Hugging Face's logo

apwic
/
summarization-seq_bn-4

TensorBoard
Indonesian
Generated from Trainer
Model card Files Metrics Community
apwic commited on
Commit
143125d
•
1 Parent(s): 7148393

Model save

Browse files
Files changed (6) hide show
  1. README.md +68 -0
  2. adapter-summarization/adapter_config.json +42 -0
  3. adapter-summarization/head_config.json +14 -0
  4. adapter-summarization/pytorch_adapter.bin +3 -0
  5. adapter-summarization/pytorch_model_head.bin +3 -0
  6. runs/Jul06_17-55-53_a94680512e46/events.out.tfevents.1720288561.a94680512e46.1588403.0 +2 -2
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-seq_bn-4
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-seq_bn-4
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: 0.4653
21
+ - Rouge1: 0.7309
22
+ - Rouge2: 0.0
23
+ - Rougel: 0.7284
24
+ - Rougelsum: 0.7264
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: 0.001
45
+ - train_batch_size: 16
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
+ | 0.7807 | 1.0 | 892 | 0.5299 | 0.6861 | 0.0 | 0.6833 | 0.6836 | 1.0 |
57
+ | 0.6079 | 2.0 | 1784 | 0.4989 | 0.7141 | 0.0 | 0.7153 | 0.7147 | 1.0 |
58
+ | 0.5583 | 3.0 | 2676 | 0.4761 | 0.7153 | 0.0 | 0.7152 | 0.7139 | 1.0 |
59
+ | 0.5208 | 4.0 | 3568 | 0.4719 | 0.7433 | 0.0 | 0.743 | 0.7395 | 1.0 |
60
+ | 0.4912 | 5.0 | 4460 | 0.4653 | 0.7309 | 0.0 | 0.7284 | 0.7264 | 1.0 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.40.2
66
+ - Pytorch 2.3.1+cu121
67
+ - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
adapter-summarization/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "dropout": 0.0,
6
+ "factorized_phm_W": true,
7
+ "factorized_phm_rule": false,
8
+ "hypercomplex_nonlinearity": "glorot-uniform",
9
+ "init_weights": "bert",
10
+ "inv_adapter": null,
11
+ "inv_adapter_reduction_factor": null,
12
+ "is_parallel": false,
13
+ "learn_phm": true,
14
+ "leave_out": [],
15
+ "ln_after": false,
16
+ "ln_before": false,
17
+ "mh_adapter": false,
18
+ "non_linearity": "relu",
19
+ "original_ln_after": true,
20
+ "original_ln_before": true,
21
+ "output_adapter": true,
22
+ "phm_bias": true,
23
+ "phm_c_init": "normal",
24
+ "phm_dim": 4,
25
+ "phm_init_range": 0.0001,
26
+ "phm_layer": false,
27
+ "phm_rank": 1,
28
+ "reduction_factor": 16,
29
+ "residual_before_ln": true,
30
+ "scaling": 1.0,
31
+ "shared_W_phm": false,
32
+ "shared_phm_rule": true,
33
+ "use_gating": false
34
+ },
35
+ "config_id": "9076f36a74755ac4",
36
+ "hidden_size": 768,
37
+ "model_class": "T5ForConditionalGeneration",
38
+ "model_name": "LazarusNLP/IndoNanoT5-base",
39
+ "model_type": "t5",
40
+ "name": "adapter-summarization",
41
+ "version": "0.2.2"
42
+ }
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:ab5576350bc627bd04079194f64a07ed8ddcb0d5eb7852db5a354d74725d2ffe
3
+ size 7191830
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
runs/Jul06_17-55-53_a94680512e46/events.out.tfevents.1720288561.a94680512e46.1588403.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b783deb4988114b53d42da73fb6ff05d77222bb8c9d3e364ce130289a7d040f
3
- size 7946
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e1ffdd798db82d000b123ce3536c0de612bbfa2c57a5ce4b7fb9254c336055
3
+ size 9036