Hugging Face's logo

disk0dancer
/
ruBert-base-finetuned-pos

Token Classification
Transformers
TensorBoard
Safetensors
Russian
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
disk0dancer commited on
Commit
f69e2f5
·
verified ·
1 Parent(s): 28f39a5

End of training

Browse files
Files changed (19) hide show
  1. README.md +71 -17
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Mar22_08-32-13_81a9b4ddc734/events.out.tfevents.1711096334.81a9b4ddc734.5595.0 +3 -0
  5. runs/Mar22_08-32-13_81a9b4ddc734/events.out.tfevents.1711096336.81a9b4ddc734.5595.1 +3 -0
  6. runs/Mar22_08-32-30_81a9b4ddc734/events.out.tfevents.1711096351.81a9b4ddc734.5595.2 +3 -0
  7. runs/Mar22_08-32-58_81a9b4ddc734/events.out.tfevents.1711096379.81a9b4ddc734.5595.3 +3 -0
  8. runs/Mar22_08-32-58_81a9b4ddc734/events.out.tfevents.1711096380.81a9b4ddc734.5595.4 +3 -0
  9. runs/Mar22_08-33-36_81a9b4ddc734/events.out.tfevents.1711096417.81a9b4ddc734.5595.5 +3 -0
  10. runs/Mar22_08-33-36_81a9b4ddc734/events.out.tfevents.1711096418.81a9b4ddc734.5595.6 +3 -0
  11. runs/Mar22_08-34-37_81a9b4ddc734/events.out.tfevents.1711096478.81a9b4ddc734.5595.7 +3 -0
  12. runs/Mar22_08-34-37_81a9b4ddc734/events.out.tfevents.1711096478.81a9b4ddc734.5595.8 +3 -0
  13. runs/Mar22_08-36-55_81a9b4ddc734/events.out.tfevents.1711096616.81a9b4ddc734.5595.10 +3 -0
  14. runs/Mar22_08-36-55_81a9b4ddc734/events.out.tfevents.1711096616.81a9b4ddc734.5595.9 +3 -0
  15. runs/Mar22_08-37-58_81a9b4ddc734/events.out.tfevents.1711096679.81a9b4ddc734.5595.11 +3 -0
  16. runs/Mar22_08-37-58_81a9b4ddc734/events.out.tfevents.1711096679.81a9b4ddc734.5595.12 +3 -0
  17. runs/Mar22_08-54-12_81a9b4ddc734/events.out.tfevents.1711097653.81a9b4ddc734.13612.0 +3 -0
  18. runs/Mar22_08-54-12_81a9b4ddc734/events.out.tfevents.1711098370.81a9b4ddc734.13612.1 +3 -0
  19. training_args.bin +1 -1
README.md CHANGED
@@ -3,14 +3,14 @@ license: apache-2.0
3
  base_model: ai-forever/ruBert-base
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
6
  model-index:
7
  - name: ruBert-base-finetuned-pos
8
  results: []
9
- language:
10
- - ru
11
- pipeline_tag: token-classification
12
- metrics:
13
- - accuracy
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,24 +18,27 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # ruBert-base-finetuned-pos
20
 
21
- This model is a PEFT fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the [disk0dancer/ru_sentances_pos](https://huggingface.co/datasets/disk0dancer/ru_sentances_pos).
 
 
 
 
 
 
22
 
23
  ## Model description
24
 
25
- This model classify tokens into 56 labels by Part of Speech&
26
-
27
 
28
- ## Training and evaluation data
29
 
30
- #### Train:
31
- - Dataset`s training part (70 sentances) was resampled by sliding window with LENGTH=[1, len(sample)] into 20.000 samples
32
 
33
- #### Validation:
34
- - Validation during training was at not resampled 20 sentances
35
 
36
- #### Test:
37
- - Finally, model was tested at not resampled 10 sentances
38
 
 
39
 
40
  ### Training hyperparameters
41
 
@@ -46,11 +49,62 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
  ### Framework versions
52
 
53
- - Transformers 4.38.2
54
  - Pytorch 2.2.1+cu121
55
  - Datasets 2.18.0
56
  - Tokenizers 0.15.2
 
3
  base_model: ai-forever/ruBert-base
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
  model-index:
12
  - name: ruBert-base-finetuned-pos
13
  results: []
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
18
 
19
  # ruBert-base-finetuned-pos
20
 
21
+ This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.8209
24
+ - Precision: 0.5
25
+ - Recall: 0.0071
26
+ - F1: 0.0140
27
+ - Accuracy: 0.2141
28
 
29
  ## Model description
30
 
31
+ More information needed
 
32
 
33
+ ## Intended uses & limitations
34
 
35
+ More information needed
 
36
 
37
+ ## Training and evaluation data
 
38
 
39
+ More information needed
 
40
 
41
+ ## Training procedure
42
 
43
  ### Training hyperparameters
44
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 45
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 1 | 3.6999 | 0.0261 | 0.0260 | 0.0260 | 0.0107 |
59
+ | No log | 2.0 | 2 | 3.4111 | 0.0382 | 0.0355 | 0.0368 | 0.0043 |
60
+ | No log | 3.0 | 3 | 3.1202 | 0.0645 | 0.0473 | 0.0546 | 0.0043 |
61
+ | No log | 4.0 | 4 | 2.8246 | 0.0625 | 0.0307 | 0.0412 | 0.0021 |
62
+ | No log | 5.0 | 5 | 2.5289 | 0.0426 | 0.0095 | 0.0155 | 0.0 |
63
+ | No log | 6.0 | 6 | 2.2452 | 0.0 | 0.0 | 0.0 | 0.0 |
64
+ | No log | 7.0 | 7 | 1.9900 | 0.0 | 0.0 | 0.0 | 0.0 |
65
+ | No log | 8.0 | 8 | 1.7794 | 0.0 | 0.0 | 0.0 | 0.0 |
66
+ | No log | 9.0 | 9 | 1.6144 | 0.0 | 0.0 | 0.0 | 0.0 |
67
+ | No log | 10.0 | 10 | 1.4867 | 0.0 | 0.0 | 0.0 | 0.0 |
68
+ | No log | 11.0 | 11 | 1.3877 | 0.0 | 0.0 | 0.0 | 0.0 |
69
+ | No log | 12.0 | 12 | 1.3110 | 0.0 | 0.0 | 0.0 | 0.0 |
70
+ | No log | 13.0 | 13 | 1.2515 | 0.0 | 0.0 | 0.0 | 0.0 |
71
+ | No log | 14.0 | 14 | 1.2053 | 0.0 | 0.0 | 0.0 | 0.0 |
72
+ | No log | 15.0 | 15 | 1.1687 | 0.0 | 0.0 | 0.0 | 0.0 |
73
+ | No log | 16.0 | 16 | 1.1389 | 0.0 | 0.0 | 0.0 | 0.0 |
74
+ | No log | 17.0 | 17 | 1.1135 | 0.0 | 0.0 | 0.0 | 0.0 |
75
+ | No log | 18.0 | 18 | 1.0908 | 0.0 | 0.0 | 0.0 | 0.0 |
76
+ | No log | 19.0 | 19 | 1.0698 | 0.0 | 0.0 | 0.0 | 0.0 |
77
+ | No log | 20.0 | 20 | 1.0500 | 0.0 | 0.0 | 0.0 | 0.0 |
78
+ | No log | 21.0 | 21 | 1.0312 | 0.0 | 0.0 | 0.0 | 0.0 |
79
+ | No log | 22.0 | 22 | 1.0132 | 0.0 | 0.0 | 0.0 | 0.0 |
80
+ | No log | 23.0 | 23 | 0.9962 | 0.0 | 0.0 | 0.0 | 0.0 |
81
+ | No log | 24.0 | 24 | 0.9801 | 0.0 | 0.0 | 0.0 | 0.0 |
82
+ | No log | 25.0 | 25 | 0.9648 | 0.0 | 0.0 | 0.0 | 0.0 |
83
+ | No log | 26.0 | 26 | 0.9504 | 0.0 | 0.0 | 0.0 | 0.0 |
84
+ | No log | 27.0 | 27 | 0.9368 | 0.0 | 0.0 | 0.0 | 0.0 |
85
+ | No log | 28.0 | 28 | 0.9241 | 0.0 | 0.0 | 0.0 | 0.0043 |
86
+ | No log | 29.0 | 29 | 0.9121 | 0.0 | 0.0 | 0.0 | 0.0128 |
87
+ | No log | 30.0 | 30 | 0.9009 | 0.0 | 0.0 | 0.0 | 0.0236 |
88
+ | No log | 31.0 | 31 | 0.8905 | 0.0 | 0.0 | 0.0 | 0.0385 |
89
+ | No log | 32.0 | 32 | 0.8809 | 0.0 | 0.0 | 0.0 | 0.0578 |
90
+ | No log | 33.0 | 33 | 0.8720 | 0.0 | 0.0 | 0.0 | 0.0792 |
91
+ | No log | 34.0 | 34 | 0.8639 | 0.0 | 0.0 | 0.0 | 0.1006 |
92
+ | No log | 35.0 | 35 | 0.8566 | 0.0 | 0.0 | 0.0 | 0.1199 |
93
+ | No log | 36.0 | 36 | 0.8500 | 0.0 | 0.0 | 0.0 | 0.1478 |
94
+ | No log | 37.0 | 37 | 0.8440 | 0.5 | 0.0024 | 0.0047 | 0.1713 |
95
+ | No log | 38.0 | 38 | 0.8388 | 0.5 | 0.0024 | 0.0047 | 0.1863 |
96
+ | No log | 39.0 | 39 | 0.8343 | 0.5 | 0.0024 | 0.0047 | 0.1949 |
97
+ | No log | 40.0 | 40 | 0.8304 | 0.5 | 0.0047 | 0.0094 | 0.2034 |
98
+ | No log | 41.0 | 41 | 0.8272 | 0.5 | 0.0047 | 0.0094 | 0.2099 |
99
+ | No log | 42.0 | 42 | 0.8247 | 0.5 | 0.0071 | 0.0140 | 0.2120 |
100
+ | No log | 43.0 | 43 | 0.8228 | 0.5 | 0.0071 | 0.0140 | 0.2120 |
101
+ | No log | 44.0 | 44 | 0.8215 | 0.5 | 0.0071 | 0.0140 | 0.2141 |
102
+ | No log | 45.0 | 45 | 0.8209 | 0.5 | 0.0071 | 0.0140 | 0.2141 |
103
+
104
 
105
  ### Framework versions
106
 
107
+ - Transformers 4.39.0
108
  - Pytorch 2.2.1+cu121
109
  - Datasets 2.18.0
110
  - Tokenizers 0.15.2
config.json CHANGED
@@ -140,7 +140,7 @@
140
  "pooler_type": "first_token_transform",
141
  "position_embedding_type": "absolute",
142
  "torch_dtype": "float32",
143
- "transformers_version": "4.38.2",
144
  "type_vocab_size": 2,
145
  "use_cache": true,
146
  "vocab_size": 120138
 
140
  "pooler_type": "first_token_transform",
141
  "position_embedding_type": "absolute",
142
  "torch_dtype": "float32",
143
+ "transformers_version": "4.39.0",
144
  "type_vocab_size": 2,
145
  "use_cache": true,
146
  "vocab_size": 120138
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9c450c9aa31d86523540290951ad34da0494ca6efccc18e32fcd396930a0719
3
  size 711062560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8bef7ffa6304e30b98cbd77ad108e809957d44c5c544a446026ac33b25ab44
3
  size 711062560
runs/Mar22_08-32-13_81a9b4ddc734/events.out.tfevents.1711096334.81a9b4ddc734.5595.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004633eca1d9305c5c4a4fe50a046a277f3ac86b92a29bc34f9e44623743e938
3
+ size 7359
runs/Mar22_08-32-13_81a9b4ddc734/events.out.tfevents.1711096336.81a9b4ddc734.5595.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb80e060361e8c5a8f059bcecea9539136f0d82da52b570202c23cb060a8876
3
+ size 533
runs/Mar22_08-32-30_81a9b4ddc734/events.out.tfevents.1711096351.81a9b4ddc734.5595.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7101e3b3232de8bf9b50555e1b29f026cd2d355ef0e9e3901ba78594cc94b0f4
3
+ size 7359
runs/Mar22_08-32-58_81a9b4ddc734/events.out.tfevents.1711096379.81a9b4ddc734.5595.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0822ad11a3ba6ad2456a5b3b4aeb2e95a9305e027339eae000c826e1f9b1489
3
+ size 7359
runs/Mar22_08-32-58_81a9b4ddc734/events.out.tfevents.1711096380.81a9b4ddc734.5595.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1b396540fed0a75de1b01914c2881cdea32ed3765f95991b3ed581545129e4
3
+ size 533
runs/Mar22_08-33-36_81a9b4ddc734/events.out.tfevents.1711096417.81a9b4ddc734.5595.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e451d0372349f8119c4a77cdd82408b952c5e76179a6af1e8b6bba6c5eabe3e3
3
+ size 7359
runs/Mar22_08-33-36_81a9b4ddc734/events.out.tfevents.1711096418.81a9b4ddc734.5595.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1dfc936f5ab6c5ab28297c9352829fc04255e6f9abe88a93b0f5b599be87415
3
+ size 533
runs/Mar22_08-34-37_81a9b4ddc734/events.out.tfevents.1711096478.81a9b4ddc734.5595.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71352bfe089d474bcd4c9186ba825aee290b78482ce40826112fb5b8cfb7584a
3
+ size 7359
runs/Mar22_08-34-37_81a9b4ddc734/events.out.tfevents.1711096478.81a9b4ddc734.5595.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142678fabcaba49e019c428ab655ed2624729eab3a0fcf326d7fdd8675a5aa4a
3
+ size 533
runs/Mar22_08-36-55_81a9b4ddc734/events.out.tfevents.1711096616.81a9b4ddc734.5595.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1496e74b2db002b86e3551b882ad67445a29a01dfde41e7a6851c507fda6a8
3
+ size 533
runs/Mar22_08-36-55_81a9b4ddc734/events.out.tfevents.1711096616.81a9b4ddc734.5595.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e28678b8d00f61c639ee6a59dfdd03f4c297d86bf6de67357f4e8ad0993d93
3
+ size 7359
runs/Mar22_08-37-58_81a9b4ddc734/events.out.tfevents.1711096679.81a9b4ddc734.5595.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdfe229fd2fe52677c1d9f8cf668fcaf7b2f2c407a974cdbd6a983a520dd011
3
+ size 7359
runs/Mar22_08-37-58_81a9b4ddc734/events.out.tfevents.1711096679.81a9b4ddc734.5595.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcc7e767c86c3cfa0f007b61533f5934646fff209ede8b7b1d8c7bc14535d07
3
+ size 533
runs/Mar22_08-54-12_81a9b4ddc734/events.out.tfevents.1711097653.81a9b4ddc734.13612.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9609d1e240645ae912e105d0fc86af792823ff8e0803e37c85b9c50c03ab9af
3
+ size 28207
runs/Mar22_08-54-12_81a9b4ddc734/events.out.tfevents.1711098370.81a9b4ddc734.13612.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b432d029b87700686f359d1c07103c90c1cda0294d3c504cc45945a9bb7c715
3
+ size 551
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba023a3342832acbecdae7796454869353f46a0acfd7e3d4bc0d5103123dfc7f
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e843f9bb13cce47a7fee3ecb79652740dc733dc8f7a6a98dc56fe2d8f07a82
3
  size 4920