Hugging Face's logo

lmaccarini
/
not-ner-v2

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
lmaccarini commited on
Commit
689b319
·
verified ·
1 Parent(s): df1e221

End of training

Browse files
Files changed (6) hide show
  1. README.md +83 -0
  2. config.json +28 -0
  3. model.safetensors +3 -0
  4. runs/Aug20_16-49-29_b5e10a5777ef/events.out.tfevents.1724172578.b5e10a5777ef.211.0 +3 -0
  5. runs/Aug20_16-49-29_b5e10a5777ef/events.out.tfevents.1724178671.b5e10a5777ef.211.1 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: dccuchile/tulio-chilean-spanish-bert
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: not-ner-v2
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
+ # not-ner-v2
20
+
21
+ This model is a fine-tuned version of [dccuchile/tulio-chilean-spanish-bert](https://huggingface.co/dccuchile/tulio-chilean-spanish-bert) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0838
24
+ - Accuracy: 0.9727
25
+ - Precision: 0.9723
26
+ - Recall: 0.9727
27
+ - F1: 0.9724
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: 5e-05
47
+ - train_batch_size: 32
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: 3
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.1679 | 0.1595 | 250 | 0.1431 | 0.9555 | 0.9546 | 0.9555 | 0.9549 |
59
+ | 0.1291 | 0.3191 | 500 | 0.1328 | 0.9595 | 0.9583 | 0.9595 | 0.9586 |
60
+ | 0.1055 | 0.4786 | 750 | 0.0925 | 0.9653 | 0.9648 | 0.9653 | 0.9650 |
61
+ | 0.1044 | 0.6382 | 1000 | 0.1415 | 0.9630 | 0.9619 | 0.9630 | 0.9615 |
62
+ | 0.1094 | 0.7977 | 1250 | 0.1030 | 0.9630 | 0.9624 | 0.9630 | 0.9612 |
63
+ | 0.0927 | 0.9572 | 1500 | 0.0878 | 0.9710 | 0.9706 | 0.9710 | 0.9707 |
64
+ | 0.0836 | 1.1168 | 1750 | 0.1265 | 0.9663 | 0.9666 | 0.9663 | 0.9665 |
65
+ | 0.0651 | 1.2763 | 2000 | 0.1025 | 0.9709 | 0.9702 | 0.9709 | 0.9704 |
66
+ | 0.0637 | 1.4359 | 2250 | 0.0998 | 0.9676 | 0.9668 | 0.9676 | 0.9667 |
67
+ | 0.0713 | 1.5954 | 2500 | 0.0838 | 0.9727 | 0.9723 | 0.9727 | 0.9724 |
68
+ | 0.0561 | 1.7549 | 2750 | 0.0905 | 0.9722 | 0.9722 | 0.9722 | 0.9722 |
69
+ | 0.058 | 1.9145 | 3000 | 0.1030 | 0.9707 | 0.9701 | 0.9707 | 0.9702 |
70
+ | 0.0531 | 2.0740 | 3250 | 0.1066 | 0.9714 | 0.9710 | 0.9714 | 0.9711 |
71
+ | 0.0398 | 2.2336 | 3500 | 0.1035 | 0.9722 | 0.9721 | 0.9722 | 0.9721 |
72
+ | 0.0444 | 2.3931 | 3750 | 0.1009 | 0.9728 | 0.9725 | 0.9728 | 0.9726 |
73
+ | 0.037 | 2.5526 | 4000 | 0.1068 | 0.9725 | 0.9721 | 0.9725 | 0.9722 |
74
+ | 0.0261 | 2.7122 | 4250 | 0.1192 | 0.9735 | 0.9731 | 0.9735 | 0.9732 |
75
+ | 0.0266 | 2.8717 | 4500 | 0.1191 | 0.9732 | 0.9727 | 0.9732 | 0.9729 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.42.4
81
+ - Pytorch 2.3.1+cu121
82
+ - Datasets 2.21.0
83
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/tulio-chilean-spanish-bert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.42.4",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ebaee33b0d8e5e18071e1822a2e245b8f5b1af819dce360f69f1ec316f740d
3
+ size 439433208
runs/Aug20_16-49-29_b5e10a5777ef/events.out.tfevents.1724172578.b5e10a5777ef.211.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10f827338d3166cbeb4917f98737b11580b05d21f5f0ca4b006a3eac47159eb
3
+ size 17733
runs/Aug20_16-49-29_b5e10a5777ef/events.out.tfevents.1724178671.b5e10a5777ef.211.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eba3c49502c4c2b595cc50a4d4113d1f37cf5385a92ab4abd796e7b46be9695
3
+ size 560
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868e0490ef260e1148781ee70d59cbb5549a962ab6cacf4eb6cbf75f58d928e8
3
+ size 5112