README.md

metadata

library_name: transformers
license: other
base_model: nvidia/Minitron-8B-Base
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: minitron-8b-tulu-v2-mix
    results: []

minitron-8b-tulu-v2-mix

This model is a fine-tuned version of nvidia/Minitron-8B-Base on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.6678

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: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 32
• 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: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.8625	0.9992	566	0.7793
0.724	1.9992	1132	0.6678

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.19.1