mtzig's picture
Model save
bf32703 verified
metadata
library_name: peft
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
tags:
  - generated_from_trainer
model-index:
  - name: tinyllama-1.1b-sft-lora
    results: []

tinyllama-1.1b-sft-lora

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 0.0003
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 4234
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
No log 0.0889 2 nan
No log 0.1778 4 nan
0.0 0.2667 6 nan
0.0 0.3556 8 nan
0.0 0.4444 10 nan
0.0 0.5333 12 nan
0.0 0.6222 14 nan
0.0 0.7111 16 nan
0.0 0.8 18 nan
0.0 0.8889 20 nan
0.0 0.9778 22 nan

Framework versions

  • PEFT 0.15.2
  • Transformers 4.51.3
  • Pytorch 2.7.0+cu128
  • Datasets 3.5.0
  • Tokenizers 0.21.1