Hugging Face's logo

splitner
/
spanclass-qa-dice-ontonotes

Transformers
PyTorch
roberta
Model card Files
xet
 Community
1
jatinarora2702 commited on
Commit
21a7ee9
·
1 Parent(s): 5d76b94

first model version

Browse files
Files changed (10) hide show
  1. config.json +64 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer_config.json +1 -0
  8. trainer_state.json +280 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "NerSpanRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
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
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_2": 2,
47
+ "LABEL_3": 3,
48
+ "LABEL_4": 4,
49
+ "LABEL_5": 5,
50
+ "LABEL_6": 6,
51
+ "LABEL_7": 7,
52
+ "LABEL_8": 8,
53
+ "LABEL_9": 9
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_position_embeddings": 514,
57
+ "model_type": "roberta",
58
+ "num_attention_heads": 12,
59
+ "num_hidden_layers": 12,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "type_vocab_size": 1,
63
+ "vocab_size": 50265
64
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2a43e77ab05d6092351ec909f157103c1d2cafc59d2809f2a3c767b8199854
3
+ size 997392285
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3efb7b5eac3ce4be9aa7b1a377dcb00d99496f85fc005dc1a73ef7eec0d9faf
3
+ size 498723309
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff077b6829b1bd4e8216d57579bdb9135780ec15cd8016bcbfcecdc00a7010d
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "roberta-base"}
trainer_state.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9582504965178059,
3
+ "best_model_checkpoint": "../out/onto_final/ner-roberta-spanclass-dice/checkpoints/checkpoint-22000",
4
+ "epoch": 17.200938232994528,
5
+ "global_step": 22000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.7818608287724785,
12
+ "learning_rate": 9.973937972374251e-06,
13
+ "loss": 0.5397671508789063,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.7818608287724785,
18
+ "eval_loss": 0.22605788707733154,
19
+ "eval_micro_f1": 0.9477679373274942,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.5637216575449568,
24
+ "learning_rate": 9.947875944748501e-06,
25
+ "loss": 0.1624965362548828,
26
+ "step": 2000
27
+ },
28
+ {
29
+ "epoch": 1.5637216575449568,
30
+ "eval_loss": 0.21387435495853424,
31
+ "eval_micro_f1": 0.9516537135790754,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.3455824863174355,
36
+ "learning_rate": 9.921813917122753e-06,
37
+ "loss": 0.12110142517089843,
38
+ "step": 3000
39
+ },
40
+ {
41
+ "epoch": 2.3455824863174355,
42
+ "eval_loss": 0.21980492770671844,
43
+ "eval_micro_f1": 0.953822518928795,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 3.127443315089914,
48
+ "learning_rate": 9.895751889497005e-06,
49
+ "loss": 0.10264362335205078,
50
+ "step": 4000
51
+ },
52
+ {
53
+ "epoch": 3.127443315089914,
54
+ "eval_loss": 0.2117234468460083,
55
+ "eval_micro_f1": 0.9575275614012327,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 3.9093041438623923,
60
+ "learning_rate": 9.869689861871255e-06,
61
+ "loss": 0.0832140121459961,
62
+ "step": 5000
63
+ },
64
+ {
65
+ "epoch": 3.9093041438623923,
66
+ "eval_loss": 0.22679875791072845,
67
+ "eval_micro_f1": 0.9530092169226502,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 4.691164972634871,
72
+ "learning_rate": 9.843627834245505e-06,
73
+ "loss": 0.06584241485595703,
74
+ "step": 6000
75
+ },
76
+ {
77
+ "epoch": 4.691164972634871,
78
+ "eval_loss": 0.23657391965389252,
79
+ "eval_micro_f1": 0.9532803175913651,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 5.473025801407349,
84
+ "learning_rate": 9.817565806619755e-06,
85
+ "loss": 0.05782469177246094,
86
+ "step": 7000
87
+ },
88
+ {
89
+ "epoch": 5.473025801407349,
90
+ "eval_loss": 0.25745341181755066,
91
+ "eval_micro_f1": 0.9544550871557965,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 6.254886630179828,
96
+ "learning_rate": 9.791503778994007e-06,
97
+ "loss": 0.04978230285644531,
98
+ "step": 8000
99
+ },
100
+ {
101
+ "epoch": 6.254886630179828,
102
+ "eval_loss": 0.2867651581764221,
103
+ "eval_micro_f1": 0.9527381162539351,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 7.0367474589523065,
108
+ "learning_rate": 9.765441751368257e-06,
109
+ "loss": 0.043348209381103515,
110
+ "step": 9000
111
+ },
112
+ {
113
+ "epoch": 7.0367474589523065,
114
+ "eval_loss": 0.30041876435279846,
115
+ "eval_micro_f1": 0.949394541339784,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 7.818608287724785,
120
+ "learning_rate": 9.739379723742509e-06,
121
+ "loss": 0.03466781616210937,
122
+ "step": 10000
123
+ },
124
+ {
125
+ "epoch": 7.818608287724785,
126
+ "eval_loss": 0.30916619300842285,
127
+ "eval_micro_f1": 0.9520151811373619,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 8.600469116497264,
132
+ "learning_rate": 9.713317696116759e-06,
133
+ "loss": 0.030826730728149412,
134
+ "step": 11000
135
+ },
136
+ {
137
+ "epoch": 8.600469116497264,
138
+ "eval_loss": 0.309920072555542,
139
+ "eval_micro_f1": 0.9503885771250722,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 9.382329945269742,
144
+ "learning_rate": 9.687255668491009e-06,
145
+ "loss": 0.027759357452392577,
146
+ "step": 12000
147
+ },
148
+ {
149
+ "epoch": 9.382329945269742,
150
+ "eval_loss": 0.3114129900932312,
151
+ "eval_micro_f1": 0.9543647202662249,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 10.16419077404222,
156
+ "learning_rate": 9.661193640865259e-06,
157
+ "loss": 0.026107059478759766,
158
+ "step": 13000
159
+ },
160
+ {
161
+ "epoch": 10.16419077404222,
162
+ "eval_loss": 0.3399326205253601,
163
+ "eval_micro_f1": 0.9531899507017935,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 10.946051602814698,
168
+ "learning_rate": 9.635131613239511e-06,
169
+ "loss": 0.019590240478515625,
170
+ "step": 14000
171
+ },
172
+ {
173
+ "epoch": 10.946051602814698,
174
+ "eval_loss": 0.337801992893219,
175
+ "eval_micro_f1": 0.9550876553827982,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 11.727912431587178,
180
+ "learning_rate": 9.609069585613761e-06,
181
+ "loss": 0.016569852828979492,
182
+ "step": 15000
183
+ },
184
+ {
185
+ "epoch": 11.727912431587178,
186
+ "eval_loss": 0.3670026957988739,
187
+ "eval_micro_f1": 0.9524670155852202,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 12.509773260359657,
192
+ "learning_rate": 9.583007557988013e-06,
193
+ "loss": 0.016996849060058595,
194
+ "step": 16000
195
+ },
196
+ {
197
+ "epoch": 12.509773260359657,
198
+ "eval_loss": 0.35762009024620056,
199
+ "eval_micro_f1": 0.9553587560515131,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 13.291634089132135,
204
+ "learning_rate": 9.556945530362263e-06,
205
+ "loss": 0.012570078849792481,
206
+ "step": 17000
207
+ },
208
+ {
209
+ "epoch": 13.291634089132135,
210
+ "eval_loss": 0.39511236548423767,
211
+ "eval_micro_f1": 0.9543647202662249,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 14.073494917904613,
216
+ "learning_rate": 9.530883502736513e-06,
217
+ "loss": 0.01412732219696045,
218
+ "step": 18000
219
+ },
220
+ {
221
+ "epoch": 14.073494917904613,
222
+ "eval_loss": 0.37808138132095337,
223
+ "eval_micro_f1": 0.9533706844809368,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 14.855355746677091,
228
+ "learning_rate": 9.504821475110765e-06,
229
+ "loss": 0.01403067398071289,
230
+ "step": 19000
231
+ },
232
+ {
233
+ "epoch": 14.855355746677091,
234
+ "eval_loss": 0.3788624405860901,
235
+ "eval_micro_f1": 0.9541839864870816,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 15.63721657544957,
240
+ "learning_rate": 9.478759447485015e-06,
241
+ "loss": 0.011390049934387208,
242
+ "step": 20000
243
+ },
244
+ {
245
+ "epoch": 15.63721657544957,
246
+ "eval_loss": 0.3904345631599426,
247
+ "eval_micro_f1": 0.9565335256159445,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 16.419077404222048,
252
+ "learning_rate": 9.452697419859265e-06,
253
+ "loss": 0.01300933837890625,
254
+ "step": 21000
255
+ },
256
+ {
257
+ "epoch": 16.419077404222048,
258
+ "eval_loss": 0.39750251173973083,
259
+ "eval_micro_f1": 0.9537321520392233,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 17.200938232994528,
264
+ "learning_rate": 9.426635392233517e-06,
265
+ "loss": 0.011849085807800292,
266
+ "step": 22000
267
+ },
268
+ {
269
+ "epoch": 17.200938232994528,
270
+ "eval_loss": 0.36782628297805786,
271
+ "eval_micro_f1": 0.9582504965178059,
272
+ "step": 22000
273
+ }
274
+ ],
275
+ "max_steps": 383700,
276
+ "num_train_epochs": 300,
277
+ "total_flos": 152916752018322864,
278
+ "trial_name": null,
279
+ "trial_params": null
280
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b06cfa9e4eb49fd9e2d57c3637beeba6c754e04bbc4442ecd914daa087ba8cb
3
+ size 1967
vocab.json ADDED
The diff for this file is too large to render. See raw diff