Update README.md
Browse files
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
- summarization
|
|
|
5 |
dataset:
|
6 |
- kmfoda/booksum
|
7 |
metrics:
|
@@ -11,11 +12,10 @@ model-index:
|
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
-
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
# tglobal-large-booksum-WIP
|
18 |
|
|
|
19 |
This model is a fine-tuned version of [google/long-t5-tglobal-large](https://huggingface.co/google/long-t5-tglobal-large) on the `kmfoda/booksum` dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 4.9519
|
@@ -27,16 +27,15 @@ It achieves the following results on the evaluation set:
|
|
27 |
|
28 |
## Model description
|
29 |
|
30 |
-
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
34 |
-
|
35 |
|
36 |
## Training and evaluation data
|
37 |
|
38 |
-
|
39 |
-
|
40 |
## Training procedure
|
41 |
|
42 |
### Training hyperparameters
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
- summarization
|
5 |
+
- book summary
|
6 |
dataset:
|
7 |
- kmfoda/booksum
|
8 |
metrics:
|
|
|
12 |
results: []
|
13 |
---
|
14 |
|
|
|
|
|
15 |
|
16 |
# tglobal-large-booksum-WIP
|
17 |
|
18 |
+
> this is a WIP checkpoint that has been fine-tuned from the vanilla (original) for 10ish epochs. It is **not ready to be used for inference**
|
19 |
This model is a fine-tuned version of [google/long-t5-tglobal-large](https://huggingface.co/google/long-t5-tglobal-large) on the `kmfoda/booksum` dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 4.9519
|
|
|
27 |
|
28 |
## Model description
|
29 |
|
30 |
+
Testing fine-tuning only on booksum with 16384/1024 the whole time (vs. previous large WIP checkpoint I made that started from a partially-trained `pubmed` checkpoint)
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
34 |
+
this is a WIP checkpoint that has been fine-tuned from the vanilla (original) for 10ish epochs. It is **not ready to be used for inference**
|
35 |
|
36 |
## Training and evaluation data
|
37 |
|
38 |
+
This is **only** fine-tuned on booksum (vs. previous large WIP checkpoint I made that started from a partially-trained `pubmed` checkpoint)
|
|
|
39 |
## Training procedure
|
40 |
|
41 |
### Training hyperparameters
|