Hugging Face's logo

ChangeIsKey
/
text-dating

Text Classification
Safetensors
English
roberta
Model card Files Community
Pierluigi Cassotti commited on
Commit
a6a528b
·
1 Parent(s): 933e95f

upload model

Browse files
Files changed (12) hide show
  1. config.json +98 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +282 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
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": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_4": 4,
79
+ "LABEL_5": 5,
80
+ "LABEL_6": 6,
81
+ "LABEL_7": 7,
82
+ "LABEL_8": 8,
83
+ "LABEL_9": 9
84
+ },
85
+ "layer_norm_eps": 1e-05,
86
+ "max_position_embeddings": 514,
87
+ "model_type": "roberta",
88
+ "num_attention_heads": 16,
89
+ "num_hidden_layers": 24,
90
+ "pad_token_id": 1,
91
+ "position_embedding_type": "absolute",
92
+ "problem_type": "single_label_classification",
93
+ "torch_dtype": "float32",
94
+ "transformers_version": "4.36.2",
95
+ "type_vocab_size": 1,
96
+ "use_cache": true,
97
+ "vocab_size": 50265
98
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef717b01f530e2a85119140693e14061eacc90ec14a9d6cba22cb6d625a7bc9b
3
+ size 1421622516
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b4988dfc9893583fcd46340afe07a2433c5f02577a6d2c3eb21e5d6fe1eb1c
3
+ size 2843477421
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d43b6ef28b7f13df3501eab6a6a402ae97554312594317a3436a2509a9bcff7
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e663ae6d343056fb306f37a79d8e48081b22d9e6b559199ea0a2c0ea08f0a9ef
3
+ size 1064
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,282 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9004832647216753,
5
+ "eval_steps": 1677,
6
+ "global_step": 15093,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 1.9403376886820598e-05,
14
+ "loss": 3.0319,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 1.8806753773641194e-05,
20
+ "loss": 2.8898,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 1.8210130660461786e-05,
26
+ "loss": 2.8471,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "eval_f1": 0.09119675351283209,
32
+ "eval_loss": 2.799565315246582,
33
+ "eval_runtime": 565.0093,
34
+ "eval_samples_per_second": 210.945,
35
+ "eval_steps_per_second": 3.297,
36
+ "step": 1677
37
+ },
38
+ {
39
+ "epoch": 0.12,
40
+ "learning_rate": 1.7613507547282383e-05,
41
+ "loss": 2.826,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 0.15,
46
+ "learning_rate": 1.701688443410298e-05,
47
+ "loss": 2.8064,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 0.18,
52
+ "learning_rate": 1.6420261320923575e-05,
53
+ "loss": 2.7912,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 0.2,
58
+ "eval_f1": 0.09886291342405676,
59
+ "eval_loss": 2.7552475929260254,
60
+ "eval_runtime": 565.8136,
61
+ "eval_samples_per_second": 210.645,
62
+ "eval_steps_per_second": 3.293,
63
+ "step": 3354
64
+ },
65
+ {
66
+ "epoch": 0.21,
67
+ "learning_rate": 1.582363820774417e-05,
68
+ "loss": 2.769,
69
+ "step": 3500
70
+ },
71
+ {
72
+ "epoch": 0.24,
73
+ "learning_rate": 1.5227015094564765e-05,
74
+ "loss": 2.7626,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 0.27,
79
+ "learning_rate": 1.463039198138536e-05,
80
+ "loss": 2.7493,
81
+ "step": 4500
82
+ },
83
+ {
84
+ "epoch": 0.3,
85
+ "learning_rate": 1.4033768868205956e-05,
86
+ "loss": 2.7485,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 0.3,
91
+ "eval_f1": 0.10934945582171454,
92
+ "eval_loss": 2.701012134552002,
93
+ "eval_runtime": 563.4598,
94
+ "eval_samples_per_second": 211.525,
95
+ "eval_steps_per_second": 3.306,
96
+ "step": 5031
97
+ },
98
+ {
99
+ "epoch": 0.33,
100
+ "learning_rate": 1.343714575502655e-05,
101
+ "loss": 2.7355,
102
+ "step": 5500
103
+ },
104
+ {
105
+ "epoch": 0.36,
106
+ "learning_rate": 1.2840522641847146e-05,
107
+ "loss": 2.7254,
108
+ "step": 6000
109
+ },
110
+ {
111
+ "epoch": 0.39,
112
+ "learning_rate": 1.2243899528667742e-05,
113
+ "loss": 2.7163,
114
+ "step": 6500
115
+ },
116
+ {
117
+ "epoch": 0.4,
118
+ "eval_f1": 0.11683918795621939,
119
+ "eval_loss": 2.6925740242004395,
120
+ "eval_runtime": 561.7517,
121
+ "eval_samples_per_second": 212.168,
122
+ "eval_steps_per_second": 3.316,
123
+ "step": 6708
124
+ },
125
+ {
126
+ "epoch": 0.42,
127
+ "learning_rate": 1.1647276415488338e-05,
128
+ "loss": 2.7101,
129
+ "step": 7000
130
+ },
131
+ {
132
+ "epoch": 0.45,
133
+ "learning_rate": 1.1050653302308931e-05,
134
+ "loss": 2.7063,
135
+ "step": 7500
136
+ },
137
+ {
138
+ "epoch": 0.48,
139
+ "learning_rate": 1.0454030189129527e-05,
140
+ "loss": 2.7037,
141
+ "step": 8000
142
+ },
143
+ {
144
+ "epoch": 0.5,
145
+ "eval_f1": 0.1264069487053307,
146
+ "eval_loss": 2.657057762145996,
147
+ "eval_runtime": 557.0113,
148
+ "eval_samples_per_second": 213.974,
149
+ "eval_steps_per_second": 3.345,
150
+ "step": 8385
151
+ },
152
+ {
153
+ "epoch": 0.51,
154
+ "learning_rate": 9.857407075950123e-06,
155
+ "loss": 2.6922,
156
+ "step": 8500
157
+ },
158
+ {
159
+ "epoch": 0.54,
160
+ "learning_rate": 9.260783962770719e-06,
161
+ "loss": 2.6857,
162
+ "step": 9000
163
+ },
164
+ {
165
+ "epoch": 0.57,
166
+ "learning_rate": 8.664160849591315e-06,
167
+ "loss": 2.6796,
168
+ "step": 9500
169
+ },
170
+ {
171
+ "epoch": 0.6,
172
+ "learning_rate": 8.06753773641191e-06,
173
+ "loss": 2.6686,
174
+ "step": 10000
175
+ },
176
+ {
177
+ "epoch": 0.6,
178
+ "eval_f1": 0.1275429879642049,
179
+ "eval_loss": 2.6493475437164307,
180
+ "eval_runtime": 556.9366,
181
+ "eval_samples_per_second": 214.003,
182
+ "eval_steps_per_second": 3.345,
183
+ "step": 10062
184
+ },
185
+ {
186
+ "epoch": 0.63,
187
+ "learning_rate": 7.470914623232505e-06,
188
+ "loss": 2.6798,
189
+ "step": 10500
190
+ },
191
+ {
192
+ "epoch": 0.66,
193
+ "learning_rate": 6.874291510053101e-06,
194
+ "loss": 2.6528,
195
+ "step": 11000
196
+ },
197
+ {
198
+ "epoch": 0.69,
199
+ "learning_rate": 6.277668396873695e-06,
200
+ "loss": 2.6469,
201
+ "step": 11500
202
+ },
203
+ {
204
+ "epoch": 0.7,
205
+ "eval_f1": 0.1396037444667752,
206
+ "eval_loss": 2.620657444000244,
207
+ "eval_runtime": 557.3053,
208
+ "eval_samples_per_second": 213.861,
209
+ "eval_steps_per_second": 3.343,
210
+ "step": 11739
211
+ },
212
+ {
213
+ "epoch": 0.72,
214
+ "learning_rate": 5.681045283694291e-06,
215
+ "loss": 2.6569,
216
+ "step": 12000
217
+ },
218
+ {
219
+ "epoch": 0.75,
220
+ "learning_rate": 5.0844221705148865e-06,
221
+ "loss": 2.6472,
222
+ "step": 12500
223
+ },
224
+ {
225
+ "epoch": 0.78,
226
+ "learning_rate": 4.487799057335481e-06,
227
+ "loss": 2.6507,
228
+ "step": 13000
229
+ },
230
+ {
231
+ "epoch": 0.8,
232
+ "eval_f1": 0.1391354358365679,
233
+ "eval_loss": 2.6126439571380615,
234
+ "eval_runtime": 556.9611,
235
+ "eval_samples_per_second": 213.993,
236
+ "eval_steps_per_second": 3.345,
237
+ "step": 13416
238
+ },
239
+ {
240
+ "epoch": 0.81,
241
+ "learning_rate": 3.891175944156077e-06,
242
+ "loss": 2.6297,
243
+ "step": 13500
244
+ },
245
+ {
246
+ "epoch": 0.84,
247
+ "learning_rate": 3.294552830976672e-06,
248
+ "loss": 2.6364,
249
+ "step": 14000
250
+ },
251
+ {
252
+ "epoch": 0.87,
253
+ "learning_rate": 2.6979297177972674e-06,
254
+ "loss": 2.6287,
255
+ "step": 14500
256
+ },
257
+ {
258
+ "epoch": 0.89,
259
+ "learning_rate": 2.101306604617863e-06,
260
+ "loss": 2.6269,
261
+ "step": 15000
262
+ },
263
+ {
264
+ "epoch": 0.9,
265
+ "eval_f1": 0.14388305284850214,
266
+ "eval_loss": 2.6065549850463867,
267
+ "eval_runtime": 556.552,
268
+ "eval_samples_per_second": 214.151,
269
+ "eval_steps_per_second": 3.347,
270
+ "step": 15093
271
+ }
272
+ ],
273
+ "logging_steps": 500,
274
+ "max_steps": 16761,
275
+ "num_input_tokens_seen": 0,
276
+ "num_train_epochs": 1,
277
+ "save_steps": 1677,
278
+ "total_flos": 4.1849662176682214e+17,
279
+ "train_batch_size": 64,
280
+ "trial_name": null,
281
+ "trial_params": null
282
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0adbf582fd2c65359d6648f80d695eddbca6ae78f9b2febd39de5fb127c32eee
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff