antphb commited on
Commit
ae74fd2
·
1 Parent(s): 4484178

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +123 -0
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: gpt2-vietnamese
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # gpt2-vietnamese
13
+
14
+ This model is a fine-tuned version of [NlpHUST/gpt2-vietnamese](https://huggingface.co/NlpHUST/gpt2-vietnamese) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 2.7042
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: cosine
41
+ - lr_scheduler_warmup_steps: 2000
42
+ - num_epochs: 2
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | No log | 0.03 | 500 | 3.5209 |
49
+ | 3.5302 | 0.06 | 1000 | 3.3902 |
50
+ | 3.5302 | 0.09 | 1500 | 3.2947 |
51
+ | 3.2733 | 0.12 | 2000 | 3.2116 |
52
+ | 3.2733 | 0.15 | 2500 | 3.1511 |
53
+ | 3.1431 | 0.18 | 3000 | 3.1054 |
54
+ | 3.1431 | 0.2 | 3500 | 3.0684 |
55
+ | 3.0471 | 0.23 | 4000 | 3.0372 |
56
+ | 3.0471 | 0.26 | 4500 | 3.0103 |
57
+ | 2.9957 | 0.29 | 5000 | 2.9863 |
58
+ | 2.9957 | 0.32 | 5500 | 2.9652 |
59
+ | 2.9472 | 0.35 | 6000 | 2.9452 |
60
+ | 2.9472 | 0.38 | 6500 | 2.9281 |
61
+ | 2.9164 | 0.41 | 7000 | 2.9123 |
62
+ | 2.9164 | 0.44 | 7500 | 2.8982 |
63
+ | 2.8991 | 0.47 | 8000 | 2.8856 |
64
+ | 2.8991 | 0.5 | 8500 | 2.8732 |
65
+ | 2.8672 | 0.53 | 9000 | 2.8621 |
66
+ | 2.8672 | 0.56 | 9500 | 2.8507 |
67
+ | 2.8456 | 0.59 | 10000 | 2.8411 |
68
+ | 2.8456 | 0.61 | 10500 | 2.8318 |
69
+ | 2.8074 | 0.64 | 11000 | 2.8234 |
70
+ | 2.8074 | 0.67 | 11500 | 2.8151 |
71
+ | 2.7959 | 0.7 | 12000 | 2.8077 |
72
+ | 2.7959 | 0.73 | 12500 | 2.8006 |
73
+ | 2.7918 | 0.76 | 13000 | 2.7943 |
74
+ | 2.7918 | 0.79 | 13500 | 2.7876 |
75
+ | 2.7773 | 0.82 | 14000 | 2.7818 |
76
+ | 2.7773 | 0.85 | 14500 | 2.7760 |
77
+ | 2.7648 | 0.88 | 15000 | 2.7706 |
78
+ | 2.7648 | 0.91 | 15500 | 2.7656 |
79
+ | 2.7559 | 0.94 | 16000 | 2.7611 |
80
+ | 2.7559 | 0.97 | 16500 | 2.7561 |
81
+ | 2.7461 | 1.0 | 17000 | 2.7521 |
82
+ | 2.7461 | 1.02 | 17500 | 2.7493 |
83
+ | 2.696 | 1.05 | 18000 | 2.7454 |
84
+ | 2.696 | 1.08 | 18500 | 2.7419 |
85
+ | 2.6808 | 1.11 | 19000 | 2.7390 |
86
+ | 2.6808 | 1.14 | 19500 | 2.7362 |
87
+ | 2.6803 | 1.17 | 20000 | 2.7335 |
88
+ | 2.6803 | 1.2 | 20500 | 2.7304 |
89
+ | 2.6753 | 1.23 | 21000 | 2.7278 |
90
+ | 2.6753 | 1.26 | 21500 | 2.7251 |
91
+ | 2.6732 | 1.29 | 22000 | 2.7228 |
92
+ | 2.6732 | 1.32 | 22500 | 2.7205 |
93
+ | 2.6687 | 1.35 | 23000 | 2.7189 |
94
+ | 2.6687 | 1.38 | 23500 | 2.7170 |
95
+ | 2.6667 | 1.41 | 24000 | 2.7154 |
96
+ | 2.6667 | 1.43 | 24500 | 2.7138 |
97
+ | 2.655 | 1.46 | 25000 | 2.7125 |
98
+ | 2.655 | 1.49 | 25500 | 2.7113 |
99
+ | 2.6592 | 1.52 | 26000 | 2.7100 |
100
+ | 2.6592 | 1.55 | 26500 | 2.7091 |
101
+ | 2.6435 | 1.58 | 27000 | 2.7084 |
102
+ | 2.6435 | 1.61 | 27500 | 2.7076 |
103
+ | 2.6577 | 1.64 | 28000 | 2.7071 |
104
+ | 2.6577 | 1.67 | 28500 | 2.7063 |
105
+ | 2.6487 | 1.7 | 29000 | 2.7060 |
106
+ | 2.6487 | 1.73 | 29500 | 2.7054 |
107
+ | 2.6596 | 1.76 | 30000 | 2.7052 |
108
+ | 2.6596 | 1.79 | 30500 | 2.7049 |
109
+ | 2.6513 | 1.82 | 31000 | 2.7046 |
110
+ | 2.6513 | 1.84 | 31500 | 2.7046 |
111
+ | 2.6564 | 1.87 | 32000 | 2.7044 |
112
+ | 2.6564 | 1.9 | 32500 | 2.7043 |
113
+ | 2.6532 | 1.93 | 33000 | 2.7043 |
114
+ | 2.6532 | 1.96 | 33500 | 2.7042 |
115
+ | 2.6582 | 1.99 | 34000 | 2.7042 |
116
+
117
+
118
+ ### Framework versions
119
+
120
+ - Transformers 4.30.1
121
+ - Pytorch 2.0.0
122
+ - Datasets 2.1.0
123
+ - Tokenizers 0.13.3