Hugging Face's logo

LightFury9
/
nlp-mini-project

Token Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
LightFury9 commited on
Commit
1295255
•
1 Parent(s): f544780

End of training

Browse files
Files changed (17) hide show
  1. README.md +84 -0
  2. config.json +53 -0
  3. model.safetensors +3 -0
  4. runs/Dec07_05-41-59_71cdfe336f81/events.out.tfevents.1701927727.71cdfe336f81.3088.0 +3 -0
  5. runs/Dec07_05-49-15_71cdfe336f81/events.out.tfevents.1701928155.71cdfe336f81.3088.1 +3 -0
  6. runs/Dec07_05-51-38_71cdfe336f81/events.out.tfevents.1701928298.71cdfe336f81.3088.2 +3 -0
  7. runs/Dec07_05-54-06_71cdfe336f81/events.out.tfevents.1701928446.71cdfe336f81.3088.3 +3 -0
  8. runs/Dec07_05-54-30_71cdfe336f81/events.out.tfevents.1701928471.71cdfe336f81.3088.4 +3 -0
  9. runs/Dec07_05-59-34_71cdfe336f81/events.out.tfevents.1701928774.71cdfe336f81.3088.5 +3 -0
  10. runs/Dec07_05-59-58_71cdfe336f81/events.out.tfevents.1701928798.71cdfe336f81.3088.6 +3 -0
  11. runs/Dec07_06-42-44_71cdfe336f81/events.out.tfevents.1701931370.71cdfe336f81.17333.0 +3 -0
  12. runs/Dec07_06-52-47_71cdfe336f81/events.out.tfevents.1701931967.71cdfe336f81.17333.1 +3 -0
  13. special_tokens_map.json +7 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +55 -0
  16. training_args.bin +3 -0
  17. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: distilbert-base-uncased
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: nlp-mini-prj
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # nlp-mini-prj
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0000
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 100
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.0841 | 3.76 | 500 | 0.0005 |
52
+ | 0.0015 | 7.52 | 1000 | 0.0002 |
53
+ | 0.0011 | 11.28 | 1500 | 0.0001 |
54
+ | 0.0042 | 15.04 | 2000 | 0.0001 |
55
+ | 0.0008 | 18.8 | 2500 | 0.0001 |
56
+ | 0.0004 | 22.56 | 3000 | 0.0001 |
57
+ | 0.0001 | 26.32 | 3500 | 0.0000 |
58
+ | 0.0001 | 30.08 | 4000 | 0.0000 |
59
+ | 0.0001 | 33.83 | 4500 | 0.0000 |
60
+ | 0.0001 | 37.59 | 5000 | 0.0000 |
61
+ | 0.0 | 41.35 | 5500 | 0.0000 |
62
+ | 0.0 | 45.11 | 6000 | 0.0000 |
63
+ | 0.0 | 48.87 | 6500 | 0.0000 |
64
+ | 0.0 | 52.63 | 7000 | 0.0000 |
65
+ | 0.0 | 56.39 | 7500 | 0.0000 |
66
+ | 0.0 | 60.15 | 8000 | 0.0000 |
67
+ | 0.0 | 63.91 | 8500 | 0.0000 |
68
+ | 0.0 | 67.67 | 9000 | 0.0000 |
69
+ | 0.0 | 71.43 | 9500 | 0.0000 |
70
+ | 0.0 | 75.19 | 10000 | 0.0000 |
71
+ | 0.0 | 78.95 | 10500 | 0.0000 |
72
+ | 0.0 | 82.71 | 11000 | 0.0000 |
73
+ | 0.0 | 86.47 | 11500 | 0.0000 |
74
+ | 0.0 | 90.23 | 12000 | 0.0000 |
75
+ | 0.0 | 93.98 | 12500 | 0.0000 |
76
+ | 0.0 | 97.74 | 13000 | 0.0000 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.35.2
82
+ - Pytorch 2.1.0+cu118
83
+ - Datasets 2.15.0
84
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "ner",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "B-move",
14
+ "1": "I-move",
15
+ "2": "B-pick",
16
+ "3": "I-pick",
17
+ "4": "B-drop",
18
+ "5": "I-drop",
19
+ "6": "B-obj",
20
+ "7": "B-loc",
21
+ "8": "I-loc",
22
+ "9": "B-furn",
23
+ "10": "I-furn",
24
+ "11": "O"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "B-drop": 4,
29
+ "B-furn": 9,
30
+ "B-loc": 7,
31
+ "B-move": 0,
32
+ "B-obj": 6,
33
+ "B-pick": 2,
34
+ "I-drop": 5,
35
+ "I-furn": 10,
36
+ "I-loc": 8,
37
+ "I-move": 1,
38
+ "I-pick": 3,
39
+ "O": 11
40
+ },
41
+ "max_position_embeddings": 512,
42
+ "model_type": "distilbert",
43
+ "n_heads": 12,
44
+ "n_layers": 6,
45
+ "pad_token_id": 0,
46
+ "qa_dropout": 0.1,
47
+ "seq_classif_dropout": 0.2,
48
+ "sinusoidal_pos_embds": false,
49
+ "tie_weights_": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.35.2",
52
+ "vocab_size": 30522
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5289b7a9d19ddc22e333030ab9c63ddb8831a85e42f90ff087a1bd8742c877
3
+ size 265500776
runs/Dec07_05-41-59_71cdfe336f81/events.out.tfevents.1701927727.71cdfe336f81.3088.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53deb30aa66acad36552f19d7665c93bbce9bbdce35fe8c3f6284baf9964700e
3
+ size 10460
runs/Dec07_05-49-15_71cdfe336f81/events.out.tfevents.1701928155.71cdfe336f81.3088.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104259d8be87b5d1c589275687acbd633b7aed40072691304ae750b86b92d269
3
+ size 7672
runs/Dec07_05-51-38_71cdfe336f81/events.out.tfevents.1701928298.71cdfe336f81.3088.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d70be3f39af618e8893c84c950611f7ef753ad3b833980754780ef0bdc2284c
3
+ size 4700
runs/Dec07_05-54-06_71cdfe336f81/events.out.tfevents.1701928446.71cdfe336f81.3088.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ec520471aebd241c7c035ce3cb23700570a71f90a898f8d7a5510a885b189a
3
+ size 5747
runs/Dec07_05-54-30_71cdfe336f81/events.out.tfevents.1701928471.71cdfe336f81.3088.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6debb3a56599d9b88e9e67dd1480bb080c56c1fc2e7b8c0b66b6532bd92e9303
3
+ size 6391
runs/Dec07_05-59-34_71cdfe336f81/events.out.tfevents.1701928774.71cdfe336f81.3088.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c313fdaf2b5879d262ca905cd5400a34807ac71cb091a897a1cceceead98410
3
+ size 4547
runs/Dec07_05-59-58_71cdfe336f81/events.out.tfevents.1701928798.71cdfe336f81.3088.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a764b5e705476068f61a17131b1f2f896884ed5f6dad73ff3466b84c9695b26
3
+ size 12138
runs/Dec07_06-42-44_71cdfe336f81/events.out.tfevents.1701931370.71cdfe336f81.17333.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4594759757feb7a45c836382515a10096bf4905a21d70e53a4dc0df112491c
3
+ size 14428
runs/Dec07_06-52-47_71cdfe336f81/events.out.tfevents.1701931967.71cdfe336f81.17333.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85f594bb7e4ce7c68a0d0e395b66f8dfbaf0d2aca25e215a0a7824c8e066db6
3
+ size 16066
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb19ae30c418df4cb67f3ee63ee680e79e66ea9abd190c6903b39c75d3f3bd6
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff