Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0

<a href="https://ibb.co/4jPnqYk"><img src="https://i.ibb.co/qRk3SW6/DALL-E-2024-08-08-05-52-48-Craft-an-epic-and-historic-image-for-a-model-card-blending-elements-of-an.webp" alt="DALL-E-2024-08-08-05-52-48-Craft-an-epic-and-historic-image-for-a-model-card-blending-elements-of-an" border="0"></a>

Model Card for Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0

Model Details

Model Description

• Finetuned from model:[Na0s/Llama-3.1-8b-Pruned-4-Layers-1.0]

<!-- Provide a quick summary of what the model is/does. -->

Training Details

model = FastLanguageModel.get_peft_model(
model,
r = 4, 
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                  "gate_proj", "up_proj", "down_proj",],
lora_alpha = 4,
lora_dropout = 0.05, 
bias = "none",    

use_gradient_checkpointing = "unsloth", 
random_state = 3407,
use_rslora = False,  
loftq_config = None, 
)

from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported

trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
dataset_text_field = "completion",
max_seq_length = max_seq_length,
dataset_num_proc = 2,
packing = False, 
args = TrainingArguments(
    per_device_train_batch_size = 10,
    gradient_accumulation_steps = 4,
    warmup_steps = 5,
    max_steps=5000,
    learning_rate = 2e-4,
    fp16 = not is_bfloat16_supported(),
    bf16 = is_bfloat16_supported(),
    logging_steps = 1,
    optim = "adamw_8bit",
    weight_decay = 0.01,
    lr_scheduler_type = "cosine",
    seed = 3407,
    output_dir = "outputs_4",
    push_to_hub=True,
    hub_always_push=True,
),
)

Training Data

[meta-math/MetaMathQA]

Evaluation

MMLU Pro 0-shot: 0.2872

Evaluation Data

<!-- This should link to a Dataset Card if possible. -->

[TIGER-AI-Lab/MMLU-Pro]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).