RaiBP/gpt2-openwebtext2-first-30-chunks-ablation-full

TORCH_CPP_LOG_LEVEL=INFO NCCL_DEBUG=INFO CUDA_VISIBLE_DEVICES=0,1 nohup python -m torch.distributed.launch \
--nproc_per_node=2 run_clm.py --output_dir="./training_full" \
--model_type="gpt2" \
--config_name="./training" \
--tokenizer_name="./training" \
--dataset_name="RaiBP/openwebtext2-first-30-chunks-ablation-full" \
--do_train \
--per_device_train_batch_size 8 \
--block_size="1024" \
--learning_rate="5e-3" --warmup_steps="1000" \
--adam_beta1="0.9" --adam_beta2="0.98" --weight_decay="0.01" \
--overwrite_output_dir \
--num_train_epochs="1" \
--logging_steps="500" \
--save_steps="5000" --preprocessing_num_workers="16" \
--gradient_accumulation_steps="4" --report_to="tensorboard" \
--logging_dir="./log_full"  > command_full_log.log 2>&1 &

import numpy as np
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
from tqdm import tqdm
import random

# Set the seed for reproducibility
random.seed(42)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Load the model
model_name = "RaiBP/gpt2-openwebtext2-first-30-chunks-ablation-full"
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_name)

target_language_dataset = "20231101.de" # change here for other languages

dataset = load_dataset("wikimedia/wikipedia", target_language_dataset, split="train")
num_examples = 2000
random_numbers = list(np.random.randint(0, len(dataset), num_examples))
examples = []
for i in tqdm(random_numbers):
    examples.append(dataset[int(i)]["text"])
encodings = tokenizer("\n\n".join(examples), return_tensors="pt")

max_length = model.config.n_positions
stride = 512
seq_len = encodings.input_ids.size(1)

nlls = []
prev_end_loc = 0
for begin_loc in tqdm(range(0, seq_len, stride)):
    end_loc = min(begin_loc + max_length, seq_len)
    trg_len = end_loc - prev_end_loc  # may be different from stride on last loop
    input_ids = encodings.input_ids[:, begin_loc:end_loc].to(device)
    target_ids = input_ids.clone()
    target_ids[:, :-trg_len] = -100

    with torch.no_grad():
        outputs = model(input_ids, labels=target_ids)

        # loss is calculated using CrossEntropyLoss which averages over valid labels
        # N.B. the model only calculates loss over trg_len - 1 labels, because it internally shifts the labels
        # to the left by 1.
        neg_log_likelihood = outputs.loss

    nlls.append(neg_log_likelihood)

    prev_end_loc = end_loc
    if end_loc == seq_len:
        break

ppl = torch.exp(torch.stack(nlls).mean())

print("Perplexity: ", ppl.item())