Hoan2k3 commited on
Commit
77e67f0
·
verified ·
1 Parent(s): cd54a6a

Upload dataset_metadata.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. dataset_metadata.json +22 -33
dataset_metadata.json CHANGED
@@ -1,50 +1,39 @@
1
  {
2
- "total_raw_samples_skipped": 6839,
3
- "total_valid_samples": 7130,
4
  "classes": [
5
- "Data & AI",
6
  "Infra, Sec, IoT",
7
  "Management & Sales",
8
- "Software Dev",
9
- "UI/UX Design"
10
  ],
11
- "train_size": 5704,
12
- "val_size": 713,
13
- "test_size": 713,
14
  "token_length_stats": {
15
  "max_length_used_in_training": 256,
16
- "min_tokens_real": 5,
17
- "max_tokens_real": 3848,
18
- "mean_tokens": 280.92538569424966,
19
- "samples_truncated": 3209,
20
- "truncation_rate_percentage": 45.0070126227209
21
  },
22
  "label_cardinality_distribution": {
23
- "1": 5908,
24
- "2": 773,
25
- "3": 357,
26
- "4": 83,
27
- "5": 9
28
  },
29
  "label_distribution_train": {
30
- "Data & AI": 468,
31
- "Infra, Sec, IoT": 1430,
32
- "Management & Sales": 1401,
33
- "Software Dev": 3642,
34
- "UI/UX Design": 183
35
  },
36
  "label_distribution_val": {
37
- "Data & AI": 58,
38
- "Infra, Sec, IoT": 178,
39
- "Management & Sales": 176,
40
- "Software Dev": 456,
41
- "UI/UX Design": 23
42
  },
43
  "label_distribution_test": {
44
- "Data & AI": 57,
45
- "Infra, Sec, IoT": 179,
46
- "Management & Sales": 173,
47
- "Software Dev": 455,
48
- "UI/UX Design": 23
49
  }
50
  }
 
1
  {
2
+ "total_raw_samples_skipped": 0,
3
+ "total_valid_samples": 10,
4
  "classes": [
 
5
  "Infra, Sec, IoT",
6
  "Management & Sales",
7
+ "Software Dev"
 
8
  ],
9
+ "train_size": 8,
10
+ "val_size": 1,
11
+ "test_size": 1,
12
  "token_length_stats": {
13
  "max_length_used_in_training": 256,
14
+ "min_tokens_real": 41,
15
+ "max_tokens_real": 636,
16
+ "mean_tokens": 313.7,
17
+ "samples_truncated": 7,
18
+ "truncation_rate_percentage": 70.0
19
  },
20
  "label_cardinality_distribution": {
21
+ "1": 9,
22
+ "3": 1
 
 
 
23
  },
24
  "label_distribution_train": {
25
+ "Infra, Sec, IoT": 5,
26
+ "Management & Sales": 2,
27
+ "Software Dev": 3
 
 
28
  },
29
  "label_distribution_val": {
30
+ "Infra, Sec, IoT": 0,
31
+ "Management & Sales": 0,
32
+ "Software Dev": 1
 
 
33
  },
34
  "label_distribution_test": {
35
+ "Infra, Sec, IoT": 1,
36
+ "Management & Sales": 0,
37
+ "Software Dev": 0
 
 
38
  }
39
  }