update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: distilbert-base-uncased__sst2__train-16-1
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# distilbert-base-uncased__sst2__train-16-1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6012
|
| 20 |
+
- Accuracy: 0.6766
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 4
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 50
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.6983 | 1.0 | 7 | 0.7036 | 0.2857 |
|
| 53 |
+
| 0.6836 | 2.0 | 14 | 0.7181 | 0.2857 |
|
| 54 |
+
| 0.645 | 3.0 | 21 | 0.7381 | 0.2857 |
|
| 55 |
+
| 0.5902 | 4.0 | 28 | 0.7746 | 0.2857 |
|
| 56 |
+
| 0.5799 | 5.0 | 35 | 0.7242 | 0.5714 |
|
| 57 |
+
| 0.3584 | 6.0 | 42 | 0.6935 | 0.5714 |
|
| 58 |
+
| 0.2596 | 7.0 | 49 | 0.7041 | 0.5714 |
|
| 59 |
+
| 0.1815 | 8.0 | 56 | 0.5930 | 0.7143 |
|
| 60 |
+
| 0.0827 | 9.0 | 63 | 0.6976 | 0.7143 |
|
| 61 |
+
| 0.0613 | 10.0 | 70 | 0.7346 | 0.7143 |
|
| 62 |
+
| 0.0356 | 11.0 | 77 | 0.6992 | 0.5714 |
|
| 63 |
+
| 0.0158 | 12.0 | 84 | 0.7328 | 0.5714 |
|
| 64 |
+
| 0.013 | 13.0 | 91 | 0.7819 | 0.5714 |
|
| 65 |
+
| 0.0103 | 14.0 | 98 | 0.8589 | 0.5714 |
|
| 66 |
+
| 0.0087 | 15.0 | 105 | 0.9177 | 0.5714 |
|
| 67 |
+
| 0.0076 | 16.0 | 112 | 0.9519 | 0.5714 |
|
| 68 |
+
| 0.0078 | 17.0 | 119 | 0.9556 | 0.5714 |
|
| 69 |
+
| 0.006 | 18.0 | 126 | 0.9542 | 0.5714 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.15.0
|
| 75 |
+
- Pytorch 1.10.2+cu102
|
| 76 |
+
- Datasets 1.18.2
|
| 77 |
+
- Tokenizers 0.10.3
|