Hugging Face's logo

ace-in-the-hole
/
cita_test

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
ace-in-the-hole commited on
Commit
3a14dac
·
verified ·
1 Parent(s): eb5abc8

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -19
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.5611
25
- - Accuracy: 0.9327
26
- - F1: 0.8897
27
- - Precision: 0.8911
28
- - Recall: 0.8883
29
 
30
  ## Model description
31
 
@@ -56,20 +56,24 @@ The following hyperparameters were used during training:
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
60
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
61
- | 0.6952 | 1.6 | 100 | 0.2931 | 0.9347 | 0.8920 | 0.8972 | 0.8870 |
62
- | 0.6952 | 3.2 | 200 | 0.3064 | 0.9295 | 0.8864 | 0.8812 | 0.8919 |
63
- | 0.2897 | 4.8 | 300 | 0.3103 | 0.9052 | 0.8579 | 0.8341 | 0.8917 |
64
- | 0.2897 | 6.4 | 400 | 0.3116 | 0.909 | 0.8623 | 0.8401 | 0.8925 |
65
- | 0.1582 | 8.0 | 500 | 0.3491 | 0.9107 | 0.8630 | 0.8440 | 0.8875 |
66
- | 0.1582 | 9.6 | 600 | 0.3723 | 0.9107 | 0.8643 | 0.8430 | 0.8926 |
67
- | 0.1582 | 11.2 | 700 | 0.4308 | 0.9323 | 0.8898 | 0.8880 | 0.8916 |
68
- | 0.091 | 12.8 | 800 | 0.5042 | 0.9315 | 0.8872 | 0.8901 | 0.8845 |
69
- | 0.091 | 14.4 | 900 | 0.4931 | 0.9273 | 0.8831 | 0.8770 | 0.8895 |
70
- | 0.0565 | 16.0 | 1000 | 0.4961 | 0.9285 | 0.8852 | 0.8786 | 0.8923 |
71
- | 0.0565 | 17.6 | 1100 | 0.5458 | 0.931 | 0.8877 | 0.8861 | 0.8893 |
72
- | 0.0565 | 19.2 | 1200 | 0.5611 | 0.9327 | 0.8897 | 0.8911 | 0.8883 |
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.5346
25
+ - Accuracy: 0.9359
26
+ - F1: 0.8894
27
+ - Precision: 0.8884
28
+ - Recall: 0.8904
29
 
30
  ## Model description
31
 
 
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
60
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
61
+ | 0.6948 | 1.2422 | 100 | 0.2617 | 0.9256 | 0.8789 | 0.8593 | 0.9034 |
62
+ | 0.6948 | 2.4845 | 200 | 0.2762 | 0.9445 | 0.9026 | 0.9081 | 0.8974 |
63
+ | 0.6948 | 3.7267 | 300 | 0.2587 | 0.9435 | 0.9017 | 0.9037 | 0.8998 |
64
+ | 0.277 | 4.9689 | 400 | 0.2791 | 0.9449 | 0.9036 | 0.9079 | 0.8993 |
65
+ | 0.277 | 6.2112 | 500 | 0.2776 | 0.9340 | 0.8904 | 0.8759 | 0.9071 |
66
+ | 0.277 | 7.4534 | 600 | 0.3288 | 0.9390 | 0.8944 | 0.8947 | 0.8941 |
67
+ | 0.1591 | 8.6957 | 700 | 0.3314 | 0.9297 | 0.8815 | 0.8721 | 0.8919 |
68
+ | 0.1591 | 9.9379 | 800 | 0.3873 | 0.9402 | 0.8959 | 0.8983 | 0.8935 |
69
+ | 0.1591 | 11.1801 | 900 | 0.4344 | 0.9320 | 0.8838 | 0.8793 | 0.8885 |
70
+ | 0.0923 | 12.4224 | 1000 | 0.4473 | 0.9258 | 0.8745 | 0.8666 | 0.8830 |
71
+ | 0.0923 | 13.6646 | 1100 | 0.4279 | 0.9169 | 0.8651 | 0.8455 | 0.8898 |
72
+ | 0.0923 | 14.9068 | 1200 | 0.5118 | 0.9340 | 0.8860 | 0.8853 | 0.8866 |
73
+ | 0.0586 | 16.1491 | 1300 | 0.5454 | 0.9417 | 0.8966 | 0.9072 | 0.8870 |
74
+ | 0.0586 | 17.3913 | 1400 | 0.5139 | 0.9338 | 0.8860 | 0.8841 | 0.8878 |
75
+ | 0.0586 | 18.6335 | 1500 | 0.5625 | 0.9392 | 0.8929 | 0.9004 | 0.8859 |
76
+ | 0.0586 | 19.8758 | 1600 | 0.5346 | 0.9359 | 0.8894 | 0.8884 | 0.8904 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf1c2f3d7471ca3d8bded646449c01816746746a2fdae04655b79600415b58dd
3
  size 540023384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df480c3a72ffb61204c36e1c4dcfbd39b17e0d784194d99408f7abcf4a69c30
3
  size 540023384
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0062d0357d2437a35cd8c6e8035bb588c8aab4795d532c616ca10057afcbc574
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19ab5a453d813194cd1f8a0d4cd0b12fdb4556c13dcb96cc0f11cd5d0da4374
3
  size 5112