update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gpt2-NaturalQuestions_2000-ep20
|
| 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-NaturalQuestions_2000-ep20
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.3117
|
| 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: 48
|
| 38 |
+
- eval_batch_size: 96
|
| 39 |
+
- seed: 1799
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 1.77 | 1.19 | 50 | 1.3795 |
|
| 49 |
+
| 1.3768 | 2.38 | 100 | 1.3164 |
|
| 50 |
+
| 1.2208 | 3.57 | 150 | 1.2818 |
|
| 51 |
+
| 1.1183 | 4.76 | 200 | 1.2704 |
|
| 52 |
+
| 1.0477 | 5.95 | 250 | 1.2626 |
|
| 53 |
+
| 0.9721 | 7.14 | 300 | 1.2632 |
|
| 54 |
+
| 0.914 | 8.33 | 350 | 1.2670 |
|
| 55 |
+
| 0.8714 | 9.52 | 400 | 1.2714 |
|
| 56 |
+
| 0.835 | 10.71 | 450 | 1.2737 |
|
| 57 |
+
| 0.7959 | 11.9 | 500 | 1.2799 |
|
| 58 |
+
| 0.7513 | 13.1 | 550 | 1.2892 |
|
| 59 |
+
| 0.7323 | 14.29 | 600 | 1.2951 |
|
| 60 |
+
| 0.7097 | 15.48 | 650 | 1.3033 |
|
| 61 |
+
| 0.6948 | 16.67 | 700 | 1.3060 |
|
| 62 |
+
| 0.6764 | 17.86 | 750 | 1.3094 |
|
| 63 |
+
| 0.6655 | 19.05 | 800 | 1.3115 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.29.2
|
| 69 |
+
- Pytorch 1.10.0+cu111
|
| 70 |
+
- Datasets 2.5.1
|
| 71 |
+
- Tokenizers 0.13.3
|