Hugging Face's logo

Eitanli
/
albert-qa-checkpoint

Question Answering
Transformers
PyTorch
TensorBoard
albert
Generated from Trainer
Model card Files
xet
Metrics Community
1
Eitanli commited on
Commit
456bac2
路
1 Parent(s): 0bdc36d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -24
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.4644
18
 
19
  ## Model description
20
 
@@ -39,32 +39,22 @@ 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
- - num_epochs: 20
43
 
44
  ### Training results
45
 
46
- | Training Loss | Epoch | Step | Validation Loss |
47
- |:-------------:|:-----:|:-----:|:---------------:|
48
- | 0.3464 | 1.0 | 773 | 0.2226 |
49
- | 0.1549 | 2.0 | 1546 | 0.2144 |
50
- | 0.1325 | 3.0 | 2319 | 0.2025 |
51
- | 0.1024 | 4.0 | 3092 | 0.1772 |
52
- | 0.0853 | 5.0 | 3865 | 0.2342 |
53
- | 0.0702 | 6.0 | 4638 | 0.2938 |
54
- | 0.0603 | 7.0 | 5411 | 0.2687 |
55
- | 0.0544 | 8.0 | 6184 | 0.2910 |
56
- | 0.0475 | 9.0 | 6957 | 0.3065 |
57
- | 0.0403 | 10.0 | 7730 | 0.2921 |
58
- | 0.0384 | 11.0 | 8503 | 0.3972 |
59
- | 0.0364 | 12.0 | 9276 | 0.4086 |
60
- | 0.0336 | 13.0 | 10049 | 0.4448 |
61
- | 0.0265 | 14.0 | 10822 | 0.3469 |
62
- | 0.0261 | 15.0 | 11595 | 0.3932 |
63
- | 0.0239 | 16.0 | 12368 | 0.4442 |
64
- | 0.0218 | 17.0 | 13141 | 0.4414 |
65
- | 0.0227 | 18.0 | 13914 | 0.4334 |
66
- | 0.0188 | 19.0 | 14687 | 0.4503 |
67
- | 0.0196 | 20.0 | 15460 | 0.4644 |
68
 
69
 
70
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3667
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 10
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.3388 | 1.0 | 773 | 0.1976 |
49
+ | 0.1564 | 2.0 | 1546 | 0.2122 |
50
+ | 0.1269 | 3.0 | 2319 | 0.2261 |
51
+ | 0.1037 | 4.0 | 3092 | 0.1888 |
52
+ | 0.0797 | 5.0 | 3865 | 0.2339 |
53
+ | 0.064 | 6.0 | 4638 | 0.2969 |
54
+ | 0.0489 | 7.0 | 5411 | 0.3004 |
55
+ | 0.0386 | 8.0 | 6184 | 0.3253 |
56
+ | 0.0355 | 9.0 | 6957 | 0.3448 |
57
+ | 0.0247 | 10.0 | 7730 | 0.3667 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions