Commit
·
d09adb5
1
Parent(s):
dd41cd2
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: pysentimiento/robertuito-base-uncased
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Robertuito-check-worthy-classifier
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# checkworty_es_classifier
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [pysentimiento/robertuito-base-uncased](https://huggingface.co/pysentimiento/robertuito-base-uncased) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2029
|
| 20 |
+
- F1 Class 0: 0.9557
|
| 21 |
+
- F1 Class 1: 0.6936
|
| 22 |
+
- F1: 0.8246
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0005
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- lr_scheduler_warmup_steps: 200
|
| 49 |
+
- training_steps: 2000
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Class 0 | F1 Class 1 | F1 |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------:|:----------:|:------:|
|
| 55 |
+
| 0.4326 | 0.16 | 200 | 0.3187 | 0.9412 | 0.6514 | 0.7963 |
|
| 56 |
+
| 0.3765 | 0.32 | 400 | 0.2572 | 0.9323 | 0.6736 | 0.8030 |
|
| 57 |
+
| 0.3523 | 0.48 | 600 | 0.2079 | 0.9527 | 0.6990 | 0.8259 |
|
| 58 |
+
| 0.3594 | 0.64 | 800 | 0.2184 | 0.9505 | 0.5761 | 0.7633 |
|
| 59 |
+
| 0.3307 | 0.8 | 1000 | 0.2109 | 0.9497 | 0.6892 | 0.8194 |
|
| 60 |
+
| 0.3166 | 0.96 | 1200 | 0.2187 | 0.9537 | 0.6288 | 0.7912 |
|
| 61 |
+
| 0.297 | 1.13 | 1400 | 0.2541 | 0.9524 | 0.6429 | 0.7976 |
|
| 62 |
+
| 0.2766 | 1.29 | 1600 | 0.2031 | 0.9561 | 0.7173 | 0.8367 |
|
| 63 |
+
| 0.2628 | 1.45 | 1800 | 0.2076 | 0.9516 | 0.7200 | 0.8358 |
|
| 64 |
+
| 0.2313 | 1.61 | 2000 | 0.2029 | 0.9557 | 0.6936 | 0.8246 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.35.1
|
| 70 |
+
- Pytorch 2.1.0+cu118
|
| 71 |
+
- Datasets 2.14.7
|
| 72 |
+
- Tokenizers 0.14.1
|