!pip install -q -U bitsandbytes
!pip install -q -U git+https://github.com/huggingface/transformers.git 
!pip install -q -U git+https://github.com/huggingface/peft.git
!pip install -q -U git+https://github.com/huggingface/accelerate.git
!pip install -q datasets

     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 92.2/92.2 MB 8.1 MB/s eta 0:00:00
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 224.5/224.5 kB 21.7 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.8/7.8 MB 112.9 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 76.9 MB/s eta 0:00:00
  Building wheel for transformers (pyproject.toml) ... done
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 219.1/219.1 kB 14.5 MB/s eta 0:00:00
  Building wheel for peft (pyproject.toml) ... done
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
  Building wheel for accelerate (pyproject.toml) ... done
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 474.6/474.6 kB 33.7 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 110.5/110.5 kB 16.8 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 212.5/212.5 kB 26.2 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 134.3/134.3 kB 18.7 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.0/1.0 MB 51.9 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 114.5/114.5 kB 10.7 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 268.8/268.8 kB 30.7 MB/s eta 0:00:00
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 149.6/149.6 kB 17.5 MB/s eta 0:00:00

!pip install einops scipy

Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting einops
  Downloading einops-0.6.1-py3-none-any.whl (42 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.2/42.2 kB 5.9 MB/s eta 0:00:00
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.10.1)
Requirement already satisfied: numpy<1.27.0,>=1.19.5 in /usr/local/lib/python3.10/dist-packages (from scipy) (1.22.4)
Installing collected packages: einops
Successfully installed einops-0.6.1

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

model_id = "tiiuae/falcon-rw-1b"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0}, trust_remote_code=True)

Downloading (…)okenizer_config.json:   0%|          | 0.00/255 [00:00<?, ?B/s]

Downloading (…)olve/main/vocab.json:   0%|          | 0.00/798k [00:00<?, ?B/s]

Downloading (…)olve/main/merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]

Downloading (…)/main/tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]

Downloading (…)cial_tokens_map.json:   0%|          | 0.00/99.0 [00:00<?, ?B/s]

Downloading (…)lve/main/config.json:   0%|          | 0.00/665 [00:00<?, ?B/s]

Downloading (…)/configuration_RW.py:   0%|          | 0.00/2.61k [00:00<?, ?B/s]

A new version of the following files was downloaded from https://huggingface.co/tiiuae/falcon-rw-1b:
- configuration_RW.py
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.

Downloading (…)main/modelling_RW.py:   0%|          | 0.00/47.5k [00:00<?, ?B/s]

A new version of the following files was downloaded from https://huggingface.co/tiiuae/falcon-rw-1b:
- modelling_RW.py
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.

from peft import prepare_model_for_kbit_training

model.gradient_checkpointing_enable()
model = prepare_model_for_kbit_training(model)

def print_trainable_parameters(model):
    """
    Prints the number of trainable parameters in the model.
    """
    trainable_params = 0
    all_param = 0
    for _, param in model.named_parameters():
        all_param += param.numel()
        if param.requires_grad:
            trainable_params += param.numel()
    print(
        f"trainable params: {trainable_params} || all params: {all_param} || trainable%: {100 * trainable_params / all_param}"
    )

from peft import LoraConfig, get_peft_model

config = LoraConfig(
    r=8, 
    lora_alpha=32, 
    target_modules=["query_key_value"], 
    lora_dropout=0.05, 
    bias="none", 
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, config)
print_trainable_parameters(model)

trainable params: 1572864 || all params: 709218304 || trainable%: 0.22177430998735193

from datasets import load_dataset

data = load_dataset("Abirate/english_quotes")
data = data.map(lambda samples: tokenizer(samples["quote"]), batched=True)

Downloading readme:   0%|          | 0.00/5.55k [00:00<?, ?B/s]

Downloading and preparing dataset json/Abirate--english_quotes to /root/.cache/huggingface/datasets/Abirate___json/Abirate--english_quotes-6e72855d06356857/0.0.0/e347ab1c932092252e717ff3f949105a4dd28b27e842dd53157d2f72e276c2e4...

Downloading data files:   0%|          | 0/1 [00:00<?, ?it/s]

Downloading data:   0%|          | 0.00/647k [00:00<?, ?B/s]

Extracting data files:   0%|          | 0/1 [00:00<?, ?it/s]

Generating train split: 0 examples [00:00, ? examples/s]

Dataset json downloaded and prepared to /root/.cache/huggingface/datasets/Abirate___json/Abirate--english_quotes-6e72855d06356857/0.0.0/e347ab1c932092252e717ff3f949105a4dd28b27e842dd53157d2f72e276c2e4. Subsequent calls will reuse this data.

  0%|          | 0/1 [00:00<?, ?it/s]

Map:   0%|          | 0/2508 [00:00<?, ? examples/s]

import transformers

# needed for gpt-neo-x tokenizer
tokenizer.pad_token = tokenizer.eos_token

output_dir = "outputs"

trainer = transformers.Trainer(
    model=model,
    train_dataset=data["train"],
    args=transformers.TrainingArguments(
        per_device_train_batch_size=1,
        gradient_accumulation_steps=4,
        warmup_steps=2,
        max_steps=10,
        learning_rate=2e-4,
        fp16=True,
        save_strategy="steps",
        save_steps=10,
        logging_steps=1,
        output_dir=output_dir,
        optim="paged_adamw_8bit"
    ),
    data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),
)
model.config.use_cache = False  # silence the warnings. Please re-enable for inference!
trainer.train()
model.save_pretrained(output_dir)

trainer = transformers.Trainer(
    model=model,
    train_dataset=data["train"],
    args=transformers.TrainingArguments(
        per_device_train_batch_size=1,
        gradient_accumulation_steps=4,
        warmup_steps=2,
        max_steps=20,
        learning_rate=2e-4,
        fp16=True,
        save_strategy="steps",
        save_steps=10,
        logging_steps=1,
        output_dir=output_dir,
        optim="paged_adamw_8bit"
    ),
    data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),
)
model.config.use_cache = False  # silence the warnings. Please re-enable for inference!
trainer.train(resume_from_checkpoint=True)
model.save_pretrained(output_dir)

Step	Training Loss
1	0.731600
2	1.149000
3	1.536000
4	1.427500
5	1.641700
6	1.081500
7	1.240100
8	0.954100
9	2.529200
10	2.134600

Step	Training Loss
11	2.117700
12	1.080800
13	2.490300
14	0.907400
15	2.219700
16	1.970600
17	2.352100
18	0.951000
19	0.715600
20	1.328000