update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: electra-base-discriminator-ner-food-combined-v2
|
| 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 |
+
# electra-base-discriminator-ner-food-combined-v2
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1277
|
| 23 |
+
- Precision: 0.8006
|
| 24 |
+
- Recall: 0.8959
|
| 25 |
+
- F1: 0.8456
|
| 26 |
+
- Accuracy: 0.9685
|
| 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: 5e-06
|
| 46 |
+
- train_batch_size: 8
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 7
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| No log | 0.45 | 400 | 0.1279 | 0.7429 | 0.8888 | 0.8093 | 0.9603 |
|
| 58 |
+
| 0.2005 | 0.9 | 800 | 0.1306 | 0.8145 | 0.8901 | 0.8506 | 0.9704 |
|
| 59 |
+
| 0.1305 | 1.35 | 1200 | 0.1197 | 0.7847 | 0.8951 | 0.8363 | 0.9667 |
|
| 60 |
+
| 0.1143 | 1.8 | 1600 | 0.1118 | 0.7876 | 0.8922 | 0.8366 | 0.9661 |
|
| 61 |
+
| 0.1169 | 2.25 | 2000 | 0.1125 | 0.7724 | 0.8959 | 0.8296 | 0.9647 |
|
| 62 |
+
| 0.1169 | 2.7 | 2400 | 0.1167 | 0.7964 | 0.8922 | 0.8415 | 0.9674 |
|
| 63 |
+
| 0.1007 | 3.15 | 2800 | 0.1222 | 0.8170 | 0.8905 | 0.8522 | 0.9708 |
|
| 64 |
+
| 0.1008 | 3.6 | 3200 | 0.1164 | 0.7732 | 0.8913 | 0.8281 | 0.9640 |
|
| 65 |
+
| 0.0973 | 4.04 | 3600 | 0.1190 | 0.8093 | 0.8993 | 0.8519 | 0.9697 |
|
| 66 |
+
| 0.0948 | 4.49 | 4000 | 0.1221 | 0.7977 | 0.8947 | 0.8434 | 0.9676 |
|
| 67 |
+
| 0.0948 | 4.94 | 4400 | 0.1220 | 0.8009 | 0.8993 | 0.8472 | 0.9684 |
|
| 68 |
+
| 0.0857 | 5.39 | 4800 | 0.1292 | 0.8085 | 0.8963 | 0.8501 | 0.9694 |
|
| 69 |
+
| 0.0845 | 5.84 | 5200 | 0.1318 | 0.8236 | 0.8943 | 0.8575 | 0.9710 |
|
| 70 |
+
| 0.0877 | 6.29 | 5600 | 0.1246 | 0.7940 | 0.8972 | 0.8425 | 0.9674 |
|
| 71 |
+
| 0.0825 | 6.74 | 6000 | 0.1277 | 0.8006 | 0.8959 | 0.8456 | 0.9685 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.27.4
|
| 77 |
+
- Pytorch 2.0.0+cu118
|
| 78 |
+
- Datasets 2.11.0
|
| 79 |
+
- Tokenizers 0.13.3
|