Hugging Face's logo

thangvip
/
vimo-1.3B

Text Generation
Transformers
Safetensors
gpt_neo
trl
sft
Generated from Trainer
Inference Endpoints
Model card Files Community
vimo-1.3B / README.md
S52000264
push model
99995d8
preview code
|
raw
history blame contribute delete
1.58 kB
metadata
base_model: VietAI/gpt-neo-1.3B-vietnamese-news
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: vimo-1.3B
    results: []

vimo-1.3B

This model is a fine-tuned version of VietAI/gpt-neo-1.3B-vietnamese-news on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0732

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 512
  • total_train_batch_size: 1024
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1.1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.0784 1.0 792 1.0781
1.0578 1.1 872 1.0732

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2