Acc0.9188514357053683, F10.9185477500192393 , Augmented with Synonym-wordnet.csv, finetuned on google/electra-base-discriminator
Browse files- README.md +75 -0
- config.json +41 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/electra-base-discriminator
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: electra-base-discriminator_Synonym-wordnet
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# electra-base-discriminator_Synonym-wordnet
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2211
|
24 |
+
- Accuracy: 0.9267
|
25 |
+
- F1: 0.9267
|
26 |
+
- Precision: 0.9267
|
27 |
+
- Recall: 0.9267
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0001
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 1000
|
53 |
+
- num_epochs: 25
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| 0.932 | 1.0 | 91 | 0.8735 | 0.6412 | 0.5915 | 0.6417 | 0.6412 |
|
60 |
+
| 0.426 | 2.0 | 182 | 0.3389 | 0.9002 | 0.9004 | 0.9008 | 0.9002 |
|
61 |
+
| 0.259 | 3.0 | 273 | 0.2577 | 0.9048 | 0.9039 | 0.9070 | 0.9048 |
|
62 |
+
| 0.1619 | 4.0 | 364 | 0.2211 | 0.9267 | 0.9267 | 0.9267 | 0.9267 |
|
63 |
+
| 0.1574 | 5.0 | 455 | 0.3301 | 0.8955 | 0.8959 | 0.9045 | 0.8955 |
|
64 |
+
| 0.0929 | 6.0 | 546 | 0.3284 | 0.9064 | 0.9054 | 0.9066 | 0.9064 |
|
65 |
+
| 0.1079 | 7.0 | 637 | 0.3467 | 0.9002 | 0.9003 | 0.9040 | 0.9002 |
|
66 |
+
| 0.0927 | 8.0 | 728 | 0.3817 | 0.9002 | 0.8993 | 0.9056 | 0.9002 |
|
67 |
+
| 0.0876 | 9.0 | 819 | 0.3524 | 0.9048 | 0.9044 | 0.9047 | 0.9048 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.37.0
|
73 |
+
- Pytorch 2.1.2
|
74 |
+
- Datasets 2.1.0
|
75 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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": "electra",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
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 sha256:292b4ccce7ce486667b24723890370f47bd886ba064c8bd53db949f075556900
|
3 |
+
size 437962324
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33c812a66a6b2fdfaeb934cce0ddbd0a1292136fcf0d4caa9360ff1ecb08298a
|
3 |
+
size 4664
|