update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: recipe-distilroberta-Is
|
| 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-distilroberta-Is
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 4.7427
|
| 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: 128
|
| 38 |
+
- eval_batch_size: 128
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 25
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 19.6191 | 1.0 | 2135 | 10.5217 |
|
| 50 |
+
| 8.6838 | 2.0 | 4270 | 7.3017 |
|
| 51 |
+
| 6.884 | 3.0 | 6405 | 6.4445 |
|
| 52 |
+
| 6.2953 | 4.0 | 8540 | 6.0610 |
|
| 53 |
+
| 6.0205 | 5.0 | 10675 | 5.9047 |
|
| 54 |
+
| 5.851 | 6.0 | 12810 | 5.7790 |
|
| 55 |
+
| 5.7464 | 7.0 | 14945 | 5.7164 |
|
| 56 |
+
| 5.6684 | 8.0 | 17080 | 5.6415 |
|
| 57 |
+
| 5.6138 | 9.0 | 19215 | 5.5671 |
|
| 58 |
+
| 5.5638 | 10.0 | 21350 | 5.5360 |
|
| 59 |
+
| 5.5288 | 11.0 | 23485 | 5.5069 |
|
| 60 |
+
| 5.4968 | 12.0 | 25620 | 5.4968 |
|
| 61 |
+
| 5.4696 | 13.0 | 27755 | 5.4539 |
|
| 62 |
+
| 5.4468 | 14.0 | 29890 | 5.4416 |
|
| 63 |
+
| 5.4177 | 15.0 | 32025 | 5.3722 |
|
| 64 |
+
| 5.3717 | 16.0 | 34160 | 5.3226 |
|
| 65 |
+
| 5.317 | 17.0 | 36295 | 5.2197 |
|
| 66 |
+
| 5.2367 | 18.0 | 38430 | 5.0888 |
|
| 67 |
+
| 5.1543 | 19.0 | 40565 | 4.9954 |
|
| 68 |
+
| 5.0919 | 20.0 | 42700 | 4.9306 |
|
| 69 |
+
| 5.038 | 21.0 | 44835 | 4.8657 |
|
| 70 |
+
| 4.9983 | 22.0 | 46970 | 4.8137 |
|
| 71 |
+
| 4.9639 | 23.0 | 49105 | 4.7704 |
|
| 72 |
+
| 4.9426 | 24.0 | 51240 | 4.7486 |
|
| 73 |
+
| 4.9312 | 25.0 | 53375 | 4.7427 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.19.0.dev0
|
| 79 |
+
- Pytorch 1.9.0+cu111
|
| 80 |
+
- Datasets 2.4.0
|
| 81 |
+
- Tokenizers 0.12.1
|