update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: t5-small-mlm-pubmed-45
|
| 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 |
+
# t5-small-mlm-pubmed-45
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.6395
|
| 18 |
+
- Rouge2 Precision: 0.3383
|
| 19 |
+
- Rouge2 Recall: 0.2424
|
| 20 |
+
- Rouge2 Fmeasure: 0.2753
|
| 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: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 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 | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
| 52 |
+
| 2.519 | 0.75 | 500 | 1.9659 | 0.3178 | 0.1888 | 0.2299 |
|
| 53 |
+
| 2.169 | 1.51 | 1000 | 1.8450 | 0.3256 | 0.2138 | 0.25 |
|
| 54 |
+
| 2.0796 | 2.26 | 1500 | 1.7900 | 0.3368 | 0.2265 | 0.2636 |
|
| 55 |
+
| 1.9978 | 3.02 | 2000 | 1.7553 | 0.3427 | 0.234 | 0.2709 |
|
| 56 |
+
| 1.9686 | 3.77 | 2500 | 1.7172 | 0.3356 | 0.2347 | 0.2692 |
|
| 57 |
+
| 1.9142 | 4.52 | 3000 | 1.6986 | 0.3358 | 0.238 | 0.2715 |
|
| 58 |
+
| 1.921 | 5.28 | 3500 | 1.6770 | 0.3349 | 0.2379 | 0.2709 |
|
| 59 |
+
| 1.8848 | 6.03 | 4000 | 1.6683 | 0.3346 | 0.2379 | 0.2708 |
|
| 60 |
+
| 1.8674 | 6.79 | 4500 | 1.6606 | 0.3388 | 0.2419 | 0.2752 |
|
| 61 |
+
| 1.8606 | 7.54 | 5000 | 1.6514 | 0.3379 | 0.2409 | 0.274 |
|
| 62 |
+
| 1.8515 | 8.3 | 5500 | 1.6438 | 0.3356 | 0.2407 | 0.2731 |
|
| 63 |
+
| 1.8403 | 9.05 | 6000 | 1.6401 | 0.3367 | 0.2421 | 0.2744 |
|
| 64 |
+
| 1.8411 | 9.8 | 6500 | 1.6395 | 0.3383 | 0.2424 | 0.2753 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.12.5
|
| 70 |
+
- Pytorch 1.10.0+cu111
|
| 71 |
+
- Datasets 1.15.1
|
| 72 |
+
- Tokenizers 0.10.3
|