metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: saves/Orca/merge_unload
model-index:
- name: SFT
results: []
SFT
This model is a fine-tuned version of saves/Orca/merge_unload on the WordProblems_SFT dataset. It achieves the following results on the evaluation set:
- Loss: 0.1966
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 300
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2823 | 0.2425 | 250 | 0.2783 |
| 0.2186 | 0.4850 | 500 | 0.2229 |
| 0.2227 | 0.7274 | 750 | 0.2104 |
| 0.1965 | 0.9699 | 1000 | 0.2038 |
| 0.2001 | 1.2124 | 1250 | 0.2003 |
| 0.2087 | 1.4549 | 1500 | 0.1980 |
| 0.1932 | 1.6974 | 1750 | 0.1969 |
| 0.2044 | 1.9399 | 2000 | 0.1966 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.0.1+cu118
- Datasets 2.17.1
- Tokenizers 0.19.1