Alfahluzi/bert2bert-dropout-0.3-lr-5e-05-ds-canonical add 5 more epoch (total 5)
Browse files- README.md +17 -10
- generation_config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -13,7 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# bert2bert-dropout-0.3-lr-5e-05-ds-canonical
|
15 |
|
16 |
-
This model
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -33,24 +38,26 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
-
- num_epochs:
|
42 |
- mixed_precision_training: Native AMP
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
-
| Training Loss | Epoch | Step
|
47 |
-
|
48 |
-
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
-
- Transformers 4.
|
54 |
-
- Pytorch 2.1.
|
55 |
- Datasets 2.16.1
|
56 |
-
- Tokenizers 0.15.
|
|
|
13 |
|
14 |
# bert2bert-dropout-0.3-lr-5e-05-ds-canonical
|
15 |
|
16 |
+
This model was trained from scratch on the id_liputan6 dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.3368
|
19 |
+
- Rouge2 Precision: 0.1701
|
20 |
+
- Rouge2 Recall: 0.181
|
21 |
+
- Rouge2 Fmeasure: 0.1731
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 48
|
42 |
+
- eval_batch_size: 48
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 3
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
53 |
+
| 2.8387 | 1.0 | 4040 | 2.6668 | 0.1434 | 0.1495 | 0.1445 |
|
54 |
+
| 2.0882 | 2.0 | 8080 | 2.3950 | 0.174 | 0.1756 | 0.1725 |
|
55 |
+
| 1.8985 | 3.0 | 12120 | 2.3368 | 0.1701 | 0.181 | 0.1731 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
+
- Transformers 4.37.0
|
61 |
+
- Pytorch 2.1.2
|
62 |
- Datasets 2.16.1
|
63 |
+
- Tokenizers 0.15.1
|
generation_config.json
CHANGED
@@ -9,5 +9,5 @@
|
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 4,
|
11 |
"pad_token_id": 0,
|
12 |
-
"transformers_version": "4.
|
13 |
}
|
|
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 4,
|
11 |
"pad_token_id": 0,
|
12 |
+
"transformers_version": "4.37.0"
|
13 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 998132132
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f68c70c946087269f5efc4e00255840f8cf74b3df575adc696f29ca98f9dba93
|
3 |
size 998132132
|