metadata
base_model: klue/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-base-finetuned-tc
results: []
roberta-base-finetuned-tc
This model is a fine-tuned version of klue/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5805
- Accuracy: 0.8378
- F1: 0.8303
- Precision: 0.8386
- Recall: 0.8378
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 13 | 1.4532 | 0.4777 | 0.3088 | 0.2282 | 0.4777 |
| No log | 2.0 | 26 | 1.1224 | 0.6190 | 0.5210 | 0.4641 | 0.6190 |
| No log | 3.0 | 39 | 0.8175 | 0.7560 | 0.7238 | 0.7040 | 0.7560 |
| No log | 4.0 | 52 | 0.7069 | 0.7932 | 0.7712 | 0.7526 | 0.7932 |
| No log | 5.0 | 65 | 0.6515 | 0.8110 | 0.7895 | 0.7705 | 0.8110 |
| No log | 6.0 | 78 | 0.6212 | 0.8170 | 0.7983 | 0.8023 | 0.8170 |
| No log | 7.0 | 91 | 0.6025 | 0.8304 | 0.8163 | 0.8395 | 0.8304 |
| No log | 8.0 | 104 | 0.5982 | 0.8318 | 0.8238 | 0.8330 | 0.8318 |
| No log | 9.0 | 117 | 0.5815 | 0.8348 | 0.8260 | 0.8344 | 0.8348 |
| No log | 10.0 | 130 | 0.5805 | 0.8378 | 0.8303 | 0.8386 | 0.8378 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2