qwen

This model is a fine-tuned version of /inspire/hdd/ws-8207e9e2-e733-4eec-a475-cfa1c36480ba/embodied-multimodality/public/yli/workspace/Model/Qwen/Qwen2.5-7B on the 2wikimultihopqa_train, the hotpotqa_train and the musique_train datasets. It achieves the following results on the evaluation set:

  • Loss: 0.1587

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: 7e-06
  • train_batch_size: 4
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • 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: 0.1
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
0.1713 0.3842 500 0.1614
0.1549 0.7685 1000 0.1432
0.0948 1.1527 1500 0.1415
0.0846 1.5370 2000 0.1369
0.0841 1.9212 2500 0.1317
0.0375 2.3055 3000 0.1596
0.0366 2.6897 3500 0.1586

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.4.0
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
1
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Leon97ZJU/qwen_answer

Base model

Qwen/Qwen2.5-7B
Finetuned
(771)
this model