ubaada/long-t5-tglobal-base-booksum
Browse files- README.md +7 -5
- model.safetensors +1 -1
- tokenizer.json +2 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Rouge1: 0.
|
22 |
-
- Rouge2: 0.
|
23 |
-
- Rougel: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -50,13 +50,15 @@ The following hyperparameters were used during training:
|
|
50 |
- total_eval_batch_size: 2
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
-
- num_epochs:
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
58 |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
59 |
| 1.5731 | 0.9996 | 600 | 1.9730 | 0.1342 | 0.0151 | 0.0912 |
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.9565
|
21 |
+
- Rouge1: 0.1423
|
22 |
+
- Rouge2: 0.0178
|
23 |
+
- Rougel: 0.0928
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
- total_eval_batch_size: 2
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 3
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
58 |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
59 |
| 1.5731 | 0.9996 | 600 | 1.9730 | 0.1342 | 0.0151 | 0.0912 |
|
60 |
+
| 1.3694 | 1.9996 | 1200 | 1.9623 | 0.1371 | 0.0175 | 0.0909 |
|
61 |
+
| 1.9561 | 2.9992 | 1800 | 1.9565 | 0.1423 | 0.0178 | 0.0928 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990386200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84f21eff3ce6deda24ca6e879a245eb12d871429288d8890407f15c1c1bb1a82
|
3 |
size 990386200
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 1024
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:296154d90ec6ea346feed2cef6a2e1a56591d88c5f82648a51e3b732668f6e6b
|
3 |
size 6776
|