output / README.md
Atipico1's picture
Model save
dd35c61 verified
metadata
base_model: Qwen/Qwen2-1.5B-Instruct
library_name: peft
license: apache-2.0
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: output
    results: []

output

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

  • Loss: 1.0250

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: 2e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.0812 1.0 1250 1.0450
1.012 2.0 2500 1.0273
1.0175 3.0 3750 1.0250

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1