Training in progress, epoch 1
Browse files- README.md +68 -0
- added_tokens.json +6 -0
- config.json +31 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Feb12_09-39-40_93f51a08e000/events.out.tfevents.1707730980.93f51a08e000.1197.0 +3 -0
- runs/Feb12_09-48-09_93f51a08e000/events.out.tfevents.1707731299.93f51a08e000.1197.1 +3 -0
- runs/Feb12_09-52-39_93f51a08e000/events.out.tfevents.1707731565.93f51a08e000.1197.2 +3 -0
- runs/Feb12_09-57-03_93f51a08e000/events.out.tfevents.1707731829.93f51a08e000.1197.3 +3 -0
- runs/Feb12_10-02-09_93f51a08e000/events.out.tfevents.1707732135.93f51a08e000.1197.4 +3 -0
- runs/Feb12_10-06-36_93f51a08e000/events.out.tfevents.1707732411.93f51a08e000.1197.5 +3 -0
- runs/Feb12_10-15-15_93f51a08e000/events.out.tfevents.1707732920.93f51a08e000.1197.6 +3 -0
- runs/Feb12_10-22-18_93f51a08e000/events.out.tfevents.1707733346.93f51a08e000.1197.7 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.json +0 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: finiteautomata/beto-sentiment-analysis
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
model-index:
|
10 |
+
- name: beto-sentiment-analysis-finetuned-detests-wandb24
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# beto-sentiment-analysis-finetuned-detests-wandb24
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [finiteautomata/beto-sentiment-analysis](https://huggingface.co/finiteautomata/beto-sentiment-analysis) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6204
|
22 |
+
- Accuracy: 0.8674
|
23 |
+
- F1-score: 0.7993
|
24 |
+
- Precision: 0.8225
|
25 |
+
- Recall: 0.7822
|
26 |
+
- Auc: 0.7822
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 5e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 4
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|:------:|
|
57 |
+
| 0.393 | 1.0 | 77 | 0.3365 | 0.8592 | 0.7633 | 0.8424 | 0.7287 | 0.7287 |
|
58 |
+
| 0.1947 | 2.0 | 154 | 0.3843 | 0.8396 | 0.7845 | 0.7716 | 0.8023 | 0.8023 |
|
59 |
+
| 0.0597 | 3.0 | 231 | 0.5486 | 0.8740 | 0.8046 | 0.8398 | 0.7814 | 0.7814 |
|
60 |
+
| 0.0028 | 4.0 | 308 | 0.6204 | 0.8674 | 0.7993 | 0.8225 | 0.7822 | 0.7822 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.37.2
|
66 |
+
- Pytorch 2.1.0+cu121
|
67 |
+
- Datasets 2.17.0
|
68 |
+
- Tokenizers 0.15.1
|
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"@usuario": 31002,
|
3 |
+
"emoji": 31005,
|
4 |
+
"hashtag": 31004,
|
5 |
+
"url": 31003
|
6 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/electra-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 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "electra",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"summary_activation": "gelu",
|
23 |
+
"summary_last_dropout": 0.1,
|
24 |
+
"summary_type": "first",
|
25 |
+
"summary_use_proj": true,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.37.2",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef76aa786109cb0e40cbc103c11d3ffcf747d860097f280429ef0c899c5aa975
|
3 |
+
size 437959248
|
runs/Feb12_09-39-40_93f51a08e000/events.out.tfevents.1707730980.93f51a08e000.1197.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29e970fcaa23ba6488b071bda1f199569abf6140cb145bbc03cb1d64fa21d0bc
|
3 |
+
size 7049
|
runs/Feb12_09-48-09_93f51a08e000/events.out.tfevents.1707731299.93f51a08e000.1197.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccb3aa453258cabb6f8fc87ccff9813ae003ee2066763ac5fdb8595d0ba11f74
|
3 |
+
size 7099
|
runs/Feb12_09-52-39_93f51a08e000/events.out.tfevents.1707731565.93f51a08e000.1197.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13b21529e804a993e9128799476e28f9f5b9d862cd1da89cde3d95a066f3e9f0
|
3 |
+
size 7026
|
runs/Feb12_09-57-03_93f51a08e000/events.out.tfevents.1707731829.93f51a08e000.1197.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e94493558f1ef8006fd3dcd25367220f38ba6b4b82e4dca7200d736eb9f01f3
|
3 |
+
size 7099
|
runs/Feb12_10-02-09_93f51a08e000/events.out.tfevents.1707732135.93f51a08e000.1197.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1797a15649ac7456a4cc9448d9d174e1e0cf5900ffdd63f1bd819c33a964e53
|
3 |
+
size 7049
|
runs/Feb12_10-06-36_93f51a08e000/events.out.tfevents.1707732411.93f51a08e000.1197.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cac9fc0cea880fe529e712c64cb99c5c05eb90c4011eebf2e4536e6c1d797c5
|
3 |
+
size 7055
|
runs/Feb12_10-15-15_93f51a08e000/events.out.tfevents.1707732920.93f51a08e000.1197.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48693b769c172d0e251d3667a2897485e2d0a1ccfdfeed657d3f256f4a57b0d0
|
3 |
+
size 12214
|
runs/Feb12_10-22-18_93f51a08e000/events.out.tfevents.1707733346.93f51a08e000.1197.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca1523dd9e923e8d7a18fe5b50c491e08044d540ee8a7ffa9af7e7a96a7240a6
|
3 |
+
size 5635
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "ElectraTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed9885188ff5a4c3cc7b08fe645f361a3cefe93bf2b0c6e436fc575f32f2d142
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|