Commit
•
bacb1d4
1
Parent(s):
f4fe554
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: t5-end2end-questions-generation_2
|
| 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-end2end-questions-generation_2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.6223
|
| 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: 1
|
| 38 |
+
- eval_batch_size: 1
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 4
|
| 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 |
+
| 2.7103 | 0.13 | 10 | 1.7584 |
|
| 51 |
+
| 1.8298 | 0.26 | 20 | 1.3377 |
|
| 52 |
+
| 1.4424 | 0.39 | 30 | 1.1610 |
|
| 53 |
+
| 1.4063 | 0.52 | 40 | 1.0564 |
|
| 54 |
+
| 1.2738 | 0.65 | 50 | 1.0332 |
|
| 55 |
+
| 1.2477 | 0.78 | 60 | 0.9531 |
|
| 56 |
+
| 1.146 | 0.91 | 70 | 0.9050 |
|
| 57 |
+
| 1.0134 | 1.04 | 80 | 0.9388 |
|
| 58 |
+
| 0.8782 | 1.17 | 90 | 0.9215 |
|
| 59 |
+
| 0.8869 | 1.3 | 100 | 0.8930 |
|
| 60 |
+
| 0.8963 | 1.43 | 110 | 0.8996 |
|
| 61 |
+
| 0.9138 | 1.56 | 120 | 0.8616 |
|
| 62 |
+
| 0.7963 | 1.69 | 130 | 0.8060 |
|
| 63 |
+
| 0.8611 | 1.82 | 140 | 0.7611 |
|
| 64 |
+
| 1.0504 | 1.95 | 150 | 0.7606 |
|
| 65 |
+
| 0.6802 | 2.08 | 160 | 0.7791 |
|
| 66 |
+
| 0.7488 | 2.21 | 170 | 0.7470 |
|
| 67 |
+
| 0.6659 | 2.34 | 180 | 0.7367 |
|
| 68 |
+
| 0.7061 | 2.47 | 190 | 0.7194 |
|
| 69 |
+
| 0.6771 | 2.6 | 200 | 0.7006 |
|
| 70 |
+
| 0.7267 | 2.73 | 210 | 0.6858 |
|
| 71 |
+
| 0.7251 | 2.86 | 220 | 0.6797 |
|
| 72 |
+
| 0.7426 | 2.99 | 230 | 0.6877 |
|
| 73 |
+
| 0.5425 | 3.12 | 240 | 0.6994 |
|
| 74 |
+
| 0.5298 | 3.25 | 250 | 0.7096 |
|
| 75 |
+
| 0.697 | 3.38 | 260 | 0.6941 |
|
| 76 |
+
| 0.5643 | 3.51 | 270 | 0.6534 |
|
| 77 |
+
| 0.6983 | 3.64 | 280 | 0.6407 |
|
| 78 |
+
| 0.587 | 3.77 | 290 | 0.6404 |
|
| 79 |
+
| 0.6487 | 3.9 | 300 | 0.6489 |
|
| 80 |
+
| 0.5862 | 4.03 | 310 | 0.6567 |
|
| 81 |
+
| 0.5524 | 4.16 | 320 | 0.6610 |
|
| 82 |
+
| 0.5432 | 4.29 | 330 | 0.6609 |
|
| 83 |
+
| 0.5165 | 4.42 | 340 | 0.6558 |
|
| 84 |
+
| 0.5248 | 4.55 | 350 | 0.6387 |
|
| 85 |
+
| 0.5322 | 4.68 | 360 | 0.6319 |
|
| 86 |
+
| 0.5272 | 4.81 | 370 | 0.6214 |
|
| 87 |
+
| 0.5555 | 4.94 | 380 | 0.6252 |
|
| 88 |
+
| 0.597 | 5.06 | 390 | 0.6281 |
|
| 89 |
+
| 0.5745 | 5.19 | 400 | 0.6283 |
|
| 90 |
+
| 0.5156 | 5.32 | 410 | 0.6265 |
|
| 91 |
+
| 0.4898 | 5.45 | 420 | 0.6307 |
|
| 92 |
+
| 0.543 | 5.58 | 430 | 0.6280 |
|
| 93 |
+
| 0.5094 | 5.71 | 440 | 0.6295 |
|
| 94 |
+
| 0.5023 | 5.84 | 450 | 0.6279 |
|
| 95 |
+
| 0.4483 | 5.97 | 460 | 0.6228 |
|
| 96 |
+
| 0.5134 | 6.1 | 470 | 0.6239 |
|
| 97 |
+
| 0.5054 | 6.23 | 480 | 0.6230 |
|
| 98 |
+
| 0.4632 | 6.36 | 490 | 0.6205 |
|
| 99 |
+
| 0.5016 | 6.49 | 500 | 0.6212 |
|
| 100 |
+
| 0.4838 | 6.62 | 510 | 0.6219 |
|
| 101 |
+
| 0.4613 | 6.75 | 520 | 0.6225 |
|
| 102 |
+
| 0.5062 | 6.88 | 530 | 0.6223 |
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
### Framework versions
|
| 106 |
+
|
| 107 |
+
- Transformers 4.28.1
|
| 108 |
+
- Pytorch 2.0.1+cu117
|
| 109 |
+
- Datasets 2.12.0
|
| 110 |
+
- Tokenizers 0.13.3
|