lesso01's picture
End of training
f25d823 verified
metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 99684001-fed9-4c76-b948-11030f04133f
    results: []

Built with Axolotl

99684001-fed9-4c76-b948-11030f04133f

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1392

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: 0.000201
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 10
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • training_steps: 248

Training results

Training Loss Epoch Step Validation Loss
No log 0.0040 1 1.8450
1.6088 0.2020 50 1.4174
1.3277 0.4040 100 1.5023
1.4604 0.6061 150 1.2100
1.2613 0.8081 200 1.1392

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1