metadata
license: apache-2.0
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
model-index:
- name: dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1-lora
results: []
dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1-lora
This model is a fine-tuned version of cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser on the https://huggingface.co/datasets/Yhyu13/glaive-function-calling-v2-llama-factory-convert/blob/main/simple-function-calling-v2_converted_5000_with_function_call_only.json dataset. It achieves the following results on the evaluation set:
- Loss: 0.0605
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2548 | 0.09 | 100 | 0.1148 |
| 0.1149 | 0.18 | 200 | 0.0914 |
| 0.0871 | 0.27 | 300 | 0.0831 |
| 0.0865 | 0.35 | 400 | 0.0760 |
| 0.0802 | 0.44 | 500 | 0.0718 |
| 0.0689 | 0.53 | 600 | 0.0702 |
| 0.0649 | 0.62 | 700 | 0.0649 |
| 0.0637 | 0.71 | 800 | 0.0632 |
| 0.0698 | 0.8 | 900 | 0.0619 |
| 0.0648 | 0.88 | 1000 | 0.0608 |
| 0.0654 | 0.97 | 1100 | 0.0605 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0