update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- rouge
|
7 |
+
- bleu
|
8 |
+
model-index:
|
9 |
+
- name: Salesforce-codet5-small-CodeXGLUE-CONCODE-adafactor
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Salesforce-codet5-small-CodeXGLUE-CONCODE-adafactor
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8118
|
21 |
+
- Exact Match: 0.1555
|
22 |
+
- Rouge1: 0.5580
|
23 |
+
- Rouge2: 0.3886
|
24 |
+
- Rougel: 0.5407
|
25 |
+
- Rougelsum: 0.5483
|
26 |
+
- Bleu: 0.1297
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 0.0003
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- lr_scheduler_warmup_ratio: 0.05
|
52 |
+
- num_epochs: 10
|
53 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|:------:|:------:|:---------:|:------:|
|
59 |
+
| 1.8525 | 0.16 | 500 | 0.9340 | 0.1435 | 0.5360 | 0.3596 | 0.5171 | 0.5238 | 0.1146 |
|
60 |
+
| 0.8679 | 0.32 | 1000 | 0.9262 | 0.1405 | 0.5385 | 0.3659 | 0.5228 | 0.5294 | 0.1179 |
|
61 |
+
| 0.8169 | 0.48 | 1500 | 0.8957 | 0.139 | 0.5372 | 0.3642 | 0.5192 | 0.5265 | 0.1135 |
|
62 |
+
| 0.7734 | 0.64 | 2000 | 0.8827 | 0.14 | 0.5485 | 0.3706 | 0.5316 | 0.5381 | 0.1210 |
|
63 |
+
| 0.743 | 0.8 | 2500 | 0.8647 | 0.155 | 0.5503 | 0.3833 | 0.5338 | 0.5411 | 0.1184 |
|
64 |
+
| 0.72 | 0.96 | 3000 | 0.8661 | 0.1545 | 0.5460 | 0.3735 | 0.5284 | 0.5366 | 0.1162 |
|
65 |
+
| 0.6539 | 1.12 | 3500 | 0.8591 | 0.156 | 0.5540 | 0.3841 | 0.5365 | 0.5444 | 0.1241 |
|
66 |
+
| 0.6301 | 1.28 | 4000 | 0.8452 | 0.1485 | 0.5556 | 0.3794 | 0.5369 | 0.5451 | 0.1237 |
|
67 |
+
| 0.6222 | 1.44 | 4500 | 0.8321 | 0.1585 | 0.5529 | 0.3818 | 0.5343 | 0.5430 | 0.1228 |
|
68 |
+
| 0.6221 | 1.6 | 5000 | 0.8317 | 0.154 | 0.5664 | 0.3925 | 0.5481 | 0.5575 | 0.1289 |
|
69 |
+
| 0.6067 | 1.76 | 5500 | 0.8228 | 0.1625 | 0.5607 | 0.3933 | 0.5438 | 0.5516 | 0.1299 |
|
70 |
+
| 0.5927 | 1.92 | 6000 | 0.8179 | 0.156 | 0.5625 | 0.3942 | 0.5457 | 0.5526 | 0.1309 |
|
71 |
+
| 0.5548 | 2.08 | 6500 | 0.8259 | 0.152 | 0.5582 | 0.3846 | 0.5402 | 0.5485 | 0.1314 |
|
72 |
+
| 0.5146 | 2.24 | 7000 | 0.8328 | 0.1545 | 0.5605 | 0.3889 | 0.5429 | 0.5514 | 0.1299 |
|
73 |
+
| 0.5193 | 2.4 | 7500 | 0.8197 | 0.1555 | 0.5604 | 0.3866 | 0.5431 | 0.5501 | 0.1268 |
|
74 |
+
| 0.5172 | 2.56 | 8000 | 0.8118 | 0.1555 | 0.5580 | 0.3886 | 0.5407 | 0.5483 | 0.1297 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.27.1
|
80 |
+
- Pytorch 1.12.1+cu113
|
81 |
+
- Datasets 2.10.1
|
82 |
+
- Tokenizers 0.13.2
|