update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: distilbert-cord-ner
|
| 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 |
+
# distilbert-cord-ner
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [Geotrend/distilbert-base-en-fr-de-no-da-cased](https://huggingface.co/Geotrend/distilbert-base-en-fr-de-no-da-cased) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1670
|
| 23 |
+
- Precision: 0.9128
|
| 24 |
+
- Recall: 0.9242
|
| 25 |
+
- F1: 0.9185
|
| 26 |
+
- Accuracy: 0.9656
|
| 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-05
|
| 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: 10
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| No log | 1.0 | 113 | 0.1814 | 0.8480 | 0.8618 | 0.8548 | 0.9393 |
|
| 58 |
+
| No log | 2.0 | 226 | 0.1755 | 0.8669 | 0.9002 | 0.8832 | 0.9427 |
|
| 59 |
+
| No log | 3.0 | 339 | 0.1499 | 0.8800 | 0.8935 | 0.8867 | 0.9533 |
|
| 60 |
+
| No log | 4.0 | 452 | 0.1340 | 0.8975 | 0.9079 | 0.9027 | 0.9596 |
|
| 61 |
+
| 0.1812 | 5.0 | 565 | 0.1553 | 0.8999 | 0.9146 | 0.9072 | 0.9592 |
|
| 62 |
+
| 0.1812 | 6.0 | 678 | 0.1474 | 0.8961 | 0.9021 | 0.8991 | 0.9562 |
|
| 63 |
+
| 0.1812 | 7.0 | 791 | 0.1682 | 0.9135 | 0.9223 | 0.9179 | 0.9622 |
|
| 64 |
+
| 0.1812 | 8.0 | 904 | 0.1663 | 0.8960 | 0.9175 | 0.9066 | 0.9613 |
|
| 65 |
+
| 0.0199 | 9.0 | 1017 | 0.1753 | 0.9061 | 0.9261 | 0.9160 | 0.9635 |
|
| 66 |
+
| 0.0199 | 10.0 | 1130 | 0.1670 | 0.9128 | 0.9242 | 0.9185 | 0.9656 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.18.0
|
| 72 |
+
- Pytorch 1.11.0
|
| 73 |
+
- Datasets 2.1.0
|
| 74 |
+
- Tokenizers 0.12.1
|