Hugging Face's logo

levshechter
/
combined_model_4class

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
levshechter commited on
Commit
b387952
·
verified ·
1 Parent(s): 66dc007

levshechter/tibetan-code-switching-detector

Browse files
Files changed (5) hide show
  1. README.md +13 -13
  2. final_model/model.safetensors +1 -1
  3. final_model/training_args.bin +1 -1
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [OMRIDRORI/mbert-tibetan-continual-unicode-240k](https://huggingface.co/OMRIDRORI/mbert-tibetan-continual-unicode-240k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2855
21
- - Accuracy: 0.8878
22
- - Proximity F1: 0.0
23
- - Proximity Recall: 0.0
24
- - Proximity Precision: 0.0
25
- - Exact Matches: 0.0
26
- - Missed Switches: 0.4031
27
- - False Switches: 0.0
28
  - Matches At 1 Words: 0.0
29
  - Matches At 2 Words: 0.0
30
  - Matches At 3 Words: 0.0
@@ -62,15 +62,15 @@ The following hyperparameters were used during training:
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 1000
65
- - num_epochs: 20
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Proximity F1 | Proximity Recall | Proximity Precision | Exact Matches | Missed Switches | False Switches | Matches At 1 Words | Matches At 2 Words | Matches At 3 Words | Matches At 4 Words | Matches At 5 Words | Matches At 6 Words | Matches At 7 Words | Matches At 8 Words | Matches At 9 Words | Matches At 10 Words |
71
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:------------:|:----------------:|:-------------------:|:-------------:|:---------------:|:--------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:-------------------:|
72
- | 0.4215 | 7.6923 | 200 | 0.3094 | 0.9133 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4031 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
73
- | 0.3247 | 15.3846 | 400 | 0.2855 | 0.8878 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4031 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
74
 
75
 
76
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [OMRIDRORI/mbert-tibetan-continual-unicode-240k](https://huggingface.co/OMRIDRORI/mbert-tibetan-continual-unicode-240k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4328
21
+ - Accuracy: 0.8455
22
+ - Proximity F1: 0.0336
23
+ - Proximity Recall: 0.1589
24
+ - Proximity Precision: 0.0195
25
+ - Exact Matches: 0.3721
26
+ - Missed Switches: 0.0310
27
+ - False Switches: 10.4729
28
  - Matches At 1 Words: 0.0
29
  - Matches At 2 Words: 0.0
30
  - Matches At 3 Words: 0.0
 
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 1000
65
+ - num_epochs: 10
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Proximity F1 | Proximity Recall | Proximity Precision | Exact Matches | Missed Switches | False Switches | Matches At 1 Words | Matches At 2 Words | Matches At 3 Words | Matches At 4 Words | Matches At 5 Words | Matches At 6 Words | Matches At 7 Words | Matches At 8 Words | Matches At 9 Words | Matches At 10 Words |
71
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------------:|:----------------:|:-------------------:|:-------------:|:---------------:|:--------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:-------------------:|
72
+ | 1.1232 | 4.8193 | 200 | 0.5908 | 0.9130 | 0.0165 | 0.0116 | 0.0310 | 0.0310 | 0.3721 | 0.1163 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
73
+ | 0.5077 | 9.6386 | 400 | 0.4328 | 0.8455 | 0.0336 | 0.1589 | 0.0195 | 0.3721 | 0.0310 | 10.4729 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
74
 
75
 
76
  ### Framework versions
final_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3b8b1d28fca9b0b13ef3b449edbdd552b08c241c22e41c5dcfcfc07a473bb79
3
  size 709087056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caff480e3e731b21022867c3dd78427cb6588177c6611bd2f14beb1e3408e690
3
  size 709087056
final_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ad596bc63b50861217fe661f36b44bd331caca45dd6638cda1198f3e97b827b
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00fa61f9f81886e1d2054f8669ebb3d16dee56ac2d3beb93b85d2b6a482c1de4
3
  size 5304
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3b8b1d28fca9b0b13ef3b449edbdd552b08c241c22e41c5dcfcfc07a473bb79
3
  size 709087056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caff480e3e731b21022867c3dd78427cb6588177c6611bd2f14beb1e3408e690
3
  size 709087056
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ad596bc63b50861217fe661f36b44bd331caca45dd6638cda1198f3e97b827b
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00fa61f9f81886e1d2054f8669ebb3d16dee56ac2d3beb93b85d2b6a482c1de4
3
  size 5304