lemonhat/Qwen2.5-7B-Instruct-agenttuning_v1_tag4

agenttuning_v1_tag4

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the agenttuning_v1_tag4 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3362

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
0.3264	0.0860	100	0.4072
0.3504	0.1720	200	0.4065
0.526	0.2580	300	0.3899
0.5176	0.3439	400	0.3735
0.3618	0.4299	500	0.3685
0.4644	0.5159	600	0.3636
0.4007	0.6019	700	0.3495
0.2761	0.6879	800	0.3478
0.3908	0.7739	900	0.3378
0.4242	0.8598	1000	0.3422
0.3176	0.9458	1100	0.3362

Framework versions

• Transformers 4.46.1
• Pytorch 2.7.1+cu126
• Datasets 3.1.0
• Tokenizers 0.20.3