Steven Liu
commited on
Commit
•
0b80543
1
Parent(s):
1c66004
Training in progress epoch 0
Browse files- README.md +20 -54
- config.json +0 -1
- tf_model.h5 +3 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -1,53 +1,26 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
-
-
|
5 |
-
datasets:
|
6 |
-
- wnut_17
|
7 |
-
metrics:
|
8 |
-
- precision
|
9 |
-
- recall
|
10 |
-
- f1
|
11 |
-
- accuracy
|
12 |
model-index:
|
13 |
-
- name: my_awesome_wnut_model
|
14 |
-
results:
|
15 |
-
- task:
|
16 |
-
name: Token Classification
|
17 |
-
type: token-classification
|
18 |
-
dataset:
|
19 |
-
name: wnut_17
|
20 |
-
type: wnut_17
|
21 |
-
config: wnut_17
|
22 |
-
split: train
|
23 |
-
args: wnut_17
|
24 |
-
metrics:
|
25 |
-
- name: Precision
|
26 |
-
type: precision
|
27 |
-
value: 0.5310245310245311
|
28 |
-
- name: Recall
|
29 |
-
type: recall
|
30 |
-
value: 0.3410565338276182
|
31 |
-
- name: F1
|
32 |
-
type: f1
|
33 |
-
value: 0.4153498871331829
|
34 |
-
- name: Accuracy
|
35 |
-
type: accuracy
|
36 |
-
value: 0.9433542815612842
|
37 |
---
|
38 |
|
39 |
-
<!-- This model card has been generated automatically according to the information
|
40 |
-
|
41 |
|
42 |
-
# my_awesome_wnut_model
|
43 |
|
44 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
45 |
It achieves the following results on the evaluation set:
|
46 |
-
- Loss: 0.
|
47 |
-
-
|
48 |
-
-
|
49 |
-
-
|
50 |
-
-
|
|
|
|
|
51 |
|
52 |
## Model description
|
53 |
|
@@ -66,26 +39,19 @@ More information needed
|
|
66 |
### Training hyperparameters
|
67 |
|
68 |
The following hyperparameters were used during training:
|
69 |
-
- learning_rate: 2e-05
|
70 |
-
-
|
71 |
-
- eval_batch_size: 16
|
72 |
-
- seed: 42
|
73 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
-
- lr_scheduler_type: linear
|
75 |
-
- num_epochs: 3
|
76 |
|
77 |
### Training results
|
78 |
|
79 |
-
|
|
80 |
-
|
81 |
-
|
|
82 |
-
| No log | 2.0 | 426 | 0.2642 | 0.5698 | 0.3216 | 0.4111 | 0.9422 |
|
83 |
-
| 0.188 | 3.0 | 639 | 0.2699 | 0.5310 | 0.3411 | 0.4153 | 0.9434 |
|
84 |
|
85 |
|
86 |
### Framework versions
|
87 |
|
88 |
- Transformers 4.22.2
|
89 |
-
-
|
90 |
- Datasets 2.5.1
|
91 |
- Tokenizers 0.12.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
+
- generated_from_keras_callback
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
model-index:
|
6 |
+
- name: stevhliu/my_awesome_wnut_model
|
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 |
+
# stevhliu/my_awesome_wnut_model
|
14 |
|
15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.3233
|
18 |
+
- Validation Loss: 0.3099
|
19 |
+
- Train Precision: 0.4155
|
20 |
+
- Train Recall: 0.2117
|
21 |
+
- Train F1: 0.2805
|
22 |
+
- Train Accuracy: 0.9333
|
23 |
+
- Epoch: 0
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 636, '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}
|
43 |
+
- training_precision: float32
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
+
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
48 |
+
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
49 |
+
| 0.3233 | 0.3099 | 0.4155 | 0.2117 | 0.2805 | 0.9333 | 0 |
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.22.2
|
55 |
+
- TensorFlow 2.8.2
|
56 |
- Datasets 2.5.1
|
57 |
- Tokenizers 0.12.1
|
config.json
CHANGED
@@ -48,7 +48,6 @@
|
|
48 |
"seq_classif_dropout": 0.2,
|
49 |
"sinusoidal_pos_embds": false,
|
50 |
"tie_weights_": true,
|
51 |
-
"torch_dtype": "float32",
|
52 |
"transformers_version": "4.22.2",
|
53 |
"vocab_size": 30522
|
54 |
}
|
|
|
48 |
"seq_classif_dropout": 0.2,
|
49 |
"sinusoidal_pos_embds": false,
|
50 |
"tie_weights_": true,
|
|
|
51 |
"transformers_version": "4.22.2",
|
52 |
"vocab_size": 30522
|
53 |
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d09d6aaaf3f1cdae11cc3bec9be4c2b37de6bc816589862737768c7a9b3c362
|
3 |
+
size 265618792
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
-
"name_or_path": "
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"special_tokens_map_file": null,
|
|
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-uncased",
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"special_tokens_map_file": null,
|