metadata

license: llama2
base_model: vilm/vinallama-7b
tags:
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: vinallama-7b-legal-chat
    results: []

vinallama-7b-legal-chat

This model is a fine-tuned version of vilm/vinallama-7b on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.5088

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: 8
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 512
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.8228	1.0	87	0.6192
0.712	2.0	174	0.5088

Framework versions

Transformers 4.35.0
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.14.1