SFT-Cryptol-2.5-Coder-14B_v5

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-14B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8053

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.8855	0.2974	20	0.9315
0.7895	0.5948	40	0.8817
0.6665	0.8922	60	0.8513
0.6695	1.1784	80	0.8323
0.5996	1.4758	100	0.8184
0.5776	1.7732	120	0.8093
0.611	2.0595	140	0.8067
0.4685	2.3569	160	0.8098
0.6223	2.6543	180	0.8054
0.5206	2.9517	200	0.8053

Framework versions

• PEFT 0.18.0
• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1