qwen-sql-ft – AI Model by vikasp1610 | AlphaNeural AI

You can deploy this model and start earning money today!

vikasp1610/
qwen-sql-ft

like

0

text-generation

generated_from_trainer

Qwen/Qwen2-0.5B

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

qwen-sql-ft

This model is a fine-tuned version of Qwen/Qwen2-0.5B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5554

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-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.5976	0.3282	500	0.6160
0.5626	0.6564	1000	0.5744
0.5297	0.9846	1500	0.5472
0.4201	1.3124	2000	0.5459
0.4178	1.6406	2500	0.5357
0.4037	1.9688	3000	0.5292
0.3244	2.2967	3500	0.5561
0.3342	2.6249	4000	0.5554
0.3237	2.9531	4500	0.5554

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4