ft-distilbert-base-uncased-with-wnut17-v-0
Browse files- README.md +91 -0
- config.json +54 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wnut_17
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
+
model-index:
|
14 |
+
- name: ft-distilbert-base-uncased-with-wnut17-v-0
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: wnut_17
|
21 |
+
type: wnut_17
|
22 |
+
config: wnut_17
|
23 |
+
split: test
|
24 |
+
args: wnut_17
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.0
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.0
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.0
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9257834209738789
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# ft-distilbert-base-uncased-with-wnut17-v-0
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.3249
|
48 |
+
- Precision: 0.0
|
49 |
+
- Recall: 0.0
|
50 |
+
- F1: 0.0
|
51 |
+
- Accuracy: 0.9258
|
52 |
+
|
53 |
+
## Model description
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Intended uses & limitations
|
58 |
+
|
59 |
+
More information needed
|
60 |
+
|
61 |
+
## Training and evaluation data
|
62 |
+
|
63 |
+
More information needed
|
64 |
+
|
65 |
+
## Training procedure
|
66 |
+
|
67 |
+
### Training hyperparameters
|
68 |
+
|
69 |
+
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 2e-05
|
71 |
+
- train_batch_size: 64
|
72 |
+
- eval_batch_size: 64
|
73 |
+
- seed: 42
|
74 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
+
- lr_scheduler_type: linear
|
76 |
+
- num_epochs: 2
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
|
82 |
+
| No log | 1.0 | 54 | 0.3637 | 0.0 | 0.0 | 0.0 | 0.9256 |
|
83 |
+
| No log | 2.0 | 108 | 0.3249 | 0.0 | 0.0 | 0.0 | 0.9258 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.35.2
|
89 |
+
- Pytorch 2.0.0
|
90 |
+
- Datasets 2.15.0
|
91 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-corporation",
|
14 |
+
"2": "I-corporation",
|
15 |
+
"3": "B-creative-work",
|
16 |
+
"4": "I-creative-work",
|
17 |
+
"5": "B-group",
|
18 |
+
"6": "I-group",
|
19 |
+
"7": "B-location",
|
20 |
+
"8": "I-location",
|
21 |
+
"9": "B-person",
|
22 |
+
"10": "I-person",
|
23 |
+
"11": "B-product",
|
24 |
+
"12": "I-product"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"label2id": {
|
28 |
+
"B-corporation": 1,
|
29 |
+
"B-creative-work": 3,
|
30 |
+
"B-group": 5,
|
31 |
+
"B-location": 7,
|
32 |
+
"B-person": 9,
|
33 |
+
"B-product": 11,
|
34 |
+
"I-corporation": 2,
|
35 |
+
"I-creative-work": 4,
|
36 |
+
"I-group": 6,
|
37 |
+
"I-location": 8,
|
38 |
+
"I-person": 10,
|
39 |
+
"I-product": 12,
|
40 |
+
"O": 0
|
41 |
+
},
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "distilbert",
|
44 |
+
"n_heads": 12,
|
45 |
+
"n_layers": 6,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"qa_dropout": 0.1,
|
48 |
+
"seq_classif_dropout": 0.2,
|
49 |
+
"sinusoidal_pos_embds": false,
|
50 |
+
"tie_weights_": true,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.35.2",
|
53 |
+
"vocab_size": 30522
|
54 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9aed0d6c3cce54af9bb5a30427968ae9df2b83a8ad8fa246a46e8a97d401ba3
|
3 |
+
size 265503852
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1347228886c4de22ff4bb62ebfa5085b2677b4e2798fde75db1a63d0e16d5b1a
|
3 |
+
size 4219
|