Commit
·
f806ff2
1
Parent(s):
b3527d3
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: masked-sentence-generation
|
| 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 |
+
# masked-sentence-generation
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.8396
|
| 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: 0.0001
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 16
|
| 41 |
+
- total_train_batch_size: 64
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 7
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 3.1508 | 0.32 | 100 | 2.8654 |
|
| 51 |
+
| 3.0787 | 0.64 | 200 | 2.8532 |
|
| 52 |
+
| 3.0573 | 0.96 | 300 | 2.8440 |
|
| 53 |
+
| 2.984 | 1.28 | 400 | 2.8398 |
|
| 54 |
+
| 2.9727 | 1.6 | 500 | 2.8364 |
|
| 55 |
+
| 2.9781 | 1.92 | 600 | 2.8336 |
|
| 56 |
+
| 2.9238 | 2.24 | 700 | 2.8346 |
|
| 57 |
+
| 2.8974 | 2.56 | 800 | 2.8334 |
|
| 58 |
+
| 2.894 | 2.88 | 900 | 2.8312 |
|
| 59 |
+
| 2.8716 | 3.2 | 1000 | 2.8348 |
|
| 60 |
+
| 2.8447 | 3.52 | 1100 | 2.8332 |
|
| 61 |
+
| 2.8467 | 3.84 | 1200 | 2.8332 |
|
| 62 |
+
| 2.8128 | 4.16 | 1300 | 2.8357 |
|
| 63 |
+
| 2.8007 | 4.48 | 1400 | 2.8362 |
|
| 64 |
+
| 2.8071 | 4.8 | 1500 | 2.8367 |
|
| 65 |
+
| 2.796 | 5.12 | 1600 | 2.8380 |
|
| 66 |
+
| 2.7628 | 5.44 | 1700 | 2.8387 |
|
| 67 |
+
| 2.7694 | 5.76 | 1800 | 2.8378 |
|
| 68 |
+
| 2.7734 | 6.08 | 1900 | 2.8384 |
|
| 69 |
+
| 2.7473 | 6.4 | 2000 | 2.8403 |
|
| 70 |
+
| 2.758 | 6.72 | 2100 | 2.8396 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.28.1
|
| 76 |
+
- Pytorch 2.0.0
|
| 77 |
+
- Datasets 2.12.0
|
| 78 |
+
- Tokenizers 0.11.0
|