add model
Browse files- .gitignore +1 -0
- README.md +72 -0
- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Aug22_18-42-34_13ee57411a2d/1629657761.5489256/events.out.tfevents.1629657761.13ee57411a2d.79.3 +3 -0
- runs/Aug22_18-42-34_13ee57411a2d/events.out.tfevents.1629657761.13ee57411a2d.79.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- amazon_reviews_multi
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model_index:
|
9 |
+
- name: roberta-base-bne-finetuned-amazon_reviews_multi-finetuned-amazon_reviews_multi
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
dataset:
|
15 |
+
name: amazon_reviews_multi
|
16 |
+
type: amazon_reviews_multi
|
17 |
+
args: es
|
18 |
+
metric:
|
19 |
+
name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.9285
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# roberta-base-bne-finetuned-amazon_reviews_multi-finetuned-amazon_reviews_multi
|
28 |
+
|
29 |
+
This model was trained from scratch on the amazon_reviews_multi dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 0.3595
|
32 |
+
- Accuracy: 0.9285
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 2e-05
|
52 |
+
- train_batch_size: 16
|
53 |
+
- eval_batch_size: 16
|
54 |
+
- seed: 42
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 2
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
62 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
63 |
+
| 0.103 | 1.0 | 1250 | 0.2864 | 0.928 |
|
64 |
+
| 0.0407 | 2.0 | 2500 | 0.3595 | 0.9285 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.9.2
|
70 |
+
- Pytorch 1.9.0+cu102
|
71 |
+
- Datasets 1.11.0
|
72 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lewtun/roberta-base-bne-finetuned-amazon_reviews_multi",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "NEGATIVO",
|
15 |
+
"1": "POSITIVO"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"NEGATIVO": 0,
|
21 |
+
"POSITIVO": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 514,
|
25 |
+
"model_type": "roberta",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.9.2",
|
33 |
+
"type_vocab_size": 1,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50262
|
36 |
+
}
|
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 sha256:5ca4f70c6220dc965be5bfe0ab41275fc267022391dae3966cd9eceb04d6684c
|
3 |
+
size 498664877
|
runs/Aug22_18-42-34_13ee57411a2d/1629657761.5489256/events.out.tfevents.1629657761.13ee57411a2d.79.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb597f3e30b18a9d0a36c2bff76d4fa804365e1097a728448eb587f6ebc2ed8f
|
3 |
+
size 4249
|
runs/Aug22_18-42-34_13ee57411a2d/events.out.tfevents.1629657761.13ee57411a2d.79.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:035494b900e2e98145b372c81aa8eb918c85cff616d55699c110c3eb7af692e3
|
3 |
+
size 5529
|
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 sha256:3175e7aeb9295893d6c80f14834ee4f12f91f315f0c2ad54cc6902cfce807d9d
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|