Hugging Face's logo

Silicon23
/
BERTForDetectingDepression-Twitter2015

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
Silicon23 commited on
Commit
e55063f
·
verified ·
1 Parent(s): 2b9945d

Training in progress, epoch 1

Browse files
Files changed (32) hide show
  1. config.json +2 -2
  2. model.safetensors +2 -2
  3. run-0/checkpoint-23/config.json +27 -0
  4. run-0/checkpoint-23/model.safetensors +3 -0
  5. run-0/checkpoint-23/optimizer.pt +3 -0
  6. run-0/checkpoint-23/rng_state.pth +3 -0
  7. run-0/checkpoint-23/scheduler.pt +3 -0
  8. run-0/checkpoint-23/special_tokens_map.json +37 -0
  9. run-0/checkpoint-23/tokenizer.json +0 -0
  10. run-0/checkpoint-23/tokenizer_config.json +59 -0
  11. run-0/checkpoint-23/trainer_state.json +47 -0
  12. run-0/checkpoint-23/training_args.bin +3 -0
  13. run-0/checkpoint-23/vocab.txt +0 -0
  14. run-1/checkpoint-92/config.json +2 -2
  15. run-1/checkpoint-92/model.safetensors +2 -2
  16. run-1/checkpoint-92/optimizer.pt +2 -2
  17. run-1/checkpoint-92/rng_state.pth +1 -1
  18. run-1/checkpoint-92/scheduler.pt +1 -1
  19. run-1/checkpoint-92/special_tokens_map.json +35 -5
  20. run-1/checkpoint-92/tokenizer.json +0 -0
  21. run-1/checkpoint-92/tokenizer_config.json +5 -1
  22. run-1/checkpoint-92/trainer_state.json +14 -23
  23. run-1/checkpoint-92/training_args.bin +1 -1
  24. run-1/checkpoint-92/vocab.txt +0 -0
  25. runs/Aug01_14-23-36_1d376fbba8fb/events.out.tfevents.1722522232.1d376fbba8fb.12065.0 +3 -0
  26. runs/Aug01_14-23-36_1d376fbba8fb/events.out.tfevents.1722522292.1d376fbba8fb.12065.1 +3 -0
  27. runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722522324.1d376fbba8fb.12065.2 +3 -0
  28. special_tokens_map.json +35 -5
  29. tokenizer.json +0 -0
  30. tokenizer_config.json +5 -1
  31. training_args.bin +1 -1
  32. 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:f51ef4d9931eed37be9beb24204e61a46ad833fe3b5a84c33b187234804f804c
3
- size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:175bc5f89c8f6b787367a8eb9255faf97634bd8adbbde950558027de0248e7d6
3
+ size 433270768
run-0/checkpoint-23/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AIMH/mental-bert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.42.4",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 28996
27
+ }
run-0/checkpoint-23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:175bc5f89c8f6b787367a8eb9255faf97634bd8adbbde950558027de0248e7d6
3
+ size 433270768
run-0/checkpoint-23/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dfdb0be779ee13cfd2a30375b7188b942e5401885bc3460a4963cd03614878
3
+ size 866662650
run-0/checkpoint-23/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37dfbc1c2593b267a292fbb343d082be91174e7b80b89c08ae3d3300594b1e86
3
+ size 14308
run-0/checkpoint-23/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0fec12afbb20610873424058d821b38d0483631cb875077b1dd7b519ce8934
3
+ size 1064
run-0/checkpoint-23/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-23/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-23/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
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-23/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.525475751995089,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-23",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 23,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.525475751995089,
14
+ "eval_loss": 0.6831346750259399,
15
+ "eval_runtime": 1.6541,
16
+ "eval_samples_per_second": 984.849,
17
+ "eval_steps_per_second": 61.666,
18
+ "step": 23
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 23,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": true
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 64,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 3.972685894290409e-06,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 64,
45
+ "seed": 17
46
+ }
47
+ }
run-0/checkpoint-23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e7791cf264dcc32d2f75aa7b83ae7cb8a2e4c2fbc565e208845605f8b5f0e4
3
+ size 5176
run-0/checkpoint-23/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-92/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-1/checkpoint-92/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a58ff401b0a6ac92c0a36e5386e9a28dad2bfa8e01bb6735d9cc91fce120c1e
3
- size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1200a24fa95d2c4097d316e5de7703df1a739a4da386ebeb498fb4b86bb2b7f1
3
+ size 433270768
run-1/checkpoint-92/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f54c8905e4488cf709d79e0163e2b57a302405c8e29ee3d8b7c6ca4cfdc34d8
3
- size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e4714f136219272fb501d958b6884f3bb9bc1f03b17ef3230f3ac1b39fd59a
3
+ size 866662650
run-1/checkpoint-92/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a719b1c14c589622afee0d9e74e5489231b8c8fb494dd422104353b032842ef
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c999a3c4bba404b024e50b390313573258b5a709f9d500ddbc205a09d779b9d
3
  size 14308
run-1/checkpoint-92/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4acd9922aaa682d26d4671827a2910784eed72ab78e80513d77ef613c57977b6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8fb046a9051f39de470820b30f07e04955647f237f362b2653fc3e086f55f6
3
  size 1064
run-1/checkpoint-92/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-1/checkpoint-92/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-92/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-1/checkpoint-92/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.7397176181706568,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-92",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 92,
7
  "is_hyper_param_search": true,
@@ -10,27 +10,18 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7084100675260896,
14
- "eval_loss": 0.6070903539657593,
15
- "eval_runtime": 1.5313,
16
- "eval_samples_per_second": 1063.788,
17
- "eval_steps_per_second": 66.609,
18
- "step": 46
19
- },
20
- {
21
- "epoch": 2.0,
22
- "eval_accuracy": 0.7397176181706568,
23
- "eval_loss": 0.5197229981422424,
24
- "eval_runtime": 1.5355,
25
- "eval_samples_per_second": 1060.891,
26
- "eval_steps_per_second": 66.428,
27
  "step": 92
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 230,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 5,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "TrainerControl": {
@@ -39,18 +30,18 @@
39
  "should_evaluate": false,
40
  "should_log": false,
41
  "should_save": true,
42
- "should_training_stop": false
43
  },
44
  "attributes": {}
45
  }
46
  },
47
  "total_flos": 0,
48
- "train_batch_size": 32,
49
  "trial_name": null,
50
  "trial_params": {
51
- "learning_rate": 6.898987655729564e-06,
52
- "num_train_epochs": 5,
53
- "per_device_train_batch_size": 32,
54
  "seed": 13
55
  }
56
  }
 
1
  {
2
+ "best_metric": 0.8189073050951504,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-92",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 92,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.8189073050951504,
14
+ "eval_loss": 0.39196860790252686,
15
+ "eval_runtime": 1.6487,
16
+ "eval_samples_per_second": 988.048,
17
+ "eval_steps_per_second": 61.867,
 
 
 
 
 
 
 
 
 
18
  "step": 92
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 92,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
30
  "should_evaluate": false,
31
  "should_log": false,
32
  "should_save": true,
33
+ "should_training_stop": true
34
  },
35
  "attributes": {}
36
  }
37
  },
38
  "total_flos": 0,
39
+ "train_batch_size": 16,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "learning_rate": 3.6926081947441575e-05,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 16,
45
  "seed": 13
46
  }
47
  }
run-1/checkpoint-92/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8113b7e429ea470e612f76a7e7ca6fc50ba0ca9fa3adb882ab6eb707dee49d51
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a929f383b51f20462238e08db18e74c65921f45ef69b55f677f5bb0dfe9d9a7c
3
  size 5176
run-1/checkpoint-92/vocab.txt CHANGED
The diff for this file is too large to render. See raw diff
 
runs/Aug01_14-23-36_1d376fbba8fb/events.out.tfevents.1722522232.1d376fbba8fb.12065.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef08715b0ed76bb3b1ea3e16793355b01639970cb89d8c12f43fbafd6b529de
3
+ size 5615
runs/Aug01_14-23-36_1d376fbba8fb/events.out.tfevents.1722522292.1d376fbba8fb.12065.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f56268bb3eb904d2c9b4fd42f9af7844db937cd05125d7554702424fbcccdb
3
+ size 5615
runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722522324.1d376fbba8fb.12065.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454b1c3339bc5463aa827d856fb3400aa647ce5cdcabdf96bdf7acaa5b64ea1c
3
+ size 5614
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 sha256:6953bb502121efd86ce9d8c46092a717d268fd06e446053bb3ffed064847c354
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e7791cf264dcc32d2f75aa7b83ae7cb8a2e4c2fbc565e208845605f8b5f0e4
3
  size 5176
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff