| Step | \n", "Training Loss | \n", "
|---|---|
| 1 | \n", "1.823800 | \n", "
| 2 | \n", "2.305700 | \n", "
| 3 | \n", "1.692300 | \n", "
| 4 | \n", "1.947700 | \n", "
| 5 | \n", "1.644000 | \n", "
| 6 | \n", "1.606900 | \n", "
| 7 | \n", "1.193300 | \n", "
| 8 | \n", "1.259600 | \n", "
| 9 | \n", "1.109400 | \n", "
| 10 | \n", "1.165600 | \n", "
| 11 | \n", "0.965400 | \n", "
| 12 | \n", "1.003300 | \n", "
| 13 | \n", "0.935300 | \n", "
| 14 | \n", "1.060800 | \n", "
| 15 | \n", "0.909900 | \n", "
| 16 | \n", "0.911000 | \n", "
| 17 | \n", "1.023900 | \n", "
| 18 | \n", "1.285800 | \n", "
| 19 | \n", "1.012700 | \n", "
| 20 | \n", "0.900200 | \n", "
| 21 | \n", "0.948100 | \n", "
| 22 | \n", "1.020000 | \n", "
| 23 | \n", "0.878700 | \n", "
| 24 | \n", "0.995400 | \n", "
| 25 | \n", "1.059700 | \n", "
| 26 | \n", "1.009600 | \n", "
| 27 | \n", "1.042100 | \n", "
| 28 | \n", "0.868600 | \n", "
| 29 | \n", "0.838100 | \n", "
| 30 | \n", "0.903600 | \n", "
| 31 | \n", "0.863300 | \n", "
| 32 | \n", "0.869000 | \n", "
| 33 | \n", "0.989600 | \n", "
| 34 | \n", "0.871400 | \n", "
| 35 | \n", "0.961300 | \n", "
| 36 | \n", "0.863600 | \n", "
| 37 | \n", "0.893200 | \n", "
| 38 | \n", "0.766200 | \n", "
| 39 | \n", "1.087300 | \n", "
| 40 | \n", "1.161900 | \n", "
| 41 | \n", "0.905700 | \n", "
| 42 | \n", "0.990900 | \n", "
| 43 | \n", "0.962200 | \n", "
| 44 | \n", "0.904800 | \n", "
| 45 | \n", "0.921000 | \n", "
| 46 | \n", "1.002200 | \n", "
| 47 | \n", "0.867700 | \n", "
| 48 | \n", "1.220900 | \n", "
| 49 | \n", "0.915000 | \n", "
| 50 | \n", "1.049000 | \n", "
| 51 | \n", "1.025800 | \n", "
| 52 | \n", "0.927400 | \n", "
| 53 | \n", "1.008100 | \n", "
| 54 | \n", "1.169400 | \n", "
| 55 | \n", "0.798900 | \n", "
| 56 | \n", "1.029200 | \n", "
| 57 | \n", "0.887000 | \n", "
| 58 | \n", "0.830200 | \n", "
| 59 | \n", "0.862500 | \n", "
| 60 | \n", "0.905400 | \n", "
"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"#@title Show final memory and time stats\n",
"used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n",
"used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n",
"used_percentage = round(used_memory /max_memory*100, 3)\n",
"lora_percentage = round(used_memory_for_lora/max_memory*100, 3)\n",
"print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n",
"print(f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\")\n",
"print(f\"Peak reserved memory = {used_memory} GB.\")\n",
"print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n",
"print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n",
"print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")"
],
"metadata": {
"id": "t8sgWPflqPbr",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "91cb1d70-2fba-4381-d8cf-ce7fd744f4ee"
},
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"440.4525 seconds used for training.\n",
"7.34 minutes used for training.\n",
"Peak reserved memory = 8.984 GB.\n",
"Peak reserved memory for training = 3.316 GB.\n",
"Peak reserved memory % of max memory = 60.917 %.\n",
"Peak reserved memory for training % of max memory = 22.484 %.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# alpaca_prompt = Copied from above\n",
"FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n",
"inputs = tokenizer(\n",
"[\n",
" alpaca_prompt.format(\n",
" \"Continue the fibonnaci sequence.\", # instruction\n",
" \"1, 1, 2, 3, 5, 8\", # input\n",
" \"\", # output - leave this blank for generation!\n",
" )\n",
"], return_tensors = \"pt\").to(\"cuda\")\n",
"\n",
"outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)\n",
"tokenizer.batch_decode(outputs)"
],
"metadata": {
"id": "R2bt9cqbqPYu",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "66ea4543-2839-482e-ac33-ae5820460865"
},
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nContinue the fibonnaci sequence.\\n\\n### Input:\\n1, 1, 2, 3, 5, 8\\n\\n### Response:\\n13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025']"
]
},
"metadata": {},
"execution_count": 14
}
]
},
{
"cell_type": "code",
"source": [
"# alpaca_prompt = Copied from above\n",
"FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n",
"inputs = tokenizer(\n",
"[\n",
" alpaca_prompt.format(\n",
" \"Continue the square sequence.\", # instruction\n",
" \"1, 4, 9, 16, 25\", # input\n",
" \"\", # output - leave this blank for generation!\n",
" )\n",
"], return_tensors = \"pt\").to(\"cuda\")\n",
"\n",
"from transformers import TextStreamer\n",
"text_streamer = TextStreamer(tokenizer)\n",
"_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)"
],
"metadata": {
"id": "V31sLCXXqPQ1",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "8b8d76b6-c5fc-41ae-9ee6-31dad0ae85c9"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n",
"\n",
"### Instruction:\n",
"Continue the square sequence.\n",
"\n",
"### Input:\n",
"1, 4, 9, 16, 25\n",
"\n",
"### Response:\n",
"36, 49, 64, 81, 100<|end_of_text|>\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model.save_pretrained(\"lora_model\") # Local saving\n",
"###model.push_to_hub(\"dreamthehacker/alpacafinetunedllama3\", token = HF_TOKEN ) # Online saving"
],
"metadata": {
"id": "EUqicb-bqPEq",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 98,
"referenced_widgets": [
"7a72fa9ded3e49c1acbc6d60226b323d",
"32f5c82da9574d63aa24c4dd54c2c270",
"74c04aaf28b54e7ba105a0448761d0a6",
"8e9c9a043e5c47138d3a693b62c981fd",
"95bed6a14a3d45059be27a3c72752f90",
"ae2617377c35450ea1ac65e9c4d5eb56",
"c529b0cf465641bbb7db997aa25c77ea",
"a1453ef5ff5d4a62abb94f5a65ac3db2",
"f896e55708504b308baac2ce3e3454c6",
"b8ddb7d6a92644c4ae8e6cad7fa73444",
"7f0859bec9d44d50937bc72aee90bca2",
"2ca1ca6e2b3941dd99f47ee391e3c9ef",
"777f181dc8fb4b0a83b323f1fb47ec90",
"a16363f7443043858b3481bae33678ab",
"4927889f52b84c9fb4b6ba58b537eecc",
"a36bcf46a8054bf2982ecf4fb1d9ffcc",
"d06952295d6f4d37a0b20f4a5bcda78e",
"fc99359a9c2c4d548a543468d96035a3",
"3f93010dfa5c4008ba98f9c36a10d704",
"ca0d9b3ea6684841a5e800cfe19bf259",
"ddd53f34b73f4ee3a7e04f1a0cf2f591",
"428ddee408ee435290521fceefe27367"
]
},
"outputId": "f1918e53-4f50-4be5-95be-1288424e51d6"
},
"execution_count": 16,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"README.md: 0%| | 0.00/581 [00:00Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nWhat is a famous tall tower in Canada?\\n\\n### Input:\\n\\n\\n### Response:\\nOne of the most famous tall towers in Canada is the CN Tower in Toronto. Standing at a height of 553.33 meters (1,815.4 feet), it is the tallest free-standing structure in the Western Hemisphere and the 9th-tallest in the world. The tower was completed in 1976']"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 141
},
"id": "SBSvXue6GKlQ",
"outputId": "420c151e-f5d9-4c7c-c70d-ccf37c06d5ef"
},
"execution_count": 21,
"outputs": [
{
"output_type": "error",
"ename": "NameError",
"evalue": "name 'captured_output' is not defined",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m