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
d4eb8a9
·
verified ·
1 Parent(s): 3b9221c

Training in progress, epoch 3

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-9/checkpoint-114/config.json +27 -0
  3. run-9/checkpoint-114/model.safetensors +3 -0
  4. run-9/checkpoint-114/optimizer.pt +3 -0
  5. run-9/checkpoint-114/rng_state.pth +3 -0
  6. run-9/checkpoint-114/scheduler.pt +3 -0
  7. run-9/checkpoint-114/special_tokens_map.json +7 -0
  8. run-9/checkpoint-114/tokenizer.json +0 -0
  9. run-9/checkpoint-114/tokenizer_config.json +55 -0
  10. run-9/checkpoint-114/trainer_state.json +56 -0
  11. run-9/checkpoint-114/training_args.bin +3 -0
  12. run-9/checkpoint-114/vocab.txt +0 -0
  13. run-9/checkpoint-171/config.json +27 -0
  14. run-9/checkpoint-171/model.safetensors +3 -0
  15. run-9/checkpoint-171/optimizer.pt +3 -0
  16. run-9/checkpoint-171/rng_state.pth +3 -0
  17. run-9/checkpoint-171/scheduler.pt +3 -0
  18. run-9/checkpoint-171/special_tokens_map.json +7 -0
  19. run-9/checkpoint-171/tokenizer.json +0 -0
  20. run-9/checkpoint-171/tokenizer_config.json +55 -0
  21. run-9/checkpoint-171/trainer_state.json +65 -0
  22. run-9/checkpoint-171/training_args.bin +3 -0
  23. run-9/checkpoint-171/vocab.txt +0 -0
  24. run-9/checkpoint-228/config.json +27 -0
  25. run-9/checkpoint-228/model.safetensors +3 -0
  26. run-9/checkpoint-228/optimizer.pt +3 -0
  27. run-9/checkpoint-228/rng_state.pth +3 -0
  28. run-9/checkpoint-228/scheduler.pt +3 -0
  29. run-9/checkpoint-228/special_tokens_map.json +7 -0
  30. run-9/checkpoint-228/tokenizer.json +0 -0
  31. run-9/checkpoint-228/tokenizer_config.json +55 -0
  32. run-9/checkpoint-228/trainer_state.json +74 -0
  33. run-9/checkpoint-228/training_args.bin +3 -0
  34. run-9/checkpoint-228/vocab.txt +0 -0
  35. run-9/checkpoint-57/config.json +27 -0
  36. run-9/checkpoint-57/model.safetensors +3 -0
  37. run-9/checkpoint-57/optimizer.pt +3 -0
  38. run-9/checkpoint-57/rng_state.pth +3 -0
  39. run-9/checkpoint-57/scheduler.pt +3 -0
  40. run-9/checkpoint-57/special_tokens_map.json +7 -0
  41. run-9/checkpoint-57/tokenizer.json +0 -0
  42. run-9/checkpoint-57/tokenizer_config.json +55 -0
  43. run-9/checkpoint-57/trainer_state.json +47 -0
  44. run-9/checkpoint-57/training_args.bin +3 -0
  45. run-9/checkpoint-57/vocab.txt +0 -0
  46. runs/Jul31_20-26-08_3d6201a3fb09/events.out.tfevents.1722458213.3d6201a3fb09.1394.9 +3 -0
  47. runs/Jul31_20-26-08_3d6201a3fb09/events.out.tfevents.1722458319.3d6201a3fb09.1394.10 +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 sha256:772e065cedcef8a11eeb2c5f34ae541835ac21af4dc8e138bd083b116b833780
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5418a83fbe2cb26801b0fa0da68a2b582734a025be3ba1f7c0f615491f6a977
3
  size 437958648
run-9/checkpoint-114/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-9/checkpoint-114/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed21b8c2ff8e072742bccb29c146959ec22cb72ef262c76da7b0d3eddf4be62e
3
+ size 437958648
run-9/checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce663db7063a5f21758703260705209b7898f12e729d1586127ab716bc7dbe9d
3
+ size 876038394
run-9/checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722f6d2ec990fc243106011beeb98fd1fbbaca0f647fc068888cec549350cd91
3
+ size 14244
run-9/checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b371fcc5d5ac00e6eadaf7ecb572371179775c6ae53eb6b6208b19375aea808
3
+ size 1064
run-9/checkpoint-114/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-9/checkpoint-114/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-114/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-9/checkpoint-114/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6015,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-9/checkpoint-114",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 114,
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": 0.5925,
14
+ "eval_loss": 0.6679326295852661,
15
+ "eval_runtime": 2.8117,
16
+ "eval_samples_per_second": 711.306,
17
+ "eval_steps_per_second": 44.457,
18
+ "step": 57
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6015,
23
+ "eval_loss": 0.6574124693870544,
24
+ "eval_runtime": 2.8097,
25
+ "eval_samples_per_second": 711.819,
26
+ "eval_steps_per_second": 44.489,
27
+ "step": 114
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 228,
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": 1.782025059242242e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 32,
54
+ "seed": 15
55
+ }
56
+ }
run-9/checkpoint-114/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
+ size 5176
run-9/checkpoint-114/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-171/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-9/checkpoint-171/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ddea832e7af836f6def1d56dd7ec4dbeda0cc3ee90dc936d20bfa0f8d7f74d
3
+ size 437958648
run-9/checkpoint-171/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139cef6f1d6d0706f4d4f9094420b603a9e0dc43b8f1624a0ed6843389a4a027
3
+ size 876038394
run-9/checkpoint-171/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c0a03290c85f6a93a99e04e99f771fb2715e443c6ea7ca724b20d8f2a4f0e6
3
+ size 14244
run-9/checkpoint-171/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d60ddedfef4cfaf4dcc62b5c8c50178330cb81ebea36a792bd94e482c26742
3
+ size 1064
run-9/checkpoint-171/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-9/checkpoint-171/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-171/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-9/checkpoint-171/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6015,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-9/checkpoint-114",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 171,
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": 0.5925,
14
+ "eval_loss": 0.6679326295852661,
15
+ "eval_runtime": 2.8117,
16
+ "eval_samples_per_second": 711.306,
17
+ "eval_steps_per_second": 44.457,
18
+ "step": 57
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6015,
23
+ "eval_loss": 0.6574124693870544,
24
+ "eval_runtime": 2.8097,
25
+ "eval_samples_per_second": 711.819,
26
+ "eval_steps_per_second": 44.489,
27
+ "step": 114
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.6,
32
+ "eval_loss": 0.668912947177887,
33
+ "eval_runtime": 2.8048,
34
+ "eval_samples_per_second": 713.073,
35
+ "eval_steps_per_second": 44.567,
36
+ "step": 171
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 228,
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": 1.782025059242242e-05,
61
+ "num_train_epochs": 4,
62
+ "per_device_train_batch_size": 32,
63
+ "seed": 15
64
+ }
65
+ }
run-9/checkpoint-171/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
+ size 5176
run-9/checkpoint-171/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-228/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-9/checkpoint-228/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd222525e4422050abe8a3f5bb6280be8f415daab96ca904ea573857d7202e7d
3
+ size 437958648
run-9/checkpoint-228/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0842cfc7ab8e6ec78bd4752ad4f66b3048dd70ee45310361205312e9bc845a84
3
+ size 876038394
run-9/checkpoint-228/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22a397b737f79b554f60b7478b98c8d7a28c9548e945f6a07f9c4ff34eae03d
3
+ size 14244
run-9/checkpoint-228/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2882219f47b5513a88d70c1e356b057af5fd39fc12f5ab88a5185dd20e2669
3
+ size 1064
run-9/checkpoint-228/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-9/checkpoint-228/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-228/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-9/checkpoint-228/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.616,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-9/checkpoint-228",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 228,
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": 0.5925,
14
+ "eval_loss": 0.6679326295852661,
15
+ "eval_runtime": 2.8117,
16
+ "eval_samples_per_second": 711.306,
17
+ "eval_steps_per_second": 44.457,
18
+ "step": 57
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6015,
23
+ "eval_loss": 0.6574124693870544,
24
+ "eval_runtime": 2.8097,
25
+ "eval_samples_per_second": 711.819,
26
+ "eval_steps_per_second": 44.489,
27
+ "step": 114
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.6,
32
+ "eval_loss": 0.668912947177887,
33
+ "eval_runtime": 2.8048,
34
+ "eval_samples_per_second": 713.073,
35
+ "eval_steps_per_second": 44.567,
36
+ "step": 171
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.616,
41
+ "eval_loss": 0.679675281047821,
42
+ "eval_runtime": 2.8911,
43
+ "eval_samples_per_second": 691.785,
44
+ "eval_steps_per_second": 43.237,
45
+ "step": 228
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 228,
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": 1.782025059242242e-05,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 15
73
+ }
74
+ }
run-9/checkpoint-228/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
+ size 5176
run-9/checkpoint-228/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-57/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-9/checkpoint-57/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf93323c350b839100ff09b11510e885da3503a020244166ea79cca84854bb49
3
+ size 437958648
run-9/checkpoint-57/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44c320afd0118c50d9bf2b6fd0de091726f7f084e00abd6645818bd0873121d
3
+ size 876038394
run-9/checkpoint-57/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9d2c8aaadc11b9172006d06cd7e80ffee603969ec3e27d3c97c3b49bd8a474
3
+ size 14244
run-9/checkpoint-57/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb884cc948444c6d5172ec01743ed1653116160685dec64ae4ff8331af76d18
3
+ size 1064
run-9/checkpoint-57/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-9/checkpoint-57/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-57/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-9/checkpoint-57/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5925,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-9/checkpoint-57",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 57,
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": 0.5925,
14
+ "eval_loss": 0.6679326295852661,
15
+ "eval_runtime": 2.8117,
16
+ "eval_samples_per_second": 711.306,
17
+ "eval_steps_per_second": 44.457,
18
+ "step": 57
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 228,
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": 32,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.782025059242242e-05,
43
+ "num_train_epochs": 4,
44
+ "per_device_train_batch_size": 32,
45
+ "seed": 15
46
+ }
47
+ }
run-9/checkpoint-57/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
+ size 5176
run-9/checkpoint-57/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul31_20-26-08_3d6201a3fb09/events.out.tfevents.1722458213.3d6201a3fb09.1394.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8599b759acac78bb1167c09f84eae00ab66ec669f8ca79dfcb329d2ea086e2da
3
+ size 6557
runs/Jul31_20-26-08_3d6201a3fb09/events.out.tfevents.1722458319.3d6201a3fb09.1394.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aee9d3e65d6a32c3a5a69cb01bb997afce87a946bae3b2fe6d9089087ae50ca
3
+ size 6736
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d13cec178ad879084ed17138bc4c01348787c78c019f83a77fa8a5dd87442175
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41af2f26a14d5fc8872624c01f3b9e5e53a0d8cacea123564d9a339ce414456d
3
  size 5176