Hugging Face's logo

choiruzzia
/
best_roberta_model_fold_5

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
choiruzzia commited on
Commit
f9a2aa8
·
verified ·
1 Parent(s): 350f4c1

Training fold 5

Browse files
Files changed (6) hide show
  1. README.md +75 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
  4. runs/Jul10_14-23-21_f6ffe0ab7d5f/events.out.tfevents.1720621402.f6ffe0ab7d5f.34.0 +3 -0
  5. runs/Jul10_14-23-21_f6ffe0ab7d5f/events.out.tfevents.1720622655.f6ffe0ab7d5f.34.1 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: best_roberta_model_fold_5
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # best_roberta_model_fold_5
20
+
21
+ This model is a fine-tuned version of [ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa](https://huggingface.co/ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.1930
24
+ - Accuracy: 0.8625
25
+ - Precision: 0.8332
26
+ - Recall: 0.8376
27
+ - F1: 0.8353
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | No log | 1.0 | 252 | 0.5996 | 0.8526 | 0.8428 | 0.7584 | 0.7817 |
59
+ | 0.4616 | 2.0 | 504 | 0.7400 | 0.8207 | 0.7814 | 0.7663 | 0.7684 |
60
+ | 0.4616 | 3.0 | 756 | 0.7731 | 0.8586 | 0.8327 | 0.8058 | 0.8173 |
61
+ | 0.1366 | 4.0 | 1008 | 0.9903 | 0.8446 | 0.8110 | 0.8439 | 0.8182 |
62
+ | 0.1366 | 5.0 | 1260 | 1.0818 | 0.8506 | 0.8198 | 0.8084 | 0.8133 |
63
+ | 0.0362 | 6.0 | 1512 | 1.1802 | 0.8486 | 0.8164 | 0.8199 | 0.8178 |
64
+ | 0.0362 | 7.0 | 1764 | 1.1920 | 0.8586 | 0.8333 | 0.8135 | 0.8224 |
65
+ | 0.0119 | 8.0 | 2016 | 1.2077 | 0.8546 | 0.8206 | 0.8323 | 0.8259 |
66
+ | 0.0119 | 9.0 | 2268 | 1.2426 | 0.8526 | 0.8178 | 0.8323 | 0.8244 |
67
+ | 0.0034 | 10.0 | 2520 | 1.1930 | 0.8625 | 0.8332 | 0.8376 | 0.8353 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.41.2
73
+ - Pytorch 2.1.2
74
+ - Datasets 2.19.2
75
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "POSITIVE",
16
+ "1": "NEUTRAL",
17
+ "2": "NEGATIVE"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "NEGATIVE": 2,
23
+ "NEUTRAL": 1,
24
+ "POSITIVE": 0
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.41.2",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 50265
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f702901326b97ed18e82249e3ab272b551bf4851ef316006cd539938b308f4f
3
+ size 498615900
runs/Jul10_14-23-21_f6ffe0ab7d5f/events.out.tfevents.1720621402.f6ffe0ab7d5f.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7346d6f602fee67cb20f766ca66648c8e83c7e5bc8bd931e63794ee8990526
3
+ size 11316
runs/Jul10_14-23-21_f6ffe0ab7d5f/events.out.tfevents.1720622655.f6ffe0ab7d5f.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1881f40d29d3b04403da96fcbf97c490ef1420de3c3f36e1b8d25ddf2ce98cdc
3
+ size 560
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d519e197f7380417b45d89211c9417294421d1d7f63a54dacd3cad8f94bf60d
3
+ size 5176