Initial Commit
Browse files- README.md +96 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: indolem/indobert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- indolem_sentiment
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-normal-finetune-clf-data-indolem_sentiment-model-indolem-indobert-base-uncased
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: indolem_sentiment
|
19 |
+
type: indolem_sentiment
|
20 |
+
config: indolem_sentiment_nusantara_text
|
21 |
+
split: validation
|
22 |
+
args: indolem_sentiment_nusantara_text
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.899749373433584
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.8181818181818181
|
30 |
+
---
|
31 |
+
|
32 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
33 |
+
should probably proofread and complete it, then remove this comment. -->
|
34 |
+
|
35 |
+
# scenario-normal-finetune-clf-data-indolem_sentiment-model-indolem-indobert-base-uncased
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indolem_sentiment dataset.
|
38 |
+
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.7320
|
40 |
+
- Accuracy: 0.8997
|
41 |
+
- F1: 0.8182
|
42 |
+
|
43 |
+
## Model description
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training and evaluation data
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Training procedure
|
56 |
+
|
57 |
+
### Training hyperparameters
|
58 |
+
|
59 |
+
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 5e-06
|
61 |
+
- train_batch_size: 8
|
62 |
+
- eval_batch_size: 8
|
63 |
+
- seed: 42
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 30
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
72 |
+
| No log | 0.44 | 200 | 0.5218 | 0.7343 | 0.2838 |
|
73 |
+
| No log | 0.88 | 400 | 0.4318 | 0.8070 | 0.7138 |
|
74 |
+
| 0.4843 | 1.32 | 600 | 0.4092 | 0.8521 | 0.7281 |
|
75 |
+
| 0.4843 | 1.76 | 800 | 0.3515 | 0.8772 | 0.7803 |
|
76 |
+
| 0.2912 | 2.2 | 1000 | 0.4582 | 0.8697 | 0.7833 |
|
77 |
+
| 0.2912 | 2.64 | 1200 | 0.5148 | 0.8747 | 0.7881 |
|
78 |
+
| 0.2912 | 3.08 | 1400 | 0.5736 | 0.8672 | 0.7837 |
|
79 |
+
| 0.2526 | 3.52 | 1600 | 0.5119 | 0.8797 | 0.7983 |
|
80 |
+
| 0.2526 | 3.96 | 1800 | 0.5242 | 0.8997 | 0.8095 |
|
81 |
+
| 0.1974 | 4.4 | 2000 | 0.5311 | 0.8997 | 0.8182 |
|
82 |
+
| 0.1974 | 4.84 | 2200 | 0.6478 | 0.8797 | 0.7983 |
|
83 |
+
| 0.1974 | 5.27 | 2400 | 0.6219 | 0.8822 | 0.8000 |
|
84 |
+
| 0.1526 | 5.71 | 2600 | 0.6591 | 0.8872 | 0.8178 |
|
85 |
+
| 0.1526 | 6.15 | 2800 | 0.6483 | 0.8947 | 0.8056 |
|
86 |
+
| 0.1159 | 6.59 | 3000 | 0.7075 | 0.8847 | 0.8099 |
|
87 |
+
| 0.1159 | 7.03 | 3200 | 0.7157 | 0.8872 | 0.8 |
|
88 |
+
| 0.1159 | 7.47 | 3400 | 0.7320 | 0.8997 | 0.8182 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.33.3
|
94 |
+
- Pytorch 2.0.1
|
95 |
+
- Datasets 2.14.5
|
96 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-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 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.33.3",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 31923
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f171149e8edc5b994768ffda2808a09f7a3d72a44a63d02cdbc63f3286b8f4
|
3 |
+
size 442307377
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e874c33054959b29d0c06a0732d9b109529fb57944f049b97f39e7815afd8faf
|
3 |
+
size 4283
|