Edit model card

Llama2_AAID_structured_train_final

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the AAID_structured dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5186

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: 0.0003
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
1.462 0.0438 40 0.5250
0.3971 0.0875 80 0.5608
0.3292 0.1313 120 0.5477
0.3107 0.1750 160 0.5437
0.3033 0.2188 200 0.5186
0.2864 0.2625 240 0.5211
0.2807 0.3063 280 0.5293
0.2748 0.3500 320 0.5545
0.2685 0.3938 360 0.5562
0.2511 0.4375 400 0.5585

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Holmeister/Llama2_AAID_structured_train_final

Adapter
(1063)
this model