Hugging Face's logo

lhy
/
char-bert-base-uncased

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
4
lhy commited on
Commit
d40b0ce
•
1 Parent(s): 23e849b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -15
README.md CHANGED
@@ -11,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # char-bert-base-uncased
13
 
14
- This model is a fine-tuned version of [char-bert-base-uncased/checkpoint-552072](https://huggingface.co/char-bert-base-uncased/checkpoint-552072) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.2103
17
 
18
  ## Model description
19
 
@@ -38,22 +38,27 @@ The following hyperparameters were used during training:
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - num_epochs: 10
42
 
43
  ### Training results
44
 
45
- | Training Loss | Epoch | Step | Validation Loss |
46
- |:-------------:|:-----:|:------:|:---------------:|
47
- | 0.8329 | 1.0 | 92012 | 0.4066 |
48
- | 0.4066 | 2.0 | 184024 | 0.3223 |
49
- | 0.3422 | 3.0 | 276036 | 0.2803 |
50
- | 0.3044 | 4.0 | 368048 | 0.2560 |
51
- | 0.2782 | 5.0 | 460060 | 0.2399 |
52
- | 0.2593 | 6.0 | 552072 | 0.2265 |
53
- | 0.2693 | 7.0 | 644084 | 0.2366 |
54
- | 0.2559 | 8.0 | 736096 | 0.2228 |
55
- | 0.2431 | 9.0 | 828108 | 0.2112 |
56
- | 0.2334 | 10.0 | 920120 | 0.2103 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
11
 
12
  # char-bert-base-uncased
13
 
14
+ This model is a fine-tuned version of [char-bert-base-uncased/checkpoint-1104144](https://huggingface.co/char-bert-base-uncased/checkpoint-1104144) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.1941
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
+ - num_epochs: 15
42
 
43
  ### Training results
44
 
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:-------:|:---------------:|
47
+ | 0.8329 | 1.0 | 92012 | 0.4066 |
48
+ | 0.4066 | 2.0 | 184024 | 0.3223 |
49
+ | 0.3422 | 3.0 | 276036 | 0.2803 |
50
+ | 0.3044 | 4.0 | 368048 | 0.2560 |
51
+ | 0.2782 | 5.0 | 460060 | 0.2399 |
52
+ | 0.2593 | 6.0 | 552072 | 0.2265 |
53
+ | 0.2693 | 7.0 | 644084 | 0.2366 |
54
+ | 0.2559 | 8.0 | 736096 | 0.2228 |
55
+ | 0.2431 | 9.0 | 828108 | 0.2112 |
56
+ | 0.2334 | 10.0 | 920120 | 0.2103 |
57
+ | 0.2453 | 11.0 | 1012132 | 0.2164 |
58
+ | 0.2372 | 12.0 | 1104144 | 0.2113 |
59
+ | 0.2288 | 13.0 | 1196156 | 0.2004 |
60
+ | 0.2208 | 14.0 | 1288168 | 0.2002 |
61
+ | 0.2152 | 15.0 | 1380180 | 0.1941 |
62
 
63
 
64
  ### Framework versions