metadata
library_name: transformers
base_model: ccore/ccore-v3
tags:
- generated_from_trainer
model-index:
- name: ccore-v3
results: []
ccore-v3
This model is a fine-tuned version of ccore/ccore-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6705
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: 0.0001
- train_batch_size: 24
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 192
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 15 | 0.7184 |
| No log | 2.0 | 30 | 0.7096 |
| No log | 3.0 | 45 | 0.6936 |
| No log | 4.0 | 60 | 0.6845 |
| No log | 5.0 | 75 | 0.6744 |
| No log | 6.0 | 90 | 0.6724 |
| No log | 7.0 | 105 | 0.6735 |
| No log | 8.0 | 120 | 0.6708 |
| No log | 9.0 | 135 | 0.6705 |
| No log | 9.3540 | 140 | 0.6705 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0