Hugging Face's logo

dyang415
/
nohto-v0-1e

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
nohto-v0-1e / README.md
dyang415's picture
dyang415
Model save
d551f1d verified
preview code
|
raw
history blame
2.78 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
  - name: nohto-v0-1e
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
chat_template: inst

datasets:
  - path: ./data/nohto/training.jsonl
    type: sharegpt

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ../nohto-v0-1e

adapter: lora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 32
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:

eval_sample_packing: false

hub_model_id: dyang415/nohto-v0-1e

wandb_project: nohto
wandb_name: nohto-v0
wandb_log_model: end

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_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

warmup_steps: 10
eval_steps: 0.2
save_steps: 0.1
eval_max_new_tokens: 128
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:

nohto-v0-1e

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 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: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Framework versions

  • PEFT 0.7.0
  • Transformers 4.37.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.17.1
  • Tokenizers 0.15.0