Hugging Face's logo

microsoft
/
Multilingual-MiniLM-L12-H384

Text Classification
Transformers
PyTorch
TensorFlow
JAX
bert
Inference Endpoints
Model card Files Community
5
system HF staff commited on
Commit
636bafe
·
1 Parent(s): 359433a

Update log.txt

Browse files
Files changed (1) hide show
  1. log.txt +141 -0
log.txt ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
2
+ INFO:transformers.configuration_utils:Model config BertConfig {
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "hidden_act": "gelu",
5
+ "hidden_dropout_prob": 0.1,
6
+ "hidden_size": 384,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 1536,
9
+ "layer_norm_eps": 1e-12,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "bert",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 12,
14
+ "pad_token_id": 0,
15
+ "type_vocab_size": 2,
16
+ "vocab_size": 250037
17
+ }
18
+
19
+ INFO:transformers.modeling_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
20
+ INFO:transformers.modeling_utils:Weights of BertModel not initialized from pretrained model: ['bert.pooler.dense.weight', 'bert.pooler.dense.bias']
21
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
22
+ INFO:transformers.configuration_utils:Model config BertConfig {
23
+ "attention_probs_dropout_prob": 0.1,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 384,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1536,
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "type_vocab_size": 2,
36
+ "vocab_size": 250037
37
+ }
38
+
39
+ INFO:transformers.modeling_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
40
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
41
+ INFO:transformers.configuration_utils:Model config BertConfig {
42
+ "attention_probs_dropout_prob": 0.1,
43
+ "hidden_act": "gelu",
44
+ "hidden_dropout_prob": 0.1,
45
+ "hidden_size": 384,
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 1536,
48
+ "layer_norm_eps": 1e-12,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "type_vocab_size": 2,
55
+ "vocab_size": 250037
56
+ }
57
+
58
+ INFO:transformers.modeling_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
59
+ INFO:transformers.modeling_utils:Weights of BertModel not initialized from pretrained model: ['bert.pooler.dense.weight', 'bert.pooler.dense.bias']
60
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
61
+ INFO:transformers.configuration_utils:Model config BertConfig {
62
+ "attention_probs_dropout_prob": 0.1,
63
+ "hidden_act": "gelu",
64
+ "hidden_dropout_prob": 0.1,
65
+ "hidden_size": 384,
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 1536,
68
+ "layer_norm_eps": 1e-12,
69
+ "max_position_embeddings": 512,
70
+ "model_type": "bert",
71
+ "num_attention_heads": 12,
72
+ "num_hidden_layers": 12,
73
+ "pad_token_id": 0,
74
+ "type_vocab_size": 2,
75
+ "vocab_size": 250037
76
+ }
77
+
78
+ INFO:transformers.modeling_tf_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
79
+ INFO:transformers.modeling_tf_pytorch_utils:Loading PyTorch weights from /home/patrick/hugging_face/models/Multilingual-MiniLM-L12-H384/pytorch_model.bin
80
+ INFO:transformers.modeling_tf_pytorch_utils:PyTorch checkpoint contains 117,904,565 parameters
81
+ INFO:transformers.modeling_tf_pytorch_utils:Loaded 117,505,920 parameters in the TF 2.0 model.
82
+ INFO:transformers.modeling_tf_pytorch_utils:Weights or buffers not loaded from PyTorch model: {'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias'}
83
+ INFO:transformers.configuration_utils:Configuration saved in ./config.json
84
+ INFO:transformers.modeling_utils:Model weights saved in ./pytorch_model.bin
85
+ INFO:transformers.configuration_utils:Configuration saved in ./config.json
86
+ INFO:transformers.modeling_tf_utils:Model weights saved in ./tf_model.h5
87
+ INFO:transformers.tokenization_utils_base:Model name '../../MiniLM-L12-H384-uncased/' not found in model shortcut name list (xlm-roberta-base, xlm-roberta-large, xlm-roberta-large-finetuned-conll02-dutch, xlm-roberta-large-finetuned-conll02-spanish, xlm-roberta-large-finetuned-conll03-english, xlm-roberta-large-finetuned-conll03-german). Assuming '../../MiniLM-L12-H384-uncased/' is a path, a model identifier, or url to a directory containing tokenizer files.
88
+ INFO:transformers.tokenization_utils_base:Didn't find file ../../MiniLM-L12-H384-uncased/sentencepiece.bpe.model. We won't load it.
89
+ INFO:transformers.tokenization_utils_base:Didn't find file ../../MiniLM-L12-H384-uncased/added_tokens.json. We won't load it.
90
+ INFO:transformers.tokenization_utils_base:Didn't find file ../../MiniLM-L12-H384-uncased/special_tokens_map.json. We won't load it.
91
+ INFO:transformers.tokenization_utils_base:Didn't find file ../../MiniLM-L12-H384-uncased/tokenizer_config.json. We won't load it.
92
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
93
+ INFO:transformers.configuration_utils:Model config BertConfig {
94
+ "attention_probs_dropout_prob": 0.1,
95
+ "hidden_act": "gelu",
96
+ "hidden_dropout_prob": 0.1,
97
+ "hidden_size": 384,
98
+ "initializer_range": 0.02,
99
+ "intermediate_size": 1536,
100
+ "layer_norm_eps": 1e-12,
101
+ "max_position_embeddings": 512,
102
+ "model_type": "bert",
103
+ "num_attention_heads": 12,
104
+ "num_hidden_layers": 12,
105
+ "pad_token_id": 0,
106
+ "type_vocab_size": 2,
107
+ "vocab_size": 250037
108
+ }
109
+
110
+ INFO:transformers.modeling_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
111
+ INFO:transformers.modeling_utils:Weights of BertModel not initialized from pretrained model: ['bert.pooler.dense.weight', 'bert.pooler.dense.bias']
112
+ INFO:transformers.configuration_utils:loading configuration file ../../Multilingual-MiniLM-L12-H384/config.json
113
+ INFO:transformers.configuration_utils:Model config BertConfig {
114
+ "attention_probs_dropout_prob": 0.1,
115
+ "hidden_act": "gelu",
116
+ "hidden_dropout_prob": 0.1,
117
+ "hidden_size": 384,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 1536,
120
+ "layer_norm_eps": 1e-12,
121
+ "max_position_embeddings": 512,
122
+ "model_type": "bert",
123
+ "num_attention_heads": 12,
124
+ "num_hidden_layers": 12,
125
+ "pad_token_id": 0,
126
+ "type_vocab_size": 2,
127
+ "vocab_size": 250037
128
+ }
129
+
130
+ INFO:transformers.modeling_tf_utils:loading weights file ../../Multilingual-MiniLM-L12-H384/pytorch_model.bin
131
+ INFO:transformers.modeling_tf_pytorch_utils:Loading PyTorch weights from /home/patrick/hugging_face/models/Multilingual-MiniLM-L12-H384/pytorch_model.bin
132
+ INFO:transformers.modeling_tf_pytorch_utils:PyTorch checkpoint contains 117,904,565 parameters
133
+ INFO:transformers.modeling_tf_pytorch_utils:Loaded 117,505,920 parameters in the TF 2.0 model.
134
+ INFO:transformers.modeling_tf_pytorch_utils:Weights or buffers not loaded from PyTorch model: {'cls.predictions.transform.dense.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.bias'}
135
+ INFO:transformers.configuration_utils:Configuration saved in ./config.json
136
+ INFO:transformers.modeling_utils:Model weights saved in ./pytorch_model.bin
137
+ INFO:transformers.configuration_utils:Configuration saved in ./config.json
138
+ INFO:transformers.modeling_tf_utils:Model weights saved in ./tf_model.h5
139
+ INFO:transformers.tokenization_utils_base:Model name '../../Multilingual-MiniLM-L12-H384/sentencepiece.bpe.model' not found in model shortcut name list (xlm-roberta-base, xlm-roberta-large, xlm-roberta-large-finetuned-conll02-dutch, xlm-roberta-large-finetuned-conll02-spanish, xlm-roberta-large-finetuned-conll03-english, xlm-roberta-large-finetuned-conll03-german). Assuming '../../Multilingual-MiniLM-L12-H384/sentencepiece.bpe.model' is a path, a model identifier, or url to a directory containing tokenizer files.
140
+ WARNING:transformers.tokenization_utils_base:Calling XLMRobertaTokenizer.from_pretrained() with the path to a single file or url is deprecated
141
+ INFO:transformers.tokenization_utils_base:loading file ../../Multilingual-MiniLM-L12-H384/sentencepiece.bpe.model