lightblue/reranker-0.5B-fulltrain-filtered

fulltrain_filtered_0dot5

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_fulltrain_filtered dataset. It achieves the following results on the evaluation set:

• Loss: 0.0596

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• 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: 0.01
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0903	0.1000	2055	0.1089
0.0847	0.2000	4110	0.0900
0.104	0.3000	6165	0.0882
0.0873	0.4001	8220	0.0805
0.0741	0.5001	10275	0.0740
0.0528	0.6001	12330	0.0680
0.0802	0.7001	14385	0.0674
0.0944	0.8001	16440	0.0616
0.0651	0.9001	18495	0.0601

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3