Hugging Face's logo

bdihia
/
model

Token Classification
Transformers
TensorBoard
Safetensors
camembert
Generated from Trainer
Model card Files Metrics Community
bdihia commited on
Commit
2ff25f5
·
verified ·
1 Parent(s): 568ca33

bdihia/model

Browse files
Files changed (17) hide show
  1. README.md +76 -0
  2. added_tokens.json +3 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. runs/Nov06_16-23-15_a360a03b1920/events.out.tfevents.1730910197.a360a03b1920.1184.0 +3 -0
  6. runs/Nov06_16-31-06_a360a03b1920/events.out.tfevents.1730910667.a360a03b1920.1184.1 +3 -0
  7. runs/Nov06_16-44-21_a360a03b1920/events.out.tfevents.1730911463.a360a03b1920.1184.2 +3 -0
  8. runs/Nov06_16-53-36_a360a03b1920/events.out.tfevents.1730912019.a360a03b1920.1184.3 +3 -0
  9. runs/Nov06_16-59-01_a360a03b1920/events.out.tfevents.1730912342.a360a03b1920.1184.4 +3 -0
  10. runs/Nov06_17-00-13_a360a03b1920/events.out.tfevents.1730912415.a360a03b1920.1184.5 +3 -0
  11. runs/Nov06_17-37-44_a360a03b1920/events.out.tfevents.1730914665.a360a03b1920.1184.6 +3 -0
  12. runs/Nov06_17-40-53_a360a03b1920/events.out.tfevents.1730914855.a360a03b1920.1184.7 +3 -0
  13. sentencepiece.bpe.model +3 -0
  14. special_tokens_map.json +20 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +84 -0
  17. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: almanach/camembert-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: model
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # model
21
+
22
+ This model is a fine-tuned version of [almanach/camembert-base](https://huggingface.co/almanach/camembert-base) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0103
25
+ - Precision: 0.0
26
+ - Recall: 0.0
27
+ - F1: 0.0
28
+ - Accuracy: 0.9982
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 10
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
59
+ | No log | 1.0 | 160 | 0.0086 | 0.0 | 0.0 | 0.0 | 0.9981 |
60
+ | No log | 2.0 | 320 | 0.0091 | 0.0 | 0.0 | 0.0 | 0.9984 |
61
+ | No log | 3.0 | 480 | 0.0101 | 0.0 | 0.0 | 0.0 | 0.9982 |
62
+ | 0.001 | 4.0 | 640 | 0.0093 | 0.0 | 0.0 | 0.0 | 0.9984 |
63
+ | 0.001 | 5.0 | 800 | 0.0094 | 0.0 | 0.0 | 0.0 | 0.9980 |
64
+ | 0.001 | 6.0 | 960 | 0.0091 | 0.0 | 0.0 | 0.0 | 0.9983 |
65
+ | 0.0007 | 7.0 | 1120 | 0.0102 | 0.0 | 0.0 | 0.0 | 0.9984 |
66
+ | 0.0007 | 8.0 | 1280 | 0.0108 | 0.0 | 0.0 | 0.0 | 0.9981 |
67
+ | 0.0007 | 9.0 | 1440 | 0.0103 | 0.0 | 0.0 | 0.0 | 0.9982 |
68
+ | 0.0009 | 10.0 | 1600 | 0.0103 | 0.0 | 0.0 | 0.0 | 0.9982 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.44.2
74
+ - Pytorch 2.4.1+cu121
75
+ - Datasets 3.1.0
76
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembert-base",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "camembert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.44.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b02d3e071fd087c28e50fda055600b912304d5b6b9b5ebd2223afb18b4f04fa
3
+ size 440155504
runs/Nov06_16-23-15_a360a03b1920/events.out.tfevents.1730910197.a360a03b1920.1184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbcef350379c0354d09c5f33c52ef7c7fe387f51005a01261cca0934635cc5a
3
+ size 10669
runs/Nov06_16-31-06_a360a03b1920/events.out.tfevents.1730910667.a360a03b1920.1184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f08c9545bd607deec920610fc4d82291cdee1fb0497154c51ccd484c62871c
3
+ size 10708
runs/Nov06_16-44-21_a360a03b1920/events.out.tfevents.1730911463.a360a03b1920.1184.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5716710f8473bb93466fd047575b28ffa85cf2dd08c7b1c56bcdc8b4b8a8733e
3
+ size 10708
runs/Nov06_16-53-36_a360a03b1920/events.out.tfevents.1730912019.a360a03b1920.1184.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259988d2f6c645670b62a4d698f54e5a1e6aa947a42b1167d353a377b70a6d23
3
+ size 10669
runs/Nov06_16-59-01_a360a03b1920/events.out.tfevents.1730912342.a360a03b1920.1184.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a79db09ffa4a453a2db4152e049d6b29de51c93513013616b3119a9a74d042c
3
+ size 6628
runs/Nov06_17-00-13_a360a03b1920/events.out.tfevents.1730912415.a360a03b1920.1184.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9401a51cf75601e997ad7d29b3084c9fad65d164d2fd9b72bec6749acb053d
3
+ size 10708
runs/Nov06_17-37-44_a360a03b1920/events.out.tfevents.1730914665.a360a03b1920.1184.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd30f3feb004694de09f42ededbd52472055d8036eec142d7c80fb44a33bcff
3
+ size 7581
runs/Nov06_17-40-53_a360a03b1920/events.out.tfevents.1730914855.a360a03b1920.1184.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953870bddf1b128ff768595a354ac2e918ea0604d983cd27de37ea6ff8b36437
3
+ size 10717
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>NOTUSED",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>NOTUSED",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "4": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "5": {
37
+ "content": "<s>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "6": {
45
+ "content": "</s>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32004": {
53
+ "content": "<mask>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32005": {
61
+ "content": "<unk>NOTUSED",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<s>NOTUSED",
71
+ "</s>NOTUSED",
72
+ "<unk>NOTUSED"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "clean_up_tokenization_spaces": true,
76
+ "cls_token": "<s>",
77
+ "eos_token": "</s>",
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 512,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d64ba85feef1a1e197ed608e8e7f5e7af14c49c1858d2a08b76dc5fc6a2be3
3
+ size 5240