Xmm commited on
Commit
9ac8c21
1 Parent(s): 70a330b

Upload 12 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
added_tokens.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</af>": 250052,
3
+ "</ar>": 250041,
4
+ "</bg>": 250066,
5
+ "</bn>": 250057,
6
+ "</de>": 250055,
7
+ "</el>": 250056,
8
+ "</en>": 250054,
9
+ "</es>": 250065,
10
+ "</et>": 250077,
11
+ "</eu>": 250048,
12
+ "</fa>": 250061,
13
+ "</fi>": 250078,
14
+ "</fr>": 250062,
15
+ "</he>": 250042,
16
+ "</hi>": 250058,
17
+ "</hu>": 250079,
18
+ "</id>": 250044,
19
+ "</it>": 250063,
20
+ "</ja>": 250068,
21
+ "</jv>": 250045,
22
+ "</ka>": 250069,
23
+ "</kk>": 250075,
24
+ "</ko>": 250070,
25
+ "</ml>": 250049,
26
+ "</mr>": 250059,
27
+ "</ms>": 250046,
28
+ "</my>": 250073,
29
+ "</nl>": 250053,
30
+ "</pt>": 250064,
31
+ "</ru>": 250067,
32
+ "</sw>": 250072,
33
+ "</ta>": 250050,
34
+ "</te>": 250051,
35
+ "</th>": 250071,
36
+ "</tl>": 250047,
37
+ "</tr>": 250076,
38
+ "</ur>": 250060,
39
+ "</vi>": 250043,
40
+ "</zh>": 250074,
41
+ "<af>": 250013,
42
+ "<ar>": 250002,
43
+ "<bg>": 250027,
44
+ "<bn>": 250018,
45
+ "<de>": 250016,
46
+ "<el>": 250017,
47
+ "<en>": 250015,
48
+ "<es>": 250026,
49
+ "<et>": 250038,
50
+ "<eu>": 250009,
51
+ "<fa>": 250022,
52
+ "<fi>": 250039,
53
+ "<fr>": 250023,
54
+ "<he>": 250003,
55
+ "<hi>": 250019,
56
+ "<hu>": 250040,
57
+ "<id>": 250005,
58
+ "<it>": 250024,
59
+ "<ja>": 250029,
60
+ "<jv>": 250006,
61
+ "<ka>": 250030,
62
+ "<kk>": 250036,
63
+ "<ko>": 250031,
64
+ "<ml>": 250010,
65
+ "<mr>": 250020,
66
+ "<ms>": 250007,
67
+ "<my>": 250034,
68
+ "<nl>": 250014,
69
+ "<pt>": 250025,
70
+ "<ru>": 250028,
71
+ "<sw>": 250033,
72
+ "<ta>": 250011,
73
+ "<te>": 250012,
74
+ "<th>": 250032,
75
+ "<tl>": 250008,
76
+ "<tr>": 250037,
77
+ "<ur>": 250021,
78
+ "<vi>": 250004,
79
+ "<zh>": 250035
80
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/EntityCS-39-PEP_MS_MLM-xlmr-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
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
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.38.1",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 250080
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cec116365ef1b036f1549fe671ef38cd38cdd50e48ff000a37c0888048133b
3
+ size 1110097420
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fda91dd1702ad659189bcabcd800638aa8658f56db4cec71d731299787b65a0
3
+ size 2220313146
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c0a7bb5c807ad5bc1c4dff28401d8ba88a8d5d80ef889d2be2ca17beb56b13
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16421db322c149675656b6ef816c336444bc6590a1774f47025ad6dacf9c462b
3
+ size 1064
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<ar>",
4
+ "<he>",
5
+ "<vi>",
6
+ "<id>",
7
+ "<jv>",
8
+ "<ms>",
9
+ "<tl>",
10
+ "<eu>",
11
+ "<ml>",
12
+ "<ta>",
13
+ "<te>",
14
+ "<af>",
15
+ "<nl>",
16
+ "<en>",
17
+ "<de>",
18
+ "<el>",
19
+ "<bn>",
20
+ "<hi>",
21
+ "<mr>",
22
+ "<ur>",
23
+ "<fa>",
24
+ "<fr>",
25
+ "<it>",
26
+ "<pt>",
27
+ "<es>",
28
+ "<bg>",
29
+ "<ru>",
30
+ "<ja>",
31
+ "<ka>",
32
+ "<ko>",
33
+ "<th>",
34
+ "<sw>",
35
+ "<my>",
36
+ "<zh>",
37
+ "<kk>",
38
+ "<tr>",
39
+ "<et>",
40
+ "<fi>",
41
+ "<hu>",
42
+ "</ar>",
43
+ "</he>",
44
+ "</vi>",
45
+ "</id>",
46
+ "</jv>",
47
+ "</ms>",
48
+ "</tl>",
49
+ "</eu>",
50
+ "</ml>",
51
+ "</ta>",
52
+ "</te>",
53
+ "</af>",
54
+ "</nl>",
55
+ "</en>",
56
+ "</de>",
57
+ "</el>",
58
+ "</bn>",
59
+ "</hi>",
60
+ "</mr>",
61
+ "</ur>",
62
+ "</fa>",
63
+ "</fr>",
64
+ "</it>",
65
+ "</pt>",
66
+ "</es>",
67
+ "</bg>",
68
+ "</ru>",
69
+ "</ja>",
70
+ "</ka>",
71
+ "</ko>",
72
+ "</th>",
73
+ "</sw>",
74
+ "</my>",
75
+ "</zh>",
76
+ "</kk>",
77
+ "</tr>",
78
+ "</et>",
79
+ "</fi>",
80
+ "</hu>"
81
+ ],
82
+ "bos_token": {
83
+ "content": "<s>",
84
+ "lstrip": false,
85
+ "normalized": false,
86
+ "rstrip": false,
87
+ "single_word": false
88
+ },
89
+ "cls_token": {
90
+ "content": "<s>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false
95
+ },
96
+ "eos_token": {
97
+ "content": "</s>",
98
+ "lstrip": false,
99
+ "normalized": false,
100
+ "rstrip": false,
101
+ "single_word": false
102
+ },
103
+ "mask_token": {
104
+ "content": "<mask>",
105
+ "lstrip": true,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false
109
+ },
110
+ "pad_token": {
111
+ "content": "<pad>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false
116
+ },
117
+ "sep_token": {
118
+ "content": "</s>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false
123
+ },
124
+ "unk_token": {
125
+ "content": "<unk>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false
130
+ }
131
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a9c017197e0b6076dc4b6c531c53b77a4b0a59b06e74c06bffd14e74f80a1c
3
+ size 17097011
tokenizer_config.json ADDED
@@ -0,0 +1,762 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "<ar>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "<he>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "<vi>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "<id>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "<jv>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "<ms>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "<tl>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "<eu>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "<ml>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "<ta>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "<te>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "<af>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "<nl>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "<en>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "<de>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "<el>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "<bn>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "<hi>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "<mr>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "<ur>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "<fa>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "<fr>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "<it>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "<pt>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "<es>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "<bg>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "<ru>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "<ja>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "<ka>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "<ko>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "<th>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "<sw>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "<my>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "<zh>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "<kk>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "<tr>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "<et>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "<fi>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "<hu>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "</ar>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "</he>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "</vi>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "</id>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "</jv>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "</ms>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "</tl>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "</eu>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "</ml>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "</ta>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "</te>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "</af>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "</nl>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "250054": {
460
+ "content": "</en>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "250055": {
468
+ "content": "</de>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "250056": {
476
+ "content": "</el>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "250057": {
484
+ "content": "</bn>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "250058": {
492
+ "content": "</hi>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "250059": {
500
+ "content": "</mr>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "250060": {
508
+ "content": "</ur>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "250061": {
516
+ "content": "</fa>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "250062": {
524
+ "content": "</fr>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "250063": {
532
+ "content": "</it>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "250064": {
540
+ "content": "</pt>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "250065": {
548
+ "content": "</es>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "250066": {
556
+ "content": "</bg>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "250067": {
564
+ "content": "</ru>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "250068": {
572
+ "content": "</ja>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "250069": {
580
+ "content": "</ka>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "250070": {
588
+ "content": "</ko>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "250071": {
596
+ "content": "</th>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "250072": {
604
+ "content": "</sw>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "250073": {
612
+ "content": "</my>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "250074": {
620
+ "content": "</zh>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "250075": {
628
+ "content": "</kk>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "250076": {
636
+ "content": "</tr>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "250077": {
644
+ "content": "</et>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "250078": {
652
+ "content": "</fi>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "250079": {
660
+ "content": "</hu>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ }
667
+ },
668
+ "additional_special_tokens": [
669
+ "<ar>",
670
+ "<he>",
671
+ "<vi>",
672
+ "<id>",
673
+ "<jv>",
674
+ "<ms>",
675
+ "<tl>",
676
+ "<eu>",
677
+ "<ml>",
678
+ "<ta>",
679
+ "<te>",
680
+ "<af>",
681
+ "<nl>",
682
+ "<en>",
683
+ "<de>",
684
+ "<el>",
685
+ "<bn>",
686
+ "<hi>",
687
+ "<mr>",
688
+ "<ur>",
689
+ "<fa>",
690
+ "<fr>",
691
+ "<it>",
692
+ "<pt>",
693
+ "<es>",
694
+ "<bg>",
695
+ "<ru>",
696
+ "<ja>",
697
+ "<ka>",
698
+ "<ko>",
699
+ "<th>",
700
+ "<sw>",
701
+ "<my>",
702
+ "<zh>",
703
+ "<kk>",
704
+ "<tr>",
705
+ "<et>",
706
+ "<fi>",
707
+ "<hu>",
708
+ "</ar>",
709
+ "</he>",
710
+ "</vi>",
711
+ "</id>",
712
+ "</jv>",
713
+ "</ms>",
714
+ "</tl>",
715
+ "</eu>",
716
+ "</ml>",
717
+ "</ta>",
718
+ "</te>",
719
+ "</af>",
720
+ "</nl>",
721
+ "</en>",
722
+ "</de>",
723
+ "</el>",
724
+ "</bn>",
725
+ "</hi>",
726
+ "</mr>",
727
+ "</ur>",
728
+ "</fa>",
729
+ "</fr>",
730
+ "</it>",
731
+ "</pt>",
732
+ "</es>",
733
+ "</bg>",
734
+ "</ru>",
735
+ "</ja>",
736
+ "</ka>",
737
+ "</ko>",
738
+ "</th>",
739
+ "</sw>",
740
+ "</my>",
741
+ "</zh>",
742
+ "</kk>",
743
+ "</tr>",
744
+ "</et>",
745
+ "</fi>",
746
+ "</hu>"
747
+ ],
748
+ "bos_token": "<s>",
749
+ "clean_up_tokenization_spaces": true,
750
+ "cls_token": "<s>",
751
+ "eos_token": "</s>",
752
+ "mask_token": "<mask>",
753
+ "max_length": 128,
754
+ "model_max_length": 1000000000000000019884624838656,
755
+ "pad_token": "<pad>",
756
+ "sep_token": "</s>",
757
+ "stride": 0,
758
+ "tokenizer_class": "XLMRobertaTokenizer",
759
+ "truncation_side": "right",
760
+ "truncation_strategy": "longest_first",
761
+ "unk_token": "<unk>"
762
+ }
trainer_state.json ADDED
@@ -0,0 +1,461 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.28671061992645264,
3
+ "best_model_checkpoint": "./checkpoint-huawei-noah/checkpoint-20000",
4
+ "epoch": 0.8854258898530193,
5
+ "eval_steps": 1000,
6
+ "global_step": 20000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 13.771051406860352,
14
+ "learning_rate": 1.9873510587163855e-05,
15
+ "loss": 0.7093,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "eval_LOC_f1": 0.6130136331478614,
21
+ "eval_ORG_f1": 0.5179822369964004,
22
+ "eval_PER_f1": 0.6815983074481896,
23
+ "eval_loss": 0.5055311322212219,
24
+ "eval_overall_accuracy": 0.8334903358124973,
25
+ "eval_overall_f1": 0.6058789768206305,
26
+ "eval_overall_precision": 0.5856612385653673,
27
+ "eval_overall_recall": 0.6275425074138874,
28
+ "eval_runtime": 974.5486,
29
+ "eval_samples_per_second": 67.416,
30
+ "eval_steps_per_second": 0.264,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.09,
35
+ "grad_norm": 23.08890151977539,
36
+ "learning_rate": 1.974702117432771e-05,
37
+ "loss": 0.501,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "eval_LOC_f1": 0.6875965698393078,
43
+ "eval_ORG_f1": 0.5727174388363369,
44
+ "eval_PER_f1": 0.7225324778200253,
45
+ "eval_loss": 0.4574837386608124,
46
+ "eval_overall_accuracy": 0.8565286056409621,
47
+ "eval_overall_f1": 0.6654497292771804,
48
+ "eval_overall_precision": 0.6761779246769729,
49
+ "eval_overall_recall": 0.6550566427755974,
50
+ "eval_runtime": 902.1725,
51
+ "eval_samples_per_second": 72.824,
52
+ "eval_steps_per_second": 0.285,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.13,
57
+ "grad_norm": 20.49671745300293,
58
+ "learning_rate": 1.9620531761491565e-05,
59
+ "loss": 0.4505,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 0.13,
64
+ "eval_LOC_f1": 0.7204635210044149,
65
+ "eval_ORG_f1": 0.5725871273468899,
66
+ "eval_PER_f1": 0.7433987684658955,
67
+ "eval_loss": 0.4243098795413971,
68
+ "eval_overall_accuracy": 0.8621471869792049,
69
+ "eval_overall_f1": 0.6874798198516072,
70
+ "eval_overall_precision": 0.6776606774900581,
71
+ "eval_overall_recall": 0.6975877000398559,
72
+ "eval_runtime": 876.2182,
73
+ "eval_samples_per_second": 74.981,
74
+ "eval_steps_per_second": 0.293,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 0.18,
79
+ "grad_norm": 14.499987602233887,
80
+ "learning_rate": 1.949404234865542e-05,
81
+ "loss": 0.4268,
82
+ "step": 4000
83
+ },
84
+ {
85
+ "epoch": 0.18,
86
+ "eval_LOC_f1": 0.7364175740245708,
87
+ "eval_ORG_f1": 0.5861517860999524,
88
+ "eval_PER_f1": 0.7518103620724146,
89
+ "eval_loss": 0.4260491728782654,
90
+ "eval_overall_accuracy": 0.8618999871026152,
91
+ "eval_overall_f1": 0.6951561442521513,
92
+ "eval_overall_precision": 0.6862764458838554,
93
+ "eval_overall_recall": 0.7042686428026184,
94
+ "eval_runtime": 900.7744,
95
+ "eval_samples_per_second": 72.937,
96
+ "eval_steps_per_second": 0.285,
97
+ "step": 4000
98
+ },
99
+ {
100
+ "epoch": 0.22,
101
+ "grad_norm": 2.379225969314575,
102
+ "learning_rate": 1.9367552935819272e-05,
103
+ "loss": 0.4023,
104
+ "step": 5000
105
+ },
106
+ {
107
+ "epoch": 0.22,
108
+ "eval_LOC_f1": 0.7258738398309293,
109
+ "eval_ORG_f1": 0.6257472293742304,
110
+ "eval_PER_f1": 0.7652099137004392,
111
+ "eval_loss": 0.3998052477836609,
112
+ "eval_overall_accuracy": 0.8690542423545061,
113
+ "eval_overall_f1": 0.70826256852105,
114
+ "eval_overall_precision": 0.7241968388877515,
115
+ "eval_overall_recall": 0.6930143954388549,
116
+ "eval_runtime": 879.0998,
117
+ "eval_samples_per_second": 74.736,
118
+ "eval_steps_per_second": 0.292,
119
+ "step": 5000
120
+ },
121
+ {
122
+ "epoch": 0.27,
123
+ "grad_norm": 17.12338638305664,
124
+ "learning_rate": 1.924106352298313e-05,
125
+ "loss": 0.3733,
126
+ "step": 6000
127
+ },
128
+ {
129
+ "epoch": 0.27,
130
+ "eval_LOC_f1": 0.7708459775529246,
131
+ "eval_ORG_f1": 0.6382364519091983,
132
+ "eval_PER_f1": 0.774621616895607,
133
+ "eval_loss": 0.3535228669643402,
134
+ "eval_overall_accuracy": 0.8847707173727775,
135
+ "eval_overall_f1": 0.7347440116838627,
136
+ "eval_overall_precision": 0.7320440692286544,
137
+ "eval_overall_recall": 0.7374639438503577,
138
+ "eval_runtime": 911.8464,
139
+ "eval_samples_per_second": 72.052,
140
+ "eval_steps_per_second": 0.282,
141
+ "step": 6000
142
+ },
143
+ {
144
+ "epoch": 0.31,
145
+ "grad_norm": 45.46567153930664,
146
+ "learning_rate": 1.9114574110146982e-05,
147
+ "loss": 0.3636,
148
+ "step": 7000
149
+ },
150
+ {
151
+ "epoch": 0.31,
152
+ "eval_LOC_f1": 0.7551567306422088,
153
+ "eval_ORG_f1": 0.6445153971205689,
154
+ "eval_PER_f1": 0.7953595339091327,
155
+ "eval_loss": 0.36239349842071533,
156
+ "eval_overall_accuracy": 0.8839519863237142,
157
+ "eval_overall_f1": 0.7360533119495638,
158
+ "eval_overall_precision": 0.7536363185945938,
159
+ "eval_overall_recall": 0.7192720542041302,
160
+ "eval_runtime": 934.2532,
161
+ "eval_samples_per_second": 70.324,
162
+ "eval_steps_per_second": 0.275,
163
+ "step": 7000
164
+ },
165
+ {
166
+ "epoch": 0.35,
167
+ "grad_norm": 23.77419090270996,
168
+ "learning_rate": 1.8988084697310836e-05,
169
+ "loss": 0.3438,
170
+ "step": 8000
171
+ },
172
+ {
173
+ "epoch": 0.35,
174
+ "eval_LOC_f1": 0.7777527075812274,
175
+ "eval_ORG_f1": 0.6523009578392771,
176
+ "eval_PER_f1": 0.7983586509404405,
177
+ "eval_loss": 0.35361218452453613,
178
+ "eval_overall_accuracy": 0.8877984416924404,
179
+ "eval_overall_f1": 0.7468599888415638,
180
+ "eval_overall_precision": 0.7522804372408594,
181
+ "eval_overall_recall": 0.741517094161437,
182
+ "eval_runtime": 964.9468,
183
+ "eval_samples_per_second": 68.087,
184
+ "eval_steps_per_second": 0.266,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 0.4,
189
+ "grad_norm": 12.217660903930664,
190
+ "learning_rate": 1.8861595284474693e-05,
191
+ "loss": 0.3388,
192
+ "step": 9000
193
+ },
194
+ {
195
+ "epoch": 0.4,
196
+ "eval_LOC_f1": 0.7769920027192643,
197
+ "eval_ORG_f1": 0.6685048661658352,
198
+ "eval_PER_f1": 0.7955169761564663,
199
+ "eval_loss": 0.36109644174575806,
200
+ "eval_overall_accuracy": 0.8892544552878013,
201
+ "eval_overall_f1": 0.7515097063573983,
202
+ "eval_overall_precision": 0.763163393230255,
203
+ "eval_overall_recall": 0.7402065755608547,
204
+ "eval_runtime": 935.4215,
205
+ "eval_samples_per_second": 70.236,
206
+ "eval_steps_per_second": 0.275,
207
+ "step": 9000
208
+ },
209
+ {
210
+ "epoch": 0.44,
211
+ "grad_norm": 6.038209438323975,
212
+ "learning_rate": 1.8735105871638546e-05,
213
+ "loss": 0.34,
214
+ "step": 10000
215
+ },
216
+ {
217
+ "epoch": 0.44,
218
+ "eval_LOC_f1": 0.7909373544148547,
219
+ "eval_ORG_f1": 0.6797622124579994,
220
+ "eval_PER_f1": 0.8097494515182176,
221
+ "eval_loss": 0.31574323773384094,
222
+ "eval_overall_accuracy": 0.8950133905201693,
223
+ "eval_overall_f1": 0.7636732236459436,
224
+ "eval_overall_precision": 0.7691121860312153,
225
+ "eval_overall_recall": 0.7583106469503421,
226
+ "eval_runtime": 875.8957,
227
+ "eval_samples_per_second": 75.009,
228
+ "eval_steps_per_second": 0.293,
229
+ "step": 10000
230
+ },
231
+ {
232
+ "epoch": 0.49,
233
+ "grad_norm": 4.172688961029053,
234
+ "learning_rate": 1.86086164588024e-05,
235
+ "loss": 0.3234,
236
+ "step": 11000
237
+ },
238
+ {
239
+ "epoch": 0.49,
240
+ "eval_LOC_f1": 0.7809025636945843,
241
+ "eval_ORG_f1": 0.6583455896967046,
242
+ "eval_PER_f1": 0.8088906849868661,
243
+ "eval_loss": 0.3503168821334839,
244
+ "eval_overall_accuracy": 0.8873938178535211,
245
+ "eval_overall_f1": 0.7490455281410953,
246
+ "eval_overall_precision": 0.7389521011220446,
247
+ "eval_overall_recall": 0.7594185080353705,
248
+ "eval_runtime": 876.8783,
249
+ "eval_samples_per_second": 74.925,
250
+ "eval_steps_per_second": 0.293,
251
+ "step": 11000
252
+ },
253
+ {
254
+ "epoch": 0.53,
255
+ "grad_norm": 0.31278446316719055,
256
+ "learning_rate": 1.8482127045966253e-05,
257
+ "loss": 0.3116,
258
+ "step": 12000
259
+ },
260
+ {
261
+ "epoch": 0.53,
262
+ "eval_LOC_f1": 0.8015539728054758,
263
+ "eval_ORG_f1": 0.6780179794520548,
264
+ "eval_PER_f1": 0.807255456750202,
265
+ "eval_loss": 0.3222993314266205,
266
+ "eval_overall_accuracy": 0.8972015203740747,
267
+ "eval_overall_f1": 0.7650194669062593,
268
+ "eval_overall_precision": 0.7538710756376371,
269
+ "eval_overall_recall": 0.7765025365965696,
270
+ "eval_runtime": 876.0279,
271
+ "eval_samples_per_second": 74.998,
272
+ "eval_steps_per_second": 0.293,
273
+ "step": 12000
274
+ },
275
+ {
276
+ "epoch": 0.58,
277
+ "grad_norm": 17.869319915771484,
278
+ "learning_rate": 1.8355637633130106e-05,
279
+ "loss": 0.3195,
280
+ "step": 13000
281
+ },
282
+ {
283
+ "epoch": 0.58,
284
+ "eval_LOC_f1": 0.8077397954482631,
285
+ "eval_ORG_f1": 0.6910689787013923,
286
+ "eval_PER_f1": 0.8216717076180746,
287
+ "eval_loss": 0.3207678496837616,
288
+ "eval_overall_accuracy": 0.8985247667722903,
289
+ "eval_overall_f1": 0.7773739255449474,
290
+ "eval_overall_precision": 0.7767264634475317,
291
+ "eval_overall_recall": 0.7780224679632244,
292
+ "eval_runtime": 885.6262,
293
+ "eval_samples_per_second": 74.185,
294
+ "eval_steps_per_second": 0.29,
295
+ "step": 13000
296
+ },
297
+ {
298
+ "epoch": 0.62,
299
+ "grad_norm": 31.75470733642578,
300
+ "learning_rate": 1.8229148220293963e-05,
301
+ "loss": 0.3038,
302
+ "step": 14000
303
+ },
304
+ {
305
+ "epoch": 0.62,
306
+ "eval_LOC_f1": 0.7926177313116938,
307
+ "eval_ORG_f1": 0.6917118970756915,
308
+ "eval_PER_f1": 0.8275611161079727,
309
+ "eval_loss": 0.3353281319141388,
310
+ "eval_overall_accuracy": 0.8932463223486391,
311
+ "eval_overall_f1": 0.775302594053191,
312
+ "eval_overall_precision": 0.7831411656868759,
313
+ "eval_overall_recall": 0.7676193821647875,
314
+ "eval_runtime": 929.7993,
315
+ "eval_samples_per_second": 70.66,
316
+ "eval_steps_per_second": 0.276,
317
+ "step": 14000
318
+ },
319
+ {
320
+ "epoch": 0.66,
321
+ "grad_norm": 4.61831521987915,
322
+ "learning_rate": 1.8102658807457817e-05,
323
+ "loss": 0.3108,
324
+ "step": 15000
325
+ },
326
+ {
327
+ "epoch": 0.66,
328
+ "eval_LOC_f1": 0.8077224388355109,
329
+ "eval_ORG_f1": 0.6909212129572154,
330
+ "eval_PER_f1": 0.8192221560207918,
331
+ "eval_loss": 0.3174687623977661,
332
+ "eval_overall_accuracy": 0.8962873233880165,
333
+ "eval_overall_f1": 0.7771138787987528,
334
+ "eval_overall_precision": 0.7788884364820847,
335
+ "eval_overall_recall": 0.7753473887579121,
336
+ "eval_runtime": 989.2234,
337
+ "eval_samples_per_second": 66.416,
338
+ "eval_steps_per_second": 0.26,
339
+ "step": 15000
340
+ },
341
+ {
342
+ "epoch": 0.71,
343
+ "grad_norm": 12.568930625915527,
344
+ "learning_rate": 1.7976169394621674e-05,
345
+ "loss": 0.3071,
346
+ "step": 16000
347
+ },
348
+ {
349
+ "epoch": 0.71,
350
+ "eval_LOC_f1": 0.794363707776905,
351
+ "eval_ORG_f1": 0.6988674651653153,
352
+ "eval_PER_f1": 0.830271581375005,
353
+ "eval_loss": 0.32856282591819763,
354
+ "eval_overall_accuracy": 0.8977907538395009,
355
+ "eval_overall_f1": 0.7767913544942637,
356
+ "eval_overall_precision": 0.7810995225703338,
357
+ "eval_overall_recall": 0.772530449291712,
358
+ "eval_runtime": 943.0369,
359
+ "eval_samples_per_second": 69.669,
360
+ "eval_steps_per_second": 0.273,
361
+ "step": 16000
362
+ },
363
+ {
364
+ "epoch": 0.75,
365
+ "grad_norm": 5.375293731689453,
366
+ "learning_rate": 1.7849679981785527e-05,
367
+ "loss": 0.294,
368
+ "step": 17000
369
+ },
370
+ {
371
+ "epoch": 0.75,
372
+ "eval_LOC_f1": 0.8179866156103497,
373
+ "eval_ORG_f1": 0.7139503216415458,
374
+ "eval_PER_f1": 0.8319541693189051,
375
+ "eval_loss": 0.3004244267940521,
376
+ "eval_overall_accuracy": 0.9056726997766982,
377
+ "eval_overall_f1": 0.7925003906754269,
378
+ "eval_overall_precision": 0.7971147209370665,
379
+ "eval_overall_recall": 0.7879391757243317,
380
+ "eval_runtime": 922.5388,
381
+ "eval_samples_per_second": 71.217,
382
+ "eval_steps_per_second": 0.279,
383
+ "step": 17000
384
+ },
385
+ {
386
+ "epoch": 0.8,
387
+ "grad_norm": 15.245515823364258,
388
+ "learning_rate": 1.772319056894938e-05,
389
+ "loss": 0.3022,
390
+ "step": 18000
391
+ },
392
+ {
393
+ "epoch": 0.8,
394
+ "eval_LOC_f1": 0.8157123906017681,
395
+ "eval_ORG_f1": 0.7098208686331968,
396
+ "eval_PER_f1": 0.8456405034257072,
397
+ "eval_loss": 0.30179163813591003,
398
+ "eval_overall_accuracy": 0.9067740352882565,
399
+ "eval_overall_f1": 0.7949277311259202,
400
+ "eval_overall_precision": 0.7816879334439119,
401
+ "eval_overall_recall": 0.808623752811873,
402
+ "eval_runtime": 877.0088,
403
+ "eval_samples_per_second": 74.914,
404
+ "eval_steps_per_second": 0.293,
405
+ "step": 18000
406
+ },
407
+ {
408
+ "epoch": 0.84,
409
+ "grad_norm": 27.571258544921875,
410
+ "learning_rate": 1.7596701156113234e-05,
411
+ "loss": 0.2932,
412
+ "step": 19000
413
+ },
414
+ {
415
+ "epoch": 0.84,
416
+ "eval_LOC_f1": 0.812069319938867,
417
+ "eval_ORG_f1": 0.711144363521586,
418
+ "eval_PER_f1": 0.8502128757579667,
419
+ "eval_loss": 0.2992981970310211,
420
+ "eval_overall_accuracy": 0.9061335916182172,
421
+ "eval_overall_f1": 0.7960065863825535,
422
+ "eval_overall_precision": 0.7903741392400006,
423
+ "eval_overall_recall": 0.8017198867820013,
424
+ "eval_runtime": 877.5146,
425
+ "eval_samples_per_second": 74.871,
426
+ "eval_steps_per_second": 0.293,
427
+ "step": 19000
428
+ },
429
+ {
430
+ "epoch": 0.89,
431
+ "grad_norm": 6.182469844818115,
432
+ "learning_rate": 1.747021174327709e-05,
433
+ "loss": 0.2943,
434
+ "step": 20000
435
+ },
436
+ {
437
+ "epoch": 0.89,
438
+ "eval_LOC_f1": 0.8233705131530693,
439
+ "eval_ORG_f1": 0.7053565992474702,
440
+ "eval_PER_f1": 0.8430738573647348,
441
+ "eval_loss": 0.28671061992645264,
442
+ "eval_overall_accuracy": 0.9084127618358795,
443
+ "eval_overall_f1": 0.7974687389257328,
444
+ "eval_overall_precision": 0.7968528685705035,
445
+ "eval_overall_recall": 0.7980855620030669,
446
+ "eval_runtime": 876.9521,
447
+ "eval_samples_per_second": 74.919,
448
+ "eval_steps_per_second": 0.293,
449
+ "step": 20000
450
+ }
451
+ ],
452
+ "logging_steps": 1000,
453
+ "max_steps": 158116,
454
+ "num_input_tokens_seen": 0,
455
+ "num_train_epochs": 7,
456
+ "save_steps": 500,
457
+ "total_flos": 6651862755777888.0,
458
+ "train_batch_size": 8,
459
+ "trial_name": null,
460
+ "trial_params": null
461
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f746b24af5f5c77a6d6b831562269236886f5a56a89a88bfa0bc250fff233b
3
+ size 4856