Hugging Face's logo

VuongQuoc
/
Debertalarg_model_multichoice_Version2

Multiple Choice
Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
VuongQuoc commited on
Commit
cd5c589
•
1 Parent(s): bebb02e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -57
README.md CHANGED
@@ -13,8 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [VuongQuoc/Debertalarg_model_multichoice_Version2](https://huggingface.co/VuongQuoc/Debertalarg_model_multichoice_Version2) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.7733
17
- - Score: 0.751
18
 
19
  ## Model description
20
 
@@ -39,64 +38,38 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - lr_scheduler_warmup_ratio: 0.6
43
- - num_epochs: 2
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:-----:|:---------------:|
49
- | 1.4268 | 0.04 | 500 | 1.3693 |
50
- | 1.4108 | 0.08 | 1000 | 1.3603 |
51
- | 1.419 | 0.12 | 1500 | 1.3444 |
52
- | 1.3911 | 0.15 | 2000 | 1.3143 |
53
- | 1.3992 | 0.19 | 2500 | 1.3018 |
54
- | 1.3495 | 0.23 | 3000 | 1.2723 |
55
- | 1.3268 | 0.27 | 3500 | 1.2392 |
56
- | 1.3156 | 0.31 | 4000 | 1.2489 |
57
- | 1.3059 | 0.35 | 4500 | 1.1842 |
58
- | 1.2759 | 0.39 | 5000 | 1.1568 |
59
- | 1.2281 | 0.42 | 5500 | 1.1469 |
60
- | 1.2769 | 0.46 | 6000 | 1.0952 |
61
- | 1.2902 | 0.5 | 6500 | 1.1061 |
62
- | 1.2502 | 0.54 | 7000 | 1.0716 |
63
- | 1.199 | 0.58 | 7500 | 1.0360 |
64
- | 1.155 | 0.62 | 8000 | 1.0077 |
65
- | 1.077 | 0.65 | 8500 | 0.9857 |
66
- | 0.9807 | 0.69 | 9000 | 1.0340 |
67
- | 1.1629 | 0.73 | 9500 | 0.9626 |
68
- | 1.2101 | 0.77 | 10000 | 0.9675 |
69
- | 1.1597 | 0.81 | 10500 | 0.9190 |
70
- | 1.1831 | 0.85 | 11000 | 0.9314 |
71
- | 1.1691 | 0.89 | 11500 | 0.9056 |
72
- | 1.1335 | 0.92 | 12000 | 0.8997 |
73
- | 1.1413 | 0.96 | 12500 | 0.8887 |
74
- | 1.1218 | 1.0 | 13000 | 0.8684 |
75
- | 1.0662 | 1.04 | 13500 | 0.8655 |
76
- | 1.0599 | 1.08 | 14000 | 0.8869 |
77
- | 1.0523 | 1.12 | 14500 | 0.8401 |
78
- | 1.075 | 1.16 | 15000 | 0.8672 |
79
- | 1.0394 | 1.19 | 15500 | 0.8323 |
80
- | 1.0957 | 1.23 | 16000 | 0.8146 |
81
- | 1.0363 | 1.27 | 16500 | 0.8549 |
82
- | 1.0995 | 1.31 | 17000 | 0.8001 |
83
- | 1.0742 | 1.35 | 17500 | 0.7952 |
84
- | 1.0417 | 1.39 | 18000 | 0.8050 |
85
- | 1.0712 | 1.43 | 18500 | 0.7935 |
86
- | 1.0654 | 1.46 | 19000 | 0.7746 |
87
- | 1.113 | 1.5 | 19500 | 0.7679 |
88
- | 1.0387 | 1.54 | 20000 | 0.8220 |
89
- | 1.0564 | 1.58 | 20500 | 0.7756 |
90
- | 1.037 | 1.62 | 21000 | 0.7907 |
91
- | 1.0565 | 1.66 | 21500 | 0.7760 |
92
- | 1.0553 | 1.7 | 22000 | 0.8027 |
93
- | 1.0582 | 1.73 | 22500 | 0.7729 |
94
- | 1.0546 | 1.77 | 23000 | 0.7844 |
95
- | 1.0346 | 1.81 | 23500 | 0.7736 |
96
- | 1.0416 | 1.85 | 24000 | 0.7791 |
97
- | 1.0402 | 1.89 | 24500 | 0.7795 |
98
- | 1.1279 | 1.93 | 25000 | 0.7698 |
99
- | 1.0703 | 1.96 | 25500 | 0.7733 |
100
 
101
 
102
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [VuongQuoc/Debertalarg_model_multichoice_Version2](https://huggingface.co/VuongQuoc/Debertalarg_model_multichoice_Version2) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.8611
 
17
 
18
  ## Model description
19
 
 
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_ratio: 0.1
42
+ - num_epochs: 1
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.0591 | 0.04 | 300 | 0.8278 |
49
+ | 1.1284 | 0.08 | 600 | 0.8545 |
50
+ | 1.0894 | 0.12 | 900 | 0.8821 |
51
+ | 0.9937 | 0.16 | 1200 | 0.9260 |
52
+ | 0.8916 | 0.2 | 1500 | 0.9562 |
53
+ | 0.7818 | 0.24 | 1800 | 1.0041 |
54
+ | 0.7193 | 0.28 | 2100 | 1.0704 |
55
+ | 0.712 | 0.32 | 2400 | 1.0295 |
56
+ | 0.6913 | 0.36 | 2700 | 1.0537 |
57
+ | 0.4193 | 0.4 | 3000 | 1.1205 |
58
+ | 0.4197 | 0.44 | 3300 | 1.1187 |
59
+ | 0.3394 | 0.48 | 3600 | 1.1435 |
60
+ | 0.2916 | 0.52 | 3900 | 1.2060 |
61
+ | 0.1957 | 0.56 | 4200 | 1.2312 |
62
+ | 0.2363 | 0.6 | 4500 | 1.1874 |
63
+ | 0.1818 | 0.64 | 4800 | 1.2510 |
64
+ | 0.1853 | 0.68 | 5100 | 1.2274 |
65
+ | 0.1488 | 0.72 | 5400 | 1.2450 |
66
+ | 0.1007 | 0.76 | 5700 | 1.2106 |
67
+ | 0.1387 | 0.8 | 6000 | 1.2997 |
68
+ | 2.1064 | 0.84 | 6300 | 0.9987 |
69
+ | 1.5963 | 0.88 | 6600 | 0.9290 |
70
+ | 1.5086 | 0.92 | 6900 | 0.8935 |
71
+ | 1.56 | 0.96 | 7200 | 0.8637 |
72
+ | 1.3432 | 1.0 | 7500 | 0.8611 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions