Hugging Face's logo

liuylhf
/
mistral-lora

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
mistral-lora / README.md
liuylhf's picture
liuylhf
End of training
3511b58 verified
preview code
|
raw
history blame
3.65 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
  - name: mistral-lora
    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/raw_format/tool_used_training.jsonl
    type: sharegpt
  - path: ./data/raw_format/tool_not_used_training.jsonl
    type: sharegpt
  - path: ./data/raw_format/no_tools_training.jsonl
    type: sharegpt

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive-inst

adapter: lora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

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

hub_model_id: liuylhf/mistral-lora

wandb_project: function-call
wandb_name: mixtral-instruct-qlora-v1
wandb_log_model: end

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 0.5
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.001
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0

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

# loss_watchdog_threshold: 5.0
# loss_watchdog_patience: 3

warmup_steps: 10
# evals_per_epoch: 20
eval_steps: 0.2
save_steps: 0.2
eval_table_size:
eval_max_new_tokens: 256
# saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 1.0
fsdp:
fsdp_config:

mistral-lora

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1480

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: 0.001
  • 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=(0.9,0.95) and epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 0.5

Training results

Training Loss Epoch Step Validation Loss
1.3787 0.0 1 1.4156
0.0868 0.1 31 0.1745
0.149 0.21 62 0.1603
0.1328 0.31 93 0.1532
0.1635 0.41 124 0.1480

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.0