Alfahluzi/bert2bert-dropout-0.3-lr-5e-05-ds-canonical train with xtreme data 5 epochs
Browse files
README.md
CHANGED
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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.
|
19 |
-
- Rouge2 Precision: 0.
|
20 |
-
- Rouge2 Recall: 0.
|
21 |
-
- Rouge2 Fmeasure: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,24 +38,28 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
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 |
-
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
-
- Transformers 4.37.
|
59 |
-
- Pytorch 2.1.
|
60 |
-
- Datasets 2.
|
61 |
-
- Tokenizers 0.15.
|
|
|
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: 2.4528
|
19 |
+
- Rouge2 Precision: 0.1519
|
20 |
+
- Rouge2 Recall: 0.1497
|
21 |
+
- Rouge2 Fmeasure: 0.1496
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 5
|
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 |
+
| 2.6029 | 1.0 | 619 | 2.2821 | 0.1605 | 0.1573 | 0.1576 |
|
54 |
+
| 2.2629 | 2.0 | 1238 | 2.3146 | 0.1566 | 0.1588 | 0.1565 |
|
55 |
+
| 2.028 | 3.0 | 1857 | 2.3690 | 0.1548 | 0.1513 | 0.1519 |
|
56 |
+
| 1.8267 | 4.0 | 2476 | 2.4174 | 0.1527 | 0.1491 | 0.1497 |
|
57 |
+
| 1.5451 | 5.0 | 3095 | 2.4528 | 0.1519 | 0.1497 | 0.1496 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
+
- Transformers 4.37.2
|
63 |
+
- Pytorch 2.1.0+cu121
|
64 |
+
- Datasets 2.17.1
|
65 |
+
- Tokenizers 0.15.2
|
generation_config.json
CHANGED
@@ -7,8 +7,7 @@
|
|
7 |
"max_length": 100,
|
8 |
"min_length": 10,
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
-
"num_beams":
|
11 |
"pad_token_id": 0,
|
12 |
-
"transformers_version": "4.37.
|
13 |
-
"temperature": 0.5,
|
14 |
}
|
|
|
7 |
"max_length": 100,
|
8 |
"min_length": 10,
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
"pad_token_id": 0,
|
12 |
+
"transformers_version": "4.37.2"
|
|
|
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 sha256:477588e80d9813c4f5428a189c3650d51255f0fb0bf2b07493ff9f73fedcc2bd
|
3 |
size 998132132
|
runs/Feb28_17-13-49_89c71633e4f4/events.out.tfevents.1709140430.89c71633e4f4.1578.0
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:aa6f6f5571ebdaa99b1b463a162b2a787af67737f1c74e6ad2e9df005e27f5fa
|
3 |
+
size 12469
|