qwen2.5_1.5b_1M_16kcw_2ep

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on the anghabench_1M_1 and the anghabench_1M_2 datasets. It achieves the following results on the evaluation set:

• Loss: 0.0010

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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0016	0.4988	61000	0.0023
0.0009	0.9977	122000	0.0015
0.0007	1.4965	183000	0.0011
0.0006	1.9953	244000	0.0010

Framework versions

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