"
],
"text/html": [
"\n",
" \n",
" \n",
"
\n",
" [102/406 2:51:51 < 8:42:26, 0.01 it/s, Epoch 0.25/1]\n",
"
\n",
" \n",
" \n",
" | Step | \n",
" Training Loss | \n",
"
\n",
" \n",
" \n",
" \n",
" | 20 | \n",
" 1.656200 | \n",
"
\n",
" \n",
" | 40 | \n",
" 1.290300 | \n",
"
\n",
" \n",
" | 60 | \n",
" 0.859200 | \n",
"
\n",
" \n",
" | 80 | \n",
" 0.753000 | \n",
"
\n",
" \n",
" | 100 | \n",
" 0.713000 | \n",
"
\n",
" \n",
"
"
]
},
"metadata": {}
},
{
"output_type": "error",
"ename": "KeyboardInterrupt",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 16\u001b[0m )\n\u001b[1;32m 17\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse_cache\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1632\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_inner_training_loop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_train_batch_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mauto_find_batch_size\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1633\u001b[0m )\n\u001b[0;32m-> 1634\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 1635\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1636\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1899\u001b[0m \u001b[0mtr_loss_step\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtraining_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1900\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1901\u001b[0;31m \u001b[0mtr_loss_step\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtraining_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1902\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1903\u001b[0m if (\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtraining_step\u001b[0;34m(self, model, inputs)\u001b[0m\n\u001b[1;32m 2651\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2652\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdo_grad_scaling\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2653\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscaler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscale\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2654\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse_apex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2655\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mamp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscale_loss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptimizer\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mscaled_loss\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/torch/_tensor.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m 486\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 487\u001b[0m )\n\u001b[0;32m--> 488\u001b[0;31m torch.autograd.backward(\n\u001b[0m\u001b[1;32m 489\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 490\u001b[0m )\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m 195\u001b[0m \u001b[0;31m# some Python versions print out the first line of a multi-line function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 196\u001b[0m \u001b[0;31m# calls in the traceback and some print out the last line\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 197\u001b[0;31m Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass\n\u001b[0m\u001b[1;32m 198\u001b[0m \u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgrad_tensors_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 199\u001b[0m allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
]
},
{
"cell_type": "markdown",
"source": [
"> Let's have an insight of our fine tuned Alpaca using Peft"
],
"metadata": {
"id": "NXRgwTDven3t"
}
},
{
"cell_type": "code",
"source": [
"model"
],
"metadata": {
"id": "PH10skP5elzb"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model.save_pretrained(\"lora-alpaca_ar\")"
],
"metadata": {
"id": "_9g0HzA5vsla"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"> Push the adapter to🤗"
],
"metadata": {
"id": "5LN4eg8F2ROK"
}
},
{
"cell_type": "code",
"source": [
"from huggingface_hub import notebook_login\n",
"\n",
"notebook_login()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 331,
"referenced_widgets": [
"d558193dc34240a0a0028c879f9d3a91",
"56e90084a870402ea765c75e59785c33",
"196842b67f6b4451b33916ad1a3f4d54",
"cd6752ed8360412485f27ff74c7dc86c",
"7f6031d9d88f47f0a35093e806c1f51d",
"ce6986c036e84106940c6de7104da2d6",
"b905d63ad7854f5bb5f5027fc73b0a3e",
"4d62895b900846aba9b687a24999bb05",
"b2910f3dbda449d99db9c46331cfb955",
"961ae75617764743a12cb03965bc3e6a",
"0e72536f08d14c80a80fdd685d2be848",
"9379a6e8d7694b988e8b514639c21498",
"43510cb3cdb84281ab5f80214b09fadf",
"9d89147fe1004a369a588f28341c761b",
"d5d6fbcc101e402e9b7882f43beadb87",
"4981580665644cd39a92c99ef460e676",
"edd70dce7d3944d1812057c3650d2c5a"
]
},
"id": "K66O_4Jj2dSG",
"outputId": "48a84d7c-e391-43aa-f6ef-a0f4af02d7bb"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Token is valid.\n",
"Your token has been saved in your configured git credential helpers (store).\n",
"Your token has been saved to /root/.cache/huggingface/token\n",
"Login successful\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model.push_to_hub(\"Yasbok/Alpaca_instruction_fine_tune_Arabic\", use_auth_token=True)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 116,
"referenced_widgets": [
"8b7ad87c92604c2fbbe084a9bcb798cf",
"c8a6a08fb64c40e384a29ef2b8b572d4",
"544fe145cd9f4d16b9e765d4c9fae159",
"85721f7b94a74ddd89d4b76f614f011b",
"85164250cb064eeb800e910d108bff89",
"acb3eaef4ac34e86a994799c106b4321",
"bc9ee26d49ea4b76991a8318dadcb4f9",
"8cc6bca9441a46489edae8f059da4838",
"70ac6f5efd32410caa0a84e57701f15e",
"fdf719ae121c48dcade058669ae65286",
"5a42640e9c23406db8d732677eeeafde",
"3179ba4cdf624e5282d131fbe88e8763",
"24ef46fccd6744958b56fa290d733815",
"6db176d8394942e788f5c58544a91c61",
"34be4197ebff417681e41d4a98418582",
"d732a799f8dd438c946b2385ff431049",
"66622d01018f4c80bd9a910853687136",
"5189de40e84c4e029362c5033aec01bd",
"b563b008da534df5b5604927ae3ac434",
"6b0e98decd6a4875b4bca6fed36aa5ba",
"6e65437ddb264b7999d661b093a7ec9e",
"e6b59602e3834b419a0bcef8cc39a8d9"
]
},
"id": "rrH4zgEDWYgs",
"outputId": "f899bf6f-2f3b-4250-b4ec-ddea8c34f734"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"adapter_model.bin: 0%| | 0.00/16.8M [00:00