Edit model card

taide_llama3_8b_lora_completion_only

This model is a fine-tuned version of taide/Llama3-TAIDE-LX-8B-Chat-Alpha1 on the DandinPower/ZH-Reading-Comprehension-Llama-Instruct dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0968

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 700
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
0.1474 0.3690 250 0.1201
0.1072 0.7380 500 0.1581
0.098 1.1070 750 0.1148
0.0963 1.4760 1000 0.1044
0.0502 1.8450 1250 0.1064
0.05 2.2140 1500 0.1017
0.0239 2.5830 1750 0.1015
0.0443 2.9520 2000 0.0968

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.2+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for DandinPower/taide_llama3_8b_lora_completion_only

Adapter
(7)
this model

Dataset used to train DandinPower/taide_llama3_8b_lora_completion_only