metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: hubert-base-cc-finance-filter
results: []
hubert-base-cc-finance-filter
This model is a fine-tuned version of papsebestyen/hubert-base-cc-finetuned-forum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5388
- F1: 0.7671
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: 3.887995089067299e-05
- train_batch_size: 60
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 160.18013334673049
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.5717 | 1.0 | 54 | 0.6918 | 0.624 |
| 0.4104 | 2.0 | 108 | 0.4236 | 0.7119 |
| 0.3124 | 3.0 | 162 | 0.6001 | 0.7451 |
| 0.1404 | 4.0 | 216 | 0.5388 | 0.7671 |
| 0.1305 | 5.0 | 270 | 0.5388 | 0.7671 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0a0+17540c5
- Datasets 2.2.1
- Tokenizers 0.12.1