Hugging Face's logo

CaffeineThief
/
cysecbert-ttp-bert-router

Safetensors
bert
Model card Files
xet
 Community
CaffeineThief commited on
Commit
a2f202e
·
verified ·
1 Parent(s): e67b090

Upload saved model files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-141/config.json +33 -0
  2. checkpoint-141/model.safetensors +3 -0
  3. checkpoint-141/optimizer.pt +3 -0
  4. checkpoint-141/rng_state.pth +3 -0
  5. checkpoint-141/scaler.pt +3 -0
  6. checkpoint-141/scheduler.pt +3 -0
  7. checkpoint-141/special_tokens_map.json +37 -0
  8. checkpoint-141/tokenizer.json +0 -0
  9. checkpoint-141/tokenizer_config.json +56 -0
  10. checkpoint-141/trainer_state.json +87 -0
  11. checkpoint-141/training_args.bin +3 -0
  12. checkpoint-141/vocab.txt +0 -0
  13. checkpoint-170/config.json +33 -0
  14. checkpoint-170/model.safetensors +3 -0
  15. checkpoint-170/optimizer.pt +3 -0
  16. checkpoint-170/rng_state.pth +3 -0
  17. checkpoint-170/scaler.pt +3 -0
  18. checkpoint-170/scheduler.pt +3 -0
  19. checkpoint-170/special_tokens_map.json +37 -0
  20. checkpoint-170/tokenizer.json +0 -0
  21. checkpoint-170/tokenizer_config.json +56 -0
  22. checkpoint-170/trainer_state.json +84 -0
  23. checkpoint-170/training_args.bin +3 -0
  24. checkpoint-170/vocab.txt +0 -0
  25. checkpoint-188/config.json +33 -0
  26. checkpoint-188/model.safetensors +3 -0
  27. checkpoint-188/optimizer.pt +3 -0
  28. checkpoint-188/rng_state.pth +3 -0
  29. checkpoint-188/scaler.pt +3 -0
  30. checkpoint-188/scheduler.pt +3 -0
  31. checkpoint-188/special_tokens_map.json +37 -0
  32. checkpoint-188/tokenizer.json +0 -0
  33. checkpoint-188/tokenizer_config.json +56 -0
  34. checkpoint-188/trainer_state.json +104 -0
  35. checkpoint-188/training_args.bin +3 -0
  36. checkpoint-188/vocab.txt +0 -0
  37. checkpoint-235/config.json +33 -0
  38. checkpoint-235/model.safetensors +3 -0
  39. checkpoint-235/optimizer.pt +3 -0
  40. checkpoint-235/rng_state.pth +3 -0
  41. checkpoint-235/scaler.pt +3 -0
  42. checkpoint-235/scheduler.pt +3 -0
  43. checkpoint-235/special_tokens_map.json +37 -0
  44. checkpoint-235/tokenizer.json +0 -0
  45. checkpoint-235/tokenizer_config.json +56 -0
  46. checkpoint-235/trainer_state.json +121 -0
  47. checkpoint-235/training_args.bin +3 -0
  48. checkpoint-235/vocab.txt +0 -0
  49. checkpoint-255/config.json +33 -0
  50. checkpoint-255/model.safetensors +3 -0
checkpoint-141/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "TRAM",
13
+ "1": "ANNOCTR"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "ANNOCTR": 1,
19
+ "TRAM": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
checkpoint-141/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db63af3e573bdbfe2715cf982cd9754a5353fbeedcd163802a1da4404cf99103
3
+ size 437958648
checkpoint-141/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b824a7da942e84fd7c8603c1a30ab34d59673b4547d77a264c78e068e86f6252
3
+ size 876038330
checkpoint-141/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d3c155bb3fb6994950ef7556da4ab88a9d77de972073b4673fa4ca32ceba95
3
+ size 14244
checkpoint-141/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
3
+ size 988
checkpoint-141/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad952416cc9c4deaf0488ff0c747c00c0816e25082ec6ed973542521c8b2d69
3
+ size 1064
checkpoint-141/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
+ }
checkpoint-141/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-141/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-141/trainer_state.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 141,
3
+ "best_metric": 0.8939393939393939,
4
+ "best_model_checkpoint": "./cysecbert-ttp-bert-router/checkpoint-141",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 141,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8790322580645161,
15
+ "eval_f1": 0.88,
16
+ "eval_loss": 0.23156200349330902,
17
+ "eval_runtime": 0.5457,
18
+ "eval_samples_per_second": 454.439,
19
+ "eval_steps_per_second": 10.994,
20
+ "step": 47
21
+ },
22
+ {
23
+ "epoch": 1.0638297872340425,
24
+ "grad_norm": 244324.0,
25
+ "learning_rate": 1.5829787234042555e-05,
26
+ "loss": 0.393,
27
+ "step": 50
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8870967741935484,
32
+ "eval_f1": 0.889763779527559,
33
+ "eval_loss": 0.24126584827899933,
34
+ "eval_runtime": 0.5406,
35
+ "eval_samples_per_second": 458.709,
36
+ "eval_steps_per_second": 11.098,
37
+ "step": 94
38
+ },
39
+ {
40
+ "epoch": 2.127659574468085,
41
+ "grad_norm": 360389.59375,
42
+ "learning_rate": 1.1574468085106382e-05,
43
+ "loss": 0.2003,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8870967741935484,
49
+ "eval_f1": 0.8939393939393939,
50
+ "eval_loss": 0.2832604646682739,
51
+ "eval_runtime": 0.5564,
52
+ "eval_samples_per_second": 445.721,
53
+ "eval_steps_per_second": 10.784,
54
+ "step": 141
55
+ }
56
+ ],
57
+ "logging_steps": 50,
58
+ "max_steps": 235,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "stateful_callbacks": {
63
+ "EarlyStoppingCallback": {
64
+ "args": {
65
+ "early_stopping_patience": 2,
66
+ "early_stopping_threshold": 0.0
67
+ },
68
+ "attributes": {
69
+ "early_stopping_patience_counter": 0
70
+ }
71
+ },
72
+ "TrainerControl": {
73
+ "args": {
74
+ "should_epoch_stop": false,
75
+ "should_evaluate": false,
76
+ "should_log": false,
77
+ "should_save": true,
78
+ "should_training_stop": false
79
+ },
80
+ "attributes": {}
81
+ }
82
+ },
83
+ "total_flos": 1752319628697600.0,
84
+ "train_batch_size": 48,
85
+ "trial_name": null,
86
+ "trial_params": null
87
+ }
checkpoint-141/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4f68038d34e18bca323801ebee2f977ae0e2c8a6e6a48bf186f9aaacac3db0
3
+ size 5368
checkpoint-141/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-170/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "TRAM",
13
+ "1": "ANNOCTR"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "ANNOCTR": 1,
19
+ "TRAM": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
checkpoint-170/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e180718fb1484ebd30e7d2d1562bbf3fea53e0edcc435064f32e1dd03e0204
3
+ size 437958648
checkpoint-170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb0901e08072ef968b5eec4bcb9fd6532eb0a912af90912064a775d1f00cad8
3
+ size 876038330
checkpoint-170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4efe0f47241e6fc27a6d35b15954af11bc2804162f8a5fa82aaf9fe783c305f
3
+ size 14244
checkpoint-170/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
3
+ size 988
checkpoint-170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ca867b5f07a5b0020195342eac2eb6841947051fea59ed1d774eee72ba43ae
3
+ size 1064
checkpoint-170/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
+ }
checkpoint-170/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-170/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-170/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 170,
3
+ "best_metric": 0.8,
4
+ "best_model_checkpoint": "./cysecbert-ttp-bert-router/checkpoint-170",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 170,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5882352941176471,
14
+ "grad_norm": 195774.109375,
15
+ "learning_rate": 1.7694117647058826e-05,
16
+ "loss": 0.4698,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8463251670378619,
22
+ "eval_f1": 0.7661016949152543,
23
+ "eval_loss": 0.29931211471557617,
24
+ "eval_runtime": 0.9434,
25
+ "eval_samples_per_second": 475.961,
26
+ "eval_steps_per_second": 10.6,
27
+ "step": 85
28
+ },
29
+ {
30
+ "epoch": 1.1764705882352942,
31
+ "grad_norm": 215225.09375,
32
+ "learning_rate": 1.5341176470588238e-05,
33
+ "loss": 0.299,
34
+ "step": 100
35
+ },
36
+ {
37
+ "epoch": 1.7647058823529411,
38
+ "grad_norm": 529117.0625,
39
+ "learning_rate": 1.2988235294117649e-05,
40
+ "loss": 0.2068,
41
+ "step": 150
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.8775055679287305,
46
+ "eval_f1": 0.8,
47
+ "eval_loss": 0.24925704300403595,
48
+ "eval_runtime": 0.926,
49
+ "eval_samples_per_second": 484.876,
50
+ "eval_steps_per_second": 10.799,
51
+ "step": 170
52
+ }
53
+ ],
54
+ "logging_steps": 50,
55
+ "max_steps": 425,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "stateful_callbacks": {
60
+ "EarlyStoppingCallback": {
61
+ "args": {
62
+ "early_stopping_patience": 2,
63
+ "early_stopping_threshold": 0.0
64
+ },
65
+ "attributes": {
66
+ "early_stopping_patience_counter": 0
67
+ }
68
+ },
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": false
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 2124358660976640.0,
81
+ "train_batch_size": 48,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb49e4ddefef59ed0e951ac7dbde7059171d7f9b6de6437c5177c6ce38bcc3d
3
+ size 5368
checkpoint-170/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-188/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "TRAM",
13
+ "1": "ANNOCTR"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "ANNOCTR": 1,
19
+ "TRAM": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
checkpoint-188/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52329fd83f15c93b643df934cee4acb8bf39b7474468dfd511e573ccfdab3b64
3
+ size 437958648
checkpoint-188/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec8f1ee5a63f04b2ef14be5995968f39d58b110e97e578bb5505bbfff2c86ac
3
+ size 876038330
checkpoint-188/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2364fa4dc0aceb9687fc6bcfc81d0cbcf0a4e9e920964e68971cafa1f7395554
3
+ size 14244
checkpoint-188/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
3
+ size 988
checkpoint-188/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24540af78f05e096d4d2f1a22a5efa5aa30308c905b0ca3d67079dece6935d90
3
+ size 1064
checkpoint-188/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
+ }
checkpoint-188/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-188/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-188/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 141,
3
+ "best_metric": 0.8939393939393939,
4
+ "best_model_checkpoint": "./cysecbert-ttp-bert-router/checkpoint-141",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 188,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8790322580645161,
15
+ "eval_f1": 0.88,
16
+ "eval_loss": 0.23156200349330902,
17
+ "eval_runtime": 0.5457,
18
+ "eval_samples_per_second": 454.439,
19
+ "eval_steps_per_second": 10.994,
20
+ "step": 47
21
+ },
22
+ {
23
+ "epoch": 1.0638297872340425,
24
+ "grad_norm": 244324.0,
25
+ "learning_rate": 1.5829787234042555e-05,
26
+ "loss": 0.393,
27
+ "step": 50
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8870967741935484,
32
+ "eval_f1": 0.889763779527559,
33
+ "eval_loss": 0.24126584827899933,
34
+ "eval_runtime": 0.5406,
35
+ "eval_samples_per_second": 458.709,
36
+ "eval_steps_per_second": 11.098,
37
+ "step": 94
38
+ },
39
+ {
40
+ "epoch": 2.127659574468085,
41
+ "grad_norm": 360389.59375,
42
+ "learning_rate": 1.1574468085106382e-05,
43
+ "loss": 0.2003,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8870967741935484,
49
+ "eval_f1": 0.8939393939393939,
50
+ "eval_loss": 0.2832604646682739,
51
+ "eval_runtime": 0.5564,
52
+ "eval_samples_per_second": 445.721,
53
+ "eval_steps_per_second": 10.784,
54
+ "step": 141
55
+ },
56
+ {
57
+ "epoch": 3.1914893617021276,
58
+ "grad_norm": 309358.59375,
59
+ "learning_rate": 7.3191489361702125e-06,
60
+ "loss": 0.1351,
61
+ "step": 150
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "eval_accuracy": 0.8951612903225806,
66
+ "eval_f1": 0.8916666666666667,
67
+ "eval_loss": 0.2920267879962921,
68
+ "eval_runtime": 0.5436,
69
+ "eval_samples_per_second": 456.231,
70
+ "eval_steps_per_second": 11.038,
71
+ "step": 188
72
+ }
73
+ ],
74
+ "logging_steps": 50,
75
+ "max_steps": 235,
76
+ "num_input_tokens_seen": 0,
77
+ "num_train_epochs": 5,
78
+ "save_steps": 500,
79
+ "stateful_callbacks": {
80
+ "EarlyStoppingCallback": {
81
+ "args": {
82
+ "early_stopping_patience": 2,
83
+ "early_stopping_threshold": 0.0
84
+ },
85
+ "attributes": {
86
+ "early_stopping_patience_counter": 1
87
+ }
88
+ },
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 2336426171596800.0,
101
+ "train_batch_size": 48,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-188/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4f68038d34e18bca323801ebee2f977ae0e2c8a6e6a48bf186f9aaacac3db0
3
+ size 5368
checkpoint-188/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-235/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "TRAM",
13
+ "1": "ANNOCTR"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "ANNOCTR": 1,
19
+ "TRAM": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
checkpoint-235/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d8653d3afdb0baffe9cf4b45d2b823f40e7fde26c7e595e299c80967a1a2ba
3
+ size 437958648
checkpoint-235/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8757b126ab16096195c84c83037cce70a5e86f824cd0aebbac4474310b12e4
3
+ size 876038330
checkpoint-235/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f3152f72695410ca19230d791ca8e0b8bcaa727c6000020d57ae4a51439b97
3
+ size 14244
checkpoint-235/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
3
+ size 988
checkpoint-235/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83526710ecacebf5cbd106052ec21d8ce799f8bdf2ac8c540d73190260bb6224
3
+ size 1064
checkpoint-235/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
+ }
checkpoint-235/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-235/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-235/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 141,
3
+ "best_metric": 0.8939393939393939,
4
+ "best_model_checkpoint": "./cysecbert-ttp-bert-router/checkpoint-141",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 235,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8790322580645161,
15
+ "eval_f1": 0.88,
16
+ "eval_loss": 0.23156200349330902,
17
+ "eval_runtime": 0.5457,
18
+ "eval_samples_per_second": 454.439,
19
+ "eval_steps_per_second": 10.994,
20
+ "step": 47
21
+ },
22
+ {
23
+ "epoch": 1.0638297872340425,
24
+ "grad_norm": 244324.0,
25
+ "learning_rate": 1.5829787234042555e-05,
26
+ "loss": 0.393,
27
+ "step": 50
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8870967741935484,
32
+ "eval_f1": 0.889763779527559,
33
+ "eval_loss": 0.24126584827899933,
34
+ "eval_runtime": 0.5406,
35
+ "eval_samples_per_second": 458.709,
36
+ "eval_steps_per_second": 11.098,
37
+ "step": 94
38
+ },
39
+ {
40
+ "epoch": 2.127659574468085,
41
+ "grad_norm": 360389.59375,
42
+ "learning_rate": 1.1574468085106382e-05,
43
+ "loss": 0.2003,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8870967741935484,
49
+ "eval_f1": 0.8939393939393939,
50
+ "eval_loss": 0.2832604646682739,
51
+ "eval_runtime": 0.5564,
52
+ "eval_samples_per_second": 445.721,
53
+ "eval_steps_per_second": 10.784,
54
+ "step": 141
55
+ },
56
+ {
57
+ "epoch": 3.1914893617021276,
58
+ "grad_norm": 309358.59375,
59
+ "learning_rate": 7.3191489361702125e-06,
60
+ "loss": 0.1351,
61
+ "step": 150
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "eval_accuracy": 0.8951612903225806,
66
+ "eval_f1": 0.8916666666666667,
67
+ "eval_loss": 0.2920267879962921,
68
+ "eval_runtime": 0.5436,
69
+ "eval_samples_per_second": 456.231,
70
+ "eval_steps_per_second": 11.038,
71
+ "step": 188
72
+ },
73
+ {
74
+ "epoch": 4.25531914893617,
75
+ "grad_norm": 91590.8125,
76
+ "learning_rate": 3.0638297872340428e-06,
77
+ "loss": 0.0876,
78
+ "step": 200
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.8911290322580645,
83
+ "eval_f1": 0.889795918367347,
84
+ "eval_loss": 0.3170631229877472,
85
+ "eval_runtime": 0.5567,
86
+ "eval_samples_per_second": 445.496,
87
+ "eval_steps_per_second": 10.778,
88
+ "step": 235
89
+ }
90
+ ],
91
+ "logging_steps": 50,
92
+ "max_steps": 235,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 5,
95
+ "save_steps": 500,
96
+ "stateful_callbacks": {
97
+ "EarlyStoppingCallback": {
98
+ "args": {
99
+ "early_stopping_patience": 2,
100
+ "early_stopping_threshold": 0.0
101
+ },
102
+ "attributes": {
103
+ "early_stopping_patience_counter": 2
104
+ }
105
+ },
106
+ "TrainerControl": {
107
+ "args": {
108
+ "should_epoch_stop": false,
109
+ "should_evaluate": false,
110
+ "should_log": false,
111
+ "should_save": true,
112
+ "should_training_stop": true
113
+ },
114
+ "attributes": {}
115
+ }
116
+ },
117
+ "total_flos": 2920532714496000.0,
118
+ "train_batch_size": 48,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
checkpoint-235/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4f68038d34e18bca323801ebee2f977ae0e2c8a6e6a48bf186f9aaacac3db0
3
+ size 5368
checkpoint-235/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-255/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "TRAM",
13
+ "1": "ANNOCTR"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "ANNOCTR": 1,
19
+ "TRAM": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
checkpoint-255/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8c1b24ecd20fdc0656aaa66a2bc6e83aefda5900ce07154dd22df8f4485a25
3
+ size 437958648