You can deploy this model and start earning money today!

Shahdddddd/
news-analyzer

Name: news-analyzer
Availability: InStock

Qwen/Qwen2.5-1.5B-Instruct

apache-2.0

Views

No views yet

news-analyzer

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the news_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3888

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 8
total_eval_batch_size: 2
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: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4231	0.2963	100	0.4306
0.4024	0.5926	200	0.3985
0.4269	0.8889	300	0.3828
0.305	1.1837	400	0.3812
0.2767	1.48	500	0.3802
0.2204	1.7763	600	0.3886
0.1858	2.0741	700	0.3927
0.2011	2.3704	800	0.3918
0.1861	2.6667	900	0.3911
0.1971	2.9630	1000	0.3887

Framework versions

PEFT 0.18.1
Transformers 4.56.1
Pytorch 2.10.0+cu128
Datasets 3.2.0
Tokenizers 0.22.2

Shahdddddd/news-analyzer

news-analyzer

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Shahdddddd/
news-analyzer