metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: rubert-base-srl
results: []
rubert-base-srl
This model is a fine-tuned version of ./ruBert-base/ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3467
- F1: 0.9582
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.5166 | 1.0 | 57 | 0.3770 | 0.8102 |
| 0.3798 | 2.0 | 114 | 0.1983 | 0.9373 |
| 0.141 | 3.0 | 171 | 0.2044 | 0.9367 |
| 0.1156 | 4.0 | 228 | 0.2323 | 0.9480 |
| 0.001 | 5.0 | 285 | 0.3252 | 0.9475 |
| 0.0022 | 6.0 | 342 | 0.2978 | 0.9582 |
| 0.0258 | 7.0 | 399 | 0.3218 | 0.9582 |
| 0.0004 | 8.0 | 456 | 0.3427 | 0.9582 |
| 0.0005 | 9.0 | 513 | 0.3455 | 0.9582 |
| 0.0002 | 10.0 | 570 | 0.3467 | 0.9582 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.10.0+cu102
- Datasets 1.15.1
- Tokenizers 0.10.3