Edit model card

llama3-ViMMRC-Answer

This model is a fine-tuned version of unsloth/llama-3-8b-Instruct-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1419
  • Accuracy: 0.885662

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

ViMMRC train and test set

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 3407
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 5
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
3.2677 0.3306 10 0.1883
0.4922 0.6612 20 0.2020
0.4551 0.9917 30 0.1609
0.4292 1.3223 40 0.2353
0.4361 1.6529 50 0.1758
0.4323 1.9835 60 0.1515
0.4232 2.3140 70 0.1451
0.411 2.6446 80 0.1424
0.413 2.9752 90 0.1419

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
10
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Angelectronic/llama3-ViMMRC-Answer

Adapter
(68)
this model