metadata

library_name: transformers
license: other
base_model: nvidia/Minitron-4B-Base
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - allenai/tulu-v2-sft-mixture
model-index:
  - name: minitron-4b-tulu-v2-mix
    results: []

minitron-4b-tulu-v2-mix

This model is a fine-tuned version of nvidia/Minitron-4B-Base on the allenai/tulu-v2-sft-mixture dataset. It achieves the following results on the evaluation set:

Loss: 1.1978

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
training_steps: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0088	5	1.1978

Framework versions

Transformers 4.44.2
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.19.1