Hugging Face's logo

spjabech
/
th_cl_23epochs_lora_pos_neg

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
th_cl_23epochs_lora_pos_neg / README.md
spjabech's picture
spjabech
End of training
ba0d241 verified
preview code
|
raw
history blame contribute delete
1.87 kB
metadata
license: llama3
library_name: peft
tags:
  - generated_from_trainer
base_model: gradientai/Llama-3-8B-Instruct-262k
metrics:
  - accuracy
model-index:
  - name: th_cl_23epochs_lora_pos_neg
    results: []

th_cl_23epochs_lora_pos_neg

This model is a fine-tuned version of gradientai/Llama-3-8B-Instruct-262k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1121
  • Balanced Accuracy: 0.47
  • Accuracy: 0.4667

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Balanced Accuracy Accuracy
0.5546 1.0 32 1.0124 0.4911 0.4889
0.3157 2.0 64 1.0066 0.4722 0.4667
0.1355 3.0 96 0.9881 0.5977 0.6
0.0512 4.0 128 1.1006 0.5536 0.5556
0.0605 5.0 160 1.1121 0.47 0.4667

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1