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
3d3da1a
·
verified ·
1 Parent(s): 6e1b233

Training in progress, epoch 1

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-138/config.json +27 -0
  3. run-7/checkpoint-138/model.safetensors +3 -0
  4. run-7/checkpoint-138/optimizer.pt +3 -0
  5. run-7/checkpoint-138/rng_state.pth +3 -0
  6. run-7/checkpoint-138/scheduler.pt +3 -0
  7. run-7/checkpoint-138/special_tokens_map.json +7 -0
  8. run-7/checkpoint-138/tokenizer.json +0 -0
  9. run-7/checkpoint-138/tokenizer_config.json +55 -0
  10. run-7/checkpoint-138/trainer_state.json +65 -0
  11. run-7/checkpoint-138/training_args.bin +3 -0
  12. run-7/checkpoint-138/vocab.txt +0 -0
  13. run-7/checkpoint-184/config.json +27 -0
  14. run-7/checkpoint-184/model.safetensors +3 -0
  15. run-7/checkpoint-184/optimizer.pt +3 -0
  16. run-7/checkpoint-184/rng_state.pth +3 -0
  17. run-7/checkpoint-184/scheduler.pt +3 -0
  18. run-7/checkpoint-184/special_tokens_map.json +7 -0
  19. run-7/checkpoint-184/tokenizer.json +0 -0
  20. run-7/checkpoint-184/tokenizer_config.json +55 -0
  21. run-7/checkpoint-184/trainer_state.json +74 -0
  22. run-7/checkpoint-184/training_args.bin +3 -0
  23. run-7/checkpoint-184/vocab.txt +0 -0
  24. run-7/checkpoint-92/config.json +27 -0
  25. run-7/checkpoint-92/model.safetensors +3 -0
  26. run-7/checkpoint-92/optimizer.pt +3 -0
  27. run-7/checkpoint-92/rng_state.pth +3 -0
  28. run-7/checkpoint-92/scheduler.pt +3 -0
  29. run-7/checkpoint-92/special_tokens_map.json +7 -0
  30. run-7/checkpoint-92/tokenizer.json +0 -0
  31. run-7/checkpoint-92/tokenizer_config.json +55 -0
  32. run-7/checkpoint-92/trainer_state.json +56 -0
  33. run-7/checkpoint-92/training_args.bin +3 -0
  34. run-7/checkpoint-92/vocab.txt +0 -0
  35. run-8/checkpoint-23/config.json +27 -0
  36. run-8/checkpoint-23/model.safetensors +3 -0
  37. run-8/checkpoint-23/optimizer.pt +3 -0
  38. run-8/checkpoint-23/rng_state.pth +3 -0
  39. run-8/checkpoint-23/scheduler.pt +3 -0
  40. run-8/checkpoint-23/special_tokens_map.json +7 -0
  41. run-8/checkpoint-23/tokenizer.json +0 -0
  42. run-8/checkpoint-23/tokenizer_config.json +55 -0
  43. run-8/checkpoint-23/trainer_state.json +47 -0
  44. run-8/checkpoint-23/training_args.bin +3 -0
  45. run-8/checkpoint-23/vocab.txt +0 -0
  46. runs/Jul31_19-18-04_20e4e50bc3c6/events.out.tfevents.1722454518.20e4e50bc3c6.1187.8 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80a3c9eb5f6212a91f1967d04c705eda0dede4c38b367aaae4bba305f7d03fe5
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6588a2357df415dcc3ef976d1fb3adfc02ef97df4f1b07792cd5b7e8e9fb71a9
3
  size 437958648
run-7/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-7/checkpoint-138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c03cdba8310fe7d38e78f90774f914509068335f94328343d8246ad578d255d
3
+ size 437958648
run-7/checkpoint-138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5389fb63e4e1fcdb6e34e29e01caa3656cb4e13ea189588ed0660d58983de92f
3
+ size 876038394
run-7/checkpoint-138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e92d8abbf9c05a4327b5b19dea76e57660e2bc0ba035c8e76c31ed5661276a9e
3
+ size 14308
run-7/checkpoint-138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624f6493d05a9cf2ad293c773700c7a78cdffd884d5c927ed38a04705707a916
3
+ size 1064
run-7/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-7/checkpoint-138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-138/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8305709023941068,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-7/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": 0.7839165131982812,
14
+ "eval_loss": 0.44573765993118286,
15
+ "eval_runtime": 1.5248,
16
+ "eval_samples_per_second": 1068.356,
17
+ "eval_steps_per_second": 66.895,
18
+ "step": 46
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4049816429615021,
24
+ "eval_runtime": 1.5307,
25
+ "eval_samples_per_second": 1064.206,
26
+ "eval_steps_per_second": 66.635,
27
+ "step": 92
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8305709023941068,
32
+ "eval_loss": 0.36977845430374146,
33
+ "eval_runtime": 1.5281,
34
+ "eval_samples_per_second": 1066.032,
35
+ "eval_steps_per_second": 66.75,
36
+ "step": 138
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 184,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
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": false
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 0,
57
+ "train_batch_size": 32,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 2.448709525953929e-05,
61
+ "num_train_epochs": 4,
62
+ "per_device_train_batch_size": 32,
63
+ "seed": 21
64
+ }
65
+ }
run-7/checkpoint-138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7783b64377581c270d4bf6ae57189eb09386ad289a71203380cd72e257c9a682
3
+ size 5176
run-7/checkpoint-138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-184/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-7/checkpoint-184/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770348fd8b1253de5a479d14ddd4bb1ce3bc917fb881aeb0c9e189cd214d6466
3
+ size 437958648
run-7/checkpoint-184/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7063058cd8d58576dd8cbe5348e8de13dfc195c4b9eacfc23d9a916dd1c4dc0b
3
+ size 876038394
run-7/checkpoint-184/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8bb9bde246d02b70bda4a225a6ccdb5bed7324dacfc3ed50db070926cf9c87
3
+ size 14308
run-7/checkpoint-184/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f7bc4fa9d630ccd56f888d0b282720d75d1e8d643c566818be703b8e6de47b
3
+ size 1064
run-7/checkpoint-184/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-7/checkpoint-184/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-184/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-7/checkpoint-184/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8367096378146102,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-7/checkpoint-184",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 184,
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": 0.7839165131982812,
14
+ "eval_loss": 0.44573765993118286,
15
+ "eval_runtime": 1.5248,
16
+ "eval_samples_per_second": 1068.356,
17
+ "eval_steps_per_second": 66.895,
18
+ "step": 46
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4049816429615021,
24
+ "eval_runtime": 1.5307,
25
+ "eval_samples_per_second": 1064.206,
26
+ "eval_steps_per_second": 66.635,
27
+ "step": 92
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8305709023941068,
32
+ "eval_loss": 0.36977845430374146,
33
+ "eval_runtime": 1.5281,
34
+ "eval_samples_per_second": 1066.032,
35
+ "eval_steps_per_second": 66.75,
36
+ "step": 138
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.8367096378146102,
41
+ "eval_loss": 0.38024526834487915,
42
+ "eval_runtime": 1.5933,
43
+ "eval_samples_per_second": 1022.426,
44
+ "eval_steps_per_second": 64.019,
45
+ "step": 184
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 184,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": true
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 2.448709525953929e-05,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 21
73
+ }
74
+ }
run-7/checkpoint-184/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7783b64377581c270d4bf6ae57189eb09386ad289a71203380cd72e257c9a682
3
+ size 5176
run-7/checkpoint-184/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-92/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e820a69d708af1b163298601b6a015ef1fe7e43e75099e76b9680dc69df233c
3
+ size 437958648
run-7/checkpoint-92/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309dd6e149e24d690e528e2696f84c13c924e62fa61de9f063306cc5a7925887
3
+ size 876038394
run-7/checkpoint-92/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f6e9481a4cbdf07df84c22c30ba3af9a25280ea47bb2a29404522a4f77a094
3
+ size 14308
run-7/checkpoint-92/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e565ea7fd8ef44eb7e399442146e38783a3382cae80d064113801df9dfdf5ff
3
+ size 1064
run-7/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-7/checkpoint-92/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-92/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8029465930018416,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-7/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": 0.7839165131982812,
14
+ "eval_loss": 0.44573765993118286,
15
+ "eval_runtime": 1.5248,
16
+ "eval_samples_per_second": 1068.356,
17
+ "eval_steps_per_second": 66.895,
18
+ "step": 46
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4049816429615021,
24
+ "eval_runtime": 1.5307,
25
+ "eval_samples_per_second": 1064.206,
26
+ "eval_steps_per_second": 66.635,
27
+ "step": 92
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 184,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
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": 2.448709525953929e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 32,
54
+ "seed": 21
55
+ }
56
+ }
run-7/checkpoint-92/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7783b64377581c270d4bf6ae57189eb09386ad289a71203380cd72e257c9a682
3
+ size 5176
run-7/checkpoint-92/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6588a2357df415dcc3ef976d1fb3adfc02ef97df4f1b07792cd5b7e8e9fb71a9
3
+ size 437958648
run-8/checkpoint-23/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c933e381d950205d84d856167dbb87e943394cd97051414df41ce88f47fae07
3
+ size 876038394
run-8/checkpoint-23/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a4be0b87d03d8e7b1b11941aa7437043f1a2d3708f55bc36ef304de36d452f
3
+ size 14244
run-8/checkpoint-23/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db4c97439609a5d811ef1e8b014882ad2206f1e09045c7004a7696f68284c57
3
+ size 1064
run-8/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-8/checkpoint-23/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-23/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5316144874155924,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-8/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": 0.5316144874155924,
14
+ "eval_loss": 0.6888889074325562,
15
+ "eval_runtime": 1.5784,
16
+ "eval_samples_per_second": 1032.038,
17
+ "eval_steps_per_second": 64.621,
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": 1.1397100287419585e-06,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 64,
45
+ "seed": 40
46
+ }
47
+ }
run-8/checkpoint-23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59777785a6c43276a6a0ab6419526423ade74aa5dec614892e554b03205be9c8
3
+ size 5176
run-8/checkpoint-23/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul31_19-18-04_20e4e50bc3c6/events.out.tfevents.1722454518.20e4e50bc3c6.1187.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a880b42f9486c65c88387433ea47a9f12c99999566db3cfe2f41b79f53e281
3
+ size 5592
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7783b64377581c270d4bf6ae57189eb09386ad289a71203380cd72e257c9a682
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59777785a6c43276a6a0ab6419526423ade74aa5dec614892e554b03205be9c8
3
  size 5176