Model save
Browse files- README.md +68 -0
- adapter-summarization/adapter_config.json +26 -0
- adapter-summarization/pytorch_adapter.bin +3 -0
- default/head_config.json +18 -0
- default/pytorch_model_head.bin +3 -0
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: indosum-lora-2
|
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 |
+
# indosum-lora-2
|
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: 0.4791
|
21 |
+
- Rouge1: 73.5231
|
22 |
+
- Rouge2: 67.0852
|
23 |
+
- Rougel: 70.6685
|
24 |
+
- Rougelsum: 72.7812
|
25 |
+
- Gen Len: 101.6091
|
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 |
+
| 0.8321 | 1.0 | 894 | 0.5275 | 69.0582 | 62.1176 | 66.1702 | 68.2139 | 106.4096 |
|
57 |
+
| 0.6308 | 2.0 | 1788 | 0.4947 | 72.4944 | 66.0482 | 69.6771 | 71.7463 | 100.4980 |
|
58 |
+
| 0.5883 | 3.0 | 2682 | 0.4842 | 73.2328 | 66.8354 | 70.4528 | 72.4857 | 101.6185 |
|
59 |
+
| 0.5637 | 4.0 | 3576 | 0.4768 | 73.2438 | 66.9667 | 70.4669 | 72.5599 | 99.1178 |
|
60 |
+
| 0.5461 | 5.0 | 4470 | 0.4791 | 73.5231 | 67.0852 | 70.6685 | 72.7812 | 101.6091 |
|
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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "T5AdapterModel",
|
22 |
+
"model_name": "LazarusNLP/IndoNanoT5-base",
|
23 |
+
"model_type": "t5",
|
24 |
+
"name": "adapter-summarization",
|
25 |
+
"version": "0.2.2"
|
26 |
+
}
|
adapter-summarization/pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:269bd19d3267d57d4f09d078d125589d51317fb20ddd721fc8d3a9a7b2f238b1
|
3 |
+
size 3594738
|
default/head_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"activation_function": null,
|
4 |
+
"bias": false,
|
5 |
+
"head_type": "seq2seq_lm",
|
6 |
+
"label2id": null,
|
7 |
+
"layer_norm": false,
|
8 |
+
"layers": 1,
|
9 |
+
"shift_labels": false,
|
10 |
+
"vocab_size": 32128
|
11 |
+
},
|
12 |
+
"hidden_size": 768,
|
13 |
+
"model_class": "T5AdapterModel",
|
14 |
+
"model_name": "LazarusNLP/IndoNanoT5-base",
|
15 |
+
"model_type": "t5",
|
16 |
+
"name": "default",
|
17 |
+
"version": "0.2.2"
|
18 |
+
}
|
default/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7630bc8df260791f15a81368176459211beed1769c6d484b76571a0f8d85a9e
|
3 |
+
size 98698515
|