metadata
license: other
base_model: 01-ai/Yi-34B
tags:
- generated_from_trainer
model-index:
- name: yi_4k_paged_optimizer
results: []
yi_4k_paged_optimizer
This model is a fine-tuned version of 01-ai/Yi-34B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5581
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: 5e-07
- 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=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2057 | 0.99 | 31 | 0.9855 |
| 0.5676 | 1.98 | 62 | 0.5699 |
| 0.5608 | 2.98 | 93 | 0.5596 |
| 0.5576 | 3.97 | 124 | 0.5581 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0