Hugging Face's logo

morten-j
/
fine_tuned_mBERT

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
morten-j commited on
Commit
9f117d4
•
1 Parent(s): 5866ef8

mehdie/fine_tuned_mBERT

Browse files
Files changed (34) hide show
  1. README.md +21 -22
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/May15_11-57-39_yoga/events.out.tfevents.1715767059.yoga.20124.0 +3 -0
  5. runs/May15_11-57-39_yoga/events.out.tfevents.1715767135.yoga.20124.1 +3 -0
  6. runs/May15_11-59-14_yoga/events.out.tfevents.1715767154.yoga.20632.0 +3 -0
  7. runs/May15_11-59-14_yoga/events.out.tfevents.1715767231.yoga.20632.1 +3 -0
  8. runs/May15_12-32-07_yoga/events.out.tfevents.1715769127.yoga.3665.0 +3 -0
  9. runs/May15_12-32-07_yoga/events.out.tfevents.1715769297.yoga.3665.1 +3 -0
  10. runs/May15_12-35-32_yoga/events.out.tfevents.1715769332.yoga.4477.0 +3 -0
  11. runs/May15_12-35-32_yoga/events.out.tfevents.1715769394.yoga.4477.1 +3 -0
  12. runs/May15_12-37-00_yoga/events.out.tfevents.1715769420.yoga.4937.0 +3 -0
  13. runs/May15_12-37-00_yoga/events.out.tfevents.1715769482.yoga.4937.1 +3 -0
  14. runs/May15_12-38-21_yoga/events.out.tfevents.1715769501.yoga.5290.0 +3 -0
  15. runs/May15_12-38-21_yoga/events.out.tfevents.1715769540.yoga.5290.1 +3 -0
  16. runs/May15_12-39-19_yoga/events.out.tfevents.1715769559.yoga.5579.0 +3 -0
  17. runs/May15_12-39-19_yoga/events.out.tfevents.1715769613.yoga.5579.1 +3 -0
  18. runs/May15_12-40-44_yoga/events.out.tfevents.1715769644.yoga.6097.0 +3 -0
  19. runs/May15_12-40-44_yoga/events.out.tfevents.1715769690.yoga.6097.1 +3 -0
  20. runs/May15_12-41-48_yoga/events.out.tfevents.1715769708.yoga.6405.0 +3 -0
  21. runs/May15_12-41-48_yoga/events.out.tfevents.1715769755.yoga.6405.1 +3 -0
  22. runs/May15_12-42-47_yoga/events.out.tfevents.1715769767.yoga.6676.0 +3 -0
  23. runs/May15_12-42-47_yoga/events.out.tfevents.1715769815.yoga.6676.1 +3 -0
  24. runs/May15_12-43-51_yoga/events.out.tfevents.1715769832.yoga.6970.0 +3 -0
  25. runs/May15_12-43-51_yoga/events.out.tfevents.1715769879.yoga.6970.1 +3 -0
  26. runs/May15_12-45-07_yoga/events.out.tfevents.1715769907.yoga.7308.0 +3 -0
  27. runs/May15_12-45-07_yoga/events.out.tfevents.1715769961.yoga.7308.1 +3 -0
  28. runs/May15_12-46-14_yoga/events.out.tfevents.1715769974.yoga.7614.0 +3 -0
  29. runs/May15_12-46-14_yoga/events.out.tfevents.1715770029.yoga.7614.1 +3 -0
  30. runs/May15_12-47-22_yoga/events.out.tfevents.1715770043.yoga.7928.0 +3 -0
  31. runs/May15_12-47-22_yoga/events.out.tfevents.1715770097.yoga.7928.1 +3 -0
  32. runs/May15_12-48-57_yoga/events.out.tfevents.1715770137.yoga.8445.0 +3 -0
  33. runs/May15_12-48-57_yoga/events.out.tfevents.1715770190.yoga.8445.1 +3 -0
  34. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0431
23
- - F1: 0.8182
24
- - F5: 0.8792
25
- - Precision: 0.6923
26
- - Recall: 1.0
27
 
28
  ## Model description
29
 
@@ -42,33 +42,32 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 2.5e-05
46
- - train_batch_size: 128
47
- - eval_batch_size: 128
48
  - seed: 42
49
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 9
 
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | F1 | F5 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
58
- | No log | 1.0 | 16 | 0.2406 | 0.0 | 0.0 | 0.0 | 0.0 |
59
- | No log | 2.0 | 32 | 0.2933 | 0.6471 | 0.6062 | 0.7857 | 0.55 |
60
- | No log | 3.0 | 48 | 0.1965 | 0.5000 | 0.4297 | 0.875 | 0.35 |
61
- | No log | 4.0 | 64 | 0.1349 | 0.6842 | 0.6707 | 0.7222 | 0.65 |
62
- | No log | 5.0 | 80 | 0.1065 | 0.7027 | 0.6816 | 0.7647 | 0.65 |
63
- | No log | 6.0 | 96 | 0.1104 | 0.7727 | 0.8005 | 0.7083 | 0.85 |
64
- | No log | 7.0 | 112 | 0.1160 | 0.7273 | 0.7534 | 0.6667 | 0.8 |
65
- | No log | 8.0 | 128 | 0.1049 | 0.7647 | 0.7164 | 0.9286 | 0.65 |
66
- | No log | 9.0 | 144 | 0.0975 | 0.7778 | 0.7461 | 0.875 | 0.7 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.38.2
72
- - Pytorch 2.3.0a0+ebedce2
73
- - Datasets 2.17.1
74
  - Tokenizers 0.15.2
 
19
 
20
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1693
23
+ - F1: 0.7857
24
+ - F5: 0.8078
25
+ - Precision: 0.7333
26
+ - Recall: 0.8462
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 64
47
+ - eval_batch_size: 64
48
  - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.2
52
+ - num_epochs: 7
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | F1 | F5 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
59
+ | No log | 1.0 | 30 | 0.2580 | 0.0 | 0.0 | 0.0 | 0.0 |
60
+ | No log | 2.0 | 60 | 0.2658 | 0.08 | 0.0592 | 1.0 | 0.0417 |
61
+ | No log | 3.0 | 90 | 0.1601 | 0.7273 | 0.7644 | 0.6452 | 0.8333 |
62
+ | No log | 4.0 | 120 | 0.1913 | 0.5946 | 0.5340 | 0.8462 | 0.4583 |
63
+ | No log | 5.0 | 150 | 0.2591 | 0.6269 | 0.7030 | 0.4884 | 0.875 |
64
+ | No log | 6.0 | 180 | 0.1832 | 0.625 | 0.625 | 0.625 | 0.625 |
65
+ | No log | 7.0 | 210 | 0.2513 | 0.6383 | 0.6332 | 0.6522 | 0.625 |
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
+ - Transformers 4.38.1
71
+ - Pytorch 2.2.1+cu121
72
+ - Datasets 2.17.0
73
  - Tokenizers 0.15.2
config.json CHANGED
@@ -33,7 +33,7 @@
33
  "position_embedding_type": "absolute",
34
  "problem_type": "single_label_classification",
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.38.2",
37
  "type_vocab_size": 2,
38
  "use_cache": true,
39
  "vocab_size": 119547
 
33
  "position_embedding_type": "absolute",
34
  "problem_type": "single_label_classification",
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
  "type_vocab_size": 2,
38
  "use_cache": true,
39
  "vocab_size": 119547
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02af24f8cb3357f39b2dc0f08945141b588bfcadbc3544e6931cdd7f2d3fce25
3
  size 711443456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a81791380147aa76429d7f2b7753dfff496489e0bdef800cddd7f331426f1d
3
  size 711443456
runs/May15_11-57-39_yoga/events.out.tfevents.1715767059.yoga.20124.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfed8d423809eaa253c2264e72d16dd6dc233f74f7ec816f0d3798d383b33c5
3
+ size 9816
runs/May15_11-57-39_yoga/events.out.tfevents.1715767135.yoga.20124.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9f30a339420a4196525fc7d58e42137a8d332b4abfe68af3af0b73f529b8fd
3
+ size 554
runs/May15_11-59-14_yoga/events.out.tfevents.1715767154.yoga.20632.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a40ba3ca2e2a4230e2052a167b943b430e43e3935bae3b2f58c1aa8aa80bab
3
+ size 9815
runs/May15_11-59-14_yoga/events.out.tfevents.1715767231.yoga.20632.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0821e8f383361b3fd7dc4a764b847aff97ff65bb48e1a50843c98d1c66e942
3
+ size 554
runs/May15_12-32-07_yoga/events.out.tfevents.1715769127.yoga.3665.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60108b0b3e6de805c4042d453a8401896b8b7b5f31fdf0423502a756d5a2e276
3
+ size 9815
runs/May15_12-32-07_yoga/events.out.tfevents.1715769297.yoga.3665.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3049b45650904d2386efd3526a79f912e52b7f57bfcecd21e488735233772c
3
+ size 554
runs/May15_12-35-32_yoga/events.out.tfevents.1715769332.yoga.4477.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb43a7db044cc84e5d9790f9fa1ca6405a6d17684c3462f9efa0d1e1c7f56b30
3
+ size 8882
runs/May15_12-35-32_yoga/events.out.tfevents.1715769394.yoga.4477.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc536ba53a214e94d7b8a13f23eb5e74b6e5f08011d2a30d04f7baba1141f534
3
+ size 554
runs/May15_12-37-00_yoga/events.out.tfevents.1715769420.yoga.4937.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4515de9fbc364de37fc74bac829ed7fbe9a1218d44a3bc1810b6ac93129577c1
3
+ size 8882
runs/May15_12-37-00_yoga/events.out.tfevents.1715769482.yoga.4937.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f057f424e5f821444bd89caa6560241474f0c7638e76a36ee1f06f99da57281c
3
+ size 554
runs/May15_12-38-21_yoga/events.out.tfevents.1715769501.yoga.5290.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c112131de81d58ada120f6ab2d028d582d2b4f96b01afe11417391cda36c30
3
+ size 7484
runs/May15_12-38-21_yoga/events.out.tfevents.1715769540.yoga.5290.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71012f0d473f67e7b62d931ddbf74ed68c9035058c9746b65a613aaaa5f841e
3
+ size 554
runs/May15_12-39-19_yoga/events.out.tfevents.1715769559.yoga.5579.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8789849b9b923283f6f25d4b4fa3aa5c80e634191f3c77af03689049a34c21b2
3
+ size 8416
runs/May15_12-39-19_yoga/events.out.tfevents.1715769613.yoga.5579.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f36f68ff9f524e51c27876562191a0cf160b19ba63c2180410d81fc61b9ccc
3
+ size 554
runs/May15_12-40-44_yoga/events.out.tfevents.1715769644.yoga.6097.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8ba5eee9684c6c3698d604f87d050bb63fd5fa64fc8652ab0e1bede2861651
3
+ size 7950
runs/May15_12-40-44_yoga/events.out.tfevents.1715769690.yoga.6097.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65d7d84063827f2930ac4cc599e277addcaef9924ff6684e0198753ac738275
3
+ size 554
runs/May15_12-41-48_yoga/events.out.tfevents.1715769708.yoga.6405.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da4b7824b02ce6e5353bc36f45d27f3901f16e8b8891641f66171ed2bb610fd
3
+ size 7950
runs/May15_12-41-48_yoga/events.out.tfevents.1715769755.yoga.6405.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95cffcfafb5e7c2667ae26aa94119e1fd5abce317154775d53b318864e5d0b9
3
+ size 554
runs/May15_12-42-47_yoga/events.out.tfevents.1715769767.yoga.6676.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c036a7f3d6dffe665acead38bb9265bfbddd5404b746a31e6c8ce3080134aaa0
3
+ size 7950
runs/May15_12-42-47_yoga/events.out.tfevents.1715769815.yoga.6676.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1e0de085700347947cace01cf040d8bb3c6d1faa85984141cc1e5b1204ac90
3
+ size 554
runs/May15_12-43-51_yoga/events.out.tfevents.1715769832.yoga.6970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d81f832bbc7b67091304169003a153e5fa61e0544b8e113c7ca130377ea1bb4
3
+ size 7950
runs/May15_12-43-51_yoga/events.out.tfevents.1715769879.yoga.6970.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745881182df270fb12a7eceea9cbe6cef0a005bb511c0b415d52bc111286adeb
3
+ size 554
runs/May15_12-45-07_yoga/events.out.tfevents.1715769907.yoga.7308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6f1d7ec2c47ace6ae6e460b951e381b63fc5ca379817fee19610f49addb79f
3
+ size 8416
runs/May15_12-45-07_yoga/events.out.tfevents.1715769961.yoga.7308.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441d9e0adb0d5454870f3423ccefb919e1fe4050d107b5a2d189baf8e4394e2c
3
+ size 554
runs/May15_12-46-14_yoga/events.out.tfevents.1715769974.yoga.7614.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda2d9ab71c70fedf2b44b73c61d5103820b2567170782cee08caeb381174612
3
+ size 8416
runs/May15_12-46-14_yoga/events.out.tfevents.1715770029.yoga.7614.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e914f4e86cd714c60cde40599c706fb8f04acc9d5c12c857f73d4271fff998
3
+ size 554
runs/May15_12-47-22_yoga/events.out.tfevents.1715770043.yoga.7928.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7cd2ba0bd92e4f93b71cfcd3cc64cf407f86d2e02f247ceed7846051817cc9
3
+ size 8416
runs/May15_12-47-22_yoga/events.out.tfevents.1715770097.yoga.7928.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570206dbfa25e6fac42e03b18e68cc3a7f1c8f5df1fa51d12d77bd3941cdf16f
3
+ size 554
runs/May15_12-48-57_yoga/events.out.tfevents.1715770137.yoga.8445.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc86286b2547cf25672d03ccfa3d34d55315b51db8d3b6c5529771d4e765444d
3
+ size 8416
runs/May15_12-48-57_yoga/events.out.tfevents.1715770190.yoga.8445.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:549886373c2d72fbdd204386af05017aa15c3ed6923b0ed3ed95f2a78aa75b73
3
+ size 554
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab980b1abcf7e240f9433a8c677a2d39e58cbba2282336155fa69ce0142fcec1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feafb12dae99288d27f51f5c2198a84f9202bc396fbcc6e35fb017a7ddd62a1b
3
  size 4920