{ "cells": [ { "cell_type": "markdown", "id": "d80bea45", "metadata": { "id": "d80bea45" }, "source": [ "# CoT Data Generation and SFT Qwen With Unsloth" ] }, { "cell_type": "markdown", "id": "Df83ecULZgqM", "metadata": { "id": "Df83ecULZgqM" }, "source": [ "To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n", "
Step | \n", "Training Loss | \n", "
---|---|
1 | \n", "0.747600 | \n", "
2 | \n", "0.803200 | \n", "
3 | \n", "0.729800 | \n", "
4 | \n", "0.752100 | \n", "
5 | \n", "0.690500 | \n", "
6 | \n", "0.532300 | \n", "
7 | \n", "0.565500 | \n", "
8 | \n", "0.421100 | \n", "
9 | \n", "0.398400 | \n", "
10 | \n", "0.378300 | \n", "
11 | \n", "0.322400 | \n", "
12 | \n", "0.267700 | \n", "
13 | \n", "0.225400 | \n", "
14 | \n", "0.221800 | \n", "
15 | \n", "0.165200 | \n", "
16 | \n", "0.167600 | \n", "
17 | \n", "0.135000 | \n", "
18 | \n", "0.131100 | \n", "
19 | \n", "0.105400 | \n", "
20 | \n", "0.116300 | \n", "
21 | \n", "0.081000 | \n", "
22 | \n", "0.095600 | \n", "
23 | \n", "0.082300 | \n", "
24 | \n", "0.041800 | \n", "
25 | \n", "0.044300 | \n", "
26 | \n", "0.069300 | \n", "
27 | \n", "0.035900 | \n", "
28 | \n", "0.056600 | \n", "
29 | \n", "0.040600 | \n", "
30 | \n", "0.029200 | \n", "
31 | \n", "0.036600 | \n", "
32 | \n", "0.019900 | \n", "
33 | \n", "0.027400 | \n", "
34 | \n", "0.020000 | \n", "
35 | \n", "0.023700 | \n", "
36 | \n", "0.017500 | \n", "
37 | \n", "0.013100 | \n", "
38 | \n", "0.026700 | \n", "
39 | \n", "0.017100 | \n", "
40 | \n", "0.012900 | \n", "
41 | \n", "0.011200 | \n", "
42 | \n", "0.015800 | \n", "
43 | \n", "0.011500 | \n", "
44 | \n", "0.010600 | \n", "
45 | \n", "0.009600 | \n", "
46 | \n", "0.008800 | \n", "
47 | \n", "0.009400 | \n", "
48 | \n", "0.007300 | \n", "
49 | \n", "0.008300 | \n", "
50 | \n", "0.007600 | \n", "
51 | \n", "0.008300 | \n", "
52 | \n", "0.005800 | \n", "
53 | \n", "0.007400 | \n", "
54 | \n", "0.006100 | \n", "
55 | \n", "0.007500 | \n", "
56 | \n", "0.005300 | \n", "
57 | \n", "0.005800 | \n", "
58 | \n", "0.008200 | \n", "
59 | \n", "0.007300 | \n", "
60 | \n", "0.005300 | \n", "
"
],
"text/plain": [
"\n",
"
\n",
" \n",
"⭐ Star us on Github , join our [*Discord*](https://discord.camel-ai.org) or follow our [*X*](https://x.com/camelaiorg) ⭐\n",
"