Hugging Face's logo

Angelectronic
/
llama3-chat_QA-test

PEFT
TensorBoard
Safetensors
trl
sft
unsloth
Generated from Trainer
Model card Files Metrics Community
llama3-chat_QA-test / README.md
Angelectronic's picture
Angelectronic
End of training
300ae64 verified
preview code
|
raw history blame contribute delete
No virus
1.96 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - unsloth
  - generated_from_trainer
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
model-index:
  - name: llama3-chat_QA-test
    results: []

llama3-chat_QA-test

This model is a fine-tuned version of unsloth/llama-3-8b-Instruct-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0283

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: 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
2.0046 0.2928 100 1.8727
1.7686 0.5857 200 1.8637
1.6753 0.8785 300 1.8871
1.5211 1.1713 400 1.9180
1.4003 1.4641 500 1.9352
1.3533 1.7570 600 1.9609
1.2794 2.0498 700 2.0143
1.1736 2.3426 800 2.0222
1.1609 2.6354 900 2.0301
1.1577 2.9283 1000 2.0283

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1