Training in progress epoch 0
Browse files- README.md +22 -22
- config.json +18 -24
- tf_model.h5 +3 -0
README.md
CHANGED
@@ -1,21 +1,27 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
-
-
|
6 |
model-index:
|
7 |
-
- name: my_awesome_wnut_model
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
-
<!-- This model card has been generated automatically according to the information
|
12 |
-
|
13 |
|
14 |
-
# my_awesome_wnut_model
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,25 +40,19 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 2e-05
|
38 |
-
-
|
39 |
-
- eval_batch_size: 16
|
40 |
-
- seed: 42
|
41 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
-
- lr_scheduler_type: linear
|
43 |
-
- num_epochs: 2
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
-
|
|
48 |
-
|
49 |
-
|
|
50 |
-
| No log | 2.0 | 4 | nan |
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
- Transformers 4.
|
56 |
-
-
|
57 |
- Datasets 2.14.6
|
58 |
- Tokenizers 0.14.1
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
model-index:
|
7 |
+
- name: Horus7/my_awesome_wnut_model
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
# Horus7/my_awesome_wnut_model
|
15 |
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.4529
|
19 |
+
- Validation Loss: 1.3140
|
20 |
+
- Train Precision: 0.0
|
21 |
+
- Train Recall: 0.0
|
22 |
+
- Train F1: 0.0
|
23 |
+
- Train Accuracy: 0.6667
|
24 |
+
- Epoch: 0
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
44 |
+
- training_precision: float32
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
+
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
49 |
+
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
50 |
+
| 1.4529 | 1.3140 | 0.0 | 0.0 | 0.0 | 0.6667 | 0 |
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- Transformers 4.35.0
|
56 |
+
- TensorFlow 2.14.0
|
57 |
- Datasets 2.14.6
|
58 |
- Tokenizers 0.14.1
|
config.json
CHANGED
@@ -1,16 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"gradient_checkpointing": false,
|
11 |
-
"hidden_act": "gelu",
|
12 |
-
"hidden_dropout_prob": 0.1,
|
13 |
-
"hidden_size": 768,
|
14 |
"id2label": {
|
15 |
"0": "O",
|
16 |
"1": "B-depart",
|
@@ -19,7 +16,6 @@
|
|
19 |
"4": "I-arrive"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"intermediate_size": 3072,
|
23 |
"label2id": {
|
24 |
"B-arrive": 3,
|
25 |
"B-depart": 1,
|
@@ -27,17 +23,15 @@
|
|
27 |
"I-depart": 2,
|
28 |
"O": 0
|
29 |
},
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"transformers_version": "4.
|
40 |
-
"
|
41 |
-
"use_cache": true,
|
42 |
-
"vocab_size": 32005
|
43 |
}
|
|
|
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 |
+
"hidden_dim": 3072,
|
|
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
"1": "B-depart",
|
|
|
16 |
"4": "I-arrive"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
|
|
19 |
"label2id": {
|
20 |
"B-arrive": 3,
|
21 |
"B-depart": 1,
|
|
|
23 |
"I-depart": 2,
|
24 |
"O": 0
|
25 |
},
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "distilbert",
|
28 |
+
"n_heads": 12,
|
29 |
+
"n_layers": 6,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
+
"transformers_version": "4.35.0",
|
36 |
+
"vocab_size": 30522
|
|
|
|
|
37 |
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e7649e3d65b58f84289c1164dd805b473dea703c553e2caa3a12444490b6bfb
|
3 |
+
size 265594128
|