Hugging Face's logo

talazz
/
results

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
results / README.md
talazz's picture
talazz
your-username/llama2_finetuned
091bcd8 verified
preview code
|
raw
history blame
1.58 kB
metadata
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TinyPixel/Llama-2-7B-bf16-sharded
model-index:
  - name: results
    results: []

Visualize in Weights & Biases

results

This model is a fine-tuned version of TinyPixel/Llama-2-7B-bf16-sharded on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5778

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: 0.0004
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.3877 1.0 4174 0.5778

Framework versions

  • PEFT 0.11.2.dev0
  • Transformers 4.41.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1