arazquin commited on
Commit
c72d8c7
·
1 Parent(s): e6b48f9

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mrm8488/electricidad-base-discriminator
3
+ tags:
4
+ - classification
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: identificador-lenguaje
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
+ # identificador-lenguaje
15
+
16
+ This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 3.0
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.33.3
46
+ - Pytorch 2.0.1+cu118
47
+ - Datasets 2.14.5
48
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mrm8488/electricidad-base-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "electra",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "summary_activation": "gelu",
66
+ "summary_last_dropout": 0.1,
67
+ "summary_type": "first",
68
+ "summary_use_proj": true,
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.33.3",
71
+ "type_vocab_size": 2,
72
+ "use_cache": true,
73
+ "vocab_size": 31002
74
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e24208f439bf6a9ecbad136c468fae864a869f6ff3fd156068d71b70dcbc9f
3
+ size 439534001
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "ElectraTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6b36b0be0c314442ae92fa4946b619c5c1fbc3af090cc183c6de3de15afa0e
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff