Magpie-Pro
Collection
Dataset built with Meta Llama 3 70B. Models are fine-tuned from Llama 3 8B.
•
8 items
•
Updated
•
14
Project Web: https://magpie-align.github.io/
Arxiv Technical Report: https://arxiv.org/abs/2406.08464
Codes: https://github.com/magpie-align/magpie
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on First 100K data of Magpie-Align/Magpie-Pro-300K-Filtered dataset.
Please use Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-v0.1 with better performance.
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8869 | 0.0036 | 1 | 0.9139 |
0.5854 | 0.3344 | 92 | 0.6158 |
0.5218 | 0.6688 | 184 | 0.5455 |
0.4878 | 1.0032 | 276 | 0.5125 |
0.3734 | 1.3226 | 368 | 0.5091 |
0.3647 | 1.6570 | 460 | 0.5056 |
axolotl version: 0.4.0
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Magpie-Align/Magpie-Pro-300K-Filtered-First100K
type: sharegpt
conversation: llama3
dataset_prepared_path: last_run_prepared
val_set_size: 0.001
output_dir: ./out_Llama-3-8B-Magpie-Pro-100K-FilteredL
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>