qwen2.5-0.5b-anghabench-16kcw-3ep

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct on the anghabench dataset. It achieves the following results on the evaluation set:

• Loss: 0.0009

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 4
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0042	0.4091	25000	0.0036
0.0026	0.8181	50000	0.0023
0.0025	1.2272	75000	0.0018
0.0009	1.6363	100000	0.0013
0.0013	2.0453	125000	0.0010
0.0012	2.4544	150000	0.0010
0.0003	2.8635	175000	0.0009

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3