metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vicuna-13b-83k-dataset-new-combined
results: []
vicuna-13b-83k-dataset-new-combined
This model is a fine-tuned version of eachadea/vicuna-13b-1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5078
- Accuracy: 0.0120
- Entropy: 1.6010
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: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|---|---|---|---|---|---|
| 1.6308 | 1.0 | 5127 | 1.5078 | 0.0120 | 1.6010 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3