update model card README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,80 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Bert_Test
|
| 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 |
+
# Bert_Test
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1965
|
| 22 |
+
- Precision: 0.9332
|
| 23 |
+
- Accuracy: 0.9223
|
| 24 |
+
- F1: 0.9223
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-05
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 7
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Accuracy | F1 |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:--------:|:------:|
|
| 56 |
+
| 0.6717 | 0.4 | 500 | 0.6049 | 0.7711 | 0.6743 | 0.6112 |
|
| 57 |
+
| 0.5704 | 0.8 | 1000 | 0.5299 | 0.7664 | 0.7187 | 0.6964 |
|
| 58 |
+
| 0.52 | 1.2 | 1500 | 0.4866 | 0.7698 | 0.7537 | 0.7503 |
|
| 59 |
+
| 0.4792 | 1.6 | 2000 | 0.4292 | 0.8031 | 0.793 | 0.7927 |
|
| 60 |
+
| 0.4332 | 2.0 | 2500 | 0.3920 | 0.8318 | 0.8203 | 0.8198 |
|
| 61 |
+
| 0.381 | 2.4 | 3000 | 0.3723 | 0.9023 | 0.8267 | 0.8113 |
|
| 62 |
+
| 0.3625 | 2.8 | 3500 | 0.3134 | 0.8736 | 0.8607 | 0.8601 |
|
| 63 |
+
| 0.3325 | 3.2 | 4000 | 0.2924 | 0.8973 | 0.871 | 0.8683 |
|
| 64 |
+
| 0.3069 | 3.6 | 4500 | 0.2671 | 0.8916 | 0.8847 | 0.8851 |
|
| 65 |
+
| 0.2866 | 4.0 | 5000 | 0.2571 | 0.8920 | 0.8913 | 0.8926 |
|
| 66 |
+
| 0.2595 | 4.4 | 5500 | 0.2450 | 0.8980 | 0.9 | 0.9015 |
|
| 67 |
+
| 0.2567 | 4.8 | 6000 | 0.2246 | 0.9057 | 0.9043 | 0.9054 |
|
| 68 |
+
| 0.2255 | 5.2 | 6500 | 0.2263 | 0.9332 | 0.905 | 0.9030 |
|
| 69 |
+
| 0.2237 | 5.6 | 7000 | 0.2083 | 0.9265 | 0.9157 | 0.9156 |
|
| 70 |
+
| 0.2248 | 6.0 | 7500 | 0.2039 | 0.9387 | 0.9193 | 0.9185 |
|
| 71 |
+
| 0.2086 | 6.4 | 8000 | 0.2038 | 0.9436 | 0.9193 | 0.9181 |
|
| 72 |
+
| 0.2029 | 6.8 | 8500 | 0.1965 | 0.9332 | 0.9223 | 0.9223 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.18.0
|
| 78 |
+
- Pytorch 1.10.0+cu111
|
| 79 |
+
- Datasets 2.0.0
|
| 80 |
+
- Tokenizers 0.11.6
|