Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: answerdotai/ModernBERT-base
|
| 4 |
+
model-index:
|
| 5 |
+
- name: ECBERT-base
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# ECBERT-base-mlm
|
| 13 |
+
|
| 14 |
+
This model is a pretrained version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on 25,581 texts (available [here](https://huggingface.co/datasets/Graimond/ECBERT-mlm-dataset)) using MLM but not yet fine-tuned on the monetary policy sentiment analysis task.
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
[Graimond/ECBERT-mlm-dataset](https://huggingface.co/datasets/Graimond/ECBERT-mlm-dataset)
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 5e-5
|
| 34 |
+
- weight_decay=0.01
|
| 35 |
+
- per_device_train_batch_size=16
|
| 36 |
+
- seed: 42
|
| 37 |
+
- epochs: 20
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
| Epoch | Training Loss | Validation Loss |
|
| 42 |
+
|-------|---------------|-----------------|
|
| 43 |
+
| 1 | 1.905000 | 1.903329 |
|
| 44 |
+
| 2 | 1.689700 | 1.764568 |
|
| 45 |
+
| 3 | 1.600900 | nan |
|
| 46 |
+
| 4 | 1.476500 | 1.683352 |
|
| 47 |
+
| 5 | 1.381200 | 1.629597 |
|
| 48 |
+
| 6 | 1.367300 | nan |
|
| 49 |
+
| 7 | 1.230300 | 1.628195 |
|
| 50 |
+
| 8 | 1.142700 | 1.567721 |
|
| 51 |
+
| 9 | 1.131800 | 1.618517 |
|
| 52 |
+
| 10 | 1.139700 | nan |
|
| 53 |
+
| 11 | 1.086200 | nan |
|
| 54 |
+
| 12 | 1.072500 | 1.560426 |
|
| 55 |
+
| 13 | 0.984800 | 1.556072 |
|
| 56 |
+
| 14 | 0.958500 | 1.606674 |
|
| 57 |
+
| 15 | 0.955600 | 1.619744 |
|
| 58 |
+
| 16 | 0.920500 | 1.581421 |
|
| 59 |
+
| 17 | 0.882300 | 1.535872 |
|
| 60 |
+
| 18 | 0.877900 | 1.565936 |
|
| 61 |
+
| 19 | 0.803100 | nan |
|
| 62 |
+
| 20 | 0.815700 | 1.604986 |
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.48.0.dev0
|
| 67 |
+
- Pytorch 2.5.1+cu121
|
| 68 |
+
- Datasets 3.2.0
|
| 69 |
+
- Tokenizers 0.21.0
|