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
86bb356
·
verified ·
1 Parent(s): 21d46fd

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-3/checkpoint-900/config.json +27 -0
  3. run-3/checkpoint-900/model.safetensors +3 -0
  4. run-3/checkpoint-900/optimizer.pt +3 -0
  5. run-3/checkpoint-900/rng_state.pth +3 -0
  6. run-3/checkpoint-900/scheduler.pt +3 -0
  7. run-3/checkpoint-900/special_tokens_map.json +7 -0
  8. run-3/checkpoint-900/tokenizer.json +0 -0
  9. run-3/checkpoint-900/tokenizer_config.json +55 -0
  10. run-3/checkpoint-900/trainer_state.json +63 -0
  11. run-3/checkpoint-900/training_args.bin +3 -0
  12. run-3/checkpoint-900/vocab.txt +0 -0
  13. run-4/checkpoint-1350/config.json +27 -0
  14. run-4/checkpoint-1350/model.safetensors +3 -0
  15. run-4/checkpoint-1350/optimizer.pt +3 -0
  16. run-4/checkpoint-1350/rng_state.pth +3 -0
  17. run-4/checkpoint-1350/scheduler.pt +3 -0
  18. run-4/checkpoint-1350/special_tokens_map.json +7 -0
  19. run-4/checkpoint-1350/tokenizer.json +0 -0
  20. run-4/checkpoint-1350/tokenizer_config.json +55 -0
  21. run-4/checkpoint-1350/trainer_state.json +79 -0
  22. run-4/checkpoint-1350/training_args.bin +3 -0
  23. run-4/checkpoint-1350/vocab.txt +0 -0
  24. run-4/checkpoint-450/config.json +27 -0
  25. run-4/checkpoint-450/model.safetensors +3 -0
  26. run-4/checkpoint-450/optimizer.pt +3 -0
  27. run-4/checkpoint-450/rng_state.pth +3 -0
  28. run-4/checkpoint-450/scheduler.pt +3 -0
  29. run-4/checkpoint-450/special_tokens_map.json +7 -0
  30. run-4/checkpoint-450/tokenizer.json +0 -0
  31. run-4/checkpoint-450/tokenizer_config.json +55 -0
  32. run-4/checkpoint-450/trainer_state.json +47 -0
  33. run-4/checkpoint-450/training_args.bin +3 -0
  34. run-4/checkpoint-450/vocab.txt +0 -0
  35. run-4/checkpoint-900/config.json +27 -0
  36. run-4/checkpoint-900/model.safetensors +3 -0
  37. run-4/checkpoint-900/optimizer.pt +3 -0
  38. run-4/checkpoint-900/rng_state.pth +3 -0
  39. run-4/checkpoint-900/scheduler.pt +3 -0
  40. run-4/checkpoint-900/special_tokens_map.json +7 -0
  41. run-4/checkpoint-900/tokenizer.json +0 -0
  42. run-4/checkpoint-900/tokenizer_config.json +55 -0
  43. run-4/checkpoint-900/trainer_state.json +63 -0
  44. run-4/checkpoint-900/training_args.bin +3 -0
  45. run-4/checkpoint-900/vocab.txt +0 -0
  46. run-5/checkpoint-450/config.json +27 -0
  47. run-5/checkpoint-450/model.safetensors +3 -0
  48. run-5/checkpoint-450/optimizer.pt +3 -0
  49. run-5/checkpoint-450/rng_state.pth +3 -0
  50. run-5/checkpoint-450/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:945b9781174e8b046d951b895257feaa6224602efda82e41c8831dea491287cc
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e4e6ae8b1ca9bdc931a2d8554a74f46b3839d00b343c4000f415969883c706
3
  size 437958648
run-3/checkpoint-900/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-3/checkpoint-900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5ad91f987d77837e6abd3c64d1bc52d6d6cf969c86b312524fc9cc6f3b0257
3
+ size 437958648
run-3/checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cbb70a5c8c7e492f151e9622a444486c8656a13e3afc25b5cf49bbb1866923
3
+ size 876038394
run-3/checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f5d8f9a9907364a1d3fcfb26dc0ae91be13e6caebd35721bdd0cdca94f2658
3
+ size 14244
run-3/checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82532e943beb1b9bf73291ee98178bdab70e38d2c3066a598c3e2a8fb86369eb
3
+ size 1064
run-3/checkpoint-900/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-3/checkpoint-900/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-900/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-3/checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.612,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-3/checkpoint-900",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
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": 0.5665,
14
+ "eval_loss": 0.6800315976142883,
15
+ "eval_runtime": 2.7996,
16
+ "eval_samples_per_second": 714.379,
17
+ "eval_steps_per_second": 44.649,
18
+ "step": 450
19
+ },
20
+ {
21
+ "epoch": 1.1111111111111112,
22
+ "grad_norm": 5.086803436279297,
23
+ "learning_rate": 4.730310535704339e-06,
24
+ "loss": 0.6897,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.612,
30
+ "eval_loss": 0.6601560115814209,
31
+ "eval_runtime": 2.8804,
32
+ "eval_samples_per_second": 694.346,
33
+ "eval_steps_per_second": 43.397,
34
+ "step": 900
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 900,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 2,
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": true
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 56009765909760.0,
55
+ "train_batch_size": 4,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 1.0643198705334763e-05,
59
+ "num_train_epochs": 2,
60
+ "per_device_train_batch_size": 4,
61
+ "seed": 40
62
+ }
63
+ }
run-3/checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33deb3254b7f6b0e209c9a3065f25b9878a491b18bdc53659f5c169a748036df
3
+ size 5176
run-3/checkpoint-900/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1350/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-4/checkpoint-1350/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b038c9bfd4e4ba0b1a125201a4437bcf3679a490d501b928458f7a8a34a7b3
3
+ size 437958648
run-4/checkpoint-1350/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38304640285f4dd066357ce4727e140aa8cb52b53146ffe0007f268613ea4c21
3
+ size 876038394
run-4/checkpoint-1350/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78393630c458cac4955f1669a0c987c3d4bf66783739b0d83ccde20f94d562c
3
+ size 14308
run-4/checkpoint-1350/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bb97e2e7a5b2905e43c27a7a790d3ab60835f36d670fb2d9514c363b1473d1
3
+ size 1064
run-4/checkpoint-1350/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-4/checkpoint-1350/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1350/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-4/checkpoint-1350/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6045,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-4/checkpoint-1350",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1350,
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": 0.576,
14
+ "eval_loss": 0.6768154501914978,
15
+ "eval_runtime": 2.8181,
16
+ "eval_samples_per_second": 709.687,
17
+ "eval_steps_per_second": 44.355,
18
+ "step": 450
19
+ },
20
+ {
21
+ "epoch": 1.1111111111111112,
22
+ "grad_norm": 6.861545085906982,
23
+ "learning_rate": 1.0742562787853938e-06,
24
+ "loss": 0.6918,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.602,
30
+ "eval_loss": 0.6691796779632568,
31
+ "eval_runtime": 2.8924,
32
+ "eval_samples_per_second": 691.478,
33
+ "eval_steps_per_second": 43.217,
34
+ "step": 900
35
+ },
36
+ {
37
+ "epoch": 2.2222222222222223,
38
+ "grad_norm": 7.6592912673950195,
39
+ "learning_rate": 4.4234082067633854e-07,
40
+ "loss": 0.6718,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.6045,
46
+ "eval_loss": 0.6652487516403198,
47
+ "eval_runtime": 2.9908,
48
+ "eval_samples_per_second": 668.71,
49
+ "eval_steps_per_second": 41.794,
50
+ "step": 1350
51
+ }
52
+ ],
53
+ "logging_steps": 500,
54
+ "max_steps": 1350,
55
+ "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 3,
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": true
66
+ },
67
+ "attributes": {}
68
+ }
69
+ },
70
+ "total_flos": 113121309363840.0,
71
+ "train_batch_size": 4,
72
+ "trial_name": null,
73
+ "trial_params": {
74
+ "learning_rate": 1.7061717368944488e-06,
75
+ "num_train_epochs": 3,
76
+ "per_device_train_batch_size": 4,
77
+ "seed": 13
78
+ }
79
+ }
run-4/checkpoint-1350/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd39f4b07fc980b4ebc347974cc75277c20296d6e89cff9ddc35a1947cef0191
3
+ size 5176
run-4/checkpoint-1350/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-450/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-4/checkpoint-450/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa6f5fd6ef6b11c877eb0036eb006ad4e103b5c59c6933e06d5dd7e5f110006
3
+ size 437958648
run-4/checkpoint-450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6883daf864a6df955dddf3fe391960e1de4282c5787cfa35273a316bd355b38a
3
+ size 876038394
run-4/checkpoint-450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fd6d476497a719a62426042ba1ee662850bd8b79745b9f6ba9a55a19f9ad52
3
+ size 14308
run-4/checkpoint-450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62d2da4bc796b6cc8806558117d7cd3055d85b9e7fc8f99e2ee2088e5f7b76c
3
+ size 1064
run-4/checkpoint-450/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-4/checkpoint-450/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-450/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-4/checkpoint-450/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.576,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-4/checkpoint-450",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 450,
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": 0.576,
14
+ "eval_loss": 0.6768154501914978,
15
+ "eval_runtime": 2.8181,
16
+ "eval_samples_per_second": 709.687,
17
+ "eval_steps_per_second": 44.355,
18
+ "step": 450
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1350,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
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": 1.7061717368944488e-06,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 4,
45
+ "seed": 13
46
+ }
47
+ }
run-4/checkpoint-450/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd39f4b07fc980b4ebc347974cc75277c20296d6e89cff9ddc35a1947cef0191
3
+ size 5176
run-4/checkpoint-450/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-900/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-4/checkpoint-900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199371a8bf103627fdd0a1a2ff227e094f53146cfe8acc10bac18629fd7c684b
3
+ size 437958648
run-4/checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f052f82bfe4bc70c272b61477a506eed1ec770f4c27b2f779f253ffe43830b
3
+ size 876038394
run-4/checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165d68d546e09f7fa5b02c47999d4256964e48eef4cb9f87934250d28d9b45ac
3
+ size 14308
run-4/checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339579d2cca89a0b9ac10322dfeb001c3806c93f927c42ecd7c3c868599f0cd2
3
+ size 1064
run-4/checkpoint-900/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-4/checkpoint-900/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-900/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-4/checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.602,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-4/checkpoint-900",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
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": 0.576,
14
+ "eval_loss": 0.6768154501914978,
15
+ "eval_runtime": 2.8181,
16
+ "eval_samples_per_second": 709.687,
17
+ "eval_steps_per_second": 44.355,
18
+ "step": 450
19
+ },
20
+ {
21
+ "epoch": 1.1111111111111112,
22
+ "grad_norm": 6.861545085906982,
23
+ "learning_rate": 1.0742562787853938e-06,
24
+ "loss": 0.6918,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.602,
30
+ "eval_loss": 0.6691796779632568,
31
+ "eval_runtime": 2.8924,
32
+ "eval_samples_per_second": 691.478,
33
+ "eval_steps_per_second": 43.217,
34
+ "step": 900
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1350,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
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": 56073488118480.0,
55
+ "train_batch_size": 4,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 1.7061717368944488e-06,
59
+ "num_train_epochs": 3,
60
+ "per_device_train_batch_size": 4,
61
+ "seed": 13
62
+ }
63
+ }
run-4/checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd39f4b07fc980b4ebc347974cc75277c20296d6e89cff9ddc35a1947cef0191
3
+ size 5176
run-4/checkpoint-900/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-450/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-5/checkpoint-450/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e4e6ae8b1ca9bdc931a2d8554a74f46b3839d00b343c4000f415969883c706
3
+ size 437958648
run-5/checkpoint-450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59882dc8339ad01d226dfea1720c700810a4b20d0056d422b589cecd95192de
3
+ size 876038394
run-5/checkpoint-450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d17ce124898c63b2b7479de88abe5067f7531c60364f53ac16e8c5c69c3bb0
3
+ size 14308
run-5/checkpoint-450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bc52119d736b2b3f731ab795c2b157a37d1e9599930fa8ab2463fb3dc8045a
3
+ size 1064