qwen3-14b-sft-1e-5-learning-rate – AI Model by kyleliu789 | AlphaNeural AI

You can deploy this model and start earning money today!

kyleliu789/
qwen3-14b-sft-1e-5-learning-rate

like

0

text-generation

Views

No views yet

qwen3_14b_svamp_sft_lr_1e-5

This model is a fine-tuned version of Qwen/Qwen3-14B on the svamp_final_sft_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3206

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: 1e-05
train_batch_size: 8
eval_batch_size: 1
seed: 42
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: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9248	0.1014	50	0.8938
0.606	0.2028	100	0.6122
0.3865	0.3043	150	0.4469
0.3375	0.4057	200	0.3763
0.3177	0.5071	250	0.3466
0.2703	0.6085	300	0.3316
0.2878	0.7099	350	0.3248
0.3151	0.8114	400	0.3217
0.3103	0.9128	450	0.3207

Framework versions

PEFT 0.18.1
Transformers 4.56.2
Pytorch 2.7.1+cu128
Datasets 3.6.0
Tokenizers 0.22.2