Hugging Face's logo

Silicon23
/
BERTForDetectingDepression-Twitter2020

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
Silicon23 commited on
Commit
99d53cf
·
verified ·
1 Parent(s): d4eb8a9

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. config.json +2 -2
  2. model.safetensors +2 -2
  3. run-0/checkpoint-450/config.json +2 -2
  4. run-0/checkpoint-450/model.safetensors +2 -2
  5. run-0/checkpoint-450/optimizer.pt +2 -2
  6. run-0/checkpoint-450/rng_state.pth +1 -1
  7. run-0/checkpoint-450/scheduler.pt +1 -1
  8. run-0/checkpoint-450/special_tokens_map.json +35 -5
  9. run-0/checkpoint-450/tokenizer.json +0 -0
  10. run-0/checkpoint-450/tokenizer_config.json +5 -1
  11. run-0/checkpoint-450/trainer_state.json +14 -23
  12. run-0/checkpoint-450/training_args.bin +1 -1
  13. run-0/checkpoint-450/vocab.txt +0 -0
  14. runs/Aug01_13-39-40_1d376fbba8fb/events.out.tfevents.1722519626.1d376fbba8fb.194.0 +3 -0
  15. special_tokens_map.json +35 -5
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +5 -1
  18. training_args.bin +1 -1
  19. vocab.txt +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google-bert/bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
@@ -23,5 +23,5 @@
23
  "transformers_version": "4.42.4",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
- "vocab_size": 30522
27
  }
 
1
  {
2
+ "_name_or_path": "AIMH/mental-bert-base-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
23
  "transformers_version": "4.42.4",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
+ "vocab_size": 28996
27
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5418a83fbe2cb26801b0fa0da68a2b582734a025be3ba1f7c0f615491f6a977
3
- size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9cf6e08108ec956b577d447f798865d5df7e0c5b49f1e0913c20b1325086e3
3
+ size 433270768
run-0/checkpoint-450/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google-bert/bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
@@ -23,5 +23,5 @@
23
  "transformers_version": "4.42.4",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
- "vocab_size": 30522
27
  }
 
1
  {
2
+ "_name_or_path": "AIMH/mental-bert-base-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
23
  "transformers_version": "4.42.4",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
+ "vocab_size": 28996
27
  }
run-0/checkpoint-450/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26e43fbc08e8d44606dc2b5a040ab066ca8d629aec26f880489c304f7658d1ce
3
- size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9cf6e08108ec956b577d447f798865d5df7e0c5b49f1e0913c20b1325086e3
3
+ size 433270768
run-0/checkpoint-450/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2306ad1a4340e6839959e59c0905b8bd4cae9702ba3a5357824e3b35d91ae8ea
3
- size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa761d75654c53d130a610651c0e5810252854f51a1b9ee85fa0e6821b99816
3
+ size 866662650
run-0/checkpoint-450/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ab80c9b99889eda685bfe2f60cadc52b3b0dda49d20b96c91ef6d8cbeacc2cd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edc5a4391b7a0bf956d9b303e80f47c2d9c175db13f6f3655c9ac11de1b1537
3
  size 14244
run-0/checkpoint-450/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f76cf881c9e186bef61e5f3c7d5e1b085f1a3e17fb05de26520bc3c85e8a4852
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10fc158db76c8f941e6026986d791697f9661c481151bb73e29a8fe812f9b06e
3
  size 1064
run-0/checkpoint-450/special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
run-0/checkpoint-450/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-450/tokenizer_config.json CHANGED
@@ -43,13 +43,17 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
 
 
54
  "unk_token": "[UNK]"
55
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
+ "max_length": 512,
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
+ "stride": 0,
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
  "unk_token": "[UNK]"
59
  }
run-0/checkpoint-450/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.5695,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-450",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 450,
7
  "is_hyper_param_search": true,
@@ -10,27 +10,18 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.555,
14
- "eval_loss": 0.6845093965530396,
15
- "eval_runtime": 2.8361,
16
- "eval_samples_per_second": 705.206,
17
- "eval_steps_per_second": 44.075,
18
- "step": 225
19
- },
20
- {
21
- "epoch": 2.0,
22
- "eval_accuracy": 0.5695,
23
- "eval_loss": 0.6817875504493713,
24
- "eval_runtime": 2.8164,
25
- "eval_samples_per_second": 710.12,
26
- "eval_steps_per_second": 44.383,
27
  "step": 450
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 675,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 3,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "TrainerControl": {
@@ -45,12 +36,12 @@
45
  }
46
  },
47
  "total_flos": 0,
48
- "train_batch_size": 8,
49
  "trial_name": null,
50
  "trial_params": {
51
- "learning_rate": 2.0067314527799928e-06,
52
- "num_train_epochs": 3,
53
- "per_device_train_batch_size": 8,
54
- "seed": 2
55
  }
56
  }
 
1
  {
2
+ "best_metric": 0.582,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-450",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 450,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.582,
14
+ "eval_loss": 0.6757144927978516,
15
+ "eval_runtime": 3.0923,
16
+ "eval_samples_per_second": 646.762,
17
+ "eval_steps_per_second": 40.423,
 
 
 
 
 
 
 
 
 
18
  "step": 450
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 1800,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
36
  }
37
  },
38
  "total_flos": 0,
39
+ "train_batch_size": 4,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "learning_rate": 6.1077174294517206e-06,
43
+ "num_train_epochs": 4,
44
+ "per_device_train_batch_size": 4,
45
+ "seed": 11
46
  }
47
  }
run-0/checkpoint-450/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b688ccd01fcc0f45d0941527d014913bbf2c71c953ca18588652a88cbf7ac1
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
3
  size 5176
run-0/checkpoint-450/vocab.txt CHANGED
The diff for this file is too large to render. See raw diff
 
runs/Aug01_13-39-40_1d376fbba8fb/events.out.tfevents.1722519626.1d376fbba8fb.194.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc74f0cf8d106e4c772f187aa552f4dfa51712c3090811509af3a2031c677db
3
+ size 5483
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,13 +43,17 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
 
 
54
  "unk_token": "[UNK]"
55
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
+ "max_length": 512,
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
+ "stride": 0,
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
  "unk_token": "[UNK]"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306a1f2e3e0a5644b71231cb5f1bf928bfa031e0dfefec97a7754c9f173d2b4d
3
  size 5176
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff