This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the 2and3_apps_30k_v6 dataset. It achieves the following results on the evaluation set:

Loss: 0.1702

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
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
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.1869	0.1025	100	0.1962
0.2003	0.2049	200	0.1868
0.1987	0.3074	300	0.1808
0.2129	0.4098	400	0.1772
0.1895	0.5123	500	0.1748
0.1897	0.6148	600	0.1727
0.1916	0.7172	700	0.1720
0.179	0.8197	800	0.1707
0.1867	0.9221	900	0.1701

Framework versions

Transformers 4.46.1
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.20.3

lemonhat/Qwen2.5-3B-Instruct-2and3_apps_30k_v6

2and3_apps_30k_v6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Qwen2.5-3B-Instruct-2and3_apps_30k_v6