update model card README.md
Browse files
README.md
CHANGED
@@ -5,14 +5,6 @@ tags:
|
|
5 |
model-index:
|
6 |
- name: flan-t5-end2end-question-generation
|
7 |
results: []
|
8 |
-
pipeline_tag: text2text-generation
|
9 |
-
inference:
|
10 |
-
parameters:
|
11 |
-
max_length: 256
|
12 |
-
num_beams: 4
|
13 |
-
length_penalty: 1.5
|
14 |
-
no_repeat_ngram_size: 3
|
15 |
-
early_stopping: True
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -20,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# flan-t5-end2end-question-generation
|
22 |
|
23 |
-
This model is a fine-tuned version of [
|
24 |
It achieves the following results on the evaluation set:
|
25 |
-
- Loss: 1.
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -49,37 +41,19 @@ The following hyperparameters were used during training:
|
|
49 |
- total_train_batch_size: 128
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
-
|
|
59 |
-
| 1.
|
60 |
-
| 1.8778 | 1.02 | 300 | 1.6817 |
|
61 |
-
| 1.8245 | 1.35 | 400 | 1.6455 |
|
62 |
-
| 1.7808 | 1.69 | 500 | 1.6298 |
|
63 |
-
| 1.754 | 2.03 | 600 | 1.6213 |
|
64 |
-
| 1.7226 | 2.37 | 700 | 1.6102 |
|
65 |
-
| 1.7078 | 2.71 | 800 | 1.5914 |
|
66 |
-
| 1.6953 | 3.05 | 900 | 1.5871 |
|
67 |
-
| 1.682 | 3.39 | 1000 | 1.5857 |
|
68 |
-
| 1.6593 | 3.73 | 1100 | 1.5742 |
|
69 |
-
| 1.6538 | 4.06 | 1200 | 1.5675 |
|
70 |
-
| 1.6417 | 4.4 | 1300 | 1.5682 |
|
71 |
-
| 1.6274 | 4.74 | 1400 | 1.5571 |
|
72 |
-
| 1.6375 | 5.08 | 1500 | 1.5566 |
|
73 |
-
| 1.6217 | 5.42 | 1600 | 1.5564 |
|
74 |
-
| 1.625 | 5.76 | 1700 | 1.5543 |
|
75 |
-
| 1.6055 | 6.1 | 1800 | 1.5517 |
|
76 |
-
| 1.6129 | 6.44 | 1900 | 1.5516 |
|
77 |
-
| 1.609 | 6.77 | 2000 | 1.5506 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
-
- Transformers 4.
|
83 |
-
- Pytorch
|
84 |
- Datasets 2.1.0
|
85 |
-
- Tokenizers 0.13.
|
|
|
5 |
model-index:
|
6 |
- name: flan-t5-end2end-question-generation
|
7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
12 |
|
13 |
# flan-t5-end2end-question-generation
|
14 |
|
15 |
+
This model is a fine-tuned version of [Michelvh/flan-t5-end2end-question-generation](https://huggingface.co/Michelvh/flan-t5-end2end-question-generation) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.5371
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
41 |
- total_train_batch_size: 128
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 1
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.5899 | 0.34 | 100 | 1.5440 |
|
51 |
+
| 1.5754 | 0.68 | 200 | 1.5371 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
+
- Transformers 4.30.0.dev0
|
57 |
+
- Pytorch 2.0.0
|
58 |
- Datasets 2.1.0
|
59 |
+
- Tokenizers 0.13.3
|