frenkd's picture
Model save
9f6d5e7 verified
|
raw
history blame
1.28 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: EleutherAI/pythia-410m
datasets:
  - generator
model-index:
  - name: pythia-410m-2024-04-16-13-51-UDGvo
    results: []

pythia-410m-2024-04-16-13-51-UDGvo

This model is a fine-tuned version of EleutherAI/pythia-410m on the generator dataset.

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: 0.0002
  • train_batch_size: 6
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 12
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3

Training results

Framework versions

  • PEFT 0.10.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2