You can deploy this model and start earning money today!

yinita/
cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian

Name: cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian
Availability: InStock

generated_from_trainer

Qwen/Qwen2.5-14B-Instruct

adapter

apache-2.0

Views

No views yet

cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian

This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the task1_stage_0 and the stage1_sync_by_lian datasets. It achieves the following results on the evaluation set:

Loss: 1.2002

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: 4
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.2178	1.0	204	1.3718
1.0078	2.0	408	1.1832
0.8351	3.0	612	1.0897
0.7388	4.0	816	1.0783
0.6647	5.0	1020	1.0801
0.5993	6.0	1224	1.0973
0.5687	7.0	1428	1.1244
0.4952	8.0	1632	1.1543
0.4508	9.0	1836	1.1873
0.4697	10.0	2040	1.2002

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

yinita/cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian

cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yinita/
cpdc-qwen14-base-maintask2-v0614-v5-lora-cp-sync-by-lian