Hugging Face's logo

VuongQuoc
/
checkpoints_29_9_microsoft_deberta_V1

Multiple Choice
Transformers
PyTorch
deberta-v2
Generated from Trainer
Model card Files
xet
Community
1
VuongQuoc commited on
Commit
754b660
·
1 Parent(s): b9a5d2d

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6667
21
- - Map@3: 0.8692
22
- - Accuracy: 0.8
23
 
24
  ## Model description
25
 
@@ -39,11 +39,11 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-06
42
- - train_batch_size: 2
43
- - eval_batch_size: 4
44
  - seed: 42
45
  - gradient_accumulation_steps: 16
46
- - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
49
  - lr_scheduler_warmup_ratio: 0.1
@@ -53,24 +53,24 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
56
- | 1.6098 | 0.05 | 100 | 1.6090 | 0.5250 | 0.38 |
57
- | 1.6092 | 0.11 | 200 | 1.6040 | 0.7408 | 0.63 |
58
- | 1.1308 | 0.16 | 300 | 1.1807 | 0.7475 | 0.63 |
59
- | 1.0343 | 0.21 | 400 | 0.9997 | 0.8108 | 0.705 |
60
- | 0.9673 | 0.27 | 500 | 0.9104 | 0.8042 | 0.69 |
61
- | 0.9579 | 0.32 | 600 | 0.8178 | 0.8542 | 0.775 |
62
- | 0.8286 | 0.37 | 700 | 0.7612 | 0.8592 | 0.785 |
63
- | 0.8198 | 0.43 | 800 | 0.7236 | 0.8600 | 0.795 |
64
- | 0.8379 | 0.48 | 900 | 0.7237 | 0.8583 | 0.79 |
65
- | 0.8646 | 0.53 | 1000 | 0.7052 | 0.8583 | 0.785 |
66
- | 0.8876 | 0.59 | 1100 | 0.6899 | 0.8692 | 0.8 |
67
- | 0.8598 | 0.64 | 1200 | 0.6897 | 0.8683 | 0.8 |
68
- | 0.8218 | 0.69 | 1300 | 0.6655 | 0.8725 | 0.805 |
69
- | 0.8695 | 0.75 | 1400 | 0.6742 | 0.8692 | 0.8 |
70
- | 0.8136 | 0.8 | 1500 | 0.6739 | 0.8692 | 0.8 |
71
- | 0.7843 | 0.85 | 1600 | 0.6644 | 0.8725 | 0.81 |
72
- | 0.8477 | 0.91 | 1700 | 0.6655 | 0.8717 | 0.805 |
73
- | 0.7881 | 0.96 | 1800 | 0.6667 | 0.8692 | 0.8 |
74
 
75
 
76
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7815
21
+ - Map@3: 0.8290
22
+ - Accuracy: 0.7333
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-06
42
+ - train_batch_size: 1
43
+ - eval_batch_size: 2
44
  - seed: 42
45
  - gradient_accumulation_steps: 16
46
+ - total_train_batch_size: 16
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
49
  - lr_scheduler_warmup_ratio: 0.1
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
56
+ | 1.6045 | 0.05 | 200 | 1.6095 | 0.4593 | 0.3030 |
57
+ | 1.3669 | 0.11 | 400 | 1.3360 | 0.7215 | 0.5980 |
58
+ | 0.9993 | 0.16 | 600 | 1.0403 | 0.7737 | 0.6727 |
59
+ | 0.9608 | 0.21 | 800 | 0.9539 | 0.7966 | 0.6990 |
60
+ | 0.9017 | 0.27 | 1000 | 0.9125 | 0.7997 | 0.6970 |
61
+ | 0.885 | 0.32 | 1200 | 0.8719 | 0.8172 | 0.7192 |
62
+ | 0.8222 | 0.37 | 1400 | 0.8462 | 0.8125 | 0.7030 |
63
+ | 0.769 | 0.43 | 1600 | 0.8376 | 0.8158 | 0.7131 |
64
+ | 0.7676 | 0.48 | 1800 | 0.8109 | 0.8178 | 0.7152 |
65
+ | 0.8413 | 0.53 | 2000 | 0.8279 | 0.8212 | 0.7212 |
66
+ | 0.809 | 0.59 | 2200 | 0.8012 | 0.8212 | 0.7212 |
67
+ | 0.8809 | 0.64 | 2400 | 0.8037 | 0.8290 | 0.7333 |
68
+ | 0.8028 | 0.69 | 2600 | 0.7949 | 0.8249 | 0.7293 |
69
+ | 0.8259 | 0.75 | 2800 | 0.7938 | 0.8283 | 0.7354 |
70
+ | 0.7548 | 0.8 | 3000 | 0.7818 | 0.8300 | 0.7354 |
71
+ | 0.7422 | 0.85 | 3200 | 0.7797 | 0.8316 | 0.7374 |
72
+ | 0.801 | 0.91 | 3400 | 0.7811 | 0.8303 | 0.7354 |
73
+ | 0.7 | 0.96 | 3600 | 0.7815 | 0.8290 | 0.7333 |
74
 
75
 
76
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b6c2e9992d35724a27cffa841dbe888b4e3374e168da283595dbec2df4645e5
3
  size 1740387701
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb678d609ef23a983d0a78396974cc549d5d51eca347166a2f33eeffa96fa793
3
  size 1740387701