bob-bob-bob-3
commited on
Commit
•
3544e49
1
Parent(s):
78c055e
End of training
Browse files- README.md +73 -0
- config.json +40 -0
- model.safetensors +3 -0
- runs/Jun19_20-33-27_80516ee61c48/events.out.tfevents.1718829214.80516ee61c48.721.21 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: indolem/indobertweet-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: sv1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# sv1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.0499
|
19 |
+
- F1 macro: 0.3977
|
20 |
+
- Weighted: 0.6145
|
21 |
+
- Balanced accuracy: 0.5186
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
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: 14
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 macro | Weighted | Balanced accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|
|
52 |
+
| 1.2727 | 1.0 | 154 | 1.2213 | 0.3786 | 0.5827 | 0.4776 |
|
53 |
+
| 0.8729 | 2.0 | 308 | 1.4909 | 0.3204 | 0.5293 | 0.4454 |
|
54 |
+
| 0.3299 | 3.0 | 462 | 1.6163 | 0.3885 | 0.5956 | 0.5035 |
|
55 |
+
| 0.2233 | 4.0 | 616 | 1.9917 | 0.3709 | 0.5977 | 0.4661 |
|
56 |
+
| 0.1323 | 5.0 | 770 | 2.5400 | 0.3797 | 0.5718 | 0.4903 |
|
57 |
+
| 0.0014 | 6.0 | 924 | 3.0973 | 0.3555 | 0.5244 | 0.5040 |
|
58 |
+
| 0.0012 | 7.0 | 1078 | 2.8258 | 0.3961 | 0.6119 | 0.5142 |
|
59 |
+
| 0.0013 | 8.0 | 1232 | 2.8277 | 0.3864 | 0.6097 | 0.5067 |
|
60 |
+
| 0.0006 | 9.0 | 1386 | 2.9388 | 0.3911 | 0.6087 | 0.5121 |
|
61 |
+
| 0.0006 | 10.0 | 1540 | 2.9096 | 0.4015 | 0.6235 | 0.5205 |
|
62 |
+
| 0.0004 | 11.0 | 1694 | 3.2002 | 0.3856 | 0.5798 | 0.5138 |
|
63 |
+
| 0.0005 | 12.0 | 1848 | 3.1226 | 0.3945 | 0.6052 | 0.5185 |
|
64 |
+
| 0.0004 | 13.0 | 2002 | 3.0566 | 0.3968 | 0.6123 | 0.5181 |
|
65 |
+
| 0.0004 | 14.0 | 2156 | 3.0499 | 0.3977 | 0.6145 | 0.5186 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.41.2
|
71 |
+
- Pytorch 2.3.0+cu121
|
72 |
+
- Datasets 2.20.0
|
73 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobertweet-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Sumber Daya Alam",
|
16 |
+
"1": "Politik",
|
17 |
+
"2": "Demografi",
|
18 |
+
"3": "Pertahanan dan Keamanan",
|
19 |
+
"4": "Ideologi",
|
20 |
+
"5": "Ekonomi",
|
21 |
+
"6": "Sosial Budaya",
|
22 |
+
"7": "Geografi"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "bert",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.41.2",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 31923
|
40 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6748106e7644688c9d8e45bca628a970530c36ef8f07ab53886211404b7f31d4
|
3 |
+
size 442280976
|
runs/Jun19_20-33-27_80516ee61c48/events.out.tfevents.1718829214.80516ee61c48.721.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041be7a4b524f9969d950f78c382e07f0e022622a48b3eb232b72dde56fba1e7
|
3 |
+
size 56890
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd7c7a42c0316b7a7df9b391781dd5df33eabf702cb72eb5a717763fca9a2d0
|
3 |
+
size 5112
|