Commit
•
20a94d8
1
Parent(s):
1090c7b
Upload v1
Browse files- config.json +31 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +162 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
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": "4.26.1",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 119547
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e698a96a13705e7dd870ef2133dff1b11843827b66a2222266a9080dcb3c69
|
3 |
+
size 709126893
|
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 |
+
}
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 90.00032091396297,
|
3 |
+
"best_model_checkpoint": "bert-base-multilingual-cased-finetuned-jsquad2/checkpoint-4989",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 6652,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.3,
|
12 |
+
"learning_rate": 2.819603126879134e-05,
|
13 |
+
"loss": 0.7946,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.6,
|
18 |
+
"learning_rate": 2.6392062537582684e-05,
|
19 |
+
"loss": 0.5012,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.9,
|
24 |
+
"learning_rate": 2.458809380637402e-05,
|
25 |
+
"loss": 0.4683,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_HasAns_exact": 75.28479445269936,
|
31 |
+
"eval_HasAns_f1": 75.4044906719498,
|
32 |
+
"eval_HasAns_total": 4038,
|
33 |
+
"eval_NoAns_exact": 98.09418806111199,
|
34 |
+
"eval_NoAns_f1": 98.09418806111199,
|
35 |
+
"eval_NoAns_total": 6349,
|
36 |
+
"eval_best_exact": 89.22691826321363,
|
37 |
+
"eval_best_exact_thresh": 0.0,
|
38 |
+
"eval_best_f1": 89.27345078784379,
|
39 |
+
"eval_best_f1_thresh": 0.0,
|
40 |
+
"eval_exact": 89.22691826321363,
|
41 |
+
"eval_f1": 89.27345078784377,
|
42 |
+
"eval_total": 10387,
|
43 |
+
"step": 1663
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 1.2,
|
47 |
+
"learning_rate": 2.2784125075165364e-05,
|
48 |
+
"loss": 0.3759,
|
49 |
+
"step": 2000
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 1.5,
|
53 |
+
"learning_rate": 2.0980156343956704e-05,
|
54 |
+
"loss": 0.3514,
|
55 |
+
"step": 2500
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 1.8,
|
59 |
+
"learning_rate": 1.9176187612748048e-05,
|
60 |
+
"loss": 0.3417,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.0,
|
65 |
+
"eval_HasAns_exact": 76.91926696384348,
|
66 |
+
"eval_HasAns_f1": 77.08023774145617,
|
67 |
+
"eval_HasAns_total": 4038,
|
68 |
+
"eval_NoAns_exact": 97.43266656166325,
|
69 |
+
"eval_NoAns_f1": 97.43266656166325,
|
70 |
+
"eval_NoAns_total": 6349,
|
71 |
+
"eval_best_exact": 89.45797631654953,
|
72 |
+
"eval_best_exact_thresh": 0.0,
|
73 |
+
"eval_best_f1": 89.520554539328,
|
74 |
+
"eval_best_f1_thresh": 0.0,
|
75 |
+
"eval_exact": 89.45797631654953,
|
76 |
+
"eval_f1": 89.520554539328,
|
77 |
+
"eval_total": 10387,
|
78 |
+
"step": 3326
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 2.1,
|
82 |
+
"learning_rate": 1.7372218881539384e-05,
|
83 |
+
"loss": 0.309,
|
84 |
+
"step": 3500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 2.41,
|
88 |
+
"learning_rate": 1.5568250150330728e-05,
|
89 |
+
"loss": 0.2527,
|
90 |
+
"step": 4000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.71,
|
94 |
+
"learning_rate": 1.376428141912207e-05,
|
95 |
+
"loss": 0.2641,
|
96 |
+
"step": 4500
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 3.0,
|
100 |
+
"eval_HasAns_exact": 77.46409113422486,
|
101 |
+
"eval_HasAns_f1": 77.57140498596667,
|
102 |
+
"eval_HasAns_total": 4038,
|
103 |
+
"eval_NoAns_exact": 97.90518191841235,
|
104 |
+
"eval_NoAns_f1": 97.90518191841235,
|
105 |
+
"eval_NoAns_total": 6349,
|
106 |
+
"eval_best_exact": 89.95860209877732,
|
107 |
+
"eval_best_exact_thresh": 0.0,
|
108 |
+
"eval_best_f1": 90.00032091396297,
|
109 |
+
"eval_best_f1_thresh": 0.0,
|
110 |
+
"eval_exact": 89.95860209877732,
|
111 |
+
"eval_f1": 90.00032091396297,
|
112 |
+
"eval_total": 10387,
|
113 |
+
"step": 4989
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 3.01,
|
117 |
+
"learning_rate": 1.1960312687913411e-05,
|
118 |
+
"loss": 0.2521,
|
119 |
+
"step": 5000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 3.31,
|
123 |
+
"learning_rate": 1.0156343956704751e-05,
|
124 |
+
"loss": 0.1924,
|
125 |
+
"step": 5500
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.61,
|
129 |
+
"learning_rate": 8.352375225496093e-06,
|
130 |
+
"loss": 0.1895,
|
131 |
+
"step": 6000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.91,
|
135 |
+
"learning_rate": 6.548406494287432e-06,
|
136 |
+
"loss": 0.1969,
|
137 |
+
"step": 6500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 4.0,
|
141 |
+
"eval_HasAns_exact": 77.73650321941555,
|
142 |
+
"eval_HasAns_f1": 77.82730724781244,
|
143 |
+
"eval_HasAns_total": 4038,
|
144 |
+
"eval_NoAns_exact": 97.57442116868798,
|
145 |
+
"eval_NoAns_f1": 97.57442116868798,
|
146 |
+
"eval_NoAns_total": 6349,
|
147 |
+
"eval_best_exact": 89.86232790988736,
|
148 |
+
"eval_best_exact_thresh": 0.0,
|
149 |
+
"eval_best_f1": 89.89762844581368,
|
150 |
+
"eval_best_f1_thresh": 0.0,
|
151 |
+
"eval_exact": 89.86232790988736,
|
152 |
+
"eval_f1": 89.89762844581368,
|
153 |
+
"eval_total": 10387,
|
154 |
+
"step": 6652
|
155 |
+
}
|
156 |
+
],
|
157 |
+
"max_steps": 8315,
|
158 |
+
"num_train_epochs": 5,
|
159 |
+
"total_flos": 1.3905168206462976e+16,
|
160 |
+
"trial_name": null,
|
161 |
+
"trial_params": null
|
162 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e3019cfed52768498548debd74b63e59ce41e38212e65b02e652f7b0a9d284e
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|