Acc0.8370786516853933, F10.8383201201124987 , Augmented with flang-bert.csv, finetuned on SALT-NLP/FLANG-ELECTRA
Browse files- README.md +78 -0
- config.json +41 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: SALT-NLP/FLANG-ELECTRA
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: FLANG-ELECTRA_flang-bert
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# FLANG-ELECTRA_flang-bert
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [SALT-NLP/FLANG-ELECTRA](https://huggingface.co/SALT-NLP/FLANG-ELECTRA) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5930
|
23 |
+
- Accuracy: 0.8705
|
24 |
+
- F1: 0.8717
|
25 |
+
- Precision: 0.8772
|
26 |
+
- Recall: 0.8705
|
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: 0.0001
|
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 |
+
- lr_scheduler_warmup_steps: 1000
|
52 |
+
- num_epochs: 25
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 0.6377 | 1.0 | 181 | 0.5174 | 0.8003 | 0.7860 | 0.8080 | 0.8003 |
|
59 |
+
| 0.4035 | 2.0 | 362 | 0.4221 | 0.8580 | 0.8578 | 0.8611 | 0.8580 |
|
60 |
+
| 0.2395 | 3.0 | 543 | 0.4535 | 0.8580 | 0.8560 | 0.8592 | 0.8580 |
|
61 |
+
| 0.231 | 4.0 | 724 | 0.4335 | 0.8658 | 0.8657 | 0.8659 | 0.8658 |
|
62 |
+
| 0.3369 | 5.0 | 905 | 0.5608 | 0.8081 | 0.8057 | 0.8151 | 0.8081 |
|
63 |
+
| 0.2203 | 6.0 | 1086 | 0.5002 | 0.8705 | 0.8691 | 0.8706 | 0.8705 |
|
64 |
+
| 0.239 | 7.0 | 1267 | 0.6676 | 0.8128 | 0.8125 | 0.8338 | 0.8128 |
|
65 |
+
| 0.0938 | 8.0 | 1448 | 0.5930 | 0.8705 | 0.8717 | 0.8772 | 0.8705 |
|
66 |
+
| 0.1329 | 9.0 | 1629 | 0.5017 | 0.8580 | 0.8571 | 0.8572 | 0.8580 |
|
67 |
+
| 0.3598 | 10.0 | 1810 | 0.5126 | 0.8690 | 0.8675 | 0.8698 | 0.8690 |
|
68 |
+
| 0.1615 | 11.0 | 1991 | 0.5945 | 0.8612 | 0.8605 | 0.8606 | 0.8612 |
|
69 |
+
| 0.0923 | 12.0 | 2172 | 0.8213 | 0.8268 | 0.8292 | 0.8450 | 0.8268 |
|
70 |
+
| 0.1296 | 13.0 | 2353 | 0.8647 | 0.8580 | 0.8586 | 0.8611 | 0.8580 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.37.0
|
76 |
+
- Pytorch 2.1.2
|
77 |
+
- Datasets 2.1.0
|
78 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SALT-NLP/FLANG-ELECTRA",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 1024,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
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": "electra",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"summary_activation": "gelu",
|
33 |
+
"summary_last_dropout": 0.1,
|
34 |
+
"summary_type": "first",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.37.0",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:841546e437fc839cdb91b0b338fa92f0178d5e2589e90bcbc1aab89315074626
|
3 |
+
size 1340628036
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfe6baacc13c4b1a123210880eaf10608591d7c50bfe2753ffa00367a3a05d8
|
3 |
+
size 4664
|