Hugging Face's logo

Habaznya
/
p_model_2

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Habaznya commited on
Commit
9df1906
•
1 Parent(s): 5a44430

End of training

Browse files
Files changed (9) hide show
  1. README.md +14 -22
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Jun18_12-06-16_6dd0c134a67e/events.out.tfevents.1718712377.6dd0c134a67e.448.3 +3 -0
  5. runs/Jun18_12-07-32_6dd0c134a67e/events.out.tfevents.1718712452.6dd0c134a67e.448.4 +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +0 -2
  8. training_args.bin +1 -1
  9. vocab.txt +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: DmitryPogrebnoy/distilbert-base-russian-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # p_model_2
17
 
18
- This model is a fine-tuned version of [DmitryPogrebnoy/distilbert-base-russian-cased](https://huggingface.co/DmitryPogrebnoy/distilbert-base-russian-cased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9677
21
- - Accuracy: 0.7463
22
 
23
  ## Model description
24
 
@@ -43,27 +43,19 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 15
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 0.9388 | 1.0 | 832 | 0.7499 | 0.7188 |
53
- | 0.7211 | 2.0 | 1664 | 0.7321 | 0.7256 |
54
- | 0.6823 | 3.0 | 2496 | 0.7019 | 0.7431 |
55
- | 0.6092 | 4.0 | 3328 | 0.7059 | 0.7481 |
56
- | 0.5631 | 5.0 | 4160 | 0.7234 | 0.7447 |
57
- | 0.5552 | 6.0 | 4992 | 0.7394 | 0.7474 |
58
- | 0.5058 | 7.0 | 5824 | 0.7752 | 0.7483 |
59
- | 0.4731 | 8.0 | 6656 | 0.7877 | 0.7431 |
60
- | 0.4635 | 9.0 | 7488 | 0.8051 | 0.7515 |
61
- | 0.434 | 10.0 | 8320 | 0.8866 | 0.7431 |
62
- | 0.4246 | 11.0 | 9152 | 0.8953 | 0.7472 |
63
- | 0.4024 | 12.0 | 9984 | 0.9281 | 0.7478 |
64
- | 0.3917 | 13.0 | 10816 | 0.9527 | 0.7465 |
65
- | 0.3787 | 14.0 | 11648 | 0.9664 | 0.7456 |
66
- | 0.3672 | 15.0 | 12480 | 0.9677 | 0.7463 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert/distilbert-base-multilingual-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # p_model_2
17
 
18
+ This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4648
21
+ - Accuracy: 0.8717
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 7
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.8037 | 1.0 | 832 | 0.5854 | 0.7853 |
53
+ | 0.4857 | 2.0 | 1664 | 0.4879 | 0.8249 |
54
+ | 0.4191 | 3.0 | 2496 | 0.4377 | 0.8522 |
55
+ | 0.3187 | 4.0 | 3328 | 0.4219 | 0.8585 |
56
+ | 0.2514 | 5.0 | 4160 | 0.4561 | 0.8612 |
57
+ | 0.2461 | 6.0 | 4992 | 0.4676 | 0.8660 |
58
+ | 0.1863 | 7.0 | 5824 | 0.4648 | 0.8717 |
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "DmitryPogrebnoy/distilbert-base-russian-cased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
@@ -36,5 +36,5 @@
36
  "tie_weights_": true,
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.41.2",
39
- "vocab_size": 13982
40
  }
 
1
  {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
36
  "tie_weights_": true,
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.41.2",
39
+ "vocab_size": 119547
40
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c094e9c9513a7b15a1492696327536658e93789efacac2b88ca4eb5db8728e9
3
- size 217030868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b756d5a072f4a43308a687417a434fe285ab83429d3dbb8389ea2e8c1e538086
3
+ size 541326604
runs/Jun18_12-06-16_6dd0c134a67e/events.out.tfevents.1718712377.6dd0c134a67e.448.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3eb905696bf83418ff17bb71d67a6dd9f695bc0407202af1388bad63ae0471
3
+ size 4930
runs/Jun18_12-07-32_6dd0c134a67e/events.out.tfevents.1718712452.6dd0c134a67e.448.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98305262745f3b3426a3796d3034c54cc2a9907a74274ba0ae8f07ac2b8cd13
3
+ size 9865
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,11 +43,9 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
  "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
- "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db2b0d264611103c12783d7f136a90baae132a2c4df19fbfd38852ebde554df
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c00bd78f64e5e4a3356da56e89b6aa7a836bc29027d58517a76319f1344e4d
3
  size 5112
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff