update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gbert-large-finetuned-cust18
|
| 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 |
+
# gbert-large-finetuned-cust18
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1232
|
| 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: 32
|
| 38 |
+
- eval_batch_size: 32
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 0.604 | 1.0 | 391 | 0.3560 |
|
| 50 |
+
| 0.3497 | 2.0 | 782 | 0.2838 |
|
| 51 |
+
| 0.2812 | 3.0 | 1173 | 0.2484 |
|
| 52 |
+
| 0.2452 | 4.0 | 1564 | 0.2232 |
|
| 53 |
+
| 0.2253 | 5.0 | 1955 | 0.2240 |
|
| 54 |
+
| 0.2202 | 6.0 | 2346 | 0.1993 |
|
| 55 |
+
| 0.1922 | 7.0 | 2737 | 0.1747 |
|
| 56 |
+
| 0.182 | 8.0 | 3128 | 0.1631 |
|
| 57 |
+
| 0.1609 | 9.0 | 3519 | 0.1555 |
|
| 58 |
+
| 0.1553 | 10.0 | 3910 | 0.1434 |
|
| 59 |
+
| 0.147 | 11.0 | 4301 | 0.1399 |
|
| 60 |
+
| 0.144 | 12.0 | 4692 | 0.1340 |
|
| 61 |
+
| 0.1307 | 13.0 | 5083 | 0.1319 |
|
| 62 |
+
| 0.128 | 14.0 | 5474 | 0.1490 |
|
| 63 |
+
| 0.1304 | 15.0 | 5865 | 0.1338 |
|
| 64 |
+
| 0.1165 | 16.0 | 6256 | 0.1233 |
|
| 65 |
+
| 0.1456 | 17.0 | 6647 | 0.1673 |
|
| 66 |
+
| 0.1419 | 18.0 | 7038 | 0.1591 |
|
| 67 |
+
| 0.1447 | 19.0 | 7429 | 0.1360 |
|
| 68 |
+
| 0.1317 | 20.0 | 7820 | 0.1232 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.28.1
|
| 74 |
+
- Pytorch 2.0.0+cu118
|
| 75 |
+
- Datasets 2.11.0
|
| 76 |
+
- Tokenizers 0.13.3
|