adapter: lora
base_model: meta-llama/Llama-3.1-8B-Instruct
bf16: true
fp16: false

datasets:
  - path: mx003/cve
    type: chat_template
    field_messages: messages
    chat_template: llama3

lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj

gradient_accumulation_steps: 4
gradient_checkpointing: true
micro_batch_size: 2
num_epochs: 3
learning_rate: 0.0002
optimizer: adamw_torch_fused
train_on_inputs: false
group_by_length: true

output_dir: ./outputs/mymodel
sequence_len: 4096
save_steps: 50
flash_attention: true
sample_packing: true
special_tokens:
  pad_token: <|end_of_text|>
tokens:
  - "<|end_of_text|>"

outputs/mymodel

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the mx003/cve dataset.

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: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2
training_steps: 63

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

mx003/cve-llama-1000_2

outputs/mymodel

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mx003/
cve-llama-1000_2