You can deploy this model and start earning money today!

Kenazin/
Deepseek-R1-Distill-Qwen-14B-peft-p-tuning-5

Name: Deepseek-R1-Distill-Qwen-14B-peft-p-tuning-5
Availability: InStock

Views

No views yet

Deepseek-R1-Distill-Qwen-14B-peft-p-tuning-5

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-14B on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.2794	1.0	1477	0.1349	0.9575	0.8706	0.8506	0.8605
0.1178	2.0	2954	0.1353	0.9505	0.9116	0.7510	0.8235
0.1084	3.0	4431	0.1036	0.9682	0.8906	0.9042	0.8973
0.0757	4.0	5908	0.1080	0.9652	0.8915	0.8812	0.8863
0.0589	5.0	7385	0.1054	0.9682	0.8819	0.9157	0.8985