metadata
license: other
base_model: 01-ai/Yi-6B
tags:
- generated_from_trainer
model-index:
- name: apt-chat-yi-34b-sft-full
results: []
apt-chat-yi-34b-sft-full
This model is a fine-tuned version of 01-ai/Yi-6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3422
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: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- total_eval_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1029 | 0.15 | 135 | 1.0746 |
| 0.8271 | 1.15 | 270 | 1.1266 |
| 0.5131 | 2.15 | 405 | 1.3422 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0.dev20230605+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1