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: 0.5452

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	0.5351
No log	2.0	30	0.5292
No log	3.0	45	0.5297
No log	4.0	60	0.5342
No log	5.0	75	0.5368
No log	6.0	90	0.5420
No log	7.0	105	0.5422
No log	8.0	120	0.5438
No log	9.0	135	0.5452
No log	9.3540	140	0.5452

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0