Hugging Face's logo

texturejc
/
texture-frames-trigger

Token Classification
Transformers
Safetensors
English
deberta-v2
frame-semantics
framenet
semantic-parsing
srl
english
Model card Files
xet
 Community
texturejc commited on
Commit
256eece
·
verified ·
1 Parent(s): ea12c21

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-645/config.json +47 -0
  2. checkpoint-645/model.safetensors +3 -0
  3. checkpoint-645/optimizer.pt +3 -0
  4. checkpoint-645/rng_state.pth +3 -0
  5. checkpoint-645/scheduler.pt +3 -0
  6. checkpoint-645/tokenizer.json +0 -0
  7. checkpoint-645/tokenizer_config.json +24 -0
  8. checkpoint-645/trainer_state.json +151 -0
  9. checkpoint-645/training_args.bin +3 -0
  10. config.json +47 -0
  11. model.safetensors +3 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +24 -0
  14. training_args.bin +3 -0
checkpoint-645/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "TRIGGER"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "O": 0,
20
+ "TRIGGER": 1
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "legacy": true,
24
+ "max_position_embeddings": 512,
25
+ "max_relative_positions": -1,
26
+ "model_type": "deberta-v2",
27
+ "norm_rel_ebd": "layer_norm",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 0,
31
+ "pooler_dropout": 0.0,
32
+ "pooler_hidden_act": "gelu",
33
+ "pooler_hidden_size": 1024,
34
+ "pos_att_type": [
35
+ "p2c",
36
+ "c2p"
37
+ ],
38
+ "position_biased_input": false,
39
+ "position_buckets": 256,
40
+ "relative_attention": true,
41
+ "share_att_key": true,
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "5.12.1",
44
+ "type_vocab_size": 0,
45
+ "use_cache": false,
46
+ "vocab_size": 128100
47
+ }
checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725fdb789a8fd22ad6c8d711eaec78b7e568694ee45fc31ab593063f133b7aa0
3
+ size 1736105856
checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9195306a905e59e5916a1ce430da22299ad4a02b24d55e0515c93b56634f3f1
3
+ size 3472447675
checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:675afdb065308f66ff44bcbcf122f8b621bf37cbfbc2a1c2476db1529fb6be71
3
+ size 14645
checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9e71125fde45151f6dea67ddbb624952bcaa5a666d91168191909473bc1e72
3
+ size 1465
checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-645/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 645,
3
+ "best_metric": 0.794392523364486,
4
+ "best_model_checkpoint": "outputs/trigger/checkpoint-645",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 645,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.23255813953488372,
14
+ "grad_norm": 2.8601179122924805,
15
+ "learning_rate": 7.538461538461539e-06,
16
+ "loss": 0.4856879425048828,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.46511627906976744,
21
+ "grad_norm": 1.5334198474884033,
22
+ "learning_rate": 9.663366336633663e-06,
23
+ "loss": 0.3592271423339844,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6976744186046512,
28
+ "grad_norm": 1.665016531944275,
29
+ "learning_rate": 9.168316831683169e-06,
30
+ "loss": 0.30700958251953125,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9302325581395349,
35
+ "grad_norm": 2.089900255203247,
36
+ "learning_rate": 8.673267326732673e-06,
37
+ "loss": 0.280797061920166,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_loss": 0.2680956721305847,
43
+ "eval_runtime": 1.3365,
44
+ "eval_samples_per_second": 245.416,
45
+ "eval_steps_per_second": 15.713,
46
+ "eval_token_f1": 0.7571644042232278,
47
+ "eval_token_precision": 0.7854269110415736,
48
+ "eval_token_recall": 0.730865224625624,
49
+ "step": 215
50
+ },
51
+ {
52
+ "epoch": 1.1627906976744187,
53
+ "grad_norm": 2.0754435062408447,
54
+ "learning_rate": 8.178217821782179e-06,
55
+ "loss": 0.265327205657959,
56
+ "step": 250
57
+ },
58
+ {
59
+ "epoch": 1.3953488372093024,
60
+ "grad_norm": 1.4235446453094482,
61
+ "learning_rate": 7.683168316831683e-06,
62
+ "loss": 0.22734785079956055,
63
+ "step": 300
64
+ },
65
+ {
66
+ "epoch": 1.627906976744186,
67
+ "grad_norm": 1.9681403636932373,
68
+ "learning_rate": 7.188118811881188e-06,
69
+ "loss": 0.22995534896850586,
70
+ "step": 350
71
+ },
72
+ {
73
+ "epoch": 1.8604651162790697,
74
+ "grad_norm": 1.9590110778808594,
75
+ "learning_rate": 6.693069306930694e-06,
76
+ "loss": 0.22398286819458008,
77
+ "step": 400
78
+ },
79
+ {
80
+ "epoch": 2.0,
81
+ "eval_loss": 0.2507256269454956,
82
+ "eval_runtime": 1.3396,
83
+ "eval_samples_per_second": 244.857,
84
+ "eval_steps_per_second": 15.677,
85
+ "eval_token_f1": 0.791769547325103,
86
+ "eval_token_precision": 0.7833876221498371,
87
+ "eval_token_recall": 0.800332778702163,
88
+ "step": 430
89
+ },
90
+ {
91
+ "epoch": 2.0930232558139537,
92
+ "grad_norm": 1.8518685102462769,
93
+ "learning_rate": 6.198019801980198e-06,
94
+ "loss": 0.20480815887451173,
95
+ "step": 450
96
+ },
97
+ {
98
+ "epoch": 2.3255813953488373,
99
+ "grad_norm": 1.9515743255615234,
100
+ "learning_rate": 5.702970297029703e-06,
101
+ "loss": 0.17671422958374022,
102
+ "step": 500
103
+ },
104
+ {
105
+ "epoch": 2.558139534883721,
106
+ "grad_norm": 1.5809895992279053,
107
+ "learning_rate": 5.207920792079208e-06,
108
+ "loss": 0.17426620483398436,
109
+ "step": 550
110
+ },
111
+ {
112
+ "epoch": 2.7906976744186047,
113
+ "grad_norm": 2.1711745262145996,
114
+ "learning_rate": 4.712871287128713e-06,
115
+ "loss": 0.1732681655883789,
116
+ "step": 600
117
+ },
118
+ {
119
+ "epoch": 3.0,
120
+ "eval_loss": 0.258331298828125,
121
+ "eval_runtime": 1.3037,
122
+ "eval_samples_per_second": 251.601,
123
+ "eval_steps_per_second": 16.109,
124
+ "eval_token_f1": 0.794392523364486,
125
+ "eval_token_precision": 0.8116319444444444,
126
+ "eval_token_recall": 0.7778702163061564,
127
+ "step": 645
128
+ }
129
+ ],
130
+ "logging_steps": 50,
131
+ "max_steps": 1075,
132
+ "num_input_tokens_seen": 0,
133
+ "num_train_epochs": 5,
134
+ "save_steps": 500,
135
+ "stateful_callbacks": {
136
+ "TrainerControl": {
137
+ "args": {
138
+ "should_epoch_stop": false,
139
+ "should_evaluate": false,
140
+ "should_log": false,
141
+ "should_save": true,
142
+ "should_training_stop": false
143
+ },
144
+ "attributes": {}
145
+ }
146
+ },
147
+ "total_flos": 1078591645294896.0,
148
+ "train_batch_size": 16,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }
checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99ad9ede6f23bd47d75def4b8715070853c39f3049288ced5ba8a8c320138f2
3
+ size 5201
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "TRIGGER"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "O": 0,
20
+ "TRIGGER": 1
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "legacy": true,
24
+ "max_position_embeddings": 512,
25
+ "max_relative_positions": -1,
26
+ "model_type": "deberta-v2",
27
+ "norm_rel_ebd": "layer_norm",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 0,
31
+ "pooler_dropout": 0.0,
32
+ "pooler_hidden_act": "gelu",
33
+ "pooler_hidden_size": 1024,
34
+ "pos_att_type": [
35
+ "p2c",
36
+ "c2p"
37
+ ],
38
+ "position_biased_input": false,
39
+ "position_buckets": 256,
40
+ "relative_attention": true,
41
+ "share_att_key": true,
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "5.12.1",
44
+ "type_vocab_size": 0,
45
+ "use_cache": false,
46
+ "vocab_size": 128100
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725fdb789a8fd22ad6c8d711eaec78b7e568694ee45fc31ab593063f133b7aa0
3
+ size 1736105856
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99ad9ede6f23bd47d75def4b8715070853c39f3049288ced5ba8a8c320138f2
3
+ size 5201