MarioPenguin
commited on
Commit
•
ad5ce26
1
Parent(s):
181c5d4
add model
Browse files- README.md +58 -0
- config.json +36 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: beto_amazon_final_pnn
|
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_amazon_final_pnn
|
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: 0.5242
|
17 |
+
- Train Accuracy: 0.7838
|
18 |
+
- Validation Loss: 0.6507
|
19 |
+
- Validation Accuracy: 0.7284
|
20 |
+
- Epoch: 4
|
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 |
+
| 0.6129 | 0.7496 | 0.6588 | 0.7248 | 0 |
|
47 |
+
| 0.5850 | 0.7566 | 0.6505 | 0.7258 | 1 |
|
48 |
+
| 0.5604 | 0.7704 | 0.6484 | 0.7278 | 2 |
|
49 |
+
| 0.5407 | 0.7840 | 0.6503 | 0.7250 | 3 |
|
50 |
+
| 0.5242 | 0.7838 | 0.6507 | 0.7284 | 4 |
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.16.2
|
56 |
+
- TensorFlow 2.8.0
|
57 |
+
- Datasets 1.18.3
|
58 |
+
- Tokenizers 0.11.6
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
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 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"output_past": true,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"transformers_version": "4.16.2",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 31002
|
36 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40424c1b6ed967ad4f8454a2aa842d1a69beeca6e60f53d187a451b97d814537
|
3 |
+
size 439700828
|