Hugging Face's logo

X-Wang
/
pruned-mt5-small

Text2Text Generation
Transformers
PyTorch
Japanese
Chinese
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
9
X-Wang commited on
Commit
afbe068
•
1 Parent(s): 4bbb896

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: X-Wang/pruned-mt5-small
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
+ model-index:
8
+ - name: pruned-mt5-small
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # pruned-mt5-small
16
+
17
+ This model is a fine-tuned version of [X-Wang/pruned-mt5-small](https://huggingface.co/X-Wang/pruned-mt5-small) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.4431
20
+ - Bleu: 11.4084
21
+ - Gen Len: 16.1053
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0005
41
+ - train_batch_size: 12
42
+ - eval_batch_size: 12
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 24
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.01
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
55
+ | 3.3446 | 0.07 | 2000 | 2.9103 | 10.3957 | 16.0567 |
56
+ | 2.8425 | 0.14 | 4000 | 2.8570 | 10.5695 | 16.1895 |
57
+ | 3.186 | 0.21 | 6000 | 2.8137 | 10.5958 | 16.1523 |
58
+ | 2.788 | 0.28 | 8000 | 2.7593 | 10.7553 | 16.0138 |
59
+ | 2.9075 | 0.35 | 10000 | 2.7266 | 10.9199 | 16.2016 |
60
+ | 3.0579 | 0.42 | 12000 | 2.7030 | 10.6 | 16.0496 |
61
+ | 2.3618 | 0.49 | 14000 | 2.6547 | 10.8026 | 16.0412 |
62
+ | 3.079 | 0.56 | 16000 | 2.6441 | 10.7945 | 16.1148 |
63
+ | 2.7597 | 0.63 | 18000 | 2.6244 | 10.5877 | 16.0507 |
64
+ | 2.8533 | 0.7 | 20000 | 2.6049 | 10.9986 | 16.1145 |
65
+ | 2.843 | 0.77 | 22000 | 2.5836 | 10.9173 | 16.0826 |
66
+ | 2.8268 | 0.84 | 24000 | 2.5685 | 10.8136 | 16.0516 |
67
+ | 2.7021 | 0.91 | 26000 | 2.5509 | 11.326 | 16.0554 |
68
+ | 3.338 | 0.98 | 28000 | 2.5289 | 11.1485 | 16.0333 |
69
+ | 2.7374 | 1.05 | 30000 | 2.5220 | 11.0166 | 16.0998 |
70
+ | 2.7996 | 1.12 | 32000 | 2.5077 | 11.1316 | 16.131 |
71
+ | 2.6897 | 1.19 | 34000 | 2.4994 | 11.0811 | 16.1139 |
72
+ | 2.4107 | 1.26 | 36000 | 2.4877 | 11.2641 | 16.142 |
73
+ | 2.7695 | 1.33 | 38000 | 2.4756 | 11.2135 | 16.0977 |
74
+ | 3.3271 | 1.41 | 40000 | 2.4658 | 11.3328 | 16.0953 |
75
+ | 2.2641 | 1.48 | 42000 | 2.4612 | 11.3065 | 16.0549 |
76
+ | 2.6594 | 1.55 | 44000 | 2.4556 | 11.2684 | 16.1371 |
77
+ | 2.7322 | 1.62 | 46000 | 2.4520 | 11.3739 | 16.1058 |
78
+ | 2.6824 | 1.69 | 48000 | 2.4462 | 11.3335 | 16.1043 |
79
+ | 2.3369 | 1.76 | 50000 | 2.4455 | 11.3851 | 16.1239 |
80
+ | 2.9537 | 1.83 | 52000 | 2.4430 | 11.4026 | 16.0858 |
81
+ | 2.3928 | 1.9 | 54000 | 2.4433 | 11.301 | 16.1129 |
82
+ | 2.4714 | 1.97 | 56000 | 2.4431 | 11.4084 | 16.1053 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.31.0
88
+ - Pytorch 2.0.0
89
+ - Datasets 2.13.1
90
+ - Tokenizers 0.13.3