Prience91 commited on
Commit
2de341f
·
verified ·
1 Parent(s): cef1fa4

Training is complete

Browse files
Files changed (6) hide show
  1. README.md +69 -0
  2. config.json +52 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +12 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: huggingface-course/bert-finetuned-ner
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: ner_model_output
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # ner_model_output
21
+
22
+ This model is a fine-tuned version of [huggingface-course/bert-finetuned-ner](https://huggingface.co/huggingface-course/bert-finetuned-ner) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2567
25
+ - Precision: 0.6421
26
+ - Recall: 0.6747
27
+ - F1: 0.6580
28
+ - Accuracy: 0.9242
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.4135 | 1.0 | 1756 | 0.3290 | 0.5395 | 0.5106 | 0.5246 | 0.8946 |
60
+ | 0.2314 | 2.0 | 3512 | 0.2702 | 0.6515 | 0.6254 | 0.6382 | 0.9213 |
61
+ | 0.1599 | 3.0 | 5268 | 0.2567 | 0.6421 | 0.6747 | 0.6580 | 0.9242 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 5.14.1
67
+ - Pytorch 2.13.0+cu130
68
+ - Datasets 5.0.0
69
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-PER",
18
+ "2": "I-PER",
19
+ "3": "B-ORG",
20
+ "4": "I-ORG",
21
+ "5": "B-LOC",
22
+ "6": "I-LOC",
23
+ "7": "B-MISC",
24
+ "8": "I-MISC"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "is_decoder": false,
29
+ "label2id": {
30
+ "B-LOC": 5,
31
+ "B-MISC": 7,
32
+ "B-ORG": 3,
33
+ "B-PER": 1,
34
+ "I-LOC": 6,
35
+ "I-MISC": 8,
36
+ "I-ORG": 4,
37
+ "I-PER": 2,
38
+ "O": 0
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "bert",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 0,
46
+ "position_embedding_type": "absolute",
47
+ "tie_word_embeddings": true,
48
+ "transformers_version": "5.14.1",
49
+ "type_vocab_size": 2,
50
+ "use_cache": false,
51
+ "vocab_size": 28996
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff30cd38c3e0873f9dd1f89cadb28ebad7b4149ff6fb93e3d257cba3bda9751f
3
+ size 430929740
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "is_local": false,
5
+ "local_files_only": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "tokenizer_class": "TokenizersBackend",
11
+ "unk_token": "[UNK]"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d88e26e17ae31ce9a772c36d1c551776ce3f2a1f26c28eff8be7e860aa32fc3
3
+ size 5201