juro95 commited on
Commit
83bc5bd
1 Parent(s): 8c8d690

Training in progress epoch 0

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: juro95/xlm-roberta-finetuned-ner-5-with-skills
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # juro95/xlm-roberta-finetuned-ner-5-with-skills
14
+
15
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.3044
18
+ - Validation Loss: 0.1808
19
+ - Epoch: 0
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 65502, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
+ - training_precision: mixed_float16
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Validation Loss | Epoch |
44
+ |:----------:|:---------------:|:-----:|
45
+ | 0.3044 | 0.1808 | 0 |
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.25.1
51
+ - TensorFlow 2.6.5
52
+ - Datasets 2.3.2
53
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-occupation",
16
+ "10": "I-company_name",
17
+ "11": "B-skill",
18
+ "12": "I-skill",
19
+ "13": "B-nace_code",
20
+ "14": "I-nace_code",
21
+ "15": "B-location",
22
+ "16": "I-location",
23
+ "2": "I-occupation",
24
+ "3": "B-working_type",
25
+ "4": "I-working_type",
26
+ "5": "B-experience/seniority",
27
+ "6": "I-experience/seniority",
28
+ "7": "B-emplyoment-/contract_type",
29
+ "8": "I-emplyoment-/contract_type",
30
+ "9": "B-company_name"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "B-company_name": "9",
36
+ "B-emplyoment-/contract_type": "7",
37
+ "B-experience/seniority": "5",
38
+ "B-location": "15",
39
+ "B-nace_code": "13",
40
+ "B-occupation": "1",
41
+ "B-skill": "11",
42
+ "B-working_type": "3",
43
+ "I-company_name": "10",
44
+ "I-emplyoment-/contract_type": "8",
45
+ "I-experience/seniority": "6",
46
+ "I-location": "16",
47
+ "I-nace_code": "14",
48
+ "I-occupation": "2",
49
+ "I-skill": "12",
50
+ "I-working_type": "4",
51
+ "O": "0"
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "max_position_embeddings": 514,
55
+ "model_type": "xlm-roberta",
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "output_past": true,
59
+ "pad_token_id": 1,
60
+ "position_embedding_type": "absolute",
61
+ "transformers_version": "4.25.1",
62
+ "type_vocab_size": 1,
63
+ "use_cache": true,
64
+ "vocab_size": 250002
65
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8ada444a6b3f0eaccbbc846605c51b0a0fbf55a696971c27bd286fd248cca0
3
+ size 1110152336
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }