apwic commited on
Commit
1a3ca2a
1 Parent(s): e8c40eb

Model save

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: LazarusNLP/IndoNanoT5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: summarization-lora-0
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # summarization-lora-0
17
+
18
+ This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5829
21
+ - Rouge1: 0.4334
22
+ - Rouge2: 0.0
23
+ - Rougel: 0.4324
24
+ - Rougelsum: 0.4298
25
+ - Gen Len: 1.0
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 8
46
+ - eval_batch_size: 32
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 5.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
+ | 1.3917 | 1.0 | 1783 | 0.6615 | 0.5471 | 0.0 | 0.5464 | 0.5441 | 1.0 |
57
+ | 0.854 | 2.0 | 3566 | 0.6181 | 0.4511 | 0.0 | 0.4501 | 0.4463 | 1.0 |
58
+ | 0.7905 | 3.0 | 5349 | 0.5925 | 0.421 | 0.0 | 0.4197 | 0.4168 | 1.0 |
59
+ | 0.7624 | 4.0 | 7132 | 0.5808 | 0.438 | 0.0 | 0.4378 | 0.433 | 1.0 |
60
+ | 0.751 | 5.0 | 8915 | 0.5829 | 0.4334 | 0.0 | 0.4324 | 0.4298 | 1.0 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.40.2
66
+ - Pytorch 2.3.0+cu121
67
+ - Datasets 2.19.1
68
+ - Tokenizers 0.19.1
adapter-summarization/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "alpha": 8,
4
+ "architecture": "lora",
5
+ "attn_matrices": [
6
+ "q",
7
+ "v"
8
+ ],
9
+ "composition_mode": "add",
10
+ "dropout": 0.0,
11
+ "init_weights": "lora",
12
+ "intermediate_lora": false,
13
+ "leave_out": [],
14
+ "output_lora": false,
15
+ "r": 8,
16
+ "selfattn_lora": true,
17
+ "use_gating": false
18
+ },
19
+ "config_id": "625403edad0bf919",
20
+ "hidden_size": 768,
21
+ "model_class": "T5ForConditionalGeneration",
22
+ "model_name": "LazarusNLP/IndoNanoT5-base",
23
+ "model_type": "t5",
24
+ "name": "adapter-summarization",
25
+ "version": "0.2.2"
26
+ }
adapter-summarization/head_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 768,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1
7
+ },
8
+ "model_class": "T5ForConditionalGeneration",
9
+ "model_name": "LazarusNLP/IndoNanoT5-base",
10
+ "model_type": "t5",
11
+ "name": null,
12
+ "num_labels": 2,
13
+ "version": "0.2.2"
14
+ }
adapter-summarization/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7f806b1532d96eea8201f2515ab1653314ba7fd7f24f925d30258bf8169a8a
3
+ size 3593010
adapter-summarization/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7467a987e0db5b7ef33f0dba6f30173b6f2a0fa4327e8d394e655fc96809b7cf
3
+ size 98698515