metadata

license: apache-2.0
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
base_model: allenai/OLMo-1B-hf
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: zephyr-1b-olmo-sft-qlora
    results: []

Note: This model card has been generated automatically according to the information the Trainer had access to. Visit the model card to see the full description.

zephyr-1b-olmo-sft-qlora

This model is a fine-tuned version of allenai/OLMo-1B-hf on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

Loss: 1.3126

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 128
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.3184	1.0	1001	1.3126

Framework versions

PEFT 0.7.1
Transformers 4.40.1
Pytorch 2.1.2+cu121
Datasets 2.19.0
Tokenizers 0.19.1