minseo0820
commited on
Commit
•
3d14468
1
Parent(s):
d5f7c05
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- fairytale_qa
|
8 |
+
metrics:
|
9 |
+
- rouge
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: t5-small-finetuned-FairytaleQA-AnswerExtraction
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Sequence-to-sequence Language Modeling
|
16 |
+
type: text2text-generation
|
17 |
+
dataset:
|
18 |
+
name: fairytale_qa
|
19 |
+
type: fairytale_qa
|
20 |
+
config: default
|
21 |
+
split: validation
|
22 |
+
args: default
|
23 |
+
metrics:
|
24 |
+
- name: Rouge1
|
25 |
+
type: rouge
|
26 |
+
value: 10.7124
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.2626
|
30 |
+
---
|
31 |
+
|
32 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
33 |
+
should probably proofread and complete it, then remove this comment. -->
|
34 |
+
|
35 |
+
# t5-small-finetuned-FairytaleQA-AnswerExtraction
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the fairytale_qa dataset.
|
38 |
+
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.0695
|
40 |
+
- Rouge1: 10.7124
|
41 |
+
- Rouge2: 3.2292
|
42 |
+
- Rougel: 10.375
|
43 |
+
- Rougelsum: 10.3824
|
44 |
+
- F1: 0.2626
|
45 |
+
- Exact Match: 0.4878
|
46 |
+
- Gen Len: 11.9668
|
47 |
+
|
48 |
+
## Model description
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Intended uses & limitations
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Training and evaluation data
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training procedure
|
61 |
+
|
62 |
+
### Training hyperparameters
|
63 |
+
|
64 |
+
The following hyperparameters were used during training:
|
65 |
+
- learning_rate: 2e-05
|
66 |
+
- train_batch_size: 4
|
67 |
+
- eval_batch_size: 4
|
68 |
+
- seed: 42
|
69 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
70 |
+
- lr_scheduler_type: linear
|
71 |
+
- num_epochs: 5
|
72 |
+
- mixed_precision_training: Native AMP
|
73 |
+
|
74 |
+
### Training results
|
75 |
+
|
76 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | F1 | Exact Match | Gen Len |
|
77 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:------:|:-----------:|:-------:|
|
78 |
+
| 0.0777 | 1.0 | 2137 | 0.0727 | 11.076 | 3.0967 | 10.6128 | 10.6396 | 0.1301 | 0.3902 | 12.522 |
|
79 |
+
| 0.0727 | 2.0 | 4274 | 0.0707 | 11.288 | 3.2828 | 10.9125 | 10.9225 | 0.152 | 0.4878 | 12.161 |
|
80 |
+
| 0.0696 | 3.0 | 6411 | 0.0699 | 10.7512 | 3.3182 | 10.406 | 10.4123 | 0.2626 | 0.4878 | 12.1122 |
|
81 |
+
| 0.0719 | 4.0 | 8548 | 0.0696 | 10.803 | 3.2133 | 10.4337 | 10.4223 | 0.2626 | 0.4878 | 11.9698 |
|
82 |
+
| 0.07 | 5.0 | 10685 | 0.0695 | 10.7124 | 3.2292 | 10.375 | 10.3824 | 0.2626 | 0.4878 | 11.9668 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.42.4
|
88 |
+
- Pytorch 2.3.1+cu121
|
89 |
+
- Datasets 2.20.0
|
90 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.42.4"
|
6 |
+
}
|
runs/Aug12_03-56-44_05f3f4260baf/events.out.tfevents.1723435004.05f3f4260baf.369.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04becf6fa087e4e563d4abda4d4548f423f57fba77d9594318aefc3dd379a903
|
3 |
+
size 13822
|