update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: recipe-distilbert-i
|
| 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 |
+
# recipe-distilbert-i
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.0288
|
| 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: 256
|
| 38 |
+
- eval_batch_size: 256
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 2.3931 | 1.0 | 152 | 1.7738 |
|
| 50 |
+
| 1.7533 | 2.0 | 304 | 1.5109 |
|
| 51 |
+
| 1.5584 | 3.0 | 456 | 1.4003 |
|
| 52 |
+
| 1.443 | 4.0 | 608 | 1.3296 |
|
| 53 |
+
| 1.3551 | 5.0 | 760 | 1.2270 |
|
| 54 |
+
| 1.2981 | 6.0 | 912 | 1.1870 |
|
| 55 |
+
| 1.2577 | 7.0 | 1064 | 1.1511 |
|
| 56 |
+
| 1.2216 | 8.0 | 1216 | 1.1298 |
|
| 57 |
+
| 1.1958 | 9.0 | 1368 | 1.1087 |
|
| 58 |
+
| 1.1685 | 10.0 | 1520 | 1.0858 |
|
| 59 |
+
| 1.1533 | 11.0 | 1672 | 1.0820 |
|
| 60 |
+
| 1.1358 | 12.0 | 1824 | 1.0659 |
|
| 61 |
+
| 1.1286 | 13.0 | 1976 | 1.0382 |
|
| 62 |
+
| 1.1128 | 14.0 | 2128 | 1.0468 |
|
| 63 |
+
| 1.11 | 15.0 | 2280 | 1.0399 |
|
| 64 |
+
| 1.094 | 16.0 | 2432 | 1.0382 |
|
| 65 |
+
| 1.0969 | 17.0 | 2584 | 1.0096 |
|
| 66 |
+
| 1.0868 | 18.0 | 2736 | 1.0235 |
|
| 67 |
+
| 1.0845 | 19.0 | 2888 | 1.0227 |
|
| 68 |
+
| 1.0855 | 20.0 | 3040 | 1.0288 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.19.0.dev0
|
| 74 |
+
- Pytorch 1.11.0+cu102
|
| 75 |
+
- Datasets 2.3.2
|
| 76 |
+
- Tokenizers 0.12.1
|