cria111 commited on
Commit
e7a33c4
1 Parent(s): 4646fe2

cria111/distilbert-base-uncased-no-perturb-early-stopping

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: training_with_callbacks
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # training_with_callbacks
20
+
21
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1529
24
+ - Precision: 0.4993
25
+ - Recall: 0.5397
26
+ - F1: 0.5187
27
+ - Accuracy: 0.9661
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 205 | 0.1641 | 0.3048 | 0.3556 | 0.3282 | 0.9556 |
59
+ | No log | 2.0 | 410 | 0.1387 | 0.4741 | 0.4365 | 0.4545 | 0.9642 |
60
+ | 0.1943 | 3.0 | 615 | 0.1430 | 0.4690 | 0.4810 | 0.4749 | 0.9648 |
61
+ | 0.1943 | 4.0 | 820 | 0.1481 | 0.4993 | 0.5365 | 0.5172 | 0.9655 |
62
+ | 0.0496 | 5.0 | 1025 | 0.1529 | 0.4993 | 0.5397 | 0.5187 | 0.9661 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.38.2
68
+ - Pytorch 2.2.0+cpu
69
+ - Datasets 2.18.0
70
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
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
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5,
30
+ "LABEL_6": 6,
31
+ "LABEL_7": 7,
32
+ "LABEL_8": 8
33
+ },
34
+ "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "pad_token_id": 0,
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": false,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.38.2",
45
+ "vocab_size": 30522
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6641ae7f9c71a72a04b5832772286328b77d79d0961a0653ede5266c37f14c23
3
+ size 265491548
runs/Apr29_15-49-20_pav/events.out.tfevents.1714398571.pav.8476.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13908f450ab292e5e051075c5947505ebc99a8150936cb6276a44c959d03c70
3
+ size 7997
runs/Apr29_15-49-20_pav/events.out.tfevents.1714400132.pav.8476.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac08af93524701ecdd9ac3402be3e7a13bfa736804b9fa42bf4a223161497f0
3
+ size 560
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "padding": true,
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5847856bb63e56084ea1425373714ba5d87d0ef7bee1940a1952b81bbfde2750
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff