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_gen
    results: []
library_name: peft

new_test_gen

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: 0.1867

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
0.1061	1.0	1192	0.1481
0.0781	2.0	2384	0.1709
0.0703	3.0	3576	0.1867

Framework versions

PEFT 0.4.0
Transformers 4.43.3
Pytorch 2.3.1+cu121
Datasets 2.13.0
Tokenizers 0.19.1