This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the t1_25k_v2_tag4 dataset. It achieves the following results on the evaluation set:

Loss: 0.2757

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: 8
total_train_batch_size: 8
total_eval_batch_size: 8
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
0.337	0.1698	100	0.3199
0.2887	0.3396	200	0.3034
0.2732	0.5093	300	0.2857
0.3099	0.6791	400	0.2798
0.2879	0.8489	500	0.2773

Framework versions

Transformers 4.46.1
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.20.3

lemonhat/Qwen2.5-7B-Instruct-t1_25k_v2_tag4

t1_25k_v2_tag4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Qwen2.5-7B-Instruct-t1_25k_v2_tag4