qwen4B_models/qwen_4B_d1_iter2_model/README.md

metadata

license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: /ML-A100/team/mm/eamon/self_instruction/models/Qwen1_5_4B
model-index:
  - name: qwen_4B_d1_iter2_model
    results: []

qwen_4B_d1_iter2_model

This model is a fine-tuned version of /ML-A100/team/mm/eamon/self_instruction/models/Qwen1_5_4B on the qwen_4B_d1_iter2_model dataset. It achieves the following results on the evaluation set:

• Loss: 0.7857

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6978	1.4706	100	0.7857

Framework versions

• PEFT 0.10.0
• Transformers 4.41.2
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1