metadata

license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
datasets:
  - generator
model-index:
  - name: tinyllama-1.1b-sum-sft-qlora
    results: []

tinyllama-1.1b-sum-sft-qlora

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the generator dataset. It achieves the following results on the evaluation set:

Loss: 2.1637

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: 32
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.1729	1.0	1340	2.1778
2.1327	2.0	2681	2.1632
2.0989	3.0	4020	2.1637

Framework versions

PEFT 0.7.1
Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2