JonatanGk commited on
Commit
fb96c2c
1 Parent(s): 7ac75c7
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - null
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: roberta-base-bne-finetuned-mnli
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ metrics:
16
+ - name: Accuracy
17
+ type: accuracy
18
+ value: 0.9607097303206997
19
+ ---
20
+
21
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
22
+ should probably proofread and complete it, then remove this comment. -->
23
+
24
+ # roberta-base-bne-finetuned-mnli
25
+
26
+ This model is a fine-tuned version of [BSC-TeMU/roberta-base-bne](https://huggingface.co/BSC-TeMU/roberta-base-bne) on the None dataset.
27
+ It achieves the following results on the evaluation set:
28
+ - Loss: 0.1657
29
+ - Accuracy: 0.9607
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 2e-05
49
+ - train_batch_size: 16
50
+ - eval_batch_size: 16
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 4
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
59
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
60
+ | 0.1512 | 1.0 | 22227 | 0.9501 | 0.1418 |
61
+ | 0.1253 | 2.0 | 44454 | 0.9567 | 0.1499 |
62
+ | 0.0973 | 3.0 | 66681 | 0.9594 | 0.1397 |
63
+ | 0.0658 | 4.0 | 88908 | 0.9607 | 0.1657 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.10.3
69
+ - Pytorch 1.9.0+cu102
70
+ - Datasets 1.12.1
71
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BSC-TeMU/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.3",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ff1eb6bd05659545bbca0f00b8c53f61a07e78e9af4c94b259f4f843bd0055
3
+ size 498664877
runs/Sep27_09-17-01_7e65ed583a12/1632734296.2019641/events.out.tfevents.1632734296.7e65ed583a12.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620f7035700267f0598db8008c9779ffe0ca3b1febbf64f763997301931718e9
3
+ size 4217
runs/Sep27_09-17-01_7e65ed583a12/events.out.tfevents.1632734296.7e65ed583a12.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9e14e6c725ad97140a62b157861f82abf99ccd3ace537636a3a04b37c2d06a
3
+ size 3394
runs/Sep27_09-17-01_7e65ed583a12/events.out.tfevents.1632734885.7e65ed583a12.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c2dddd17e60636b46279175dfec290b2d9ef2d15ea4ef9e5ee48f305baf257
3
+ size 369
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "BSC-TeMU/roberta-base-bne", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53c3507b589b62c95cfb31a6944c5ec82ea454cbb1b90edbb710a090fb94269
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff