bzhang0426's picture
Upload 14 files
a0dc21b verified
metadata
license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - unsloth
  - generated_from_trainer
base_model: unsloth/llama-3-70b-Instruct-bnb-4bit
model-index:
  - name: A61K
    results: []

A61K

This model is a fine-tuned version of unsloth/llama-3-70b-Instruct-bnb-4bit on the patents_A61K_cla_abs_det_sample_2100_balance_train_llama-factory dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3432

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: 3e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5658 0.4938 100 0.4336
0.361 0.9877 200 0.3438
0.3343 1.4815 300 0.3503
0.3275 1.9753 400 0.3462
0.2916 2.4691 500 0.3432
0.291 2.9630 600 0.3441

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1