Model save
Browse files- README.md +86 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- glue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: hBERTv1_new_pretrain_w_init_48_ver2_qqp
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: glue
|
18 |
+
type: glue
|
19 |
+
config: qqp
|
20 |
+
split: validation
|
21 |
+
args: qqp
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.7089290131090774
|
26 |
+
- name: F1
|
27 |
+
type: f1
|
28 |
+
value: 0.6289335939963422
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# hBERTv1_new_pretrain_w_init_48_ver2_qqp
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the glue dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.5789
|
39 |
+
- Accuracy: 0.7089
|
40 |
+
- F1: 0.6289
|
41 |
+
- Combined Score: 0.6689
|
42 |
+
|
43 |
+
## Model description
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training and evaluation data
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Training procedure
|
56 |
+
|
57 |
+
### Training hyperparameters
|
58 |
+
|
59 |
+
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 4e-05
|
61 |
+
- train_batch_size: 64
|
62 |
+
- eval_batch_size: 64
|
63 |
+
- seed: 10
|
64 |
+
- distributed_type: multi-GPU
|
65 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
66 |
+
- lr_scheduler_type: linear
|
67 |
+
- num_epochs: 15
|
68 |
+
|
69 |
+
### Training results
|
70 |
+
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|
72 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
|
73 |
+
| 0.5279 | 1.0 | 5686 | 0.4918 | 0.7601 | 0.6952 | 0.7277 |
|
74 |
+
| 0.4826 | 2.0 | 11372 | 0.5367 | 0.7644 | 0.6556 | 0.7100 |
|
75 |
+
| 0.4943 | 3.0 | 17058 | 0.5223 | 0.7594 | 0.6440 | 0.7017 |
|
76 |
+
| 0.492 | 4.0 | 22744 | 0.5379 | 0.7600 | 0.6465 | 0.7032 |
|
77 |
+
| 0.505 | 5.0 | 28430 | 0.5431 | 0.7423 | 0.6507 | 0.6965 |
|
78 |
+
| 0.5428 | 6.0 | 34116 | 0.5789 | 0.7089 | 0.6289 | 0.6689 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.34.0
|
84 |
+
- Pytorch 1.14.0a0+410ce96
|
85 |
+
- Datasets 2.14.5
|
86 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 481099229
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e545f96399bd889a370e509abe955f3cb051d468957355b65900c0a00cbbff81
|
3 |
size 481099229
|