metadata
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: new_test
results: []
library_name: peft
new_test
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1960
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: True
- _load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
- bnb_4bit_quant_storage: uint8
- load_in_4bit: False
- load_in_8bit: True
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.107 | 1.0 | 776 | 0.1502 |
| 0.0818 | 2.0 | 1552 | 0.1786 |
| 0.0693 | 3.0 | 2328 | 0.1960 |
Framework versions
- PEFT 0.4.0
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.13.0
- Tokenizers 0.19.1