pingkeest/newly_fine_tuned_bert
Browse files- README.md +53 -0
- config.json +185 -0
- model.safetensors +3 -0
- runs/Nov03_13-36-42_PingkeePC/events.out.tfevents.1730612207.PingkeePC +3 -0
- runs/Nov03_13-37-49_PingkeePC/events.out.tfevents.1730612272.PingkeePC +3 -0
- runs/Nov03_13-39-56_PingkeePC/events.out.tfevents.1730612399.PingkeePC +3 -0
- runs/Nov03_13-41-08_PingkeePC/events.out.tfevents.1730612471.PingkeePC +3 -0
- runs/Nov03_13-50-20_PingkeePC/events.out.tfevents.1730613025.PingkeePC +3 -0
- runs/Nov03_13-52-46_PingkeePC/events.out.tfevents.1730613169.PingkeePC +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: bert-base-uncased
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: newly_fine_tuned_bert
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# newly_fine_tuned_bert
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 5e-05
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 3
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.45.2
|
51 |
+
- Pytorch 2.4.0+cu124
|
52 |
+
- Datasets 3.0.1
|
53 |
+
- Tokenizers 0.20.1
|
config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "1000",
|
14 |
+
"1": "1001",
|
15 |
+
"2": "1002",
|
16 |
+
"3": "1004",
|
17 |
+
"4": "1005",
|
18 |
+
"5": "1006",
|
19 |
+
"6": "1007",
|
20 |
+
"7": "1008",
|
21 |
+
"8": "1009",
|
22 |
+
"9": "1010",
|
23 |
+
"10": "1011",
|
24 |
+
"11": "1012",
|
25 |
+
"12": "1013",
|
26 |
+
"13": "1014",
|
27 |
+
"14": "1015",
|
28 |
+
"15": "1016",
|
29 |
+
"16": "1017",
|
30 |
+
"17": "1018",
|
31 |
+
"18": "1019",
|
32 |
+
"19": "1020",
|
33 |
+
"20": "1021",
|
34 |
+
"21": "1022",
|
35 |
+
"22": "1023",
|
36 |
+
"23": "1024",
|
37 |
+
"24": "1025",
|
38 |
+
"25": "1026",
|
39 |
+
"26": "1027",
|
40 |
+
"27": "1028",
|
41 |
+
"28": "1029",
|
42 |
+
"29": "1030",
|
43 |
+
"30": "1031",
|
44 |
+
"31": "1032",
|
45 |
+
"32": "1033",
|
46 |
+
"33": "1034",
|
47 |
+
"34": "1035",
|
48 |
+
"35": "1036",
|
49 |
+
"36": "1037",
|
50 |
+
"37": "1038",
|
51 |
+
"38": "1039",
|
52 |
+
"39": "1040",
|
53 |
+
"40": "1041",
|
54 |
+
"41": "1042",
|
55 |
+
"42": "1043",
|
56 |
+
"43": "1044",
|
57 |
+
"44": "1045",
|
58 |
+
"45": "1046",
|
59 |
+
"46": "1047",
|
60 |
+
"47": "1048",
|
61 |
+
"48": "1049",
|
62 |
+
"49": "1050",
|
63 |
+
"50": "1051",
|
64 |
+
"51": "1052",
|
65 |
+
"52": "1053",
|
66 |
+
"53": "1054",
|
67 |
+
"54": "1055",
|
68 |
+
"55": "1056",
|
69 |
+
"56": "1057",
|
70 |
+
"57": "1058",
|
71 |
+
"58": "1059",
|
72 |
+
"59": "1060",
|
73 |
+
"60": "1061",
|
74 |
+
"61": "1062",
|
75 |
+
"62": "1063",
|
76 |
+
"63": "1064",
|
77 |
+
"64": "1065",
|
78 |
+
"65": "1066",
|
79 |
+
"66": "1067",
|
80 |
+
"67": "1068",
|
81 |
+
"68": "1069",
|
82 |
+
"69": "1070",
|
83 |
+
"70": "1071",
|
84 |
+
"71": "1072",
|
85 |
+
"72": "1073",
|
86 |
+
"73": "1074",
|
87 |
+
"74": "1075",
|
88 |
+
"75": "1076",
|
89 |
+
"76": "1077"
|
90 |
+
},
|
91 |
+
"initializer_range": 0.02,
|
92 |
+
"intermediate_size": 3072,
|
93 |
+
"label2id": {
|
94 |
+
"1000": 0,
|
95 |
+
"1001": 1,
|
96 |
+
"1002": 2,
|
97 |
+
"1004": 3,
|
98 |
+
"1005": 4,
|
99 |
+
"1006": 5,
|
100 |
+
"1007": 6,
|
101 |
+
"1008": 7,
|
102 |
+
"1009": 8,
|
103 |
+
"1010": 9,
|
104 |
+
"1011": 10,
|
105 |
+
"1012": 11,
|
106 |
+
"1013": 12,
|
107 |
+
"1014": 13,
|
108 |
+
"1015": 14,
|
109 |
+
"1016": 15,
|
110 |
+
"1017": 16,
|
111 |
+
"1018": 17,
|
112 |
+
"1019": 18,
|
113 |
+
"1020": 19,
|
114 |
+
"1021": 20,
|
115 |
+
"1022": 21,
|
116 |
+
"1023": 22,
|
117 |
+
"1024": 23,
|
118 |
+
"1025": 24,
|
119 |
+
"1026": 25,
|
120 |
+
"1027": 26,
|
121 |
+
"1028": 27,
|
122 |
+
"1029": 28,
|
123 |
+
"1030": 29,
|
124 |
+
"1031": 30,
|
125 |
+
"1032": 31,
|
126 |
+
"1033": 32,
|
127 |
+
"1034": 33,
|
128 |
+
"1035": 34,
|
129 |
+
"1036": 35,
|
130 |
+
"1037": 36,
|
131 |
+
"1038": 37,
|
132 |
+
"1039": 38,
|
133 |
+
"1040": 39,
|
134 |
+
"1041": 40,
|
135 |
+
"1042": 41,
|
136 |
+
"1043": 42,
|
137 |
+
"1044": 43,
|
138 |
+
"1045": 44,
|
139 |
+
"1046": 45,
|
140 |
+
"1047": 46,
|
141 |
+
"1048": 47,
|
142 |
+
"1049": 48,
|
143 |
+
"1050": 49,
|
144 |
+
"1051": 50,
|
145 |
+
"1052": 51,
|
146 |
+
"1053": 52,
|
147 |
+
"1054": 53,
|
148 |
+
"1055": 54,
|
149 |
+
"1056": 55,
|
150 |
+
"1057": 56,
|
151 |
+
"1058": 57,
|
152 |
+
"1059": 58,
|
153 |
+
"1060": 59,
|
154 |
+
"1061": 60,
|
155 |
+
"1062": 61,
|
156 |
+
"1063": 62,
|
157 |
+
"1064": 63,
|
158 |
+
"1065": 64,
|
159 |
+
"1066": 65,
|
160 |
+
"1067": 66,
|
161 |
+
"1068": 67,
|
162 |
+
"1069": 68,
|
163 |
+
"1070": 69,
|
164 |
+
"1071": 70,
|
165 |
+
"1072": 71,
|
166 |
+
"1073": 72,
|
167 |
+
"1074": 73,
|
168 |
+
"1075": 74,
|
169 |
+
"1076": 75,
|
170 |
+
"1077": 76
|
171 |
+
},
|
172 |
+
"layer_norm_eps": 1e-12,
|
173 |
+
"max_position_embeddings": 512,
|
174 |
+
"model_type": "bert",
|
175 |
+
"num_attention_heads": 12,
|
176 |
+
"num_hidden_layers": 12,
|
177 |
+
"pad_token_id": 0,
|
178 |
+
"position_embedding_type": "absolute",
|
179 |
+
"problem_type": "multi_label_classification",
|
180 |
+
"torch_dtype": "float32",
|
181 |
+
"transformers_version": "4.45.2",
|
182 |
+
"type_vocab_size": 2,
|
183 |
+
"use_cache": true,
|
184 |
+
"vocab_size": 30522
|
185 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7045cf4968a2533c15588bbebf1b8f6829409c464d49bbc2ac118509605c339d
|
3 |
+
size 438189348
|
runs/Nov03_13-36-42_PingkeePC/events.out.tfevents.1730612207.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6cbaeb88728df3af9412f381a85536bd86b8f7bf7bc91cf559f34fcbc1348d
|
3 |
+
size 7583
|
runs/Nov03_13-37-49_PingkeePC/events.out.tfevents.1730612272.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:006dfa4e8dbfd9cc61d250651faf8279bbc7a5d78a90be553e2054064cab451e
|
3 |
+
size 7583
|
runs/Nov03_13-39-56_PingkeePC/events.out.tfevents.1730612399.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f44247a092d3da313fd91abe45d833bd37d91aced50e310d4c3e704d10a51681
|
3 |
+
size 7583
|
runs/Nov03_13-41-08_PingkeePC/events.out.tfevents.1730612471.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be87e8c7508d9428a614f2a9ceb01ea985684148ff101896fd2068aaa4fb3df1
|
3 |
+
size 7926
|
runs/Nov03_13-50-20_PingkeePC/events.out.tfevents.1730613025.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61eb95665908258f9b4ca413f3081338d8c02fdf1cefbf94aec9db23fff38948
|
3 |
+
size 7926
|
runs/Nov03_13-52-46_PingkeePC/events.out.tfevents.1730613169.PingkeePC
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da17975f0e0b821092fcad1c570d95d14a23663e2b9abc823b809534e381c82b
|
3 |
+
size 7926
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2bc4ea3390b594e2a3ddcd21c9075ef96a9a7d0c4ae2cd4e1147e14063f2df3
|
3 |
+
size 5240
|