Model save
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: beomi/KcELECTRA-base-v2022
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: KcELECTRA-base-v2022-KEmoFact-EFE-0927
|
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 |
+
# KcELECTRA-base-v2022-KEmoFact-EFE-0927
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [beomi/KcELECTRA-base-v2022](https://huggingface.co/beomi/KcELECTRA-base-v2022) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5879
|
23 |
+
- Precision: 0.4052
|
24 |
+
- Recall: 0.4497
|
25 |
+
- F1: 0.4263
|
26 |
+
- Ov Accuracy: 0.8253
|
27 |
+
- Jaccard: 0.7374
|
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: 5e-05
|
47 |
+
- train_batch_size: 32
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Ov Accuracy | Jaccard |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:-----------:|:-------:|
|
58 |
+
| No log | 1.0 | 414 | 0.4141 | 0.3382 | 0.3897 | 0.3622 | 0.8209 | 0.6966 |
|
59 |
+
| 0.4519 | 2.0 | 828 | 0.4230 | 0.3456 | 0.3988 | 0.3703 | 0.8211 | 0.7086 |
|
60 |
+
| 0.302 | 3.0 | 1242 | 0.4758 | 0.3660 | 0.4208 | 0.3915 | 0.8204 | 0.7164 |
|
61 |
+
| 0.2037 | 4.0 | 1656 | 0.5589 | 0.3649 | 0.4083 | 0.3854 | 0.8193 | 0.7084 |
|
62 |
+
| 0.1394 | 5.0 | 2070 | 0.6199 | 0.3533 | 0.4089 | 0.3791 | 0.8148 | 0.7064 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.33.2
|
68 |
+
- Pytorch 2.0.1+cu118
|
69 |
+
- Datasets 2.14.5
|
70 |
+
- Tokenizers 0.13.3
|