qwen3-horoscope-sft – AI Model by zhaozefeng0409 | AlphaNeural AI

You can deploy this model and start earning money today!

zhaozefeng0409/
qwen3-horoscope-sft

like

0

text-generation

generated_from_trainer

Qwen/Qwen3-0.6B

text-generation-inference

endpoints_compatible

Views

No views yet

qwen3-horoscope-sft

This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5442
Token Accuracy: 0.6706

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: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Token Accuracy
2.0847	1.0	1236	2.1549	0.5326
1.8152	2.0	2472	1.8032	0.6150
1.5603	3.0	3708	1.7049	0.6339
1.3579	4.0	4944	1.6371	0.6487
1.4338	5.0	6180	1.5916	0.6591
1.3579	6.0	7416	1.5640	0.6660
1.3322	7.0	8652	1.5517	0.6690
1.3495	8.0	9888	1.5459	0.6706
1.6366	9.0	11124	1.5444	0.6710
1.3321	10.0	12360	1.5442	0.6706

Framework versions

Transformers 5.10.2
Pytorch 2.8.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2