update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: ViTGPT2I2A
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# ViTGPT2I2A
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0715
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 2
|
| 37 |
+
- eval_batch_size: 2
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 2
|
| 41 |
+
- total_train_batch_size: 4
|
| 42 |
+
- total_eval_batch_size: 4
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 5.0
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 52 |
+
| 0.1528 | 0.17 | 1000 | 0.0869 |
|
| 53 |
+
| 0.0899 | 0.34 | 2000 | 0.0817 |
|
| 54 |
+
| 0.084 | 0.51 | 3000 | 0.0790 |
|
| 55 |
+
| 0.0814 | 0.68 | 4000 | 0.0773 |
|
| 56 |
+
| 0.0803 | 0.85 | 5000 | 0.0757 |
|
| 57 |
+
| 0.077 | 1.02 | 6000 | 0.0745 |
|
| 58 |
+
| 0.0739 | 1.19 | 7000 | 0.0740 |
|
| 59 |
+
| 0.0719 | 1.37 | 8000 | 0.0737 |
|
| 60 |
+
| 0.0717 | 1.54 | 9000 | 0.0730 |
|
| 61 |
+
| 0.0731 | 1.71 | 10000 | 0.0727 |
|
| 62 |
+
| 0.0708 | 1.88 | 11000 | 0.0720 |
|
| 63 |
+
| 0.0697 | 2.05 | 12000 | 0.0717 |
|
| 64 |
+
| 0.0655 | 2.22 | 13000 | 0.0719 |
|
| 65 |
+
| 0.0653 | 2.39 | 14000 | 0.0719 |
|
| 66 |
+
| 0.0657 | 2.56 | 15000 | 0.0712 |
|
| 67 |
+
| 0.0663 | 2.73 | 16000 | 0.0710 |
|
| 68 |
+
| 0.0654 | 2.9 | 17000 | 0.0708 |
|
| 69 |
+
| 0.0645 | 3.07 | 18000 | 0.0716 |
|
| 70 |
+
| 0.0616 | 3.24 | 19000 | 0.0712 |
|
| 71 |
+
| 0.0607 | 3.41 | 20000 | 0.0712 |
|
| 72 |
+
| 0.0611 | 3.58 | 21000 | 0.0711 |
|
| 73 |
+
| 0.0615 | 3.76 | 22000 | 0.0711 |
|
| 74 |
+
| 0.0614 | 3.93 | 23000 | 0.0710 |
|
| 75 |
+
| 0.0594 | 4.1 | 24000 | 0.0716 |
|
| 76 |
+
| 0.0587 | 4.27 | 25000 | 0.0715 |
|
| 77 |
+
| 0.0574 | 4.44 | 26000 | 0.0715 |
|
| 78 |
+
| 0.0579 | 4.61 | 27000 | 0.0715 |
|
| 79 |
+
| 0.0581 | 4.78 | 28000 | 0.0715 |
|
| 80 |
+
| 0.0579 | 4.95 | 29000 | 0.0715 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.16.2
|
| 86 |
+
- Pytorch 1.10.2+cu113
|
| 87 |
+
- Datasets 1.18.3
|
| 88 |
+
- Tokenizers 0.11.0
|