{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":8587424,"sourceType":"datasetVersion","datasetId":5135632}],"dockerImageVersionId":30716,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"from transformers import (\n    AutoModelForSeq2SeqLM,\n    AutoTokenizer,\n    DataCollatorForSeq2Seq,\n    Seq2SeqTrainer,\n    Seq2SeqTrainingArguments,\n    pipeline,\n)\n\nfrom datasets import load_dataset\n\nmodel_name = \"google/umt5-small\"","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:18:55.032642Z","iopub.execute_input":"2024-06-03T11:18:55.033345Z","iopub.status.idle":"2024-06-03T11:19:13.773777Z","shell.execute_reply.started":"2024-06-03T11:18:55.033313Z","shell.execute_reply":"2024-06-03T11:19:13.772989Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stderr","text":"2024-06-03 11:19:02.256736: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n2024-06-03 11:19:02.256864: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n2024-06-03 11:19:02.368948: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"}]},{"cell_type":"code","source":"dataset = load_dataset('csv', data_files='/kaggle/input/ngl-data/nlg_data.csv', split='train').train_test_split(test_size=0.1)\ndataset","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:19:13.775364Z","iopub.execute_input":"2024-06-03T11:19:13.775904Z","iopub.status.idle":"2024-06-03T11:19:14.356839Z","shell.execute_reply.started":"2024-06-03T11:19:13.775878Z","shell.execute_reply":"2024-06-03T11:19:14.355976Z"},"trusted":true},"execution_count":2,"outputs":[{"output_type":"display_data","data":{"text/plain":"Generating train split: 0 examples [00:00, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"fdd37b65a44d42b2931bdc0db8229fa7"}},"metadata":{}},{"execution_count":2,"output_type":"execute_result","data":{"text/plain":"DatasetDict({\n    train: Dataset({\n        features: ['mr', 'ref'],\n        num_rows: 18564\n    })\n    test: Dataset({\n        features: ['mr', 'ref'],\n        num_rows: 2063\n    })\n})"},"metadata":{}}]},{"cell_type":"code","source":"tokenizer = AutoTokenizer.from_pretrained(model_name)\n\n\ndef tokenize_samples(samples):\n    inputs = [f\"generate text: {mr}\" for mr in samples[\"mr\"]]\n\n    tokenized_inputs = tokenizer(\n        inputs,\n        max_length=128,\n        padding=\"max_length\",\n        truncation=True,\n    )\n\n    labels = tokenizer(\n        text_target=samples[\"ref\"],\n        max_length=128,\n        padding=\"max_length\",\n        truncation=True,\n    )\n\n    labels[\"input_ids\"] = [\n        [\n            (token_id if token_id != tokenizer.pad_token_id else -100)\n            for token_id in label\n        ]\n        for label in labels[\"input_ids\"]\n    ]\n\n    tokenized_inputs[\"labels\"] = labels[\"input_ids\"]\n    return tokenized_inputs\n\n\ntokenized_dataset = dataset.map(\n    tokenize_samples,\n    batched=True,\n    remove_columns=[\"mr\", \"ref\"],\n)\n\ntokenized_dataset","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:19:14.357803Z","iopub.execute_input":"2024-06-03T11:19:14.358052Z","iopub.status.idle":"2024-06-03T11:19:24.614600Z","shell.execute_reply.started":"2024-06-03T11:19:14.358030Z","shell.execute_reply":"2024-06-03T11:19:24.613696Z"},"trusted":true},"execution_count":3,"outputs":[{"output_type":"display_data","data":{"text/plain":"tokenizer_config.json:   0%|          | 0.00/6.84k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"9418d01ad2124c74bcd05cc4d41b9b1d"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"spiece.model:   0%|          | 0.00/4.55M [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"935f78ee0b3148929c9c0e022d590930"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"tokenizer.json:   0%|          | 0.00/16.9M [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"7eed04b1f7464253aa0be410233d4be2"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"special_tokens_map.json:   0%|          | 0.00/6.62k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"2d97cb1699b64507a746e6ca305e5dc9"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Map:   0%|          | 0/18564 [00:00<?, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"c01c194e06124c7098a0488f52459b65"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Map:   0%|          | 0/2063 [00:00<?, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"c0281a7c463d4b01aad30fb53bb116a3"}},"metadata":{}},{"execution_count":3,"output_type":"execute_result","data":{"text/plain":"DatasetDict({\n    train: Dataset({\n        features: ['input_ids', 'attention_mask', 'labels'],\n        num_rows: 18564\n    })\n    test: Dataset({\n        features: ['input_ids', 'attention_mask', 'labels'],\n        num_rows: 2063\n    })\n})"},"metadata":{}}]},{"cell_type":"code","source":"model = AutoModelForSeq2SeqLM.from_pretrained(model_name)\ndata_collator = DataCollatorForSeq2Seq(tokenizer, model=model, label_pad_token_id=-100, pad_to_multiple_of=8)","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:19:24.617326Z","iopub.execute_input":"2024-06-03T11:19:24.617755Z","iopub.status.idle":"2024-06-03T11:19:32.668136Z","shell.execute_reply.started":"2024-06-03T11:19:24.617722Z","shell.execute_reply":"2024-06-03T11:19:32.667368Z"},"trusted":true},"execution_count":4,"outputs":[{"output_type":"display_data","data":{"text/plain":"config.json:   0%|          | 0.00/771 [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"e47f1b3962e1476a92d6a882cb4c6a29"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"pytorch_model.bin:   0%|          | 0.00/1.23G [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"b37a692087264ab695bf1523f9e17d18"}},"metadata":{}},{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()\n  return self.fget.__get__(instance, owner)()\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"generation_config.json:   0%|          | 0.00/171 [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bc2f8a03813c447cb86c287ea44fdefe"}},"metadata":{}}]},{"cell_type":"code","source":"training_args = Seq2SeqTrainingArguments(\n    output_dir=\"/kaggle/working\",\n    per_device_train_batch_size=8,\n    per_device_eval_batch_size=16,\n    predict_with_generate=True,\n    learning_rate=5e-5,\n    num_train_epochs=3,\n    evaluation_strategy=\"epoch\",\n    save_strategy=\"epoch\",\n    save_total_limit=1,\n    load_best_model_at_end=True,\n)\n\ntrainer = Seq2SeqTrainer(\n    model=model,\n    args=training_args,\n    data_collator=data_collator,\n    train_dataset=tokenized_dataset[\"train\"],\n    eval_dataset=tokenized_dataset[\"test\"],\n)","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:19:32.669304Z","iopub.execute_input":"2024-06-03T11:19:32.669593Z","iopub.status.idle":"2024-06-03T11:19:33.908748Z","shell.execute_reply.started":"2024-06-03T11:19:32.669569Z","shell.execute_reply":"2024-06-03T11:19:33.907938Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1474: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead\n  warnings.warn(\n","output_type":"stream"}]},{"cell_type":"code","source":"trainer.train()","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:19:33.910001Z","iopub.execute_input":"2024-06-03T11:19:33.910359Z","iopub.status.idle":"2024-06-03T11:58:53.889473Z","shell.execute_reply.started":"2024-06-03T11:19:33.910324Z","shell.execute_reply":"2024-06-03T11:58:53.888465Z"},"trusted":true},"execution_count":6,"outputs":[{"name":"stderr","text":"\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.\n\u001b[34m\u001b[1mwandb\u001b[0m: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server)\n\u001b[34m\u001b[1mwandb\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize\n\u001b[34m\u001b[1mwandb\u001b[0m: Paste an API key from your profile and hit enter, or press ctrl+c to quit:","output_type":"stream"},{"output_type":"stream","name":"stdin","text":"  ········································\n"},{"name":"stderr","text":"\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"Tracking run with wandb version 0.17.0"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"Run data is saved locally in <code>/kaggle/working/wandb/run-20240603_111947-zd4tutif</code>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"Syncing run <strong><a href='https://wandb.ai/filnow42/huggingface/runs/zd4tutif' target=\"_blank\">/kaggle/working</a></strong> to <a href='https://wandb.ai/filnow42/huggingface' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":" View project at <a href='https://wandb.ai/filnow42/huggingface' target=\"_blank\">https://wandb.ai/filnow42/huggingface</a>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":" View run at <a href='https://wandb.ai/filnow42/huggingface/runs/zd4tutif' target=\"_blank\">https://wandb.ai/filnow42/huggingface/runs/zd4tutif</a>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"\n    <div>\n      \n      <progress value='6963' max='6963' style='width:300px; height:20px; vertical-align: middle;'></progress>\n      [6963/6963 38:47, Epoch 3/3]\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    <tr>\n      <td>1</td>\n      <td>0.732900</td>\n      <td>0.331611</td>\n    </tr>\n    <tr>\n      <td>2</td>\n      <td>0.373100</td>\n      <td>0.246366</td>\n    </tr>\n    <tr>\n      <td>3</td>\n      <td>0.326900</td>\n      <td>0.231167</td>\n    </tr>\n  </tbody>\n</table><p>"},"metadata":{}},{"name":"stderr","text":"There were missing keys in the checkpoint model loaded: ['encoder.embed_tokens.weight', 'decoder.embed_tokens.weight'].\n","output_type":"stream"},{"execution_count":6,"output_type":"execute_result","data":{"text/plain":"TrainOutput(global_step=6963, training_loss=1.0388871652717377, metrics={'train_runtime': 2359.6292, 'train_samples_per_second': 23.602, 'train_steps_per_second': 2.951, 'total_flos': 7499132383002624.0, 'train_loss': 1.0388871652717377, 'epoch': 3.0})"},"metadata":{}}]},{"cell_type":"code","source":"nlg = pipeline('summarization', model=model, tokenizer=tokenizer)","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:58:53.891542Z","iopub.execute_input":"2024-06-03T11:58:53.891952Z","iopub.status.idle":"2024-06-03T11:58:53.897775Z","shell.execute_reply.started":"2024-06-03T11:58:53.891924Z","shell.execute_reply":"2024-06-03T11:58:53.896741Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"nlg(f'generate text: dish[tatar], price[50], ingredient[wolowina]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:58:53.898928Z","iopub.execute_input":"2024-06-03T11:58:53.899234Z","iopub.status.idle":"2024-06-03T11:59:05.979970Z","shell.execute_reply.started":"2024-06-03T11:58:53.899195Z","shell.execute_reply":"2024-06-03T11:59:05.978805Z"},"trusted":true},"execution_count":8,"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"'Nie mamy tatar w menu. Cena wynosi 50. Składnik to owoce.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: payment_methods[gotowka], price[150], addresses[ulica Dluga 5]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:05.981291Z","iopub.execute_input":"2024-06-03T11:59:05.981585Z","iopub.status.idle":"2024-06-03T11:59:06.533378Z","shell.execute_reply.started":"2024-06-03T11:59:05.981559Z","shell.execute_reply":"2024-06-03T11:59:06.532379Z"},"trusted":true},"execution_count":9,"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"'Nie obsługujemy płatności gotowka. Cena wynosi 150. Oczywiście, dostarczymy na ulica Dluga 5.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: dish[tiramisu], ingredient[mleko], allergy[laktoza]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:06.537427Z","iopub.execute_input":"2024-06-03T11:59:06.538123Z","iopub.status.idle":"2024-06-03T11:59:06.938435Z","shell.execute_reply.started":"2024-06-03T11:59:06.538081Z","shell.execute_reply":"2024-06-03T11:59:06.937299Z"},"trusted":true},"execution_count":10,"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"'Nie mamy tiramisu w menu. Składnik mleko jest dostępny. Nie zawiera alergenu laktoza.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: time[dziesiata]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:06.939929Z","iopub.execute_input":"2024-06-03T11:59:06.940331Z","iopub.status.idle":"2024-06-03T11:59:07.132913Z","shell.execute_reply.started":"2024-06-03T11:59:06.940292Z","shell.execute_reply":"2024-06-03T11:59:07.131901Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stderr","text":"Your max_length is set to 20, but your input_length is only 10. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=5)\n","output_type":"stream"},{"execution_count":11,"output_type":"execute_result","data":{"text/plain":"'Zamknięte o dziesiata.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: dish[spaghetti], ingredient[ser]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:07.134067Z","iopub.execute_input":"2024-06-03T11:59:07.134671Z","iopub.status.idle":"2024-06-03T11:59:07.405347Z","shell.execute_reply.started":"2024-06-03T11:59:07.134642Z","shell.execute_reply":"2024-06-03T11:59:07.404117Z"},"trusted":true},"execution_count":12,"outputs":[{"name":"stderr","text":"Your max_length is set to 20, but your input_length is only 14. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=7)\n","output_type":"stream"},{"execution_count":12,"output_type":"execute_result","data":{"text/plain":"'Nie mamy spaghetti w menu. Składnik ser jest dostępny.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: dish[pierogi], ingredient[kozi ser]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:07.407270Z","iopub.execute_input":"2024-06-03T11:59:07.410442Z","iopub.status.idle":"2024-06-03T11:59:07.697634Z","shell.execute_reply.started":"2024-06-03T11:59:07.410396Z","shell.execute_reply":"2024-06-03T11:59:07.695355Z"},"trusted":true},"execution_count":13,"outputs":[{"name":"stderr","text":"Your max_length is set to 20, but your input_length is only 16. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=8)\n","output_type":"stream"},{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"'Nie mamy pierogi w menu. Składnik to koti ser.'"},"metadata":{}}]},{"cell_type":"code","source":"nlg(f'generate text: time[23:00], adres[ul Krótka 256]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:07.698906Z","iopub.execute_input":"2024-06-03T11:59:07.699269Z","iopub.status.idle":"2024-06-03T11:59:08.138934Z","shell.execute_reply.started":"2024-06-03T11:59:07.699233Z","shell.execute_reply":"2024-06-03T11:59:08.137833Z"},"trusted":true},"execution_count":14,"outputs":[{"execution_count":14,"output_type":"execute_result","data":{"text/plain":"'Zamknięte o 23:00. Nie dostarczamy na ulica Krótka 256.'"},"metadata":{}}]},{"cell_type":"code","source":"model.save_pretrained(\"/kaggle/working\")","metadata":{"execution":{"iopub.status.busy":"2024-06-03T11:59:08.140399Z","iopub.execute_input":"2024-06-03T11:59:08.140718Z","iopub.status.idle":"2024-06-03T11:59:11.078579Z","shell.execute_reply.started":"2024-06-03T11:59:08.140689Z","shell.execute_reply":"2024-06-03T11:59:11.077378Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"from kaggle_secrets import UserSecretsClient\nuser_secrets = UserSecretsClient()\nsecret_value_0 = user_secrets.get_secret(\"huggingface-write\")","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:03:34.283930Z","iopub.execute_input":"2024-06-03T12:03:34.284674Z","iopub.status.idle":"2024-06-03T12:03:34.468881Z","shell.execute_reply.started":"2024-06-03T12:03:34.284637Z","shell.execute_reply":"2024-06-03T12:03:34.467812Z"},"trusted":true},"execution_count":18,"outputs":[]},{"cell_type":"code","source":"from huggingface_hub import login\nlogin(secret_value_0)","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:03:38.979682Z","iopub.execute_input":"2024-06-03T12:03:38.980042Z","iopub.status.idle":"2024-06-03T12:03:39.119457Z","shell.execute_reply.started":"2024-06-03T12:03:38.980011Z","shell.execute_reply":"2024-06-03T12:03:39.118367Z"},"trusted":true},"execution_count":19,"outputs":[{"name":"stdout","text":"The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\nToken is valid (permission: write).\nYour token has been saved to /root/.cache/huggingface/token\nLogin successful\n","output_type":"stream"}]},{"cell_type":"code","source":"trainer.push_to_hub(\"filnow/nlg-umt5-pol\")","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:03:45.289755Z","iopub.execute_input":"2024-06-03T12:03:45.290131Z","iopub.status.idle":"2024-06-03T12:04:24.555639Z","shell.execute_reply.started":"2024-06-03T12:03:45.290099Z","shell.execute_reply":"2024-06-03T12:04:24.554427Z"},"trusted":true},"execution_count":20,"outputs":[{"output_type":"display_data","data":{"text/plain":"events.out.tfevents.1717413574.743112a2decd.34.0:   0%|          | 0.00/9.10k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bc999b688b0b4163b518f7047380dc7d"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"model.safetensors:   0%|          | 0.00/1.23G [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bbc79a9e89444b41b2df98deeb0b4add"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Upload 3 LFS files:   0%|          | 0/3 [00:00<?, ?it/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bec70bfa21154c47a7680cdc214dd320"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"training_args.bin:   0%|          | 0.00/5.24k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"fc812bdfac0d4fc0ac5bab1590240a73"}},"metadata":{}},{"execution_count":20,"output_type":"execute_result","data":{"text/plain":"CommitInfo(commit_url='https://huggingface.co/filnow/working/commit/72c855645f38e057804135cb1de549ce045e18ea', commit_message='filnow/nlg-umt5-pol', commit_description='', oid='72c855645f38e057804135cb1de549ce045e18ea', pr_url=None, pr_revision=None, pr_num=None)"},"metadata":{}}]},{"cell_type":"code","source":"my_model = AutoModelForSeq2SeqLM.from_pretrained(\"filnow/nlg-umt5-pol\")","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:14:22.428309Z","iopub.execute_input":"2024-06-03T12:14:22.429205Z","iopub.status.idle":"2024-06-03T12:14:44.972041Z","shell.execute_reply.started":"2024-06-03T12:14:22.429157Z","shell.execute_reply":"2024-06-03T12:14:44.970939Z"},"trusted":true},"execution_count":21,"outputs":[{"output_type":"display_data","data":{"text/plain":"config.json:   0%|          | 0.00/859 [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"c0cdb81c53394a9981be4af7cadc1b27"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"model.safetensors:   0%|          | 0.00/1.23G [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"87317339f97b4710b6ca2112bf689984"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"generation_config.json:   0%|          | 0.00/166 [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"25639ec6e2e4415bb5d9d51d1755fc4c"}},"metadata":{}}]},{"cell_type":"code","source":"my_nlg = pipeline('summarization', model=my_model, tokenizer=tokenizer)","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:15:13.703433Z","iopub.execute_input":"2024-06-03T12:15:13.704377Z","iopub.status.idle":"2024-06-03T12:15:13.710676Z","shell.execute_reply.started":"2024-06-03T12:15:13.704327Z","shell.execute_reply":"2024-06-03T12:15:13.709499Z"},"trusted":true},"execution_count":23,"outputs":[]},{"cell_type":"code","source":"my_nlg(f'generate text: time[23:00], adres[ul Krótka 256]')[0]['summary_text']","metadata":{"execution":{"iopub.status.busy":"2024-06-03T12:15:31.134517Z","iopub.execute_input":"2024-06-03T12:15:31.134884Z","iopub.status.idle":"2024-06-03T12:15:32.440573Z","shell.execute_reply.started":"2024-06-03T12:15:31.134855Z","shell.execute_reply":"2024-06-03T12:15:32.439690Z"},"trusted":true},"execution_count":25,"outputs":[{"execution_count":25,"output_type":"execute_result","data":{"text/plain":"'Zamknięte o 23:00. Nie dostarczamy na ulica Krótka 256.'"},"metadata":{}}]}]}