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
b6a3ac2
·
verified ·
1 Parent(s): 3a2dba3

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-1101/config.json +27 -0
  3. run-6/checkpoint-1101/model.safetensors +3 -0
  4. run-6/checkpoint-1101/optimizer.pt +3 -0
  5. run-6/checkpoint-1101/rng_state.pth +3 -0
  6. run-6/checkpoint-1101/scheduler.pt +3 -0
  7. run-6/checkpoint-1101/special_tokens_map.json +37 -0
  8. run-6/checkpoint-1101/tokenizer.json +0 -0
  9. run-6/checkpoint-1101/tokenizer_config.json +59 -0
  10. run-6/checkpoint-1101/trainer_state.json +79 -0
  11. run-6/checkpoint-1101/training_args.bin +3 -0
  12. run-6/checkpoint-1101/vocab.txt +0 -0
  13. run-6/checkpoint-1468/config.json +27 -0
  14. run-6/checkpoint-1468/model.safetensors +3 -0
  15. run-6/checkpoint-1468/optimizer.pt +3 -0
  16. run-6/checkpoint-1468/rng_state.pth +3 -0
  17. run-6/checkpoint-1468/scheduler.pt +3 -0
  18. run-6/checkpoint-1468/special_tokens_map.json +37 -0
  19. run-6/checkpoint-1468/tokenizer.json +0 -0
  20. run-6/checkpoint-1468/tokenizer_config.json +59 -0
  21. run-6/checkpoint-1468/trainer_state.json +88 -0
  22. run-6/checkpoint-1468/training_args.bin +3 -0
  23. run-6/checkpoint-1468/vocab.txt +0 -0
  24. run-6/checkpoint-734/config.json +27 -0
  25. run-6/checkpoint-734/model.safetensors +3 -0
  26. run-6/checkpoint-734/optimizer.pt +3 -0
  27. run-6/checkpoint-734/rng_state.pth +3 -0
  28. run-6/checkpoint-734/scheduler.pt +3 -0
  29. run-6/checkpoint-734/special_tokens_map.json +37 -0
  30. run-6/checkpoint-734/tokenizer.json +0 -0
  31. run-6/checkpoint-734/tokenizer_config.json +59 -0
  32. run-6/checkpoint-734/trainer_state.json +63 -0
  33. run-6/checkpoint-734/training_args.bin +3 -0
  34. run-6/checkpoint-734/vocab.txt +0 -0
  35. run-8/checkpoint-367/config.json +27 -0
  36. run-8/checkpoint-367/model.safetensors +3 -0
  37. run-8/checkpoint-367/optimizer.pt +3 -0
  38. run-8/checkpoint-367/rng_state.pth +3 -0
  39. run-8/checkpoint-367/scheduler.pt +3 -0
  40. run-8/checkpoint-367/special_tokens_map.json +37 -0
  41. run-8/checkpoint-367/tokenizer.json +0 -0
  42. run-8/checkpoint-367/tokenizer_config.json +59 -0
  43. run-8/checkpoint-367/trainer_state.json +47 -0
  44. run-8/checkpoint-367/training_args.bin +3 -0
  45. run-8/checkpoint-367/vocab.txt +0 -0
  46. runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722523188.1d376fbba8fb.12065.10 +3 -0
  47. runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722523195.1d376fbba8fb.12065.11 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40275dd2836b8811ff18fba2a7bf39f1932ab41f679061e65d6bef13e0dac2d8
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17223b4c3a97ff55fd4af93e2c6eefab375250deee7a9b7a148bc39128e33aac
3
  size 433270768
run-6/checkpoint-1101/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-6/checkpoint-1101/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33be63f2f5bf318a3d8fd4cea00f6cc975bd15bb53ce25abb0efbfc1f9fee9b
3
+ size 433270768
run-6/checkpoint-1101/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb2b822abd3f6119f9abe6e248b269b45891f5f125e149454d100620b005191
3
+ size 866662650
run-6/checkpoint-1101/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb7b411c2d485c46884afb7921e5d6bf0a85322932642cfd1305eeba2303bdc
3
+ size 14244
run-6/checkpoint-1101/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef5200ba90904c2e9ce6293ec596bbcbc1aed450c5d4303b558cf7432fff075
3
+ size 1064
run-6/checkpoint-1101/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-6/checkpoint-1101/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1101/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-6/checkpoint-1101/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8631062001227747,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-6/checkpoint-734",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1101,
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": 0.8391651319828115,
14
+ "eval_loss": 0.43991297483444214,
15
+ "eval_runtime": 1.6123,
16
+ "eval_samples_per_second": 1010.376,
17
+ "eval_steps_per_second": 63.265,
18
+ "step": 367
19
+ },
20
+ {
21
+ "epoch": 1.3623978201634879,
22
+ "grad_norm": 0.4125554859638214,
23
+ "learning_rate": 1.2475826974915665e-05,
24
+ "loss": 0.4104,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.8631062001227747,
30
+ "eval_loss": 0.5845241546630859,
31
+ "eval_runtime": 1.6087,
32
+ "eval_samples_per_second": 1012.6,
33
+ "eval_steps_per_second": 63.404,
34
+ "step": 734
35
+ },
36
+ {
37
+ "epoch": 2.7247956403269757,
38
+ "grad_norm": 0.010006480850279331,
39
+ "learning_rate": 6.0317014713435245e-06,
40
+ "loss": 0.1537,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.8575813382443217,
46
+ "eval_loss": 0.7331406474113464,
47
+ "eval_runtime": 1.6329,
48
+ "eval_samples_per_second": 997.62,
49
+ "eval_steps_per_second": 62.466,
50
+ "step": 1101
51
+ }
52
+ ],
53
+ "logging_steps": 500,
54
+ "max_steps": 1468,
55
+ "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 4,
57
+ "save_steps": 500,
58
+ "stateful_callbacks": {
59
+ "TrainerControl": {
60
+ "args": {
61
+ "should_epoch_stop": false,
62
+ "should_evaluate": false,
63
+ "should_log": false,
64
+ "should_save": true,
65
+ "should_training_stop": false
66
+ },
67
+ "attributes": {}
68
+ }
69
+ },
70
+ "total_flos": 137761248587280.0,
71
+ "train_batch_size": 4,
72
+ "trial_name": null,
73
+ "trial_params": {
74
+ "learning_rate": 1.8919952478487808e-05,
75
+ "num_train_epochs": 4,
76
+ "per_device_train_batch_size": 4,
77
+ "seed": 36
78
+ }
79
+ }
run-6/checkpoint-1101/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e974703738cd1f415a4f4efc92c7381dd4a4a9a0bb16c4bf1c81a64e05f6b4
3
+ size 5176
run-6/checkpoint-1101/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1468/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-6/checkpoint-1468/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbd21cf279f3014f8a817028cc9cc889de9b9c3ff8104cde59a1bc3e57c7b70
3
+ size 433270768
run-6/checkpoint-1468/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311eea4fca70bbba5779ba0d5acda0002035d1edffbe18798a9a4af358c0f2a6
3
+ size 866662650
run-6/checkpoint-1468/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd45616dc62e17bcd5446e94c821099eb33db6a4b61277fec4e919c6fa2f12a
3
+ size 14244
run-6/checkpoint-1468/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761ea8408f78da6d3f15cec13177090af2cebc9d7a7e10d62a55c16995fadd7c
3
+ size 1064
run-6/checkpoint-1468/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-6/checkpoint-1468/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1468/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-6/checkpoint-1468/trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8680171884591774,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-6/checkpoint-1468",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1468,
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": 0.8391651319828115,
14
+ "eval_loss": 0.43991297483444214,
15
+ "eval_runtime": 1.6123,
16
+ "eval_samples_per_second": 1010.376,
17
+ "eval_steps_per_second": 63.265,
18
+ "step": 367
19
+ },
20
+ {
21
+ "epoch": 1.3623978201634879,
22
+ "grad_norm": 0.4125554859638214,
23
+ "learning_rate": 1.2475826974915665e-05,
24
+ "loss": 0.4104,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.8631062001227747,
30
+ "eval_loss": 0.5845241546630859,
31
+ "eval_runtime": 1.6087,
32
+ "eval_samples_per_second": 1012.6,
33
+ "eval_steps_per_second": 63.404,
34
+ "step": 734
35
+ },
36
+ {
37
+ "epoch": 2.7247956403269757,
38
+ "grad_norm": 0.010006480850279331,
39
+ "learning_rate": 6.0317014713435245e-06,
40
+ "loss": 0.1537,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.8575813382443217,
46
+ "eval_loss": 0.7331406474113464,
47
+ "eval_runtime": 1.6329,
48
+ "eval_samples_per_second": 997.62,
49
+ "eval_steps_per_second": 62.466,
50
+ "step": 1101
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.8680171884591774,
55
+ "eval_loss": 0.7264055013656616,
56
+ "eval_runtime": 1.6885,
57
+ "eval_samples_per_second": 964.744,
58
+ "eval_steps_per_second": 60.408,
59
+ "step": 1468
60
+ }
61
+ ],
62
+ "logging_steps": 500,
63
+ "max_steps": 1468,
64
+ "num_input_tokens_seen": 0,
65
+ "num_train_epochs": 4,
66
+ "save_steps": 500,
67
+ "stateful_callbacks": {
68
+ "TrainerControl": {
69
+ "args": {
70
+ "should_epoch_stop": false,
71
+ "should_evaluate": false,
72
+ "should_log": false,
73
+ "should_save": true,
74
+ "should_training_stop": true
75
+ },
76
+ "attributes": {}
77
+ }
78
+ },
79
+ "total_flos": 137761248587280.0,
80
+ "train_batch_size": 4,
81
+ "trial_name": null,
82
+ "trial_params": {
83
+ "learning_rate": 1.8919952478487808e-05,
84
+ "num_train_epochs": 4,
85
+ "per_device_train_batch_size": 4,
86
+ "seed": 36
87
+ }
88
+ }
run-6/checkpoint-1468/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e974703738cd1f415a4f4efc92c7381dd4a4a9a0bb16c4bf1c81a64e05f6b4
3
+ size 5176
run-6/checkpoint-1468/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-734/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-6/checkpoint-734/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56aa4d88af2613f79d9816341b96f1af24fd268ba0a3fb2e24e811a6f26c0fe5
3
+ size 433270768
run-6/checkpoint-734/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2206e670d57cf11e55afc1c8f15b5770de798c2fbbdbf236dec2df53db5869ed
3
+ size 866662650
run-6/checkpoint-734/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76877246b8dacd644ce64c9038d679db1b7b03480ba2f0f07865ade2c633e96f
3
+ size 14244
run-6/checkpoint-734/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991fbdfc77ea41a149d876fdcc4922730df148297e67e7efcb1f8b9b65b1fc38
3
+ size 1064
run-6/checkpoint-734/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-6/checkpoint-734/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-734/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-6/checkpoint-734/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8631062001227747,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-6/checkpoint-734",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 734,
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": 0.8391651319828115,
14
+ "eval_loss": 0.43991297483444214,
15
+ "eval_runtime": 1.6123,
16
+ "eval_samples_per_second": 1010.376,
17
+ "eval_steps_per_second": 63.265,
18
+ "step": 367
19
+ },
20
+ {
21
+ "epoch": 1.3623978201634879,
22
+ "grad_norm": 0.4125554859638214,
23
+ "learning_rate": 1.2475826974915665e-05,
24
+ "loss": 0.4104,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.8631062001227747,
30
+ "eval_loss": 0.5845241546630859,
31
+ "eval_runtime": 1.6087,
32
+ "eval_samples_per_second": 1012.6,
33
+ "eval_steps_per_second": 63.404,
34
+ "step": 734
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1468,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 4,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 93628480160880.0,
55
+ "train_batch_size": 4,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 1.8919952478487808e-05,
59
+ "num_train_epochs": 4,
60
+ "per_device_train_batch_size": 4,
61
+ "seed": 36
62
+ }
63
+ }
run-6/checkpoint-734/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e974703738cd1f415a4f4efc92c7381dd4a4a9a0bb16c4bf1c81a64e05f6b4
3
+ size 5176
run-6/checkpoint-734/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-367/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-8/checkpoint-367/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17223b4c3a97ff55fd4af93e2c6eefab375250deee7a9b7a148bc39128e33aac
3
+ size 433270768
run-8/checkpoint-367/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440099784d9412a82197b0e5a2bce52407782a1b3057e42b944870f51878edec
3
+ size 866662650
run-8/checkpoint-367/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40eb39e01f913e5fa7423045cb192f9c90b84f199876e17c79aca6af38dfc38c
3
+ size 14244
run-8/checkpoint-367/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635c53a18a833a2f1f12759336373675aedfc135309d53a2fdca8ae9d32c5f83
3
+ size 1064
run-8/checkpoint-367/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-8/checkpoint-367/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-367/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-8/checkpoint-367/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8023327194597912,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/checkpoint-367",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 367,
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": 0.8023327194597912,
14
+ "eval_loss": 0.44339078664779663,
15
+ "eval_runtime": 1.6033,
16
+ "eval_samples_per_second": 1016.045,
17
+ "eval_steps_per_second": 63.62,
18
+ "step": 367
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1468,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
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": 4,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 8.71284477294112e-06,
43
+ "num_train_epochs": 4,
44
+ "per_device_train_batch_size": 4,
45
+ "seed": 2
46
+ }
47
+ }
run-8/checkpoint-367/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256e398ac7345fdf4b30e008dd44ff8361fbc85422dda11a718e92bb3707fb34
3
+ size 5176
run-8/checkpoint-367/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722523188.1d376fbba8fb.12065.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b981ab87f723e0c723366e247303fc9da2be5aaadf722fc210d64593e7471cb
3
+ size 5266
runs/Aug01_14-25-19_1d376fbba8fb/events.out.tfevents.1722523195.1d376fbba8fb.12065.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4647f7e347014421ca16baa4f5863dee5dab9ad5b3cd560d199bafb25d461960
3
+ size 5803
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e974703738cd1f415a4f4efc92c7381dd4a4a9a0bb16c4bf1c81a64e05f6b4
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256e398ac7345fdf4b30e008dd44ff8361fbc85422dda11a718e92bb3707fb34
3
  size 5176