Hugging Face's logo

evelinamorim
/
bert-lusa-eventype-classifier

Token Classification
Safetensors
English
bert
event-extraction
named-entity-recognition
Eval Results (legacy)
Model card Files
xet
 Community
Evelin Amorim commited on
Commit
34720bb
·
1 Parent(s): a16ab89

Reorganize: move model files to root directory

Browse files
Files changed (40) hide show
  1. checkpoint-48/model.safetensors +0 -3
  2. checkpoint-48/optimizer.pt +0 -3
  3. checkpoint-48/rng_state.pth +0 -3
  4. checkpoint-48/scheduler.pt +0 -3
  5. checkpoint-48/trainer_state.json +0 -145
  6. checkpoint-54/config.json +0 -43
  7. checkpoint-54/model.safetensors +0 -3
  8. checkpoint-54/optimizer.pt +0 -3
  9. checkpoint-54/rng_state.pth +0 -3
  10. checkpoint-54/scheduler.pt +0 -3
  11. checkpoint-54/special_tokens_map.json +0 -7
  12. checkpoint-54/tokenizer.json +0 -0
  13. checkpoint-54/tokenizer_config.json +0 -56
  14. checkpoint-54/trainer_state.json +0 -156
  15. checkpoint-54/training_args.bin +0 -3
  16. checkpoint-54/vocab.txt +0 -0
  17. checkpoint-60/config.json +0 -43
  18. checkpoint-60/optimizer.pt +0 -3
  19. checkpoint-60/rng_state.pth +0 -3
  20. checkpoint-60/scheduler.pt +0 -3
  21. checkpoint-60/special_tokens_map.json +0 -7
  22. checkpoint-60/tokenizer.json +0 -0
  23. checkpoint-60/tokenizer_config.json +0 -56
  24. checkpoint-60/trainer_state.json +0 -174
  25. checkpoint-60/training_args.bin +0 -3
  26. checkpoint-60/vocab.txt +0 -0
  27. checkpoint-48/config.json → config.json +0 -0
  28. final_model/config.json +0 -43
  29. final_model/model.safetensors +0 -3
  30. final_model/special_tokens_map.json +0 -7
  31. final_model/tokenizer.json +0 -0
  32. final_model/tokenizer_config.json +0 -56
  33. final_model/training_args.bin +0 -3
  34. final_model/vocab.txt +0 -0
  35. checkpoint-60/model.safetensors → model.safetensors +0 -0
  36. checkpoint-48/special_tokens_map.json → special_tokens_map.json +0 -0
  37. checkpoint-48/tokenizer.json → tokenizer.json +0 -0
  38. checkpoint-48/tokenizer_config.json → tokenizer_config.json +0 -0
  39. checkpoint-48/training_args.bin → training_args.bin +0 -0
  40. checkpoint-48/vocab.txt → vocab.txt +0 -0
checkpoint-48/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01faf1d29cb503f0de21e2acbe219eb857cdf4cb4a2904d24feb63d54a5fe3fd
3
- size 430923588
 
 
 
 
checkpoint-48/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3715e3091428940c8b928b0cd62a0f3f5b62d42b20e5a3daef11d9a89ea4235f
3
- size 861970123
 
 
 
 
checkpoint-48/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a7f6db4f25ebb874b08c876b4784237bc8bbc65edd183ebb2052692e69c3a4
3
- size 14645
 
 
 
 
checkpoint-48/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:754ac7ebc7d98475d8ad8093d5523e6779bb225817e39dffbda732388b7985b2
3
- size 1465
 
 
 
 
checkpoint-48/trainer_state.json DELETED
@@ -1,145 +0,0 @@
1
- {
2
- "best_global_step": 48,
3
- "best_metric": 0.3314285714285714,
4
- "best_model_checkpoint": "models/bert-focal/checkpoint-48",
5
- "epoch": 8.0,
6
- "eval_steps": 500,
7
- "global_step": 48,
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_f1": 0.07218212104386451,
15
- "eval_loss": 1.8895986080169678,
16
- "eval_precision": 0.04669540229885057,
17
- "eval_recall": 0.15892420537897312,
18
- "eval_runtime": 0.1968,
19
- "eval_samples_per_second": 86.366,
20
- "eval_steps_per_second": 10.161,
21
- "step": 6
22
- },
23
- {
24
- "epoch": 2.0,
25
- "eval_f1": 0.1630598892803221,
26
- "eval_loss": 1.728238821029663,
27
- "eval_precision": 0.10266159695817491,
28
- "eval_recall": 0.3960880195599022,
29
- "eval_runtime": 0.135,
30
- "eval_samples_per_second": 125.896,
31
- "eval_steps_per_second": 14.811,
32
- "step": 12
33
- },
34
- {
35
- "epoch": 3.0,
36
- "eval_f1": 0.25148908007941767,
37
- "eval_loss": 1.575783133506775,
38
- "eval_precision": 0.1724137931034483,
39
- "eval_recall": 0.46454767726161367,
40
- "eval_runtime": 0.1294,
41
- "eval_samples_per_second": 131.389,
42
- "eval_steps_per_second": 15.458,
43
- "step": 18
44
- },
45
- {
46
- "epoch": 3.3333333333333335,
47
- "grad_norm": 2.1542773246765137,
48
- "learning_rate": 2.277777777777778e-05,
49
- "loss": 1.7537,
50
- "step": 20
51
- },
52
- {
53
- "epoch": 4.0,
54
- "eval_f1": 0.2753950338600451,
55
- "eval_loss": 1.4765726327896118,
56
- "eval_precision": 0.19891304347826086,
57
- "eval_recall": 0.4474327628361858,
58
- "eval_runtime": 0.1272,
59
- "eval_samples_per_second": 133.656,
60
- "eval_steps_per_second": 15.724,
61
- "step": 24
62
- },
63
- {
64
- "epoch": 5.0,
65
- "eval_f1": 0.2781954887218045,
66
- "eval_loss": 1.4043300151824951,
67
- "eval_precision": 0.2008686210640608,
68
- "eval_recall": 0.45232273838630804,
69
- "eval_runtime": 0.1288,
70
- "eval_samples_per_second": 131.985,
71
- "eval_steps_per_second": 15.528,
72
- "step": 30
73
- },
74
- {
75
- "epoch": 6.0,
76
- "eval_f1": 0.3000739098300074,
77
- "eval_loss": 1.3685083389282227,
78
- "eval_precision": 0.21504237288135594,
79
- "eval_recall": 0.4963325183374083,
80
- "eval_runtime": 0.1272,
81
- "eval_samples_per_second": 133.646,
82
- "eval_steps_per_second": 15.723,
83
- "step": 36
84
- },
85
- {
86
- "epoch": 6.666666666666667,
87
- "grad_norm": 2.3210318088531494,
88
- "learning_rate": 1.1666666666666668e-05,
89
- "loss": 1.1637,
90
- "step": 40
91
- },
92
- {
93
- "epoch": 7.0,
94
- "eval_f1": 0.3288749016522423,
95
- "eval_loss": 1.3436888456344604,
96
- "eval_precision": 0.24245939675174014,
97
- "eval_recall": 0.511002444987775,
98
- "eval_runtime": 0.126,
99
- "eval_samples_per_second": 134.972,
100
- "eval_steps_per_second": 15.879,
101
- "step": 42
102
- },
103
- {
104
- "epoch": 8.0,
105
- "eval_f1": 0.3314285714285714,
106
- "eval_loss": 1.3188272714614868,
107
- "eval_precision": 0.24877450980392157,
108
- "eval_recall": 0.4963325183374083,
109
- "eval_runtime": 0.1255,
110
- "eval_samples_per_second": 135.437,
111
- "eval_steps_per_second": 15.934,
112
- "step": 48
113
- }
114
- ],
115
- "logging_steps": 20,
116
- "max_steps": 60,
117
- "num_input_tokens_seen": 0,
118
- "num_train_epochs": 10,
119
- "save_steps": 500,
120
- "stateful_callbacks": {
121
- "EarlyStoppingCallback": {
122
- "args": {
123
- "early_stopping_patience": 3,
124
- "early_stopping_threshold": 0.0
125
- },
126
- "attributes": {
127
- "early_stopping_patience_counter": 0
128
- }
129
- },
130
- "TrainerControl": {
131
- "args": {
132
- "should_epoch_stop": false,
133
- "should_evaluate": false,
134
- "should_log": false,
135
- "should_save": true,
136
- "should_training_stop": false
137
- },
138
- "attributes": {}
139
- }
140
- },
141
- "total_flos": 93400971112086.0,
142
- "train_batch_size": 16,
143
- "trial_name": null,
144
- "trial_params": null
145
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-54/config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForTokenClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "dtype": "float32",
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "O",
14
- "1": "B-State",
15
- "2": "I-State",
16
- "3": "B-Process",
17
- "4": "I-Process",
18
- "5": "B-Transition",
19
- "6": "I-Transition"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "B-Process": 3,
25
- "B-State": 1,
26
- "B-Transition": 5,
27
- "I-Process": 4,
28
- "I-State": 2,
29
- "I-Transition": 6,
30
- "O": 0
31
- },
32
- "layer_norm_eps": 1e-12,
33
- "max_position_embeddings": 512,
34
- "model_type": "bert",
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 12,
37
- "pad_token_id": 0,
38
- "position_embedding_type": "absolute",
39
- "transformers_version": "4.57.1",
40
- "type_vocab_size": 2,
41
- "use_cache": true,
42
- "vocab_size": 28996
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-54/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e05a774747cdd282ec9eabb6db8d5f0b96240acdfd60df640756a2243700e9b
3
- size 430923588
 
 
 
 
checkpoint-54/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f293a9514c85a08bd57d6def0debc55065384c1bb901176e37822978b7cc7fe
3
- size 861970123
 
 
 
 
checkpoint-54/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1566120c149341e6b7935a4d8dbe26ee97cf5105aef69601ec707512af91618
3
- size 14645
 
 
 
 
checkpoint-54/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eec016e1f0015ba555635be315ff1f165a8c41fccfd6f3bfe58d3d1b762d1a7
3
- size 1465
 
 
 
 
checkpoint-54/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
checkpoint-54/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-54/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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": false,
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-54/trainer_state.json DELETED
@@ -1,156 +0,0 @@
1
- {
2
- "best_global_step": 48,
3
- "best_metric": 0.3314285714285714,
4
- "best_model_checkpoint": "models/bert-focal/checkpoint-48",
5
- "epoch": 9.0,
6
- "eval_steps": 500,
7
- "global_step": 54,
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_f1": 0.07218212104386451,
15
- "eval_loss": 1.8895986080169678,
16
- "eval_precision": 0.04669540229885057,
17
- "eval_recall": 0.15892420537897312,
18
- "eval_runtime": 0.1968,
19
- "eval_samples_per_second": 86.366,
20
- "eval_steps_per_second": 10.161,
21
- "step": 6
22
- },
23
- {
24
- "epoch": 2.0,
25
- "eval_f1": 0.1630598892803221,
26
- "eval_loss": 1.728238821029663,
27
- "eval_precision": 0.10266159695817491,
28
- "eval_recall": 0.3960880195599022,
29
- "eval_runtime": 0.135,
30
- "eval_samples_per_second": 125.896,
31
- "eval_steps_per_second": 14.811,
32
- "step": 12
33
- },
34
- {
35
- "epoch": 3.0,
36
- "eval_f1": 0.25148908007941767,
37
- "eval_loss": 1.575783133506775,
38
- "eval_precision": 0.1724137931034483,
39
- "eval_recall": 0.46454767726161367,
40
- "eval_runtime": 0.1294,
41
- "eval_samples_per_second": 131.389,
42
- "eval_steps_per_second": 15.458,
43
- "step": 18
44
- },
45
- {
46
- "epoch": 3.3333333333333335,
47
- "grad_norm": 2.1542773246765137,
48
- "learning_rate": 2.277777777777778e-05,
49
- "loss": 1.7537,
50
- "step": 20
51
- },
52
- {
53
- "epoch": 4.0,
54
- "eval_f1": 0.2753950338600451,
55
- "eval_loss": 1.4765726327896118,
56
- "eval_precision": 0.19891304347826086,
57
- "eval_recall": 0.4474327628361858,
58
- "eval_runtime": 0.1272,
59
- "eval_samples_per_second": 133.656,
60
- "eval_steps_per_second": 15.724,
61
- "step": 24
62
- },
63
- {
64
- "epoch": 5.0,
65
- "eval_f1": 0.2781954887218045,
66
- "eval_loss": 1.4043300151824951,
67
- "eval_precision": 0.2008686210640608,
68
- "eval_recall": 0.45232273838630804,
69
- "eval_runtime": 0.1288,
70
- "eval_samples_per_second": 131.985,
71
- "eval_steps_per_second": 15.528,
72
- "step": 30
73
- },
74
- {
75
- "epoch": 6.0,
76
- "eval_f1": 0.3000739098300074,
77
- "eval_loss": 1.3685083389282227,
78
- "eval_precision": 0.21504237288135594,
79
- "eval_recall": 0.4963325183374083,
80
- "eval_runtime": 0.1272,
81
- "eval_samples_per_second": 133.646,
82
- "eval_steps_per_second": 15.723,
83
- "step": 36
84
- },
85
- {
86
- "epoch": 6.666666666666667,
87
- "grad_norm": 2.3210318088531494,
88
- "learning_rate": 1.1666666666666668e-05,
89
- "loss": 1.1637,
90
- "step": 40
91
- },
92
- {
93
- "epoch": 7.0,
94
- "eval_f1": 0.3288749016522423,
95
- "eval_loss": 1.3436888456344604,
96
- "eval_precision": 0.24245939675174014,
97
- "eval_recall": 0.511002444987775,
98
- "eval_runtime": 0.126,
99
- "eval_samples_per_second": 134.972,
100
- "eval_steps_per_second": 15.879,
101
- "step": 42
102
- },
103
- {
104
- "epoch": 8.0,
105
- "eval_f1": 0.3314285714285714,
106
- "eval_loss": 1.3188272714614868,
107
- "eval_precision": 0.24877450980392157,
108
- "eval_recall": 0.4963325183374083,
109
- "eval_runtime": 0.1255,
110
- "eval_samples_per_second": 135.437,
111
- "eval_steps_per_second": 15.934,
112
- "step": 48
113
- },
114
- {
115
- "epoch": 9.0,
116
- "eval_f1": 0.3287449392712551,
117
- "eval_loss": 1.3076528310775757,
118
- "eval_precision": 0.2457627118644068,
119
- "eval_recall": 0.4963325183374083,
120
- "eval_runtime": 0.1257,
121
- "eval_samples_per_second": 135.269,
122
- "eval_steps_per_second": 15.914,
123
- "step": 54
124
- }
125
- ],
126
- "logging_steps": 20,
127
- "max_steps": 60,
128
- "num_input_tokens_seen": 0,
129
- "num_train_epochs": 10,
130
- "save_steps": 500,
131
- "stateful_callbacks": {
132
- "EarlyStoppingCallback": {
133
- "args": {
134
- "early_stopping_patience": 3,
135
- "early_stopping_threshold": 0.0
136
- },
137
- "attributes": {
138
- "early_stopping_patience_counter": 1
139
- }
140
- },
141
- "TrainerControl": {
142
- "args": {
143
- "should_epoch_stop": false,
144
- "should_evaluate": false,
145
- "should_log": false,
146
- "should_save": true,
147
- "should_training_stop": false
148
- },
149
- "attributes": {}
150
- }
151
- },
152
- "total_flos": 105012870628182.0,
153
- "train_batch_size": 16,
154
- "trial_name": null,
155
- "trial_params": null
156
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-54/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2e4c7155b032b605830eb23ad722f2ddd24f07f38bcd84f7ba9036aa2e7bd68
3
- size 5777
 
 
 
 
checkpoint-54/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-60/config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForTokenClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "dtype": "float32",
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "O",
14
- "1": "B-State",
15
- "2": "I-State",
16
- "3": "B-Process",
17
- "4": "I-Process",
18
- "5": "B-Transition",
19
- "6": "I-Transition"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "B-Process": 3,
25
- "B-State": 1,
26
- "B-Transition": 5,
27
- "I-Process": 4,
28
- "I-State": 2,
29
- "I-Transition": 6,
30
- "O": 0
31
- },
32
- "layer_norm_eps": 1e-12,
33
- "max_position_embeddings": 512,
34
- "model_type": "bert",
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 12,
37
- "pad_token_id": 0,
38
- "position_embedding_type": "absolute",
39
- "transformers_version": "4.57.1",
40
- "type_vocab_size": 2,
41
- "use_cache": true,
42
- "vocab_size": 28996
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-60/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed137ddf51590efe9cbb7efc904f7a654ea9a898e5da6be06114fbfb6a2a9a2
3
- size 861970123
 
 
 
 
checkpoint-60/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec8dec0c3f6be29845db7d280dbaa6fa25c6684092f071e2ed197479f35b6f8
3
- size 14645
 
 
 
 
checkpoint-60/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2f4e021e454fc4e90a8ef9c6436087b99b3b421419c5271c40ea17210ffea35
3
- size 1465
 
 
 
 
checkpoint-60/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
checkpoint-60/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-60/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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": false,
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-60/trainer_state.json DELETED
@@ -1,174 +0,0 @@
1
- {
2
- "best_global_step": 60,
3
- "best_metric": 0.33495145631067963,
4
- "best_model_checkpoint": "models/bert-focal/checkpoint-60",
5
- "epoch": 10.0,
6
- "eval_steps": 500,
7
- "global_step": 60,
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_f1": 0.07218212104386451,
15
- "eval_loss": 1.8895986080169678,
16
- "eval_precision": 0.04669540229885057,
17
- "eval_recall": 0.15892420537897312,
18
- "eval_runtime": 0.1968,
19
- "eval_samples_per_second": 86.366,
20
- "eval_steps_per_second": 10.161,
21
- "step": 6
22
- },
23
- {
24
- "epoch": 2.0,
25
- "eval_f1": 0.1630598892803221,
26
- "eval_loss": 1.728238821029663,
27
- "eval_precision": 0.10266159695817491,
28
- "eval_recall": 0.3960880195599022,
29
- "eval_runtime": 0.135,
30
- "eval_samples_per_second": 125.896,
31
- "eval_steps_per_second": 14.811,
32
- "step": 12
33
- },
34
- {
35
- "epoch": 3.0,
36
- "eval_f1": 0.25148908007941767,
37
- "eval_loss": 1.575783133506775,
38
- "eval_precision": 0.1724137931034483,
39
- "eval_recall": 0.46454767726161367,
40
- "eval_runtime": 0.1294,
41
- "eval_samples_per_second": 131.389,
42
- "eval_steps_per_second": 15.458,
43
- "step": 18
44
- },
45
- {
46
- "epoch": 3.3333333333333335,
47
- "grad_norm": 2.1542773246765137,
48
- "learning_rate": 2.277777777777778e-05,
49
- "loss": 1.7537,
50
- "step": 20
51
- },
52
- {
53
- "epoch": 4.0,
54
- "eval_f1": 0.2753950338600451,
55
- "eval_loss": 1.4765726327896118,
56
- "eval_precision": 0.19891304347826086,
57
- "eval_recall": 0.4474327628361858,
58
- "eval_runtime": 0.1272,
59
- "eval_samples_per_second": 133.656,
60
- "eval_steps_per_second": 15.724,
61
- "step": 24
62
- },
63
- {
64
- "epoch": 5.0,
65
- "eval_f1": 0.2781954887218045,
66
- "eval_loss": 1.4043300151824951,
67
- "eval_precision": 0.2008686210640608,
68
- "eval_recall": 0.45232273838630804,
69
- "eval_runtime": 0.1288,
70
- "eval_samples_per_second": 131.985,
71
- "eval_steps_per_second": 15.528,
72
- "step": 30
73
- },
74
- {
75
- "epoch": 6.0,
76
- "eval_f1": 0.3000739098300074,
77
- "eval_loss": 1.3685083389282227,
78
- "eval_precision": 0.21504237288135594,
79
- "eval_recall": 0.4963325183374083,
80
- "eval_runtime": 0.1272,
81
- "eval_samples_per_second": 133.646,
82
- "eval_steps_per_second": 15.723,
83
- "step": 36
84
- },
85
- {
86
- "epoch": 6.666666666666667,
87
- "grad_norm": 2.3210318088531494,
88
- "learning_rate": 1.1666666666666668e-05,
89
- "loss": 1.1637,
90
- "step": 40
91
- },
92
- {
93
- "epoch": 7.0,
94
- "eval_f1": 0.3288749016522423,
95
- "eval_loss": 1.3436888456344604,
96
- "eval_precision": 0.24245939675174014,
97
- "eval_recall": 0.511002444987775,
98
- "eval_runtime": 0.126,
99
- "eval_samples_per_second": 134.972,
100
- "eval_steps_per_second": 15.879,
101
- "step": 42
102
- },
103
- {
104
- "epoch": 8.0,
105
- "eval_f1": 0.3314285714285714,
106
- "eval_loss": 1.3188272714614868,
107
- "eval_precision": 0.24877450980392157,
108
- "eval_recall": 0.4963325183374083,
109
- "eval_runtime": 0.1255,
110
- "eval_samples_per_second": 135.437,
111
- "eval_steps_per_second": 15.934,
112
- "step": 48
113
- },
114
- {
115
- "epoch": 9.0,
116
- "eval_f1": 0.3287449392712551,
117
- "eval_loss": 1.3076528310775757,
118
- "eval_precision": 0.2457627118644068,
119
- "eval_recall": 0.4963325183374083,
120
- "eval_runtime": 0.1257,
121
- "eval_samples_per_second": 135.269,
122
- "eval_steps_per_second": 15.914,
123
- "step": 54
124
- },
125
- {
126
- "epoch": 10.0,
127
- "grad_norm": 7.213730812072754,
128
- "learning_rate": 5.555555555555555e-07,
129
- "loss": 0.9385,
130
- "step": 60
131
- },
132
- {
133
- "epoch": 10.0,
134
- "eval_f1": 0.33495145631067963,
135
- "eval_loss": 1.3036588430404663,
136
- "eval_precision": 0.2503022974607013,
137
- "eval_recall": 0.5061124694376528,
138
- "eval_runtime": 0.1259,
139
- "eval_samples_per_second": 135.016,
140
- "eval_steps_per_second": 15.884,
141
- "step": 60
142
- }
143
- ],
144
- "logging_steps": 20,
145
- "max_steps": 60,
146
- "num_input_tokens_seen": 0,
147
- "num_train_epochs": 10,
148
- "save_steps": 500,
149
- "stateful_callbacks": {
150
- "EarlyStoppingCallback": {
151
- "args": {
152
- "early_stopping_patience": 3,
153
- "early_stopping_threshold": 0.0
154
- },
155
- "attributes": {
156
- "early_stopping_patience_counter": 0
157
- }
158
- },
159
- "TrainerControl": {
160
- "args": {
161
- "should_epoch_stop": false,
162
- "should_evaluate": false,
163
- "should_log": false,
164
- "should_save": true,
165
- "should_training_stop": true
166
- },
167
- "attributes": {}
168
- }
169
- },
170
- "total_flos": 116447161976574.0,
171
- "train_batch_size": 16,
172
- "trial_name": null,
173
- "trial_params": null
174
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-60/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2e4c7155b032b605830eb23ad722f2ddd24f07f38bcd84f7ba9036aa2e7bd68
3
- size 5777
 
 
 
 
checkpoint-60/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-48/config.json → config.json RENAMED
File without changes
final_model/config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForTokenClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "dtype": "float32",
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "O",
14
- "1": "B-State",
15
- "2": "I-State",
16
- "3": "B-Process",
17
- "4": "I-Process",
18
- "5": "B-Transition",
19
- "6": "I-Transition"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "B-Process": 3,
25
- "B-State": 1,
26
- "B-Transition": 5,
27
- "I-Process": 4,
28
- "I-State": 2,
29
- "I-Transition": 6,
30
- "O": 0
31
- },
32
- "layer_norm_eps": 1e-12,
33
- "max_position_embeddings": 512,
34
- "model_type": "bert",
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 12,
37
- "pad_token_id": 0,
38
- "position_embedding_type": "absolute",
39
- "transformers_version": "4.57.1",
40
- "type_vocab_size": 2,
41
- "use_cache": true,
42
- "vocab_size": 28996
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
final_model/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbaf710c9c1a514148f671d4d85536eaca7b273cb9c5e12a7e25c00a361d71c7
3
- size 430923588
 
 
 
 
final_model/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
final_model/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
final_model/tokenizer_config.json DELETED
@@ -1,56 +0,0 @@
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": false,
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
final_model/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2e4c7155b032b605830eb23ad722f2ddd24f07f38bcd84f7ba9036aa2e7bd68
3
- size 5777
 
 
 
 
final_model/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-60/model.safetensors → model.safetensors RENAMED
File without changes
checkpoint-48/special_tokens_map.json → special_tokens_map.json RENAMED
File without changes
checkpoint-48/tokenizer.json → tokenizer.json RENAMED
File without changes
checkpoint-48/tokenizer_config.json → tokenizer_config.json RENAMED
File without changes
checkpoint-48/training_args.bin → training_args.bin RENAMED
File without changes
checkpoint-48/vocab.txt → vocab.txt RENAMED
File without changes