See axolotl config
axolotl version: 0.4.1
base_model: mistralai/Mistral-Nemo-Instruct-2407
model_type: MistralForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
chat_template: inst
rl: dpo
datasets:
- path: HumanLLMs/humanish-dpo-project
type: chatml.prompt_pairs
conversation: mistral
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./humanish-mistral-nemo-instruct-2407
sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 4
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: Humanish-DPO
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: HumanLLMs/Humanish-Mistral-Nemo-Instruct-2407
gradient_accumulation_steps: 8
micro_batch_size: 2
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: 2
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: </s>
save_safetensors: true
Humanish-Mistral-Nemo-Instruct-2407
This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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
- training_steps: 341
Training results
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.20.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 22.88 |
IFEval (0-Shot) | 54.51 |
BBH (3-Shot) | 32.71 |
MATH Lvl 5 (4-Shot) | 7.63 |
GPQA (0-shot) | 5.03 |
MuSR (0-shot) | 9.40 |
MMLU-PRO (5-shot) | 28.01 |
- Downloads last month
- 26
Model tree for HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard54.510
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard32.710
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard7.630
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.030
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.400
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard28.010