update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- bleu
|
| 6 |
+
model-index:
|
| 7 |
+
- name: t5-small-ENG2BASH-NL2BASH
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# t5-small-ENG2BASH-NL2BASH
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.9071
|
| 19 |
+
- Bleu: 22.5899
|
| 20 |
+
- Gen Len: 16.6106
|
| 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: 0.0002
|
| 40 |
+
- train_batch_size: 5
|
| 41 |
+
- eval_batch_size: 5
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 52 |
+
| 1.5303 | 1.0 | 2017 | 1.3430 | 16.1379 | 16.8501 |
|
| 53 |
+
| 1.284 | 2.0 | 4034 | 1.1602 | 18.2161 | 16.6542 |
|
| 54 |
+
| 1.1289 | 3.0 | 6051 | 1.0617 | 19.8231 | 16.563 |
|
| 55 |
+
| 1.0573 | 4.0 | 8068 | 1.0064 | 20.1614 | 16.429 |
|
| 56 |
+
| 0.9723 | 5.0 | 10085 | 0.9780 | 21.3802 | 16.4393 |
|
| 57 |
+
| 0.915 | 6.0 | 12102 | 0.9451 | 21.3512 | 16.7304 |
|
| 58 |
+
| 0.8774 | 7.0 | 14119 | 0.9272 | 22.102 | 16.6178 |
|
| 59 |
+
| 0.8411 | 8.0 | 16136 | 0.9133 | 22.4544 | 16.7407 |
|
| 60 |
+
| 0.7958 | 9.0 | 18153 | 0.9095 | 22.5116 | 16.5726 |
|
| 61 |
+
| 0.7943 | 10.0 | 20170 | 0.9071 | 22.5899 | 16.6106 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.27.0.dev0
|
| 67 |
+
- Pytorch 1.13.1
|
| 68 |
+
- Datasets 2.9.0
|
| 69 |
+
- Tokenizers 0.13.2
|