metadata
license: apache-2.0
base_model: IDEA-CCNL/Erlangshen-Longformer-110M
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSEC-f1-vv1
results: []
Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSEC-f1-vv1
This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8567
- F1: 0.5217
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 34 | 0.7194 | 0.5652 |
| No log | 2.0 | 68 | 0.6541 | 0.0 |
| No log | 3.0 | 102 | 0.6205 | 0.1429 |
| No log | 4.0 | 136 | 0.5815 | 0.4211 |
| No log | 5.0 | 170 | 0.8307 | 0.1429 |
| No log | 6.0 | 204 | 0.6281 | 0.7333 |
| No log | 7.0 | 238 | 1.0374 | 0.2667 |
| No log | 8.0 | 272 | 0.7771 | 0.4762 |
| No log | 9.0 | 306 | 0.8541 | 0.4444 |
| No log | 10.0 | 340 | 0.8567 | 0.5217 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1