metadata
license: other
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- ruozhiba
base_model: 01-ai/Yi-6B
model-index:
- name: Yi-6B-ruozhiba-1e-5-50
results: []
Yi-6B-ruozhiba-1e-5-50
This model is a fine-tuned version of 01-ai/Yi-6B on the ruozhiba dataset. It achieves the following results on the evaluation set:
- Loss: 3.5129
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5902 | 2.0 | 110 | 2.0347 |
| 0.4146 | 4.0 | 220 | 2.7832 |
| 0.2193 | 5.0 | 275 | 3.0240 |
| 0.1547 | 6.0 | 330 | 3.2444 |
| 0.1096 | 7.0 | 385 | 3.3953 |
| 0.1053 | 8.0 | 440 | 3.4807 |
| 0.0969 | 9.0 | 495 | 3.5086 |
| 0.1768 | 10.0 | 550 | 3.5129 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2