Qwen2.5-7B-agenttuning_v1_tag4 – AI Model by lemonhat | AlphaNeural AI

You can deploy this model and start earning money today!

lemonhat/
Qwen2.5-7B-agenttuning_v1_tag4

like

0

text-generation

generated_from_trainer

Qwen/Qwen2.5-7B

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

agenttuning_v1_tag4

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

Loss: 0.3350

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
0.3436	0.0860	100	0.4208
0.3526	0.1720	200	0.4048
0.5279	0.2580	300	0.3871
0.5256	0.3439	400	0.3733
0.3576	0.4299	500	0.3631
0.4693	0.5159	600	0.3564
0.3993	0.6019	700	0.3512
0.2761	0.6879	800	0.3458
0.3935	0.7739	900	0.3355
0.4377	0.8598	1000	0.3406
0.3258	0.9458	1100	0.3352

Framework versions

Transformers 4.46.1
Pytorch 2.7.1+cu126
Datasets 3.1.0
Tokenizers 0.20.3