Edit model card

th_cl_28epochs_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: 1.1198
  • Balanced Accuracy: 0.5119
  • Accuracy: 0.5111

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
0.4669 1.0 32 1.0226 0.515 0.5111
0.2575 2.0 64 1.0064 0.5395 0.5333
0.0998 3.0 96 0.9974 0.5744 0.5778
0.0339 4.0 128 1.1087 0.5741 0.5778
0.048 5.0 160 1.1198 0.5119 0.5111

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for spjabech/th_cl_28epochs_lora_pos_neg

Adapter
(12)
this model