ipft.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "42a0da24-c70a-4b68-8790-7f93e0e37990",
   "metadata": {},
   "outputs": [],
   "source": [
    "pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c595f8f0-2e4a-442b-bde8-b48dfe762355",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4958f755-f0fc-40ca-b8b3-e625811d4d79",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install transformers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8cd636d6-84cf-4d10-826f-258c6e1646d6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting peft\n",
      "  Downloading peft-0.13.2-py3-none-any.whl.metadata (13 kB)\n",
      "Requirement already satisfied: numpy>=1.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (1.24.4)\n",
      "Requirement already satisfied: packaging>=20.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (24.1)\n",
      "Requirement already satisfied: psutil in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (7.2.2)\n",
      "Requirement already satisfied: pyyaml in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (6.0.3)\n",
      "Requirement already satisfied: torch>=1.13.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (2.4.1)\n",
      "Requirement already satisfied: transformers in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (4.46.3)\n",
      "Requirement already satisfied: tqdm in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (4.67.3)\n",
      "Collecting accelerate>=0.21.0 (from peft)\n",
      "  Downloading accelerate-1.0.1-py3-none-any.whl.metadata (19 kB)\n",
      "Requirement already satisfied: safetensors in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (0.5.3)\n",
      "Requirement already satisfied: huggingface-hub>=0.17.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from peft) (0.36.2)\n",
      "Requirement already satisfied: filelock in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from huggingface-hub>=0.17.0->peft) (3.16.1)\n",
      "Requirement already satisfied: fsspec>=2023.5.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from huggingface-hub>=0.17.0->peft) (2024.9.0)\n",
      "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from huggingface-hub>=0.17.0->peft) (1.4.3)\n",
      "Requirement already satisfied: requests in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from huggingface-hub>=0.17.0->peft) (2.32.4)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from huggingface-hub>=0.17.0->peft) (4.13.2)\n",
      "Requirement already satisfied: sympy in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (1.13.3)\n",
      "Requirement already satisfied: networkx in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (3.1)\n",
      "Requirement already satisfied: jinja2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (3.1.6)\n",
      "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.105)\n",
      "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.105)\n",
      "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.105)\n",
      "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (9.1.0.70)\n",
      "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.3.1)\n",
      "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (11.0.2.54)\n",
      "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (10.3.2.106)\n",
      "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (11.4.5.107)\n",
      "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.0.106)\n",
      "Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (2.20.5)\n",
      "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (12.1.105)\n",
      "Requirement already satisfied: triton==3.0.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from torch>=1.13.0->peft) (3.0.0)\n",
      "Requirement already satisfied: nvidia-nvjitlink-cu12 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.13.0->peft) (12.9.86)\n",
      "Requirement already satisfied: regex!=2019.12.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from transformers->peft) (2024.11.6)\n",
      "Requirement already satisfied: tokenizers<0.21,>=0.20 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from transformers->peft) (0.20.3)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from jinja2->torch>=1.13.0->peft) (2.1.5)\n",
      "Requirement already satisfied: charset_normalizer<4,>=2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from requests->huggingface-hub>=0.17.0->peft) (3.4.7)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from requests->huggingface-hub>=0.17.0->peft) (3.13)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from requests->huggingface-hub>=0.17.0->peft) (2.2.3)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from requests->huggingface-hub>=0.17.0->peft) (2026.4.22)\n",
      "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.8/site-packages (from sympy->torch>=1.13.0->peft) (1.3.0)\n",
      "Downloading peft-0.13.2-py3-none-any.whl (320 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m320.7/320.7 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading accelerate-1.0.1-py3-none-any.whl (330 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m330.9/330.9 kB\u001b[0m \u001b[31m48.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25h\u001b[33mDEPRECATION: omegaconf 2.0.6 has a non-standard dependency specifier PyYAML>=5.1.*. pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of omegaconf or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063\u001b[0m\u001b[33m\n",
      "\u001b[0mInstalling collected packages: accelerate, peft\n",
      "Successfully installed accelerate-1.0.1 peft-0.13.2\n",
      "\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.0.1\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install peft"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "42e90884-c40b-46b4-9067-529725bc208d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading local datasets...\n",
      "Tokenizing data...\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3a61e1d780f442bf84f1f07e7297663c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/139266 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "317e41ddb2bc4db8b6ca8fe82b1bf598",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/2404 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9754734338f14749b74c734cb24bf8db",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/1183 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2ed4906d44f54e33b0da8c5a0ef58cfd",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "pytorch_model.bin:   0%|          | 0.00/2.46G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f033726ad0c64c6f876322d4f9dcf501",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "generation_config.json:   0%|          | 0.00/189 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "trainable params: 4,718,592 || all params: 619,792,384 || trainable%: 0.7613\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import os\n",
    "import numpy as np\n",
    "import evaluate\n",
    "from datasets import Dataset, DatasetDict\n",
    "from transformers import (\n",
    "    AutoModelForSeq2SeqLM, \n",
    "    AutoTokenizer, \n",
    "    Seq2SeqTrainingArguments, \n",
    "    Seq2SeqTrainer, \n",
    "    DataCollatorForSeq2Seq\n",
    ")\n",
    "from peft import LoraConfig, get_peft_model, TaskType\n",
    "\n",
    "# ==========================================\n",
    "# 1. DATA LOADING (Local Files)\n",
    "# ==========================================\n",
    "def load_local_data(en_path, mni_path):\n",
    "    if not os.path.exists(en_path) or not os.path.exists(mni_path):\n",
    "        raise FileNotFoundError(f\"Ensure {en_path} and {mni_path} exist in this folder.\")\n",
    "        \n",
    "    with open(en_path, \"r\", encoding=\"utf-8\") as f_en, \\\n",
    "         open(mni_path, \"r\", encoding=\"utf-8\") as f_mni:\n",
    "        en_lines = [l.strip() for l in f_en if l.strip()]\n",
    "        mni_lines = [l.strip() for l in f_mni if l.strip()]\n",
    "    \n",
    "    # Align lengths to prevent index errors\n",
    "    length = min(len(en_lines), len(mni_lines))\n",
    "    return Dataset.from_dict({\n",
    "        \"english\": en_lines[:length], \n",
    "        \"manipuri\": mni_lines[:length]\n",
    "    })\n",
    "\n",
    "print(\"Loading local datasets...\")\n",
    "dataset = DatasetDict({\n",
    "    \"train\": load_local_data(\"data/train.eng_Latn\", \"data/train.mni_Beng\"),\n",
    "    \"validation\": load_local_data(\"data/dev.eng_Latn\", \"data/dev.mni_Beng\"),\n",
    "    \"test\": load_local_data(\"data/test.eng_Latn\", \"data/test.mni_Beng\")\n",
    "})\n",
    "\n",
    "# ==========================================\n",
    "# 2. MODEL & TOKENIZER SETUP\n",
    "# ==========================================\n",
    "model_id = \"facebook/nllb-200-distilled-600M\"\n",
    "# We explicitly set the language tags for NLLB\n",
    "tokenizer = AutoTokenizer.from_pretrained(\n",
    "    model_id, \n",
    "    src_lang=\"eng_Latn\", \n",
    "    tgt_lang=\"mni_Beng\"\n",
    ")\n",
    "\n",
    "def preprocess_function(examples):\n",
    "    model_inputs = tokenizer(\n",
    "        examples[\"english\"], \n",
    "        text_target=examples[\"manipuri\"], \n",
    "        max_length=128, \n",
    "        truncation=True\n",
    "    )\n",
    "    return model_inputs\n",
    "\n",
    "print(\"Tokenizing data...\")\n",
    "tokenized_ds = dataset.map(\n",
    "    preprocess_function, \n",
    "    batched=True, \n",
    "    remove_columns=[\"english\", \"manipuri\"]\n",
    ")\n",
    "\n",
    "# Load model in FP16 to avoid bitsandbytes/quantization issues\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\n",
    "    model_id, \n",
    "    torch_dtype=torch.float16, \n",
    "    device_map=\"auto\"\n",
    ")\n",
    "\n",
    "# LSFTL Framework: Low-Rank Adaptation (LoRA)\n",
    "peft_config = LoraConfig(\n",
    "    task_type=TaskType.SEQ_2_SEQ_LM,\n",
    "    r=16, \n",
    "    lora_alpha=32, \n",
    "    target_modules=[\"q_proj\", \"v_proj\", \"k_proj\", \"out_proj\"],\n",
    "    lora_dropout=0.05\n",
    ")\n",
    "model = get_peft_model(model, peft_config)\n",
    "model.print_trainable_parameters()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "651bce1c-34e5-4951-b887-4d114bbecd10",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf6a71f5-a65e-4884-84c5-02f35b3ff47d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2bac2437-48f1-401f-ba6a-c7b5152c45b4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c6fded3a5ffb4343a3495b31194f18a2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading builder script: 0.00B [00:00, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/zeus/miniconda3/envs/cloudspace/lib/python3.8/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead\n",
      "  warnings.warn(\n",
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
      "/tmp/ipykernel_4611/2745601905.py:45: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.\n",
      "  trainer = Seq2SeqTrainer(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Starting Fine-tuning...\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      \n",
       "      <progress value='86' max='26112' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      [   86/26112 01:35 < 8:10:42, 0.88 it/s, Epoch 0.01/3]\n",
       "    </div>\n",
       "    <table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       " <tr style=\"text-align: left;\">\n",
       "      <th>Epoch</th>\n",
       "      <th>Training Loss</th>\n",
       "      <th>Validation Loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table><p>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# ==========================================\n",
    "# 3. METRIC CALCULATION (SacreBLEU)\n",
    "# ==========================================\n",
    "metric = evaluate.load(\"sacrebleu\")\n",
    "\n",
    "def compute_metrics(eval_preds):\n",
    "    preds, labels = eval_preds\n",
    "    if isinstance(preds, tuple):\n",
    "        preds = preds[0]\n",
    "    \n",
    "    # Decode predictions\n",
    "    decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)\n",
    "\n",
    "    # Replace -100 (ignored index) in labels\n",
    "    labels = np.where(labels != -100, labels, tokenizer.pad_token_id)\n",
    "    decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)\n",
    "\n",
    "    # Post-processing for SacreBLEU\n",
    "    decoded_preds = [pred.strip() for pred in decoded_preds]\n",
    "    decoded_labels = [[label.strip()] for label in decoded_labels]\n",
    "\n",
    "    result = metric.compute(predictions=decoded_preds, references=decoded_labels)\n",
    "    return {\"bleu\": result[\"score\"]}\n",
    "\n",
    "# ==========================================\n",
    "# 4. TRAINING CONFIGURATION\n",
    "# ==========================================\n",
    "training_args = Seq2SeqTrainingArguments(\n",
    "    output_dir=\"./nllb-mni-lsftl\",\n",
    "    evaluation_strategy=\"epoch\",\n",
    "    save_strategy=\"epoch\",\n",
    "    learning_rate=2e-4,\n",
    "    per_device_train_batch_size=4,\n",
    "    gradient_accumulation_steps=4,\n",
    "    weight_decay=0.01,\n",
    "    num_train_epochs=3,\n",
    "    predict_with_generate=True, # Critical for BLEU calculation\n",
    "    fp16=True,\n",
    "    optim=\"adamw_torch\",       # Forcing standard PyTorch optimizer\n",
    "    logging_steps=10,\n",
    "    save_total_limit=1,\n",
    "    load_best_model_at_end=True\n",
    ")\n",
    "\n",
    "trainer = Seq2SeqTrainer(\n",
    "    model=model,\n",
    "    args=training_args,\n",
    "    train_dataset=tokenized_ds[\"train\"],\n",
    "    eval_dataset=tokenized_ds[\"validation\"],\n",
    "    tokenizer=tokenizer,\n",
    "    data_collator=DataCollatorForSeq2Seq(tokenizer, model=model),\n",
    "    compute_metrics=compute_metrics,\n",
    ")\n",
    "\n",
    "# ==========================================\n",
    "# 5. EXECUTION: TRAIN & TEST\n",
    "# ==========================================\n",
    "print(\"Starting Fine-tuning...\")\n",
    "trainer.train()\n",
    "\n",
    "print(\"\\n--- Final Evaluation on Test Set ---\")\n",
    "test_results = trainer.evaluate(eval_dataset=tokenized_ds[\"test\"])\n",
    "print(f\"Test BLEU Score: {test_results['eval_bleu']:.2f}\")\n",
    "\n",
    "# ==========================================\n",
    "# 6. SAMPLE INFERENCE CHECK\n",
    "# ==========================================\n",
    "print(\"\\n--- Sample Predictions from Test Set ---\")\n",
    "model.eval()\n",
    "mni_id = tokenizer.convert_tokens_to_ids(\"mni_Beng\")\n",
    "\n",
    "for i in range(5):\n",
    "    input_text = dataset[\"test\"][\"english\"][i]\n",
    "    inputs = tokenizer(input_text, return_tensors=\"pt\").to(model.device)\n",
    "    \n",
    "    with torch.no_grad():\n",
    "        generated_tokens = model.generate(\n",
    "            **inputs, \n",
    "            forced_bos_token_id=mni_id, \n",
    "            max_length=128\n",
    "        )\n",
    "    \n",
    "    prediction = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)\n",
    "    reference = dataset[\"test\"][\"manipuri\"][i]\n",
    "    \n",
    "    print(f\"Input: {input_text}\")\n",
    "    print(f\"Pred:  {prediction}\")\n",
    "    print(f\"Truth: {reference}\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4b8abf64-f671-49f6-9fed-006c875a8485",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/teamspace/studios/this_studio'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f4b05fb0-0738-4370-9686-6f1df42314a5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0m\u001b[01;32mcheckpoint1.pt\u001b[0m*   \u001b[01;32mcheckpoint15.pt\u001b[0m*  \u001b[01;32mcheckpoint20.pt\u001b[0m*  \u001b[01;32mcheckpoint8.pt\u001b[0m*\n",
      "\u001b[01;32mcheckpoint10.pt\u001b[0m*  \u001b[01;32mcheckpoint16.pt\u001b[0m*  \u001b[01;32mcheckpoint3.pt\u001b[0m*   \u001b[01;32mcheckpoint9.pt\u001b[0m*\n",
      "\u001b[01;32mcheckpoint11.pt\u001b[0m*  \u001b[01;32mcheckpoint17.pt\u001b[0m*  \u001b[01;32mcheckpoint4.pt\u001b[0m*   \u001b[01;32mcheckpoint_best.pt\u001b[0m*\n",
      "\u001b[01;32mcheckpoint12.pt\u001b[0m*  \u001b[01;32mcheckpoint18.pt\u001b[0m*  \u001b[01;32mcheckpoint5.pt\u001b[0m*   \u001b[01;32mcheckpoint_last.pt\u001b[0m*\n",
      "\u001b[01;32mcheckpoint13.pt\u001b[0m*  \u001b[01;32mcheckpoint19.pt\u001b[0m*  \u001b[01;32mcheckpoint6.pt\u001b[0m*\n",
      "\u001b[01;32mcheckpoint14.pt\u001b[0m*  \u001b[01;32mcheckpoint2.pt\u001b[0m*   \u001b[01;32mcheckpoint7.pt\u001b[0m*\n"
     ]
    }
   ],
   "source": [
    "ls\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5b279caa-ceed-483c-b174-bb3eede61772",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/teamspace/studios/this_studio/checkpoints\n"
     ]
    }
   ],
   "source": [
    "cd checkpoints"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cc0f8abd-63e9-4de0-8c5b-ea9ff61d71c3",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.20"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}