Edit model card

icdsum-llm

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4557

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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
3.5036 0.96 6 3.4557
3.5188 1.92 12 3.4557
3.5224 2.88 18 3.4557
3.0173 4.0 25 3.4557
3.5133 4.96 31 3.4557
3.5226 5.92 37 3.4557
3.5147 6.88 43 3.4557
3.0128 8.0 50 3.4557
3.5179 8.96 56 3.4557
3.115 9.6 60 3.4557

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for jitendra89/icdsum-llm