lemonhat/Qwen2.5-7B-Instruct-APIGen_5k_arguments_fixed

APIGen_5k_arguments_fixed

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the APIGen_5k_arguments_fixed dataset. It achieves the following results on the evaluation set:

• Loss: 0.1258

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: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• 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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.3193	0.1297	100	0.2052
0.2016	0.2594	200	0.1736
0.2494	0.3891	300	0.1569
0.1697	0.5188	400	0.1487
0.1385	0.6485	500	0.1367
0.1413	0.7782	600	0.1283
0.2557	0.9079	700	0.1260

Framework versions

• Transformers 4.46.1
• Pytorch 2.6.0+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3