/content/wandb/run-20220815_183650-1vg0u8vz"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "| Epoch | \n", + "Training Loss | \n", + "Validation Loss | \n", + "Rouge1 | \n", + "Rouge2 | \n", + "Rougel | \n", + "Rougelsum | \n", + "Gen Len | \n", + "
|---|---|---|---|---|---|---|---|
| 0 | \n", + "1.383300 | \n", + "1.474443 | \n", + "53.272800 | \n", + "28.590700 | \n", + "43.989100 | \n", + "48.679700 | \n", + "25.975600 | \n", + "
| 1 | \n", + "1.076200 | \n", + "1.424853 | \n", + "54.429300 | \n", + "29.312500 | \n", + "44.662600 | \n", + "50.003100 | \n", + "30.932800 | \n", + "
| 2 | \n", + "0.855500 | \n", + "1.471171 | \n", + "54.421100 | \n", + "29.536100 | \n", + "45.117600 | \n", + "50.065900 | \n", + "30.431500 | \n", + "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-500/special_tokens_map.json\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-1000\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-1000/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-1000/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-1000/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-1000/special_tokens_map.json\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-1500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-1500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-1500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-1500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-1500/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-500] due to args.save_total_limit\n",
+ "The following columns in the evaluation set don't have a corresponding argument in `BartForConditionalGeneration.forward` and have been ignored: id, dialogue, summary. If id, dialogue, summary are not expected by `BartForConditionalGeneration.forward`, you can safely ignore this message.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 818\n",
+ " Batch size = 4\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-2000\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-2000/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-2000/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-2000/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-2000/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-1000] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-2500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-2500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-2500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-2500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-2500/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-1500] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-3000\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-3000/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-3000/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-3000/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-3000/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-2000] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-3500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-3500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-3500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-3500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-3500/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-2500] due to args.save_total_limit\n",
+ "The following columns in the evaluation set don't have a corresponding argument in `BartForConditionalGeneration.forward` and have been ignored: id, dialogue, summary. If id, dialogue, summary are not expected by `BartForConditionalGeneration.forward`, you can safely ignore this message.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 818\n",
+ " Batch size = 4\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-4000\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-4000/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-4000/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-4000/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-4000/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-3000] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-4500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-4500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-4500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-4500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-4500/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-3500] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-5000\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-5000/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-5000/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-5000/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-5000/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-4000] due to args.save_total_limit\n",
+ "Saving model checkpoint to test-dialogue-summarization/checkpoint-5500\n",
+ "Configuration saved in test-dialogue-summarization/checkpoint-5500/config.json\n",
+ "Model weights saved in test-dialogue-summarization/checkpoint-5500/pytorch_model.bin\n",
+ "tokenizer config file saved in test-dialogue-summarization/checkpoint-5500/tokenizer_config.json\n",
+ "Special tokens file saved in test-dialogue-summarization/checkpoint-5500/special_tokens_map.json\n",
+ "Deleting older checkpoint [test-dialogue-summarization/checkpoint-4500] due to args.save_total_limit\n",
+ "The following columns in the evaluation set don't have a corresponding argument in `BartForConditionalGeneration.forward` and have been ignored: id, dialogue, summary. If id, dialogue, summary are not expected by `BartForConditionalGeneration.forward`, you can safely ignore this message.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 818\n",
+ " Batch size = 4\n",
+ "\n",
+ "\n",
+ "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "TrainOutput(global_step=5523, training_loss=1.1176997911189748, metrics={'train_runtime': 4282.7561, 'train_samples_per_second': 10.32, 'train_steps_per_second': 1.29, 'total_flos': 2.609612124409037e+16, 'train_loss': 1.1176997911189748, 'epoch': 3.0})"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 16
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "ceEjkJM0b0FS",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 300
+ },
+ "outputId": "029236fd-a28f-4e64-d396-11913936ace5"
+ },
+ "source": [
+ "trainer.evaluate()"
+ ],
+ "execution_count": 17,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "The following columns in the evaluation set don't have a corresponding argument in `BartForConditionalGeneration.forward` and have been ignored: id, dialogue, summary. If id, dialogue, summary are not expected by `BartForConditionalGeneration.forward`, you can safely ignore this message.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 818\n",
+ " Batch size = 4\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Run history:
eval/gen_len ▁█▇▇ eval/loss █▁██ eval/rouge1 ▁███ eval/rouge2 ▁▆██ eval/rougeL ▁▅██ eval/rougeLsum ▁███ eval/runtime ▁███ eval/samples_per_second █▁▁▁ eval/steps_per_second █▁▁▁ train/epoch ▁▂▂▃▃▄▄▅▅▆▇▇████ train/global_step ▁▂▂▃▃▄▄▅▅▆▇▇████ train/learning_rate █▇▇▆▅▅▄▃▂▂▁ train/loss █▇▆▅▃▃▃▂▁▁▁ train/total_flos ▁ train/train_loss ▁ train/train_runtime ▁ train/train_samples_per_second ▁ train/train_steps_per_second ▁ Run summary:
eval/gen_len 30.4315 eval/loss 1.47117 eval/rouge1 54.4211 eval/rouge2 29.5361 eval/rougeL 45.1176 eval/rougeLsum 50.0659 eval/runtime 238.6829 eval/samples_per_second 3.427 eval/steps_per_second 0.859 train/epoch 3.0 train/global_step 5523 train/learning_rate 0.0 train/loss 0.8555 train/total_flos 2.609612124409037e+16 train/train_loss 1.1177 train/train_runtime 4282.7561 train/train_samples_per_second 10.32 train/train_steps_per_second 1.29
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "./wandb/run-20220815_183650-1vg0u8vz/logs"
+ ]
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from huggingface_hub import notebook_login"
+ ],
+ "metadata": {
+ "id": "rNHeK_85Hexx"
+ },
+ "execution_count": 22,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "notebook_login()"
+ ],
+ "metadata": {
+ "id": "SqajLxR6He6b",
+ "outputId": "1f697656-747b-4fbc-8c2a-7d3e742d83d9",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 327,
+ "referenced_widgets": [
+ "e8bcdcb3fde44602b14b56bee31640a8",
+ "ff5fb4f3e88945519acd3ddabbab6fe3",
+ "01e39f0a1fc5451abacc189f239c62b1",
+ "1208a58cdf7441ab8c2f37f863c45174",
+ "2af0897110a248faaf4c8d1531b903cb",
+ "c5b389df71ac4078855de4d82ffc2905",
+ "5a46713386054278837116c2bf6a9877",
+ "de6dd8f1aed145fca0495e4fbc5acb39",
+ "6602e0387799434ab6349cc169e349b6",
+ "8f59442ac94f405bbf4b1939e4ef293c",
+ "a4fca7d79c394ef7ade2a833bde4ed36",
+ "e29b722358444c75a9e5e895105f203e",
+ "c02f97f6b7154078a9552497fc451390",
+ "1a125fda3f0c4c4ea41ba62e4299d6c9"
+ ]
+ }
+ },
+ "execution_count": 23,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Login successful\n",
+ "Your token has been saved to /root/.huggingface/token\n",
+ "\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
+ "You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
+ "\n",
+ "git config --global credential.helper store\u001b[0m\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "model.push_to_hub(\"clyde\")"
+ ],
+ "metadata": {
+ "id": "-FgslojBJ0c5",
+ "outputId": "0f9908ba-4749-4dce-9569-c217a3ffe13d",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 404,
+ "referenced_widgets": [
+ "a7cf6106216141b88b20cd1ef7695d11",
+ "c9b6054279e04ba5866749631b22782f",
+ "2724838e7f724941854ea149c677cd26",
+ "6dd8ce3664874c5892aab35df099171a",
+ "9e2e77dfa6074f62af0b0c1d07ef467f",
+ "22e028cc89c24f5383b5abcbdc09d119",
+ "fecb2bd873824af589bffa701c10048e",
+ "755dd21c708545628d8fa9e048fdaed0",
+ "de136514cc23460b85eb59c2b1bffe7c",
+ "190ab6d43a0241bab3b2b80d517e4868",
+ "bb3cc478330445e4b223d8b38c43b438",
+ "4bcebaf0444543f4ace87f218b4d94e5",
+ "ea38305f9ee04bdbaae396d86eaa545d",
+ "aef9c132cd29404f9c03e747c15805d5",
+ "2105bb9ed09e4f028d3a81a76455d8a8",
+ "07a033bd8a7e46d68e6e73b7dfdf472d",
+ "5923d73cb86b42098d9a4035db682cdf",
+ "f86bd7533adb42899e644fc7157aef82",
+ "77e3fae31b6c49e2ad47cc58f7583ae3",
+ "9c54334f671144abbcaa97b2a954268a",
+ "40639549cd2549a085b4c8d7df9d9143",
+ "98629ced08e741a2b3fad86ee4ebffc0",
+ "d00906353ff4498cb32ef260e50af75c",
+ "3a45fadea26f43ff92d8f926f3a3d367",
+ "cc74a0c469654102a92bdf2e7e6a2c94",
+ "706756528d5a4ed1ba74392d9acb7178",
+ "3154d9492ca846e7b2a02b8e30a8045a",
+ "cda954cda82c4aa084d3d1a1702951a2",
+ "3ad8a19b66a1431fa8ff505e97f8d96f",
+ "0a5ba573a19144a9b4497fcea36ee932",
+ "b9f8fae54afc456fa0e318aedcddea8e",
+ "222d65e2c7e54fab8c220e26f0d452e9",
+ "b505286b14734c438080036c12f4fdcb",
+ "043fb7b71ed24217a1e8fcc99a7fce88",
+ "6ee461137eba4e88b55c6d620e70d18b",
+ "08cfc01922b643e6ba05e7f1ff698c98",
+ "fccb68c17aa34658bec0b79052971172",
+ "4d29f9bcf16647b9bd902c1b97ae5f61",
+ "3e65ec01943042b7a05048750a3707d0",
+ "d0093af426c74ad1bf06945e6e452c7b",
+ "6e94f90693944effb4b20bcbbb053a9f",
+ "e8a45680d3ef4afdb4d2a38077f9e30a",
+ "7f2c0b39be624c2aa97732efb5806653",
+ "c4266415615b466ca5216f8311e04a75",
+ "615446d5ef5640b49f7155d5f26d5705",
+ "aa57df9b125c49339679de31477b15a2",
+ "fb1358aa45f74b519400a3bfb8e18152",
+ "47b1ce9368ee4dbc89a070440b4a49e7",
+ "84f53d18c8764b20a6d8916219f1c64b",
+ "2da0c2d6f1f8418bae6d7a93f1d4e035",
+ "4afef9a3fc24458a80123beef80b58d1",
+ "c4f84ba7cd77435788ab5c07878201ef",
+ "5169f864b8e14e4cb32626cc442dfb19",
+ "63999e902d684f6b823d557bea3e16b5",
+ "3eb6da7f84d64ba7b74ad5ef717a9025"
+ ]
+ }
+ },
+ "execution_count": 43,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Configuration saved in clyde/config.json\n",
+ "Model weights saved in clyde/pytorch_model.bin\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Upload file optimizer.pt: 0%| | 3.33k/3.03G [00:00 main\n",
+ "\n",
+ "WARNING:huggingface_hub.repository:remote: Scanning LFS files for validity, may be slow... \n",
+ "remote: LFS file scan complete. \n",
+ "To https://huggingface.co/Ayoola/clyde\n",
+ " 1cf1d86..7d9a15b main -> main\n",
+ "\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "'https://huggingface.co/Ayoola/clyde/commit/7d9a15bad003beb24e7c06238c5a4857c505538e'"
+ ],
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
+ }
+ },
+ "metadata": {},
+ "execution_count": 43
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ ""
+ ],
+ "metadata": {
+ "id": "QWy8BsqcIB1x"
+ },
+ "execution_count": 24,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000,
+ "referenced_widgets": [
+ "ecb7fc9d07ac44248c795d95cf949231",
+ "f25c9782e4fe46368ccb154ba274c1ec",
+ "b62ea6f0bb3b407f91cec0a6331e7fe4",
+ "59527de736ed40b0986fce03e5a4bfda",
+ "cd7572ef160b4b5fbfa2d85b97a77b09",
+ "0ded7010ea504705ab6e5c9504ec8aed",
+ "c97be7687f6e4112a41f4e1dfd112080",
+ "a6ab1267ae074a5b83d5f7e938d28b45",
+ "1bb48d1406a24252ae8fb7822459475b",
+ "59aec02001334c419ba620ac4aadab1b",
+ "7285bc26557a43cc9377db331638e51f",
+ "7bbdc485cd3849c28a368821325cdbe5",
+ "86f4deead37547ccbced6089224b29f8",
+ "cc4e47b701394aa9b7f1c70f98fd8157",
+ "cfb7f94663ac4124b799a90223563ba2",
+ "6a050fd4b84e4c119fe6e887ed8c0eb6",
+ "b096fc4aa1d9428aaa5937f112efa924",
+ "4ab2bc00ab9b463895fa2b084e0d99c2",
+ "53bfbfd5a8f74f1c9246022b8363cf0d",
+ "67b9fb90c100467f9455472b4f81215a",
+ "6d438bc44c544e708d2b19521be04f24",
+ "85a0fd0c27f547919426a1c358c0178c",
+ "b6098cff9a5b431aa82b859082616d37",
+ "4084228fe2854cafa3d69a2d88e4287b",
+ "ee80c0d34c9642c08639043c844cdd63",
+ "44d1a1ab883c4c17a310dc14047cb79b",
+ "7f48b60e5a5c406d86ef06f2a2b478ba",
+ "936bf243d8834d0db8cb1e07208c7bce",
+ "c0d68052f38343df98f26013848588e4",
+ "e7866bbac2704a6e9b9924a282fc9dbf",
+ "4e9389fe6d9b49a89e30084bf918cc18",
+ "bfa3df1dd10f4a2781c48bc49affa4ea",
+ "14c0035a91384122b47d13ea1b2c1890",
+ "318676b785f04b1caf87c9cd5b4b2e63",
+ "b99cec46a1ce4cbd87f0e1fd0cf37f62",
+ "1dff21769676463ca66920e3b33279a0",
+ "4c046bf10f6c404ba36f26e106516b26",
+ "468d382a98b145238a3a3ef064f48fcc",
+ "74a7e17a1f3d4590a81cf26c40aa678b",
+ "43632cb67cad4613bfc6a81ab51a02c7",
+ "eee0dc645376472086c5e8eb55148661",
+ "7613573a4d7645eeaad8124149a7b6be",
+ "a200630b98b44eb7b4d3cab51f0d9d45",
+ "51072b54beb44e51941a52a9075fa455"
+ ]
+ },
+ "id": "JPEM-oeaq6Ka",
+ "outputId": "24afe383-1669-4910-ca96-e004b3fa3978"
+ },
+ "source": [
+ "from transformers import pipeline\n",
+ "\n",
+ "summarizer = pipeline(\"summarization\", model=\"Ayoola/clyde\")\n",
+ "conversation = '''che: Hey, have you built the model?\n",
+ "Ayo: Lemme check\n",
+ "Ayo: Sorry, i have not.\n",
+ "Ayo: I will tomorrow\n",
+ "Ayo: i think we need more data\n",
+ "Ayo: but i may be wrong\n",
+ "Ayo: it is just an hypothesis\n",
+ "che: If you say so..\n",
+ "che: i am working converting the transcriptions to the right format\n",
+ "Ayo: Awesome 🙂\n",
+ "che: see you soon\n",
+ "che: Bye\n",
+ "Ayo: Bye bye \n",
+ "'''\n",
+ "summarizer(conversation)"
+ ],
+ "execution_count": 44,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "loading configuration file https://huggingface.co/Ayoola/clyde/resolve/main/config.json from cache at /root/.cache/huggingface/transformers/3925684a81d704d784ffab4bdb4097fcb08c20930badd3337c07782d0eb5d666.9b8c0031ba05106ba501a98678111e6eb1447b983b16dfba9960cba29742333d\n",
+ "Model config BartConfig {\n",
+ " \"_name_or_path\": \"Ayoola/clyde\",\n",
+ " \"_num_labels\": 3,\n",
+ " \"activation_dropout\": 0.0,\n",
+ " \"activation_function\": \"gelu\",\n",
+ " \"add_bias_logits\": false,\n",
+ " \"add_final_layer_norm\": false,\n",
+ " \"architectures\": [\n",
+ " \"BartForConditionalGeneration\"\n",
+ " ],\n",
+ " \"attention_dropout\": 0.0,\n",
+ " \"bos_token_id\": 0,\n",
+ " \"classif_dropout\": 0.0,\n",
+ " \"classifier_dropout\": 0.0,\n",
+ " \"d_model\": 1024,\n",
+ " \"decoder_attention_heads\": 16,\n",
+ " \"decoder_ffn_dim\": 4096,\n",
+ " \"decoder_layerdrop\": 0.0,\n",
+ " \"decoder_layers\": 12,\n",
+ " \"decoder_start_token_id\": 2,\n",
+ " \"dropout\": 0.1,\n",
+ " \"early_stopping\": true,\n",
+ " \"encoder_attention_heads\": 16,\n",
+ " \"encoder_ffn_dim\": 4096,\n",
+ " \"encoder_layerdrop\": 0.0,\n",
+ " \"encoder_layers\": 12,\n",
+ " \"eos_token_id\": 2,\n",
+ " \"eos_token_ids\": [\n",
+ " 2\n",
+ " ],\n",
+ " \"forced_eos_token_id\": 2,\n",
+ " \"gradient_checkpointing\": false,\n",
+ " \"id2label\": {\n",
+ " \"0\": \"LABEL_0\",\n",
+ " \"1\": \"LABEL_1\",\n",
+ " \"2\": \"LABEL_2\"\n",
+ " },\n",
+ " \"init_std\": 0.02,\n",
+ " \"is_encoder_decoder\": true,\n",
+ " \"label2id\": {\n",
+ " \"LABEL_0\": 0,\n",
+ " \"LABEL_1\": 1,\n",
+ " \"LABEL_2\": 2\n",
+ " },\n",
+ " \"max_length\": 62,\n",
+ " \"max_position_embeddings\": 1024,\n",
+ " \"min_length\": 11,\n",
+ " \"model_type\": \"bart\",\n",
+ " \"no_repeat_ngram_size\": 3,\n",
+ " \"normalize_before\": false,\n",
+ " \"normalize_embedding\": true,\n",
+ " \"num_beams\": 6,\n",
+ " \"num_hidden_layers\": 12,\n",
+ " \"output_past\": true,\n",
+ " \"pad_token_id\": 1,\n",
+ " \"prefix\": \" \",\n",
+ " \"replacing_rate\": 0,\n",
+ " \"scale_embedding\": false,\n",
+ " \"static_position_embeddings\": false,\n",
+ " \"student_decoder_layers\": null,\n",
+ " \"student_encoder_layers\": null,\n",
+ " \"task_specific_params\": {},\n",
+ " \"torch_dtype\": \"float32\",\n",
+ " \"transformers_version\": \"4.21.1\",\n",
+ " \"use_cache\": true,\n",
+ " \"vocab_size\": 50264\n",
+ "}\n",
+ "\n",
+ "loading configuration file https://huggingface.co/Ayoola/clyde/resolve/main/config.json from cache at /root/.cache/huggingface/transformers/3925684a81d704d784ffab4bdb4097fcb08c20930badd3337c07782d0eb5d666.9b8c0031ba05106ba501a98678111e6eb1447b983b16dfba9960cba29742333d\n",
+ "Model config BartConfig {\n",
+ " \"_name_or_path\": \"Ayoola/clyde\",\n",
+ " \"_num_labels\": 3,\n",
+ " \"activation_dropout\": 0.0,\n",
+ " \"activation_function\": \"gelu\",\n",
+ " \"add_bias_logits\": false,\n",
+ " \"add_final_layer_norm\": false,\n",
+ " \"architectures\": [\n",
+ " \"BartForConditionalGeneration\"\n",
+ " ],\n",
+ " \"attention_dropout\": 0.0,\n",
+ " \"bos_token_id\": 0,\n",
+ " \"classif_dropout\": 0.0,\n",
+ " \"classifier_dropout\": 0.0,\n",
+ " \"d_model\": 1024,\n",
+ " \"decoder_attention_heads\": 16,\n",
+ " \"decoder_ffn_dim\": 4096,\n",
+ " \"decoder_layerdrop\": 0.0,\n",
+ " \"decoder_layers\": 12,\n",
+ " \"decoder_start_token_id\": 2,\n",
+ " \"dropout\": 0.1,\n",
+ " \"early_stopping\": true,\n",
+ " \"encoder_attention_heads\": 16,\n",
+ " \"encoder_ffn_dim\": 4096,\n",
+ " \"encoder_layerdrop\": 0.0,\n",
+ " \"encoder_layers\": 12,\n",
+ " \"eos_token_id\": 2,\n",
+ " \"eos_token_ids\": [\n",
+ " 2\n",
+ " ],\n",
+ " \"forced_eos_token_id\": 2,\n",
+ " \"gradient_checkpointing\": false,\n",
+ " \"id2label\": {\n",
+ " \"0\": \"LABEL_0\",\n",
+ " \"1\": \"LABEL_1\",\n",
+ " \"2\": \"LABEL_2\"\n",
+ " },\n",
+ " \"init_std\": 0.02,\n",
+ " \"is_encoder_decoder\": true,\n",
+ " \"label2id\": {\n",
+ " \"LABEL_0\": 0,\n",
+ " \"LABEL_1\": 1,\n",
+ " \"LABEL_2\": 2\n",
+ " },\n",
+ " \"max_length\": 62,\n",
+ " \"max_position_embeddings\": 1024,\n",
+ " \"min_length\": 11,\n",
+ " \"model_type\": \"bart\",\n",
+ " \"no_repeat_ngram_size\": 3,\n",
+ " \"normalize_before\": false,\n",
+ " \"normalize_embedding\": true,\n",
+ " \"num_beams\": 6,\n",
+ " \"num_hidden_layers\": 12,\n",
+ " \"output_past\": true,\n",
+ " \"pad_token_id\": 1,\n",
+ " \"prefix\": \" \",\n",
+ " \"replacing_rate\": 0,\n",
+ " \"scale_embedding\": false,\n",
+ " \"static_position_embeddings\": false,\n",
+ " \"student_decoder_layers\": null,\n",
+ " \"student_encoder_layers\": null,\n",
+ " \"task_specific_params\": {},\n",
+ " \"torch_dtype\": \"float32\",\n",
+ " \"transformers_version\": \"4.21.1\",\n",
+ " \"use_cache\": true,\n",
+ " \"vocab_size\": 50264\n",
+ "}\n",
+ "\n",
+ "loading weights file https://huggingface.co/Ayoola/clyde/resolve/main/pytorch_model.bin from cache at /root/.cache/huggingface/transformers/6974d0c32a3900e59ce81fe93488da86351c060548f66b355dfce8572b0616e3.d4e32efdf3309375c2f467e1288a2d31e8e14e1cb021c70a255d59c8dc532c47\n",
+ "All model checkpoint weights were used when initializing BartForConditionalGeneration.\n",
+ "\n",
+ "All the weights of BartForConditionalGeneration were initialized from the model checkpoint at Ayoola/clyde.\n",
+ "If your task is similar to the task the model of the checkpoint was trained on, you can already use BartForConditionalGeneration for predictions without further training.\n",
+ "https://huggingface.co/Ayoola/clyde/resolve/main/tokenizer_config.json not found in cache or force_download set to True, downloading to /root/.cache/huggingface/transformers/tmpt4776gsd\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading tokenizer_config.json: 0%| | 0.00/390 [00:00