End of training
Browse files- README.md +138 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +29 -0
- model.safetensors +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vinai/phobert-base-v2
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: GenZ-mental-health-toxic-content-classification-v2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# GenZ-mental-health-toxic-content-classification-v2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7329
|
21 |
+
- Accuracy: 0.8816
|
22 |
+
- F1: 0.8088
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 20
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
52 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
|
53 |
+
| No log | 0.2558 | 200 | 0.3588 | 0.8499 | 0.7643 |
|
54 |
+
| No log | 0.5115 | 400 | 0.3447 | 0.8649 | 0.7834 |
|
55 |
+
| No log | 0.7673 | 600 | 0.3380 | 0.8740 | 0.7832 |
|
56 |
+
| 0.3661 | 1.0230 | 800 | 0.3297 | 0.8771 | 0.8042 |
|
57 |
+
| 0.3661 | 1.2788 | 1000 | 0.2997 | 0.8829 | 0.8085 |
|
58 |
+
| 0.3661 | 1.5345 | 1200 | 0.3038 | 0.8841 | 0.7980 |
|
59 |
+
| 0.3661 | 1.7903 | 1400 | 0.3058 | 0.8859 | 0.8110 |
|
60 |
+
| 0.2685 | 2.0460 | 1600 | 0.3259 | 0.8867 | 0.8171 |
|
61 |
+
| 0.2685 | 2.3018 | 1800 | 0.3194 | 0.8861 | 0.8086 |
|
62 |
+
| 0.2685 | 2.5575 | 2000 | 0.3328 | 0.8792 | 0.8137 |
|
63 |
+
| 0.2685 | 2.8133 | 2200 | 0.3462 | 0.8823 | 0.7894 |
|
64 |
+
| 0.2176 | 3.0691 | 2400 | 0.4151 | 0.8867 | 0.8209 |
|
65 |
+
| 0.2176 | 3.3248 | 2600 | 0.3727 | 0.8830 | 0.8129 |
|
66 |
+
| 0.2176 | 3.5806 | 2800 | 0.3754 | 0.8807 | 0.8126 |
|
67 |
+
| 0.2176 | 3.8363 | 3000 | 0.3496 | 0.8905 | 0.8229 |
|
68 |
+
| 0.1825 | 4.0921 | 3200 | 0.4204 | 0.8839 | 0.8058 |
|
69 |
+
| 0.1825 | 4.3478 | 3400 | 0.4341 | 0.8890 | 0.8129 |
|
70 |
+
| 0.1825 | 4.6036 | 3600 | 0.3610 | 0.8908 | 0.8166 |
|
71 |
+
| 0.1825 | 4.8593 | 3800 | 0.3546 | 0.8883 | 0.8143 |
|
72 |
+
| 0.1592 | 5.1151 | 4000 | 0.4929 | 0.8740 | 0.8073 |
|
73 |
+
| 0.1592 | 5.3708 | 4200 | 0.4861 | 0.8865 | 0.8029 |
|
74 |
+
| 0.1592 | 5.6266 | 4400 | 0.4340 | 0.8856 | 0.8162 |
|
75 |
+
| 0.1592 | 5.8824 | 4600 | 0.4357 | 0.8724 | 0.8038 |
|
76 |
+
| 0.1375 | 6.1381 | 4800 | 0.4334 | 0.8885 | 0.8157 |
|
77 |
+
| 0.1375 | 6.3939 | 5000 | 0.4724 | 0.8760 | 0.8083 |
|
78 |
+
| 0.1375 | 6.6496 | 5200 | 0.4504 | 0.8899 | 0.8162 |
|
79 |
+
| 0.1375 | 6.9054 | 5400 | 0.3867 | 0.8854 | 0.8096 |
|
80 |
+
| 0.1255 | 7.1611 | 5600 | 0.5133 | 0.8756 | 0.8070 |
|
81 |
+
| 0.1255 | 7.4169 | 5800 | 0.4806 | 0.8883 | 0.8163 |
|
82 |
+
| 0.1255 | 7.6726 | 6000 | 0.4748 | 0.8816 | 0.8114 |
|
83 |
+
| 0.1255 | 7.9284 | 6200 | 0.5101 | 0.8803 | 0.8084 |
|
84 |
+
| 0.115 | 8.1841 | 6400 | 0.5017 | 0.8832 | 0.8068 |
|
85 |
+
| 0.115 | 8.4399 | 6600 | 0.4820 | 0.8823 | 0.8041 |
|
86 |
+
| 0.115 | 8.6957 | 6800 | 0.5131 | 0.8865 | 0.8089 |
|
87 |
+
| 0.115 | 8.9514 | 7000 | 0.4742 | 0.8858 | 0.8145 |
|
88 |
+
| 0.1005 | 9.2072 | 7200 | 0.5905 | 0.8870 | 0.8108 |
|
89 |
+
| 0.1005 | 9.4629 | 7400 | 0.5393 | 0.8796 | 0.8067 |
|
90 |
+
| 0.1005 | 9.7187 | 7600 | 0.5595 | 0.8776 | 0.8077 |
|
91 |
+
| 0.1005 | 9.9744 | 7800 | 0.5101 | 0.8859 | 0.8079 |
|
92 |
+
| 0.0918 | 10.2302 | 8000 | 0.6249 | 0.8781 | 0.8067 |
|
93 |
+
| 0.0918 | 10.4859 | 8200 | 0.5490 | 0.8825 | 0.8077 |
|
94 |
+
| 0.0918 | 10.7417 | 8400 | 0.5394 | 0.8769 | 0.8040 |
|
95 |
+
| 0.0818 | 10.9974 | 8600 | 0.6048 | 0.8807 | 0.8099 |
|
96 |
+
| 0.0818 | 11.2532 | 8800 | 0.5951 | 0.8745 | 0.8011 |
|
97 |
+
| 0.0818 | 11.5090 | 9000 | 0.6220 | 0.8819 | 0.8077 |
|
98 |
+
| 0.0818 | 11.7647 | 9200 | 0.6505 | 0.8785 | 0.8063 |
|
99 |
+
| 0.078 | 12.0205 | 9400 | 0.6327 | 0.8785 | 0.8048 |
|
100 |
+
| 0.078 | 12.2762 | 9600 | 0.6260 | 0.8796 | 0.8084 |
|
101 |
+
| 0.078 | 12.5320 | 9800 | 0.5645 | 0.8800 | 0.8075 |
|
102 |
+
| 0.078 | 12.7877 | 10000 | 0.6264 | 0.8823 | 0.8083 |
|
103 |
+
| 0.071 | 13.0435 | 10200 | 0.6611 | 0.8798 | 0.8118 |
|
104 |
+
| 0.071 | 13.2992 | 10400 | 0.6474 | 0.8845 | 0.8125 |
|
105 |
+
| 0.071 | 13.5550 | 10600 | 0.6508 | 0.8819 | 0.8125 |
|
106 |
+
| 0.071 | 13.8107 | 10800 | 0.6394 | 0.8823 | 0.8089 |
|
107 |
+
| 0.0652 | 14.0665 | 11000 | 0.6261 | 0.8783 | 0.8069 |
|
108 |
+
| 0.0652 | 14.3223 | 11200 | 0.6541 | 0.8809 | 0.8070 |
|
109 |
+
| 0.0652 | 14.5780 | 11400 | 0.7019 | 0.8778 | 0.8088 |
|
110 |
+
| 0.0652 | 14.8338 | 11600 | 0.6469 | 0.8830 | 0.8091 |
|
111 |
+
| 0.0606 | 15.0895 | 11800 | 0.7078 | 0.8767 | 0.8049 |
|
112 |
+
| 0.0606 | 15.3453 | 12000 | 0.6889 | 0.8809 | 0.8070 |
|
113 |
+
| 0.0606 | 15.6010 | 12200 | 0.7316 | 0.8787 | 0.8090 |
|
114 |
+
| 0.0606 | 15.8568 | 12400 | 0.6827 | 0.8801 | 0.8033 |
|
115 |
+
| 0.0575 | 16.1125 | 12600 | 0.7547 | 0.8812 | 0.8094 |
|
116 |
+
| 0.0575 | 16.3683 | 12800 | 0.7358 | 0.8825 | 0.8055 |
|
117 |
+
| 0.0575 | 16.6240 | 13000 | 0.7128 | 0.8794 | 0.8045 |
|
118 |
+
| 0.0575 | 16.8798 | 13200 | 0.7322 | 0.8818 | 0.8061 |
|
119 |
+
| 0.054 | 17.1355 | 13400 | 0.7335 | 0.8814 | 0.8072 |
|
120 |
+
| 0.054 | 17.3913 | 13600 | 0.7275 | 0.8818 | 0.8058 |
|
121 |
+
| 0.054 | 17.6471 | 13800 | 0.7316 | 0.8810 | 0.8063 |
|
122 |
+
| 0.054 | 17.9028 | 14000 | 0.7090 | 0.8823 | 0.8056 |
|
123 |
+
| 0.052 | 18.1586 | 14200 | 0.7444 | 0.8781 | 0.8051 |
|
124 |
+
| 0.052 | 18.4143 | 14400 | 0.7201 | 0.8810 | 0.8066 |
|
125 |
+
| 0.052 | 18.6701 | 14600 | 0.7200 | 0.8825 | 0.8103 |
|
126 |
+
| 0.052 | 18.9258 | 14800 | 0.7259 | 0.8800 | 0.8073 |
|
127 |
+
| 0.049 | 19.1816 | 15000 | 0.7419 | 0.8830 | 0.8085 |
|
128 |
+
| 0.049 | 19.4373 | 15200 | 0.7344 | 0.8823 | 0.8085 |
|
129 |
+
| 0.049 | 19.6931 | 15400 | 0.7400 | 0.8816 | 0.8085 |
|
130 |
+
| 0.049 | 19.9488 | 15600 | 0.7329 | 0.8816 | 0.8088 |
|
131 |
+
|
132 |
+
|
133 |
+
### Framework versions
|
134 |
+
|
135 |
+
- Transformers 4.44.0
|
136 |
+
- Pytorch 2.1.2
|
137 |
+
- Datasets 2.20.0
|
138 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
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 |
+
"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": 258,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"tokenizer_class": "PhobertTokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.44.0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64001
|
29 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a903dcabbfe05a066c91528bd87cb97c93ac2108fd4cc321a7f6c59845b1273
|
3 |
+
size 540023384
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "PhobertTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf75042925b9a2e45417abe3aa7da0c372e76fa5edef5d5e34d3f1b911feff9b
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|