metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: roberta-base-finetuned-nlp-letters-TEXT-all-class-weighted
results: []
roberta-base-finetuned-nlp-letters-TEXT-all-class-weighted
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7120
- F1: 0.7740
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 1.0 | 221 | 0.4726 | 0.4302 |
No log | 2.0 | 442 | 0.4392 | 0.4995 |
0.4877 | 3.0 | 663 | 0.3867 | 0.4836 |
0.4877 | 4.0 | 884 | 0.5359 | 0.6492 |
0.4029 | 5.0 | 1105 | 0.4401 | 0.6013 |
0.4029 | 6.0 | 1326 | 0.4508 | 0.7301 |
0.3208 | 7.0 | 1547 | 0.7120 | 0.7740 |
0.3208 | 8.0 | 1768 | 1.0509 | 0.7690 |
0.3208 | 9.0 | 1989 | 1.5755 | 0.7444 |
0.2085 | 10.0 | 2210 | 1.8282 | 0.7580 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1