BaselMousi commited on
Commit
59c22d7
·
verified ·
1 Parent(s): 6347475

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - wnut_17
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ - accuracy
14
+ model-index:
15
+ - name: distilbert_wnut_model
16
+ results:
17
+ - task:
18
+ name: Token Classification
19
+ type: token-classification
20
+ dataset:
21
+ name: wnut_17
22
+ type: wnut_17
23
+ config: wnut_17
24
+ split: test
25
+ args: wnut_17
26
+ metrics:
27
+ - name: Precision
28
+ type: precision
29
+ value: 0.559040590405904
30
+ - name: Recall
31
+ type: recall
32
+ value: 0.2808155699721965
33
+ - name: F1
34
+ type: f1
35
+ value: 0.3738433066008636
36
+ - name: Accuracy
37
+ type: accuracy
38
+ value: 0.9409601983668933
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # distilbert_wnut_model
45
+
46
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.2784
49
+ - Precision: 0.5590
50
+ - Recall: 0.2808
51
+ - F1: 0.3738
52
+ - Accuracy: 0.9410
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 2e-05
72
+ - train_batch_size: 16
73
+ - eval_batch_size: 16
74
+ - seed: 42
75
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
76
+ - lr_scheduler_type: linear
77
+ - num_epochs: 2
78
+
79
+ ### Training results
80
+
81
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | No log | 1.0 | 213 | 0.2856 | 0.4622 | 0.2150 | 0.2935 | 0.9368 |
84
+ | No log | 2.0 | 426 | 0.2784 | 0.5590 | 0.2808 | 0.3738 | 0.9410 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.49.0
90
+ - Pytorch 2.6.0+cu124
91
+ - Datasets 3.4.1
92
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
13
+ "1": "B-corporation",
14
+ "2": "I-corporation",
15
+ "3": "B-creative-work",
16
+ "4": "I-creative-work",
17
+ "5": "B-group",
18
+ "6": "I-group",
19
+ "7": "B-location",
20
+ "8": "I-location",
21
+ "9": "B-person",
22
+ "10": "I-person",
23
+ "11": "B-product",
24
+ "12": "I-product"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "B-corporation": 1,
29
+ "B-creative-work": 3,
30
+ "B-group": 5,
31
+ "B-location": 7,
32
+ "B-person": 9,
33
+ "B-product": 11,
34
+ "I-corporation": 2,
35
+ "I-creative-work": 4,
36
+ "I-group": 6,
37
+ "I-location": 8,
38
+ "I-person": 10,
39
+ "I-product": 12,
40
+ "O": 0
41
+ },
42
+ "max_position_embeddings": 512,
43
+ "model_type": "distilbert",
44
+ "n_heads": 12,
45
+ "n_layers": 6,
46
+ "pad_token_id": 0,
47
+ "qa_dropout": 0.1,
48
+ "seq_classif_dropout": 0.2,
49
+ "sinusoidal_pos_embds": false,
50
+ "tie_weights_": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.49.0",
53
+ "vocab_size": 30522
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36183d8caf70a666ff1cfd6a383f1f6a01bebef50cdffffaa89b3f5a90129052
3
+ size 265503852
runs/Mar24_07-48-43_5b1bc1e3325d/events.out.tfevents.1742802534.5b1bc1e3325d.1827.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcefd0099434bafaf84ef880258d2fd2054f914a818904dc8574b1b55add3c65
3
+ size 6888
runs/Mar24_07-52-29_5b1bc1e3325d/events.out.tfevents.1742802750.5b1bc1e3325d.1827.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb653e39d00729767faa336588b58fd3d9b0325d05e17595d43aa7b871058bba
3
+ size 7591
runs/Mar24_08-20-40_5b1bc1e3325d/events.out.tfevents.1742804442.5b1bc1e3325d.11700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835139daa0474ac30e246862aa6a77f6f734256880f274e5f5e8e7dc8006090a
3
+ size 6073
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
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:c5e607f9cbbf6509d329fada507f60ea70d48230a37b04150308e08b64a5a969
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff