update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- precision
|
6 |
+
- recall
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: Bert_v5
|
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 |
+
# Bert_v5
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9191
|
22 |
+
- Precision: 0.7612
|
23 |
+
- Recall: 0.8007
|
24 |
+
- F1: 0.5106
|
25 |
+
- Accuracy: 0.7357
|
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: 1
|
46 |
+
- eval_batch_size: 1
|
47 |
+
- seed: 42
|
48 |
+
- gradient_accumulation_steps: 8
|
49 |
+
- total_train_batch_size: 8
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 7
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 1.0663 | 1.0 | 934 | 0.8636 | 0.6973 | 0.8467 | 0.4082 | 0.7023 |
|
60 |
+
| 0.8354 | 2.0 | 1868 | 0.8261 | 0.7367 | 0.8086 | 0.4733 | 0.7221 |
|
61 |
+
| 0.7164 | 3.0 | 2802 | 0.7737 | 0.7572 | 0.7988 | 0.5055 | 0.7347 |
|
62 |
+
| 0.6149 | 4.0 | 3736 | 0.7542 | 0.7488 | 0.8402 | 0.5176 | 0.7438 |
|
63 |
+
| 0.5153 | 5.0 | 4670 | 0.8185 | 0.7614 | 0.8123 | 0.5017 | 0.7389 |
|
64 |
+
| 0.4314 | 6.0 | 5604 | 0.8599 | 0.7543 | 0.8259 | 0.5085 | 0.7395 |
|
65 |
+
| 0.3689 | 7.0 | 6538 | 0.9191 | 0.7612 | 0.8007 | 0.5106 | 0.7357 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.18.0
|
71 |
+
- Pytorch 1.10.0+cu111
|
72 |
+
- Datasets 2.1.0
|
73 |
+
- Tokenizers 0.12.1
|