Hugging Face's logo

ele-sage
/
camembertav2-base-name-classifier-v2

Text Classification
Transformers
TensorBoard
Safetensors
French
English
deberta-v2
Generated from Trainer
name
person
company
Model card Files
xet
Metrics Community
ele-sage commited on
Commit
1cf0973
·
verified ·
1 Parent(s): 405b46f

camembertav2-base-name-classifier-v2

Browse files
Files changed (5) hide show
  1. README.md +25 -19
  2. model.safetensors +1 -1
  3. runs/Nov26_22-24-41_elesage-pc/events.out.tfevents.1764213980.elesage-pc.93364.0 +3 -0
  4. runs/Nov26_22-24-41_elesage-pc/events.out.tfevents.1764216758.elesage-pc.93364.1 +3 -0
  5. 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 [almanach/camembertav2-base](https://huggingface.co/almanach/camembertav2-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0258
25
- - Accuracy: 0.9929
26
- - Precision: 0.9963
27
- - Recall: 0.9911
28
- - F1: 0.9937
29
 
30
  ## Model description
31
 
@@ -50,25 +50,31 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
- - lr_scheduler_warmup_steps: 500
54
- - num_epochs: 1
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.0335 | 0.0788 | 2000 | 0.0330 | 0.9909 | 0.9955 | 0.9884 | 0.9919 |
61
- | 0.0345 | 0.1575 | 4000 | 0.0310 | 0.9916 | 0.9949 | 0.9902 | 0.9925 |
62
- | 0.033 | 0.2363 | 6000 | 0.0303 | 0.9918 | 0.9958 | 0.9896 | 0.9927 |
63
- | 0.0306 | 0.3150 | 8000 | 0.0282 | 0.9921 | 0.9960 | 0.9898 | 0.9929 |
64
- | 0.0325 | 0.3938 | 10000 | 0.0283 | 0.9922 | 0.9954 | 0.9908 | 0.9931 |
65
- | 0.0286 | 0.4725 | 12000 | 0.0275 | 0.9924 | 0.9960 | 0.9905 | 0.9932 |
66
- | 0.029 | 0.5513 | 14000 | 0.0286 | 0.9921 | 0.9941 | 0.9919 | 0.9930 |
67
- | 0.031 | 0.6300 | 16000 | 0.0266 | 0.9926 | 0.9953 | 0.9915 | 0.9934 |
68
- | 0.0281 | 0.7088 | 18000 | 0.0263 | 0.9927 | 0.9960 | 0.9911 | 0.9935 |
69
- | 0.0265 | 0.7876 | 20000 | 0.0260 | 0.9929 | 0.9961 | 0.9912 | 0.9936 |
70
- | 0.0277 | 0.8663 | 22000 | 0.0258 | 0.9929 | 0.9963 | 0.9911 | 0.9937 |
71
- | 0.0287 | 0.9451 | 24000 | 0.0256 | 0.9929 | 0.9959 | 0.9915 | 0.9937 |
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [almanach/camembertav2-base](https://huggingface.co/almanach/camembertav2-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.0331
25
+ - Accuracy: 0.9912
26
+ - Precision: 0.9971
27
+ - Recall: 0.9872
28
+ - F1: 0.9922
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 1000
54
+ - num_epochs: 1.5
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.0416 | 0.0826 | 2000 | 0.0355 | 0.9902 | 0.9949 | 0.9876 | 0.9913 |
61
+ | 0.0325 | 0.1652 | 4000 | 0.0330 | 0.9910 | 0.9942 | 0.9898 | 0.9920 |
62
+ | 0.0335 | 0.2479 | 6000 | 0.0314 | 0.9914 | 0.9950 | 0.9896 | 0.9923 |
63
+ | 0.0342 | 0.3305 | 8000 | 0.0313 | 0.9916 | 0.9948 | 0.9902 | 0.9925 |
64
+ | 0.0305 | 0.4131 | 10000 | 0.0331 | 0.9912 | 0.9971 | 0.9873 | 0.9922 |
65
+ | 0.0305 | 0.4957 | 12000 | 0.0298 | 0.9920 | 0.9958 | 0.9898 | 0.9928 |
66
+ | 0.0302 | 0.5783 | 14000 | 0.0294 | 0.9919 | 0.9948 | 0.9907 | 0.9928 |
67
+ | 0.0309 | 0.6609 | 16000 | 0.0286 | 0.9920 | 0.9964 | 0.9895 | 0.9929 |
68
+ | 0.0287 | 0.7436 | 18000 | 0.0293 | 0.9918 | 0.9939 | 0.9916 | 0.9928 |
69
+ | 0.0284 | 0.8262 | 20000 | 0.0288 | 0.9922 | 0.9954 | 0.9907 | 0.9931 |
70
+ | 0.0274 | 0.9088 | 22000 | 0.0287 | 0.9924 | 0.9962 | 0.9902 | 0.9932 |
71
+ | 0.0293 | 0.9914 | 24000 | 0.0281 | 0.9925 | 0.9960 | 0.9906 | 0.9933 |
72
+ | 0.025 | 1.0740 | 26000 | 0.0285 | 0.9923 | 0.9955 | 0.9909 | 0.9932 |
73
+ | 0.0233 | 1.1566 | 28000 | 0.0292 | 0.9924 | 0.9954 | 0.9911 | 0.9932 |
74
+ | 0.024 | 1.2393 | 30000 | 0.0283 | 0.9924 | 0.9950 | 0.9914 | 0.9932 |
75
+ | 0.0286 | 1.3219 | 32000 | 0.0275 | 0.9925 | 0.9961 | 0.9905 | 0.9933 |
76
+ | 0.0249 | 1.4045 | 34000 | 0.0277 | 0.9925 | 0.9958 | 0.9908 | 0.9933 |
77
+ | 0.0246 | 1.4871 | 36000 | 0.0278 | 0.9925 | 0.9956 | 0.9910 | 0.9933 |
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f3fffb9e2691deb99ce8841f116a00d46ac8df58c72a9cce99a8e5083b25a3
3
  size 444859368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819b07d35e93e321d11d555e2d77b0d710d9204013a3a0179b62e23abe00a600
3
  size 444859368
runs/Nov26_22-24-41_elesage-pc/events.out.tfevents.1764213980.elesage-pc.93364.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0744b669a2cc991dada5867b9904af05909cc5591c3c361c7e4bc511aef12a3
3
+ size 53065
runs/Nov26_22-24-41_elesage-pc/events.out.tfevents.1764216758.elesage-pc.93364.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300a9ddf0a4c505db9403d8f8bb42a9ac9d006d3e4f3938d0007d22a7a951de6
3
+ size 569
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa52cba152a55427793e263e64139b06dc4eab7f445bc03ee2bf25199b056610
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e04c1ca5bd29e8db7f77c0d409bae611beb9b68bce5aa05b5e5e44c5a96d8a3
3
  size 5905