pavithrav commited on
Commit
597c2b7
1 Parent(s): c0dce96

complete the training

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: distilbert-base-uncased-finetuned-custom-data
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # distilbert-base-uncased-finetuned-custom-data
18
+
19
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.3125
22
+ - Accuracy: 0.6929
23
+ - F1: 0.6442
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 64
44
+ - eval_batch_size: 64
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 2
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | 2.6735 | 1.0 | 7 | 2.5007 | 0.3786 | 0.2079 |
55
+ | 2.5092 | 2.0 | 14 | 2.3125 | 0.6929 | 0.6442 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.33.3
61
+ - Pytorch 2.0.1+cu118
62
+ - Datasets 2.14.5
63
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1,
32
+ "LABEL_10": 10,
33
+ "LABEL_11": 11,
34
+ "LABEL_12": 12,
35
+ "LABEL_13": 13,
36
+ "LABEL_14": 14,
37
+ "LABEL_2": 2,
38
+ "LABEL_3": 3,
39
+ "LABEL_4": 4,
40
+ "LABEL_5": 5,
41
+ "LABEL_6": 6,
42
+ "LABEL_7": 7,
43
+ "LABEL_8": 8,
44
+ "LABEL_9": 9
45
+ },
46
+ "max_position_embeddings": 512,
47
+ "model_type": "distilbert",
48
+ "n_heads": 12,
49
+ "n_layers": 6,
50
+ "pad_token_id": 0,
51
+ "problem_type": "single_label_classification",
52
+ "qa_dropout": 0.1,
53
+ "seq_classif_dropout": 0.2,
54
+ "sinusoidal_pos_embds": false,
55
+ "tie_weights_": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.33.3",
58
+ "vocab_size": 30522
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7089a535e038310180680c20fc932d355ca6b58057b97054650bca3641f17ff9
3
+ size 267895533
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186354602bbb854be6cd9bf780feaddd7277a1bbd8de1231985c86f42c11a5a0
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff