Hugging Face's logo

timonziegenbein
/
appropriateness-classifier-binary

Text Classification
Transformers
PyTorch
English
deberta-v2
Inference Endpoints
Model card Files Community
1
NHWP25179 commited on
Commit
95b9e97
·
1 Parent(s): f9d719d

init

Browse files
Files changed (12) hide show
  1. added_tokens.json +3 -0
  2. config.json +36 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +9 -0
  8. spm.model +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +17 -0
  11. trainer_state.json +178 -0
  12. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "problem_type": "single_label_classification",
30
+ "relative_attention": true,
31
+ "share_att_key": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.26.0",
34
+ "type_vocab_size": 0,
35
+ "vocab_size": 128100
36
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25325f6ddb6ff56a0cbdbab4757cbd99070f039ee44fa6cbb436416825e15442
3
+ size 3480741957
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc29f1123923257b119359e0b10618ae69988713e618ee4cbff797f4eb14fb0
3
+ size 1740396281
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7687bd7d2b7302a5af87a09108e2fe2286c0bc15ff4d80560c1fca41f1d356
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2eba298b0d634acc305b9f84ec6419be67a610253ce0301a567bb6a3417980
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "microsoft/deberta-v3-large",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.735576923076923,
3
+ "best_model_checkpoint": "/bigwork/nhwpziet/appropriateness-style-transfer/data/models/binary-debertav3-conservative/fold0/0/checkpoint-600",
4
+ "epoch": 9.375,
5
+ "global_step": 1800,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.78,
12
+ "eval_Appropriateness_binaryF1": 0.24193548387096772,
13
+ "eval_Inappropriateness_binaryF1": 0.7025316455696202,
14
+ "eval_Inappropriateness_macroF1": 0.472233564720294,
15
+ "eval_Inappropriateness_microF1": 0.5727272727272728,
16
+ "eval_loss": 0.6738538146018982,
17
+ "eval_runtime": 2.8905,
18
+ "eval_samples_per_second": 76.112,
19
+ "eval_steps_per_second": 9.687,
20
+ "step": 150
21
+ },
22
+ {
23
+ "epoch": 1.56,
24
+ "eval_Appropriateness_binaryF1": 0.6870229007633587,
25
+ "eval_Inappropriateness_binaryF1": 0.5393258426966292,
26
+ "eval_Inappropriateness_macroF1": 0.613174371729994,
27
+ "eval_Inappropriateness_microF1": 0.6272727272727273,
28
+ "eval_loss": 0.6069997549057007,
29
+ "eval_runtime": 2.9102,
30
+ "eval_samples_per_second": 75.596,
31
+ "eval_steps_per_second": 9.621,
32
+ "step": 300
33
+ },
34
+ {
35
+ "epoch": 2.34,
36
+ "eval_Appropriateness_binaryF1": 0.696078431372549,
37
+ "eval_Inappropriateness_binaryF1": 0.7372881355932204,
38
+ "eval_Inappropriateness_macroF1": 0.7166832834828847,
39
+ "eval_Inappropriateness_microF1": 0.7181818181818181,
40
+ "eval_loss": 0.6120564341545105,
41
+ "eval_runtime": 2.9124,
42
+ "eval_samples_per_second": 75.539,
43
+ "eval_steps_per_second": 9.614,
44
+ "step": 450
45
+ },
46
+ {
47
+ "epoch": 2.6,
48
+ "learning_rate": 2.483101851851852e-06,
49
+ "loss": 0.5884,
50
+ "step": 500
51
+ },
52
+ {
53
+ "epoch": 3.12,
54
+ "eval_Appropriateness_binaryF1": 0.721153846153846,
55
+ "eval_Inappropriateness_binaryF1": 0.75,
56
+ "eval_Inappropriateness_macroF1": 0.735576923076923,
57
+ "eval_Inappropriateness_microF1": 0.7363636363636363,
58
+ "eval_loss": 0.698798418045044,
59
+ "eval_runtime": 2.9139,
60
+ "eval_samples_per_second": 75.501,
61
+ "eval_steps_per_second": 9.609,
62
+ "step": 600
63
+ },
64
+ {
65
+ "epoch": 3.91,
66
+ "eval_Appropriateness_binaryF1": 0.6995515695067265,
67
+ "eval_Inappropriateness_binaryF1": 0.6912442396313364,
68
+ "eval_Inappropriateness_macroF1": 0.6953979045690315,
69
+ "eval_Inappropriateness_microF1": 0.6954545454545454,
70
+ "eval_loss": 0.7792043089866638,
71
+ "eval_runtime": 2.9114,
72
+ "eval_samples_per_second": 75.565,
73
+ "eval_steps_per_second": 9.617,
74
+ "step": 750
75
+ },
76
+ {
77
+ "epoch": 4.69,
78
+ "eval_Appropriateness_binaryF1": 0.6986899563318776,
79
+ "eval_Inappropriateness_binaryF1": 0.6729857819905214,
80
+ "eval_Inappropriateness_macroF1": 0.6858378691611995,
81
+ "eval_Inappropriateness_microF1": 0.6863636363636364,
82
+ "eval_loss": 0.9839176535606384,
83
+ "eval_runtime": 2.9088,
84
+ "eval_samples_per_second": 75.632,
85
+ "eval_steps_per_second": 9.626,
86
+ "step": 900
87
+ },
88
+ {
89
+ "epoch": 5.21,
90
+ "learning_rate": 1.6439814814814818e-06,
91
+ "loss": 0.3639,
92
+ "step": 1000
93
+ },
94
+ {
95
+ "epoch": 5.47,
96
+ "eval_Appropriateness_binaryF1": 0.7130434782608694,
97
+ "eval_Inappropriateness_binaryF1": 0.6857142857142857,
98
+ "eval_Inappropriateness_macroF1": 0.6993788819875776,
99
+ "eval_Inappropriateness_microF1": 0.7,
100
+ "eval_loss": 1.1842643022537231,
101
+ "eval_runtime": 2.9105,
102
+ "eval_samples_per_second": 75.589,
103
+ "eval_steps_per_second": 9.62,
104
+ "step": 1050
105
+ },
106
+ {
107
+ "epoch": 6.25,
108
+ "eval_Appropriateness_binaryF1": 0.7074235807860262,
109
+ "eval_Inappropriateness_binaryF1": 0.6824644549763034,
110
+ "eval_Inappropriateness_macroF1": 0.6949440178811648,
111
+ "eval_Inappropriateness_microF1": 0.6954545454545454,
112
+ "eval_loss": 1.3936840295791626,
113
+ "eval_runtime": 2.9081,
114
+ "eval_samples_per_second": 75.652,
115
+ "eval_steps_per_second": 9.628,
116
+ "step": 1200
117
+ },
118
+ {
119
+ "epoch": 7.03,
120
+ "eval_Appropriateness_binaryF1": 0.7079646017699115,
121
+ "eval_Inappropriateness_binaryF1": 0.6915887850467289,
122
+ "eval_Inappropriateness_macroF1": 0.6997766934083203,
123
+ "eval_Inappropriateness_microF1": 0.7,
124
+ "eval_loss": 1.534929871559143,
125
+ "eval_runtime": 2.9065,
126
+ "eval_samples_per_second": 75.692,
127
+ "eval_steps_per_second": 9.634,
128
+ "step": 1350
129
+ },
130
+ {
131
+ "epoch": 7.81,
132
+ "learning_rate": 8.048611111111111e-07,
133
+ "loss": 0.2237,
134
+ "step": 1500
135
+ },
136
+ {
137
+ "epoch": 7.81,
138
+ "eval_Appropriateness_binaryF1": 0.7048458149779735,
139
+ "eval_Inappropriateness_binaryF1": 0.6854460093896714,
140
+ "eval_Inappropriateness_macroF1": 0.6951459121838224,
141
+ "eval_Inappropriateness_microF1": 0.6954545454545454,
142
+ "eval_loss": 1.604066014289856,
143
+ "eval_runtime": 2.9577,
144
+ "eval_samples_per_second": 74.383,
145
+ "eval_steps_per_second": 9.467,
146
+ "step": 1500
147
+ },
148
+ {
149
+ "epoch": 8.59,
150
+ "eval_Appropriateness_binaryF1": 0.706896551724138,
151
+ "eval_Inappropriateness_binaryF1": 0.6730769230769231,
152
+ "eval_Inappropriateness_macroF1": 0.6899867374005306,
153
+ "eval_Inappropriateness_microF1": 0.6909090909090909,
154
+ "eval_loss": 1.6559981107711792,
155
+ "eval_runtime": 2.9142,
156
+ "eval_samples_per_second": 75.494,
157
+ "eval_steps_per_second": 9.608,
158
+ "step": 1650
159
+ },
160
+ {
161
+ "epoch": 9.38,
162
+ "eval_Appropriateness_binaryF1": 0.7136563876651982,
163
+ "eval_Inappropriateness_binaryF1": 0.6948356807511736,
164
+ "eval_Inappropriateness_macroF1": 0.704246034208186,
165
+ "eval_Inappropriateness_microF1": 0.7045454545454546,
166
+ "eval_loss": 1.6468514204025269,
167
+ "eval_runtime": 2.9039,
168
+ "eval_samples_per_second": 75.759,
169
+ "eval_steps_per_second": 9.642,
170
+ "step": 1800
171
+ }
172
+ ],
173
+ "max_steps": 1920,
174
+ "num_train_epochs": 10,
175
+ "total_flos": 5135315033335992.0,
176
+ "trial_name": null,
177
+ "trial_params": null
178
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc93e74e313037454e107057e2e1a43a49aed503ebdcd47e4ab5f07b2a37e394
3
+ size 3643