Hugging Face's logo

Dmitry2000
/
xlm-roberta-base-finetuned-panx-de

TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Model card Files Metrics Community
Dmitry2000 commited on
Commit
688b15f
·
verified ·
1 Parent(s): 3e2d8ad

Training completed

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. README.md +62 -0
  3. config.json +47 -0
  4. model.safetensors +3 -0
  5. runs/Oct12_15-30-16_SRV/events.out.tfevents.1728736235.SRV.3871554.0 +3 -0
  6. runs/Oct12_15-33-05_SRV/events.out.tfevents.1728736386.SRV.3871554.1 +3 -0
  7. runs/Oct12_15-58-25_SRV/events.out.tfevents.1728737919.SRV.3871554.2 +3 -0
  8. runs/Oct14_22-59-18_SRV/events.out.tfevents.1728935959.SRV.3092729.0 +3 -0
  9. runs/Oct14_23-03-53_SRV/events.out.tfevents.1728936299.SRV.3092729.1 +3 -0
  10. runs/Oct17_18-39-57_SRV/events.out.tfevents.1729179598.SRV.2230521.0 +3 -0
  11. runs/Oct18_17-53-35_SRV/events.out.tfevents.1729263216.SRV.3730705.0 +3 -0
  12. runs/Oct18_17-53-35_SRV/events.out.tfevents.1729264094.SRV.3730705.1 +3 -0
  13. runs/Oct18_18-36-09_SRV/events.out.tfevents.1729265770.SRV.3768434.0 +3 -0
  14. runs/Oct19_12-48-02_SRV/events.out.tfevents.1729331284.SRV.412824.0 +3 -0
  15. runs/Oct19_12-48-02_SRV/events.out.tfevents.1729331339.SRV.412824.1 +3 -0
  16. runs/Oct19_12-48-02_SRV/events.out.tfevents.1729333703.SRV.412824.2 +3 -0
  17. runs/Oct19_14-58-36_SRV/events.out.tfevents.1729339117.SRV.515691.0 +3 -0
  18. runs/Oct19_14-58-36_SRV/events.out.tfevents.1729339270.SRV.515691.1 +3 -0
  19. runs/Oct19_14-58-36_SRV/events.out.tfevents.1729354813.SRV.515691.2 +3 -0
  20. sentencepiece.bpe.model +3 -0
  21. special_tokens_map.json +15 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +54 -0
  24. training_args.bin +3 -0
.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
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: xlm-roberta-base-finetuned-panx-de
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # xlm-roberta-base-finetuned-panx-de
17
+
18
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.1418
21
+ - F1: 0.1097
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 48
42
+ - eval_batch_size: 48
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | No log | 1.0 | 6 | 1.4556 | 0.0 |
53
+ | 1.5911 | 2.0 | 12 | 1.2352 | 0.0397 |
54
+ | 1.5911 | 3.0 | 18 | 1.1418 | 0.1097 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.41.2
60
+ - Pytorch 2.3.1+cu118
61
+ - Datasets 2.20.0
62
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "-100": "IGN",
15
+ "0": "O",
16
+ "1": "B-PER",
17
+ "2": "I-PER",
18
+ "3": "B-ORG",
19
+ "4": "I-ORG",
20
+ "5": "B-LOC",
21
+ "6": "I-LOC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 5,
27
+ "B-ORG": 3,
28
+ "B-PER": 1,
29
+ "I-LOC": 6,
30
+ "I-ORG": 4,
31
+ "I-PER": 2,
32
+ "O": 0
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 514,
36
+ "model_type": "xlm-roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "output_past": true,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.41.2",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6171a014afb07a8252642bbc6b6dad1057a80e1e0391c72e863644167fe26a01
3
+ size 1109860880
runs/Oct12_15-30-16_SRV/events.out.tfevents.1728736235.SRV.3871554.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713c72015409e0f624f7e75abb5b4ab1a2a463fe0396e9ffe13eb97d2066a9d8
3
+ size 5161
runs/Oct12_15-33-05_SRV/events.out.tfevents.1728736386.SRV.3871554.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6409604aff607f72af620c83f8e0b9f86e3ca4f4d00131d7cf485582c7e1721e
3
+ size 6677
runs/Oct12_15-58-25_SRV/events.out.tfevents.1728737919.SRV.3871554.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:204a84b83141399253a07018d7eb9b50b5a6abb350576605e01ce6922580fb8e
3
+ size 9741
runs/Oct14_22-59-18_SRV/events.out.tfevents.1728935959.SRV.3092729.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ee94082b05b37122cafdcdd3be95310d5e20ce7aa5081b3cbd151c21388d49
3
+ size 5479
runs/Oct14_23-03-53_SRV/events.out.tfevents.1728936299.SRV.3092729.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ae376582ee90707270d000b65a44ecfd66eea8d0bcdf91ef0274a8a5fa1242
3
+ size 6677
runs/Oct17_18-39-57_SRV/events.out.tfevents.1729179598.SRV.2230521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b0b17f6a4034b598b564eec1f2542ccb7e681a6a5a357760948b20bac90a41
3
+ size 6677
runs/Oct18_17-53-35_SRV/events.out.tfevents.1729263216.SRV.3730705.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7566a0a22308d358ca0d2e376b4c8bb77132227586d9db9fa66da2f5a31f9a81
3
+ size 6677
runs/Oct18_17-53-35_SRV/events.out.tfevents.1729264094.SRV.3730705.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3d805ddbdde9eae0ea96d6f2e2f09943e9822b3953fa185e96547d2828ed8b
3
+ size 6696
runs/Oct18_18-36-09_SRV/events.out.tfevents.1729265770.SRV.3768434.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826dccbd7773e81235ff56b7fcc99160228e2dbe9c5dd1ceaf43d57ffa2c3595
3
+ size 6677
runs/Oct19_12-48-02_SRV/events.out.tfevents.1729331284.SRV.412824.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a9520a83a724038872505678c1760a89e8e3382a6319ec31c1113b5c44eb87
3
+ size 5161
runs/Oct19_12-48-02_SRV/events.out.tfevents.1729331339.SRV.412824.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48d6c9d341993d2417d8e531888edb064f40131915ed8f722956ae3ed095599
3
+ size 6677
runs/Oct19_12-48-02_SRV/events.out.tfevents.1729333703.SRV.412824.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b625b3b316f40aace501f00498d8171da7cb8a23b5b1cac715de8b8652443731
3
+ size 6696
runs/Oct19_14-58-36_SRV/events.out.tfevents.1729339117.SRV.515691.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15204b3d18c10bbd47c0c816928b6ea9e1ac33bd4b55594385db30c1a356e48c
3
+ size 5161
runs/Oct19_14-58-36_SRV/events.out.tfevents.1729339270.SRV.515691.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da32a9dad12ab22e11d962bd9e2746ce5ba023b36e8b484fb1cfe1920cb79fb1
3
+ size 6677
runs/Oct19_14-58-36_SRV/events.out.tfevents.1729354813.SRV.515691.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2729ad75a43b48047866526caf34f64f3b0d7669f369ccb99288e03f9ddf23e3
3
+ size 6667
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
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 sha256:6dbe8fe490c7e63827220021cb9d883e2069b894fc26857f872444b90b3337f1
3
+ size 5112