Hugging Face's logo

Pragades
/
LlaMa_3.1_8B

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
LlaMa_3.1_8B / README.md
Pragades's picture
Pragades
Pragades/LlaMa_3.1_8Billion_instruct(Interviewer))
b33600b verified
preview code
|
raw
history blame contribute delete
1.59 kB
metadata
base_model: meta-llama/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: LlaMa_3.1_8B
    results: []

LlaMa_3.1_8B

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5818

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 450
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.7086 0.0615 100 0.6413
0.6102 0.1229 200 0.6121
0.596 0.1844 300 0.5943
0.5438 0.2459 400 0.5818

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1