limstral-7B-v0.1 / README.md
librarian-bot's picture
Librarian Bot: Add base_model information to model
3df7223
|
raw
history blame
2.87 kB
metadata
language:
  - en
license: apache-2.0
datasets:
  - GAIR/lima
pipeline_tag: text-generation
thumbnail: https://huggingface.co/mrm8488/limstral-7B-v0.1/resolve/main/limstral_logo.png
base_model: mistralai/Mistral-7B-v0.1

LIMSTRAL πŸ‡²πŸ‹

limstral logo

Mistral 7B fine-tuned on LIMA

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the LIMA dataset for instruction following downstream task.

Training procedure

The model was loaded on 8 bits and fine-tuned on the LIMA dataset using the LoRA PEFT technique with the huggingface/peft library and trl/sft for 2 epochs on 1 x A100 (40GB) GPU.

SFT Trainer params:

trainer = SFTTrainer(
    model=model,
    train_dataset=train_ds,
    eval_dataset=test_ds,
    peft_config=peft_config,
    dataset_text_field="text",
    max_seq_length=2048,
    tokenizer=tokenizer,
    args=training_arguments,
    packing=False
)

LoRA config:

config = LoraConfig(
        lora_alpha=16,
        lora_dropout=0.1,
        r=64,
        bias="none",
        task_type="CAUSAL_LM",
        target_modules = ['q_proj', 'k_proj', 'down_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj']
    )

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 66
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Step Training Loss Validation Loss
5 1.802800 1.848371
10 1.605800 1.803416
15 1.844800 1.762276
20 1.752600 1.754042
25 1.512400 1.750550

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

repo_id = "mrm8488/limstral-7B-v0.1"

model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(repo_id)

gen = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)

instruction = "[INST] Write an email to say goodbye to me boss [\INST]"
res = gen(instruction, max_new_tokens=512, temperature=0.3, top_p=0.75, top_k=40, repetition_penalty=1.2)
print(res[0]['generated_text'])

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1