Downloads · 30 days
9.2K
4% of all-time downloads
lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half
suzume-llama-3-8B-multilingual-orpo-borda-half is a text generation model from lightblue. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
<p align="center" <img width=500 src="https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kWQSu02YfgYdUQqv4s5lq.png" alt="Suzume with Mitsu - a Japanese tree sparrow with honey on it"/ </p
Downloads · 30 days
9.2K
4% of all-time downloads
All-time downloads
251K
Public
Parameters
8B
16.1 GB on disk
Likes
16
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
This is Suzume ORPO, an ORPO trained fine-tune of the lightblue/suzume-llama-3-8B-multilingual model using our lightblue/mitsu dataset.
We have trained several versions of this model using ORPO and so recommend that you use the best performing model from our tests, lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half.
Note that this model has a non-commerical license as we used the Command R and Command R+ models to generate our training data for this model (lightblue/mitsu).
We are currently working on a developing a commerically usable model, so stay tuned for that!
We have ORPO trained the following models using different proportions of the lightblue/mitsu dataset:
We compare the MT-Bench scores across 6 languages for our 4 ORPO trained models, as well as some baselines:
| MT-Bench language | meta-llama/Meta-Llama-3-8B-Instruct | Nexusflow/Starling-LM-7B-beta | gpt-3.5-turbo | lightblue/suzume-llama-3-8B-multilingual | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75 | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25 |
|---|---|---|---|---|---|---|---|---|
| Chinese 🇨🇳 | NaN | 6.97 | 7.55 | 7.11 | 7.65 | 7.77 | 7.74 | 7.44 |
| English 🇺🇸 | 7.98 | 7.92 | 8.26 | 7.73 | 7.98 | 7.94 | 7.98 | 8.22 |
| French 🇫🇷 | NaN | 7.29 | 7.74 | 7.66 | 7.84 | 7.46 | 7.78 | 7.81 |
| German 🇩🇪 | NaN | 6.99 | 7.68 | 7.26 | 7.28 | 7.64 | 7.7 | 7.71 |
| Japanese 🇯🇵 | NaN | 6.22 | 7.84 | 6.56 | 7.2 | 7.12 | 7.34 | 7.04 |
| Russian 🇷🇺 | NaN | 8.28 | 7.94 | 8.19 | 8.3 | 8.74 | 8.94 | 8.81 |
We can see noticable improvement on most languages compared to the base model. We also find that our ORPO models achieve the highest score out of all the models we evaluated for a number of languages.
We trained this model using the lightblue/mitsu_full_borda dataset.
axolotl version: 0.4.0
base_model: lightblue/suzume-llama-3-8B-multilingual
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer # PreTrainedTokenizerFast
load_in_8bit: false
load_in_4bit: false
strict: false
rl: orpo
orpo_alpha: 0.1
remove_unused_columns: false
chat_template: chatml
datasets:
- path: lightblue/mitsu_tophalf_borda
type: orpo.chat_template
conversation: llama-3
dataset_prepared_path: /workspace/llm_training/axolotl/llama3-multilingual-orpo/prepared_mitsu_half_borda
val_set_size: 0.02
output_dir: /workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_half_borda
sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true
use_wandb: true
wandb_project: axolotl
wandb_entity: peterd
wandb_name: mitsu_half_borda
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 8e-6
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: 10
evals_per_epoch: 20
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
</details><br>
This model is a fine-tuned version of lightblue/suzume-llama-3-8B-multilingual on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.6299 | 0.02 | 1 | 7.7014 |
| 7.041 | 0.07 | 3 | 3.9786 |
| 0.6089 | 0.15 | 6 | 0.1393 |
| 0.1308 | 0.22 | 9 | 0.1244 |
| 0.1051 | 0.29 | 12 | 0.1112 |
| 0.1021 | 0.36 | 15 | 0.1063 |
| 0.0861 | 0.44 | 18 | 0.1026 |
| 0.1031 | 0.51 | 21 | 0.0979 |
| 0.0996 | 0.58 | 24 | 0.0967 |
| 0.0923 | 0.65 | 27 | 0.0960 |
| 0.1025 | 0.73 | 30 | 0.0944 |
| 0.1103 | 0.8 | 33 | 0.0939 |
| 0.0919 | 0.87 | 36 | 0.0937 |
| 0.104 | 0.94 | 39 | 0.0935 |
@article{devine2024sure,
title={Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets},
author={Devine, Peter},
journal={arXiv preprint arXiv:2405.18952},
year={2024}
}
Peter Devine - (ptrdvn)