See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Llama-3.1-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: ahmedelgebaly/SQuad_2_Alpaca
    type: alpaca
    split: train

test_datasets:
  - path: ahmedelgebaly/SQuad_2_Alpaca
    type: alpaca
    split: validation
    
dataset_prepared_path:
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: llama-3.1-8b-squadv2_e2
wandb_entity:
wandb_watch:
wandb_name: llama-3.1-8b-squadv2-v0_e2
wandb_log_model:

hub_model_id: ahmedelgebaly/llama-3.1-8b-squadv2_e2

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 2
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

llama-3.1-8b-squadv2_e2

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9133

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.4871	0.0033	1	1.5437
0.9082	0.2512	77	0.9307
0.9116	0.5024	154	0.9171
0.8508	0.7537	231	0.9130
0.8106	1.0024	308	0.9063
0.7906	1.2537	385	0.9150
0.8229	1.5049	462	0.9151
0.8233	1.7561	539	0.9133

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1