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-tis
|
| 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-tis
|
| 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: 0.9886
|
| 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 |
+
| 1.8792 | 1.0 | 1038 | 1.4680 |
|
| 50 |
+
| 1.4691 | 2.0 | 2076 | 1.3122 |
|
| 51 |
+
| 1.3471 | 3.0 | 3114 | 1.2343 |
|
| 52 |
+
| 1.2798 | 4.0 | 4152 | 1.1829 |
|
| 53 |
+
| 1.2284 | 5.0 | 5190 | 1.1437 |
|
| 54 |
+
| 1.1956 | 6.0 | 6228 | 1.1120 |
|
| 55 |
+
| 1.1683 | 7.0 | 7266 | 1.0905 |
|
| 56 |
+
| 1.1458 | 8.0 | 8304 | 1.0731 |
|
| 57 |
+
| 1.126 | 9.0 | 9342 | 1.0645 |
|
| 58 |
+
| 1.113 | 10.0 | 10380 | 1.0471 |
|
| 59 |
+
| 1.0962 | 11.0 | 11418 | 1.0348 |
|
| 60 |
+
| 1.0864 | 12.0 | 12456 | 1.0256 |
|
| 61 |
+
| 1.0772 | 13.0 | 13494 | 1.0173 |
|
| 62 |
+
| 1.0692 | 14.0 | 14532 | 1.0130 |
|
| 63 |
+
| 1.0622 | 15.0 | 15570 | 1.0111 |
|
| 64 |
+
| 1.0577 | 16.0 | 16608 | 1.0021 |
|
| 65 |
+
| 1.0537 | 17.0 | 17646 | 1.0001 |
|
| 66 |
+
| 1.0474 | 18.0 | 18684 | 0.9928 |
|
| 67 |
+
| 1.0471 | 19.0 | 19722 | 0.9908 |
|
| 68 |
+
| 1.0458 | 20.0 | 20760 | 0.9886 |
|
| 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
|