Initial Commit
Browse files- README.md +101 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlm-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- smsa
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-normal-finetune-clf-data-smsa-model-xlm-roberta-base
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: smsa
|
19 |
+
type: smsa
|
20 |
+
config: smsa_nusantara_text
|
21 |
+
split: validation
|
22 |
+
args: smsa_nusantara_text
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.9222222222222223
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.9010725836501758
|
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-smsa-model-xlm-roberta-base
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the smsa dataset.
|
38 |
+
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.3511
|
40 |
+
- Accuracy: 0.9222
|
41 |
+
- F1: 0.9011
|
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-05
|
61 |
+
- train_batch_size: 32
|
62 |
+
- eval_batch_size: 32
|
63 |
+
- seed: 42
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 6969
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
72 |
+
| No log | 0.29 | 100 | 0.4204 | 0.8397 | 0.6487 |
|
73 |
+
| No log | 0.58 | 200 | 0.3298 | 0.9095 | 0.8696 |
|
74 |
+
| No log | 0.87 | 300 | 0.2664 | 0.9214 | 0.8843 |
|
75 |
+
| No log | 1.16 | 400 | 0.2882 | 0.9151 | 0.8849 |
|
76 |
+
| 0.3642 | 1.45 | 500 | 0.2531 | 0.9175 | 0.8808 |
|
77 |
+
| 0.3642 | 1.74 | 600 | 0.2847 | 0.9175 | 0.8820 |
|
78 |
+
| 0.3642 | 2.03 | 700 | 0.2889 | 0.9294 | 0.9060 |
|
79 |
+
| 0.3642 | 2.33 | 800 | 0.3066 | 0.9270 | 0.8996 |
|
80 |
+
| 0.3642 | 2.62 | 900 | 0.3736 | 0.9190 | 0.8914 |
|
81 |
+
| 0.2064 | 2.91 | 1000 | 0.2706 | 0.9214 | 0.8853 |
|
82 |
+
| 0.2064 | 3.2 | 1100 | 0.3201 | 0.9190 | 0.8878 |
|
83 |
+
| 0.2064 | 3.49 | 1200 | 0.2372 | 0.9254 | 0.9007 |
|
84 |
+
| 0.2064 | 3.78 | 1300 | 0.2534 | 0.9190 | 0.8904 |
|
85 |
+
| 0.2064 | 4.07 | 1400 | 0.3266 | 0.9214 | 0.8939 |
|
86 |
+
| 0.1543 | 4.36 | 1500 | 0.3405 | 0.9135 | 0.8815 |
|
87 |
+
| 0.1543 | 4.65 | 1600 | 0.3485 | 0.9238 | 0.8988 |
|
88 |
+
| 0.1543 | 4.94 | 1700 | 0.3287 | 0.9270 | 0.9011 |
|
89 |
+
| 0.1543 | 5.23 | 1800 | 0.3631 | 0.9167 | 0.8866 |
|
90 |
+
| 0.1543 | 5.52 | 1900 | 0.3714 | 0.9167 | 0.8922 |
|
91 |
+
| 0.1227 | 5.81 | 2000 | 0.3030 | 0.9119 | 0.8794 |
|
92 |
+
| 0.1227 | 6.1 | 2100 | 0.3363 | 0.9286 | 0.9046 |
|
93 |
+
| 0.1227 | 6.4 | 2200 | 0.3511 | 0.9222 | 0.9011 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.33.3
|
99 |
+
- Pytorch 2.0.1
|
100 |
+
- Datasets 2.14.5
|
101 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "xlm-roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.33.3",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c771bc260cb83871603ce6ffc006ec1fc21ada94dd786ebf17dd5c5e1ae509
|
3 |
+
size 1112252785
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562a9a94d8dcd18b4acda8b11216fd2f03cd2d10c9c7301961b9a586ff2a120f
|
3 |
+
size 4155
|