hyperinfer
commited on
Commit
•
358409f
1
Parent(s):
a0d40c4
Model save
Browse files- README.md +69 -0
- config.json +129 -0
- model.safetensors +3 -0
- runs/Aug06_13-28-33_10db6dd1f421/events.out.tfevents.1722950924.10db6dd1f421.959.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: google-bert/bert-base-german-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: BERT_Reciever_6
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# BERT_Reciever_6
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1356
|
21 |
+
- Accuracy: 0.9561
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 160
|
42 |
+
- eval_batch_size: 160
|
43 |
+
- seed: 2805
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10.0
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 31 | 0.3889 | 0.9196 |
|
53 |
+
| No log | 2.0 | 62 | 0.2137 | 0.9342 |
|
54 |
+
| No log | 3.0 | 93 | 0.1763 | 0.9433 |
|
55 |
+
| No log | 4.0 | 124 | 0.1660 | 0.9433 |
|
56 |
+
| No log | 5.0 | 155 | 0.1592 | 0.9415 |
|
57 |
+
| No log | 6.0 | 186 | 0.1522 | 0.9470 |
|
58 |
+
| No log | 7.0 | 217 | 0.1454 | 0.9525 |
|
59 |
+
| No log | 8.0 | 248 | 0.1448 | 0.9506 |
|
60 |
+
| No log | 9.0 | 279 | 0.1388 | 0.9525 |
|
61 |
+
| No log | 10.0 | 310 | 0.1356 | 0.9561 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.44.0.dev0
|
67 |
+
- Pytorch 2.3.1+cu121
|
68 |
+
- Datasets 2.20.0
|
69 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-german-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "text-classification",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "0",
|
14 |
+
"1": "1",
|
15 |
+
"2": "10",
|
16 |
+
"3": "11",
|
17 |
+
"4": "12",
|
18 |
+
"5": "13",
|
19 |
+
"6": "14",
|
20 |
+
"7": "15",
|
21 |
+
"8": "16",
|
22 |
+
"9": "17",
|
23 |
+
"10": "18",
|
24 |
+
"11": "19",
|
25 |
+
"12": "2",
|
26 |
+
"13": "20",
|
27 |
+
"14": "21",
|
28 |
+
"15": "22",
|
29 |
+
"16": "23",
|
30 |
+
"17": "24",
|
31 |
+
"18": "25",
|
32 |
+
"19": "26",
|
33 |
+
"20": "27",
|
34 |
+
"21": "28",
|
35 |
+
"22": "29",
|
36 |
+
"23": "3",
|
37 |
+
"24": "30",
|
38 |
+
"25": "31",
|
39 |
+
"26": "32",
|
40 |
+
"27": "33",
|
41 |
+
"28": "34",
|
42 |
+
"29": "35",
|
43 |
+
"30": "36",
|
44 |
+
"31": "37",
|
45 |
+
"32": "38",
|
46 |
+
"33": "39",
|
47 |
+
"34": "4",
|
48 |
+
"35": "40",
|
49 |
+
"36": "41",
|
50 |
+
"37": "42",
|
51 |
+
"38": "43",
|
52 |
+
"39": "44",
|
53 |
+
"40": "45",
|
54 |
+
"41": "46",
|
55 |
+
"42": "47",
|
56 |
+
"43": "48",
|
57 |
+
"44": "5",
|
58 |
+
"45": "6",
|
59 |
+
"46": "7",
|
60 |
+
"47": "8",
|
61 |
+
"48": "9"
|
62 |
+
},
|
63 |
+
"initializer_range": 0.02,
|
64 |
+
"intermediate_size": 3072,
|
65 |
+
"label2id": {
|
66 |
+
"0": 0,
|
67 |
+
"1": 1,
|
68 |
+
"10": 2,
|
69 |
+
"11": 3,
|
70 |
+
"12": 4,
|
71 |
+
"13": 5,
|
72 |
+
"14": 6,
|
73 |
+
"15": 7,
|
74 |
+
"16": 8,
|
75 |
+
"17": 9,
|
76 |
+
"18": 10,
|
77 |
+
"19": 11,
|
78 |
+
"2": 12,
|
79 |
+
"20": 13,
|
80 |
+
"21": 14,
|
81 |
+
"22": 15,
|
82 |
+
"23": 16,
|
83 |
+
"24": 17,
|
84 |
+
"25": 18,
|
85 |
+
"26": 19,
|
86 |
+
"27": 20,
|
87 |
+
"28": 21,
|
88 |
+
"29": 22,
|
89 |
+
"3": 23,
|
90 |
+
"30": 24,
|
91 |
+
"31": 25,
|
92 |
+
"32": 26,
|
93 |
+
"33": 27,
|
94 |
+
"34": 28,
|
95 |
+
"35": 29,
|
96 |
+
"36": 30,
|
97 |
+
"37": 31,
|
98 |
+
"38": 32,
|
99 |
+
"39": 33,
|
100 |
+
"4": 34,
|
101 |
+
"40": 35,
|
102 |
+
"41": 36,
|
103 |
+
"42": 37,
|
104 |
+
"43": 38,
|
105 |
+
"44": 39,
|
106 |
+
"45": 40,
|
107 |
+
"46": 41,
|
108 |
+
"47": 42,
|
109 |
+
"48": 43,
|
110 |
+
"5": 44,
|
111 |
+
"6": 45,
|
112 |
+
"7": 46,
|
113 |
+
"8": 47,
|
114 |
+
"9": 48
|
115 |
+
},
|
116 |
+
"layer_norm_eps": 1e-12,
|
117 |
+
"max_position_embeddings": 512,
|
118 |
+
"model_type": "bert",
|
119 |
+
"num_attention_heads": 12,
|
120 |
+
"num_hidden_layers": 12,
|
121 |
+
"pad_token_id": 0,
|
122 |
+
"position_embedding_type": "absolute",
|
123 |
+
"problem_type": "single_label_classification",
|
124 |
+
"torch_dtype": "float32",
|
125 |
+
"transformers_version": "4.44.0.dev0",
|
126 |
+
"type_vocab_size": 2,
|
127 |
+
"use_cache": true,
|
128 |
+
"vocab_size": 30000
|
129 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76cbdbb60327ef2490b757bde465dd28d47a9d68fde85bf31f3a66d40b268588
|
3 |
+
size 436499628
|
runs/Aug06_13-28-33_10db6dd1f421/events.out.tfevents.1722950924.10db6dd1f421.959.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0062d70a4b4a20e43ecea222269addaf68179eb95f560e811fce32778188b5fb
|
3 |
+
size 10030
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"2": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e81911aff73cd24327c590422964b2e1d0f1fbc8b39abd845bbefdd204d7c63d
|
3 |
+
size 5240
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|