adriansanz
commited on
Commit
•
44b9405
1
Parent(s):
ec19b79
fm-tc-hybridXML-MULTILINGUAL-spain-cat-end-10ep
Browse files- .gitattributes +1 -0
- README.md +75 -0
- config.json +51 -0
- model.safetensors +3 -0
- runs/Jun12_09-00-26_3c858a0c66c5/events.out.tfevents.1718182827.3c858a0c66c5.1055.0 +3 -0
- runs/Jun12_09-00-26_3c858a0c66c5/events.out.tfevents.1718184471.3c858a0c66c5.1055.1 +3 -0
- runs/Jun12_09-31-54_3c858a0c66c5/events.out.tfevents.1718184715.3c858a0c66c5.1055.2 +3 -0
- runs/Jun12_09-31-54_3c858a0c66c5/events.out.tfevents.1718188010.3c858a0c66c5.1055.3 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
- 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 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: FacebookAI/xlm-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: fm-tc-end_mix_xml
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# fm-tc-end_mix_xml
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2061
|
24 |
+
- Accuracy: 0.97
|
25 |
+
- Precision: 0.9706
|
26 |
+
- Recall: 0.9700
|
27 |
+
- F1: 0.9700
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| 0.6642 | 1.0 | 1188 | 0.4540 | 0.894 | 0.8983 | 0.8940 | 0.8938 |
|
59 |
+
| 0.4074 | 2.0 | 2376 | 0.4206 | 0.918 | 0.9241 | 0.9180 | 0.9183 |
|
60 |
+
| 0.2403 | 3.0 | 3564 | 0.4380 | 0.918 | 0.9221 | 0.9180 | 0.9165 |
|
61 |
+
| 0.1625 | 4.0 | 4752 | 0.4773 | 0.926 | 0.9297 | 0.9260 | 0.9262 |
|
62 |
+
| 0.0991 | 5.0 | 5940 | 0.2999 | 0.952 | 0.9536 | 0.9520 | 0.9521 |
|
63 |
+
| 0.0549 | 6.0 | 7128 | 0.2217 | 0.966 | 0.9671 | 0.966 | 0.9659 |
|
64 |
+
| 0.0226 | 7.0 | 8316 | 0.2770 | 0.964 | 0.9650 | 0.9640 | 0.9637 |
|
65 |
+
| 0.0154 | 8.0 | 9504 | 0.2061 | 0.97 | 0.9706 | 0.9700 | 0.9700 |
|
66 |
+
| 0.0061 | 9.0 | 10692 | 0.2372 | 0.97 | 0.9706 | 0.9700 | 0.9699 |
|
67 |
+
| 0.0048 | 10.0 | 11880 | 0.2419 | 0.964 | 0.9650 | 0.9640 | 0.9640 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.41.2
|
73 |
+
- Pytorch 2.3.0+cu121
|
74 |
+
- Datasets 2.19.2
|
75 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": "Aig\u00fces",
|
15 |
+
"1": "Consum, comer\u00e7 i mercats",
|
16 |
+
"2": "Cultura",
|
17 |
+
"3": "Economia",
|
18 |
+
"4": "Educaci\u00f3",
|
19 |
+
"5": "Enllumenat p\u00fablic",
|
20 |
+
"6": "Esports",
|
21 |
+
"7": "Habitatge",
|
22 |
+
"8": "Horta",
|
23 |
+
"9": "Informaci\u00f3 general",
|
24 |
+
"10": "Inform\u00e0tica",
|
25 |
+
"11": "Joventut",
|
26 |
+
"12": "Medi ambient",
|
27 |
+
"13": "Neteja de la via p\u00fablica",
|
28 |
+
"14": "Salut p\u00fablica i Cementiri",
|
29 |
+
"15": "Seguretat",
|
30 |
+
"16": "Serveis socials",
|
31 |
+
"17": "Tramitacions",
|
32 |
+
"18": "Urbanisme",
|
33 |
+
"19": "Via p\u00fablica i mobilitat"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "xlm-roberta",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"problem_type": "single_label_classification",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.41.2",
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 250002
|
51 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c3d57964286f3110ffce6f1d7729d0ecf7f19645924e2c2c7eefbe34897f1df
|
3 |
+
size 1112260376
|
runs/Jun12_09-00-26_3c858a0c66c5/events.out.tfevents.1718182827.3c858a0c66c5.1055.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:675a55a2ce68260ed459062d6a2c7438592b675b35c6eb26311e7d6a056e798c
|
3 |
+
size 10479
|
runs/Jun12_09-00-26_3c858a0c66c5/events.out.tfevents.1718184471.3c858a0c66c5.1055.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:678df1161c5c9096582c8f6b148ae77807e8fc967f69f2cd44f8fc187f136138
|
3 |
+
size 560
|
runs/Jun12_09-31-54_3c858a0c66c5/events.out.tfevents.1718184715.3c858a0c66c5.1055.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf04ef51deb80884cd011e2499729b22146e25d733d51fa1c2d9947aa6d17ef3
|
3 |
+
size 15372
|
runs/Jun12_09-31-54_3c858a0c66c5/events.out.tfevents.1718188010.3c858a0c66c5.1055.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a36f1eaf887030f93532dfc9ac63d19e64af5ad557440375f72a0b3c74ce304f
|
3 |
+
size 1032
|
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:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
|
3 |
+
size 17082987
|
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:dca8bc091248388b9d3ca403befd3d4a93474f31b8ee5cac17f36dda9cf8c74b
|
3 |
+
size 5112
|