amirdnc commited on
Commit
27c5f49
1 Parent(s): b1b4430

added model files

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.0,
3
+ "eval_samples": 1666,
4
+ "exact_match": 62.69946808510638,
5
+ "f1": 71.41972213728964,
6
+ "test_samples": 1626,
7
+ "train_loss": 0.41084846325115426,
8
+ "train_runtime": 10637.12,
9
+ "train_samples": 29233,
10
+ "train_samples_per_second": 41.223,
11
+ "train_steps_per_second": 1.289
12
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.24.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
eval_nbest_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.0,
3
+ "eval_samples": 1666,
4
+ "exact_match": 61.359093937375086,
5
+ "f1": 70.77972929660706
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955adbdfdd50ba9afa9053865820df203068bd1fd18bfbd45dc4d8f482134bc8
3
+ size 709129709
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
test_nbest_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
test_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
test_results.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "exact_match": 62.69946808510638,
3
+ "f1": 71.41972213728964,
4
+ "test_samples": 1626
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-multilingual-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.0,
3
+ "train_loss": 0.41084846325115426,
4
+ "train_runtime": 10637.12,
5
+ "train_samples": 29233,
6
+ "train_samples_per_second": 41.223,
7
+ "train_steps_per_second": 1.289
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 15.0,
5
+ "global_step": 13710,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 5.000000000000001e-07,
13
+ "loss": 5.9308,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.55,
18
+ "learning_rate": 4.85304922850845e-05,
19
+ "loss": 2.2869,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 1.09,
24
+ "learning_rate": 4.6693607641440116e-05,
25
+ "loss": 1.5406,
26
+ "step": 1000
27
+ },
28
+ {
29
+ "epoch": 1.64,
30
+ "learning_rate": 4.485672299779574e-05,
31
+ "loss": 1.1804,
32
+ "step": 1500
33
+ },
34
+ {
35
+ "epoch": 2.19,
36
+ "learning_rate": 4.301983835415136e-05,
37
+ "loss": 1.0226,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 2.74,
42
+ "learning_rate": 4.1182953710506984e-05,
43
+ "loss": 0.8362,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 3.28,
48
+ "learning_rate": 3.93460690668626e-05,
49
+ "loss": 0.6883,
50
+ "step": 3000
51
+ },
52
+ {
53
+ "epoch": 3.83,
54
+ "learning_rate": 3.750918442321822e-05,
55
+ "loss": 0.5913,
56
+ "step": 3500
57
+ },
58
+ {
59
+ "epoch": 4.38,
60
+ "learning_rate": 3.5672299779573845e-05,
61
+ "loss": 0.456,
62
+ "step": 4000
63
+ },
64
+ {
65
+ "epoch": 4.92,
66
+ "learning_rate": 3.383541513592947e-05,
67
+ "loss": 0.4352,
68
+ "step": 4500
69
+ },
70
+ {
71
+ "epoch": 5.47,
72
+ "learning_rate": 3.1998530492285084e-05,
73
+ "loss": 0.3212,
74
+ "step": 5000
75
+ },
76
+ {
77
+ "epoch": 6.02,
78
+ "learning_rate": 3.0161645848640706e-05,
79
+ "loss": 0.3159,
80
+ "step": 5500
81
+ },
82
+ {
83
+ "epoch": 6.56,
84
+ "learning_rate": 2.8324761204996326e-05,
85
+ "loss": 0.2223,
86
+ "step": 6000
87
+ },
88
+ {
89
+ "epoch": 7.11,
90
+ "learning_rate": 2.6487876561351948e-05,
91
+ "loss": 0.2304,
92
+ "step": 6500
93
+ },
94
+ {
95
+ "epoch": 7.66,
96
+ "learning_rate": 2.465099191770757e-05,
97
+ "loss": 0.1776,
98
+ "step": 7000
99
+ },
100
+ {
101
+ "epoch": 8.21,
102
+ "learning_rate": 2.281410727406319e-05,
103
+ "loss": 0.1594,
104
+ "step": 7500
105
+ },
106
+ {
107
+ "epoch": 8.75,
108
+ "learning_rate": 2.097722263041881e-05,
109
+ "loss": 0.1383,
110
+ "step": 8000
111
+ },
112
+ {
113
+ "epoch": 9.3,
114
+ "learning_rate": 1.9140337986774432e-05,
115
+ "loss": 0.1164,
116
+ "step": 8500
117
+ },
118
+ {
119
+ "epoch": 9.85,
120
+ "learning_rate": 1.730345334313005e-05,
121
+ "loss": 0.1007,
122
+ "step": 9000
123
+ },
124
+ {
125
+ "epoch": 10.39,
126
+ "learning_rate": 1.5466568699485674e-05,
127
+ "loss": 0.082,
128
+ "step": 9500
129
+ },
130
+ {
131
+ "epoch": 10.94,
132
+ "learning_rate": 1.3629684055841293e-05,
133
+ "loss": 0.0761,
134
+ "step": 10000
135
+ },
136
+ {
137
+ "epoch": 11.49,
138
+ "learning_rate": 1.1792799412196914e-05,
139
+ "loss": 0.0598,
140
+ "step": 10500
141
+ },
142
+ {
143
+ "epoch": 12.04,
144
+ "learning_rate": 9.955914768552535e-06,
145
+ "loss": 0.0599,
146
+ "step": 11000
147
+ },
148
+ {
149
+ "epoch": 12.58,
150
+ "learning_rate": 8.119030124908156e-06,
151
+ "loss": 0.0395,
152
+ "step": 11500
153
+ },
154
+ {
155
+ "epoch": 13.13,
156
+ "learning_rate": 6.282145481263777e-06,
157
+ "loss": 0.0379,
158
+ "step": 12000
159
+ },
160
+ {
161
+ "epoch": 13.68,
162
+ "learning_rate": 4.445260837619398e-06,
163
+ "loss": 0.0282,
164
+ "step": 12500
165
+ },
166
+ {
167
+ "epoch": 14.22,
168
+ "learning_rate": 2.6083761939750186e-06,
169
+ "loss": 0.0278,
170
+ "step": 13000
171
+ },
172
+ {
173
+ "epoch": 14.77,
174
+ "learning_rate": 7.714915503306393e-07,
175
+ "loss": 0.0203,
176
+ "step": 13500
177
+ },
178
+ {
179
+ "epoch": 15.0,
180
+ "step": 13710,
181
+ "total_flos": 8.593299100871424e+16,
182
+ "train_loss": 0.41084846325115426,
183
+ "train_runtime": 10637.12,
184
+ "train_samples_per_second": 41.223,
185
+ "train_steps_per_second": 1.289
186
+ }
187
+ ],
188
+ "max_steps": 13710,
189
+ "num_train_epochs": 15,
190
+ "total_flos": 8.593299100871424e+16,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef2ef0c086667bf7b446f711ae785f2cfcfd861cc8d6a454efefb28c5718ee2
3
+ size 3387
vocab.txt ADDED
The diff for this file is too large to render. See raw diff