metadata

license: other
base_model: google/gemma-2b
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: gemma-2b-ultrachat-sft
    results: []

gemma-2b-ultrachat-sft

This model is a fine-tuned version of google/gemma-2b on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

Loss: 1.2072

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
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
1.2073	1.0	954	1.2288
1.1523	2.0	1908	1.2081
1.1174	3.0	2862	1.2072

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2