Hugging Face's logo

haryoaw
/
scenario-kd-from-pre-finetune-silver-div-2-data-hate_speech_filipino-model-xlm-r

Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
07280ba
•
1 Parent(s): bcc5d1a

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +98 -0
  2. config.json +28 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - hate_speech_filipino
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-kd-from-pre-finetune-silver-div-2-data-hate_speech_filipino-model-xlm-r
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
+ # scenario-kd-from-pre-finetune-silver-div-2-data-hate_speech_filipino-model-xlm-r
20
+
21
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the hate_speech_filipino dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4122
24
+ - Accuracy: 0.7810
25
+ - F1: 0.7699
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: 5e-05
45
+ - train_batch_size: 32
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: 6969
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
56
+ | No log | 0.32 | 100 | 1.4902 | 0.7143 | 0.7119 |
57
+ | No log | 0.64 | 200 | 1.0099 | 0.7379 | 0.7416 |
58
+ | No log | 0.96 | 300 | 0.9000 | 0.7531 | 0.7410 |
59
+ | No log | 1.28 | 400 | 0.7416 | 0.7595 | 0.7548 |
60
+ | 1.3478 | 1.6 | 500 | 0.7405 | 0.7703 | 0.7495 |
61
+ | 1.3478 | 1.92 | 600 | 0.6557 | 0.7743 | 0.7569 |
62
+ | 1.3478 | 2.24 | 700 | 0.6338 | 0.7661 | 0.7656 |
63
+ | 1.3478 | 2.56 | 800 | 0.6421 | 0.7682 | 0.7429 |
64
+ | 1.3478 | 2.88 | 900 | 0.5503 | 0.7746 | 0.7649 |
65
+ | 0.667 | 3.19 | 1000 | 0.5596 | 0.7741 | 0.7623 |
66
+ | 0.667 | 3.51 | 1100 | 0.6638 | 0.7729 | 0.7365 |
67
+ | 0.667 | 3.83 | 1200 | 0.5504 | 0.7798 | 0.7545 |
68
+ | 0.667 | 4.15 | 1300 | 0.5163 | 0.7769 | 0.7613 |
69
+ | 0.667 | 4.47 | 1400 | 0.6817 | 0.7498 | 0.7641 |
70
+ | 0.4362 | 4.79 | 1500 | 0.5097 | 0.7717 | 0.7725 |
71
+ | 0.4362 | 5.11 | 1600 | 0.5382 | 0.7765 | 0.7460 |
72
+ | 0.4362 | 5.43 | 1700 | 0.5237 | 0.7800 | 0.7493 |
73
+ | 0.4362 | 5.75 | 1800 | 0.4712 | 0.7786 | 0.7552 |
74
+ | 0.4362 | 6.07 | 1900 | 0.4671 | 0.7755 | 0.7570 |
75
+ | 0.3401 | 6.39 | 2000 | 0.4376 | 0.7859 | 0.7752 |
76
+ | 0.3401 | 6.71 | 2100 | 0.4753 | 0.7706 | 0.7720 |
77
+ | 0.3401 | 7.03 | 2200 | 0.4661 | 0.7854 | 0.7706 |
78
+ | 0.3401 | 7.35 | 2300 | 0.4555 | 0.7774 | 0.7605 |
79
+ | 0.3401 | 7.67 | 2400 | 0.4362 | 0.7812 | 0.7683 |
80
+ | 0.2844 | 7.99 | 2500 | 0.4511 | 0.7864 | 0.7734 |
81
+ | 0.2844 | 8.31 | 2600 | 0.4433 | 0.7767 | 0.7707 |
82
+ | 0.2844 | 8.63 | 2700 | 0.5001 | 0.7656 | 0.7699 |
83
+ | 0.2844 | 8.95 | 2800 | 0.4337 | 0.7810 | 0.7723 |
84
+ | 0.2844 | 9.27 | 2900 | 0.4145 | 0.7812 | 0.7668 |
85
+ | 0.2436 | 9.58 | 3000 | 0.4143 | 0.7840 | 0.7698 |
86
+ | 0.2436 | 9.9 | 3100 | 0.3993 | 0.7786 | 0.7687 |
87
+ | 0.2436 | 10.22 | 3200 | 0.4030 | 0.7899 | 0.7734 |
88
+ | 0.2436 | 10.54 | 3300 | 0.4054 | 0.7826 | 0.7666 |
89
+ | 0.2436 | 10.86 | 3400 | 0.3996 | 0.7762 | 0.7716 |
90
+ | 0.2246 | 11.18 | 3500 | 0.4122 | 0.7810 | 0.7699 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.33.3
96
+ - Pytorch 2.0.1
97
+ - Datasets 2.14.5
98
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassificationKD"
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.33.3",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd7194fd49ae317640bbd5f4317c10d58603f187de2b045ad949f8b73339cda
3
+ size 942107569
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2d0a47763a4d81f4828e33426ce1cfb97aa054438f94be648f15f978a723c4
3
+ size 4219