Xtiphyn commited on
Commit
6feee6d
·
verified ·
1 Parent(s): 32e1d8f

xtiphyn/news-category-classification

Browse files
Files changed (4) hide show
  1. README.md +67 -0
  2. config.json +88 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: results
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # results
19
+
20
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.1131
23
+ - Accuracy: 0.7275
24
+ - F1: 0.7255
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 4
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
56
+ | 0.9698 | 1.0 | 5872 | 0.9485 | 0.7162 | 0.7105 |
57
+ | 0.7279 | 2.0 | 11744 | 0.9095 | 0.7329 | 0.7253 |
58
+ | 0.4669 | 3.0 | 17616 | 1.0053 | 0.7291 | 0.7257 |
59
+ | 0.2848 | 4.0 | 23488 | 1.1131 | 0.7275 | 0.7255 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.54.0
65
+ - Pytorch 2.6.0+cu124
66
+ - Datasets 4.0.0
67
+ - Tokenizers 0.21.2
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_10": 10,
47
+ "LABEL_11": 11,
48
+ "LABEL_12": 12,
49
+ "LABEL_13": 13,
50
+ "LABEL_14": 14,
51
+ "LABEL_15": 15,
52
+ "LABEL_16": 16,
53
+ "LABEL_17": 17,
54
+ "LABEL_18": 18,
55
+ "LABEL_19": 19,
56
+ "LABEL_2": 2,
57
+ "LABEL_20": 20,
58
+ "LABEL_21": 21,
59
+ "LABEL_22": 22,
60
+ "LABEL_23": 23,
61
+ "LABEL_24": 24,
62
+ "LABEL_25": 25,
63
+ "LABEL_26": 26,
64
+ "LABEL_27": 27,
65
+ "LABEL_28": 28,
66
+ "LABEL_29": 29,
67
+ "LABEL_3": 3,
68
+ "LABEL_4": 4,
69
+ "LABEL_5": 5,
70
+ "LABEL_6": 6,
71
+ "LABEL_7": 7,
72
+ "LABEL_8": 8,
73
+ "LABEL_9": 9
74
+ },
75
+ "max_position_embeddings": 512,
76
+ "model_type": "distilbert",
77
+ "n_heads": 12,
78
+ "n_layers": 6,
79
+ "pad_token_id": 0,
80
+ "problem_type": "single_label_classification",
81
+ "qa_dropout": 0.1,
82
+ "seq_classif_dropout": 0.2,
83
+ "sinusoidal_pos_embds": false,
84
+ "tie_weights_": true,
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.54.0",
87
+ "vocab_size": 30522
88
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69252b1daedf4f7e579b36fae334d35fd197859865846c6bba66c121e4c4d17
3
+ size 267918696
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727961f2fb934f7d9c2a5d50164a998b6457b796689bdd8ce117e38e589e8051
3
+ size 5754