update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- bleu
|
6 |
+
model-index:
|
7 |
+
- name: BERT2BERT_finetuned
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# BERT2BERT_finetuned
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [JulienRPA/BERT2BERT_pretrained_LC-QuAD_2.0](https://huggingface.co/JulienRPA/BERT2BERT_pretrained_LC-QuAD_2.0) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4253
|
19 |
+
- Bleu: 95.481
|
20 |
+
- Em: 0.6019
|
21 |
+
- Rm: 0.6547
|
22 |
+
- Gen Len: 80.4676
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 64
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 2000
|
48 |
+
- num_epochs: 300.0
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Em | Rm | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:-------:|
|
55 |
+
| 2.9129 | 50.0 | 1000 | 0.3861 | 92.7571 | 0.2302 | 0.2422 | 79.2806 |
|
56 |
+
| 0.052 | 100.0 | 2000 | 0.3532 | 95.3257 | 0.5156 | 0.5635 | 80.6859 |
|
57 |
+
| 0.0155 | 150.0 | 3000 | 0.4280 | 94.8017 | 0.5659 | 0.6355 | 79.3165 |
|
58 |
+
| 0.0086 | 200.0 | 4000 | 0.4077 | 95.5885 | 0.5803 | 0.6283 | 80.6978 |
|
59 |
+
| 0.0051 | 250.0 | 5000 | 0.4169 | 95.5923 | 0.6019 | 0.6523 | 80.6523 |
|
60 |
+
| 0.0038 | 300.0 | 6000 | 0.4253 | 95.481 | 0.6019 | 0.6547 | 80.4676 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.30.0.dev0
|
66 |
+
- Pytorch 2.0.1+cu118
|
67 |
+
- Datasets 2.12.0
|
68 |
+
- Tokenizers 0.13.3
|