5274 |
|
| 55 |
+
| 3.398 | 8.0 | 472 | 3.5072 |
|
| 56 |
+
| 3.3253 | 9.0 | 531 | 3.4833 |
|
| 57 |
+
| 3.4111 | 10.0 | 590 | 3.4688 |
|
| 58 |
+
| 3.3461 | 11.0 | 649 | 3.4503 |
|
| 59 |
+
| 3.3133 | 12.0 | 708 | 3.4373 |
|
| 60 |
+
| 3.3921 | 13.0 | 767 | 3.4246 |
|
| 61 |
+
| 3.2661 | 14.0 | 826 | 3.4102 |
|
| 62 |
+
| 3.2257 | 15.0 | 885 | 3.4052 |
|
| 63 |
+
| 3.1837 | 16.0 | 944 | 3.3911 |
|
| 64 |
+
| 3.1935 | 17.0 | 1003 | 3.3849 |
|
| 65 |
+
| 2.9369 | 18.0 | 1062 | 3.3774 |
|
| 66 |
+
| 3.2486 | 19.0 | 1121 | 3.3721 |
|
| 67 |
+
| 3.1542 | 20.0 | 1180 | 3.3681 |
|
| 68 |
+
| 3.0771 | 21.0 | 1239 | 3.3624 |
|
| 69 |
+
| 3.1206 | 22.0 | 1298 | 3.3581 |
|
| 70 |
+
| 3.0358 | 23.0 | 1357 | 3.3585 |
|
| 71 |
+
| 2.9207 | 24.0 | 1416 | 3.3568 |
|
| 72 |
+
| 3.0496 | 25.0 | 1475 | 3.3564 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.25.1
|
| 78 |
+
- Pytorch 1.13.0+cu116
|
| 79 |
+
- Datasets 2.8.0
|
| 80 |
+
- Tokenizers 0.13.2
|