Jangmin Oh commited on
Commit
b1cb162
1 Parent(s): 6f9f6f4

commit the trained model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-large
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: clarifier-good-name-xlm-roberta
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # clarifier-good-name-xlm-roberta
17
+
18
+ This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3007
21
+ - F1: 0.8746
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 64
42
+ - eval_batch_size: 64
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 0.2794 | 1.0 | 553 | 0.2373 | 0.8460 |
53
+ | 0.208 | 2.0 | 1106 | 0.2176 | 0.8585 |
54
+ | 0.1915 | 3.0 | 1659 | 0.2057 | 0.8542 |
55
+ | 0.1662 | 4.0 | 2212 | 0.2216 | 0.8635 |
56
+ | 0.1472 | 5.0 | 2765 | 0.2160 | 0.8709 |
57
+ | 0.132 | 6.0 | 3318 | 0.2297 | 0.8703 |
58
+ | 0.1255 | 7.0 | 3871 | 0.2617 | 0.8709 |
59
+ | 0.1162 | 8.0 | 4424 | 0.2973 | 0.8738 |
60
+ | 0.1036 | 9.0 | 4977 | 0.2818 | 0.8713 |
61
+ | 0.1 | 10.0 | 5530 | 0.3007 | 0.8746 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.32.0.dev0
67
+ - Pytorch 2.0.0
68
+ - Datasets 2.14.0
69
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_f1": 0.8746249184605349,
4
+ "eval_loss": 0.3006608486175537,
5
+ "eval_runtime": 1.2659,
6
+ "eval_samples": 3933,
7
+ "eval_samples_per_second": 3106.995,
8
+ "eval_steps_per_second": 48.979,
9
+ "train_loss": 0.16197810992194342,
10
+ "train_runtime": 673.3062,
11
+ "train_samples": 35391,
12
+ "train_samples_per_second": 525.63,
13
+ "train_steps_per_second": 8.213
14
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-NAME",
16
+ "2": "I-NAME",
17
+ "3": "E-NAME"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "B-NAME": 1,
23
+ "E-NAME": 3,
24
+ "I-NAME": 2,
25
+ "O": 0
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "xlm-roberta",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "output_past": true,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.32.0.dev0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_f1": 0.8746249184605349,
4
+ "eval_loss": 0.3006608486175537,
5
+ "eval_runtime": 1.2659,
6
+ "eval_samples": 3933,
7
+ "eval_samples_per_second": 3106.995,
8
+ "eval_steps_per_second": 48.979
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fb514b239f559373a4d46f2d9a9f7e550d39628783a99749a3f685a3f03dba
3
+ size 2235514665
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.16197810992194342,
4
+ "train_runtime": 673.3062,
5
+ "train_samples": 35391,
6
+ "train_samples_per_second": 525.63,
7
+ "train_steps_per_second": 8.213
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 5530,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.36,
12
+ "learning_rate": 9.64737793851718e-06,
13
+ "loss": 0.4565,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.72,
18
+ "learning_rate": 9.285714285714288e-06,
19
+ "loss": 0.2794,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_f1": 0.8460078451221056,
25
+ "eval_loss": 0.23727749288082123,
26
+ "eval_runtime": 1.2571,
27
+ "eval_samples_per_second": 3128.599,
28
+ "eval_steps_per_second": 49.319,
29
+ "step": 553
30
+ },
31
+ {
32
+ "epoch": 1.08,
33
+ "learning_rate": 8.924050632911393e-06,
34
+ "loss": 0.2371,
35
+ "step": 600
36
+ },
37
+ {
38
+ "epoch": 1.45,
39
+ "learning_rate": 8.562386980108501e-06,
40
+ "loss": 0.2237,
41
+ "step": 800
42
+ },
43
+ {
44
+ "epoch": 1.81,
45
+ "learning_rate": 8.200723327305607e-06,
46
+ "loss": 0.208,
47
+ "step": 1000
48
+ },
49
+ {
50
+ "epoch": 2.0,
51
+ "eval_f1": 0.8584722760759984,
52
+ "eval_loss": 0.2176441252231598,
53
+ "eval_runtime": 1.2612,
54
+ "eval_samples_per_second": 3118.527,
55
+ "eval_steps_per_second": 49.161,
56
+ "step": 1106
57
+ },
58
+ {
59
+ "epoch": 2.17,
60
+ "learning_rate": 7.839059674502714e-06,
61
+ "loss": 0.2034,
62
+ "step": 1200
63
+ },
64
+ {
65
+ "epoch": 2.53,
66
+ "learning_rate": 7.47739602169982e-06,
67
+ "loss": 0.1856,
68
+ "step": 1400
69
+ },
70
+ {
71
+ "epoch": 2.89,
72
+ "learning_rate": 7.115732368896926e-06,
73
+ "loss": 0.1915,
74
+ "step": 1600
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_f1": 0.8542068079640335,
79
+ "eval_loss": 0.20573046803474426,
80
+ "eval_runtime": 1.2605,
81
+ "eval_samples_per_second": 3120.201,
82
+ "eval_steps_per_second": 49.187,
83
+ "step": 1659
84
+ },
85
+ {
86
+ "epoch": 3.25,
87
+ "learning_rate": 6.754068716094033e-06,
88
+ "loss": 0.1757,
89
+ "step": 1800
90
+ },
91
+ {
92
+ "epoch": 3.62,
93
+ "learning_rate": 6.392405063291139e-06,
94
+ "loss": 0.163,
95
+ "step": 2000
96
+ },
97
+ {
98
+ "epoch": 3.98,
99
+ "learning_rate": 6.0307414104882465e-06,
100
+ "loss": 0.1662,
101
+ "step": 2200
102
+ },
103
+ {
104
+ "epoch": 4.0,
105
+ "eval_f1": 0.8634553628773282,
106
+ "eval_loss": 0.22162207961082458,
107
+ "eval_runtime": 1.2593,
108
+ "eval_samples_per_second": 3123.225,
109
+ "eval_steps_per_second": 49.235,
110
+ "step": 2212
111
+ },
112
+ {
113
+ "epoch": 4.34,
114
+ "learning_rate": 5.669077757685353e-06,
115
+ "loss": 0.1514,
116
+ "step": 2400
117
+ },
118
+ {
119
+ "epoch": 4.7,
120
+ "learning_rate": 5.30741410488246e-06,
121
+ "loss": 0.1472,
122
+ "step": 2600
123
+ },
124
+ {
125
+ "epoch": 5.0,
126
+ "eval_f1": 0.870850622406639,
127
+ "eval_loss": 0.21599918603897095,
128
+ "eval_runtime": 1.2572,
129
+ "eval_samples_per_second": 3128.475,
130
+ "eval_steps_per_second": 49.317,
131
+ "step": 2765
132
+ },
133
+ {
134
+ "epoch": 5.06,
135
+ "learning_rate": 4.9457504520795664e-06,
136
+ "loss": 0.1502,
137
+ "step": 2800
138
+ },
139
+ {
140
+ "epoch": 5.42,
141
+ "learning_rate": 4.584086799276673e-06,
142
+ "loss": 0.1321,
143
+ "step": 3000
144
+ },
145
+ {
146
+ "epoch": 5.79,
147
+ "learning_rate": 4.22242314647378e-06,
148
+ "loss": 0.132,
149
+ "step": 3200
150
+ },
151
+ {
152
+ "epoch": 6.0,
153
+ "eval_f1": 0.8702744691869497,
154
+ "eval_loss": 0.2296592891216278,
155
+ "eval_runtime": 1.2604,
156
+ "eval_samples_per_second": 3120.552,
157
+ "eval_steps_per_second": 49.193,
158
+ "step": 3318
159
+ },
160
+ {
161
+ "epoch": 6.15,
162
+ "learning_rate": 3.860759493670886e-06,
163
+ "loss": 0.1311,
164
+ "step": 3400
165
+ },
166
+ {
167
+ "epoch": 6.51,
168
+ "learning_rate": 3.499095840867993e-06,
169
+ "loss": 0.1204,
170
+ "step": 3600
171
+ },
172
+ {
173
+ "epoch": 6.87,
174
+ "learning_rate": 3.1374321880650997e-06,
175
+ "loss": 0.1255,
176
+ "step": 3800
177
+ },
178
+ {
179
+ "epoch": 7.0,
180
+ "eval_f1": 0.8709216170544651,
181
+ "eval_loss": 0.2616898715496063,
182
+ "eval_runtime": 1.259,
183
+ "eval_samples_per_second": 3123.885,
184
+ "eval_steps_per_second": 49.245,
185
+ "step": 3871
186
+ },
187
+ {
188
+ "epoch": 7.23,
189
+ "learning_rate": 2.7757685352622067e-06,
190
+ "loss": 0.1178,
191
+ "step": 4000
192
+ },
193
+ {
194
+ "epoch": 7.59,
195
+ "learning_rate": 2.414104882459313e-06,
196
+ "loss": 0.1067,
197
+ "step": 4200
198
+ },
199
+ {
200
+ "epoch": 7.96,
201
+ "learning_rate": 2.0524412296564196e-06,
202
+ "loss": 0.1162,
203
+ "step": 4400
204
+ },
205
+ {
206
+ "epoch": 8.0,
207
+ "eval_f1": 0.8737610850286907,
208
+ "eval_loss": 0.2972545921802521,
209
+ "eval_runtime": 1.2617,
210
+ "eval_samples_per_second": 3117.195,
211
+ "eval_steps_per_second": 49.14,
212
+ "step": 4424
213
+ },
214
+ {
215
+ "epoch": 8.32,
216
+ "learning_rate": 1.6907775768535265e-06,
217
+ "loss": 0.0998,
218
+ "step": 4600
219
+ },
220
+ {
221
+ "epoch": 8.68,
222
+ "learning_rate": 1.3291139240506329e-06,
223
+ "loss": 0.1036,
224
+ "step": 4800
225
+ },
226
+ {
227
+ "epoch": 9.0,
228
+ "eval_f1": 0.8713283077722902,
229
+ "eval_loss": 0.2818024754524231,
230
+ "eval_runtime": 1.2619,
231
+ "eval_samples_per_second": 3116.737,
232
+ "eval_steps_per_second": 49.132,
233
+ "step": 4977
234
+ },
235
+ {
236
+ "epoch": 9.04,
237
+ "learning_rate": 9.692585895117542e-07,
238
+ "loss": 0.1046,
239
+ "step": 5000
240
+ },
241
+ {
242
+ "epoch": 9.4,
243
+ "learning_rate": 6.075949367088608e-07,
244
+ "loss": 0.0923,
245
+ "step": 5200
246
+ },
247
+ {
248
+ "epoch": 9.76,
249
+ "learning_rate": 2.4593128390596746e-07,
250
+ "loss": 0.1,
251
+ "step": 5400
252
+ },
253
+ {
254
+ "epoch": 10.0,
255
+ "eval_f1": 0.8746249184605349,
256
+ "eval_loss": 0.3006608486175537,
257
+ "eval_runtime": 1.2724,
258
+ "eval_samples_per_second": 3090.907,
259
+ "eval_steps_per_second": 48.725,
260
+ "step": 5530
261
+ },
262
+ {
263
+ "epoch": 10.0,
264
+ "step": 5530,
265
+ "total_flos": 2.160884009653253e+16,
266
+ "train_loss": 0.16197810992194342,
267
+ "train_runtime": 673.3062,
268
+ "train_samples_per_second": 525.63,
269
+ "train_steps_per_second": 8.213
270
+ }
271
+ ],
272
+ "max_steps": 5530,
273
+ "num_train_epochs": 10,
274
+ "total_flos": 2.160884009653253e+16,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9421c76fc4ed283d50a38aa6ee18824009dd76d92e3e5f92ec7946335f3ea671
3
+ size 4027