MarioPenguin
commited on
Commit
•
fa38d0c
1
Parent(s):
5ec2538
add model
Browse files- README.md +68 -0
- config.json +40 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: beto_stars
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# beto_stars
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.8954
|
17 |
+
- Train Accuracy: 0.6248
|
18 |
+
- Validation Loss: 1.1278
|
19 |
+
- Validation Accuracy: 0.5148
|
20 |
+
- Epoch: 14
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 5e-07, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
40 |
+
- training_precision: float32
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
45 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
46 |
+
| 1.5935 | 0.2626 | 1.5553 | 0.3482 | 0 |
|
47 |
+
| 1.5072 | 0.3782 | 1.4289 | 0.4188 | 1 |
|
48 |
+
| 1.3590 | 0.4312 | 1.2929 | 0.4406 | 2 |
|
49 |
+
| 1.2463 | 0.4628 | 1.2197 | 0.4682 | 3 |
|
50 |
+
| 1.1754 | 0.4970 | 1.1785 | 0.4830 | 4 |
|
51 |
+
| 1.1299 | 0.5114 | 1.1533 | 0.4908 | 5 |
|
52 |
+
| 1.0847 | 0.5362 | 1.1398 | 0.5006 | 6 |
|
53 |
+
| 1.0492 | 0.5440 | 1.1273 | 0.5046 | 7 |
|
54 |
+
| 1.0278 | 0.5592 | 1.1237 | 0.5034 | 8 |
|
55 |
+
| 1.0031 | 0.5690 | 1.1171 | 0.5118 | 9 |
|
56 |
+
| 0.9798 | 0.5712 | 1.1163 | 0.5120 | 10 |
|
57 |
+
| 0.9598 | 0.5894 | 1.1180 | 0.5114 | 11 |
|
58 |
+
| 0.9406 | 0.5964 | 1.1219 | 0.5122 | 12 |
|
59 |
+
| 0.9178 | 0.6104 | 1.1269 | 0.5150 | 13 |
|
60 |
+
| 0.8954 | 0.6248 | 1.1278 | 0.5148 | 14 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.17.0
|
66 |
+
- TensorFlow 2.8.0
|
67 |
+
- Datasets 1.18.4
|
68 |
+
- Tokenizers 0.11.6
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.5,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.5,
|
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 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"output_past": true,
|
34 |
+
"pad_token_id": 1,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"transformers_version": "4.17.0",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 31002
|
40 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbb6532949b96a8da8ba103bd2e8cfaf9951fb2e79261eacb41cf53d0ac7f693
|
3 |
+
size 439706980
|