Hugging Face's logo

wcyat
/
roberta-suicide-detection-hk

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
wcyat commited on
Commit
d9751da
•
1 Parent(s): 6a1c370

Training in progress, step 50

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. README.md +61 -0
  3. config.json +29 -0
  4. model.safetensors +3 -0
  5. runs/May26_17-08-39_2cad317fbdf9/events.out.tfevents.1716743320.2cad317fbdf9.1996.0 +3 -0
  6. runs/May26_17-13-24_2cad317fbdf9/events.out.tfevents.1716743605.2cad317fbdf9.1996.1 +3 -0
  7. runs/May26_17-14-46_2cad317fbdf9/events.out.tfevents.1716743687.2cad317fbdf9.1996.2 +3 -0
  8. runs/May26_17-15-16_2cad317fbdf9/events.out.tfevents.1716743717.2cad317fbdf9.1996.3 +3 -0
  9. runs/May26_17-17-00_2cad317fbdf9/events.out.tfevents.1716743821.2cad317fbdf9.1996.4 +3 -0
  10. runs/May26_17-17-40_2cad317fbdf9/events.out.tfevents.1716743860.2cad317fbdf9.1996.5 +3 -0
  11. runs/May26_17-19-02_2cad317fbdf9/events.out.tfevents.1716743942.2cad317fbdf9.1996.6 +3 -0
  12. runs/May26_17-32-10_2cad317fbdf9/events.out.tfevents.1716744731.2cad317fbdf9.1996.7 +3 -0
  13. runs/May26_17-37-17_2cad317fbdf9/events.out.tfevents.1716745037.2cad317fbdf9.1996.8 +3 -0
  14. runs/May26_17-44-09_2cad317fbdf9/events.out.tfevents.1716745450.2cad317fbdf9.1996.9 +3 -0
  15. runs/May26_17-44-21_2cad317fbdf9/events.out.tfevents.1716745461.2cad317fbdf9.1996.10 +3 -0
  16. runs/May26_17-44-31_2cad317fbdf9/events.out.tfevents.1716745471.2cad317fbdf9.1996.11 +3 -0
  17. runs/May26_17-44-58_2cad317fbdf9/events.out.tfevents.1716745499.2cad317fbdf9.1996.12 +3 -0
  18. runs/May26_17-45-03_2cad317fbdf9/events.out.tfevents.1716745503.2cad317fbdf9.1996.13 +3 -0
  19. runs/May26_17-45-53_2cad317fbdf9/events.out.tfevents.1716745555.2cad317fbdf9.11544.0 +3 -0
  20. runs/May26_17-49-25_2cad317fbdf9/events.out.tfevents.1716745767.2cad317fbdf9.11544.1 +3 -0
  21. runs/May26_17-53-13_2cad317fbdf9/events.out.tfevents.1716745994.2cad317fbdf9.11544.2 +3 -0
  22. sentencepiece.bpe.model +3 -0
  23. special_tokens_map.json +15 -0
  24. tokenizer.json +3 -0
  25. tokenizer_config.json +54 -0
  26. training_args.bin +3 -0
  27. vocab.txt +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-multilingual-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: distilbert-suicide-detection-hk
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # distilbert-suicide-detection-hk
15
+
16
+ This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.3105
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 5
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 27 | 0.3452 |
50
+ | No log | 2.0 | 54 | 0.3644 |
51
+ | No log | 3.0 | 81 | 0.3075 |
52
+ | No log | 4.0 | 108 | 0.3395 |
53
+ | No log | 5.0 | 135 | 0.3105 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.41.0
59
+ - Pytorch 2.3.0+cu121
60
+ - Datasets 2.19.1
61
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-large",
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": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.41.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4b148f4781e9783602008ddbffe2e5c1002927988b7c5579b6c18ab20f411a
3
+ size 2239618672
runs/May26_17-08-39_2cad317fbdf9/events.out.tfevents.1716743320.2cad317fbdf9.1996.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6089363521ca574f9346b4b5e192755319ecd0a55454450deb7b4b776c8dde9c
3
+ size 4744
runs/May26_17-13-24_2cad317fbdf9/events.out.tfevents.1716743605.2cad317fbdf9.1996.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e415d57d9a57af400148369af60e5a2f841c0b2434546f0880cb66ba7f54dc
3
+ size 4744
runs/May26_17-14-46_2cad317fbdf9/events.out.tfevents.1716743687.2cad317fbdf9.1996.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b525932d4ef0832ec962b7a2fca326032833b9a662c6bd7c9135bcee0996bd
3
+ size 4744
runs/May26_17-15-16_2cad317fbdf9/events.out.tfevents.1716743717.2cad317fbdf9.1996.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2056631f9c99a20e4735cef0615cfe512137f775166c2b7e1610a8d3381b1052
3
+ size 4744
runs/May26_17-17-00_2cad317fbdf9/events.out.tfevents.1716743821.2cad317fbdf9.1996.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b300a8f32f6a6197820de8f0fd95a38c9121f27fa3bf55135469e76b350cc525
3
+ size 4744
runs/May26_17-17-40_2cad317fbdf9/events.out.tfevents.1716743860.2cad317fbdf9.1996.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7899e604ea5df2aaf0ef3a516240f4b037a92c1d19b441dc47adafb9ba633a6f
3
+ size 4793
runs/May26_17-19-02_2cad317fbdf9/events.out.tfevents.1716743942.2cad317fbdf9.1996.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da16adec9d7c82b328c3ecf0bbf3b93f9f67c1b53c52b98adcd5f16df484e3c5
3
+ size 6529
runs/May26_17-32-10_2cad317fbdf9/events.out.tfevents.1716744731.2cad317fbdf9.1996.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576d750b5bd14c56dd84dc5f441738f05c189f4e9b3b4ec852bcc8a4d4487268
3
+ size 9769
runs/May26_17-37-17_2cad317fbdf9/events.out.tfevents.1716745037.2cad317fbdf9.1996.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbc632c580c1428d46594d3e13b95398d135e907f333360676bb3e8660838b5
3
+ size 14415
runs/May26_17-44-09_2cad317fbdf9/events.out.tfevents.1716745450.2cad317fbdf9.1996.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ea71898496c03d7cfa616fa96342f4c8a67d3ec8eb317d4f60e290b0010fc5
3
+ size 4184
runs/May26_17-44-21_2cad317fbdf9/events.out.tfevents.1716745461.2cad317fbdf9.1996.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a810e05a4221de4604816dde9fce5dcb2eca29c7f6c95998009233be14ba6de9
3
+ size 4184
runs/May26_17-44-31_2cad317fbdf9/events.out.tfevents.1716745471.2cad317fbdf9.1996.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef99f93d12180beba5ee7d8270d5bf36a600282c16a4aae8b6be064ad60b87b
3
+ size 5807
runs/May26_17-44-58_2cad317fbdf9/events.out.tfevents.1716745499.2cad317fbdf9.1996.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f565eb847062d8e21c78ed0ecab89c701a7571ef067030eac2c3c5b955a688
3
+ size 4184
runs/May26_17-45-03_2cad317fbdf9/events.out.tfevents.1716745503.2cad317fbdf9.1996.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1ef5b24679d4f4b3b3998cec791cbd49a4607c88fa94a6d4e98dfef92e162c
3
+ size 4184
runs/May26_17-45-53_2cad317fbdf9/events.out.tfevents.1716745555.2cad317fbdf9.11544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617d1c6e76daa5488de3740eff9a24753491c4fc76ebbf12412568d126e15d54
3
+ size 5336
runs/May26_17-49-25_2cad317fbdf9/events.out.tfevents.1716745767.2cad317fbdf9.11544.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b612e3725adb4ea6fa364d876e613c24b6a0a50572c1043fae8a9edbe8a5f2
3
+ size 4863
runs/May26_17-53-13_2cad317fbdf9/events.out.tfevents.1716745994.2cad317fbdf9.11544.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b633002dfeb881be6fb367eb5bfb9e6f6f9f98d30cc509c8c0f0e691e7a396d0
3
+ size 5336
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
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
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
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": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3370869cdf2e04788fe9f37c402ee2d9e0817628f17083977df4e8f725563489
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff