update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: paraphraser-german-mt5-small
|
| 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 |
+
# paraphraser-german-mt5-small
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.7678
|
| 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: 10
|
| 38 |
+
- eval_batch_size: 10
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 1
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 3.7064 | 0.05 | 2000 | 2.0731 |
|
| 49 |
+
| 2.8673 | 0.11 | 4000 | 2.0420 |
|
| 50 |
+
| 2.6133 | 0.16 | 6000 | 2.0080 |
|
| 51 |
+
| 2.4563 | 0.21 | 8000 | 1.9556 |
|
| 52 |
+
| 2.385 | 0.27 | 10000 | 1.9090 |
|
| 53 |
+
| 2.3122 | 0.32 | 12000 | 1.9127 |
|
| 54 |
+
| 2.2775 | 0.38 | 14000 | 1.8658 |
|
| 55 |
+
| 2.2323 | 0.43 | 16000 | 1.8407 |
|
| 56 |
+
| 2.17 | 0.48 | 18000 | 1.8342 |
|
| 57 |
+
| 2.1672 | 0.54 | 20000 | 1.8328 |
|
| 58 |
+
| 2.1488 | 0.59 | 22000 | 1.8071 |
|
| 59 |
+
| 2.1026 | 0.64 | 24000 | 1.8328 |
|
| 60 |
+
| 2.1036 | 0.7 | 26000 | 1.7979 |
|
| 61 |
+
| 2.0854 | 0.75 | 28000 | 1.7895 |
|
| 62 |
+
| 2.0594 | 0.81 | 30000 | 1.7944 |
|
| 63 |
+
| 2.0793 | 0.86 | 32000 | 1.7726 |
|
| 64 |
+
| 2.0661 | 0.91 | 34000 | 1.7762 |
|
| 65 |
+
| 2.0722 | 0.97 | 36000 | 1.7714 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.26.0
|
| 71 |
+
- Pytorch 1.13.1+cu116
|
| 72 |
+
- Datasets 2.9.0
|
| 73 |
+
- Tokenizers 0.13.2
|