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
2df4513
·
verified ·
1 Parent(s): 29c2df1

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-138/config.json +27 -0
  3. run-0/checkpoint-138/model.safetensors +3 -0
  4. run-0/checkpoint-138/optimizer.pt +3 -0
  5. run-0/checkpoint-138/rng_state.pth +3 -0
  6. run-0/checkpoint-138/scheduler.pt +3 -0
  7. run-0/checkpoint-138/special_tokens_map.json +7 -0
  8. run-0/checkpoint-138/tokenizer.json +0 -0
  9. run-0/checkpoint-138/tokenizer_config.json +55 -0
  10. run-0/checkpoint-138/trainer_state.json +65 -0
  11. run-0/checkpoint-138/training_args.bin +3 -0
  12. run-0/checkpoint-138/vocab.txt +0 -0
  13. run-0/checkpoint-92/config.json +27 -0
  14. run-0/checkpoint-92/model.safetensors +3 -0
  15. run-0/checkpoint-92/optimizer.pt +3 -0
  16. run-0/checkpoint-92/rng_state.pth +3 -0
  17. run-0/checkpoint-92/scheduler.pt +3 -0
  18. run-0/checkpoint-92/special_tokens_map.json +7 -0
  19. run-0/checkpoint-92/tokenizer.json +0 -0
  20. run-0/checkpoint-92/tokenizer_config.json +55 -0
  21. run-0/checkpoint-92/trainer_state.json +56 -0
  22. run-0/checkpoint-92/training_args.bin +3 -0
  23. run-0/checkpoint-92/vocab.txt +0 -0
  24. run-1/checkpoint-115/config.json +27 -0
  25. run-1/checkpoint-115/model.safetensors +3 -0
  26. run-1/checkpoint-115/optimizer.pt +3 -0
  27. run-1/checkpoint-115/rng_state.pth +3 -0
  28. run-1/checkpoint-115/scheduler.pt +3 -0
  29. run-1/checkpoint-115/special_tokens_map.json +7 -0
  30. run-1/checkpoint-115/tokenizer.json +0 -0
  31. run-1/checkpoint-115/tokenizer_config.json +55 -0
  32. run-1/checkpoint-115/trainer_state.json +83 -0
  33. run-1/checkpoint-115/training_args.bin +3 -0
  34. run-1/checkpoint-115/vocab.txt +0 -0
  35. run-1/checkpoint-23/config.json +27 -0
  36. run-1/checkpoint-23/model.safetensors +3 -0
  37. run-1/checkpoint-23/optimizer.pt +3 -0
  38. run-1/checkpoint-23/rng_state.pth +3 -0
  39. run-1/checkpoint-23/scheduler.pt +3 -0
  40. run-1/checkpoint-23/special_tokens_map.json +7 -0
  41. run-1/checkpoint-23/tokenizer.json +0 -0
  42. run-1/checkpoint-23/tokenizer_config.json +55 -0
  43. run-1/checkpoint-23/trainer_state.json +47 -0
  44. run-1/checkpoint-23/training_args.bin +3 -0
  45. run-1/checkpoint-23/vocab.txt +0 -0
  46. run-1/checkpoint-46/config.json +2 -2
  47. run-1/checkpoint-46/model.safetensors +2 -2
  48. run-1/checkpoint-46/optimizer.pt +2 -2
  49. run-1/checkpoint-46/rng_state.pth +2 -2
  50. run-1/checkpoint-46/scheduler.pt +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0950bccb6e8f42ff8aaf183690786f4f587f3e867be81f34f2e747546f1f694
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a3600272e96e508d95cd7d0fd4b74d14a69bf837314e079cf130d77ecb3317
3
  size 437958648
run-0/checkpoint-138/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
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": 30522
27
+ }
run-0/checkpoint-138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbf8b7bb52b22fabaeff1fad1884fcb9fcbefc79c054ab5f513ba8dbb49de65
3
+ size 437958648
run-0/checkpoint-138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512fd546f75ddfaacc16badd6b502b618262232831aa7635939d990df20c4cf
3
+ size 876038394
run-0/checkpoint-138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8ecd154d55702ed68fc41ceef15cb10a21893a89828613680e414311fa1854
3
+ size 14308
run-0/checkpoint-138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4029d4852946489c5a724dd947a32439cf547712bf02327b54e8f09e18d217ad
3
+ size 1064
run-0/checkpoint-138/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-138/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ }
run-0/checkpoint-138/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6789441375076735,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-138",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 138,
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": 0.6187845303867403,
14
+ "eval_loss": 0.677045464515686,
15
+ "eval_runtime": 1.5174,
16
+ "eval_samples_per_second": 1073.531,
17
+ "eval_steps_per_second": 67.219,
18
+ "step": 46
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6642111724984653,
23
+ "eval_loss": 0.6484399437904358,
24
+ "eval_runtime": 1.475,
25
+ "eval_samples_per_second": 1104.382,
26
+ "eval_steps_per_second": 69.151,
27
+ "step": 92
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.6789441375076735,
32
+ "eval_loss": 0.6311272978782654,
33
+ "eval_runtime": 1.5486,
34
+ "eval_samples_per_second": 1051.891,
35
+ "eval_steps_per_second": 65.864,
36
+ "step": 138
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 138,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": true
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 0,
57
+ "train_batch_size": 32,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 2.2663564697926915e-06,
61
+ "num_train_epochs": 3,
62
+ "per_device_train_batch_size": 32,
63
+ "seed": 14
64
+ }
65
+ }
run-0/checkpoint-138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837929207f0b87e3e725511aaedbea183a5274d57f3b1b522598d3b04a5f07f3
3
+ size 5176
run-0/checkpoint-138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-92/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
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": 30522
27
+ }
run-0/checkpoint-92/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026ee48e0cf3df0d2bef65cc3c1807d8cafaa676d2d85937b5cd5364ee373b86
3
+ size 437958648
run-0/checkpoint-92/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0192798ed32647f48c44b20c85c5f19a33c6aea50695de9147cd29e9f60a5d7
3
+ size 876038394
run-0/checkpoint-92/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb4e9720d55f98334341af4c3b61159260bbef267c474db89d3c3c8dea14f5a
3
+ size 14308
run-0/checkpoint-92/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e80f81925f9d805c8ec1205135b1649c03f930eaa068b7b25681ba2bfc6fa6
3
+ size 1064
run-0/checkpoint-92/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-92/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-92/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ }
run-0/checkpoint-92/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6642111724984653,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-0/checkpoint-92",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 92,
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": 0.6187845303867403,
14
+ "eval_loss": 0.677045464515686,
15
+ "eval_runtime": 1.5174,
16
+ "eval_samples_per_second": 1073.531,
17
+ "eval_steps_per_second": 67.219,
18
+ "step": 46
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6642111724984653,
23
+ "eval_loss": 0.6484399437904358,
24
+ "eval_runtime": 1.475,
25
+ "eval_samples_per_second": 1104.382,
26
+ "eval_steps_per_second": 69.151,
27
+ "step": 92
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 138,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
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": 2.2663564697926915e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 32,
54
+ "seed": 14
55
+ }
56
+ }
run-0/checkpoint-92/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837929207f0b87e3e725511aaedbea183a5274d57f3b1b522598d3b04a5f07f3
3
+ size 5176
run-0/checkpoint-92/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-115/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
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": 30522
27
+ }
run-1/checkpoint-115/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e6fc5fe1da3684a3a006ea683bb96ed5863b38fdd49e6442c434ae74cf24da
3
+ size 437958648
run-1/checkpoint-115/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0c1124a2903d09bbce354ea2ac2b170be98000e57d38e53fa95efd3dd81ebb
3
+ size 876038394
run-1/checkpoint-115/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee419a7bbda5a4c1c2e5021a889b682984c20c35dcb9baf6728157769e86872
3
+ size 14308
run-1/checkpoint-115/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c2df8857b6a5107644eba751f3ebd133f3275664b8e32d47687421b2a44b08
3
+ size 1064
run-1/checkpoint-115/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-115/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-115/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ }
run-1/checkpoint-115/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.761817065684469,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/checkpoint-115",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 115,
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": 0.6642111724984653,
14
+ "eval_loss": 0.6271333694458008,
15
+ "eval_runtime": 1.4666,
16
+ "eval_samples_per_second": 1110.761,
17
+ "eval_steps_per_second": 69.55,
18
+ "step": 23
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7188459177409454,
23
+ "eval_loss": 0.5219240784645081,
24
+ "eval_runtime": 1.5,
25
+ "eval_samples_per_second": 1085.998,
26
+ "eval_steps_per_second": 68.0,
27
+ "step": 46
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7415592387968079,
32
+ "eval_loss": 0.47888997197151184,
33
+ "eval_runtime": 1.4904,
34
+ "eval_samples_per_second": 1092.984,
35
+ "eval_steps_per_second": 68.437,
36
+ "step": 69
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.7483118477593615,
41
+ "eval_loss": 0.4670851230621338,
42
+ "eval_runtime": 1.5143,
43
+ "eval_samples_per_second": 1075.722,
44
+ "eval_steps_per_second": 67.356,
45
+ "step": 92
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.761817065684469,
50
+ "eval_loss": 0.4600331485271454,
51
+ "eval_runtime": 1.5741,
52
+ "eval_samples_per_second": 1034.87,
53
+ "eval_steps_per_second": 64.799,
54
+ "step": 115
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 115,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "stateful_callbacks": {
63
+ "TrainerControl": {
64
+ "args": {
65
+ "should_epoch_stop": false,
66
+ "should_evaluate": false,
67
+ "should_log": false,
68
+ "should_save": true,
69
+ "should_training_stop": true
70
+ },
71
+ "attributes": {}
72
+ }
73
+ },
74
+ "total_flos": 0,
75
+ "train_batch_size": 64,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "learning_rate": 6.9782836266139365e-06,
79
+ "num_train_epochs": 5,
80
+ "per_device_train_batch_size": 64,
81
+ "seed": 14
82
+ }
83
+ }
run-1/checkpoint-115/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc052e058e0609700f4d71cef9b05f3a649bb73e2cb1fa9b826998feb955cce
3
+ size 5176
run-1/checkpoint-115/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-23/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
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": 30522
27
+ }
run-1/checkpoint-23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc1d1256baafc947da02e08de244f6ef734bb9d040a77a53b980f908f3b01ea
3
+ size 437958648
run-1/checkpoint-23/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ebe142b0f28c27a4b17f530c60b6118539865507e1bb9be63fdfb09428dd7c
3
+ size 876038394
run-1/checkpoint-23/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8adece8090459f26eab2fc804d4ef31922b8e56c6cf9a7588bab1f0364f48b33
3
+ size 14308
run-1/checkpoint-23/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee95a1c37f8ac4d9c53fe171baff3651d7f3b83675dbd8ad69cca835ca30f34b
3
+ size 1064
run-1/checkpoint-23/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-23/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-23/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ }
run-1/checkpoint-23/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6642111724984653,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-1/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": 0.6642111724984653,
14
+ "eval_loss": 0.6271333694458008,
15
+ "eval_runtime": 1.4666,
16
+ "eval_samples_per_second": 1110.761,
17
+ "eval_steps_per_second": 69.55,
18
+ "step": 23
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 115,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
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": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 64,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 6.9782836266139365e-06,
43
+ "num_train_epochs": 5,
44
+ "per_device_train_batch_size": 64,
45
+ "seed": 14
46
+ }
47
+ }
run-1/checkpoint-23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc052e058e0609700f4d71cef9b05f3a649bb73e2cb1fa9b826998feb955cce
3
+ size 5176
run-1/checkpoint-23/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-46/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "AIMH/mental-bert-base-cased",
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": 28996
27
  }
 
1
  {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
23
  "transformers_version": "4.42.4",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
+ "vocab_size": 30522
27
  }
run-1/checkpoint-46/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc917e584973edc749cf694c1228f611a6882a562c84dfbe1aff346e9cb16bcd
3
- size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4163412194623739457773b30f405c0e8b5f6414abe78bf60a38bd8cea092426
3
+ size 437958648
run-1/checkpoint-46/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f2217fb0fcd8060d966470a3c91c46cc7bf5c372277d447ed5fb517e2b69e0
3
- size 866662650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e533af6af1ce210e1fb52cf9ead6151c788ddd91459e191fbcf345fd9f02a9
3
+ size 876038394
run-1/checkpoint-46/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3741068fe73763fea3a5f64541b64a384c4ecbb4560207f9ece1de7c171e503e
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6908d76e4b94598f7d7d295f3110d78f44327859ae99e6f608f73aa224224364
3
+ size 14308
run-1/checkpoint-46/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0773ccd18bf9c6a00d48af6c1c6112e2af9a5be3524a5aa8341b6fa206346db9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e6c1efd917b07685110ab129135faf25a14970b3e6d6b6e96f57377e6f487f
3
  size 1064