Hugging Face's logo

thomaslim6793
/
indra_bert_negation_detector

Safetensors
bert
Model card Files
xet
 Community
thomaslim6793 commited on
Commit
3850a2f
·
verified ·
1 Parent(s): ce6927d

Update two-step negation detector

Browse files
Files changed (38) hide show
  1. config.json +25 -0
  2. cue_checkpoint/checkpoint-432/config.json +25 -0
  3. cue_checkpoint/checkpoint-432/model.safetensors +3 -0
  4. cue_checkpoint/checkpoint-432/optimizer.pt +3 -0
  5. cue_checkpoint/checkpoint-432/rng_state.pth +3 -0
  6. cue_checkpoint/checkpoint-432/scheduler.pt +3 -0
  7. cue_checkpoint/checkpoint-432/special_tokens_map.json +7 -0
  8. cue_checkpoint/checkpoint-432/tokenizer.json +0 -0
  9. cue_checkpoint/checkpoint-432/tokenizer_config.json +58 -0
  10. cue_checkpoint/checkpoint-432/trainer_state.json +76 -0
  11. cue_checkpoint/checkpoint-432/training_args.bin +3 -0
  12. cue_checkpoint/checkpoint-432/vocab.txt +0 -0
  13. cue_checkpoint/config.json +25 -0
  14. cue_checkpoint/model.safetensors +3 -0
  15. cue_checkpoint/special_tokens_map.json +7 -0
  16. cue_checkpoint/tokenizer.json +0 -0
  17. cue_checkpoint/tokenizer_config.json +58 -0
  18. cue_checkpoint/training_args.bin +3 -0
  19. cue_checkpoint/vocab.txt +0 -0
  20. cue_label2id.json +1 -0
  21. model.safetensors +3 -0
  22. scope_checkpoint/checkpoint-232/config.json +25 -0
  23. scope_checkpoint/checkpoint-232/model.safetensors +3 -0
  24. scope_checkpoint/checkpoint-232/optimizer.pt +3 -0
  25. scope_checkpoint/checkpoint-232/rng_state.pth +3 -0
  26. scope_checkpoint/checkpoint-232/scheduler.pt +3 -0
  27. scope_checkpoint/checkpoint-232/special_tokens_map.json +7 -0
  28. scope_checkpoint/checkpoint-232/tokenizer.json +0 -0
  29. scope_checkpoint/checkpoint-232/tokenizer_config.json +58 -0
  30. scope_checkpoint/checkpoint-232/trainer_state.json +57 -0
  31. scope_checkpoint/checkpoint-232/training_args.bin +3 -0
  32. scope_checkpoint/checkpoint-232/vocab.txt +0 -0
  33. special_tokens_map.json +7 -0
  34. test_eval_results_20251117_190113.txt +27 -0
  35. tokenizer.json +0 -0
  36. tokenizer_config.json +58 -0
  37. training_args.bin +3 -0
  38. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NegationDetectorModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cue_num_labels": 3,
8
+ "dtype": "float32",
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
+ "transformers_version": "4.56.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 28895
25
+ }
cue_checkpoint/checkpoint-432/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NegationDetectorModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cue_num_labels": 3,
8
+ "dtype": "float32",
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
+ "transformers_version": "4.56.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 28895
25
+ }
cue_checkpoint/checkpoint-432/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2679e4540f782737fd5476f09ad7af5d20c38fefc00fc8b89804e9a074d8fac
3
+ size 434543084
cue_checkpoint/checkpoint-432/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d736be481ecc110e30e85048f80e3a3262d774ecbc101b5d306d57033e9ab998
3
+ size 861325067
cue_checkpoint/checkpoint-432/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6880baee9eb659fce03cdadebcd9aa687fe98820ceac79edb3919a05800ba662
3
+ size 14645
cue_checkpoint/checkpoint-432/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7135b546e3b6fefbcc5af944f4b35405e96330785f4884dec78ac66b830da07
3
+ size 1465
cue_checkpoint/checkpoint-432/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
+ }
cue_checkpoint/checkpoint-432/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cue_checkpoint/checkpoint-432/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
cue_checkpoint/checkpoint-432/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 432,
3
+ "best_metric": 0.9311827906841024,
4
+ "best_model_checkpoint": "output/negation_detector/cue_checkpoint/checkpoint-432",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 432,
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
+ "grad_norm": 0.14013254642486572,
15
+ "learning_rate": 1.800925925925926e-05,
16
+ "loss": 0.0356,
17
+ "step": 216
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_cue_FN": 25,
22
+ "eval_cue_FP": 48,
23
+ "eval_cue_TP": 425,
24
+ "eval_cue_f1": 0.9209100708228034,
25
+ "eval_cue_precision": 0.8985200845476,
26
+ "eval_cue_recall": 0.9444444444234568,
27
+ "eval_loss": 0.01801697537302971,
28
+ "eval_runtime": 0.2711,
29
+ "eval_samples_per_second": 1586.253,
30
+ "eval_steps_per_second": 99.602,
31
+ "step": 216
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 0.08337937295436859,
36
+ "learning_rate": 1.600925925925926e-05,
37
+ "loss": 0.0117,
38
+ "step": 432
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_cue_FN": 17,
43
+ "eval_cue_FP": 47,
44
+ "eval_cue_TP": 433,
45
+ "eval_cue_f1": 0.9311827906841024,
46
+ "eval_cue_precision": 0.9020833333145399,
47
+ "eval_cue_recall": 0.9622222222008395,
48
+ "eval_loss": 0.014065760187804699,
49
+ "eval_runtime": 0.2698,
50
+ "eval_samples_per_second": 1593.576,
51
+ "eval_steps_per_second": 100.062,
52
+ "step": 432
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 2160,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 10,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": false
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 254669583358320.0,
73
+ "train_batch_size": 16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
cue_checkpoint/checkpoint-432/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f17cd8c06bcf00dd4da7f408102435eaa0d97675641a6a61824cbdadddabf4
3
+ size 5777
cue_checkpoint/checkpoint-432/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
cue_checkpoint/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NegationDetectorModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cue_num_labels": 3,
8
+ "dtype": "float32",
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
+ "transformers_version": "4.56.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 28895
25
+ }
cue_checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2679e4540f782737fd5476f09ad7af5d20c38fefc00fc8b89804e9a074d8fac
3
+ size 434543084
cue_checkpoint/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
+ }
cue_checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cue_checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
cue_checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f17cd8c06bcf00dd4da7f408102435eaa0d97675641a6a61824cbdadddabf4
3
+ size 5777
cue_checkpoint/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
cue_label2id.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"O": 0, "B-cue": 1, "I-cue": 2}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163d17d1afad6049c4e18b0d1a7039a69077d41771102d93eb60cedd56c0bf14
3
+ size 434543084
scope_checkpoint/checkpoint-232/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NegationDetectorModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cue_num_labels": 3,
8
+ "dtype": "float32",
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
+ "transformers_version": "4.56.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 28895
25
+ }
scope_checkpoint/checkpoint-232/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163d17d1afad6049c4e18b0d1a7039a69077d41771102d93eb60cedd56c0bf14
3
+ size 434543084
scope_checkpoint/checkpoint-232/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9b38801e77453aaf74d855578b970cc909614b9886907d91ba06781c709d5a
3
+ size 864467147
scope_checkpoint/checkpoint-232/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6766a054a39672a0a4dd9afca2b0b5fce89a6250d827e8ac967f8c7b016e0e
3
+ size 14645
scope_checkpoint/checkpoint-232/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9c5c2c5107f896adc329be4d226253d795c879dab7d44fddc3cb91e46fe36f
3
+ size 1465
scope_checkpoint/checkpoint-232/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
+ }
scope_checkpoint/checkpoint-232/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
scope_checkpoint/checkpoint-232/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
scope_checkpoint/checkpoint-232/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 232,
3
+ "best_metric": 0.0,
4
+ "best_model_checkpoint": "output/negation_detector/scope_checkpoint/checkpoint-232",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 232,
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
+ "grad_norm": 28.243114471435547,
15
+ "learning_rate": 9.004310344827587e-06,
16
+ "loss": 2.2311,
17
+ "step": 232
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 1.2262825965881348,
22
+ "eval_runtime": 0.3335,
23
+ "eval_samples_per_second": 1412.397,
24
+ "eval_scope_FN": 471,
25
+ "eval_scope_FP": 471,
26
+ "eval_scope_TP": 0,
27
+ "eval_scope_end_accuracy": 0.004246284501061571,
28
+ "eval_scope_f1": 0.0,
29
+ "eval_scope_precision": 0.0,
30
+ "eval_scope_recall": 0.0,
31
+ "eval_scope_start_accuracy": 0.0,
32
+ "eval_steps_per_second": 89.962,
33
+ "step": 232
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 2320,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 10,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "TrainerControl": {
43
+ "args": {
44
+ "should_epoch_stop": false,
45
+ "should_evaluate": false,
46
+ "should_log": false,
47
+ "should_save": true,
48
+ "should_training_stop": false
49
+ },
50
+ "attributes": {}
51
+ }
52
+ },
53
+ "total_flos": 140536436135718.0,
54
+ "train_batch_size": 16,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
scope_checkpoint/checkpoint-232/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079947665ea177ab2d8fda0bfe36024cd58c3f65e0ac0e705faadc8d28253805
3
+ size 5777
scope_checkpoint/checkpoint-232/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
test_eval_results_20251117_190113.txt ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ CUE DETECTION METRICS:
2
+ eval_loss: 0.011682962998747826
3
+ eval_cue_precision: 0.9399141630699589
4
+ eval_cue_recall: 0.9733333333117037
5
+ eval_cue_f1: 0.9563318727099026
6
+ eval_cue_TP: 438
7
+ eval_cue_FP: 28
8
+ eval_cue_FN: 12
9
+ eval_runtime: 0.2825
10
+ eval_samples_per_second: 1525.549
11
+ eval_steps_per_second: 95.568
12
+ epoch: 10.0
13
+
14
+ SCOPE PREDICTION METRICS:
15
+ eval_loss: 1.258516788482666
16
+ eval_scope_precision: 0.0
17
+ eval_scope_recall: 0.0
18
+ eval_scope_f1: 0.0
19
+ eval_scope_TP: 0
20
+ eval_scope_FP: 469
21
+ eval_scope_FN: 469
22
+ eval_scope_start_accuracy: 0.0
23
+ eval_scope_end_accuracy: 0.008528784648187633
24
+ eval_runtime: 0.3415
25
+ eval_samples_per_second: 1373.442
26
+ eval_steps_per_second: 87.853
27
+ epoch: 10.0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079947665ea177ab2d8fda0bfe36024cd58c3f65e0ac0e705faadc8d28253805
3
+ size 5777
vocab.txt ADDED
The diff for this file is too large to render. See raw diff