Upload TFBertForTokenClassification
Browse files- README.md +65 -0
- config.json +51 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: NERTESTING
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# NERTESTING
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.0080
|
| 18 |
+
- Validation Loss: 0.2646
|
| 19 |
+
- Epoch: 12
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 28900, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
| 39 |
+
- training_precision: mixed_float16
|
| 40 |
+
|
| 41 |
+
### Training results
|
| 42 |
+
|
| 43 |
+
| Train Loss | Validation Loss | Epoch |
|
| 44 |
+
|:----------:|:---------------:|:-----:|
|
| 45 |
+
| 0.4750 | 0.1843 | 0 |
|
| 46 |
+
| 0.1754 | 0.2091 | 1 |
|
| 47 |
+
| 0.1081 | 0.1819 | 2 |
|
| 48 |
+
| 0.0658 | 0.2115 | 3 |
|
| 49 |
+
| 0.0463 | 0.2220 | 4 |
|
| 50 |
+
| 0.0281 | 0.1990 | 5 |
|
| 51 |
+
| 0.0268 | 0.2807 | 6 |
|
| 52 |
+
| 0.0249 | 0.3543 | 7 |
|
| 53 |
+
| 0.0178 | 0.2623 | 8 |
|
| 54 |
+
| 0.0122 | 0.3002 | 9 |
|
| 55 |
+
| 0.0137 | 0.2659 | 10 |
|
| 56 |
+
| 0.0111 | 0.2615 | 11 |
|
| 57 |
+
| 0.0080 | 0.2646 | 12 |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- Transformers 4.22.1
|
| 63 |
+
- TensorFlow 2.8.2
|
| 64 |
+
- Datasets 2.5.1
|
| 65 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 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 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "B-Brand",
|
| 15 |
+
"10": "I-TM",
|
| 16 |
+
"2": "I-brand",
|
| 17 |
+
"3": "B-Model",
|
| 18 |
+
"4": "I-Model",
|
| 19 |
+
"5": "B-Tipe",
|
| 20 |
+
"6": "I-Tipe",
|
| 21 |
+
"7": "B-CC",
|
| 22 |
+
"8": "I-CC",
|
| 23 |
+
"9": "B-TM"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"B-Brand": "1",
|
| 29 |
+
"B-CC": "7",
|
| 30 |
+
"B-Model": "3",
|
| 31 |
+
"B-TM": "9",
|
| 32 |
+
"B-Tipe": "5",
|
| 33 |
+
"I-CC": "8",
|
| 34 |
+
"I-Model": "4",
|
| 35 |
+
"I-TM": "10",
|
| 36 |
+
"I-Tipe": "6",
|
| 37 |
+
"I-brand": "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 |
+
"transformers_version": "4.22.1",
|
| 48 |
+
"type_vocab_size": 2,
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 28996
|
| 51 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c4bb67c4c70e979989717ab5ab5df35b00b3eb7cfad26f3f4b8930e72e4fe83
|
| 3 |
+
size 431198260
|