Commit
•
5dab43f
1
Parent(s):
dbf5b6a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: bert-finetuned-ner
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# bert-finetuned-ner
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 6.1090
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 30
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 70 | 8.6531 |
|
| 49 |
+
| No log | 2.0 | 140 | 8.3935 |
|
| 50 |
+
| No log | 3.0 | 210 | 8.2279 |
|
| 51 |
+
| No log | 4.0 | 280 | 8.0728 |
|
| 52 |
+
| No log | 5.0 | 350 | 7.9139 |
|
| 53 |
+
| No log | 6.0 | 420 | 7.7655 |
|
| 54 |
+
| No log | 7.0 | 490 | 7.6321 |
|
| 55 |
+
| 8.2602 | 8.0 | 560 | 7.4960 |
|
| 56 |
+
| 8.2602 | 9.0 | 630 | 7.3789 |
|
| 57 |
+
| 8.2602 | 10.0 | 700 | 7.2505 |
|
| 58 |
+
| 8.2602 | 11.0 | 770 | 7.1390 |
|
| 59 |
+
| 8.2602 | 12.0 | 840 | 7.0327 |
|
| 60 |
+
| 8.2602 | 13.0 | 910 | 6.9259 |
|
| 61 |
+
| 8.2602 | 14.0 | 980 | 6.8442 |
|
| 62 |
+
| 7.4097 | 15.0 | 1050 | 6.7584 |
|
| 63 |
+
| 7.4097 | 16.0 | 1120 | 6.6727 |
|
| 64 |
+
| 7.4097 | 17.0 | 1190 | 6.5904 |
|
| 65 |
+
| 7.4097 | 18.0 | 1260 | 6.5285 |
|
| 66 |
+
| 7.4097 | 19.0 | 1330 | 6.4555 |
|
| 67 |
+
| 7.4097 | 20.0 | 1400 | 6.4051 |
|
| 68 |
+
| 7.4097 | 21.0 | 1470 | 6.3435 |
|
| 69 |
+
| 6.82 | 22.0 | 1540 | 6.2980 |
|
| 70 |
+
| 6.82 | 23.0 | 1610 | 6.2529 |
|
| 71 |
+
| 6.82 | 24.0 | 1680 | 6.2188 |
|
| 72 |
+
| 6.82 | 25.0 | 1750 | 6.1833 |
|
| 73 |
+
| 6.82 | 26.0 | 1820 | 6.1628 |
|
| 74 |
+
| 6.82 | 27.0 | 1890 | 6.1386 |
|
| 75 |
+
| 6.82 | 28.0 | 1960 | 6.1211 |
|
| 76 |
+
| 6.4746 | 29.0 | 2030 | 6.1138 |
|
| 77 |
+
| 6.4746 | 30.0 | 2100 | 6.1090 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.26.1
|
| 83 |
+
- Pytorch 1.13.1+cu116
|
| 84 |
+
- Datasets 2.10.1
|
| 85 |
+
- Tokenizers 0.13.2
|