ncardus/SeqClassifier
Browse files- README.md +82 -0
- config.json +26 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
- f1
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
model-index:
|
10 |
+
- name: BertSeq
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# BertSeq
|
18 |
+
|
19 |
+
This model was trained from scratch on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2244
|
22 |
+
- Accuracy: 1.0
|
23 |
+
- F1: 1.0
|
24 |
+
- Precision: 1.0
|
25 |
+
- Recall: 1.0
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 5e-05
|
45 |
+
- train_batch_size: 16
|
46 |
+
- eval_batch_size: 32
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 50
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|:---------:|:------:|
|
56 |
+
| 0.6468 | 2.5 | 5 | 0.5917 | 1.0 | 1.0 | 1.0 | 1.0 |
|
57 |
+
| 0.5888 | 5.0 | 10 | 0.5269 | 1.0 | 1.0 | 1.0 | 1.0 |
|
58 |
+
| 0.5427 | 7.5 | 15 | 0.4736 | 1.0 | 1.0 | 1.0 | 1.0 |
|
59 |
+
| 0.4919 | 10.0 | 20 | 0.4295 | 1.0 | 1.0 | 1.0 | 1.0 |
|
60 |
+
| 0.4872 | 12.5 | 25 | 0.3927 | 1.0 | 1.0 | 1.0 | 1.0 |
|
61 |
+
| 0.4447 | 15.0 | 30 | 0.3615 | 1.0 | 1.0 | 1.0 | 1.0 |
|
62 |
+
| 0.4242 | 17.5 | 35 | 0.3353 | 1.0 | 1.0 | 1.0 | 1.0 |
|
63 |
+
| 0.4133 | 20.0 | 40 | 0.3128 | 1.0 | 1.0 | 1.0 | 1.0 |
|
64 |
+
| 0.3889 | 22.5 | 45 | 0.2939 | 1.0 | 1.0 | 1.0 | 1.0 |
|
65 |
+
| 0.3736 | 25.0 | 50 | 0.2780 | 1.0 | 1.0 | 1.0 | 1.0 |
|
66 |
+
| 0.3736 | 27.5 | 55 | 0.2655 | 1.0 | 1.0 | 1.0 | 1.0 |
|
67 |
+
| 0.3847 | 30.0 | 60 | 0.2557 | 1.0 | 1.0 | 1.0 | 1.0 |
|
68 |
+
| 0.382 | 32.5 | 65 | 0.2483 | 1.0 | 1.0 | 1.0 | 1.0 |
|
69 |
+
| 0.3239 | 35.0 | 70 | 0.2418 | 1.0 | 1.0 | 1.0 | 1.0 |
|
70 |
+
| 0.3254 | 37.5 | 75 | 0.2361 | 1.0 | 1.0 | 1.0 | 1.0 |
|
71 |
+
| 0.3441 | 40.0 | 80 | 0.2316 | 1.0 | 1.0 | 1.0 | 1.0 |
|
72 |
+
| 0.3435 | 42.5 | 85 | 0.2284 | 1.0 | 1.0 | 1.0 | 1.0 |
|
73 |
+
| 0.3541 | 45.0 | 90 | 0.2262 | 1.0 | 1.0 | 1.0 | 1.0 |
|
74 |
+
| 0.2947 | 47.5 | 95 | 0.2248 | 1.0 | 1.0 | 1.0 | 1.0 |
|
75 |
+
| 0.3678 | 50.0 | 100 | 0.2244 | 1.0 | 1.0 | 1.0 | 1.0 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.35.2
|
81 |
+
- Pytorch 2.1.1
|
82 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ncardus/TrainedMLM",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 128,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1024,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 8,
|
17 |
+
"num_hidden_layers": 8,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"problem_type": "single_label_classification",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.35.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 256
|
26 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58ae5981b26d2fb531765afda3e4435f975521e4fc9392cbd33989353e1b1d41
|
3 |
+
size 11033176
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d728f7f339e24002e2436d40c18d59662e0d60c58012536a3fecf8777a3b55
|
3 |
+
size 4536
|