metadata

base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - unsloth
  - generated_from_trainer
model-index:
  - name: meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D30003
    results: []

meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D30003

This model is a fine-tuned version of unsloth/meta-llama-3.1-8b-instruct-bnb-4bit on the None dataset.

Model description

This model was trained on Successful episodes of the top 3 model similar to D20002 but instead of using the whole episode as input, each episode was split into conversation pieces.

e.g.

[
{
  role: 'user'
  content: '...'
},
{
  role: 'assistant'
  content: '...'
},
{
  role: 'user'
  content: '...'
},
{
  role: 'assistant'
  content: '...'
},
]

is split int:

[
{
  role: 'user'
  content: '...'
},
{
  role: 'assistant'
  content: '...'
},

and

[
{
  role: 'user'
  content: '...'
},
{
  role: 'assistant'
  content: '...'
},
{
  role: 'user'
  content: '...'
},
{
  role: 'assistant'
  content: '...'
},
]

Training and evaluation data

After splitting, the dataset contains about 4122 conversation bits accross all games.

The Dataset ID is D30003

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 7331
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
lr_scheduler_warmup_steps: 5
num_epochs: 1

Training results

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1