stulcrad commited on
Commit
f455b84
1 Parent(s): eb38e0a

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore CHANGED
@@ -1,3 +1,3 @@
1
- *
2
- *.json
3
- !.gitignore
 
1
+ # *
2
+ # *.json
3
+ # !.gitignore
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-large
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: fine_tuned_XLMROBERTA_cs_wikann
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # fine_tuned_XLMROBERTA_cs_wikann
15
+
16
+ This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.1238
19
+ - Overall Precision: 0.8962
20
+ - Overall Recall: 0.9193
21
+ - Overall F1: 0.9076
22
+ - Overall Accuracy: 0.9684
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 3.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
53
+ | 0.3625 | 0.4 | 500 | 0.1809 | 0.7915 | 0.8509 | 0.8201 | 0.9486 |
54
+ | 0.1807 | 0.8 | 1000 | 0.1373 | 0.8363 | 0.8785 | 0.8568 | 0.9583 |
55
+ | 0.1384 | 1.2 | 1500 | 0.1371 | 0.8758 | 0.9085 | 0.8918 | 0.9651 |
56
+ | 0.1079 | 1.6 | 2000 | 0.1467 | 0.8924 | 0.9168 | 0.9044 | 0.9659 |
57
+ | 0.0997 | 2.0 | 2500 | 0.1170 | 0.9018 | 0.9264 | 0.9139 | 0.9700 |
58
+ | 0.0644 | 2.4 | 3000 | 0.1344 | 0.9123 | 0.9285 | 0.9203 | 0.9706 |
59
+ | 0.0594 | 2.8 | 3500 | 0.1269 | 0.9138 | 0.9345 | 0.9240 | 0.9718 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.36.2
65
+ - Pytorch 2.1.2+cu121
66
+ - Datasets 2.16.1
67
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
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": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-PER",
16
+ "2": "I-PER",
17
+ "3": "B-ORG",
18
+ "4": "I-ORG",
19
+ "5": "B-LOC",
20
+ "6": "I-LOC"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "B-LOC": 5,
26
+ "B-ORG": 3,
27
+ "B-PER": 1,
28
+ "I-LOC": 6,
29
+ "I-ORG": 4,
30
+ "I-PER": 2,
31
+ "O": 0
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.36.2",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 250002
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd09fa201110d056da479b14b1129f7282c8edb220bcc420dc589e675504f988
3
+ size 2235440556
runs/Dec13_02-41-07_n26/events.out.tfevents.1702431672.n26.81031.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1129ce5f9877fa60b7ab89844cf258785a36a84c7441d141d0c6589959f76f02
3
+ size 9583
runs/Dec13_02-52-24_n26/events.out.tfevents.1702432347.n26.81031.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1726fa5ce7e0efcd1fd4e610962ce2832de720eaae83daee2be597e96cce076f
3
+ size 5932
runs/Dec13_02-55-54_n26/events.out.tfevents.1702432556.n26.81674.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b810b69f975eb710278b80c77bdde91084d22940b9994097f309bc1fcbf59fb6
3
+ size 9591
runs/Dec13_02-55-54_n26/events.out.tfevents.1702433096.n26.81674.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fe102b19696534326c5884e8e9d41b939a2a67a7ac788cdab988b8ae812c4bd
3
+ size 544
runs/Dec26_19-04-22_n32/events.out.tfevents.1703613867.n32.1384543.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2b4fbb715c834474af544036c6cadd459cbcc09e7dd89b0f61ccce8522b936
3
+ size 9593
runs/Dec26_19-04-22_n32/events.out.tfevents.1703615214.n32.1384543.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c088b1a2bc1c41d7c2be35b4092898e831c100ce5081819be27abe3c0c8ee8d
3
+ size 1048
runs/Jan16_01-53-22_n25/events.out.tfevents.1705366426.n25.620727.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b37afb07a85605d16d5dcc029cf7c5404f572ae72c602f077cafd69c0772e6
3
+ size 9630
runs/Jan16_01-53-22_n25/events.out.tfevents.1705367769.n25.620727.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff0c1083c10bd180fbb396238aceafce51f072d8b826c3c3b2bce16f14c8638
3
+ size 1552
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a30c003ed329cd968cc7b555311e89954f12c145a30513142693b6cde2e58a5
3
+ size 4728