Hugging Face's logo

femT-data
/
llama-3.1-8B-instruct-overall

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
llama-3.1-8B-instruct-overall / README.md
femT-data's picture
femT-data
End of training
2ad496e verified
preview code
|
raw
history blame contribute delete
3.07 kB
metadata
license: llama3.1
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: meta-llama/Llama-3.1-8B-Instruct
model-index:
  - name: llama-3.1-8B-instruct-overall
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

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

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: data.jsonl
    ds_type: json
    type: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out
hub_model_id: femT-data/llama-3.1-8B-instruct-overall
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
optimizer: adamw_bnb_8bit
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
s2_attention:

warmup_steps: 10
evals_per_epoch: 1
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|end_of_text|>

llama-3.1-8B-instruct-overall

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

  • Loss: 0.3622

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
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_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: 1

Training results

Training Loss Epoch Step Validation Loss
0.5302 0.8889 6 0.3622

Framework versions

  • PEFT 0.11.1
  • Transformers 4.43.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1