Hugging Face's logo

axolotl-ai-co
/
romulus-mistral-nemo-12b-simpo

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
3
romulus-mistral-nemo-12b-simpo / README.md
leaderboard-pt-pr-bot's picture
leaderboard-pt-pr-bot
Adding the Open Portuguese LLM Leaderboard Evaluation Results
6220cbd verified
preview code
|
raw
history blame
4.22 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: winglian/m12b-20240721-test010
model-index:
  - name: outputs/simpo-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: winglian/m12b-20240721-test010
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
rl: simpo
rl_beta: 2.5
cpo_alpha: 0.05
simpo_gamma: 0.1
datasets:
  - path: princeton-nlp/gemma2-ultrafeedback-armorm
    type: chat_template.default
    chat_template: chatml
    field_messages: chosen
    field_chosen: chosen
    field_rejected: rejected
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path:
val_set_size: 0.0
output_dir: ./outputs/simpo-out

save_safetensors: true
save_only_model: true  # fsdp seems to crap out saving the optimizer

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

adapter: 
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
  # peft_use_rslora: true

wandb_project: romulus-12b
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 5.0e-7

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: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:

Visualize in Weights & Biases

outputs/simpo-out

This model is a fine-tuned version of winglian/m12b-20240721-test010 on an unknown dataset.

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: 5e-07
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 25
  • training_steps: 466

Training results

Framework versions

  • Transformers 4.43.1
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric Value
Average 71.97
ENEM Challenge (No Images) 70.96
BLUEX (No Images) 60.78
OAB Exams 53.62
Assin2 RTE 90.52
Assin2 STS 78.70
FaQuAD NLI 68.05
HateBR Binary 84.42
PT Hate Speech Binary 71.65
tweetSentBR 69.05